In this paper, a real-time scheduling problem of a dual-resource flexible job shop with robots is studied. Multiple independent robots and their supervised machine sets form their own work cells. First, a mixed integer programming model is established, which considers the scheduling problems of jobs and machines in the work cells, and of jobs between work cells, based on the process plan flexibility. Second, in order to make real-time scheduling decisions, a framework of multi-task multi-agent reinforcement learning based on centralized training and decentralized execution is proposed. Each agent interacts with the environment and completes three decision-making tasks: job sequencing, machine selection, and process planning. In the process of centralized training, the value network is used to evaluate and optimize the policy network to achieve multi-agent cooperation, and the attention mechanism is introduced into the policy network to realize information sharing among multiple tasks. In the process of decentralized execution, each agent performs multiple task decisions through local observations according to the trained policy network. Then, observation, action, and reward are designed. Rewards include global and local rewards, which are decomposed into sub-rewards corresponding to tasks. The reinforcement learning training algorithm is designed based on a double-deep Q-network. Finally, the scheduling simulation environment is derived from benchmarks, and the experimental results show the effectiveness of the proposed method.

In complex environments, signals from rotor bearing systems can easily be drowned out by strong noise, leading to low fault diagnosis accuracy. In order to reduce noise and improve diagnostic accuracy, this paper proposes a rotor bearing system fault diagnosis method based on future search algorithm based on sine cosine algorithm-variational mode decomposition (FSASCA-VMD) and Graph SAmple and aggreGatE-self attention (GraphSAGE-SA). First, the FSASCA optimization algorithm is used to determine two parameters in VMD. The best combination found is then input into VMD to decompose the original signal. Then, filter the intrinsic mode function (IMF) components with high correlation to the original signal using cumulative percentage kurtosis. Reconstruct the filtered IMF components to complete signal denoising. Finally, this paper utilizes graph theory and time series correlation to uncover the hidden relationships within the data. Utilizing the Euclidean distance as the edge weight between nodes, a graph model is established based on the topological structure of the PathGraph, and a GraphSAGE-SA fault diagnosis framework is constructed. Utilizing a self-attention mechanism to aggregate nodes enhances the weight allocation of important information. The experimental results indicate that the method proposed in this paper can effectively remove most of the noise in the signal while preserving a significant amount of useful information. In rotor bearing system fault diagnosis, the diagnostic accuracies of this method for simulated and laboratory signals are 98.33% and 98.56%, respectively, surpassing those of other methods.

Future search algorithm imitates the person living life. If one person finds that his life is not good, he will try to change his living life, and he will imitate a more successful person. To overcome insufficient performances of the basic Future search algorithm, this paper proposed an improved Future search algorithm based on the sine cosine algorithm (FSASCA). The proposed algorithm uses sine cosine algorithm to loop-progressive find the best solution. The searching method of the sine cosine algorithm can make the feasible solution to be re-positioned around another feasible solutions, which can make the proposed algorithm have a strong exploitation ability. Four coefficient factors are added in the basic FSA, and new update methods are introduced in the searching phase. To verify the searching and optimization performances of the proposed algorithm in this paper, this paper also gives data calculation results, Wilcoxon rank sum test, iteration figures, box plot figures, and searching path figures. Experimental results showed that FSASCA has a better iteration speed, the convergence precision, the solving accuracy, the strong competitive, and the high balance.

To improve the accuracy of rolling-bearing fault diagnosis and solve the problem of incomplete information about the feature-evaluation method of the single-measurement model, this paper combines the advantages of various measurement models and proposes a fault-diagnosis method based on multi-measurement hybrid-feature evaluation. In this study, an original feature set was first obtained through analyzing a collected vibration signal. The feature set included time- and frequency-domain features, and also, based on the empirical-mode decomposition (EMD)-obtained time-frequency domain, energy and Lempel–Ziv complexity features. Second, a feature-evaluation framework of multiplicative hybrid models was constructed based on correlation, distance, information, and other measures. The framework was used to rank features and obtain rank weights. Then the weights were multiplied by the features to obtain a new feature set. Finally, the fault-feature set was used as the input of the category-divergence fault-diagnosis model based on kernel principal component analysis (KPCA), and the fault-diagnosis model was based on a support vector machine (SVM). The clustering effect of different fault categories was more obvious and classification accuracy was improved.

Optimization algorithms are popular to solve different problems in many fields, and are inspired by natural principles, animal living habits, plant pollinations, chemistry principles, and physic principles. Optimization algorithm performances will directly impact on solving accuracy. The Crow Search Algorithm (CSA) is a simple and efficient algorithm inspired by the natural behaviors of crows. However, the flight length of CSA is a fixed value, which makes the algorithm fall into the local optimum, severely limiting the algorithm solving ability. To solve this problem, this paper proposes a Variable Step Crow Search Algorithm (VSCSA). The proposed algorithm uses the cosine function to enhance CSA searching abilities, which greatly improves both the solution quality of the population and the convergence speed. In the update phase, the VSCSA increases population diversities and enhances the global searching ability of the basic CSA. The experiment used 14 test functions,2017 CEC functions, and engineering application problems to compare VSCSA with different algorithms. The experiment results showed that VSCSA performs better in fitness values, iteration curves, box plots, searching paths, and the Wilcoxon test results, which indicates that VSCSA has strong competitiveness and sufficient superiority. The VSCSA has outstanding performances in various test functions and the searching accuracy has been greatly improved.

Aiming to resolve the problem of redundant information concerning rolling bearing degradation characteristics and to tackle the difficulty faced by convolutional deep learning models in learning feature information in complex time series, a prediction model for remaining useful life based on multiscale fusion permutation entropy (MFPE) and a multiscale convolutional attention neural network (MACNN) is proposed. The original signal of the rolling bearing was extracted and decomposed by resonance sparse decomposition to obtain the high-resonance and low-resonance components. The multiscale permutation entropy of the low-resonance component was calculated. Moreover, the locally linear-embedding algorithm was used for dimensionality reduction to remove redundant information. The multiscale convolution module was constructed to learn the feature information at different time scales. The attention module was used to fuse the feature information and input it into the remaining useful life prediction module for evaluation. The appropriate network structure and parameter configuration were determined, and a multiscale convolutional attention neural network was designed to determine the remaining useful life prediction model. The results show that the method demonstrates effectiveness and superiority in degrading the feature information representation and improving the remaining useful life prediction accuracy compared with other models.