Skip to main content

aGent Oriented Zero Defect Multi-stage mANufacturing

Periodic Reporting for period 2 - GO0D MAN (aGent Oriented Zero Defect Multi-stage mANufacturing)

Reporting period: 2018-04-01 to 2019-09-30

The main idea of GO0D MAN project is to integrate and combine process and quality control for a multi – stage manufacturing production into a distributed system architecture built on agent-based Cyber-Physical Systems and smart inspection tools. This framework, based on agents associated to each process and to each product, supports the real-time data collection and defect diagnosis at single process level, as well as the inter-stage sharing and processing of information at global level using data analytics techniques. The ZDM strategy proposed by the GO0D MAN project runs on this framework, at local and at global system level, and has been demonstrated in three relevant industrial cases with multi-stage production lines, having different levels of automation and production rate.
The objectives of GO0D MAN project were set to allow realization of a fully functional, replicable and therefore widely exploitable solution. The developed architecture contains all the technological pillars of the GO0D MAN project and shows their relations and roles at Operational and Information Technology levels and they are: Smart On-line Inspection Tools, the Multi Agent System, the ZDM Data Analytics and the ZDM Knowledge Management.
The proposed architecture and approach have been fully implemented and integrated in the three selected industrial cases, which were chosen in order to represent more than 80% of the manufacturing sector, namely: Volkswagen Autoeuropa which represents a typical modern assembly plant for semi-automated car mass production, at relatively high production rate; Zannini which represents a typical multi-stage production of components in batches ; Electrolux Professional which represents a mainly manual and customized type of production at slow production rate. In all the three plants the GO0D MAN project brought innovation at the levels of advanced instrumentation for in-line quality control, distributed IT architecture based on agents, data analytics software and knowledge management software. The demonstration phase of the project successfully validated the proposed architecture and its technological components.
At the end, the project demonstrated that the GO0D MAN concept is general and fully deployable in the different manufacturing contexts, bringing some important impacts. The results obtained have been very promising. Some lessons learned have been deducted and they will drive the future activities of the partners that are looking forward for a business take off for the majority of components developed.
This Innovation Actions primarily consists of activities directly aimed at producing and demonstrating improved manufacturing processes. For this purpose, it includes prototyping, testing and demonstration in an operational environment.
At the end of the GO0DMAN project all the Work Packages have been successfully completed and finalized.
The first 18 months of the project dealt with the development of the components of the GO0D MAN architecture, i.e. the on line smart quality control systems, the MAS CPS architecture, the data analytics environment and the knowledge management environment. As well the methodology for the ZDM strategy has been defined and the KPI for the different end users defined.
The second half of the project has been devoted to the integration of the developed components in the three different end user production lines and to the definition of the general integration approach. In particular, the final period has been devoted to the validation of the GO0D MAN approach in each of the end user manufacturing lines through the measurement of the KPIs in real operating conditions.
The results obtained have been very promising and it has been demonstrated that through the GO0D MAN architecture it is possible to increase the quality in a multi stage production and to decrease the costs of the production.
17 different exploitable items/components have been identified: 2 related to the general concept of the GO0D MAN concept as composite product, 5 related to the ZDM- Data analytics and Data Knowledge environments, 3 related to the multi agent layer and 7 related to the Smart Inspection Tools developed. In particular, 2 Smart Inspection Tools have been patented and further activities and contacts are going on to industrialize these tools, both internally to the consortium and with the support of third parties.
An Innovation Shop has been conceptualized, implemented, and deployed in forms of a web-based environment ( https://go0dman.boc-group.eu/innovationshop/ ) where all the innovative items have been collected and presented to a wider community of possible users.
The results of the GO0D MAN project have been largely disseminated and communicated to different audiences. Great efforts have been devoted to the connection with the other funded projects of the 4ZDM Cluster.
At present, worldwide manufacturing industry is very varied. In automated production lines, the state-of-art is to perform quality controls on the final product at the end of the production line on 100% of production, overcoming traditional Statistical Process Control (SPC). Furthermore, reliability tests are performed on statistical basis on production samples. At the same time all automated machines include sensors to monitor performance and run feedback control loops. In the meanwhile, simpler production environments continue to exist, where most operations are human-based including quality controls; a very limited numbers of sensors are used, hence data are lacking. Indeed, understanding and controlling the quality in complex multi-stage manufacturing systems goes beyond the capacity of the model driven approaches and requires the right quantity and quality of meaningful data, in order to extract relevant information and build-up useful knowledge. Therefore, the simplest production environments should evolve to acquire the minimum required amount of data while the advanced ones should optimize the use of the already available data for an effective implementation of Zero Defect Manufacturing (ZDM). Moreover, today, data coming from quality controls are not used in real-time for production process control and vice versa: they are usually processed together as vertical silos in a multistage process, mainly off-line at the level of SPC.
GO0D MAN addressed all this complexity through the deployment of a Zero Defects Manufacturing framework based on smart inspection tools, intelligent agents, an ICT infrastructure for data collection, transmission and mining and advanced data analysis tools.
The GO0D MAN architecture and its components have been successfully deployed and validated in three industrial production lines and the reached impacts are the following:
- Increasing of the number of quality control stations distributed in order to have a multi-stage production line with a decreased number of repaired products at the end of the production line.
- Reduction of production costs.
- Increased production flexibility.
- Reduction of waste and scrap
- Wide adoption of the new strategies in the existing manufacturing systems in particular related to data analysis and knowledge managements from local to global level.
For each use case, specific quantitative and qualitative KPIs have been computed and analysed, showing that benefits that can be obtained through the adoption of the ZDM concept and the deployment of the GO0D MAN architecture.
GO0DMAN Key Innovations
GO0DMAN Architecture