Search

This paper investigates the application of a self-coder neural network in oilfield rod pump anomaly detection. Rod pumps are critical equipment in oilfield production engineering, and their stability and reliability are crucial to the production efficiency and economic benefits. However, rod pumps are often affected by anomalies such as wax deposition, leading to increased maintenance costs and production interruptions. Traditional wax deposition detection methods are inefficient and fail to provide early warning capabilities. This paper reviews the research progress in sucker rod pump anomaly detection and autoencoder neural networks, providing a detailed description of the construction and training process of the autoencoder neural network model. Utilizing data from the rod-pumped wells of the Tuha oilfield in China, this study achieves the automatic recognition of various anomalies through data preprocessing and the training of an autoencoder model. This study also includes a comparative analysis of the differences in the anomaly detection performance between the autoencoder and traditional methods and verifies the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Wheel re-profiling has frequently been used as a method for improving polygonal wheel wear. It is very necessary to set a reasonable re-profiling threshold. According to the actual wear state of the wheel, a wheel profile model considering the three-dimensional (3D) wear form of the polygonal wheel is established in this paper. The effect of the 3D polygonal wheel on vehicle system dynamics is analyzed. Based on the comprehensive dynamics characteristics of the vehicle, the re-profiling threshold of the polygonal wheel was studied under different amplitudes and orders of polygon. The results show that periodic coupled vibration occurs when there is 3D polygonal wear on the wheels, which deteriorates the vehicle dynamics characteristics. The vehicle system dynamics indexes vary considerably with the orders and amplitudes of polygonal wear. The re-profiling threshold decreases gradually from the increase in the orders and amplitudes of the polygon, which presents strong nonlinear characteristics. In general, when the order of wheel polygon is less than 4, the re-profiling threshold is less than 0.2mm. These studies improve the understanding of the effects of polygonal wheel wear and provide theoretical guidance for the determination of the re-profiling threshold. [ABSTRACT FROM AUTHOR]

The traditional orthogonal matching pursuit algorithm exploits only the overall sparsity of signals without considering the effects caused by structural characteristics. To this end, this paper proposes an enhanced Bayesian sparse representation (EBSR) of mechanical fault signals by structural feature-oriented matching redundant dictionary construction. First, an EBSR model which can improve sparse reconstruction results is proposed. The proposed model improves the recovery accuracy and robustness of the sparse representation by using the structural information as a priori information. Subsequently, a composite dictionary is designed combining a Sin-Chirplet dictionary with an Impulse dictionary, and a multi-group and multi-strategy grey wolf optimizer algorithm is employed to enable the composite dictionary match the structural features of the fault signal and reduce its redundancy degree. Finally, the optimized matching composite dictionary is introduced into the EBSR algorithm, endowing it with an efficient atom selection strategy and reducing the complexity of the sparse representation. The simulation and experimental results demonstrated that the proposed method can effectively reduce the interference from background noise and impurity frequencies, verifying the effectiveness and applicability of the proposed method for the sparse representation of mechanical faults. [ABSTRACT FROM AUTHOR]

Polygonized wear of wheel is a three-dimensional wear state which includes circumferential periodic wear and lateral hollow wear. When polygonized wear of wheel occurs, wheel-rail dynamic characteristics will be affected and the subsequent wear distribution of the wheel will be influenced. To study this phenomenon, a prediction method for the three-dimensional wheel wear state is put forward and a united simulation model is established in this paper. Based on this model, wheelset vibration characteristics, wheel-rail contact characteristics, and wheel wear characteristics were analyzed. The results show that when considering three-dimensional wear state of wheel, the stress distribution in the wheel-rail contact patch is affected by the coupling of the lateral and vertical vibration caused by the polygonized wheel, which in turn affects longitudinal and lateral creep force and creepage distribution in the contact patch. Then, the distribution of circumferential and lateral wear on the wheel will be changed. Finally, the three-dimensional polygonized wear of wheel with different wear depths and widths at different wheel phase angles will be formed. [ABSTRACT FROM AUTHOR]

Coal thermochemical conversion processes unavoidably generate gaseous pollutants, endangering the environment or influencing synthetic processes downstream. In order to display the differences in release behaviours of nitrogen among different coal thermochemical conversion stages, the nitrogen release characteristics of Shenhua bituminous coal under Ar, CO2, and air atmospheres were investigated using X‐ray photoelectron spectrum (XPS) and thermogravimetry‐mass spectrometry (TG‐MS). Results indicate that the reaction atmosphere has an important influence on nitrogen release. The total released mass of nitrogen when using 100 g raw coal in the whole experiment under Ar, CO2, and air atmospheres is 0.54, 0.64, and 0.75 g, respectively. The organic forms of nitrogen in raw coal and coal char are pyridine nitrogen (N‐6), pyrrole nitrogen (N‐5), quaternary nitrogen (N‐Q), and nitrogen oxide (N‐X). While in the coal ash, the sub‐peaks of N‐Q and N‐X disappear entirely, leaving only N‐5 and N‐6 sub‐peaks. The released nitrogen‐containing gas consists of NH3, HCN, NO, and NO2 during experiments in CO2 and air atmospheres. However, only NH3 and HCN are detected during experiments in the Ar atmosphere. The revolution characteristics of NH3 and HCN under Ar and CO2 atmospheres are similar. [ABSTRACT FROM AUTHOR]