State of health (SOH) estimation of lithium-ion batteries (LIBs) is of critical importance for battery management systems (BMSs) of electronic devices. An accurate SOH estimation is still a challenging problem limited by diverse usage conditions between training and testing LIBs. To tackle this problem, this article proposes a transfer learning-based method for personalized SOH estimation of a new battery. More specifically, a convolutional neural network (CNN) combined with an improved domain adaptation method is used to construct an SOH estimation model, where the CNN is used to automatically extract features from raw charging voltage trajectories, while the domain adaptation method named maximum mean discrepancy (MMD) is adopted to reduce the distribution difference between training and testing battery data. This article extends MMD from classification tasks to regression tasks, which can therefore be used for SOH estimation. Three different datasets with different charging policies, discharging policies, and ambient temperatures are used to validate the effectiveness and generalizability of the proposed method. The superiority of the proposed SOH estimation method is demonstrated through the comparison with direct model training using state-of-the-art machine learning methods and several other domain adaptation approaches. The results show that the proposed transfer learning-based method has wide generalizability as well as a positive precision improvement.

Parts with high-quality freeform surfaces have been widely used in industries, which require strict quality control during the manufacturing process. Among all the industrial inspection methods, contact measurement with coordinate measuring machines or computer numerical control machine tool is a fundamental technique due to its high accuracy, robustness, and universality. In this paper, the existing research in the contact measurement field is systematically reviewed. First, different configurations of the measuring machines are introduced in detail, which may have influence on the corresponding sampling and inspection path generation criteria. Then, the entire inspection pipeline is divided into two stages, namely the pre-inspection and post-inspection stages. The typical methods of each sub-stage are systematically overviewed and classified, including sampling, accessibility analysis, inspection path generation, probe tip radius compensation, surface reconstruction, and uncertainty analysis. Apart from those classical research, the applications of the emerging deep learning technique in some specific tasks of measurement are introduced. Furthermore, some potential and promising trends are provided for future investigation.

This work presents a solution for fatigue recognition through a new deep learning model that has a characteristic input of the power spectrum of an electroencephalogram (EEG) signal. Firstly, four rhythms are obtained through the designed FIR filters, and the curve areas of their power spectrum density are coupled into four fatigue indicators. Secondly, a deep sparse contractive autoencoder network is proposed to learn more local fatigue characteristics, and the recognition results of pilots mental fatigue status are given. Compared with the state-of-the-art models, the results show that our model has good learning performance in extracting local features and fatigue status detection.

This article proposes a gated recurrent unit (GRU) neural network prediction and compensation (NNC) strategy for precision multiaxis motion control systems with contouring performance orientation. First, some characteristic contouring tasks are carried out on a multiaxis linear-motor-driven motion system, and the true contouring error values obtained by the Newton numerical calculation method are used as the training data of a developed artificial GRU neural network. Essentially, the proposed GRU neural network structure can be viewed as a data-based black-box error model, which can capture the dynamic characteristics of contouring motion rather accurately. The well-trained GRU network can predict the contouring error precisely even under the tasks those have not been conducted during the training session. Moreover, the predicted contouring error is compensated into the reference contour as feedforward compensation to improve the final contouring performance. Comparison between the predicted contouring error and the actual contouring error practically proves the effective prediction ability of the proposed GRU neural network. Furthermore, comparative experiments among proportional-integral-differential, iterative learning control (ILC), and the proposed NNC controller are conducted. The results consistently validate that NNC can basically achieve excellent contouring motion performance as ILC, significantly without need of motion repetition and iteration. Due to the implementation convenience and excellent prediction/compensation ability, the proposed NNC would have good potential in industrial mechatronic applications.

To simultaneously achieve accurate tracking error prediction, rigorous motion accuracy, and certain robustness to parameter variations and unknown disturbances, this article proposes a data-based learning adaptive robust control (LARC) strategy based on gated recurrent unit (GRU) neural network. Firstly, parameter adaptive control and robust control are utilized to guarantee the robustness against parametric uncertainties and unknown disturbances. A GRU neural network is then constructed and capable of precisely predicting the tracking error after training with data collected from a linear-motor-driven stage. Essentially, the GRU network can be viewed as a data-based model, which captures the tracking error dynamic characteristics and provides a prediction even before implementing the real trajectory. Consequently, a reference modification and a feedforward compensation part can be formed, which is the significant part of the whole LARC control structure. Comparative experimental investigation not only validates the effectiveness of the tracking error prediction ability, but also demonstrates the practically satisfactory transient/steady-state tracking performance of the proposed control strategy.

Aiming to simulate the experimentally observed three kinds of one-stepping characteristics in stick-slip piezoelectric actuators, i.e., backward motion, smooth motion and sudden jump, a new dynamic model was proposed with consideration of the deformation of overall system. Being different from the existing dynamic models that consider the overall system as a rigid body, the stiffness coefficient and damping coefficient of the overall system were introduced in the newly proposed model. By adjusting the parameters according to the experimental conditions, these three kinds of characteristics were successfully simulated for the first time in this field. By comparison with the existing dynamic models of stick-slip piezoelectric actuators, the effectiveness, advancement, and necessity of the proposed dynamic model were demonstrated. This model is expected to be helpful for the structure design and performance prediction of stick-slip piezoelectric actuators.