Abstract
With the development of intelligent manufacturing and computer science, the system of equipment in the workshop has become more and more complex. In the intricate environment, the state of device changes constantly, which could affect the accuracy of methods since they cannot adapt the changing context. Recently, Digital Twin (DT) has received great focus among academic world and industrial world, which provides a new normal form for solving problems. In this paper, the structure of DT is discussed and a DT and Stacked Auto Encoder (SAE) Based Model is proposed to monitor the product quality. Based on the classical structure of DT, the digital model of DT is further divided into two parts, a task-achieved part and a self-update part. The former that comprises an encoder network that is a part of SAE and an Artificial Neural Network (ANN)-based classifier could check whether products are qualified. And a decoder network, another part of SAE, and a parameters-update rule make up the self-update part that could detect the accuracy of the task-achieved part and retrain the neural networks as the accuracy is poor. Furthermore, a new loss function is put forward as a training criterion in order to magnify the tiny difference between input data and result. In order to emulate the changing environment, the experimental data are collected at two different points in time. The data are then input to the proposed model and two other traditional methods to test the ability of accuracy and the adaptability for changing context. The comparisons show that the proposed method has got improvements, especially in where the effect of working environment is significant.
Highlights
As the process of globalization continues to accelerate and the concept of intelligent manufacturing increases, the business environment pushes the manufacturing industry to improve its product quality [1]
The digital model is composed by a task-achieved part and a self-update part. The former is made up by a encoder network which is a part of Stacked Auto Encoder (SAE) and used to reduce the data dimension and an Artificial Neural Network (ANN) used to classify the production quality; the latter comprises a decoder network and a parameters-update rule that can update the parameters of the model, including the encoder network, the decoder network, and the classifier, once the reconstruction error of SAE is too large over a certain period
The SAE model and the ANN-based classifier will be retrained by data that contain those used to train models before and the new collected data stored in the Digital Twin (DT) data
Summary
As the process of globalization continues to accelerate and the concept of intelligent manufacturing increases, the business environment pushes the manufacturing industry to improve its product quality [1]. The accuracy of the data-driven model would not be maintained for a long term, because of the factors. The DT promotes the digitalization in industry and provides a new path to solve problems in data-driven methods [14]. With the help of features of Digital Twin (DT), this paper combines DT and Stacked Auto Encoder (SAE) to propose a DT and SAE Based Model (DSBM) for products quality detection. Comparing to using only a data-driven method, the method this paper proposed has an ability to update parameters through calculating the trend of the stored historical data, which could be suitable well with the data disturbed by the work environment. A case study is presented to validate the proposed DSBM method has better accuracy than traditional data-driven methods without DT model under the changing work environment.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.