Management system for monitoring equipment defects on line

Abstract

The invention provides a management system for on-line monitoring of equipment defects, and belongs to the technical field of monitoring management, the method comprises an information acquisition module, a defect prediction module, a danger evaluation module and a model optimization module, data of to-be-monitored equipment is acquired to extract characteristic parameters of equipment health conditions, voiceprint construction is carried out, and a voiceprint result is obtained; the method determines the analysis defect and the prediction defect of the to-be-monitored equipment, generates a fault diagnosis report, evaluates the operation risk of the corresponding to-be-monitored equipment, and carries out feedback optimization on the defect prediction model of the equipment according to the real-time data, thereby achieving the real-time monitoring of the operation state of the equipment, finding the potential problems of the equipment in advance, and improving the safety of the equipment. The monitoring range can be effectively expanded, and powerful support can be provided for maintenance and optimization of equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring management, and in particular to a management system for online monitoring of equipment defects. Background Art

[0002] In the past few years, equipment maintenance has been a hot topic. From large industrial equipment to small household equipment, more effective maintenance and repair methods are always sought. However, with the development and upgrading of technology, it is not enough to repair equipment only when there is a problem. It is easy to accelerate equipment loss. In addition, the traditional monitoring method is to use red-hot external imaging and partial discharge monitoring, which have limited monitoring ranges and cannot effectively detect existing problems.

[0003] Therefore, the present invention provides a management system for online monitoring of equipment defects. Summary of the invention

[0004] The present invention provides a management system for online monitoring of equipment defects. The system collects data of the equipment to be monitored, extracts characteristic parameters of the equipment health status therefrom, constructs voiceprints, determines the analyzed defects and predicted defects of the equipment to be monitored, generates a fault diagnosis report, and evaluates the operating risks of the corresponding equipment to be monitored. The system then performs feedback optimization on the defect prediction model of the equipment based on the real-time data, thereby realizing real-time monitoring of the equipment's operating status and discovering potential problems of the equipment in advance. The monitoring scope can be effectively expanded, and strong support can be provided for equipment maintenance and optimization.

[0005] The present invention provides a management system for online monitoring of equipment defects, comprising: Information collection module: collects the sound information and vibration information of the equipment to be monitored to extract characteristic parameters that characterize the health status of the equipment, and constructs voiceprints for the characteristic parameters to obtain the analysis defects of the equipment to be monitored; Defect prediction module: inputs the collected information into the defect prediction model to obtain the predicted defects of the equipment to be monitored; Risk assessment module: generating a fault diagnosis report of the equipment to be monitored according to the analyzed defects and predicted defects, and assessing the operation risk of the equipment to be monitored, wherein the fault diagnosis report is related to the existing defect causes and the defect degree of each defect cause; Model optimization module: collects defect treatment effects of equipment whose operating risks reach the set risks in real time, and continuously optimizes the defect prediction model.

[0006] The present invention provides a management system for online monitoring of equipment defects, an information collection module, comprising: Ranking unit: obtains the importance levels of all types of operating components of the equipment to be monitored from the equipment-component importance table; Information conversion unit: converts the collected sound information into a sound spectrum diagram, and at the same time, converts the collected vibration information into a vibration visual diagram; Health parameter determination unit: constructing a standard feature model of the device to be monitored according to the standard operation data of the device to be monitored, and determining a device health feature parameter set according to the standard feature model; Standard voiceprint module: according to the importance level of each component in the device to be monitored, the characteristic parameters involved in each component are marked as important, and the standard voiceprint of the device to be monitored is constructed in combination with the device health characteristic parameter set; Analysis defect determination unit: constructs an operation voiceprint based on the sound spectrum diagram and the vibration visual diagram, and roughly compares it with the standard voiceprint to obtain the analysis defect of the equipment to be monitored.

[0007] The present invention provides a management system for online monitoring of equipment defects, a defect prediction module, comprising: Data correction unit: performs a first correction on the historical fault data according to the analyzed defects, and performs a second correction on the historical normal operation data, wherein the first correction amplitude is greater than the second correction amplitude; Range adjustment unit: constructing a device usage characteristic model according to the first correction result and the second correction, determining a device wear characteristic parameter set according to the usage characteristic model, adjusting a parameter range of a device health characteristic parameter set according to the device wear characteristic parameter set, and thereby obtaining a third characteristic parameter set related to the sound information and a fourth characteristic parameter set related to the vibration information; Model building unit: wear marking the corresponding components according to the characteristic parameters involved in each component, and building a defect prediction model in combination with the third characteristic parameter set and the fourth characteristic parameter set.

[0008] The present invention provides a management system for online monitoring of equipment defects, a risk assessment module, comprising: Setting interval unit: generating a corresponding discrete signal sequence in a time domain order according to the standard voiceprint combined with the analysis defect, setting a first initial change interval of sound and a second initial change interval of vibration according to the discrete signal sequence, adding wear parameters to the first initial change interval and the second initial change interval according to the predicted defect, and obtaining a corresponding first change speed interval and a second change speed interval; Calculation unit: calculates the comprehensive sound intensity change speed and the comprehensive sound frequency change speed of the collected sound information and vibration information at each collection moment; Screening unit: performing a first screening of all comprehensive sound intensity change speeds according to a first change speed interval, and performing a second screening of all comprehensive sound frequency change speeds according to a second change speed interval; Voiceprint prediction unit: determines the screening voiceprints composed of all speeds that meet the corresponding speed change interval at the same moment according to the first screening result and the second screening result, and predicts the degradation of the screening voiceprints at the next moment; Report generation unit: perform fault diagnosis on the equipment to be monitored according to the screening voiceprint and degradation prediction result at the same time, determine the fault type and the defect cause corresponding to the fault and the defect degree of the defect cause, and generate a fault diagnosis report.

[0009] The present invention provides a management system for online monitoring of equipment defects, a risk assessment module, and further includes: Evaluation unit: performing a first evaluation on the device to be monitored according to the technical performance, usage and safety level of the device to be monitored in the current environment; Performing a second assessment on the equipment to be monitored according to the equipment operation difficulty, maintenance difficulty and repair difficulty during the operation of the equipment to be monitored; Performing a third evaluation on the equipment to be monitored according to the equipment importance of the equipment to be monitored in the power plant, wherein the equipment importance is determined by the harm of the equipment to the power plant predicted by the fault diagnosis report of the equipment to be monitored; Risk determination unit: Determines the operating risk of the equipment to be monitored based on the first assessment, the second assessment and the third assessment.

[0010] The present invention provides a management system for online monitoring of equipment defects, a report generating unit, comprising: Voiceprint screening block: constructs the voiceprint vector at the corresponding moment based on the screened voiceprint and degradation prediction results at the same moment; Anomaly marking block: compares the voiceprint vector at each moment with the anomaly vectors of different types, and marks the anomaly type for each voiceprint vector; Type determination block: Determine the fault type of the device to be monitored based on the type labeling result of each voiceprint vector at each moment.

[0011] The present invention provides a management system for online monitoring of equipment defects, a computing unit, comprising: ; in, Indicates the speed of change of the comprehensive sound intensity at the corresponding acquisition time P; Indicates the speed of change of the sound frequency at the corresponding acquisition time P; Indicates the instantaneous sound intensity at the corresponding acquisition time P; Indicates the instantaneous vibration intensity at the corresponding acquisition time P; represents the sound impact function at the corresponding acquisition time P; represents the vibration impact function at the corresponding acquisition time P; It represents the intensity area composed of the sound information and vibration information involved at the corresponding acquisition time P; Indicates the instantaneous cumulative length of time corresponding to the acquisition time P; Indicates the cumulative effective time length of the sound information at the corresponding collection time P; Indicates the cumulative effective time length of vibration information at the corresponding collection time P; Indicates based on , as well as The variance of Indicates the collection period of sound information and vibration information; represents the logarithmic function symbol; exp represents the exponential function symbol.

[0012] The present invention provides a management system for online monitoring of equipment defects, a model optimization module, comprising: Range determination unit: set the risk level range according to the historical fault diagnosis list and the operational risk of the corresponding fault; Effect evaluation unit: evaluate the effect of equipment defect treatment according to the corresponding set risk level range of the operation risk; Optimization unit: Optimize the defect prediction model based on effect evaluation and defect handling methods.

[0013] Compared with the prior art, the beneficial effects of the present application are as follows: by collecting data of the equipment to be monitored, characteristic parameters of the equipment health status are extracted therefrom, voiceprints are constructed, analytical defects and predicted defects of the equipment to be monitored are determined, fault diagnosis reports are generated, and the operating risks of the corresponding equipment to be monitored are evaluated, and then feedback optimization is performed on the defect prediction model of the equipment based on real-time data, thereby realizing real-time monitoring of the equipment's operating status and discovering potential problems of the equipment in advance. The monitoring scope can be effectively expanded, and it can also provide strong support for equipment maintenance and optimization.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a structural diagram of a management system for online monitoring of equipment defects provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Embodiment 1: The embodiment of the present invention provides a management system for online monitoring of equipment defects, such as Figure 1 As shown, including: Information collection module: collects the sound information and vibration information of the equipment to be monitored to extract characteristic parameters that characterize the health status of the equipment, and constructs voiceprints for the characteristic parameters to obtain the analysis defects of the equipment to be monitored; Defect prediction module: inputs the collected information into the defect prediction model to obtain the predicted defects of the equipment to be monitored; Risk assessment module: generating a fault diagnosis report of the equipment to be monitored according to the analyzed defects and predicted defects, and assessing the operation risk of the equipment to be monitored, wherein the fault diagnosis report is related to the existing defect causes and the defect degree of each defect cause; Model optimization module: collects defect treatment effects of equipment whose operating risks reach the set risks in real time, and continuously optimizes the defect prediction model.

[0019] In this embodiment, the characteristic parameters may include the peak frequency representing the frequency with the highest energy in the audio signal, corresponding to a specific action or vibration of a component during the operation of the device; the total energy may reflect the overall operating status of the device, and the occurrence of abnormal frequencies may indicate loss or failure of a part of the device.

[0020] In this embodiment, voiceprint construction is a device feature model constructed based on the sound information emitted by the device. After the feature parameters of the device sound information are extracted, the voiceprint is constructed using these parameters, and the status of the device is identified and judged through the voiceprint.

[0021] In this embodiment, defect analysis refers to the extraction of characteristic parameters and voiceprint construction based on the sound information and vibration information of the monitored equipment, and the current problems or abnormalities of the equipment, such as wear, failure, abnormal sound or vibration of certain parts, etc. This defect is found based on the comparison of the normal operation data of the equipment in the past, that is, it is identified by analyzing the difference between the current operating state of the equipment and the normal state.

[0022] In this embodiment, the defect prediction model determines the relationship between the equipment operation rules and equipment failures based on historical data and learned rules, and predicts possible problems that may arise in the equipment in the future. The input data is historical failure data and historical normal operation data, and the output data is possible defects. The training number is 10,000 times.

[0023] In this embodiment, predicting defects means inputting the current device status information into a trained defect prediction model, and the model predicts possible future failures or problems of the device based on historical data and learned rules.

[0024] In this embodiment, the fault diagnosis report is obtained by analyzing the change speed interval of the voiceprint set by the defect and the predicted defect, calculating the comprehensive sound intensity change speed and the comprehensive sound frequency change speed of the monitored equipment, judging whether the calculation result exists in the interval, determining the screening voiceprint, predicting the degradation of the screening voiceprint, and determining the fault situation and the corresponding processing method according to the degradation prediction result.

[0025] In this embodiment, the operational risk is assessed from three aspects: the technical performance, usage and safety level of the monitored equipment in the current environment, the difficulty of equipment operation, maintenance and overhaul during the operation of the monitored equipment, and the importance of the equipment in the power plant.

[0026] In this embodiment, the defect handling effect is obtained by comparing the subsequent tracking data of the defect handling with the current operating risk level. For example, if the subsequent tracking data is consistent with the standard operating data, the defect handling effect is excellent. Depending on the deviation, the effect decreases to good, medium and poor.

[0027] The working principle and beneficial effects of the above technical solution are: by collecting data of the equipment to be monitored, characteristic parameters of the equipment health status are extracted therefrom, voiceprint is constructed, the analysis defects and predicted defects of the equipment to be monitored are determined, a fault diagnosis report is generated, and the operation risk of the corresponding equipment to be monitored is evaluated, and then the real-time data is used to optimize the defect prediction model of the equipment, thereby realizing real-time monitoring of the equipment's operating status, discovering potential problems of the equipment in advance, and the monitoring scope can be effectively expanded, and it can also provide strong support for equipment maintenance and optimization.

[0028] Embodiment 2: The embodiment of the present invention provides a management system for online monitoring of equipment defects, an information collection module, including: Ranking unit: obtains the importance levels of all types of operating components of the equipment to be monitored from the equipment-component importance table; Information conversion unit: converts the collected sound information into a sound spectrum diagram, and at the same time, converts the collected vibration information into a vibration visual diagram; Health parameter determination unit: constructing a standard feature model of the device to be monitored according to the standard operation data of the device to be monitored, and determining a device health feature parameter set according to the standard feature model; Standard voiceprint module: according to the importance level of each component in the device to be monitored, the characteristic parameters involved in each component are marked as important, and the standard voiceprint of the device to be monitored is constructed in combination with the device health characteristic parameter set; Analysis defect determination unit: constructs an operation voiceprint based on the sound spectrum diagram and the vibration visual diagram, and roughly compares it with the standard voiceprint to obtain the analysis defect of the equipment to be monitored.

[0029] In this embodiment, the equipment-component importance table is the degree of impact of a component failure of the monitored equipment within a certain period of time under standard operating conditions on the overall operation of the monitored equipment. For example, if the corresponding operating component of the power equipment that monitors the power production fails, the importance is 2; if the operating component corresponding to the power production of the power equipment fails, the importance is 10, and the highest importance is 10.

[0030] In this embodiment, the importance levels are distributed according to the distribution of importance, with importance 1-3 being primary, importance 4-7 being intermediate, and importance 8-10 being critical.

[0031] In this embodiment, the standard feature model is a simulation model of the standard operating conditions of the monitored equipment. The input is the standard operating data of the same type of equipment and the standard operating data of the monitored equipment. The output is the equipment health feature parameters. The training times are 5000.

[0032] In this embodiment, the device health characteristic parameter set includes the peak frequency, total energy and abnormal frequency of the device to be monitored under standard operation conditions.

[0033] In this embodiment, the rough comparison is a comparison of the consistency between the running voiceprint and the standard voiceprint image.

[0034] The working principle and beneficial effects of the above technical solution are: by collecting information on the monitored equipment, determining the operating voiceprint of the equipment, determining the standard voiceprint of the equipment based on the information under the standard operation of the equipment, determining the analytical defects of the monitored equipment, and realizing timely determination of equipment losses in different time periods, providing strong support for equipment maintenance and optimization.

[0035] Embodiment 3: The embodiment of the present invention provides a management system for online monitoring of equipment defects, a defect prediction module, including: Data correction unit: performs a first correction on the historical fault data according to the analyzed defects, and performs a second correction on the historical normal operation data, wherein the first correction amplitude is greater than the second correction amplitude; Range adjustment unit: constructing a device usage characteristic model according to the first correction result and the second correction, determining a device wear characteristic parameter set according to the usage characteristic model, adjusting a parameter range of a device health characteristic parameter set according to the device wear characteristic parameter set, and thereby obtaining a third characteristic parameter set related to the sound information and a fourth characteristic parameter set related to the vibration information; Model building unit: wear marking the corresponding components according to the characteristic parameters involved in each component, and building a defect prediction model in combination with the third characteristic parameter set and the fourth characteristic parameter set.

[0036] In this embodiment, a feature model is used to simulate the current equipment condition of the equipment to be monitored. The input is the current operating data of the equipment to be monitored, and the output is the wear feature parameters of the equipment to be monitored. The training times are 10,000 times.

[0037] In this embodiment, the first correction and the second correction are corrections to the historical fault data and the historical normal operation data according to the inherent analysis defects of the equipment to be monitored.

[0038] In this embodiment, the equipment wear characteristic parameter set includes parameters corresponding to operating errors caused by mechanical wear and material oxidation.

[0039] In this embodiment, the third characteristic parameter set includes frequency, amplitude, and phase, and the fourth characteristic parameter set includes vibration frequency and amplitude.

[0040] In this embodiment, the parameter range adjustment is to make a one-to-one correspondence between the wear characteristic parameter set and the influencing components of the equipment health characteristic parameters, add the wear characteristic parameter factor to the equipment health characteristic parameters at the corresponding position, and reduce the range of the equipment health characteristic parameter set to the corresponding components.

[0041] In this embodiment, the defect prediction model is a model for predicting defects on the operating data of the equipment to be monitored, the input is the current operating data of the equipment to be monitored, and the output is the overall defect situation of the equipment to be monitored.

[0042] The working principle and beneficial effects of the above technical solution are: by correcting historical data based on defect analysis, determining the wear condition of the equipment to be monitored, adjusting the parameters of the collected sound data and vibration data, building a defect prediction model, and realizing the prediction of possible equipment failure at the next moment, reducing equipment loss, and providing strong support for equipment maintenance and optimization.

[0043] Embodiment 4: The embodiment of the present invention provides a management system for online monitoring of equipment defects, a risk assessment module, including: Setting interval unit: generating a corresponding discrete signal sequence in a time domain order according to the standard voiceprint combined with the analysis defect, setting a first initial change interval of sound and a second initial change interval of vibration according to the discrete signal sequence, adding wear parameters to the first initial change interval and the second initial change interval according to the predicted defect, and obtaining a corresponding first change speed interval and a second change speed interval; Calculation unit: calculates the comprehensive sound intensity change speed and the comprehensive sound frequency change speed of the collected sound information and vibration information at each collection moment; Screening unit: performing a first screening of all comprehensive sound intensity change speeds according to a first change speed interval, and performing a second screening of all comprehensive sound frequency change speeds according to a second change speed interval; Voiceprint prediction unit: determines the screening voiceprints composed of all speeds that meet the corresponding speed change interval at the same moment according to the first screening result and the second screening result, and predicts the degradation of the screening voiceprints at the next moment; Report generation unit: perform fault diagnosis on the equipment to be monitored according to the screening voiceprint and degradation prediction result at the same time, determine the fault type and the defect cause corresponding to the fault and the defect degree of the defect cause, and generate a fault diagnosis report.

[0044] In this embodiment, the first initial change interval and the second initial change interval are initial range settings for the collected data based on defect analysis, and the first change speed interval and the second change speed interval are secondary range precisions for adding wear parameters to the range setting to stabilize the range setting. For example, the former range is [1,10] and the latter range is [2.5,8.8].

[0045] In this embodiment, the maximum value and the minimum value of the discrete signal sequence are used as the first initial change interval of the sound, and the maximum change value and the minimum change value of the discrete signal sequence are used as the second initial change interval of the vibration.

[0046] In this embodiment, the wear characteristic parameter set is standardized, and then the standardized result is normally distributed, the wear factor corresponding to the highest peak is taken, and the wear factor is multiplied with the first initial change interval and the second initial change interval to obtain the first change speed interval and the second change speed interval.

[0047] In this embodiment, the screening criterion is that data that does not belong to the first change speed interval and the second change speed interval are used as the first screening result and the second screening result.

[0048] In this embodiment, degradation prediction uses a Gaussian mixture degradation prediction algorithm to degrade the screening voiceprints, and then diagnose possible faults.

[0049] In this embodiment, the fault diagnosis report gives recommended repair and maintenance measures based on the analyzed defects and predicted defects found, including replacing a component, adjusting the working mode of the equipment, or conducting a more in-depth inspection. At the same time, the maintenance and repair actions are prioritized according to the severity of each defect and the impact on the equipment, with a focus on problems that may cause serious damage to the equipment or affect the main functions of the equipment.

[0050] The working principle and beneficial effects of the above technical solution are: by analyzing defects and predicting defects to set the change speed range of voiceprints, calculating the comprehensive sound intensity change speed and the comprehensive sound frequency change speed of the monitored equipment, judging whether the calculation result exists in the range, determining the screening voiceprints, predicting the degradation of the screening voiceprints, and generating a fault diagnosis report, the accuracy of predicting possible failures of the monitored equipment is improved.

[0051] Embodiment 5: The embodiment of the present invention provides a management system for online monitoring of equipment defects, a risk assessment module, and further includes: Evaluation unit: performing a first evaluation on the device to be monitored according to the technical performance, usage and safety level of the device to be monitored in the current environment; Performing a second assessment on the equipment to be monitored according to the equipment operation difficulty, maintenance difficulty and repair difficulty during the operation of the equipment to be monitored; Performing a third evaluation on the equipment to be monitored according to the equipment importance of the equipment to be monitored in the power plant, wherein the equipment importance is determined by the harm of the equipment to the power plant predicted by the fault diagnosis report of the equipment to be monitored; Risk determination unit: Determines the operating risk of the equipment to be monitored based on the first assessment, the second assessment and the third assessment.

[0052] In this embodiment, the operational risks include mechanical risks, motor risks, radiation risks, explosion risks, etc.

[0053] In this embodiment, the lowest level of the evaluation results of the first evaluation, the second evaluation, and the third evaluation is used as the operation risk level to further determine the operation risk.

[0054] The working principle and beneficial effects of the above technical solution are: to evaluate the operating risks of the monitored equipment from three aspects, to help understand the current health status of the equipment, and to predict the possible operating risks of the equipment in the future, so as to take preventive or repair measures in advance and reduce the impact of equipment failure.

[0055] Embodiment 6: The embodiment of the present invention provides a management system for online monitoring of equipment defects, a report generating unit, including: Voiceprint screening block: constructs the voiceprint vector at the corresponding moment based on the screened voiceprint and degradation prediction results at the same moment; Anomaly marking block: compares the voiceprint vector at each moment with the anomaly vectors of different types, and marks the anomaly type for each voiceprint vector; Type determination block: Determine the fault type of the device to be monitored based on the type labeling result of each voiceprint vector at each moment.

[0056] In this embodiment, the fault types that can be monitored by voiceprint anomalies include mechanical wear, insufficient lubrication, motor failure, electrical failure, poor contact of equipment, and other fault types.

[0057] The working principle and beneficial effect of the above technical solution are: by traversing the abnormal vector of the voiceprint vector at each moment, the traversal result can be used to further judge the health status of the equipment, perform fault diagnosis and prediction, reduce equipment loss, and provide strong support for equipment maintenance and optimization.

[0058] Embodiment 7: An embodiment of the present invention provides a management system for online monitoring of equipment defects, a computing unit, including: ; in, Indicates the speed of change of the comprehensive sound intensity at the corresponding acquisition time P; Indicates the speed of change of the sound frequency at the corresponding acquisition time P; Indicates the instantaneous sound intensity at the corresponding acquisition time P; Indicates the instantaneous vibration intensity at the corresponding acquisition time P; represents the sound impact function at the corresponding acquisition time P; represents the vibration impact function at the corresponding acquisition time P; It represents the intensity area composed of the sound information and vibration information involved at the corresponding acquisition time P; Indicates the instantaneous cumulative length of time corresponding to the acquisition time P; Indicates the cumulative effective time length of the sound information at the corresponding collection time P; Indicates the cumulative effective time length of vibration information at the corresponding collection time P; Indicates based on , as well as The variance of Indicates the collection period of sound information and vibration information; represents the logarithmic function symbol; exp represents the exponential function symbol.

[0059] The working principle and beneficial effects of the above technical solution are: by calculating the comprehensive sound intensity change rate and the comprehensive sound frequency change rate of the collected sound information and vibration information at each collection moment, it is possible to accurately determine the fault condition and the corresponding type, providing strong support for equipment maintenance and optimization.

[0060] Embodiment 8: The embodiment of the present invention provides a management system for online monitoring of equipment defects, a model optimization module, including: Range determination unit: set the risk level range according to the historical fault diagnosis list and the operational risk of the corresponding fault; Effect evaluation unit: evaluate the effect of equipment defect treatment according to the corresponding set risk level range of the operation risk; Optimization unit: Optimize the defect prediction model based on effect evaluation and defect handling methods.

[0061] In this embodiment, the effect evaluation is to track the subsequent data of the effect of defect treatment, and to evaluate the effect according to the deviation between the subsequent data and the standard data. The results of the effect evaluation include excellent, good, medium and poor.

[0062] In this embodiment, the risk level range is to classify the risk according to the fault situation. If the fault is a cascading fault, the risk level is higher, and if the fault causes great damage to the equipment, the risk level is high.

[0063] In this embodiment, the defect prediction model is optimized by adjusting the defect handling method according to the result of the effect evaluation. If the result of the effect evaluation is still poor after the adjustment, the defect prediction process corresponding to the fault is supplemented by analyzing the defects.

[0064] The working principle and beneficial effects of the above technical solution are: setting the risk level range through historical fault diagnosis sheets, evaluating the effect of equipment defect handling, and finally optimizing and adjusting the data feedback of the defect prediction model according to the evaluation results, thereby realizing real-time monitoring of the equipment's operating status and discovering potential problems of the equipment in advance.

[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A management system for online monitoring of equipment defects, characterized in that: include: Information collection module: collects the sound information and vibration information of the equipment to be monitored to extract characteristic parameters that characterize the health status of the equipment, and constructs voiceprints for the characteristic parameters to obtain the analysis defects of the equipment to be monitored; Defect prediction module: inputs the collected information into the defect prediction model to obtain the predicted defects of the equipment to be monitored; Risk assessment module: generating a fault diagnosis report of the equipment to be monitored according to the analyzed defects and predicted defects, and assessing the operation risk of the equipment to be monitored, wherein the fault diagnosis report is related to the existing defect causes and the defect degree of each defect cause; Model optimization module: collects defect treatment effects of equipment whose operating risks reach the set risks in real time, and continuously optimizes the defect prediction model.

2. A management system for online monitoring of equipment defects according to claim 1, characterized in that: Information collection module, including: Ranking unit: obtains the importance levels of all types of operating components of the equipment to be monitored from the equipment-component importance table; Information conversion unit: converts the collected sound information into a sound spectrum diagram, and at the same time, converts the collected vibration information into a vibration visual diagram; Health parameter determination unit: constructing a standard feature model of the device to be monitored according to the standard operation data of the device to be monitored, and determining a device health feature parameter set according to the standard feature model; Standard voiceprint module: according to the importance level of each component in the device to be monitored, the characteristic parameters involved in each component are marked as important, and the standard voiceprint of the device to be monitored is constructed in combination with the device health characteristic parameter set; Analysis defect determination unit: constructs an operation voiceprint based on the sound spectrum diagram and the vibration visual diagram, and roughly compares it with the standard voiceprint to obtain the analysis defect of the equipment to be monitored.

3. A management system for online monitoring of equipment defects according to claim 1, characterized in that: Defect prediction module, including: Data correction unit: performs a first correction on the historical fault data according to the analyzed defects, and performs a second correction on the historical normal operation data, wherein the first correction amplitude is greater than the second correction amplitude; Range adjustment unit: constructing a device usage characteristic model according to the first correction result and the second correction, determining a device wear characteristic parameter set according to the usage characteristic model, adjusting a parameter range of a device health characteristic parameter set according to the device wear characteristic parameter set, and thereby obtaining a third characteristic parameter set related to the sound information and a fourth characteristic parameter set related to the vibration information; Model building unit: wear marking the corresponding components according to the characteristic parameters involved in each component, and building a defect prediction model in combination with the third characteristic parameter set and the fourth characteristic parameter set.

4. A management system for online monitoring of equipment defects according to claim 1, characterized in that: Hazard assessment module, including: Setting interval unit: generating a corresponding discrete signal sequence in a time domain order according to the standard voiceprint combined with the analysis defect, setting a first initial change interval of sound and a second initial change interval of vibration according to the discrete signal sequence, adding wear parameters to the first initial change interval and the second initial change interval according to the predicted defect, and obtaining a corresponding first change speed interval and a second change speed interval; Calculation unit: calculates the comprehensive sound intensity change speed and the comprehensive sound frequency change speed of the collected sound information and vibration information at each collection moment; Screening unit: performing a first screening of all comprehensive sound intensity change speeds according to a first change speed interval, and performing a second screening of all comprehensive sound frequency change speeds according to a second change speed interval; Voiceprint prediction unit: determines the screening voiceprints composed of all speeds that meet the corresponding speed change interval at the same moment according to the first screening result and the second screening result, and predicts the degradation of the screening voiceprints at the next moment; Report generation unit: perform fault diagnosis on the equipment to be monitored according to the screening voiceprint and degradation prediction result at the same time, determine the fault type and the defect cause corresponding to the fault and the defect degree of the defect cause, and generate a fault diagnosis report.

5. A management system for online monitoring of equipment defects according to claim 4, characterized in that: The hazard assessment module also includes: Evaluation unit: performing a first evaluation on the device to be monitored according to the technical performance, usage and safety level of the device to be monitored in the current environment; Performing a second assessment on the equipment to be monitored according to the equipment operation difficulty, maintenance difficulty and repair difficulty during the operation of the equipment to be monitored; Performing a third evaluation on the equipment to be monitored according to the equipment importance of the equipment to be monitored in the power plant, wherein the equipment importance is determined by the harm of the equipment to the power plant predicted by the fault diagnosis report of the equipment to be monitored; Risk determination unit: Determines the operating risk of the equipment to be monitored based on the first assessment, the second assessment and the third assessment.

6. A management system for online monitoring of equipment defects according to claim 4, characterized in that: Report generation unit, including: Voiceprint screening block: constructs the voiceprint vector at the corresponding moment based on the screened voiceprint and degradation prediction results at the same moment; Anomaly marking block: compares the voiceprint vector at each moment with the anomaly vectors of different types, and marks the anomaly type for each voiceprint vector; Type determination block: Determine the fault type of the device to be monitored based on the type labeling result of each voiceprint vector at each moment.

7. A management system for online monitoring of equipment defects according to claim 4, characterized in that: Computing unit, including: ； in, Indicates the speed of change of the comprehensive sound intensity at the corresponding acquisition time P; Indicates the speed of change of the sound frequency at the corresponding acquisition time P; Indicates the instantaneous sound intensity at the corresponding acquisition time P; Indicates the instantaneous vibration intensity at the corresponding acquisition time P; represents the sound impact function at the corresponding acquisition time P; represents the vibration impact function at the corresponding acquisition time P; It represents the intensity area composed of the sound information and vibration information involved at the corresponding acquisition time P; Indicates the instantaneous cumulative length of time corresponding to the acquisition time P; Indicates the cumulative effective time length of the sound information at the corresponding collection time P; Indicates the cumulative effective time length of vibration information at the corresponding collection time P; Indicates based on , as well as The variance of Indicates the collection period of sound information and vibration information; represents the logarithmic function symbol; exp represents the exponential function symbol.

8. A management system for online monitoring of equipment defects according to claim 1, characterized in that: Model optimization module, including: Range determination unit: set the risk level range according to the historical fault diagnosis list and the operational risk of the corresponding fault; Effect evaluation unit: evaluate the effect of equipment defect treatment according to the corresponding set risk level range of the operation risk; Optimization unit: Optimize the defect prediction model based on effect evaluation and defect handling methods.

Images