Motor cooling control system with fault diagnosis function

Abstract

The invention discloses a motor cooling control system with a fault diagnosis function, and relates to the field of motor cooling control, and the system comprises a water pump, a water pump controller, a pipeline, a plurality of sensors, and a fault diagnosis module. Early warning of faults such as pipeline blockage, pipeline leakage, water pump degradation and water pump failure is achieved, the self-adaptive compensation function is achieved, control parameters can be automatically adjusted when the performance of part of assemblies is degraded, the optimal working state of the system is maintained, and the overall reliability is improved. In order to realize the accuracy of a prediction result, blind source separation is carried out on a water pump vibration signal and a pipeline vibration signal based on an independent component analysis method, clustering sampling is carried out on sample data through a clustering algorithm, sample redundancy is reduced, meanwhile, periodic changes of motor temperature are considered when the water pump degradation degree is predicted, and the prediction accuracy is improved. And the prediction accuracy is improved.

Description

Technical Field

[0001] The invention relates to the field of motor cooling control, in particular to a motor cooling control system with a fault diagnosis function. Background Art

[0002] The motor will generate a lot of heat during operation. If the cooling control is not carried out in time, the motor temperature will be too high, which will affect its performance and life. Therefore, a reasonable cooling control method is an indispensable part of motor design. Water cooling is one of the commonly used motor cooling methods. It is to set up water cooling pipes inside or outside the motor and use circulating water to absorb and take away the heat generated by the motor. The water cooling method has excellent heat dissipation effect and is suitable for high-power and high-heat motors. However, the water cooling system is relatively complex and prone to failure. If the fault cannot be eliminated in advance, it will cause serious consequences such as motor overheating.

[0003] In the prior art, the motor cooling system is usually inspected manually periodically, which is inefficient and cannot detect faults before they occur or in the early stages, and cannot predict and handle faults. Summary of the invention

[0004] In order to solve the technical problem of fault prediction of a motor cooling control system in the prior art, the present invention provides a motor cooling control system with a fault diagnosis function.

[0005] The present invention is achieved through the following technical solutions: A motor cooling control system with a fault diagnosis function, comprising: a water pump, a water pump controller, a pipeline, a plurality of vibration sensors, a flow sensor, a pressure difference sensor, a temperature sensor, and a fault diagnosis module; The vibration sensor is arranged on the water pump and the pipeline; the flow sensor and the pressure difference sensor are arranged in the pipeline; the temperature sensor is arranged on the cooled motor; the water pump controller controls the water pump; The fault diagnosis module realizes the fault prediction of the motor cooling control system through the following steps: S1: Signal acquisition, obtaining water pump current, speed, vibration signal, motor temperature signal, pipeline vibration, flow rate, and pressure difference; S2: Process the collected signals and extract features; S3: Classify the motor cooling control system status based on K-means clustering algorithm combined with LSTM model; S4: Motor cooling control system status judgment; if the current motor cooling control system water pump performance is degraded, but there is no water pump failure, pipeline blockage and pipeline leakage, then go to step S5, otherwise go to S6; S5: Calculate the pump degradation degree and perform adaptive compensation; S6: Predict system failure probability based on the competitive failure model and issue early warning.

[0006] Furthermore, the processing of the collected signals includes blind source separation of the water pump vibration signal and the pipeline vibration signal based on an independent component analysis method.

[0007] Furthermore, the classification results of the motor cooling control system status include normal, water pump performance degradation, water pump failure, pipe blockage and pipe leakage; among which, water pump failure, pipe blockage and pipe leakage are divided into three levels of mild, medium and severe according to the severity.

[0008] Furthermore, the step S3 further includes: S31: Clustering sample data based on K-means clustering algorithm; S32: Determine training and verification samples according to the clustering results; S33: Establish LSTM model and train it; S34: Classify the input data based on the trained LSTM model to obtain a classification result of the motor cooling control system state.

[0009] Further, the determining of the training and validation samples according to the clustering results includes performing mixed sampling on the clustering results to determine the training and validation samples, wherein the mixed sampling combines stratified sampling and random sampling; Stratified sampling obtains sampling results for N cluster classification samples and discrete samples respectively, and the expression is as follows: ; in, is the sample set of the i-th cluster center, is the extraction ratio, and L is the discrete sample set.

[0010] Furthermore, Determined by: ; in, is the adjustment coefficient, is the Davis-Boulding index of the ith cluster, To set the Davis-Boulding index threshold, Is a set constant.

[0011] Furthermore, the step S5 comprises: S51: Calculate the degradation degree of the water pump; S52: When the water pump degradation degree reaches a certain threshold, the water pump control parameters are calculated based on the adaptive control algorithm, and the water pump control parameters are sent to the water pump controller to achieve adaptive adjustment control.

[0012] Further, the calculating the water pump degradation degree includes: Obtain the time series of water pump current, pressure and flow; predict the time series of water pump current, pressure and flow based on the autoregressive integrated moving average model of periodic correlation; calculate the water pump degradation degree according to the time series prediction results.

[0013] Furthermore, the adaptive adjustment control includes: An adaptive adjustment model is constructed based on the FNN network to obtain the degradation degree of the water pump as the input parameter of the adaptive adjustment model; the degradation degree prediction result is input into the adaptive adjustment model to obtain the control parameters of the water pump motor output by the adaptive adjustment model.

[0014] Furthermore, the step S6 includes: S61: calculating the system reliability ; in, is the system reliability when only the pump fails during time t and there is no sudden failure factor. is the system reliability under the influence of sudden failure factors within time t; S62: Calculate the predicted system failure probability: ; in, is the system density function, and its expression is as follows: .

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes early warning of pipeline blockage, pipeline leakage, water pump degradation, water pump failure and other faults, and has an adaptive compensation function. When the performance of some components is degraded, the control parameters can be automatically adjusted to maintain the optimal working state of the system and improve the overall reliability. In order to achieve the accuracy of the prediction results, the present invention performs blind source separation on the water pump vibration signal and the pipeline vibration signal based on the independent component analysis method, and clusters and samples the sample data through a clustering algorithm, combines mixed sampling to ensure the comprehensiveness and accuracy of the training sample data, and reduces sample redundancy. At the same time, in the prediction of the water pump degradation degree, the autoregressive integral sliding average model with periodic correlation is used for prediction, taking into account the periodic changes in the motor temperature, and improving the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a schematic diagram of a fault prediction process of a motor cooling control system according to an embodiment of the present application; Figure 2 It is a flow chart of a method for classifying the state of a motor cooling control system based on a K-means clustering algorithm combined with an LSTM model according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0018] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0019] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the form, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0020] A motor cooling control system with a fault diagnosis function, comprising a water pump, a water pump controller, a pipeline, a plurality of vibration sensors, a flow sensor, a pressure difference sensor, a temperature sensor, and a fault diagnosis module; The vibration sensor is arranged on the water pump and the pipeline; the flow sensor and the pressure difference sensor are arranged in the pipeline; the temperature sensor is arranged on the cooled motor; the water pump controller controls the water pump; like Figure 1 As shown, the fault diagnosis module realizes the fault prediction of the motor cooling control system through the following steps: S1: Signal acquisition, obtaining water pump current, speed, vibration signal, motor temperature signal, pipeline vibration, flow rate, and pressure difference; The water pump vibration signal is obtained by a vibration sensor arranged on the water pump; the pipeline vibration is obtained by a vibration sensor arranged on the pipeline; the motor temperature signal refers to the temperature of the cooled motor; S2: Process the collected signals and extract features, including: S21: signal preprocessing, including filtering, denoising and normalizing the collected signal; S22: performing blind source separation on the water pump vibration signal and the pipeline vibration signal; Since the vibrations of the water pump and the pipeline affect each other, the vibration signals obtained by the vibration sensors installed on the water pump and the vibration sensors installed on the pipeline are the result of the mutual influence of the two. In order to more accurately realize the subsequent signal analysis and processing, the two signals need to be separated and processed. The present invention restores the observed vibration signals received by the two vibration sensors into independent vibration source signals based on the independent component analysis method, including the following steps: a. Preprocess the acquired vibration sensor signal, including centering and whitening processing; b. Pre-separate the pre-processed vibration sensor signal through the convolution ICA algorithm to obtain the pre-separated signal , , corresponding to the original signal of water pump vibration and the original signal of pipeline vibration respectively; c. , After normalization, it is further transformed to the time-frequency domain through short-time Fourier transform to obtain , , estimate the binary mask and perform cepstrum smoothing; d. Mask value pair after cepstrum smoothing , To strengthen , ; e. Through the short-time Fourier inverse transform , Converted into pure isolated vibration source signal , , that is, the processed water pump vibration signal and pipeline vibration signal.

[0021] S23: feature extraction, including time domain and frequency domain feature extraction of water pump current, water pump vibration signal, and pipeline vibration signal; time domain feature extraction of water pump speed, motor temperature signal, pipeline flow, and pressure difference signal; S3: Classify the motor cooling control system status based on the K-means clustering algorithm combined with the LSTM model, such as Figure 2As shown, the classification results include normal, water pump performance degradation, water pump failure, pipeline blockage and pipeline leakage. Among them, water pump failure, pipeline blockage and pipeline leakage are divided into three levels according to the severity: slight, medium and severe.

[0022] S31: Clustering sample data based on K-means clustering algorithm; In a preferred embodiment, clustering includes the following steps: a. Import the sample data set into the list; the sample data set includes the collected signals and the extracted features; b. Construct a set of N cluster centers for a given data set, use the improved k-means algorithm based on the maximum and minimum principle to initialize the cluster centers, and then perform k-means clustering on each category of data, and finally cluster to obtain N optimal cluster centers; c. Calculate the Euclidean distance between two sample vectors; d. Create a matrix to store the cluster assignment results of each point, including the cluster index value and error, calculate the distance from the current sample to each cluster center, find the cluster center closest to it, and assign the sample to the cluster with the closest distance; e. After all samples are assigned, recalculate the centers of N clusters; f. Compare with the N cluster centers calculated last time. If the cluster center changes, go to step c. Otherwise go to step g; g. When the cluster center does not change, stop and output the clustering results; h. Merge the output clustering results and delete duplicate results to obtain the final set.

[0023] S32: Determine training and verification samples according to the clustering results; It includes performing mixed sampling on the clustering results to determine the training and validation samples, wherein the clustering results include N cluster classification samples and discrete samples; the mixed sampling combines stratified sampling and random sampling, and sets the proportion a% in the training and validation samples to be obtained by stratified sampling, and b% to be obtained by random sampling, and a%+b%=1.

[0024] In a preferred embodiment, stratified sampling obtains sampling results for N cluster classification samples and discrete samples respectively, and the expression is as follows: ; in, is the sample set of the i-th cluster center, is the extraction ratio, and L is the discrete sample set.

[0025] Optional, Determined by: ; in, is the adjustment coefficient, which is determined according to the actual situation. is the Davis-Boulding index of the ith cluster, To set the Davis-Boulding index threshold, Is a set constant.

[0026] The above sampling method determines sampling parameters according to the performance indicators of clustering, realizes a more comprehensive sampling method, and reduces the redundancy of the sampling data volume.

[0027] S33: Build and train the LSTM model, including: Encapsulate the sample data set and classification categories, construct a training set, establish a classification model, and determine the loss function; use the training set to train the classification model, and observe how the loss function value changes with the number of iterations until the classification accuracy requirements are met.

[0028] S34: Classify the input data based on the trained LSTM model to obtain the classification results of the motor cooling control system state. The classification results include normal, water pump performance degradation, water pump failure, pipeline blockage and pipeline leakage. Among them, water pump failure, pipeline blockage and pipeline leakage are divided into three levels according to the severity: slight, medium and severe.

[0029] S4: Motor cooling control system status judgment; if the current motor cooling control system water pump performance is degraded, but there is no water pump failure, pipeline blockage and pipeline leakage, then enter step S5, otherwise enter S6.

[0030] S5: Calculate the pump degradation degree and perform adaptive compensation; S51: Calculating the degradation degree of the water pump, specifically including the following steps: S511: Obtain the time series of water pump current, pressure and flow; S512: Predict the time series of water pump current, pressure and flow rate based on the autoregressive integral moving average model of periodic correlation; since the temperature change of the motor operation is periodic, the corresponding water pump control parameters and flow rate of the cooling system also change periodically. Therefore, the present invention predicts the time series of parameters based on the autoregressive integral moving average model of periodic correlation, and the model is expressed as follows: ; Where: is the time series value at time t; is the white noise sequence value at time t; is a constant term; is the delay operator; For the general Move backward in time s times, that is , and They are p-order autoregressive polynomial and q-order sliding average polynomial respectively; and They are P-order periodic autoregressive polynomial and Q-order periodic moving average polynomial with period s, respectively. The model contains 7 parameters, namely p, d, q, s, P, D, and Q. The process of determining these parameters is called model order determination. p, d, and q represent the order of autoregressive, differential, and moving average, respectively, while P, D, and Q represent the order of periodic autoregressive, differential, and moving average with period s.

[0031] The process of model establishment and prediction includes: data processing: observe whether the sequence is stable according to the time series diagram of the original data. If it is a non-stationary sequence, perform a differential transformation on it to make it stable; model parameter identification: identify the model type through the autocorrelation coefficient and preliminarily determine the order values ​​of p, d, q and P, D, Q; model identification and model diagnosis: select the most suitable model through the Akaike information criterion, model verification: use the verification set sample data to verify the optimal model; model prediction: use the optimal model to predict the water pump current, pressure, and flow time series.

[0032] S513: Calculating the water pump degradation degree according to the time series prediction result; Optionally, the pump degradation degree is calculated based on a supervised learning classifier.

[0033] S52: When the water pump degradation degree reaches a certain threshold, the water pump control parameters are calculated based on the adaptive control algorithm, and the water pump control parameters are sent to the water pump controller to achieve adaptive adjustment control. The specific steps are as follows: S521: Building an Adaptive Adjustment Model The model is constructed by an FNN network. The network structure includes five layers, namely, an input layer, a fuzzification layer, a rule reasoning layer, a synthesis layer, a defuzzification layer, and an output layer. The network membership function is expressed as follows: ; Among them, m is the center point, a is the width, and b is the slope.

[0034] S522: Obtaining the water pump degradation degree as an input parameter of the adaptive adjustment model; S523: Inputting the degradation prediction result into the adaptive adjustment model to obtain the water pump motor control parameters output by the adaptive adjustment model, including the modulation ratio, modulation index, duty cycle, phase offset and overmodulation of SVPWM.

[0035] S6: Predict system failure probability based on the competitive failure model and issue an early warning; including the following steps: S61: Calculation of system reliability ; in, is the system reliability when only the pump fails during time t and there is no sudden failure factor. is the system reliability under the influence of sudden failure factors within time t; S62: Calculate the predicted system failure probability: ; in, is the system density function, and its expression is as follows: 。

[0036] In this embodiment, early warning of pipeline blockage, pipeline leakage, water pump degradation, water pump failure and other faults is achieved, and it has an adaptive compensation function. When the performance of some components is degraded, the control parameters can be automatically adjusted to maintain the optimal working state of the system and improve the overall reliability. In order to achieve the accuracy of the prediction results, the present invention performs blind source separation on the water pump vibration signal and the pipeline vibration signal based on the independent component analysis method, and clusters the sample data through the clustering algorithm. It combines mixed sampling to ensure the comprehensiveness and accuracy of the training sample data and reduce sample redundancy. At the same time, in the prediction of the degradation degree of the water pump, the autoregressive integral sliding average model with periodic correlation is used for prediction, taking into account the periodic changes in the motor temperature, and improving the accuracy of the prediction.

[0037] The embodiments described above are only descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A motor cooling control system with a fault diagnosis function, characterized in that: include: Water pump, water pump controller, pipeline, several vibration sensors, flow sensor, differential pressure sensor, temperature sensor, fault diagnosis module; The vibration sensor is arranged on the water pump and the pipeline; the flow sensor and the pressure difference sensor are arranged in the pipeline; the temperature sensor is arranged on the cooled motor; the water pump controller controls the water pump; The fault diagnosis module realizes the fault prediction of the motor cooling control system through the following steps: S1: Signal acquisition, obtaining water pump current, speed, vibration signal, motor temperature signal, pipeline vibration, flow rate, and pressure difference; S2: Process the collected signals and extract features; S3: Classify the motor cooling control system status based on K-means clustering algorithm combined with LSTM model; S4: Motor cooling control system status judgment; if the current motor cooling control system water pump performance is degraded, but there is no water pump failure, pipeline blockage and pipeline leakage, then go to step S5, otherwise go to S6; S5: Calculate the pump degradation degree and perform adaptive compensation; S6: Predict system failure probability based on the competitive failure model and issue early warning.

2. The motor cooling control system with fault diagnosis function according to claim 1, characterized in that: The processing of the collected signals includes blind source separation of the water pump vibration signal and the pipeline vibration signal based on an independent component analysis method.

3. The motor cooling control system with fault diagnosis function according to claim 1, characterized in that: The classification results of the motor cooling control system status include normal, water pump performance degradation, water pump failure, pipe blockage and pipe leakage; wherein water pump failure, pipe blockage and pipe leakage are respectively divided into three levels of slight, medium and severe according to the severity.

4. The motor cooling control system with fault diagnosis function according to claim 3, characterized in that: The step S3 further comprises: S31: Clustering sample data based on K-means clustering algorithm; S32: Determine training and verification samples according to the clustering results; S33: Establish LSTM model and train it; S34: Classify the input data based on the trained LSTM model to obtain a classification result of the motor cooling control system state.

5. The motor cooling control system with fault diagnosis function according to claim 4, characterized in that: Determining the training and validation samples according to the clustering results includes performing mixed sampling on the clustering results to determine the training and validation samples, wherein the mixed sampling combines stratified sampling and random sampling; Stratified sampling obtains sampling results for N cluster classification samples and discrete samples respectively, and the expression is as follows: in, is the sample set of the i-th cluster center, is the extraction ratio, and L is the discrete sample set.

6. The motor cooling control system with fault diagnosis function according to claim 5, characterized in that: Determined by: in, is the adjustment coefficient, is the Davis-Boulding index of the ith cluster, To set the Davis-Boulding index threshold, Is a set constant.

7. The motor cooling control system with fault diagnosis function according to claim 1, characterized in that: The step S5 comprises: S51: Calculate the degradation degree of the water pump; S52: When the water pump degradation degree reaches a certain threshold, the water pump control parameters are calculated based on the adaptive control algorithm, and the water pump control parameters are sent to the water pump controller to achieve adaptive adjustment control.

8. The motor cooling control system with fault diagnosis function according to claim 6, characterized in that: The calculation of the water pump degradation degree comprises: Obtain the time series of water pump current, pressure and flow; predict the time series of water pump current, pressure and flow based on the autoregressive integrated moving average model of periodic correlation; calculate the water pump degradation degree according to the time series prediction results.

9. The motor cooling control system with fault diagnosis function according to claim 6, characterized in that: The adaptive adjustment control includes: An adaptive adjustment model is constructed based on the FNN network to obtain the degradation degree of the water pump as the input parameter of the adaptive adjustment model; the degradation degree prediction result is input into the adaptive adjustment model to obtain the control parameters of the water pump motor output by the adaptive adjustment model.

10. The motor cooling control system with fault diagnosis function according to claim 1, characterized in that: The step S6 includes: S61: calculating system reliability : in, is the system reliability when only the pump fails during time t and there is no sudden failure factor. is the system reliability under the influence of sudden failure factors within time t; S62: Calculate the predicted system failure probability: in, is the system density function, and its expression is as follows: 。

Images