Search

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 nonstandard 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 data set, 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.

Under severe working conditions in mines, common wear detection methods are difficult to apply to the hoisting cage sliding sleeves. This article proposes a wear detection method based on flexible printed circuit (FPC), which is conceived for the wear detection of sliding sleeves or the edge of complex curved surfaces under severe conditions. First, a new type of sensor based on FPC is proposed, and its detection principle is presented. Then, according to the wear mechanism of sliding sleeves, a wear detection system is designed and manufactured. In order to express wear value, a formula about the relationship between the number of broken wires and wear value is established. Finally, a series of verification experiments are carried out, and the obtained results confirm the feasibility of proposed approach and explain the causes of voltage fluctuations.

Visual inspection method (VIM) has attracted more and more attention because it is fast, nondestructive, automatic, and objective, which can replace manual inspection method or assist other non-destructive testing methods for wire ropes (WR) to a certain extent. However, it is still a challenging task to accurately detect the potential defects and identify the types from the WR surface morphology. In this paper, an efficient hybrid data-driven method based on texture features and optimized support vector machine (SVM) is proposed to solve this problem, which is called WR-IFOA-SVM. Uniform local binary pattern and gray-level co-occurrence matrix features were extracted and fused from image dataset which contains three most common states, i.e. healthy, broken and worn WRs. The inertial dynamic weight function was introduced into the fruit fly optimization algorithm (FOA) to overcome the problem that the traditional FOA cannot balance the global and local search ability. And the data mining experiments of the established feature dataset were carried out relying on the proposed WR-IFOA-SVM model, which was then compared with other methods. The experimental results show that this method can effectively detect various defect types on the WR surface, furthermore demonstrate that our method outperforms the state-of-the-art works in WR visual inspection field.

Overwinding protection devices are used to brake hoisting containers before these containers reach a limited height, thereby preventing the hoisting containers from impacting the hoisting system. However, in ultra-deep shafts (depth > 1000 m), traditional overwinding protection methods fail to protect the hoisting system, because this type of hoisting system has a greater mass, kinetic energy, and inertia than the traditional hoisting system, and also the environment of ultra-deep shafts is more complex. This paper presents a novel overwinding protection method that applies a linear permanent magnet eddy current brake (LPMECB) to the hoisting system in ultra-deep shafts. This paper also finds the optimum setting parameter of permanent magnets (PMs). First, an analytical model of the LPMECB is built, and the time-domain signals of the braking force are processed via fast Fourier transform, confirming the mechanism of the optimum setting parameter. Subsequently, the simulations are conducted by establishing a finite-element model of the LPMECB; the simulations prove the existence of the optimum setting parameter of PMs and demonstrate the influence of the air gap, velocity, and conductivity on this parameter. Finally, the experimental studies are carried out on a test bench of the LPMECB to validate the analytical model and the simulation results. The results show the existence of the optimum setting parameter of PMs and prove that the air gap has an effect on this parameter.

double feed mechanism refers to the mechanism in which the performing link has two working and return strokes within one cycle of the driving link, it is mainly used in automatic feeding of automatic machine tools. Elliptic crank is a planet mechanism which is able to generate elliptic curve, with elliptic crank as the driven crank of the slider-crank mechanism is equal to the mechanism which has a crank of the varying length and varying speed and moving along the elliptical, which changed the kinematic characteristics of the slider. The III type of the slider elliptic-crank mechanism has properties of double working strokes. In this paper, a special type III mechanism is used as a double feed mechanism. The methods of mechanism analysis and synthesis are presented. The influence of mechanism parameters on each stroke is analyzed. The selection range of mechanism parameters is given. It provides a theoretical basis for the design of double working stroke mechanism.

Real-time, efficient detection of wire ropes (WR) surface detect is a challenging task. Affected by the performance of the algorithm, there is a problem that the detection and diagnosis effects are not ideal. To this end, an automatic detection method for surface detects of WRs on the basis of deep convolutional neural networks (DCNN) is put forward in this article. First, according to the actual situation, the state of the WR is defined as three main states of health, broken wire and wear. Then, a big data set of the WR surface image with three states is established, and an improved DCNN model is used to perform deep mining on the established data set. Finally, performance comparisons are made with traditional machine learning algorithms. Through a large number of tests and contrasting analysis, the results show that the method we proposed can achieve a higher diagnostic accuracy than the traditional methods, which meets the actual detection requirements.

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.

Visual method is a potential way to intuitively grasp the surface damage state of wire ropes to guarantee its reliability and safety. However, the various appearance characteristics of ropes are seriously affected by noise and effective inspection methods are lacking; therefore, efficient preprocessing and damage detection methods are urgently needed. Aiming at the influence of illumination, feature dimension, and the performance of different classification algorithms, this paper presents a novel method for the damage detection of wire ropes based on texture features, called WR-LBPML. To uniform illuminate and highlight textures of the rope images, different homomorphic filtering algorithms were compared and applied. A total of 59 texture features were extracted from rope surface images using uniform local binary patterns (u-LBP) operators. Due to the redundancy of the dataset, the features were processed using principal component analysis. Finally, we conducted a comparative study of three machine learning algorithms. Extensive experiments and comparisons of rope damage detection indicated that the proposed method can achieve optimal performance (accuracy: 93.3%, efficiency: 0.04 ms per sample) using a support vector machine with 10 features extracted by u-LBP operator, in which the images were filtered by a Gaussian low-pass filter with a block size of 1.