Relevant:
Associated Results
In the RiaStone Qu4lity Pilot the ZDM-AQL is implemented in a modular architecture, which includes both in-factory data processing, Edge processing Systems, Cloud processing systems, and Machine Learning processing Services.
The RiaStone Qu4lity Pilot goal is to recognize, detect, and reconfigure the production process parameters as soon as a failure is detected in real-time.
This process is based in the collected data, advanced analytics, machine learning image inspection methods
The ambition is to create a modular monitoring and control system that can be used with many different sensors and process models. The models need to be adaptable to the actual task, for a specific geometry or dedicated material processing conditions. Real-time process and machine signals need to be analysed in by machine-learning algorithms to find structures and pattern related to the required key quality indicators (critical defects per track, distortion, keeping of dimensions).The system will be also connected to a higher-level factory data interface which allows to exchange process information and reassign the production strategy based on additional factory conditions.
Solutions, methodologies, and tools that are being developed within different work packages of QU4LITY are being applied to this pilot in the task T7.2 of WP7. As is shown in the figure, different components of the FAGOR platform such as FA-LINK, IKCLOUD+ and IKSEC+ are being extended focusing in ZDM of press machines. FA-LINK platform has been completed with the following components:
- ETL@FA-LINK is responsible to extract transform and load the data. Additionally to the sensor data, and with ZDM on mind, contextual data is also collected by the platform. This component prepares the data for the AI training process. This component is composed by an extended version of iKCloud that is being designed in WP3 and integrated in this pilot in WP7.
- Then, TRAIN@FA-LINK uses the previously obtained and persisted data to create an AI model for ZDM. The model is generated using cutting edge machine learning technologies. This model is used to identify situations and generate suggestions to the users to increase performance and reduce defectives of press machine. The model training is performed by the extension of ikCloud+ developed in WP3/WP7 work packages of QU4LITY.
- Next, the model is executed by EXECUTE@FA-LINK using the data obtained from the press machine. This way, ZDM related alarms, indicators and suggestions are obtained and persisted. This component uses FA-LINK and IK-Cloud+ solutions that are being implemented in WP3 and WP7.
- Finally, the obtained results are shown to the users using different views of FA-LINK. A set of new views focused on ZDM and quality are being implemented in the WP7 of QU4LITY in this pilot. These new views provide the ability to the platform to show, suggest and guide the user to improve press machine performance and reduce downtimes and defectives.
-
Results:
Process Data from Manufacturing Data Lake is analysed online for suspicious outliers. A Webinterface enables online intervention by staff.
Part of the improved decision process enabled by the holistic platrom can be close looped into machine control parametes, allowing an autonomous quality management at factory level
MONDRAGON pilot is being developed considering 2 IoT platfrom and interoperability layer developed by MGEP together with OPC-UA and AAS. Real time process optimisation enables Autonomous quality outcomes and Zero Defect Manufacturing for Automotve (Fagor Arrasate )and railway (Danobat) manufacturing lines. The FA-LINK platfrom monitored industrial assets for Fagor Arrasate and SAVVY IoT platfrom for DANOBAT.
The introduction of IA algorithms by ATLANTIS and VTT are developed offline achieving high top optimisation production. On the other hand, the approach of Machine Learning approach should be further developed. The interaction of the operators, maintenance workers and R&D staff are stil crucial for Top high level Autonomous Manufacturing process Optmisation
-
Results:
1. Augmented Reality is improving supporting processes Change over, Maintenance and Training. Partner PACE will apply their AR technology to avoid utilization of human resource in Maintenance documents handling. Instead Technologies like smart glasses and Holo lens will be applied. Virtual assistants will guide Maintenances staff through maintenance and repair processes instead. Same is targeted for Training.
2. Visualisation of machine and process data in realtime will enable immediate intervention in case of abnormal behaviour.
The acquired data is used in on-line prediction of defects. The predicted defects are used to adapt the visual quality inspection with an in-hand camera with a robot. The robot is guided to and between predetermined viewpoints associated with the predicted defects. The robot motion is generated autonomously on-line.
At a certain point of integration, the correlation between overall process parameters and the output product characteristics could be realized in real time in order to adjust, without any Human action, the different parameters along the production line.
This is the ideal towards which we wish to achieve with our future production lines.
The data acquired through computer vision, is processed through machine learning algorithms and compared to an existing database of ~10000+ images already noted by human operators
Inspection results are fed into the synesis-consortium machine control platform that decides necessary changes to the machine parameters driving production in both Business Processes (1&2)
Thanks to this new approach with modular adaptable signal processing system and a strong interaction with data space and simulation tools trough the platform, will be possible to detect anomaly and have anequipment condition reporting , reduce reject rate by application of data-driven process model that has been derived by AI algorithms, increase OEE by recommending process adjustments to the operator or directly change the parameters in real time, so to reduce also the operator costs.
The variables monitored in real time throght IoT platfroms for 2 manufacturing lines enables the Zero Defect Manufuactiring goal. Multiple industrial assets monitored force to have an strategic in terms of enchacement processes.
The implementation of modular architecture interconected involving Cloud and Edge Systems, Data Modelling and Learning Service and Iot Hub produce top quality production. The introduction of Interoperability layer for gathering data from two different manufacturing lines together with OPC-UA and AAS is key for the goal.