Along with the number and the functional complexity of machines increase in the intelligent manufacturing system, the probability of faults will increase, which may lead to huge economic losses. Traditional passive or regular maintenance methods of solving the faults have the problems of low efficiency and huge resource consumption. Besides, traditional maintenance methods mostly contain single model, so all the prognostics and maintenance tasks of the intelligent manufacturing system can hardly be addressed at the same time. Therefore, this paper proposes a novel predictive maintenance (PDM) method based on the improved deep adversarial learning (LSTM-GAN). The long-short-term memory (LSTM) network can solve the disadvantage of vanishing gradients and the mode collapse from the generative adversarial network (GAN). The method can not only avoid the mode collapse of GAN but also realize the self-detection of abnormal data. Meanwhile, the predictive maintenance model includes two prediction models and a maintenance decision model. The prediction models can predict the state of the machine and the fault of the machine in advance. Then the maintenance decision model will arrange maintenance personnel and offer a plan of maintenance. Finally, a case study about predictive maintenance using LSTM-GAN in the intelligent manufacturing system is presented. The fault prediction accuracy of LTSM-GAN is as high as 99.68%. With the comparison between LSTM-GAN and other traditional methods, LSTM-GAN shows priority both in accuracy and efficiency. Moreover, the proposed PDM can reduce maintenance costs and downtime so that the life of machines in the intelligent manufacturing system will extend.

Rapid advances of sensing and cloud technologies transform the manufacturing system into a data-rich environment and make production scheduling increasingly complex. Traditional offline scheduling methods are limited in the ability to handle low-volume-high-mix workorders with diverse design specifications. Simulation-based methods show the promise for distributed scheduling of manufacturing jobs but are mostly implemented with historical data and empirical rules in a static manner. Recently, artificial intelligence (AI) algorithms fuel increasing interests to solve dynamic scheduling problems in the manufacturing setting. However, it’s difficult to utilize high-dimensional data for production scheduling while considering multiple practical objectives for smart manufacturing (e.g., minimize the makespan, reduce production costs, balance workloads). Therefore, this paper presents a new AI scheduler with composite reward functions for data-driven dynamic scheduling of manufacturing jobs under uncertainty in a smart factory. Internet-enabled sensor networks are deployed in the smart factory to track real-time statuses of workorders, machines, and material handling systems. A novel manufacturing value network is developed to take high-dimensional data as the input and then learn the state-action values for real-time decision making. Based on reinforcement learning (RL), composite rewards help the AI scheduler learn efficiently to achieve multiple objectives for production scheduling in real time. The proposed methodology is evaluated and validated with experimental studies in a smart manufacturing setting. Experimental results show that the new AI scheduler not only improves the multi-objective performance metrics in the production scheduling problem but also effectively copes with unexpected events (e.g., urgent workorders, machine failures) in manufacturing systems.

In make-to-order manufacturing workshops, accurate prediction value of production progress (PP) is a significant reference index for dynamic optimisation of production process and on-time delivery of production orders. The implementation of big data and Industrial Internet of Things (IIoT) in manufacturing workshops makes it possible to obtain large amounts of production data which can affect PP. However, the particularities of massive historical order data are not fully excavated and the amount of target order data is insufficient to support the training of high-precision prediction model, which will result in bad training approximation and generalisation. To overcome these shortcomings, a PP prediction approach consisting of two models with transfer learning (TL) is proposed. TL can avoid the training of PP prediction model from scratch every time. Consequently, computational efficiency can be greatly improved. A convolutional neural network (CNN) model with TL is devised to excavate the comprehensive features from historical and current orders. Additionally, a long short-term memory network (LSTM) model with TL is constructed to fit the nonlinear relation of the features provided by CNN-TL model for PP prediction. In order to validate the performance of the proposed PP prediction approach, comparative experiments of eight algorithms are conducted in an IIoT-enabled manufacturing workshop.

Flexible job shop scheduling problem with combined processing constraint is a common scheduling problem in assembly manufacturing industry. However, traditional methods for classic flexible job shop scheduling problem (FJSP) cannot be directly applied. To address this problem, the concepts of ‘combined processing constraint’ and ‘virtual operation’ are studied and introduced to simplify and transform FJSP with combined processing constraint into FJSP. A Multi-agent system (MAS) for FJSP is used for fitting the requirement of building complex, flexible, robust and dynamic manufacturing scheduling. On this basis, a novel adaptive real-time scheduling method for MAS is further proposed for better adaptability and performance. This method solves the previously converted problem and conquers the shortcoming of poor performance of traditional single dispatching rule method in MAS. In this approach, the scheduling process is modeled as contextual bandit, so that each job agent can select the most suitable dispatching rules according to the environment state after learning to achieve scheduling optimization. The proposed method is compared with some common dispatching rules that have been widely used in MAS. Results illustrate the high performance of the proposed method in a simulated environment.

With increasingly stringent environmental regulations on emission standards, enterprises and investigators are looking for effective ways to decrease GHG emission from products. As an important method for reducing GHG emission of products, low-carbon product family design has attracted more and more attention. Existing research, related to low-carbon product family design, did not take into account remanufactured products. Nowadays, it is popular to launch remanufactured products for environmental benefit and meeting customer needs. On the one hand, the design of remanufactured products is influenced by product family design. On the other hand, the launch of remanufactured products may cannibalize the sale of new products. Thus, the design of remanufactured products should be considered together with the product family design for obtaining the maximum profit and reducing the GHG emission as soon as possible. The purpose of this paper is to present an optimization model to concurrently determine product family design, remanufactured products planning and remanufacturing parameters selection with consideration of the customer preference, the total profit of a company and the total GHG emission from production. A genetic algorithm is applied to solve the optimization problem. The proposed method can help decision-makers to simultaneously determine the design of a product family and remanufactured products with a better trade-off between profit and environmental impact. Finally, a case study is performed to demonstrate the effectiveness of the presented approach.

The cloud manufacturing system can provide consumers with on-demand manufacturing services, which significantly improve the utilization rate of distributed manufacturing resources and the response speed of personalized product needs. In the cloud manufacturing platform, the successful implementation of various industrial applications relies on the uploading and streaming of related field-level manufacturing data. For example, the realization of manufacturing service composition application should match the manufacturing tasks with distributed manufacturing resources according to their working state data and performance measurement data. Therefore, this paper proposes a data integration and analysis framework of a cloud manufacturing system based on cloud–edge collaboration and the Industrial Internet of Things (IIoT). A service-oriented information model is established to uniformly describe the related operational data and functional attributes of heterogeneous manufacturing resources. Secondly, a real-time transmission and integration method of high-volume operational field and sensor data based on message middleware is proposed to realize the remote monitoring of distributed manufacturing resources and efficient distribution of related data. Finally, a cloud–edge collaboration mechanism is put forward to train and update the parameters of various artificial intelligence models deployed at edge gateways. In the experiment, taking the computer numerical control (CNC) lathe as an example, the effectiveness of the proposed manufacturing resource access method is verified. Taking the fault diagnosis model of the CNC lathe as an example, the efficiency of the proposed cloud–edge collaboration mechanism for model updating is verified.