Research On ADCN Method for Damage Detection of Mining Conveyor Belt

Qu, Dingran; Qiao, Tiezhu; Pang, Yusong; Yang, Yi; Zhang, Haitao

doi:10.1109/jsen.2020.3048057

Cited by 26 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to testing the algorithm on the dataset, we chose conveyor belt damage data from the Refs. [25,26,29,30,32] for validation of the model's generalization ability, and the results are shown in Figure 8. Generalization ability refers to the ability of the neural network model to adapt to fresh samples, and we expect that the model we obtain through training on the dataset will still give reasonable output when faced with data outside the dataset, i.e.…”

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

“…In Figure 8, the first row show the original image of the conveyor belt damage, figures shown in the second row are the detection results using the method in this paper, and the third row are the detection results given in Refs. [25,26,29,30,32] respectively. Among them, (c) shows the tear detection method based on image processing, (f) shows the detection method based on infrared, (i) shows the method based on infrared spectral analysis, which integrates the problem of local temperature increase due to sliding friction during the tearing process of the conveyor belt, and (l) shows the method assisted by a line laser, which transforms the detection problem of tears into the detection of corner points in a continuous smooth curve with the help of a line laser generator, (m,n) are the damage form of the conveyor belt proposed in Ref.…”

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

“…Among them, (c) shows the tear detection method based on image processing, (f) shows the detection method based on infrared, (i) shows the method based on infrared spectral analysis, which integrates the problem of local temperature increase due to sliding friction during the tearing process of the conveyor belt, and (l) shows the method assisted by a line laser, which transforms the detection problem of tears into the detection of corner points in a continuous smooth curve with the help of a line laser generator, (m,n) are the damage form of the conveyor belt proposed in Ref. [32], (m) shows scratch, and (n) shows tear, but the recognition results in this paper are all tears, because the annotations in our dataset are different from that. As shown in Figure 8, the algorithm in this paper achieves good detection results in these fresh samples, proving the strong model generalization capability of the algorithmic model in this paper.…”

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

“…A conveyor belt damage detection method based on ADCN (Adaptive Deep Convolutional Network), which is essentially a variant of SPP-Yolov3, was mentioned in Ref. [32], enabling the detection of both Scratch and Tearing damage states. Then a deep learning-based detection method was mentioned in Ref.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of Lightweight Convolutional Neural Network for Damage Detection of Conveyor Belt

Zhang

Zhou

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Aiming at the problem that mining conveyor belts are easily damaged under severe working conditions, the paper proposed a deep learning-based conveyor belt damage detection method. To further explore the possibility of the application of lightweight CNNs in the detection of conveyor belt damage, the paper deeply integrates the MobileNet and Yolov4 network to achieve the lightweight of Yolov4, and performs a test on the exiting conveyor belt damage dataset containing 3000 images. The test results show that the lightweight network can effectively detect the damage of the conveyor belt, with the fastest test speed 70.26 FPS, and the highest test accuracy 93.22%. Compared with the original Yolov4, the accuracy increased by 3.5% with the speed increased by 188%. By comparing other existing detection methods, the strong generalization ability of the model is verified, which provides technical support and empirical reference for the visual monitoring and intelligent development of belt conveyors.

show abstract

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

Section: Verification Of Generalization Proficiencymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Lightweight Convolutional Neural Network for Damage Detection of Conveyor Belt

Zhang

Zhou

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Conveyers are considered a critical component of modern coal mining transportation system; therefore, it is essential to diagnose and monitor their damage accurately. Recent trends in this regard have led to the development of Adaptive Deep Convolutional Network methods which can better meet the real-time and reliability requirements of conveyor belt damage detection [1]. Also, high processing computing has led to an extensive use of numerical models for analysing the behaviour of mining equipment in operation and for characterizing their dynamics under various conditions [2].…”

Section: Introductionmentioning

confidence: 99%

Reliability and maintainability of scraper conveyor used in coal mining in the Jiu Valley

Florea¹,

Păsculescu²,

Pasculescu³

2021

Min. miner. depos.

View full text Add to dashboard Cite

Purpose.The aim of the study is to determine and analyse causes of faults in the operation of TR-7A scraper conveyor and to estimate the required time for their remediation and select the methods of their prevention and elimination. Methods. The characteristic of a system, such as the scraper conveyor, intended to fulfil its specified function in time and operation conditions, can be studied, theoretically, by determining its operational reliability. This implies the existence of a framework that incorporates several interconnected components of technical, operational, commercial and management nature. The quantitative expression of reliability was based on elements of mathematical probability theory and statistics (exponential distribution law), failure and repair mechanism not being subject to certain laws. Findings. The following TR-7A subassemblies, if defective, could have been the cause of a failure: chains, hydraulic couplings, chain lifters, drive, return drums, some electrical equipment. After 28 months of monitoring the TR-7A operation, we have established the number of failures (defects) ni, the operating time between failures ti, frequency of failures fc, time to repair tri, weight repair time pr, mean time between failures (MTBF), mean time to repair (MTR). Originality.Data collection and processing involves the adoption of specific procedures to allow the correct highlighting of the causes and frequency of failures. The accomplishment of this approach allowed finding the solutions for increasing reliability of some subassemblies of TR-7A conveyor (i.e., those subjected to abrasive wear). Practical implications.One solution was to use materials with compositional and functional gradient in the case of worn surfaces of some subassemblies. It was successfully applied for the chain lifters where a significant increase in the mean time between failures was obtained. The field of application of these materials can be extended to the metal subassemblies of machines and equipment with abrasion wear that occurs both in underground mines and in quarries.

show abstract