1 April 2021 in Journal of Cleaner Production
1 January 2020 in Journal of Algorithms & Computational Technology
With the wide application of intelligent sensors and internet of things (IoT) in the smart job shop, a large number of real-time production data is collected. Accurate analysis of the collected data can help producers to make effective decisions. Compared with the traditional data processing methods, artificial intelligence, as the main big data analysis method, is more and more applied to the manufacturing industry. However, the ability of different AI models to process real-time data of smart job shop production is also different. Based on this, a real-time big data processing method for the job shop production process based on Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) is proposed. This method uses the historical production data extracted by the IoT job shop as the original data set, and after data preprocessing, uses the LSTM and GRU model to train and predict the real-time data of the job shop. Through the description and implementation of the model, it is compared with KNN, DT and traditional neural network model. The results show that in the real-time big data processing of production process, the performance of the LSTM and GRU models is superior to the traditional neural network, K nearest neighbor (KNN), decision tree (DT). When the performance is similar to LSTM, the training time of GRU is much lower than LSTM model.
30 September 2021 in Advances in Mechanical Engineering
Industry 4.0 describes the future production of workpiece in job shop as: the workpiece is a smart one; it knows the details of how to manufacture itself; and it can communicate with manufacturing environment to support its own machining processes. This means that the production of workpiece places more emphasis on the smart realization of the process level in Industry 4.0. However, how to implement the production scenario based on existing technologies has not yet been well studied. On account of this, this article aims to study how to use existing technologies in job shop such as digital twins, Internet of Things (IoT), Cyber-physical Production System (CPPS), etc., to realize the workpiece-driven process-level production. The process-level production of a workpiece is divided into three stages according to the different manufacturing resources involved. On this basis, the production of the workpiece in digital twin job shop is divided into process level, operation level, and IoT/sensor level. Firstly, the manufacturing requirements at process level are generated according to production planning and process sheet. And these requirements are written into RFID tag of the workpiece. The workpiece dynamically interacts with different workstations via RFID reader/antenna in order to complete the manufacturing requirements. Secondly, based on the tag data, the interaction model of operation level, and IoT/sensor level CPPSs is given. Thirdly, at IoT/sensor level, the RFID devices are treated as a CPPS to track the manufacturing resources. And different smart sensors are used as independent sensor CPPSs to monitor the running status of machine tool. The RFID and sensor CPPSs are triggered by operation level CPPSs. Finally, a digital twin job shop is taken as an example to illustrate the feasibility of the proposed models and methods.
3 July 2020 in Science Progress
To find the optimal one from all feasible module configuration schemes of high-end computer numerical control machine tools according to performance, cost, and delivery, this article studies the method of module configuration optimization. An ideal outranking cardinal point based on the module configuration optimization approach of vertical computer numerical control honing machine is proposed in this article. First, it establishes the multi-objective decision model of the module configuration optimization according to performance indicator function, cost indicator function, and delivery indicator function. Second, the feasible configuration schemes, which are obtained based on customer requirements, are transformed into the data matrix of decision attributes. Third, ideal outranking cardinal point is used to calculate the multi-objective decision model of the module configuration optimization. According to the comprehensive distance between the feasible configuration schemes and the ideal outranking cardinal point, and the inverse ideal outranking cardinal point, the optimal configuration scheme is selected. The feasibility and universality of the proposed approach is verified by a module configuration optimization case of vertical computer numerical control honing machine.