A method and system for detecting seal faults of pump units based on voiceprint characterization

Abstract

The present invention relates to the technical field of seal detection, and discloses a method and system for detecting seal faults of a pump unit based on acoustic signature characterization. The system includes: an acquisition unit, an analysis unit, an adjustment unit, and an early warning unit; the acquisition unit sets an acoustic signature sampling rate, and respectively obtains sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the acoustic signature sampling rate. The analysis unit extracts the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculates the seal characteristics of the pump unit according to the sound characteristics and vibration characteristics, obtains the seal fault prediction value of the pump unit based on the random forest model, acquires the ambient temperature data of each detection point and compares it with historical data, and determines whether to adjust the seal fault prediction value according to the comparison result; the adjustment unit determines a seal adjustment factor according to the temperature similarity; the early warning unit issues a corresponding alarm based on the seal state. The present invention has good comprehensive analysis ability and seal detection effect.

Description

Technical Field

[0001] The present invention relates to the technical field of seal detection, and in particular, to a method and system for detecting seal faults of pump units based on acoustic fingerprint characterization. Background Art

[0002] In recent years, the phenomenon of oil pipelines being shut down due to the shutdown of pump units has occurred frequently. The seal fault of pump units is an important factor leading to the decline of equipment performance, unstable operation and even accidents. Therefore, accurately and efficiently detecting the seal state of pump units is an important link to ensure the safe operation of equipment.

[0003] Traditional seal fault detection mainly relies on a single data source, such as vibration signals. However, a single data source cannot comprehensively reflect the seal state of pump units, resulting in misjudgment or missed judgment, thus reducing the reliability and accuracy of fault detection. In addition, the detection of the seal state is interfered by the ambient temperature, resulting in inaccurate judgment of seal faults. For example, the fluctuation of the ambient temperature will affect the sensitivity of sensors. The current seal fault detection cannot be dynamically adjusted according to the ambient temperature, and thus cannot accurately obtain the seal state of pump units, and further cannot give an accurate early warning.

[0004] Therefore, it is necessary to design a method and system for detecting seal faults of pump units based on acoustic fingerprint characterization to solve the problems existing in the current technology. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for detecting seal faults of pump units based on acoustic fingerprint characterization, aiming to solve the problems that the characteristics of multi-dimensional data cannot be fully utilized and the influence of ambient temperature on the detection results cannot be effectively dealt with.

[0006] On the one hand, the present invention proposes a system for detecting seal faults of pump units based on acoustic fingerprint characterization, including:

[0007] An acquisition unit, an analysis unit, an adjustment unit and an early warning unit;

[0008] The acquisition unit is configured to set an acoustic fingerprint sampling rate, and respectively obtain sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the acoustic fingerprint sampling rate, preprocess the sound data and the vibration data, and respectively obtain target sound data and target vibration data;

[0009] The analysis unit is configured to extract the sound features of the target sound data and the vibration features of the target vibration data, calculate the seal features of the pump unit according to the sound features and vibration features, count the historical seal features of all detection points and establish a seal data set, obtain the seal fault prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and judge whether to adjust the seal fault prediction value according to the comparison result;

[0010] The adjustment unit is configured to, when it is judged that the seal fault prediction value needs to be adjusted, determine a seal adjustment factor according to the temperature similarity. When the temperature similarity is greater than or equal to the similarity threshold, determine the seal adjustment factor according to the historical data. When the temperature similarity is lower than the similarity threshold, determine the seal temperature features for the corresponding detection point according to the ambient temperature data. The seal temperature features include a first temperature feature and a second temperature feature. Count the upward number of the first temperature feature, count the downward number of the second temperature feature, determine the seal adjustment factor according to the upward number and the downward number, and adjust the seal fault prediction value based on the seal adjustment factor;

[0011] The warning unit is configured to set a fault warning value, compare the fault warning value with the adjusted seal fault prediction value, obtain the seal state of the pump unit based on the comparison result, and issue a corresponding alarm based on the seal state.

[0012] Further, when setting the voiceprint sampling rate and respectively obtaining the sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the voiceprint sampling rate, the preprocessing of the sound data and the vibration data includes:

[0013] The voiceprint sampling rate includes a sound sampling rate and a vibration sampling rate;

[0014] Obtain the sound data of each detection point based on the sound sampling rate, and obtain the vibration data of each detection point based on the vibration sampling rate;

[0015] Preprocess the sound data and the vibration data. The preprocessing includes: noise filtering, signal segmentation, and data normalization.

[0016] Further, when extracting the sound features of the target sound data and the vibration features of the target vibration data and calculating the seal features of the pump unit according to the sound features and vibration features, it includes:

[0017] The seal features of the pump unit are obtained from the following formula:

[0018] ;

[0019] ;

[0020] ;

[0021] Among them, represents the sound feature, represents the number of detection points, represents the normalization result of the target sound data of the i-th detection point, represents the average value of the normalization results of the target sound data of all detection points, represents the vibration feature, represents the normalization result of the target vibration data of the i-th detection point, represents the average value of the normalization results of the target vibration data of all detection points, represents the seal feature of the pump unit, and represents the weight coefficient, and + = 1.

[0022] Further, when statistically analyzing the historical seal features of all detection points and establishing a seal data set, and obtaining the seal fault prediction value of the pump unit based on the random forest model, it includes:

[0023] Using the seal data set as the model training set and the model test set, adopting cross-validation and combining grid search to find the construction parameters of the random forest model, establishing the random forest model, using the model training set to fit the random forest model, inputting the model test set into the random forest model for verification, and when the correct rate of the seal fault prediction value reaches the preset correct rate threshold, obtaining the seal fault prediction value of the pump unit according to the seal feature.

[0024] Further, when obtaining the ambient temperature data of each detection point and comparing it with the historical data, and judging whether to adjust the seal fault prediction value according to the comparison result, it includes:

[0025] The historical data includes the historical temperature qualified average value, the historical detection point temperature, the historical seal adjustment factor, and the historical seal fault prediction value, and the historical detection point temperature, the historical seal adjustment factor, and the historical seal fault prediction value correspond;

[0026] Comparing the ambient temperature data with the historical temperature qualified average value, and judging whether to adjust the seal fault prediction value according to the comparison result;

[0027] When all the ambient temperature data are equal to the historical qualified temperature mean value, it is determined that the seal fault prediction value is not adjusted, and the seal fault prediction value is determined as the pump unit fault value according to the seal fault prediction value;

[0028] When there is ambient temperature data that is not equal to the historical qualified temperature mean value, it is determined that the seal fault prediction value is adjusted.

[0029] Furthermore, when it is determined that the seal fault prediction value is adjusted, a seal adjustment factor is determined according to the temperature similarity. When the temperature similarity is greater than or equal to the similarity threshold, when determining the seal adjustment factor according to the historical data, it includes:

[0030] ;

[0031] where, represents the temperature similarity, represents the number of detection points, represents the normalization result of the ambient temperature data of the i-th detection point, represents the historical qualified temperature mean value, represents the historical detection point temperature;

[0032] When is greater than or equal to the similarity threshold, the mean value of the historical seal adjustment factors is determined as the seal adjustment factor of the seal fault prediction value.

[0033] Furthermore, when the temperature similarity is lower than the similarity threshold, seal temperature characteristics are determined for the corresponding detection points according to the ambient temperature data. When the seal temperature characteristics include a first temperature characteristic and a second temperature characteristic, it includes:

[0034] Determine the standard temperature data corresponding to each detection point;

[0035] Compare the ambient temperature data with the standard temperature data. If the ambient temperature data is less than the standard temperature data, the corresponding detection point is determined as the first temperature characteristic;

[0036] If the ambient temperature data is greater than or equal to the standard temperature data, the corresponding detection point is determined as the second temperature characteristic.

[0037] Furthermore, when determining the seal adjustment factor according to the upward quantity and the downward quantity and adjusting the seal fault prediction value based on the seal adjustment factor, it includes:

[0038] The seal adjustment factor is obtained by the following formula:

[0039] ;

[0040] Among them, represents the seal adjustment factor, represents the up quantity, represents the down quantity, represents the sum of the up quantity and the down quantity;

[0041] The seal fault prediction value is directly proportional to the seal adjustment factor to obtain the pump unit fault value.

[0042] Furthermore, when setting a fault warning value, comparing the fault warning value with the adjusted seal fault prediction value, and obtaining the seal state of the pump unit based on the comparison result, and issuing a corresponding alarm based on the seal state, it includes:

[0043] Preset a first preset fault warning value and a second preset fault warning value, and the first preset fault warning value is greater than the second preset fault warning value;

[0044] When the pump unit fault value is greater than or equal to the first preset fault warning value, it is determined that the seal state of the pump unit is at the first-level abnormality and a serious alarm is issued;

[0045] When the pump unit fault value is less than the first preset fault warning value and greater than the second preset fault warning value, it is determined that the seal state of the pump unit is at the second-level abnormality and a medium alarm is issued;

[0046] When the pump unit fault value is less than or equal to the second preset fault warning value, it is determined that the seal state of the pump unit is at the third-level abnormality and a minor alarm is issued.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows: By collecting the sound data and vibration data of multiple detection points of the pump unit and comprehensively analyzing them in combination with the ambient temperature data, the problem of misjudgment caused by a single data source is effectively avoided, the ability to comprehensively process data is improved, and then the sealing state of the pump unit is accurately obtained, improving the accuracy of seal failure detection. Through the random forest model and the dynamic adjustment mechanism based on temperature similarity, automatic data processing and prediction of seal failures can be achieved, reducing the need for manual intervention, improving the detection efficiency and reducing the risk of errors caused by human factors. By comparing the ambient temperature data with the historical data, it can automatically determine whether to adjust the seal failure prediction value, and can avoid the problem of the influence of environmental factors on the detection result. When dealing with the influence of ambient temperature, the seal adjustment factor is determined by combining the number of upward and downward quantities, fully considering the influence of temperature changes on the operating state of the pump unit, ensuring accurate seal failure detection can still be maintained in a complex environment, improving the adaptability of the detection. Based on the comparison between the adjusted seal failure prediction value and the preset failure warning value, the sealing state of the pump unit is generated in a timely manner and the corresponding alarm is triggered, enabling potential seal failures to be detected at an early stage, effectively preventing the pump unit from shutting down due to seal failures, and at the same time reducing the risks of missed reports and false alarms, improving the safety, stability and operating efficiency of the pump unit.

[0048] On the other hand, the present application also provides a method for detecting seal failures of a pump unit based on voiceprint characterization, which is used to apply the above-mentioned system for detecting seal failures of a pump unit based on voiceprint characterization, and includes:

[0049] Set the voiceprint sampling rate, and respectively obtain the sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the voiceprint sampling rate, and preprocess the sound data and the vibration data to respectively obtain the target sound data and the target vibration data;

[0050] Extract the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculate the seal characteristics of the pump unit according to the sound characteristics and vibration characteristics, statistically analyze the historical seal characteristics of all detection points and establish a seal data set, obtain the seal failure prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and judge whether to adjust the seal failure prediction value according to the comparison result;

[0051] When it is determined that the sealing failure prediction value is to be adjusted, a sealing adjustment factor is determined according to the temperature similarity; when the temperature similarity is greater than or equal to the similarity threshold, the sealing adjustment factor is determined according to the historical data; when the temperature similarity is lower than the similarity threshold, a sealing temperature feature is determined for a corresponding detection point according to the ambient temperature data, the sealing temperature feature includes a first temperature feature and a second temperature feature, the number of upstreams of the first temperature feature is counted, the number of downstreams of the second temperature feature is counted, a sealing adjustment factor is determined according to the upstream number and the downstream number, and the sealing failure prediction value is adjusted based on the sealing adjustment factor;

[0052] A fault warning value is set, and the fault warning value is compared with the adjusted sealing fault prediction value, the sealing state of the pump unit is obtained based on the comparison result, and a corresponding alarm is issued based on the sealing state.

[0053] It can be understood that the above-mentioned pump unit seal fault detection method and system based on voiceprint characterization have the same beneficial effects, which will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0055] Figure 1 A functional block diagram of a pump unit sealing fault detection system based on voiceprint characterization provided by an embodiment of the present invention;

[0056] Figure 2 A flow chart of a pump unit sealing fault detection method based on voiceprint characterization provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] In some embodiments of the present application, see Figure 1 As shown, a pump unit sealing fault detection system based on voiceprint characterization includes:

[0059] A collection unit, an analysis unit, an adjustment unit, and an early warning unit;

[0060] The collection unit is configured to set the voiceprint sampling rate, respectively obtain the sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the voiceprint sampling rate, preprocess the sound data and vibration data, and respectively obtain the target sound data and target vibration data;

[0061] The analysis unit is configured to extract the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculate the seal characteristics of the pump unit according to the sound characteristics and vibration characteristics, statistically analyze the historical seal characteristics of all detection points and establish a seal data set, obtain the seal fault prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and judge whether to adjust the seal fault prediction value according to the comparison result;

[0062] The adjustment unit is configured to, when it is determined to adjust the seal fault prediction value, determine the seal adjustment factor according to the temperature similarity. When the temperature similarity is greater than or equal to the similarity threshold, determine the seal adjustment factor according to the historical data. When the temperature similarity is lower than the similarity threshold, determine the seal temperature characteristics for the corresponding detection point according to the ambient temperature data. The seal temperature characteristics include the first temperature characteristic and the second temperature characteristic. Statistically analyze the upward number of the first temperature characteristic, statistically analyze the downward number of the second temperature characteristic, determine the seal adjustment factor according to the upward number and the downward number, and adjust the seal fault prediction value based on the seal adjustment factor;

[0063] The early warning unit is configured to set a fault warning value, compare the fault warning value with the adjusted seal fault prediction value, obtain the seal state of the pump unit based on the comparison result, and issue a corresponding alarm based on the seal state.

[0064] Specifically, the acquisition unit sets the voiceprint sampling rate. By setting an appropriate voiceprint sampling rate, the acquisition unit can effectively capture the sound data and vibration data of each detection point among multiple detection points deployed on the pump unit through the sound sensor and the vibration sensor. Since there will be signal interference between the acquired data, it is necessary to preprocess the sound data and vibration data to finally obtain the target sound data and target vibration data that can represent the pump unit. The target sound data and target vibration data reflect the real-time condition of the pump unit. Extract the sound features from the target sound data and the vibration features from the target vibration data. The sound features and vibration features are two important features that constitute the seal features. Statistically analyze the historical seal features of all detection points and establish a seal data set. The seal data set represents the seal features of the pump unit at different times. The seal data set is used to train the random forest model. The random forest model is a machine learning algorithm. By training the random forest model, the seal fault prediction value of the pump unit can be obtained based on the input seal features. The prediction accuracy of the random forest model depends on the quality of the seal features and the training effect of the model. Simply using the model for prediction cannot comprehensively consider the influence of environmental factors on the seal fault prediction value. Obtain the environmental temperature data of each detection point through the temperature sensor and compare it with the historical data to determine whether it is necessary to adjust the seal fault prediction value, thereby improving the flexibility and prediction accuracy of the system. When it is determined that the seal fault prediction value needs to be adjusted, calculate the temperature similarity to determine the determination method of the seal adjustment factor. The seal adjustment factor is a parameter for dynamically adjusting the seal features based on the environmental temperature, which improves the accuracy and reliability of the system prediction. Set a fault warning value, compare the adjusted seal fault prediction value with the fault warning value, and obtain the seal state of the pump unit based on the comparison result and issue a corresponding alarm, providing processing time for the maintenance personnel to make decisions, avoiding the risk of major accidents caused by the seal fault of the pump unit, and being conducive to the safe management of the pump unit.

[0065] It can be understood that the seal features of the pump unit are calculated based on the sound features and vibration features and analyzed in combination with the random forest model. The random forest model has good robustness in dealing with complex nonlinear problems, improving the stability of the prediction. Introducing the environmental temperature data to dynamically adjust the seal fault prediction value enables the system to adapt to different operating environments, thereby improving the reliability of the detection results. The real-time detection and automatic analysis of the system eliminate the need for frequent manual inspections, reducing the operation and maintenance costs of the pump unit and ensuring the detection of the seal state of the pump unit, thus reducing the risk of seal faults.

[0066] In some embodiments of the present application, when setting the voiceprint sampling rate and respectively obtaining the sound data and vibration data of each detection point among multiple detection points deployed on the pump unit based on the voiceprint sampling rate and preprocessing the sound data and vibration data, it includes:

[0067] The voiceprint sampling rate includes the sound sampling rate and the vibration sampling rate;

[0068] Obtain the sound data of each detection point based on the sound sampling rate, and obtain the vibration data of each detection point based on the vibration sampling rate;

[0069] Preprocess the sound data and the vibration data. The preprocessing includes: noise filtering, signal segmentation, and data normalization.

[0070] In some embodiments of the present application, when extracting the sound features of the target sound data and the vibration features of the target vibration data, and calculating the seal features of the pump unit according to the sound features and the vibration features, it includes:

[0071] The seal features of the pump unit are obtained by the following formula:

[0072] ;

[0073] ;

[0074] ;

[0075] Wherein, represents the sound feature, represents the number of detection points, represents the normalization result of the target sound data of the i-th detection point, represents the average value of the normalization results of the target sound data of all detection points, represents the vibration feature, represents the normalization result of the target vibration data of the i-th detection point, represents the average value of the normalization results of the target vibration data of all detection points, represents the seal features of the pump unit, and represent the weight coefficients, and + = 1.

[0076] Specifically, the sound sampling rate is preferably 15 kHz - 30 kHz, and the vibration sampling rate is preferably 5 kHz - 20 kHz. The sound sampling rate and the vibration sampling rate can be set according to specific requirements. Noise filtering can filter out environmental noise. Signal segmentation ensures the time continuity of sound data and vibration data during feature extraction. Data normalization unifies the dimension of the data. Through noise filtering, signal segmentation, and data normalization, the accuracy of sound features and vibration features is improved. By the mean value of the standardized results of the target sound data and the mean value of the standardized results of the target vibration data, it is ensured that the calculation of the seal feature is carried out under the same dimension. The seal feature of the pump unit is calculated based on the sound feature and the vibration feature, reducing the dependence on manual experience, reducing the influence of human error on the seal state of the pump unit, and improving the automation degree and reliability of the system.

[0077] In some embodiments of the present application, when statistically analyzing the historical seal features of all detection points and establishing a seal data set, and obtaining the seal fault prediction value of the pump unit based on the random forest model, it includes:

[0078] Taking the seal data set as the model training set and the model test set, using cross-validation and combining with grid search to find the construction parameters of the random forest model, establishing the random forest model, using the model training set to fit the random forest model, inputting the model test set into the random forest model for verification. When the correct rate of the seal fault prediction value reaches the preset correct rate threshold, the seal fault prediction value of the pump unit is obtained according to the seal feature.

[0079] Specifically, the seal data set records the seal features of the pump unit at different time periods. The seal data set is divided into the model training set and the model test set. 80% - 90% of the data is used as the model training set, and the rest is used as the model test set, ensuring that both the model training set and the model test set contain data of various seal features, thereby improving the generalization ability of the random forest model. Using cross-validation and combining with grid search to find the construction parameters of the random forest model, cross-validation trains the model multiple times to verify its stability, and grid search searches for the construction parameters of the random forest model among the parameters, such as the number of trees. Secondly, using the model training set to fit the random forest model, by integrating multiple decision trees and averaging the prediction results of multiple trees, the risk of overfitting is reduced, thereby improving the stability of the random forest model. Inputting the model test set into the trained random forest model, calculating the prediction correct rate of the random forest model. The correct rate reflects the performance of the random forest model on unknown data. When the random forest model reaches the preset correct rate threshold, inputting the current seal feature into the random forest model, thereby obtaining the seal fault prediction value of the pump unit, improving the system's efficient and accurate seal fault prediction ability for the pump unit, thus timely discovering potential problems and enhancing the safety management of the pump unit.

[0080] In some embodiments of the present application, when obtaining the ambient temperature data of each detection point, comparing it with historical data, and determining whether to adjust the seal failure prediction value according to the comparison result, it includes:

[0081] The historical data includes the historical temperature qualified mean value, the historical detection point temperature, the historical seal adjustment factor, and the historical seal failure prediction value, and the historical detection point temperature, the historical seal adjustment factor, and the historical seal failure prediction value correspond to each other;

[0082] Compare the ambient temperature data with the historical temperature qualified mean value, and determine whether to adjust the seal failure prediction value according to the comparison result;

[0083] When the ambient temperature data are all equal to the historical temperature qualified mean value, it is determined not to adjust the seal failure prediction value, and the seal failure prediction value is determined as the pump unit failure value;

[0084] When there is ambient temperature data that is not equal to the historical temperature qualified mean value, it is determined to adjust the seal failure prediction value.

[0085] Specifically, the historical temperature qualified mean value can be adjusted according to the temperature environment where the pump unit is located. For example, when the pump unit is in an environment of 70°C for a long time, the historical temperature qualified mean value can be set to 65 - 75°C to ensure that it is within the allowable temperature error range of the pump unit. The ambient temperature will have a certain impact on the seal of the pump unit. By introducing the historical temperature qualified mean value as the judgment benchmark, the accuracy and automation degree of adjusting the seal failure prediction value are improved, the interference and error of human judgment are reduced, and the adaptability of the system to different environmental conditions is enhanced.

[0086] In some embodiments of the present application, when it is determined to adjust the seal failure prediction value, the seal adjustment factor is determined according to the temperature similarity. When the temperature similarity is greater than or equal to the similarity threshold, when determining the seal adjustment factor according to the historical data, it includes:

[0087] ;

[0088] Among them, represents the temperature similarity, represents the number of detection points, represents the standardized result of the ambient temperature data of the i-th detection point, represents the historical temperature qualified mean value, represents the historical detection point temperature;

[0089] When is greater than or equal to the similarity threshold, the mean value of the historical seal adjustment factors is determined as the seal adjustment factor of the seal failure prediction value.

[0090] Specifically, the matching degree between the ambient temperature data and the historical adjustment is judged by the similarity threshold. When historical data with a high temperature similarity is found, these data can be used to determine the seal adjustment factor. By comprehensively using the historical data, rich reference data is provided for the determination of the seal adjustment factor, the automation level of the system is improved, and the reliability of the adjustment of the seal fault prediction value is ensured.

[0091] In some embodiments of the present application, when the temperature similarity is lower than the similarity threshold, the seal temperature characteristics are determined for the corresponding detection points according to the ambient temperature data. When the seal temperature characteristics include the first temperature characteristic and the second temperature characteristic, it includes:

[0092] Determine the standard temperature data corresponding to each detection point;

[0093] Compare the ambient temperature data with the standard temperature data. If the ambient temperature data is less than the standard temperature data, the corresponding detection point is determined as the first temperature characteristic;

[0094] If the ambient temperature data is greater than or equal to the standard temperature data, the corresponding detection point is determined as the second temperature characteristic.

[0095] In some embodiments of the present application, when determining the seal adjustment factor according to the number of upstream and downstream, and adjusting the seal fault prediction value based on the seal adjustment factor, it includes:

[0096] The seal adjustment factor is obtained by the following formula:

[0097] ;

[0098] Wherein, represents the seal adjustment factor, represents the number of upstream, represents the number of downstream, represents the sum of the number of upstream and downstream;

[0099] The seal fault prediction value is in a direct proportion relationship with the seal adjustment factor, and the pump unit fault value is obtained.

[0100] Specifically, the standard temperature data corresponding to each detection point is the working temperature environment permitted by the pump unit. The seal adjustment factor is determined according to the number of upstream and downstream, and then the dynamic adjustment of the seal fault prediction value can be realized. The number of upstream and downstream reflects the distribution situation with the standard temperature data. The seal fault prediction value is adjusted according to the seal adjustment factor. Assuming the seal fault prediction value is A and the seal adjustment factor is B, then the adjusted seal fault prediction value is determined as the pump unit fault value, and the pump unit fault value is equal to A*B, which improves the flexibility of the dynamic adjustment of the system.

[0101] In some embodiments of the present application, when setting a fault warning value, comparing the fault warning value with the adjusted seal fault prediction value, and obtaining the seal state of the pump unit based on the comparison result, and issuing a corresponding alarm based on the seal state, it includes:

[0102] Preset a first preset fault warning value and a second preset fault warning value, where the first preset fault warning value is greater than the second preset fault warning value;

[0103] When the fault value of the pump unit is greater than or equal to the first preset fault warning value, it is determined that the seal state of the pump unit is at the first-level abnormality and a severe alarm is issued;

[0104] When the fault value of the pump unit is less than the first preset fault warning value and greater than the second preset fault warning value, it is determined that the seal state of the pump unit is at the second-level abnormality and a moderate alarm is issued;

[0105] When the fault value of the pump unit is less than or equal to the second preset fault warning value, it is determined that the seal state of the pump unit is at the third-level abnormality and a minor alarm is issued.

[0106] Specifically, by setting the first preset fault warning value and the second preset fault warning value, the seal state of the pump unit can be judged according to the fault value of the pump unit and the corresponding alarm can be issued. The hierarchical alarm mechanism can effectively remind the current seal state of the pump unit, improve the response efficiency of seal fault handling, avoid false negatives and false positives caused by manual detection, reduce the risk of ignoring seal faults, and thus reduce the probability of accidents.

[0107] In summary, the beneficial effects of the present invention are as follows: By collecting the sound data and vibration data of multiple detection points of the pump unit and comprehensively analyzing them in combination with the ambient temperature data, the problem of misjudgment caused by a single data source is effectively avoided, the ability to comprehensively process data is improved, and then the sealing state of the pump unit is accurately obtained, improving the accuracy of seal fault detection. Through the random forest model and the dynamic adjustment mechanism based on temperature similarity, automated data processing and prediction of seal faults can be achieved, reducing the need for manual intervention, improving the detection efficiency and reducing the risk of errors caused by human factors. By comparing the ambient temperature data with the historical data, it is possible to automatically determine whether the seal fault prediction value needs to be adjusted, and the problem of the influence of environmental factors on the detection results can be avoided. When dealing with the influence of ambient temperature, the seal adjustment factor is determined by combining the upward and downward quantities, fully considering the influence of temperature changes on the operating state of the pump unit, ensuring accurate seal fault detection can still be maintained in a complex environment, improving the adaptability of the detection. Based on the comparison between the adjusted seal fault prediction value and the preset fault warning value, the sealing state of the pump unit is generated in a timely manner and the corresponding alarm is triggered, enabling potential seal faults to be detected at an early stage, effectively preventing the pump unit from shutting down due to seal faults, and at the same time reducing the risks of missed alarms and false alarms, improving the safety, stability and operating efficiency of the pump unit.

[0108] In another preferred embodiment based on the above embodiments, refer to Figure 2 As shown, this embodiment provides a method for detecting seal faults of a pump unit based on voiceprint characterization, which is used to apply the above-mentioned system for detecting seal faults of a pump unit based on voiceprint characterization, and includes:

[0109] S100: Set the voiceprint sampling rate, and respectively obtain the sound data and vibration data of each detection point deployed at multiple detection points of the pump unit based on the voiceprint sampling rate. Preprocess the sound data and vibration data to obtain the target sound data and target vibration data respectively;

[0110] S200: Extract the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculate the seal characteristics of the pump unit based on the sound characteristics and vibration characteristics, statistically analyze the historical seal characteristics of all detection points and establish a seal data set, obtain the seal fault prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and determine whether to adjust the seal fault prediction value according to the comparison result;

[0111] S300: When it is determined to adjust the seal fault prediction value, determine the seal adjustment factor according to the temperature similarity. When the temperature similarity is greater than or equal to the similarity threshold, determine the seal adjustment factor according to historical data. When the temperature similarity is lower than the similarity threshold, determine the seal temperature characteristics for the corresponding detection points according to the ambient temperature data. The seal temperature characteristics include the first temperature characteristic and the second temperature characteristic. Count the upward number of the first temperature characteristic and count the downward number of the second temperature characteristic. Determine the seal adjustment factor according to the upward number and the downward number, and adjust the seal fault prediction value based on the seal adjustment factor;

[0112] S400: Set the fault warning value, compare the fault warning value with the adjusted seal fault prediction value, obtain the seal state of the pump unit based on the comparison result, and issue a corresponding alarm based on the seal state.

[0113] Specifically, in step S100, the voiceprint sampling rate is set, and voice data and vibration data are obtained from each detection point of the pump unit according to the voiceprint sampling rate. The voice data comes from the voice sensors deployed at each detection point, and the vibration data comes from the vibration sensors deployed at each detection point. Then, the voice data and vibration data are preprocessed to obtain the target voice data and target vibration data respectively, which improves the quality of the preprocessed data and provides data support for subsequent analysis. In step S200, voice features and vibration features are extracted from the target voice data and target vibration data respectively. By analyzing these features, the seal feature of the pump unit is calculated. The historical seal features of all detection points are statistically analyzed to establish a seal data set, and the seal fault value of the pump unit is obtained by training a random forest model. Using a machine learning model improves the accuracy of prediction. The ambient temperature data of each detection point is obtained, and the ambient temperature data comes from the temperature sensors deployed at each detection point. The ambient temperature data is compared with the historical data to determine whether to adjust the seal fault prediction value to improve the accuracy of the prediction result. In step S300, when it is determined to adjust the seal fault prediction value, the seal adjustment factor is determined according to the temperature similarity, which improves the flexibility and adaptability of the adjustment. When the temperature similarity is greater than or equal to the similarity threshold, the seal adjustment factor is determined according to the historical data. When the temperature similarity is lower than the similarity threshold, the seal temperature feature is determined for the corresponding detection point. The seal temperature feature includes the first temperature feature and the second temperature feature. The seal adjustment factor is determined by statistically analyzing the upward and downward numbers of these two features. The seal fault prediction value is adjusted according to the seal adjustment factor, which improves the accuracy and reliability of the prediction. In step S400, a fault warning value is set, and the fault warning value is compared with the adjusted seal fault prediction value to determine the seal state of the pump unit and send out corresponding alarm signals according to the seal state. According to the corresponding alarm signals, the degree of the seal fault can be judged to ensure that the seal fault can be processed in time and further damage to the pump unit can be avoided, effectively improving the operation safety of the pump unit.

[0114] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a machine for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0116] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 a device for the functions specified in one block or multiple blocks.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: it is still possible to modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A pump unit seal fault detection system based on voiceprint characterization, characterized in that: include: Collection unit, analysis unit, adjustment unit and early warning unit; The acquisition unit is configured to set a soundprint sampling rate, obtain sound data and vibration data of each detection point deployed at a plurality of detection points of the pump unit based on the soundprint sampling rate, pre-process the sound data and the vibration data, and obtain target sound data and target vibration data respectively; The analysis unit is configured to extract the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculate the sealing characteristics of the pump unit according to the sound characteristics and the vibration characteristics, count the historical sealing characteristics of all detection points and establish a sealing data set, obtain the sealing failure prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and determine whether to adjust the sealing failure prediction value according to the comparison result; The adjustment unit is configured to determine a sealing adjustment factor according to the temperature similarity when it is determined that the sealing failure prediction value is to be adjusted; when the temperature similarity is greater than or equal to the similarity threshold, determine the sealing adjustment factor according to the historical data; when the temperature similarity is lower than the similarity threshold, determine a sealing temperature feature for a corresponding detection point according to the ambient temperature data, the sealing temperature feature including a first temperature feature and a second temperature feature, count the number of upstreams of the first temperature feature, count the number of downstreams of the second temperature feature, determine the sealing adjustment factor according to the upstream number and the downstream number, and adjust the sealing failure prediction value based on the sealing adjustment factor; The early warning unit is configured to set a fault early warning value, and compare the fault early warning value with the adjusted sealing fault prediction value, obtain the sealing state of the pump unit based on the comparison result, and issue a corresponding alarm based on the sealing state; When the temperature similarity is lower than the similarity threshold, determining the sealing temperature feature for the corresponding detection point according to the ambient temperature data, and when the sealing temperature feature includes the first temperature feature and the second temperature feature, comprising: Determine the standard temperature data corresponding to each detection point; Comparing the ambient temperature data with the standard temperature data, if the ambient temperature data is less than the standard temperature data, determining the corresponding detection point as the first temperature feature; If the ambient temperature data is greater than or equal to the standard temperature data, determining the corresponding detection point as the second temperature feature; When a sealing adjustment factor is determined according to the upstream number and the downstream number, and the sealing failure prediction value is adjusted based on the sealing adjustment factor, the method includes: The seal adjustment factor is given by the following formula: ； in, represents the seal adjustment factor, Indicates the number of upstream connections. Indicates the number of downstream Indicates the sum of the upstream and downstream numbers; The seal failure prediction value is proportional to the seal adjustment factor, and the pump unit failure value is obtained.

2. The pump unit seal fault detection system based on voiceprint characterization according to claim 1 is characterized in that: When setting the voiceprint sampling rate, acquiring the sound data and vibration data of each detection point deployed at the multiple detection points of the pump unit based on the voiceprint sampling rate, and preprocessing the sound data and the vibration data, it includes: The voiceprint sampling rate includes the sound sampling rate and the vibration sampling rate; Acquire sound data of each detection point based on the sound sampling rate, and acquire vibration data of each detection point based on the vibration sampling rate; The sound data and the vibration data are preprocessed, and the preprocessing includes: noise filtering, signal segmentation and data normalization.

3. The pump unit seal fault detection system based on voiceprint characterization according to claim 2 is characterized in that: When extracting the sound feature of the target sound data and the vibration feature of the target vibration data, and calculating the sealing feature of the pump unit according to the sound feature and the vibration feature, it includes: The sealing characteristics of the pump unit are derived from the following formula: ； ； ； in, Indicates the sound characteristics, represents the number of detection points, represents the normalized result of the target sound data at the i-th detection point, Represents the standardized mean value of all detection point target sound data, Represents the vibration characteristics, represents the normalized result of the target vibration data of the i-th detection point, Represents the standardized result mean of the target vibration data of all detection points, Indicates the sealing characteristics of the pump unit, and represents the weight coefficient, and + =1.

4. The pump unit seal fault detection system based on voiceprint characterization according to claim 3 is characterized in that: When the historical sealing characteristics of all detection points are counted and a sealing data set is established, and the sealing failure prediction value of the pump unit is obtained based on the random forest model, it includes: The sealing data set is used as a model training set and a model test set. Cross-validation is used in combination with grid search to find the construction parameters of the random forest model, and a random forest model is established. The model training set is used to fit the random forest model, and the model test set is input into the random forest model for verification. When the accuracy of the sealing failure prediction value reaches a preset accuracy threshold, the sealing failure prediction value of the pump unit is obtained according to the sealing characteristics.

5. The pump unit seal fault detection system based on voiceprint characterization according to claim 4 is characterized in that: When the ambient temperature data of each detection point is obtained and compared with the historical data, and whether to adjust the sealing failure prediction value according to the comparison result is determined, it includes: The historical data includes the historical temperature qualified mean value, the historical detection point temperature, the historical sealing adjustment factor and the historical sealing failure prediction value, and the historical detection point temperature, the historical sealing adjustment factor and the historical sealing failure prediction value correspond to each other; Compare the ambient temperature data with the qualified mean value of historical temperature, and determine whether to adjust the sealing failure prediction value according to the comparison result; When the ambient temperature data are all equal to the qualified mean value of the historical temperature, it is determined that the sealing failure prediction value is not adjusted, and the pump unit failure value is determined according to the sealing failure prediction value; When the ambient temperature data is not equal to the qualified mean value of the historical temperature, it is determined that the sealing failure prediction value should be adjusted.

6. The pump unit seal fault detection system based on voiceprint characterization according to claim 5 is characterized in that: When it is determined that the sealing failure prediction value is to be adjusted, a sealing adjustment factor is determined according to the temperature similarity, and when the temperature similarity is greater than or equal to the similarity threshold, the sealing adjustment factor is determined according to the historical data, including: ； in, represents the temperature similarity, represents the number of detection points, represents the standardized result of the ambient temperature data of the i-th detection point, Represents the qualified mean value of historical temperature, Indicates the temperature of the historical detection point; when When it is greater than or equal to the similarity threshold, the mean value of the historical sealing adjustment factors is determined as the sealing adjustment factor of the sealing failure prediction value.

7. The pump unit seal fault detection system based on voiceprint characterization according to claim 6 is characterized in that: When a fault warning value is set, and the fault warning value is compared with the adjusted sealing fault prediction value, the sealing state of the pump unit is obtained based on the comparison result, and a corresponding alarm is issued based on the sealing state, it includes: Presetting a first preset fault warning value and a second preset fault warning value, wherein the first preset fault warning value is greater than the second preset fault warning value; When the pump unit fault value is greater than or equal to the first preset fault warning value, the sealing state of the pump unit is judged to be a first-level abnormality and a serious alarm is issued; When the pump unit fault value is less than the first preset fault warning value and greater than the second preset fault warning value, the sealing state of the pump unit is judged to be a secondary abnormality and a moderate alarm is issued; When the pump unit fault value is less than or equal to the second preset fault warning value, the sealing state of the pump unit is judged to be a level 3 abnormality and a slight alarm is issued.

8. A pump unit seal fault detection method based on voiceprint characterization, using the pump unit seal fault detection system based on voiceprint characterization as described in any one of claims 1 to 7, characterized in that: include: Setting a soundprint sampling rate, acquiring sound data and vibration data of each detection point deployed at a plurality of detection points of the pump unit based on the soundprint sampling rate, preprocessing the sound data and the vibration data, and obtaining target sound data and target vibration data respectively; Extract the sound characteristics of the target sound data and the vibration characteristics of the target vibration data, calculate the sealing characteristics of the pump unit according to the sound characteristics and the vibration characteristics, count the historical sealing characteristics of all detection points and establish a sealing data set, obtain the sealing failure prediction value of the pump unit based on the random forest model, obtain the ambient temperature data of each detection point and compare it with the historical data, and determine whether to adjust the sealing failure prediction value according to the comparison result; When it is determined that the sealing failure prediction value is to be adjusted, a sealing adjustment factor is determined according to the temperature similarity; when the temperature similarity is greater than or equal to the similarity threshold, the sealing adjustment factor is determined according to the historical data; when the temperature similarity is lower than the similarity threshold, a sealing temperature feature is determined for a corresponding detection point according to the ambient temperature data, the sealing temperature feature includes a first temperature feature and a second temperature feature, the number of upstreams of the first temperature feature is counted, the number of downstreams of the second temperature feature is counted, a sealing adjustment factor is determined according to the upstream number and the downstream number, and the sealing failure prediction value is adjusted based on the sealing adjustment factor; A fault warning value is set, and the fault warning value is compared with the adjusted sealing fault prediction value, the sealing state of the pump unit is obtained based on the comparison result, and a corresponding alarm is issued based on the sealing state.

Images