Explore the vast range of titles available.

Reciprocating compressor is the core equipment of petrochemical industry and its stable running is very important for productions in the offshore drilling platform. The reason why it is difficult to extract features from vibration signals to reflect the operating state of the compressor is that its internal structure is complex and there are many excitation sources. To solve this problem, a new fault diagnosis method based on spatio-temporal features fusion based on deep belief network (STF-DBN) was proposed, which comprehensively processes multi-source signal features from dimensions of time and space. The temporal features extraction strategy is designed to reflect the data trend by reconstructing the time series according to different period characteristics of fault-related parameters. And the spatial features are extracted to reflect the non-amplitude characteristic of data by breaking down the raw data trend and considering the importance of reconstructed series to various faults. STF-DBN can overcome the deficiency of traditional unsupervised network DBN that cannot extract periodic features, no longer rely on the number of fault data samples, and construct a more comprehensive health curve representing the operation status of reciprocating compressors for fault diagnosis and early warning. The classic Tennessee Eastman (TE) data set in the control field is used for the diagnosis effect test, and the STF-DBN is applied to the operation status detection of the reciprocating compressor for offshore natural gas extraction of China National Offshore Oil Corporation. The experimental results confirm the effectiveness of the proposed method in fault defection and early warning.

Operating condition detection and fault diagnosis are very important for reliable operation of reciprocating compressors. Machine learning is one of the most powerful tools in this field. However, there are very few comprehensive reviews which summarize the current research of machine learning in monitoring reciprocating compressor operating condition and fault diagnosis. In this paper, the recent application of machine learning techniques in reciprocating compressor fault diagnosis is reviewed. The advantages and challenges in the detection process, based on three main monitoring parameters in practical applications, are discussed. Future research direction and development are proposed.

This study numerically analyzes the flow-induced noise of a hermetic reciprocating compressor (HRC) using fluid-structure interaction (FSI) analysis, acoustic excitation source modeling, and acoustic-structure interaction (ASI). Acoustic modeling, which calculates acoustic excitation source strength from pressure pulsation of the refrigerant caused by the behavior of the piston and valve, is presented for predicting flow-induced noise. Pressure pulsation is obtained by performing FSI analysis of the internal flow and valve behavior of the compressor. Based on this, acoustic excitation source strength is calculated by applying acoustic modeling such as planar wave conditions. Using the calculated acoustic excitation source, ASI analysis between the refrigerant and the shell housing is performed to predict the radiated flow-induced noise of the hermetic compressor. The numerical noise analysis results showed good agreement with experimental results, especially with high accuracy in the frequency band of cavity resonance. This study reveals that the primary cause of flow-induced noise of the HRC is acoustic waves generated by the structural movement of the piston and valve, providing important implications for future compressor design improvements.

As for the complex shock vibration characteristics, the issue of difficult to extract the characteristic information of reciprocating compressor valve, a fault diagnosis method combining informational variational mode decomposition (IVMD) and cyclic modulation spectrum (CMS) is proposed. In this paper, the Bayesian information criterion (BIC) is optimized for the VMD decomposition parameter firstly, and the obtained IVMD algorithm is applied to decompose the signal into intrinsic mode functions (IMFs). Secondly, the signal is reconstructed with the correlation coefficient. Finally, the CMS algorithm is utilized for the reconstructed signal analysis, from which main spectral features of the carrier frequency and cyclic frequency on the cyclic modulation spectrum are obtained. The characteristic information of the signal is high-lighted with the amplitude and relationship of the frequency feature. The effectiveness and superiority of the method in the diagnosis of reciprocating compressor valve faults are demonstrated with the numerical simulation and experimental analysis.

In this paper, the noise radiation characteristics of hermetic reciprocating compressor (HRC) are studied. Compressor noise is difficult to investigate because various excitation sources are simultaneously applied. Thus, numerical analysis is performed to identify excitation sources generated by the compression process. Finite element models of HRC are constructed by considering the acoustic-structure interaction. Acoustic propagation can be identified visually by applying each excitation source to the configured finite element models. The analysis and experimental results are compared to confirm the computational simulation methodology. From the analysis results, the HRC noise generation mechanism is verified. In addition, it is possible to investigate the acoustic characteristics of each noise source, which is difficult to identify using experimental methods.

In order to effectively extract the key feature information hidden in the original vibration signal, this paper proposes a fault feature extraction method combining adaptive uniform phase local mean decomposition (AUPLMD) and refined time-shift multiscale weighted permutation entropy (RTSMWPE). The proposed method focuses on two aspects: solving the serious modal aliasing problem of local mean decomposition (LMD) and the dependence of permutation entropy on the length of the original time series. First, by adding a sine wave with a uniform phase as a masking signal, adaptively selecting the amplitude of the added sine wave, the optimal decomposition result is screened by the orthogonality and the signal is reconstructed based on the kurtosis value to remove the signal noise. Secondly, in the RTSMWPE method, the fault feature extraction is realized by considering the signal amplitude information and replacing the traditional coarse-grained multi-scale method with a time-shifted multi-scale method. Finally, the proposed method is applied to the analysis of the experimental data of the reciprocating compressor valve; the analysis results demonstrate the effectiveness of the proposed method.

In practical engineering applications, the vibration signals collected by sensors often contain outliers, resulting in the separation accuracy of source signals from the observed signals being seriously affected. The mixing matrix estimation is crucial to the underdetermined blind source separation (UBSS), determining the accuracy level of the source signals recovery. Therefore, a two-stage clustering method is proposed by combining hierarchical clustering and K-means to improve the reliability of the estimated mixing matrix in this paper. The proposed method is used to solve the two major problems in the K-means algorithm: the random selection of initial cluster centers and the sensitivity of the algorithm to outliers. Firstly, the observed signals are clustered by hierarchical clustering to get the cluster centers. Secondly, the cosine distance is used to eliminate the outliers deviating from cluster centers. Then, the initial cluster centers are obtained by calculating the mean value of each remaining cluster. Finally, the mixing matrix is estimated with the improved K-means, and the sources are recovered using the least square method. Simulation and the reciprocating compressor fault experiments demonstrate the effectiveness of the proposed method.

Reed valves are commonly used in low-capacity refrigeration compressors due to their simple structure and low cost. The design of these valves requires a multidisciplinary approach to ensure both the thermodynamic performance and structural reliability. This paper proposes an optimization procedure for reed valves based on thermodynamic and bending fatigue criteria. The thermodynamic state of the gas in the compression chamber is evaluated with a lumped simulation model, whereas the bending stresses are predicted using a beam model discretized by the finite element method. The procedure is applied to design the suction valve of a high-efficiency reciprocating compressor used in household refrigeration systems. The influence of the reed thickness and clearance volume is assessed by comparing the compressor efficiency, valve displacement and instantaneous flow rate through the valve for each condition. The results reveal that this computationally inexpensive procedure can be used to find the optimal valve design in terms of thermodynamic efficiency and reliability.

Aiming at the long-term unpredictability of the reciprocating compressor vibration signal, a non-parametric prediction method of reciprocating compressor time series based on the prediction credibility scale is proposed in this paper. The method is to take the multifractal singular spectrum as the prediction parameter and use the Smoothness Priors Approach (SPA) method to obtain the singular spectrum parameters of different components, and construct the phase space reconstruction dynamic modeling domains. It enables the prediction model to reflect the real-time characteristics of the dynamics evolution of complex systems and highlights the independent influence of each component on the prediction. Meanwhile, the information entropy saturation principle is introduced into the K-Nearest Neighbor (KNN) model to establish the improved K neighborhood dynamic non-parametric prediction model based on the maximum prediction credibility scale, which improves the credibility of the prediction results. Finally, a complete SPA&PSR_KNN prediction algorithm is proposed. Through example validation and error analysis, compared with KNN, BP, and SVM, it can be seen that the prediction results of spectral characteristic parameters obtained by this algorithm have smaller error and higher reliability, and faster operation speed. Thus, the prediction of vibration signal time series of reciprocating compressor is realized.

The verification of mathematical models for multistage reciprocating compressors is crucial for ensuring their accuracy and reliability. In this study, we used different machine learning (ML) models to verify the results of MATLAB-based models of single-stage reciprocating compressors, multistage reciprocating compressors without intercoolers, and multistage reciprocating compressors with intercoolers to simulate the real-world operating conditions of a reciprocating compressor. The verification focuses on key performance indicators, such as the pressure–volume (PV) graph, outlet temperature graph, volumetric efficiency, and pressure ratio graph. The MATLAB model computes thermodynamic parameters, such as the power required, outlet pressure, and outlet temperature for various operating conditions. The MATLAB model produced the following results for single-stage compressor: the outlet pressure increased by 1.6 times the inlet pressure of the compressor, the volume reduced by 20% of the volume at the inlet of the single-stage compressor, and the outlet temperature increased by 30% of the inlet temperature. In the case of a multistage compressor without an intercooler, the outlet pressure increased by about 3.3–3.6 times the inlet pressure of the compressor; the volume reduced by 60% of the volume at the inlet, and the outlet temperature increased by 35% in comparison to the inlet temperature of the multistage compressor without an intercooler. Subsequently, in the case of a multistage compressor with an intercooler at the first stage of compression, the pressure increased by three times the inlet pressure; at the second stage of compression, the pressure increased by six times the inlet pressure of the compressor, the volume was reduced by approximately 80%, and the intercooler maintained the increase in outlet temperature by 30%, limiting it and preventing excessive expansion of air in the compressor and increasing the efficiency of the compressor by 12% in comparison to the multistage compressor without an intercooler. In addition, the results generated by all the machine learning models used in the study were in correlation with the results generated by the MATLAB model for all three compressors, with an accuracy of approximately 90% or more for almost all the models implemented for prediction. By comparing the predicted outputs from the ML model with the MATLAB-generated results, the accuracy and consistency of the simulation were assessed. This study aims to bridge the gap between traditional mathematical modeling and modern data-driven validation techniques to ensure robustness in compressor performance predictions.