Accurately predicting the State of Health (SOH) of new energy vehicle batteries is critical for ensuring their reliable operation and extending battery’s service life. To address the issue of low SOH prediction accuracy across different prediction lengths, this paper proposes a prediction method based on long-short-term battery degradation feature extraction and FEA-TimeMixer model. First, a novel automatic SOH extraction algorithm for offline charging data is introduced to label the battery SOH degradation data. Then, the autoencoder is utilized to fuse the features of long-term and short-term SOH degradation trends extracted by empirical degradation models and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise to improve the prediction accuracy over different prediction lengths. Finally, a Frequency Enhanced Attention (FEA) mechanism is introduced to improve the TimeMixer model, which integrates time-domain and frequency-domain information to overcome the limitations of the original model in capturing frequency-domain features. Experimental results show that the proposed method achieves a Mean Absolute Error of less than 0.0219 for short-term SOH predictions and less than 0.1007 for long-term SOH predictions, outperforming other deep learning models in prediction accuracy over multiple prediction lengths.

In order to effectively utilize the large amount of high-dimensionality historical data generated by energy meters during operation, this paper proposes a DBN-MLP fusion neural network method for multi-dimensional analysis and fault-type diagnosis of smart energy meter fault data. In this paper, we first use DBN to strengthen the feature extraction ability of the network and solve the problem of many kinds of feature data and high dimensionality of historical data. After that, the processed feature information is input into the MLP neural network, and the strong processing ability of MLP for nonlinear numbers is used to solve the problem of weak correlation among data in the historical data set and improve the accuracy rate of faults diagnosis. The final results show that the DBN-MLP method used in this paper can effectively reduce the number of training iterations to reduce the training time and improve the accuracy of diagnosis.

To solve the problem that the elevator traction wheel slippage is difficult to detect quantitatively, a slippage detection method is proposed based on machine vision. The slip between the traction wheel and the wire rope will occur during the round-trip operation of the elevator, the displacement distance between the traction wheel and the wire rope in the circumferential direction is obtained through the image signal processing algorithm and related data analysis. First, the ROI (region of interest) of the collected original image is selected to reduce redundant information. Then, a nonlinear geometric transformation is carried out to transform the image into the target image with an equal object distance. Finally, the centroid method is used to obtain the slippage between the traction wheel and the wire rope. The field test results show that the absolute error of the system developed in this paper is 0.74 mm and the relative error is 2%, the extending uncertainty of the slip detection results is (33.8 ± 0.69) mm, the confidence probability is p = 0.95, and the degree of freedom is v = 8, which can meet accuracy requirements of elevator maintenance.

This paper concentrates on the elevator passenger detection task, a pivotal element for subsequent elevator passenger tracking and behavior recognition, crucial for ensuring passenger safety. To enhance the accuracy of detecting passenger positions inside elevators, we improved the YOLOv8 network and proposed the SC-YOLOv8 elevator passenger detection network with soft-pooling and attention mechanisms. The main improvements in this paper encompass the following aspects: Firstly, we transformed the convolution module (ConvModule) of the YOLOv8 backbone network by introducing spatial and channel reconstruction convolution (SCConv). This improvement aims to reduce spatial and channel redundancy in the feature extraction process of the backbone network, thereby improving the overall efficiency and performance of the detection network. Secondly, we propose a dual-branch SPP-Fast module by incorporating a soft-pooling branch into the YOLOv8 network’s SPP-Fast module. This dual-branch SPP-Fast module can preserve essential information while reducing the impact of noise. Finally, we propose a soft-pooling and multi-scale convolution CBAM module to further enhance the network’s performance. This module enhances the network’s focus on key regions, allowing for more targeted feature extraction, thereby further improving the accuracy of object detection. Additionally, the attention module enhances the network’s robustness in handling complex backgrounds. We conducted experiments on an elevator passenger dataset. The results show that the precision, recall, and mAP of our improved YOLOv8 network are 94.32%, 91.17%, and 92.95%, respectively, all surpassing those of the original YOLOv8 network.

The built-in relay in a meter is a key control component of a smart meter, and its reliability determines whether the user can use electricity safely and smoothly. In this paper, the degradation characteristics of the arc-burning energy are enhanced by the method of K-means clustering to replace degradation data, such as the overtravel time, release time, and other data. In existing methods, the meter needs to be disassembled to describe the degradation trend of the meter relay. The proposed method is combined with a bidirectional long short-term memory (Bi-LSTM) neural network to predict the degradation trend of the relay’s performance. In this paper, K-means clustering is used to enhance the extraction of arc energy data features, and then the arc energy data obtained from the reliability lifetime test is assessed to predict the degradation trend of the meter relay by means of a bidirectional LSTM.

Due to the high reliability of present meters, it is difficult to obtain the failure time of meters through accelerated life tests. Based on the failure data of the accelerated life test, this paper studies the mathematical model based on the Wiener process and establishes the degradation model of the instrument by the maximum likelihood to estimate the parameters of the Wiener model. With full consideration of the possible nonlinear effects in modeling, the time scale transformation method is used to study and obtain the reliability life prediction model of smart meters based on nonlinear data. Finally, the reliability life prediction model of meters is verified and evaluated through the example data of the accelerated life test of smart meters. Compared with the conventional method, this method has less error in calculating the reliability, greatly saves test time, and has a higher accuracy than estimating the lifetime model using the Wiener process directly.