Oil pump state detection system based on deep learning and detection method thereof

Abstract

The invention discloses an oil pump state detection technology, and aims to provide an oil pump state detection system based on deep learning and a detection method thereof, and the key points of the technical scheme are that the oil pump state detection system comprises the following modules: a data collection module used for collecting operation data of an oil pump in real time; the data preprocessing module is used for processing the collected original operation data; the deep learning model training module is used for training the preprocessed data through a back propagation algorithm by adopting a convolutional neural network architecture, so that the model can learn the characteristics of the normal state and the fault state of the oil pump; the state detection module is used for classifying the data by utilizing the trained deep learning model when monitoring the operation data of the oil pump in real time, outputting the current state of the oil pump and judging whether an abnormity or a potential fault exists or not; when the fault early warning module detects that the oil pump is abnormal or has a potential fault, an early warning signal is sent out in time; the method is suitable for the technical field of oil pump state detection.

Description

Technical Field

[0001] The present invention relates to an oil pump state detection technology, and more specifically, to an oil pump state detection system and a detection method thereof based on deep learning. Background Art

[0002] The oil pump is an important component in industrial equipment, and its operating status directly affects the stability and production efficiency of the entire equipment. However, traditional oil pump status detection mainly relies on manual inspections and regular maintenance, which is inefficient and difficult to detect potential faults in a timely manner. In recent years, with the rapid development of deep learning technology, its application in fault diagnosis and status detection has become more and more extensive. Therefore, developing an oil pump status detection system based on deep learning is of great significance to improving the operating efficiency and stability of the oil pump. Summary of the invention

[0003] In view of the shortcomings of the prior art, the object of the present invention is to provide an oil pump state detection system and a detection method thereof based on deep learning.

[0004] To achieve the above object, the present invention provides the following technical solution: a deep learning-based oil pump state detection system, comprising the following modules: Data acquisition module, used to collect the operation data of the oil pump in real time; The data preprocessing module is used to clean, extract features, and standardize the collected raw operating data to provide high-quality input data for the deep learning model; The deep learning model training module uses a convolutional neural network architecture to train the pre-processed data through a back-propagation algorithm, so that the model can learn the characteristics of the normal and fault states of the oil pump; The status detection module is used to classify the data using the trained deep learning model when monitoring the oil pump operation data in real time, and output the current status of the oil pump to determine whether there is an abnormality or potential fault; The fault warning module, based on the output results of the status detection module, will promptly issue a warning signal when an abnormality or potential fault in the oil pump is detected, so as to notify the maintenance personnel to take corresponding measures.

[0005] The present invention is further configured as follows: the data acquisition module includes but is not limited to a temperature sensor, a vibration sensor, a noise sensor, a pressure sensor, and a voltage and current sensor, and collects multi-dimensional operating data of the oil pump in real time through the temperature sensor, the vibration sensor, the noise sensor, the pressure sensor, and the voltage and current sensor, and transmits the operating data to a data preprocessing module.

[0006] The present invention is further configured as follows: the data preprocessing module includes the following processing steps: Data cleaning: remove missing values, outliers and duplicate data to ensure data accuracy; Feature extraction: Extract representative features for oil pump status detection from the raw data; Standardization: Normalize the data to make the data collected by different sensors uniform, so as to facilitate the training and reasoning of deep learning models.

[0007] The present invention is further configured as follows: the fault warning module includes an alarm system, and when an abnormality or potential fault of the oil pump is detected, the maintenance personnel are notified in time by sound and light alarm, SMS notification, email reminder or mobile APP.

[0008] The present invention is further configured as follows: the detection system also includes a remote monitoring module, which uploads the detection data and fault warning information to the cloud platform through the network for remote monitoring personnel to view and process.

[0009] A detection method of an oil pump state detection system based on deep learning, characterized in that it comprises the following steps: S1. Real-time data collection: The multi-dimensional operating data of the oil pump is collected in real time through sensors, including but not limited to the temperature, vibration, noise, pressure, voltage and current of the oil pump, and the frequency of data collection is set according to the actual situation to ensure real-time monitoring of the oil pump status; S2. Data transmission: The collected oil pump operation data is transmitted to the data preprocessing module through the communication network. The timeliness and accuracy of the data should be ensured during the data transmission process to prevent information delay or loss; S3. Data preprocessing: Preprocess the collected raw data: Data cleaning: remove missing values, outliers and duplicate data; Feature extraction: Extract representative features for oil pump status detection from the raw data; Data standardization: Normalize the data to facilitate the training and reasoning of deep learning models; S4. Deep learning model training: Use convolutional neural network to train the preprocessed data. During the training process, the convolutional neural network continuously adjusts parameters through the back propagation algorithm, learns the different characteristics of the oil pump under normal operation and fault conditions, and establishes a set of classification models, so as to accurately detect the status of new operation data; S5. Model verification and optimization: After model training is completed, the model is evaluated through the validation set to check the performance of the model in the actual data. If the model performance is found to be insufficient, further optimization is required; S6. Real-time status detection: The real-time collected oil pump operation data is input into the trained deep learning model, and the current operation status of the oil pump is judged through the model's reasoning process. The model outputs the status of the oil pump based on the input data features, which is usually "normal", "abnormal" or "potential fault"; S7, Fault warning trigger: When the oil pump status is detected as "abnormal" or "potential fault", the system will trigger the fault warning mechanism. The warning mechanism will determine whether to issue a warning signal based on the preset threshold to ensure that the fault can be discovered in time before it occurs; S8, Early warning notification and processing: When a fault or potential fault is detected, the system will promptly send early warning information to maintenance personnel through sound and light alarms, SMS notifications, email reminders or mobile APP. Maintenance personnel can take corresponding measures in time according to the early warning information to prevent further deterioration of the fault; S9, Fault analysis and repair: After receiving the warning information, the maintenance personnel will conduct a detailed inspection of the oil pump, analyze the cause of the fault, determine the fault type, and take appropriate repair measures. After the fault is repaired, the oil pump status will be re-tested to ensure the repair effect; S10. Data feedback and system optimization: After troubleshooting, maintenance personnel will feed back the operation and repair results to the system as new data samples to further improve the deep learning model, which will help improve the system's detection accuracy for similar faults in the future and optimize the performance of the overall monitoring system.

[0010] The present invention is further configured as follows: the detection method includes the following determination rules: When the temperature of the oil pump is greater than the preset threshold, if the vibration parameters are abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the vibration parameters of the oil pump exceed the normal range, if the noise level increases, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the oil pump current and voltage fluctuate unstably, if the pressure is abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the operating data of the oil pump conforms to the normal state mode, the monitoring continues and returns to S6 for state detection; When the oil pump temperature, vibration, noise, pressure, current, and voltage exceed the normal range at the same time, the fault warning will be triggered in S7. When the noise signal and vibration signal of the oil pump confirm each other, the fault warning of S7 is triggered; When the oil pump shows a gradual abnormal trend in long-term operation and the fault signs are not obvious, go to S6 for status detection; When no abnormality is detected in the running state of the oil pump, monitoring continues and returns to S6 for state detection.

[0011] The beneficial effects of the present invention are: 1. Compared with the prior art, the oil pump status detection system based on deep learning in the present invention can monitor the operating status of the oil pump in real time and identify its abnormalities and potential faults, greatly improving the operating safety and reliability of the oil pump. A large amount of oil pump operation data is trained and learned through convolutional neural networks, so as to accurately determine whether there is a problem with the oil pump. Compared with traditional manual inspections, the deep learning model can adaptively extract meaningful features from complex and multi-dimensional sensor data, avoiding the limitations of artificially set rules; the system can detect abnormalities in time and issue early warnings, greatly improving the accuracy and response speed of fault diagnosis, helping enterprises to take measures in the shortest time to avoid greater economic losses caused by fault expansion; in addition, traditional oil pump status monitoring and fault diagnosis usually rely on manual inspections and regular inspections, which are not only labor-intensive, but also unable to achieve all-weather, real-time monitoring. The present invention greatly reduces the dependence on manual inspections through automated data collection and real-time monitoring.

[0012] 2. The data acquisition module of the oil pump state detection system based on deep learning in the present invention can acquire the multi-dimensional operation data of the oil pump in real time and comprehensively by integrating multiple sensors (such as temperature, vibration, noise, pressure, voltage and current, etc.). The synergistic effect of these sensors ensures the comprehensiveness and accuracy of the collected data. Different states of the oil pump are usually accompanied by multiple changes. Multi-channel perception can provide rich input data for the deep learning model, thereby improving the accuracy of fault detection. In addition, the diversity and real-time nature of the sensors ensure timely monitoring of the oil pump state, and can accurately identify and warn of faults in the early stages, thereby reducing the impact of faults on production.

[0013] 3. In the present invention, the data preprocessing module provides high-quality and standardized data input for the deep learning model through multiple steps such as data cleaning, feature extraction and standardization. The data cleaning step helps to eliminate the interference of noise data, missing values ​​and outliers, and ensure the accuracy and effectiveness of the data. Feature extraction helps to extract highly representative features for oil pump status monitoring from complex raw data, such as frequency domain features, time domain features, etc., thereby enhancing the learning effect of the model. Standardization processing can eliminate the differences in data scales of different sensors, so that various types of data can be trained under the same standard, thereby improving the stability and accuracy of the model. Through these preprocessing steps, the detection accuracy and reliability of the entire system are significantly improved.

[0014] 4. The fault warning module monitors the status of the oil pump in real time and sends out warning signals in time when abnormalities or potential faults are found. Through various means such as sound and light alarms, SMS notifications, and email reminders, maintenance personnel can quickly receive warning information and take measures to prevent further development of the fault. This mechanism not only improves the response speed of oil pump failures, but also helps enterprises reduce losses caused by downtime due to failures. In addition, it also greatly improves the operating stability and equipment life of the oil pump. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the detection method of the oil pump status detection system based on deep learning of the present invention. DETAILED DESCRIPTION

[0016] Reference Figure 1 The oil pump state detection system and detection method embodiments based on deep learning of the present invention are further described.

[0017] Figure 1 The oil pump status detection system shown in the figure based on deep learning includes the following modules: Data acquisition module, used to collect the operation data of the oil pump in real time; The data preprocessing module is used to clean, extract features, and standardize the collected raw operating data to provide high-quality input data for the deep learning model; The deep learning model training module uses a convolutional neural network architecture to train the pre-processed data through a back-propagation algorithm, so that the model can learn the characteristics of the normal and fault states of the oil pump; The status detection module is used to classify the data using the trained deep learning model when monitoring the oil pump operation data in real time, and output the current status of the oil pump to determine whether there is an abnormality or potential fault; The fault warning module, based on the output results of the status detection module, will promptly issue a warning signal when an abnormality or potential fault in the oil pump is detected, so as to notify the maintenance personnel to take corresponding measures; Compared with the prior art, the oil pump status detection system based on deep learning in the present invention can monitor the operating status of the oil pump in real time and identify its abnormalities and potential faults, greatly improving the operating safety and reliability of the oil pump. A large amount of oil pump operating data is trained and learned through a convolutional neural network, so as to accurately determine whether there is a problem with the oil pump. Compared with traditional manual inspections, the deep learning model can adaptively extract meaningful features from complex and multi-dimensional sensor data, avoiding the limitations of artificially set rules; the system can detect abnormalities in a timely manner and issue early warnings, greatly improving the accuracy and response speed of fault diagnosis, and helping enterprises to take measures in the shortest time to avoid greater economic losses caused by fault expansion; In addition, traditional oil pump status monitoring and fault diagnosis usually rely on manual inspections and regular inspections, which are not only labor-intensive but also unable to achieve all-weather, real-time monitoring. The present invention greatly reduces the reliance on manual inspections through automated data collection and real-time monitoring.

[0018] The data acquisition module includes but is not limited to a temperature sensor, a vibration sensor, a noise sensor, a pressure sensor, and a voltage and current sensor, which collects multi-dimensional operation data of the oil pump in real time through the temperature sensor, the vibration sensor, the noise sensor, the pressure sensor, and the voltage and current sensor, and transmits the operation data to the data preprocessing module; The data acquisition module integrates multiple sensors (such as temperature, vibration, noise, pressure, voltage and current, etc.) to obtain multi-dimensional operating data of the oil pump in real time and comprehensively. The synergy of these sensors ensures the comprehensiveness and accuracy of the collected data. Different states of the oil pump are usually accompanied by multiple changes. Multi-channel perception can provide rich input data for the deep learning model, thereby improving the accuracy of fault detection. In addition, the diversity and real-time nature of the sensors ensure timely monitoring of the oil pump status, and can accurately identify and warn of faults in the early stages, thereby reducing the impact of faults on production.

[0019] The data preprocessing module includes the following processing steps: Data cleaning: remove missing values, outliers and duplicate data to ensure data accuracy; Feature extraction: Extract representative features for oil pump status detection from the raw data; Standardization: Normalize the data to make the data collected by different sensors uniform, so as to facilitate the training and reasoning of deep learning models; The data preprocessing module provides high-quality, standardized data input for the deep learning model through multiple steps such as data cleaning, feature extraction and standardization. The data cleaning step helps to eliminate the interference of noise data, missing values ​​and outliers, ensuring the accuracy and effectiveness of the data. Feature extraction helps to extract highly representative features for oil pump status monitoring from complex raw data, such as frequency domain features, time domain features, etc., thereby enhancing the learning effect of the model. Standardization processing can eliminate the differences in data scales of different sensors, so that various types of data can be trained under the same standard, thereby improving the stability and accuracy of the model. Through these preprocessing steps, the detection accuracy and reliability of the entire system have been significantly improved.

[0020] The fault warning module includes an alarm system, which promptly notifies maintenance personnel through sound and light alarms, SMS notifications, email reminders or mobile APP when an abnormality or potential fault in the oil pump is detected; The fault warning module monitors the status of the oil pump in real time and sends out warning signals in time when abnormalities or potential faults are found. Through various means such as sound and light alarms, SMS notifications, and email reminders, maintenance personnel can quickly receive warning information and take measures to prevent further development of the fault. This mechanism not only improves the response speed of oil pump failures, but also helps companies reduce losses caused by downtime due to failures. It also greatly improves the operating stability and equipment life of the oil pump.

[0021] The detection system also includes a remote monitoring module, which uploads the detection data and fault warning information to the cloud platform through the network for remote monitoring personnel to view and process; The remote monitoring module not only enables enterprises to centrally manage multiple oil pumps, but also obtains the operating status in real time through the remote platform and responds to any potential failure risks in a timely manner. In addition, remote monitoring also facilitates the unified management of multiple work sites, reduces the workload of maintenance personnel for on-site inspections, and can share experience and data between multiple factories or locations. This module significantly improves operation and maintenance efficiency and makes the oil pump monitoring system flexible and scalable, which facilitates the company's adaptation to future expansion needs.

[0022] A detection method of an oil pump state detection system based on deep learning, characterized in that it comprises the following steps: S1. Real-time data collection: The multi-dimensional operating data of the oil pump is collected in real time through sensors, including but not limited to the temperature, vibration, noise, pressure, voltage and current of the oil pump, and the frequency of data collection is set according to the actual situation to ensure real-time monitoring of the oil pump status; S2. Data transmission: The collected oil pump operation data is transmitted to the data preprocessing module through the communication network. The timeliness and accuracy of the data should be ensured during the data transmission process to prevent information delay or loss; S3. Data preprocessing: Preprocess the collected raw data: Data cleaning: remove missing values, outliers and duplicate data; Feature extraction: Extract representative features for oil pump status detection from the raw data; Data standardization: Normalize the data to facilitate the training and reasoning of deep learning models; S4. Deep learning model training: Use convolutional neural network to train the preprocessed data. During the training process, the convolutional neural network continuously adjusts parameters through the back propagation algorithm, learns the different characteristics of the oil pump under normal operation and fault state, and establishes a set of classification models, so as to accurately detect the state of new operation data; the training data should contain a variety of normal and fault data to ensure that the model has good generalization ability; S5. Model verification and optimization: After model training is completed, the model is evaluated through the validation set to check the performance of the model in the actual data. If the model performance is found to be insufficient, further optimization is required, such as adjusting the network structure, improving the feature extraction method, and increasing the training data. S6. Real-time status detection: The real-time collected oil pump operation data is input into the trained deep learning model, and the current operation status of the oil pump is judged through the model's reasoning process. The model outputs the status of the oil pump based on the input data features, which is usually "normal", "abnormal" or "potential fault"; S7, Fault warning trigger: When the oil pump status is detected as "abnormal" or "potential fault", the system will trigger the fault warning mechanism. The warning mechanism will determine whether to issue a warning signal based on the preset threshold to ensure that the fault can be discovered in time before it occurs; S8. Early warning notification and processing: When a fault or potential fault is detected, the system will promptly send early warning information to maintenance personnel through sound and light alarms, SMS notifications, email reminders or mobile APPs. Maintenance personnel can take corresponding measures in a timely manner based on the early warning information, such as checking the operating status of the oil pump, adjusting parameters or performing equipment maintenance, so as to prevent further deterioration of the fault; S9, Fault analysis and repair: After receiving the warning information, the maintenance personnel will conduct a detailed inspection of the oil pump, analyze the cause of the fault, determine the fault type, and take appropriate repair measures. After the fault is repaired, the oil pump status will be re-tested to ensure the repair effect; S10, Data feedback and system optimization: After troubleshooting, maintenance personnel will feed back the operation and repair results to the system as new data samples to further improve the deep learning model, which will help improve the system's detection accuracy for similar faults in the future and optimize the performance of the overall monitoring system; This detection method performs real-time monitoring and fault detection of the oil pump through a series of systematic steps. It can monitor the operating status of the oil pump in real time, detect abnormalities and potential faults in time, and improve the operating efficiency and stability of the oil pump.

[0023] The detection method includes the following determination rules: When the temperature of the oil pump is greater than the preset threshold, if the vibration parameters are abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the vibration parameters of the oil pump exceed the normal range, if the noise level increases, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the oil pump current and voltage fluctuate unstably, if the pressure is abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the operating data of the oil pump conforms to the normal state mode, the monitoring continues and returns to S6 for state detection; When the oil pump temperature, vibration, noise, pressure, current, and voltage exceed the normal range at the same time, the fault warning will be triggered in S7. When the noise signal and vibration signal of the oil pump confirm each other, the fault warning of S7 is triggered; When the oil pump shows a gradual abnormal trend in long-term operation and the fault signs are not obvious, go to S6 for status detection; When no abnormality is detected in the running state of the oil pump, the monitoring continues and returns to S6 for state detection; By setting judgment rules, the system can make more accurate fault judgments under the synergy of multi-dimensional sensor data. The judgment rules enhance the accuracy of oil pump status detection through mutual verification of different sensor data. For example, when temperature and vibration parameters are abnormal, the system can further check the status of other parameters such as noise and pressure, thereby improving the reliability of fault identification. At the same time, the judgment rules can effectively prevent the occurrence of false warnings and avoid system overreaction. The multiple verification mechanism of the rules enables the system to adapt to the complex changes in the operation of the oil pump and accurately judge its operating status. Through the nested judgment of this rule, the system can make accurate responses in different situations, improving the efficiency and accuracy of the overall oil pump fault diagnosis.

[0024] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Common changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. A deep learning-based oil pump status detection system, characterized in that: Includes the following modules: Data acquisition module, used to collect the operation data of the oil pump in real time; The data preprocessing module is used to clean, extract features, and standardize the collected raw operating data to provide high-quality input data for the deep learning model; The deep learning model training module uses a convolutional neural network architecture to train the pre-processed data through a back-propagation algorithm, so that the model can learn the characteristics of the normal and fault states of the oil pump; The status detection module is used to classify the data using the trained deep learning model when monitoring the oil pump operation data in real time, and output the current status of the oil pump to determine whether there is an abnormality or potential fault; The fault warning module, based on the output results of the status detection module, will promptly issue a warning signal when an abnormality or potential fault in the oil pump is detected, so as to notify the maintenance personnel to take corresponding measures.

2. The oil pump state detection system based on deep learning according to claim 1, characterized in that: The data acquisition module includes but is not limited to temperature sensors, vibration sensors, noise sensors, pressure sensors and voltage and current sensors. The temperature sensors, vibration sensors, noise sensors, pressure sensors and voltage and current sensors are used to collect multi-dimensional operating data of the oil pump in real time, and the operating data is transmitted to the data preprocessing module.

3. The oil pump state detection system based on deep learning according to claim 1, characterized in that: The data preprocessing module includes the following processing steps: Data cleaning: remove missing values, outliers and duplicate data to ensure data accuracy; Feature extraction: Extract representative features for oil pump status detection from the raw data; Standardization: Normalize the data to make the data collected by different sensors uniform, so as to facilitate the training and reasoning of deep learning models.

4. The oil pump state detection system based on deep learning according to claim 1, characterized in that: The fault warning module includes an alarm system, which promptly notifies maintenance personnel through sound and light alarms, SMS notifications, email reminders or mobile APP when an abnormality or potential fault in the oil pump is detected.

5. The oil pump state detection system based on deep learning according to claim 1, characterized in that: The detection system also includes a remote monitoring module, which uploads the detection data and fault warning information to the cloud platform through the network for remote monitoring personnel to view and process.

6. A detection method for the oil pump state detection system based on deep learning applicable to any one of claims 1-5, characterized in that: The following steps are involved: S1. Real-time data collection: The multi-dimensional operating data of the oil pump is collected in real time through sensors, including but not limited to the temperature, vibration, noise, pressure, voltage and current of the oil pump, and the frequency of data collection is set according to the actual situation to ensure real-time monitoring of the oil pump status; S2. Data transmission: The collected oil pump operation data is transmitted to the data preprocessing module through the communication network. The timeliness and accuracy of the data should be guaranteed during the data transmission process to prevent information delay or loss; S3. Data preprocessing: Preprocess the collected raw data: Data cleaning: remove missing values, outliers and duplicate data; Feature extraction: Extract representative features for oil pump status detection from the raw data; Data standardization: Normalize the data to facilitate the training and reasoning of deep learning models; S4. Deep learning model training: Use convolutional neural network to train the preprocessed data. During the training process, the convolutional neural network continuously adjusts parameters through the back propagation algorithm, learns the different characteristics of the oil pump under normal operation and fault conditions, and establishes a set of classification models, so as to accurately detect the status of new operation data; S5. Model verification and optimization: After model training is completed, the model is evaluated through the validation set to check the performance of the model in the actual data. If the model performance is found to be insufficient, further optimization is required; S6. Real-time status detection: The real-time collected oil pump operation data is input into the trained deep learning model, and the current operation status of the oil pump is judged through the model's reasoning process. The model outputs the status of the oil pump based on the input data features, usually "normal", "abnormal" or "potential fault"; S7, Fault warning trigger: When the oil pump status is detected as "abnormal" or "potential fault", the system will trigger the fault warning mechanism. The warning mechanism will determine whether to issue a warning signal based on the preset threshold to ensure that the fault can be discovered in time before it occurs; S8, Early warning notification and processing: When a fault or potential fault is detected, the system will promptly send early warning information to maintenance personnel through sound and light alarms, SMS notifications, email reminders or mobile APP. Maintenance personnel can take corresponding measures in time according to the early warning information to prevent further deterioration of the fault; S9, Fault analysis and repair: After receiving the warning information, the maintenance personnel will conduct a detailed inspection of the oil pump, analyze the cause of the fault, determine the fault type, and take appropriate repair measures. After the fault is repaired, the oil pump status will be re-tested to ensure the repair effect; S10. Data feedback and system optimization: After troubleshooting, maintenance personnel will feed back the operation and repair results to the system as new data samples to further improve the deep learning model, which will help improve the system's detection accuracy for similar faults in the future and optimize the performance of the overall monitoring system.

7. The detection method of the oil pump state detection system based on deep learning according to claim 6 is characterized in that: The detection method includes the following determination rules: When the temperature of the oil pump is greater than the preset threshold, if the vibration parameters are abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the vibration parameters of the oil pump exceed the normal range, if the noise level increases, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the oil pump current and voltage fluctuate unstably, if the pressure is abnormal, it will go to S7 for fault warning triggering, otherwise it will go to S6 for status detection; When the operating data of the oil pump conforms to the normal state mode, the monitoring continues and returns to S6 for state detection; When the oil pump temperature, vibration, noise, pressure, current, and voltage exceed the normal range at the same time, the fault warning will be triggered in S7. When the noise signal and vibration signal of the oil pump confirm each other, the fault warning of S7 is triggered; When the oil pump shows a gradual abnormal trend in long-term operation and the fault signs are not obvious, go to S6 for status detection; When no abnormality is detected in the running state of the oil pump, monitoring continues and returns to S6 for state detection.

Images