Compressor fault diagnosis system based on PCA-PSO-LSSVM algorithm

Zhang, Kun; Su, Jinpeng; Sun, Shaoan; Liu, Zhixiang; Wang, Jinrui; Du, Mingchao; Liu, Zengkai; Zhang, Qiang

doi:10.1177/00368504211026110

Cited by 15 publications

(9 citation statements)

References 14 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, the more commonly used parameter optimization methods are swarm intelligence optimization algorithms, such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Algorithm (ACO), Sparrow Search Algorithm (SSA), etc. [20][21][22][23]. In the above algorithms, the SSA method has the advantages of strong optimization ability and fast convergence speed.…”

Section: B Ssa-spamentioning

confidence: 99%

Fault Feature Extraction Method of Reciprocating Compressor Valve Based on SPA-MF

Pan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Aiming at the problem that the traditional multifractal detrended fluctuation analysis (MFDFA) using the least squares method to fit the trend term is prone to overfitting and takes a long time, this paper proposes a new non-stationary signal analysis method-smoothed prior analysis multifractal (SPA-MF).Firstly, the time sequence data is adaptively decomposed by smooth prior analysis (SPA) to eliminate the local trends of sequence data at different scales, and then the multifractal analysis is performed on the detrended data obtained by the decomposition. At the same time, the sparrow search algorithm (SSA) is used to optimize the parameter of the SPA, so as to eliminate the trend item data more accurately. Through the simulation signal which composed of the BMS signal and noise signal, the feasibility of SPA-MF for feature extraction is proved. Finally, SPA-MF is applied to extract the features of the reciprocating compressor valve vibration signal, and the extracted reciprocating compressor valve features are input into support vector machine (SVM) for classification and recognition. Through the analysis of the experimental results, it can be seen that the recognition rate of the valve features obtained by the traditional MFDFA method is only 87.5%, and the recognition rate of the SPA-MF method proposed in this paper reaches 96.87%, and the time spent on feature extraction using SPA-MF is only about 36% of that of MFDFA method, which proves the SPA-MF method is a feature extraction method with high accuracy and effectiveness.INDEX TERMS reciprocating compressor valve, smooth prior analysis, MFDFA, SPA-MF.

show abstract

Section: B Ssa-spamentioning

confidence: 99%

Fault Feature Extraction Method of Reciprocating Compressor Valve Based on SPA-MF

Pan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Then, the region of interest for target is segmented based on the optimal threshold obtained through the optimization algorithm. PSO has been widely used in image segmentation [16], path planning [17], resource allocation [18], and fault diagnosis [19] due to its simplicity in calculation and image segmentation, and fast convergence. Therefore, this paper used the PSO algorithm to solve Equation (7).…”

Section: Otsu Optimization Based On Apso Algorithmmentioning

confidence: 99%

Small targets detection in dual-energy X-ray images of coal and gangue based on APSO-C_Otsu

Zhao

Wang

Guo

et al. 2022

Preprint

View full text Add to dashboard Cite

The positioning accuracy of coal and gangue is related to the discharge accuracy of gangue, which will affect the utilization rate of coal. But the detectability of the small coal and gangue is poor due to the fewer number of pixels and texture information in coal and gangue dual-energy X-ray images. So, the Otsu with crotch structure based on Adaptive Partical Swarm Optimization (APSO) for small targets detection is proposed, called after APSO-C_Otsu. Firstly, the Otsu with crotch structure is used to perform multi-threshold segmentation of coal and gangue dual-energy X-ray images to increase the contrast between small target and background. Meanwhile, the APSO algorithm was used to optimize the Otsu algorithm with crotch structure in order to improve its convergence speed and reduce its calculation amount. Finally, the processed image is binarized, and the location of the target was labeled based on the bwlabel algorithm. The experimental results revealed that the APSO-C_Otsu algorithm could effectively detect the small pixel size (less than 8 × 8 pixels) of coal and gangue with a particle size of 6 ~ 30 mm, and was also applicable to the coal and gangue with the particle size larger than 30 mm, which was of great significance for accurate separation of coal and gangue and the improvement of coal utilization.

show abstract

“…In the mentioned study, the Weibull distribution function was applied by using the leave-one-out cross-validation method to study the failure behavior of air compressors in a deep mine in South Africa. Zhang et al 10 proposed a fault diagnosis system for compressors. In this study, an algorithm based on the least squares supports vector machine was optimized using particle swarm optimization and then applied to create a fault diagnosis model.…”

Section: Introductionmentioning

confidence: 99%

Reliability analysis of the compressed air supplying system in underground mines

Rahimdel

Ghodrati

2023

Sci Rep

View full text Add to dashboard Cite

Despite the high cost and low efficiency, compressed air is mostly used in underground mining for ore extraction, hoisting, and mineral processing operations. Failures of compressed air systems not only threaten the health and safety of workers but also contribute to inefficient control of airflow and stopped all equipment that operates by compressed air. In such uncertain conditions, mine managers are faced with the big challenge to supply enough compressed air, and therefore, the reliability evaluation of these systems is essential. This paper aims to analyze the reliability of the compressed air system using the Markov modeling approach as a case study, Qaleh-Zari Copper Mine, Iran. To achieve this, the state space diagram was constructed considering all relevant states for all compressors in the main compressor house of the mine. The failure and repair rate of all main and reserve compressors were calculated for all possible transitions between states to obtain the probability of being of the system in each of the states. Moreover, the probability of failure at any time period was considered to study the reliability behavior. The results of this study show that there is 31.5% probability that the compressed air supplying system is in operating condition with two main and one standby compressors. The system probability that two main compressors are remain in the operation without failure for one months is 92.32%. Furthermore, the lifetime of the system is estimated 33 months when at least one main compressor is active.

show abstract

Compressor fault diagnosis system based on PCA-PSO-LSSVM algorithm

Cited by 15 publications

References 14 publications

Fault Feature Extraction Method of Reciprocating Compressor Valve Based on SPA-MF

Fault Feature Extraction Method of Reciprocating Compressor Valve Based on SPA-MF

Small targets detection in dual-energy X-ray images of coal and gangue based on APSO-C_Otsu

Reliability analysis of the compressed air supplying system in underground mines

Contact Info

Product

Resources

About