Skip to main content
European Commission logo print header

Advanced decision support system for chemical/petrochemical manufacturing processes

Deliverables

The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Toolbox "Fault diagnosis using information systems and fuzzy reasoning" primary task is real time assessment of residuals and isolation of faults in industrial processes. "Fault diagnosis using information systems and fuzzy reasoning" TB (toolbox) is suited for fault isolation in instrumentation, actuators and process components. This toolbox is particularly suited to be applied in the continuous processes such as in: chemical, petrochemical, pharmaceutical, food, power, metallurgical, and thermal industries. Algorithms applied in the toolbox are especially valuable for large-scale systems, when huge sets of residuals and faults have to be considered. The fault isolation process is based on analysis of the detected symptoms set in respect to the relation between faults and symptoms defined by experts during TB configuration. The fault symptoms are calculated by assessment of residuals generated by other decision support system modules. The fault isolation procedure generates a diagnosis that points out a set of faults weighted by the faults’ certainty factors. Such a diagnosis more precisely specifies the system malfunction, comparing for example to the sequences of alarms generated by SCADA or DCS systems. Fast and precise diagnosis increases the process safety, decreases the pollution hazard and lowers the economical losses. Fuzzy logic is applied for residual assessment and diagnostic reasoning, which makes possible, among others, to produce the uncertainty degrees of symptoms. Also, knowledge of symptoms’ dynamics may be fed optionally to the toolbox. This increases the fault isolability, protects against incorrect diagnosis, and makes the FDI process more robust. The toolbox is divided into on-line calculation module and off-line configuration module. TB works under MS Windows 2000/XP. Residuals, inputs to on-line module, can be calculated by "Process modelling using fuzzy logic and neural networks for fault detection" toolbox. Toolboxes "Process modelling using fuzzy logic and neural networks for fault detection" and "Fault diagnosis using information systems and fuzzy reasoning" cooperate with each other in AMandD – Advance Monitoring and Diagnostic System. The preliminary tests of the "Fault diagnosis using information systems and fuzzy reasoning" were conducted on: IDR Urea Synthesis Section of Urea Manufacturing Process in Nitrogen Factory "Pulawy" SA, Steam Generator Laboratory Stand in LAIL Universite Des Sciences et Technologies de Lille, Laboratory Stand for Diagnostic of Industrial Process at Warsaw University of Technology. Procedures delivered in the software can help user to monitor and diagnose the state of his system. Its application can potentially bring following benefits: - Reduction of costs caused by abnormal states of process; - Increasing process safety; - Reduction of environmental hazard; - Increase comfort of working for plant operators by reduction the number of alarms; - Decrease costs of planned repairs.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The “Temporal bounds generation” is a fault detection system the objective of the toolbox is to detect internal faults in dynamic processes. The methodology is based on analytical redundancy: the behaviour of the real process and the behaviour of a model of the process are compared. When the behaviour of a variable is abnormal, an internal fault is detected and an alarm is launched. The uncertainty of the process, either on parameters’ values or on measurements, is expressed by means of interval values. This toolbox requires a discrete-time interval model of the process and interval measurements of the process variables. The behaviour of the model of the process is obtained by simulation, reformulating the simulation problem as a problem of computation of the range of a function in a parameter space. This problem is solved by means of global optimisation methods based on interval computations, so it is a semi-qualitative approach. The simulation propagates the intervals and obtains envelopes. The method is also based on multiple sliding time windows, i.e. it uses several time horizons simultaneously. If the process is complex, the model is divided in sub models and each one is dealt with independently.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The aim of this toolbox ('Scheduling and planning procedure under multiobjective criteria') is to provide the basic optimisation algorithms, the management of the objective function and the coordination between the different optimisation modules. Three optimisation techniques will be provided: simulated annealing (SA), mixed stochastic enumerative search (MSES) and genetic algorithms (GA). Simulated annealing is an evolutionary optimisation technique that allows the improvement of an initial schedule generated using simple heuristic rules (like EDD earliest due-date). The SA algorithm improves the initial point exploring a defined neighbourhood trying to improve a configurable objective function. Mixed stochastic enumerative search is an improvement of the SA mixing concepts given by the tabu search. The neighbourhood is explored but the explored points are inserted in a tabu list. The idea is that in this way the local optima are detected so and automatic change to another point of the space of solutions could be generated. The genetic algorithms optimisation technique starts with a population of initial schedules and evolve it using crossover and mutation operators. At The end of the evolving process only the best individuals (those schedules with the best objective function) will be available. All the optimisation algorithms need the evaluation of performance index. Therefore this toolbox also provides and objective function manager and evaluator, which allow the configuration of, customised objective functions.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The dynamic behaviour of a typical industrial process comprises a large number of concurrent phenomena. Typical dynamic process phenomena include gradual performance degradation (due to, e.g. fouling), stationary fluctuation (due to, e.g. resonating control loops) and sporadic changes (due to, e.g. vessel overflows). These phenomena have different time scales, and should be analysed separately. However, they are superimposed on top of each other in the time series measured from the process. 'Decomposition of process trends' toolbox provides functionality for extracting relevant features from the measured process trends. The toolbox is rapidly tailored for the needs of the plant. The toolbox has been used, e.g., to detect filter blocking in an industrial gas-cleaning tower.
These deliverable covers the Detailed Design and the software modules developed for the Integration Platform. The design and development of the Integration platform is the principal deliverable of WP10. The detailed design provides in depth description of the structure, functions and interfaces of each of the Integration Platform’s components. It constitutes the reference documentation that toolbox developers will use to develop their software. The Integration Platform consists of a set of software modules built using Java and Gensym's G2 (Trademark) that provide communication, data management, configuration, coordination and UI functionality. It is a very flexible generic platform that integrates industry standards and proven technology such as XML and message oriented middleware. To enable this flexibility, a loosely coupled approach is being adopted using messages rather than a tightly coupled approach, which would put increased responsibility on individual toolboxes. Since toolboxes vary in their design and language, the integration platform must be able to accommodate these differences by providing common interfaces and functionality that toolboxes can use with a minimum of adaptation. The platform also masks the differences between different toolboxes.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. This software ("Fault diagnosis and abnormal situation management using neuro-fuzzy reasoning") is a tool for alarm generation and decision-making support. It acquires expert knowledge from the operator in a visual and intuitive manner and by writing if-then rules. It has also the capability to automatically adapt to process changes in order to avoid false alarms allowing in addition fast and reliable fault detection and diagnosis. Information coming from a Hazard and Operability analysis (HAZOP) is used to provide operators support in case of alarms. In addition, the use of artificial neural networks allows the utilisation of available data (i.e. process variables data or data pre-processed by other CHEM software) to realise a classification or a clustering of the plant states and to realize process models. This capability can be used to perform fault diagnosis, as well as to generate symptoms for a further diagnosis stage. The main objective is to avoid plant shutdowns. Furthermore, early diagnosis can reduce the loss of productivity during an abnormal event if it is performed when the plant is still operating in a controllable region. The on-line connection of this toolbox with the real process, as well as the integration with other toolbox/es of the CHEM project allows the implementation of real-time on-line fault diagnosis. The FDS includes the identification of the root causes of process upsets (fault diagnosis) and can provide recommended corrective actions to restore the process to normal operating condition (fault correction). In this regard, real-time appropriate actions must be taken in present chemical and petrochemical manufacturing. The complexity of process control in present batch chemical plants affects the execution of the supervision tasks making it very difficult. This support is also necessary at the upper levels in the decision-making system as is the planning and scheduling level. Due to its inherent flexibility, batch plants can operate efficiently under different scenarios if the consequences of abnormal situations can be anticipated. This robust Fault Diagnosis System (FDS), that timely provides the fault information to the scheduling level, allows improving the efficiency of the reactive scheduling, to update the schedules in the most effective way.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Plant Knowledge and Advice System (PlantKAS) is based on two CHEM toolboxes (TB7.3 and TB7.4). Originally TB7.3 was called "Plant reliability and safety knowledge management system" and TB7.4 "Plant operator advice system for abnormal situations". In practise these toolboxes are developed as an integrated system, the 'Plant Knowledge and Advice System'. TB7.3&7.4 (PlantKAS) collects and applies safety and reliability knowledge related to a process plant. As a result of reliability and safety analyses of a plant, knowledge on the causes and consequences of failures and disturbances of the process is identified. The challenge is to utilise such knowledge when the identified abnormal situations appear. PlantKAS supports the storage and processing of unstructured knowledge about abnormal situations so that the system allows user to have situation-based advice when it is really needed. By utilising safety and reliability analyses, knowledge about abnormal situations is collected by mill personnel together with VTT's experts. The gathered knowledge is stored in a database as ASM advice in various forms. An applicability profile, defined as a combination of the measurements and the process state, is attached to every piece of ASM advice. The advice is assumed to be relevant when its applicability profile matches the current state of the process. PlantKAS supports operators in decision-making by indicating the relevant portions of ASM advice and giving easy access to the advice. The ASM advice can be in the form of, e.g. a HAZOP deviation with its causes and consequences presented as event graphs created from a safety and reliability analysis, or a link to a document describing the process state and how to manage the abnormal situation. Another function of the system is to collect operating experience data to complement or revise the contents of database. The system is to be used during plant operation and access to real time measurements and the process state is required.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Modelling is the first step needed for the solution of a production scheduling problem. As the problem has a high degree of complexity, the final result of this toolbox ('Flexible modelling framework structure based on EON') will be a modelling system capable to deal with the following aspects: - Discontinuous (batch), continuous processes and a hybrid combination of both. - Complex time relationships between operations. - Complex transfer rules, and intermediate storage policies. - Calendar and resource availability aspects. The approach chosen is based on EON (event operation networks). The resultant module is provided with the following functionalities: - Automatic generation of EON structures from information contained in ISA S88 like structure. The EON generated should include all the additional information related with the storage constraints and the resource constraints. - Solving of the EON structure generated using fast EON solving algorithm. - Writing of the solution in the ISA S88 like data structure. - Interaction with the user using an EGC (Electronic Gantt Chart) module. Using the EGC module the user can modify manually the different constraints applied to the problem as well as perform sequence and assignment changes. Every change modifies the associated EON that is automatically recalculated and the results of the changes are shown in the EGC.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The goal of this toolbox is to provide a G2 based environment that allows the user to introduce site-specific rules for building and optimising a schedule. The system will provide a set of pre-defined rules and actions that could be graphically combined in order to generate specific algorithms. Once generated, the new algorithms could be used in the integrated environment to generate an optimal schedule according to the specific procedures and constraints of the site. The system should be capable to evaluate predefined parameters (such as makespan, ending times of all the units, time used of each unit, etc) and configured parameters of partial schedules. It also provides functions used in the creation of a new schedule (create a batch, change the unit assignment of one task, etc). The ordered combination of evaluation of parameters and functions allows the creation of a new site-specific rules (rapid prototyping).
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The toolbox ”Qualitative situation assessment”, basically will allow the determination and recognition of qualitative and semi-qualitative user-defined process situations or states from on-line quantitative measurements and/or qualitative interpretations of process variables. The toolbox is based on a self-learning classifying technique called LAMDA (which relies on the generalizing power of Fuzzy Logic and the interpolation capability of logical hybrid connectives). The special nature of LAMDA’s algorithms enables it to cope simultaneously with numerical and qualitative information. Consequently, LAMDA clearly outperforms many other classifying techniques that have to transform qualitative inputs into binary codes. The classification algorithms based on the hybrid connectives are closely related to the neural networks operation. However, LAMDA’s explanation capabilities makes it a much more useful tool than neural networks when it comes to analysing the obtained outputs. The scope of the toolbox is divided into two main stages. An off-line stage concerning the design and construction of a classification system, from a set of experimental data. The second stage will be an on-line stage, where the use of this classification system will determine the present functional state of the process.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The objective of "System reconfigurability analysis" Toolbox is to suggest recovery decisions in case of fault occurrences in order to allow continuing the production in a degraded mode. These advices can be new remedial operations or operation directives. They are displayed to the operators on a graphical user interface or they are sent to other toolboxes such as "State transition support" toolbox. The toolbox consists of two parts. The first part is a model builder that enables a designer to produce a functional model of the plant. It works off-line. The second part of the toolbox is used on-line. It is a reconfiguration possibility analyser based on artificial intelligence techniques. It analyses the faults that it has received and provides recovery decisions as outputs.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Typical industrial processes have several discrete operating states. These states can be defined by, e.g. the raw material used or the end product produced. In a paper machine, the most important discrete operating states are the paper grades produced. Speeding up the grade changes can significantly increase the production efficiency of a paper machine. This toolbox ('Benchmarking changes in the process operating state') provides functionality for analysing and benchmarking changes in the operating state of a process. Benchmarking is based on keeping a record of state changes. Values of various performance indices from each state change are stored in a database. When analysing a new state change, the corresponding changes (i.e., all changes from state A to state B) are searched for, and used as reference material in the analysis. The changes are analysed to determine how the multiple goals, such as speed and safety, have been reached in a particular state change. Multiple corresponding changes are analysed to determine the bottlenecks, which should be addressed when speeding up the changes. The toolbox is being marketed under the name KCL-GraPPa (the Grade Change Performance Package by KCL).
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. "Process modelling using fuzzy logic and neural networks for fault detection" toolbox is the software package intended to identify, verify and simulate models of process variables. This toolbox's primary tasks are real time process variables reconstruction (virtual sensors, software redundancy) and generation of residuals for fault detection purposes in industrial processes. It provides easy to use and friendly environment for identification of linear, fuzzy and neural models. Identification is carried out by means of historical process data obtained from SCADA and/or DCS systems. The toolbox is divided into on-line and off-line parts. Fuzzy and neural process models are created in the off-line part. In the "Process modelling using fuzzy logic and neural networks for fault detection" on-line part, residuals are yielded based on models provided by the off-line part of the toolbox. Residuals are generated as differences of models’ outputs and process values. This toolbox is particularly applicable in the continuous processes such as in: chemical, petrochemical, pharmaceutical, food, power, metallurgical, and thermal industries. It works under MS Windows 2000/XP. "Process modelling using fuzzy logic and neural networks for fault detection" and "Fault diagnosis using information systems and fuzzy reasoning" toolbox cooperate with each other in AMandD – Advance Monitoring and Diagnostic System. The preliminary tests of the "Process modelling using fuzzy logic and neural networks for fault detection" were conducted on: IDR Urea Synthesis Section of Urea Manufacturing Process in Nitrogen Factory "Pulawy" SA, Steam Generator Laboratory Stand in LAIL Universite Des Sciences et Technologies de Lille, Laboratory Stand for Diagnostic of Industrial Process at Warsaw University of Technology.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. This toolbox "Fault diagnosis and alarm management using causal graphs" consists in the localisation of faulty components using a causal graph (see Toolbox "Alarm generation") and Artificial Intelligence techniques. First, a hitting set algorithm is used to determine sets of suspected components. Then, knowledge based modules containing human operator knowledge and dedicated to each suspected components are used to identify the faults and to generate messages to the operator indicating the faults and the actions that must be undertaken.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Users of "Functional model builder for qualitative and structural analysis" toolbox can input the architectural model of their plant (Process and Instrumentation Diagram) by interconnecting components from a generic plant item database. The primary objectives are to create this database and to provide graphical means to utilise them and derive complex symbolic mathematical relations automatically. Deliverables: - Generic Plant Item Database (incorporates physical characteristics); - Interface to create graphical models using the database and syntactical validation; - Means to derive behavioural models (for simulation); - Interface to derive fault indicators to be tested in real time; - Interface to derive structural fault detection and isolation ability from above results. The project aims at creating an integrated interface to easily create models for plants and derive fault diagnostics specific results from it in symbolic equation forms. It also aims at providing means for the validation of these results through offline simulations and exporting the results for on-line implementation by other toolboxes. All these are implemented in a single integrated development environment and significantly reduce the time and cost of modelling and manual derivation of equations.
The methodology is described in a document D1.4 that indicates how to integrate several toolboxes (TB) in CHEM architecture and how to create supervision applications on new processes. It contains an activity model indicating the interactions between toolboxes, the description of the operations to be handled and constraints to be respected for adding a new toolbox to CHEM architecture, the description of the toolboxes developed in the project. This description includes several aspects: functions supported by a TB, its interfaces and parameters, the information it provides, a user Manual in a functional point of view, examples of application.
A prototype of the user interface of situation-based instructions was developed and integrated to metsoDNA control system. The goal was to provide an operator with instructions which are focused to the situation and in that way make the decision making process in disturbance situations more simple than with traditional instructions. The userinterface prototype was built on VTT's toolboxes 7.3. and 7.4. and was integrated to metsoDNA control system. The purpose of the research was to study the utility and the usability of this new tool. Many new possibilities for utilization and hints to improve the usability were found. Based on this prototype concept Metso Automation aims at developing and integrating new knowledge management products into metsoDNA process control system. The new products complete the metsoDNA Knowledge Management Activity that now includes e.g. DNAdiary and functional descriptions (loop based guides).
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. An application has been developed to predict process instability on a blast furnace based on wall pressure trends and gas analysis. The objective is to give sufficient warning to enable remedial action to be taken to reduce the extent of the instability. Several combinations of toolboxes have been used. Combinations of Toolboxes: - Toolbox "Performance and quality management based on MSPC" (iMPSC) is used alone to combine the signals described above. The bi-variate trend is assessed using contribution analysis so that if the action limit is exceeded, an alarm message is generated when a certain number of parameters have been identified as experiencing the greatest change. - Toolbox "Qualitative representation of process trends" (Qualtrend) with "Qualitative situation assessment" (Salsa) to generate episodes using 4 individual signals from the process. The 4 sets of episodes are classified to either normal, pre-fault or fault. - Toolbox "Performance and quality management based on MSPC" (iMSPC)is used with "Qualitative representation of process trends" (Qualtras). Episodes are generated from the first two principal components. Heuristic rules have been developed to analyse the sequence of episodes generated from both principal components. An alarm is generated when certain sequences of episodes are detected. These rules are written in G2. - Toolbox "Performance and quality management based on MSPC" (iMPSC) is used with "Qualitative situation assessment" (Salsa). Salsa continually classifies the combination of outputs from "Performance and quality management based on MSPC". It was not found to be worthwhile to classify episodes generated from the outputs of "Performance and quality management based on MSPC". Results: It was found that from the 22 days test period analysed almost all of the major unstable events could be predicted using either "Performance and quality management based on MSPC" alone (a) or "Performance and quality management based on MSPC" with "Qualitative representation of process trends" plus G2 rules (c). Application of a simple enabler, based on heat flux trend(heat loss through the furnace wall to the cooling water), was required to remove false alarms generated by "Performance and quality management based on MSPC", "Qualitative representation of process trends" plus rules. This did not remove any of the valid alarms. On line evaluation of the packages which include Salsa is continuing. The off line version suggests that the classification of episodes produced by "Qualitative representation of process trends" from raw signals is more robust than the classification of outputs from "Performance and quality management based on MSPC" in that fewer false alarms are generated. However, not every event was predicted. The anticipated benefits, once the advice from these techniques has been released to operators, is to give better advice on when the production rate needs to be slightly reduced. This will reduce the extent of instability and so cause less stress to the furnace. The package as tuned is applicable only to this particular plant, but it could be adapted to other blast furnaces which have appropriate stack pressure measurement available.
The aim of this result is to present how the global software has been applied to a FCC (Fluid Catalytic Cracking) pilot plant. It will integrate at least toolboxes TB3.4 & TB5.4 and presents how to get the FCC causal model required for the diagnosis. It will also show how others toolboxes can complement TB3.4 & TB5.4. This application could be "derived" for a FCC industrial plant. At present time, this document is not written.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. Toolbox "Performance and quality management based on MSPC" is a comprehensive implementation of the theory of Multivariate Statistical Process Control (MSPC). MSPC extends standard SPC by taking into account the simultaneous variation of many process variables. The process variables are mapped to a smaller number of orthogonal latent variables, that capture the essential variability of the original data set in a more compact and more easily comprehendible way (for operators and process engineers). The Toolkit contains all standard functions in MSPC theory, such as PCA (Principal Component Analysis), PLS (Projection to Latent Structures), etc. Generation of MSPC models from raw data, as well as on-line calculation of relevant statistical metrics are supported. APIs are defined for full access of all MSPC functions from G2, hence allowing further processing and reasoning on statistical results. The MSPC modules are embedded in a framework for on-line analysis that emulates sophisticated expert reasoning on the results of the MSPC calculations. The aim is to enable early detection and prevention of performance and quality problems. "Performance and quality management based on MSPC” is on line at Redcar Blast Furnace to predict aerodynamic instability using a PCA model. The PC's are used to generate a stability index used for both long-term analysis, and to give a minute by minute indication of process stability. Automatic contribution analysis indicates which parameters have changed significantly when the bi-variate or PC trend is outside its warning limits. The calculated values are fed into toolbox "Qualitative representation of process trends" and are being assessed for "Qualitative situation assessment". Further results from "Qualitative representation of process trends" are being assessed. This toolbox is also used to run PLS prediction models for hot metal quality at Redcar Blast Furnace, and for liquor quality from a distillation column at Dawes Lane Coke Ovens, Scunthorpe.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The toolbox “Qualitative representation of process trends variables” has the objective of converting numeric signals into qualitative representations. The developed tool obtains information from directly measured, pre-processed or estimated process variables and is capable of deriving and showing the qualitative process perception that expert operators could have (e.g. “the pressure dropped abruptly”). Trends of numeric variables are symbolically represented by means of qualitative descriptions of signals composed by episodes that characterise a constant state over a specific time interval with constant signal behaviour. It allows a compact representation of process variables from the temporal point of view (periods of time with constant behaviour) and from the point of view of signal behaviour (qualitative description). The trends representation in episodes can be used for monitoring, as additional simplified information for operators and as a pre-processing tool for detection and fault diagnosis. The toolbox is delivered as a software library in G2 that can be used to build customized applications in an easy way. It can be configured in a way that only the interesting characteristics of the signal behaviour, from the expert operator point of view, are used to obtain its description. The representation of a variable can be obtained off-line (from a recorded signal, useful in order to choose the configuration parameters or to analyse past situations), or on-line, generating episodes when significant changes occur. A representation is obtained for each variable; but it is possible to obtain representations of several variables at the same time.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The scheduling systems should be able to acquire and process the data provided online by the real process in the plant. Such information must be evaluated and taken into account in order to re-schedule. This toolbox provides all the data structures required in the scheduling system, including functions as persistence and communication. The persistence function will be carried out using a SQL database whilst the communication function will be carried out by means of XML message structures and XML-RPC calls. ISA S88 information hierarchy will be used as a representation of the information needed in the scheduling system. The use of the ISA S88 standard allows and easy communication with the control systems and easier integration with other systems that use the same standard for their information repositories. The use of the ISA S88 structure allows also the use of the same data model to store both control and scheduling information. The most detailed level of information can be used bye the control system whilst the less detailed and generic information will be used by the scheduling system. This last point assures the coherence between the scheduling and the control toolboxes.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. JGrafchart is toolbox for sequential, procedural, and state-oriented operations in the process industry. It may be used on both the direct control level and on supervisory levels. On the supervisory level it may be used for operator procedure handling, for recipe-based batch control, and as a workflow editor. JGrafchart is a graphical language based on the concepts of Sequential Function Charts (SFC) from IEC 61131-3. To this has been added features from Statecharts and concepts from text-based procedural and object-oriented programming languages. JGrafchart consists of an interactive graphical object editor where function charts and procedures are created and executed. JGrafchart supports communication with the external environments using TCP sockets and using XML-based message passing. JGrafchart is implemented in Java 1.4 and Swing. It runs on all platforms that support Sun Java.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The diagnosis of analog systems raises many specific difficulties, which justify the development of specific methods. This toolbox provides a fault detection and isolation procedure especially well adapted because no derivative approximation is required and imprecise data continuously varying over time are considered using temporal band sequences. Due to those particularities, no false alarms are ensured. Based on the Model-based diagnosis approach, results are deduced from the evaluation of residuals consistency and allow multiple faults isolation. The piecewise nature of the processed residuals allows to model many real-life systems, including models defined by diagrams. Intermediary states (brutal changes in the structure of the system, such as opening of valves) which are generally very badly known, can be described by very rough models without limiting the diagnostic power of the method since the evaluation process is based on integration and hence the contribution of intermediary states in the value of the residuals remain negligible. During past years, THALES Airborne Systems has developed research in the field of continuous dynamic systems aiming at the automation of analog circuits diagnosis. Last have been proved valuable for analog electronics circuits. From numerous discussions with the process community it is expected that these features can be of some value for the diagnosis of chemical processes.
The aim of the CHEM project was to develop and implement advanced Decision Support Systems (DSS) for process monitoring, data and event analysis, and operation support in industrial processes. The systems are synergistic integration of innovative software tools, which improve the safety, product quality and operation reliability as well as reduce the economic losses due to faulty states, mainly in refining, chemical and petrochemical processes. The CHEM applications consist of integrated sets of software toolboxes that provide robust detection and diagnosis of process problems in real-time. The systems assist operators in assessing process status and responding to abnormal events. The project provides a flexible architecture and a methodology in order to facilitate the development of such applications on many processes. The approach proposed in 'Scheduling and planning procedure under multiobjective criteria' toolbox is a practical one since the efforts are dedicated to help the user to explore, analyse and find a feasible solution better than any other they could expect within the limited period of time for the decision-making. However, the solution reached is not strictly the optimum in mathematical terms. This will arise from the rigorous solution of the global optimisation problem, which is an unaffordable task to attempt without a very good starting point. General purpose models, based on MILP and MINLP formulations, run out of proportion when trying to solve complex scheduling problems. Different algorithms (based on MILP formulations) have been reported for the optimal scheduling of multiproduct/ multipurpose batch plants. This toolbox will provide a new graph theoretical approach to efficiently solve the scheduling of multiproduct/multipurpose batch plants with intermediate storage. Specifically, a graph theoretical approach for solving multipurpose batch plants is applied. This representation has the advantage of exploiting the problem-specific knowledge from the very beginning to develop efficient algorithms. Therefore, the optimisation strategy appears as a symbiotic procedure that will take advantage of practical approach ('Scheduling and planning procedure under multiobjective criteria' toolbox) to feasible good solutions to build-up automatically good starting points for the rigorous solution of the problem. Hence, the graph-theoretic approach uses a practical good starting point to search for optimal solutions. Thus after the activation energy initially given by the user, the Optimisation Module will go readily towards the optimum.

Searching for OpenAIRE data...

There was an error trying to search data from OpenAIRE

No results available