WELD-IT project -- Welding Process Planning and Parametric Pricing Software Solution for SMEs
When designing a joint, from an engineering point of view, many aspects have to be taken into account such as amount of load, nature of load, sheet thickness, material, welding technology, etc. But on the other hand, as an industrial process, the cost of welding plays a more crucial role in manufacturing decisions. Many different variables affect the total cost, including equipment cost, labour cost, material cost, and energy cost. Companies commonly employ or hire welding engineers exclusively for performing this task. Depending on the volume and complexity of the project, pricing process can last from hours to weeks, costing from few hundreds to tens of thousands Euros. Due to its inflexibility, it is clear that this method will become inappropriate in a short time and a highly computed method will be required in order to catch up with the even shorter product development cycles, the increasing demands and the tough competition. It will be highly important for SMEs in the welding industry to be able to have access to such type of innovation in order to keep on being competitive in front of large companies and big players in the sector. Because of the complex nature of welding and the several requirements set by customers, capabilities, legislation and competition, many parameters had to be taken into account during generating quoting and planning of welding projects. To support and speed up this process, a software tool that could interpret Computer Aided Design (CAD) models was required to assist welding engineers. The WELD-IT project has received funding from the European Union’s Seventh Framework Programme managed by REA-Research Executive Agency under grant agreement 262580. Seven participants (2 research organization and 5 Small and Medium Enterprises) worked on the realization of the project since 1st November 2010, each of them had its defined tasks in the work plan. The consortium members had identified the need for targeting the following objectives: - To develop a costing tool that helps welding experts and engineers in calculating the overall costs of complex welding projects and preparing quotes. - To develop a decision tool that helps companies realize their limitations in manufacturing capabilities in terms of technology, thus supporting investment decisions. - To develop a tool that manages the planning and execution of welding projects from a technological point of view taking into account major parameters like facilities, capabilities, resources and expertise of a company. During the development of the WELD-IT system a training set was collected by RTD partners both for the estimation of the technological parameters as well as for the project planning and timing. A set of Welding Procedure Specification (WPS) was investigated in-depth and the results were uploaded into a database which can be considered as the training set of the decision support system. The system contains approximately 160 WPSs described by 22 identified parameters taken from the defined input domain. In parallel a set of equipments and their corresponding properties have been extracted from databases of the project partners and were uploaded into a central database. This information was identified as a company inventory and was used for the pricing. Finally a set of different equipments and resources were introduced into the system, such as facilities, workshops, welding and moving equipments to support the process planning capability of the system. Conventional mathematical tools used for system modelling or system description were not suitable to handle uncertainties in situation like in WELD-IT therefore a system was needed which can deal with uncompleted input data. For this purpose a fuzzy inference system employing fuzzy “if-then” rules can model the qualitative aspects of human knowledge and reasoning processes without employing precise quantitative analyses. ANFIS (Adaptive Neuro-Fuzzy Inference System) is an adaptive network which is able to acquire knowledge by rules and membership functions examples. This can be considered as network of nodes and directional links. Associated with the network is a learning rule - for example back propagation. It is called adaptive because some, or all, of the nodes have parameters which affect the output of the node. The primary aim of these networks is to build stable relationships between inputs and outputs. Different “if-then” rules are activated by the input values through several processing layers. This means that the system is a multilayer system with defined nodes in each layer and well defined connection between the nodes. As ANFIS has three types of structures each was investigated and evaluated and based on the requirements Type 2 was identified as appropriate solution. The system consists of five plus two layers having two different node types in the architecture, where the circle nodes are fixed and is set up during the development of the system (such as rules and transformations) and there are square nodes as well, which represent data nodes with free parameters that have to be taught during the training of the system. These parameters have effect on the output of the node, such as multipliers for weighting, membership functions, etc. With regards to the papers and following the design directives of the ANFIS system the developed system looks like as it is depicted in Figure 6. For the proposed solution of the problem Type 2 had been chosen as it was capable to select a specific WPS based on the specified rules. As it can be clearly seen the system deviates in one point from the general way. The third layer was not implemented therefore it has no effect on the output as there was no overlapping in the Linguistic Variable list which means that the input parameters had no effect on each other. That was the reason why every “Linguistic Variable Node” had its related and own Product Node for calculation and that was why the result could be sent directly into the fourth layer. In all other details the system completely matches with the original AFNIS design As a result of the developed solution WELD-IT is more and more accurate as the more time is spent on using its functionalities as it is be able to store newly created elements as an element of the training set. The development of the ANFIS system was completed and validated and in parallel an intuitive Graphical User Interface was designed and developed with the involvement of the end-users of the system. As result of the integration of the two systems welding experts were supplied with an easy-to-use tool that speeded up the preparation of the costing of welding jobs. Due to the fact that the development phase has not been completed, the project obtained two more months for the conclusion and is going to terminate on the 31th of December. For more information please visit www.weldit.eu or contact the Coordinator of the project through weldit@mfkk.hu.
Países
Austria, Belgium, Bulgaria, Cyprus, Czechia, Germany, Denmark, Estonia, Greece, Spain, Finland, France, Hungary, Ireland, Italy, Lithuania, Luxembourg, Latvia, Malta, Netherlands, Poland, Portugal, Romania, Sweden, Slovenia, Slovakia, United Kingdom