As an important load-bearing component, steel wire ropes (WRs) are widely used in complex systems such as mine hoists, cranes, ropeways, elevators, oil rigs, and cable-stayed bridges. Non-destructive damage detection for WRs is an important way to assess damage states to guarantee WR’s reliability and safety. With intelligent sensors, signal processing, and pattern recognition technology developing rapidly, this field has made great progress. However, there is a lack of a systematic review on technologies or methods introduced and employed, as well as research summaries and prospects in recent years. In order to bridge this gap, and to promote the development of non-destructive detection technology for WRs, we present an overview of non-destructive damage detection research of WRs and discuss the core issues on this topic in this paper. First, the WRs’ damage type is introduced, and its causes are explained. Then, we summarize several main non-destructive detection methods for WRs, including electromagnetic detection method, optical detection method, ultrasonic guided wave detection method, and acoustic emission detection method. Finally, a prospect is put forward. Based on the review of papers, we provide insight about the future of the non-destructive damage detection methods for steel WRs to a certain extent.

Solder bump/ball technology has been extensively applied in microelectronic packaging industry. However, the size of solder balls/bumps as well as the pitch are getting smaller and smaller, conventional inspection techniques are insufficient for diagnosis of the defect. It is indispensable to explore new methods for solder joint inspection. In this paper, a nondestructive diagnosis system based on active thermography was proposed. The test vehicles, named as SFA1 and SFA2, were excited by the laser pulse, and the consequent thermal response of the packages were captured by a thermal imager. In order to improve the signal to noise ratio, the polynomial fit and differential absolute contrast (DAC) techniques were utilized to reconstruct the thermal images. Then the statistical features corresponding to each solder ball were extracted from the reconstructed thermal images, and used for clustering analysis with K-Means algorithm. The results show that all the solder balls were recognized accurately, which demonstrates that the intelligent system using active thermography and K-Means algorithm is effective for defects inspection in microelectronic packaging industry.

Nondestructive detection of the steel wire rope (SWR) is an essential scientific means to ensure the safe operation of rope systems, in which visual sensing inspection method can directly grasp the surface damage condition of SWRs. However, due to the influence of algorithm performance, timely and accurate detection of SWR surface damage has always been a challenging task. At present, manual visual inspection is still the primary method in SWR maintenance. This paper proposes an intelligent detection method of SWR surface damage based on an improved YOLO (You Only Look Once) by introducing the object detection algorithm of deep learning (DL) for the first time, called WR-YOLO. The classic version-YOLOv3 was studied, and the backbone network was changed to improve its speed. To improve the algorithm adaptability under different working conditions, the data set of SWR surface images including three main states of health, broken wire and wear was established. The proposed WR-YOLO was tested on the established data set and compared with other YOLO algorithms. The results show that the proposed WR-YOLO can achieve a mean average precision of 93.92% (mAP) with a detection speed of 116 FPS, which is better than other YOLO algorithms in performance. Finally, the dynamic detection test was carried out, and the results show that it can achieve an accurate dynamic detection effect. Therefore, this method provides the most advanced visual inspection solution for rope surface damages, which can provide the basis for guiding engineering practice of health maintenance.

Surface wear, which is most likely to occur in early damage of wire ropes (WRs), is a serious threat to WR safety. Visual perception technology (VPT) can intuitively grasp the surface damage situation of WRs. However, efficient detection of WR surface damage from complex morphological characteristics using VPT has always been a challenging task, and there are various problems, such as non-standard data, low automation/intelligence, and poor detection effect. To overcome the above difficulties, this study proposes a deep learning-based VPT framework, which relies on an image preprocessing (IP) scheme and a deep convolutional neural network (DCNN), called WR-IPDCNN. The IP scheme is designed to remove the influence of the image background and to normalize data, including posture adjustment and region of interest (ROI) extraction. The improved DCNN based on LeNet-5 is proposed to mine the newly established WR dataset, which considers different working conditions. Experimental results demonstrate that the proposed framework can accurately extract the ROI area of WR images and achieve 95.55% detection accuracy, which is 12.44% higher than LeNet-5, and a significant improvement on the automation/intelligence level in this field.

With the arrival of the big data era, it has become possible to apply deep learning to the health monitoring of mine production. In this paper, a convolutional neural network (CNN)-based method is proposed to monitor the health condition of the balancing tail ropes (BTRs) of the hoisting system, in which the feature of the BTR image is adaptively extracted using a CNN. This method can automatically detect various BTR faults in real-time, including disproportional spacing, twisted rope, broken strand and broken rope faults. Firstly, a CNN structure is proposed, and regularization technology is adopted to prevent overfitting. Then, a method of image dataset description and establishment that can cover the entire feature space of overhanging BTRs is put forward. Finally, the CNN and two traditional data mining algorithms, namely, k-nearest neighbor (KNN) and an artificial neural network with back propagation (ANN-BP), are adopted to train and test the established dataset, and the influence of hyperparameters on the network diagnostic accuracy is investigated experimentally. The experimental results showed that the CNN could effectively avoid complex steps such as manual feature extraction, that the learning rate and batch-size strongly affected the accuracy and training efficiency, and that the fault diagnosis accuracy of CNN was 100%, which was higher than that of KNN and ANN-BP. Therefore, the proposed CNN with high accuracy, real-time functioning and generalization performance is suitable for application in the health monitoring of hoisting system BTRs.

As a portable energy storage system, lithium-ion batteries (LIBs) are widely used in wireless sensor networks, electric vehicles and other fields. To ensure the continuity of power supply, it is necessary to monitor the state of charge (SOC) of LIBs. However, due to the nonlinearity of battery operation, accurate SOC estimation has become a challenging task. In this paper, a SOC estimation method based on long-term short-term memory (LSTM) network and improved particle filter (IPF) is proposed, which maps the easily observed voltage, current and temperature to the target SOC. Firstly, through a layer of the LSTM network, the timing characteristics of the data are fully utilized to obtain the SOC variation trend of LIBs. Then, the noise variance adaptive algorithm and particle distribution optimization algorithm are introduced to improve the standard particle filter (PF). On this basis, the estimation results of the LSTM network are optimized by IPF. In addition, the performance of the proposed LSTM-IPF method is compared with other methods. The results show that the estimation performance of the proposed model is excellent, and the root mean squared error (RMSE) and maximum error (MAX) are controlled below 1% and 2% respectively, which meets the requirements of SOC estimation and verifies the effectiveness of the proposed method.