Intrinsic Mode Function Components Research Articles

A novel rolling bearing fault diagnosis method based on parameter optimization variational mode decomposition with feature weighted reconstruction and multi-target attention convolutional neural networks under small samples.

To enhance the precision of rolling bearing fault diagnosis, an intelligent hybrid approach is proposed in this paper for signal processing and fault diagnosis in small samples. This approach is based on advanced techniques, combining parameter optimization variational mode decomposition weighted by multiscale permutation entropy (MPE) with maximal information coefficient and multi-target attention convolutional neural networks (MTACNN). First, an improved variational mode decomposition (VMD) is developed to denoise the raw signal. The whale optimization algorithm was used to optimize the penalty factor and mode component number in the VMD algorithm to obtain several intrinsic mode functions (IMFs). Second, separate MPE calculations are performed for both the raw signal and each of the IMF components obtained from the VMD decomposition; the results are used to calculate the maximum information coefficient (MIC). Subsequently, each MIC is normalized and converted to a weight coefficient for signal reconstruction. Ultimately, the reconstructed signals serve as input to the MTACNN for diagnosing rolling bearing faults. Results demonstrate that the signal processing approach exhibits superior noise reduction capability through simple processing. Furthermore, compared to several similar approaches, The method proposed for fault diagnosis achieves superior performance levels in the fault pattern recognition target and the fault severity recognition target.

VWM-DCRNN: A Method of Combining Signal Processing With Deep Learning for Fault Diagnosis in Single-Phase PWM Rectifier

Based on variational mode decomposition and dual model of convolutional recurrent neural network (VMD-DCRNN), a novel diagnosis method is proposed to discover the faults of IGBTs, diodes and series resonant circuit in single-phase pulse width modulation (PWM) AC-DC rectifier, an important part of traction power supply system of high-speed railway. By virtue of the combination of signal processing and deep learning schemes, the multi-scale feature information for fault diagnosis is extracted by regarding the input current of the rectifier and the voltage of dc side as the original signal. More clearly, VMD is adopted to decompose the original signal to a series of intrinsic mode function components (IMFs). Then, the submodel of current is designed to detect the fault types of IGBTs and diodes. Meanwhile, the submodel of voltage is established to identify the fault types of series resonant circuit. These IMFs are fed into DCRNN consisting of the two submodels for training and testing. Finally, the features extracted from the two submodels are integrated and converted to label space to complete fault diagnosis. Experimental results show that the proposed VMD-DCRNN algorithm is superior to the single-channel models, reaching 96.27%.

Noise suppression in the reconstructed image of digital holography based on the BEMDV method using improved particle swarm optimization.

In digital holography, the speckle noise caused by the coherent nature of the light source and the light scattering generated by the light path system degrade the quality of the reconstructed image seriously. Therefore, in this paper, we propose what we believe to be is a novel noise reduction method combining bidimensional empirical mode decomposition (BEMD) with the variational method, termed BEMDV. The reconstructed image is first decomposed into a series of bidimensional intrinsic mode function (BIMF) components with different frequencies using the BEMD method, and then a certain number of BIMF components are selected for noise reduction by the variational method. An improved particle swarm optimization algorithm is adopted to optimize the key parameters of the proposed method, so as to further improve its noise reduction performance. A reflective off-axis digital holographic imaging system is used to collect the holograms of the coin and optical resolution plate, and the experimental research on noise reduction is carried out. The results with qualitative and quantitative analyses show that the proposed method achieves a better performance on noise reduction and detail preservation than other general methods, enormously enhancing the image quality of holographic reconstruction.

A New Hybrid Forecasting Model Based on Dual Series Decomposition with Long-Term Short-Term Memory

In recent years, ozone (O3) has gradually become the primary pollutant plaguing urban air quality. Accurate and efficient ozone prediction is of great significance to the prevention and control of ozone pollution. The air quality monitoring network provides multisource pollutant concentration monitoring data for ozone prediction, but ozone prediction based on multisource monitoring data still faces the challenges of each station’s series of data. Aiming at the problems of low prediction accuracy and low computational efficiency in traditional atmospheric ozone concentration prediction, ozone concentration prediction using dual series decomposition was proposed by variational mode decomposition (VMD), ensemble empirical mode decomposition (EEMD), and long short-term memory (LSTM). First, the historical data series of Nanjing air quality monitoring stations is decomposed by VMD, and then the EEMD algorithm is applied to the residual of VMD to obtain several characteristic intrinsic mode function (IMF) components; each characteristic IMF component is trained by LSTM to obtain the prediction result of each component, and then the final result can be obtained by linear superposition. The proposed method achieved the best results with R2 = 99%, MSE = 5.38, MAE = 4.54, and MAPE = 3.12. Because LSTM has strong adaptive learning ability and good memory function, it has the learning advantage of long-term memory for long-term data, and the prediction results are more accurate. According to the data, the proposed method is superior to the baseline models in terms of statistical metrics. As a result, the proposed hybrid method can serve as a reliable model for ozone forecasting.

A novel deep learning carbon price short-term prediction model with dual-stage attention mechanism

Carbon price prediction can help participants keep abreast of carbon market dynamics and develop trading strategies. It is challenging for statistical models to accurately capture the nonlinear characteristics of the carbon pricing, and machine learning methods need sophisticated artificial feature engineering. To successfully address these drawbacks, our research suggests a carbon price forecasting model built on a deep learning architecture. Complete Ensemble Empirical Mode Decomposition with Adaptive Noise decomposes historical price to obtain Intrinsic Mode Function and Principal Component Analysis reduces the dimensionality of each influential factor. Dual-Stage Attention-Based Recurrent Neural Network, a Seq2Seq model, made up of an encoder with feature attention and a decoder with temporal attention, is employed to predicted price of the Hubei Carbon Emissions Allowance. The dual-attention mechanism enables preprocessing to be done adaptively and more effectively than manual processing. As shown by statistical analysis and grey correlation analysis, Hubei Carbon Emissions Allowance has a high autocorrelation, and the carbon market, energy and industry, economy, and environment have high to low correlations on it. The accuracy metrics of this framework, Mean Absolute Error = 0.75, Mean Absolute Percentage Error = 1.59 and Root Mean Squared Error = 1.28, are lower than compared models.

An AQI decomposition ensemble model based on SSA-LSTM using improved AMSSA-VMD decomposition reconstruction technique

Air quality index (AQI) is a key index for monitoring air pollution and can be used as guide for ensuring good public health. Accurate AQI prediction allows timely control and management of air pollution. In this study, a new integrated learning model was constructed to predict AQI. A smart reverse learning approach based on AMSSA was utilized to increase the diversity of populations, and an improved AMSSA (IAMSSA) was established. The optimum parameters with penalty factor α and mode number K of VMD were obtained using IAMSSA. The IAMSSA-VMD was used to decompose nonlinear and non-stationary AQI information series into several regular and smooth sub-sequences. The Sparrow Search Algorithm (SSA) was used to determine the optimum LSTM parameters. The results showed that: (1) IAMSSA exhibits faster convergence and higher accuracy and stability using simulation experiments compared with seven conventional optimization algorithms in 12 test functions. (2) IAMSSA-VMD was used to decompose the original air quality data results in multiple uncoupled intrinsic mode function (IMF) components and one residual (RES). An SSA-LSTM model was built for each IMF and one RES component, which effectively extracted the predicted values. (3) LSTM, SSA-LSTM, VMD-LSTM, VMD-SSA-LSTM, AMSSA-VMD-SSA-LSTM, and IAMSSA-VMD-SSA-LSTM models were used for prediction of AQI based on data from three cities (Chengdu, Guangzhou, and Shenyang). IAMSSA-VMD-SSA-LSTM exhibited the optimal prediction performance with MAE, RMSE, MAPE, and R2 of 3.692, 4.909, 6.241, and 0.981, respectively. (4) Generalization outcomes revealed that the IAMSSA-VMD-SSA-LSTM model had optimal generalization ability. In summary, the decomposition ensemble model proposed in this study has higher prediction accuracy, improved fitting effect and generalization ability compared with other models. These properties indicate the superiority of the decomposition ensemble model and provides a theoretical and technical basis for prediction of air pollution and ecosystem restoration.

Study on Life Prediction Method of Ball Screw Base on Constructed Degradation Feature and IGWO-BiLSTM

Regarding the problem of reduced remaining useful life (RUL) due to wear of the ball screw in the feed system of CNC (computer numerical control) machine tools, a prediction method based on constructing the degradation feature vector of the signal data and the improved gray-wolf optimization with bidirectional long short-term memory (IGWO-BiLSTM) neural network regression model is proposed. Firstly, a time-domain analysis and the complete ensemble empirical mode decomposition with adaptive noise analysis (CEEMDAN) were carried out based on the collected life cycle signal data of a ball screw. The time-domain feature vector and the energy feature vector of each IMF (intrinsic mode function) component after CEEMDAN decomposition were constructed. The Pearson correlation coefficient was used to filter feature vectors and construct the multivariate feature vector. Secondly, this paper improves the traditional gray wolf optimization algorithm, adds a search strategy based on dimension learning, and combines the improved algorithm with the BiLSTM model, based on the IGWO-BiLSTM theory. A regression model between feature vectors and the remaining life of a ball-screw system was established. Finally, the prediction model was established according to the proposed method and compared with the other five neural network models: LSTM, BiLSTM, BO-LSTM (Bayesian optimization of LSTM), BO-BiLSTM, and IGWO-LSTM. The results indicate that this method has high accuracy and good generalization ability for predicting the remaining life of a ball-screw system.

A Hybrid Forecast Model of EEMD-CNN-ILSTM for Crude Oil Futures Price

Crude oil has dual attributes of finance and energy. Its price fluctuation significantly impacts global economic development and financial market stability. Therefore, it is necessary to predict crude oil futures prices. In this paper, a hybrid forecast model of EEMD-CNN-ILSTM for crude oil futures price is proposed, which is based on Ensemble Empirical Mode Decomposition (EEMD), Convolutional Neural Network (CNN), and Improved Long Short-Term Memory (ILSTM). ILSTM improves the output gate of Long Short-Term Memory (LSTM) and adds important hidden state information based on the original output. In addition, ILSTM adds the learning of cell state at the previous time in the forget gate and input gate, which makes the model learn more fully from historical data. EEMD decomposes time series data into a residual sequence and multiple Intrinsic Mode Functions (IMF). Then, the IMF components are reconstructed into three sub-sequences of high-frequency, middle-frequency, and low-frequency, which are convenient for CNN to extract the input data’s features effectively. The forecast accuracy of ILSTM is improved efficiently by learning historical data. This paper uses the daily crude oil futures data of the Shanghai Energy Exchange in China as the experimental data set. The EEMD-CNN-ILSTM is compared with seven prediction models: Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), LSTM, ILSTM, CNN-LSTM, CNN-ILSTM, and EEMD-CNN-LSTM. The results of the experiment show the model is more effective and accurate.

A Rolling Bearing Fault Diagnosis Method Based on the WOA-VMD and the GAT.

In complex industrial environments, the vibration signal of the rolling bearing is covered by noise, which makes fault diagnosis inaccurate. In order to overcome the effect of noise on the signal, a rolling bearing fault diagnosis method based on the WOA-VMD (Whale Optimization Algorithm-Variational Mode Decomposition) and the GAT (Graph Attention network) is proposed to deal with end effect and mode mixing issues in signal decomposition. Firstly, the WOA is used to adaptively determine the penalty factor and decomposition layers in the VMD algorithm. Meanwhile, the optimal combination is determined and input into the VMD, which is used to decompose the original signal. Then, the Pearson correlation coefficient method is used to select IMF (Intrinsic Mode Function) components that have a high correlation with the original signal, and selected IMF components are reconstructed to remove the noise in the original signal. Finally, the KNN (K-Nearest Neighbor) method is used to construct the graph structure data. The multi-headed attention mechanism is used to construct the fault diagnosis model of the GAT rolling bearing in order to classify the signal. The results show an obvious noise reduction effect in the high-frequency part of the signal after the application of the proposed method, where a large amount of noise was removed. In the diagnosis of rolling bearing faults, the accuracy of the test set diagnosis in this study was 100%, which is higher than that of the four other compared methods, and the diagnosis accuracy rate of various faults reached 100%.

Hybrid Prediction Model Based on Decomposed and Synthesized COVID-19 Cumulative Confirmed Data

Since 2020, COVID-19 has repeatedly arisen around the world, which has had a significant impact on the global economy and culture. The prediction of the COVID-19 epidemic will help to deal with the current epidemic and similar risks that may arise in the future. So, this paper proposes a hybrid prediction model based on particle swarm optimization variational mode decomposition (PSO-VMD), Long Short-Term Memory Network (LSTM) and AdaBoost algorithm. To address the issue of determining the optimal number of modes K and the penalty factor (α) in the variational mode decomposition (VMD), an adaptive value for particle swarm optimization (PSO) is proposed. Specifically, the weighted average sample entropy of the relevant coefficients is utilized to determine the adaptive value. First, the epidemic data are decomposed into multiple modal components, known as intrinsic mode functions (IMFs), using PSO-VMD. These components, along with policy-based factors, are integrated to form a multivariate forecast dataset. Next, each IMF is predicted using AdaBoost-LSTM. Finally, the prediction results of all the IMF components are reconstructed to obtain the final prediction result. Our proposed method is validated by the cumulative confirmed data of Hubei and Hebei provinces. Specifically, in the case of cumulative confirmation data, the coefficient of determination (R2) of the mixed model is increased compared to the control model, and the average mean absolute error (MAE) and root mean square error (RMSE) decreased. The experimental results demonstrate that the VMD–AdaBoost–LSTM model achieves the highest prediction accuracy, thereby offering a new approach to COVID-19 epidemic prediction.

Prediction method of PM2.5 concentration based on decomposition and integration

With the acceleration of urbanization leading to a general decrease in air quality, accurate PM2.5 concentration prediction is of the utmost practical meaning for the control and prevention of air pollution in the region. Therefore, a new hybrid prediction model for PM2.5 concentration based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), approximate entropy (ApEn), variational mode decomposition optimized by capuchin search algorithm (CVMD), long short-term memory optimized by pelican optimization algorithm (POA-LSTM) and error correction (EC), named CEEMDAN-ApEn-CVMD-POA-LSTM-EC, is proposed. First, CEEMDAN is used to acquire a limited amount of intrinsic mode functions (IMFs). Second, calculate ApEn value for each IMF component, and divide each IMF component into high-complexity and low-complexity components by the size of ApEn values. Third, variational mode decomposition optimized by capuchin search algorithm (CVMD), named CVMD, is proposed. CVMD is used as a secondary decomposition method to further decompose high-complexity components adaptively into a finite number of IMFs. Fourth, long short-term memory optimized by pelican optimization algorithm, named POA-LSTM, is proposed. POA-LSTM predicts all IMF components, and the results of their predictions are combined to generate the original prediction results. Final, error sequence is decomposed and predicted again by the EC module CVMD-POA-LSTM to obtain prediction results of error sequence, and final prediction results are acquired by combining original prediction results and prediction results of error sequence. The datasets in Beijing, Shanghai, and Xi'an were selected for simulation experiments to demonstrate the superiority of the proposed model. Taking Beijing as an example, RMSE, MAE, MAPE and R2 values are 1.9947, 1.5577, 0.1157 and 0.9947, which are superior to other comparison models and have the best performance.

A Novel Method to the Aging Feature Extraction of Viscoelastic Sandwich Structures

The viscoelastic sandwich structure exhibits highly nonlinear dynamic characteristics, and minimal changes in signal caused by aging state alterations, thus posing a challenge for extracting its aging characteristics. A method is proposed for extracting aging features from viscoelastic sandwich structures using variational mode decomposition (VMD) and permutation entropy (PE). First, the original dynamic response signal is decomposed by VMD to acquire several intrinsic mode functions (IMF). Then the permutation entropy characteristics of each IMF are calculated. The research results show that there are obvious differences in the distribution of permutation entropy corresponding to each IMF component, which indicates that the permutation entropy feature extracted based on the variational modal decomposition is more susceptive to the change of the aging state of the structure, thus verifying the availability of this method for feature extraction.

High-G MEMS Accelerometer Calibration Denoising Method Based on EMD and Time-Frequency Peak Filtering.

In order to remove noise generated during the accelerometer calibration process, an accelerometer denoising method based on empirical mode decomposition (EMD) and time-frequency peak filtering (TFPF) is proposed in this paper. Firstly, a new design of the accelerometer structure is introduced and analyzed by finite element analysis software. Then, an algorithm combining EMD and TFPF is proposed for the first time to deal with the noise of the accelerometer calibration process. Specific steps taken are to remove the intrinsic mode function (IMF) component of the high frequency band after the EMD decomposition, and then to use the TFPF algorithm to process the IMF component of the medium frequency band; meanwhile, the IMF component of the low frequency band is reserved, and finally the signal is reconstructed. The reconstruction results show that the algorithm can effectively suppress the random noise generated during the calibration process. The results of spectrum analysis show that EMD + TFPF can effectively protect the characteristics of the original signal and that the error can be controlled within 0.5%. Finally, Allan variance is used to analyze the results of the three methods to verify the filtering effect. The results show that the filtering effect of EMD + TFPF is the most obvious, being 97.4% higher than the original data.

Ensemble Empirical Mode Decomposition and a Long Short-Term Memory Neural Network for Surface Water Quality Prediction of the Xiaofu River, China

Water quality prediction is an important part of water pollution prevention and control. Using a long short-term memory (LSTM) neural network to predict water quality can solve the problem that comprehensive water quality models are too complex and difficult to apply. However, as water quality time series are generally multiperiod hybrid time series, which have strongly nonlinear and nonstationary characteristics, the prediction accuracy of LSTM for water quality is not high. The ensemble empirical mode decomposition (EEMD) method can decompose the multiperiod hybrid water quality time series into several simpler single-period components. To improve the accuracy of surface water quality prediction, a water quality prediction model based on EEMD–LSTM was developed in this paper. The water quality time series was first decomposed into several intrinsic mode function components and one residual item, and then these components were used as the input of LSTM to predict water quality. The model was trained and validated using four water quality parameters (NH3-N, pH, DO, CODMn) collected from the Xiaofu River and compared with the results of a single LSTM. During the validation period, the R2 values when using LSTM for NH3-N, pH, DO and CODMn were 0.567, 0.657, 0.817 and 0.693, respectively, and the R2 values when using EEMD–LSTM for NH3-N, pH, DO and CODMn were 0.924, 0.965, 0.961 and 0.936, respectively. The results show that the developed model outperforms the single LSTM model in various evaluation indicators and greatly improves the model performance in terms of the hysteresis problem. The EEMD–LSTM model has high prediction accuracy and strong generalization ability, and further development may be valuable.

Research on the health status evaluation method of rolling bearing based on EMD‐GA‐BP

AbstractTo more accurately evaluate the health state of rolling bearings, this paper proposes a health status evaluation method based on empirical pattern decomposition, genetic algorithm and BP neural network. Firstly, the vibration signal is decomposed by empirical mode decomposition (EMD) and the time domain features of each intrinsic mode function (IMF) component are extracted, and the signal‐to‐noise ratio (Snr) of the signal is improved effectively. Then, the initial threshold and weight of BP neural network are optimized by genetic algorithm, which effectively improves the Snr of the signal. Finally, the extracted features are input into the optimized BP neural network to realize the identification of different states of the bearing. The effectiveness of the method has been effectively verified in the bearing data of Case Western Reserve University bearing dataset and it has higher accuracy and robustness than other common evaluation methods.

Combined noise reduction and DOA estimation algorithm for MEMS vector hydrophone based on variational mode decomposition

PurposeThis paper aims to solve the problem that strong noise interference seriously affects the direction of arrival (DOA) estimation in complex underwater acoustic environment. In this paper, a combined noise reduction algorithm and micro-electro-mechanical system (MEMS) vector hydrophone DOA estimation algorithm based on singular value decomposition (SVD), variational mode decomposition (VMD) and wavelet threshold denoising (WTD) is proposed.Design/methodology/approachFirstly, the parameters of VMD are determined by SVD, and the VMD method can decompose the signal into multiple intrinsic mode functions (IMFs). Secondly, the effective IMF component is determined according to the correlation coefficient criterion and the IMF less than the threshold is processed by WTD. Then, reconstruction is carried out to achieve the purpose of denoising and calibration baseline drift. Finally, DOA estimation is achieved by the combined directional algorithm of preprocessed signal.FindingsSimulation and field experiments results show that the algorithm has good noise reduction and baseline drift correction effects for nonstationary underwater signals, and high-precision azimuth estimation is realized.Originality/valueThis research provides the basis for MEMS hydrophone detection and positioning and has great engineering significance in underwater detection system.

Fault location of flexible grounding distribution system based on multivariate modes and kurtosis calibration

Aiming at the problems of large fault location errors when the traditional traveling wave fault location is applied to flexible ground distribution systems. This paper proposed the fault location of flexible grounding distribution system based on multivariate modes and kurtosis calibration. Firstly, a disturbance signal is generated by putting a small resistor in parallel. This signal reaches the fault point and undergoes a sudden change, generating an aerial mode traveling wave signal. Secondly, it used the multivariate variational mode decomposition algorithm to decompose the aerial mode current and extracts the fault features. Then, the discrete kurtosis value is calculated for the highest frequency intrinsic mode function component. The moment of maximum kurtosis is the arrival time of the aerial mode current. Finally, it adopted the head-end detection device to calculate the fault distance. For the complex topology of the flexible ground distribution systems, the localization equation of the overhead line, cable line, and hybrid lines are studied, and the pseudo-fault points are excluded by adding auxiliary devices at the branch end. The simulation results demonstrate that the proposed method can accurately locate faults and is not affected by the fault's initial phase angle, transition resistance, and location.

A novel prediction model based on decomposition-integration and error correction for COVID-19 daily confirmed and death cases

Coronavirus disease (COVID-19) has infected billion people around the world and affected the economy, but most countries are considering reopening, so the COVID-19 daily confirmed and death cases have increased greatly. It is very necessary to predict the COVID-19 daily confirmed and death cases in order to help every country formulate prevention policies. To enhance the prediction performance, this paper proposes a prediction model based on improved variational mode decomposition by sparrow search algorithm (SVMD), improved kernel extreme learning machine by Aquila optimizer algorithm (AO-KELM) and error correction idea, named SVMD-AO-KELM-error for short-term prediction of COVID-19 cases. Firstly, to solve mode number and penalty factor selection of variational mode decomposition (VMD), an improved VMD based on sparrow search algorithm (SSA), named SVMD, is proposed. SVMD decomposes the COVID-19 case data into some intrinsic mode function (IMF) components and residual is considered. Secondly, to properly selected regularization coefficients and kernel parameters of kernel extreme learning machine (KELM) and improve the prediction performance of KELM, an improved KELM by Aquila optimizer (AO) algorithm, named AO-KELM, is proposed. Each component is predicted by AO-KELM. Then, the prediction error of IMF and residual are predicted by AO-KELM to correct prediction results, which is error correction idea. Finally, prediction results of each component and error prediction results are reconstructed to get final prediction results. Through the simulation experiment of the COVID-19 daily confirmed and death cases in Brazil, Mexico, and Russia and comparison with twelve comparative models, simulation experiment gives that SVMD-AO-KELM-error has best prediction accuracy. It also proves that the proposed model can be used to predict the pandemic COVID-19 cases and offers a novel approach for COVID-19 cases prediction.

Research on milling chatter identification of thin-walled parts based on incremental learning and multi-signal fusion

Chatter is a kind of self-excited vibration that often occurs in the milling process of thin-walled parts, which has become the main factor restricting production efficiency and quality. Due to the occurrence of chatter, the signal becomes more complex and unstable. In order to realize milling chatter detection of thin-walled parts, the method of multi-sensor signal fusion is used. A chatter detection method based on variational mode decomposition (VMD) and nonlinear dimensionless index is proposed by analyzing the characteristics of signals in time–frequency domain. Firstly, a series of intrinsic mode function (IMF) components are obtained by decomposing force and acceleration signals with VMD. When chatter occurs, the energy is transferred to the chatter frequency band. Each IMF signal’s nonlinear energy entropy (EE) is extracted to construct the feature vector. A support vector machine chatter identification model based on multi-sensor signal fusion is established. To solve the problem of model incremental updating, supervised learning and unsupervised learning are combined to provide a method for chatter detection.

Fault diagnosis of gearbox based on adaptive wavelet de-noising and convolution neural network

In this paper, in order to solve the problem that it is difficult to carry out accurate fault diagnosis for gearbox under noise environment, complete ensemble imperial mode decomposition with adaptive noise analysis (CEEMDAN) is used to solve the sample entropy of the original signal and each intrinsic mode function (IMF) component, adaptive wavelet is adopted to decompose and reconstruct IMF with large sample entropy for noise reduction, and first layer wide convolution kernel deep convolution neural network (WDCNN) and long short term memory (LSTM) are used to extract the basic digital features of the reconstructed signal and the correlation features between the features. Therefore, a new fault diagnosis method for gearbox under noise environment is proposed. Taking the public data set of Jiangsu Qiangpeng Diagnostic Engineering Co., Ltd as the research object, the experiments were carried out with the method proposed in this paper. The experimental results show that the proposed method has high accuracy and strong anti-noise ability. Under the environment of no noise and low noise, the fault diagnosis accuracy of the gearbox is 100%; even if the signal to noise ratio is −4 dB, the fault diagnosis accuracy of the gearbox can still reach 99.97%. Therefore, this paper provides a method support for gearbox fault diagnosis under noise environment.