A novel method-based reinforcement learning with deep temporal difference network for flexible double shop scheduling problem.

This paper studies the flexible double shop scheduling problem (FDSSP) that considers simultaneously job shop and assembly shop. It brings about the problem of scheduling association of the related tasks. To this end, a reinforcement learning algorithm with a deep temporal difference network is proposed to minimize the makespan. Firstly, the FDSSP is defined as the mathematical model of the flexible job-shop scheduling problem joined to the assembly constraint level. It is translated into a Markov decision process that directly selects behavioral strategies according to historical machining state data. Secondly, the proposed ten generic state features are input into the deep neural network model to fit the state value function. Similarly, eight simple constructive heuristics are used as candidate actions for scheduling decisions. From the greedy mechanism, optimally combined actions of all machines are obtained for each decision step. Finally, a deep temporal difference reinforcement learning framework is established, and a large number of comparative experiments are designed to analyze the basic performance of this algorithm. The results showed that the proposed algorithm was better than most other methods, which contributed to solving the practical production problem of the manufacturing industry.

A novel integrated MADM method for design concept evaluation.

Design concept evaluation plays a significant role in new product development. Rough set based methods are regarded as effective evaluation techniques when facing a vague and uncertain environment and are widely used in product research and development. This paper proposed an improved rough-TOPSIS method, which aims to reduce the imprecision of design concept evaluation in two ways. First, the expert group for design concept evaluation is classified into three clusters: designers, manufacturers, and customers. The cluster weight is determined by roles in the assessment using a Multiplicative Analytic Hierarchy Process method. Second, the raw information collection method is improved with a 3-step process, and both design values and expert linguistic preferences are integrated into the rough decision matrix. The alternatives are then ranked with a rough-TOPSIS method with entropy criteria weight. A practical example is shown to demonstrate the method's viability. The findings suggest that the proposed decision-making process is effective in product concept design evaluation.

An integrated expert weight determination method for design concept evaluation.

Expert weight determination is a critical issue in the design concept evaluation process, especially for complex products. However, this phase is often ignored by most decision makers. For the evaluation of complex product design concepts, experts are selected by clusters with different backgrounds. This work proposes a novel integrated two-layer method to determine expert weight under these circumstances. In the first layer, a hybrid model integrated by the entropy weight model and the Multiplicative analytical hierarchy process method is presented. In the second layer, a minimized variance model is applied to reach a consensus. Then the final expert weight is determined by the results of both layers. A real-life example of cruise ship cabin design evaluation is implemented to demonstrate the proposed expert weight determination method. To analyze the feasibility of the proposed method, weight determination with and without using experts is compared. The result shows the expert weight determination method is an effective approach to improve the accuracy of design concept evaluation.

A computational efficient optimization of flow shop scheduling problems.

Flow shop scheduling problems are NP-hard problems. Heuristic algorithms and evolutionary metaheuristic algorithms are commonly used to solve this kind of problem. Although heuristic algorithms have high solving speed, the solution quality is not good. Evolutionary algorithms make up for this defect in small-scale problems, but the solution performance will deteriorate with the expansion of the problem scale and there will be premature problems. In order to improve the solving accuracy of flow shop scheduling problems, a computational efficient optimization approach combining NEH and niche genetic algorithm (NEH-NGA) is developed. It is strengthened in the following three aspects: NEH algorithm is used to optimize the initial population, three crossover operators are used to enhance the genetic efficiency, and the niche mechanism is used to control the population distribution. A concrete application scheme of the proposed method is introduced. The results of compared with NEH heuristic algorithm and standard genetic algorithm (SGA) evolutionary metaheuristic algorithm after testing on 101 FSP benchmark instances show that the solution accuracy has been significantly improved.

P_VggNet: A convolutional neural network (CNN) with pixel-based attention map.

Attention maps have been fused in the VggNet structure (EAC-Net) [1] and have shown significant improvement compared to that of the VggNet structure. However, in [1], E-Net was designed based on the facial action unit (AU) center and for facial AU detection only. Thus, for the use of attention maps in every image type, this paper proposed a new convolutional neural network (CNN) structure, P_VggNet, comprising the following parts: P_Net and VggNet with 16 layers (VggNet-16). The generation approach of P_Net was designed, and the P_VggNet structure was proposed. To prove the efficiency of P_VggNet, we designed two experiments, which indicated that P_VggNet could more efficiently extract image features than VggNet-16.