Intelligent methods have long been researched in fault diagnosis. Traditionally, feature extraction and fault classification are separated, and this process is not completely intelligent. In addition, most traditional intelligent methods use an individual model, which cannot extract the discriminate features when the machines work in a complex condition. To overcome the shortcomings of traditional intelligent fault diagnosis methods, in this paper, an intelligent bearing fault diagnosis method based on ensemble sparse auto-encoders was proposed. Three different sparse auto-encoders were used as the main architecture. To improve the robustness and stability, a novel weight strategy based on distance metric and standard deviation metric was employed to assign the weights of three sparse auto-encodes. Softmax classifier is used to classify the fault types of integrated features. The effectiveness of the proposed method is validated with extensive experiments, and comparisons with the related methods and researches on the widely-used motor bearing dataset verify the superiority of the proposed method. The results show that the testing accuracy and the standard deviation are 99.71% and 0.05%.

Achieving deep learning-based bearing fault diagnosis heavily relies on large labeled training samples. However, in real industry applications, labeled data are scarce or even impossible to obtain. In this study, we addressed a challenging few-shot bearing fault diagnosis problem with few or no training labeled samples of novel categories. To tackle this problem, we considered a semi-supervised prototype network based on few-shot bearing fault diagnosis with pseudo-labels. The existing prototypical networks with pseudo-label methods train a pseudo label model to label unlabeled samples using high-dimensional labeled data, which cannot eliminate the instability of the pseudo-label model caused by dimensional labeled features. To mitigate this issue, we used kernel principal component analysis to reduce the dimensions of and remove redundant information from high-dimensional data. Specifically, we used the pseudo-label prediction algorithm with probability distance to label unlabeled samples, aiming to improve the labeling accuracy. We applied two well-known bearing data sets for the validation experiments with symmetry parameters. The findings illustrated that the classification accuracy of the proposed method is higher than that of other existing methods.

Considering the performance requirements in actual applications, a look-up table based fractional order composite control scheme for the permanent magnet synchronous motor speed servo system is proposed. Firstly, an extended state observer based compensation scheme was adopted to suppress the motor parametric uncertainties and convert the speed servo plant into a double-integrator model. Then, a fractional order proportional-derivative ($\mathrm{P}{\mathrm{D}}^{\mu }$) controller was adopted as the speed controller to provide the optimal step response performance for the servo system. A universal look-up table was established to estimate the derivative order of the $\mathrm{P}{\mathrm{D}}^{\mu }$ controller, according to the optimal samples collected by an improved differential evolution algorithm. With the look-up table, the optimal $\mathrm{P}{\mathrm{D}}^{\mu }$ controller can be tuned analytically. Simulation and experimental results show that the servo system using the composite control scheme can achieve optimal tracking performance and has robustness to the motor parametric uncertainties and disturbance torques.

Path planning is of great research significance as it is key to affecting the efficiency and safety of mobile robot autonomous navigation task execution. The traditional gray wolf optimization algorithm is widely used in the field of path planning due to its simple structure, few parameters, and easy implementation, but the algorithm still suffers from the disadvantages of slow convergence, ease of falling into the local optimum, and difficulty in effectively balancing exploration and exploitation in practical applications. For this reason, this paper proposes a multi-strategy improved gray wolf optimization algorithm (MSIAR-GWO) based on reinforcement learning. First, a nonlinear convergence factor is introduced, and intelligent parameter configuration is performed based on reinforcement learning to solve the problem of high randomness and over-reliance on empirical values in the parameter selection process to more effectively coordinate the balance between local and global search capabilities. Secondly, an adaptive position-update strategy based on detour foraging and dynamic weights is introduced to adjust the weights according to changes in the adaptability of the leadership roles, increasing the guiding role of the dominant individual and accelerating the overall convergence speed of the algorithm. Furthermore, an artificial rabbit optimization algorithm bypass foraging strategy, by adding Brownian motion and Levy flight perturbation, improves the convergence accuracy and global optimization-seeking ability of the algorithm when dealing with complex problems. Finally, the elimination and relocation strategy based on stochastic center-of-gravity dynamic reverse learning is introduced for the inferior individuals in the population, which effectively maintains the diversity of the population and improves the convergence speed of the algorithm while avoiding falling into the local optimal solution effectively. In order to verify the effectiveness of the MSIAR-GWO algorithm, it is compared with a variety of commonly used swarm intelligence optimization algorithms in benchmark test functions and raster maps of different complexities in comparison experiments, and the results show that the MSIAR-GWO shows excellent stability, higher solution accuracy, and faster convergence speed in the majority of the benchmark-test-function solving. In the path planning experiments, the MSIAR-GWO algorithm is able to plan shorter and smoother paths, which further proves that the algorithm has excellent optimization-seeking ability and robustness.

A 2-D numerical simulation model was established based on a small-sized metal hydride storage tank, and the model was validated by the existing experiments. An external cooling bath was equipped to simulate the heating effects of hydrogen absorption reactions. Furthermore, both the type and the flow rate of the cooling fluids in the cooling bath were altered, so that changes in temperature and hydrogen storage capacity in the hydrogen storage model could be analyzed. It is demonstrated that the reaction rate in the center of the hydrogen storage tank gradually becomes lower than that at the wall surface. When the flow rate of the fluid is small, significant differences can be found in the cooling liquid temperature at the inlet and the outlet cooling bath. In areas adjacent to its inlet, the reaction rate is higher than that at the outlet, and a better cooling effect is produced by water. As the flow rate increases, the total time consumed by hydrogen adsorption reaction is gradually reduced to a constant value. At the same flow rate, the wall surface of the tank shows a reaction rate insignificantly different from that in its center, provided that cooling water or oil coolant is replaced with air.

Traditional deep learning-based fault diagnosis scenarios always rely on a certain type of deep neural networks(DNNs) to extract its inherent features, which can overcome the drawbacks of shallow model methods. However, the invariant features extracted have some inevitable limitations, which lead to the performance degeneration and lower generalization ability of these scenarios. To address this problem, we propose a feature integration boosting based discriminative stacked auto-encoder(D-SAE) network for bearing fault diagnosis. Specifically, multiple D-SAEs are used as weak classifiers to extract features from the raw signal. To relax the inevitable limitations of a single DNN, D-SAE networks are employed to build the features by integrating boosting into the feature level adaptively, which can combine the weighted features extracted by the D-SAEs according to the classification accuracy. Additionally, the classification information is stored in the hidden layer of the networks, preventing any potential loss of classification information that may occur as the D-SAE becomes more complex. This ensures that the performance of the classifiers does not deteriorate. With extensive experiments on the Case Western Reserve University dataset and a real petrochemical industrial unit dataset, the results indicate that significant improvements over several existing other previous methods were achieved.