Coal power equipment fault intelligent diagnosis method, device, equipment, medium and product

Abstract

The invention discloses a coal power equipment fault intelligent diagnosis method and device, equipment, a medium and a product. The method comprises the following steps: acquiring operation state data of target coal power equipment, and determining equipment characteristic data according to the operation state data; inputting the equipment feature data into an intelligent diagnosis model obtained by pre-training to obtain a first fault mode output by the model and a mode prediction similarity corresponding to the first fault mode; and inputting the equipment feature data into a pre-constructed expert rule base for fault mode matching, and obtaining a second fault mode and a mode matching confidence coefficient corresponding to the second fault mode, and generating an equipment fault diagnosis result of the target coal power equipment according to the first fault mode and the mode prediction similarity corresponding to the first fault mode and the second fault mode and the mode matching confidence corresponding to the second fault mode. According to the technical scheme of the embodiment of the invention, the intelligent fault diagnosis efficiency and diagnosis accuracy of the coal power equipment in a power grid scene are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent detection and fault diagnosis, and in particular to a coal power equipment fault intelligent diagnosis method, device, equipment, medium and product. BACKGROUND

[0002] As the base load power source in China's energy supply system, coal power bears the core responsibility of ensuring the stable operation of the power system and energy security. Its core equipment, such as steam turbine generator units and boilers, has been in continuous operation under high temperature, high pressure and high load for a long time, which is prone to failure due to mechanical wear, thermal stress fatigue, medium corrosion and other factors. If the equipment failure cannot be quickly solved, it may cause major safety accidents and safety risks. Therefore, realizing real-time, accurate and automatic diagnosis of coal power equipment failure is a key technical requirement for ensuring the safe and efficient operation of coal power plants.

[0003] At present, the field of coal power equipment fault diagnosis mainly relies on two types of technical solutions. One is the traditional manual fault diagnosis method, and the other is intelligent early warning based on a single parameter early warning or simple rule-based diagnosis model. However, although the existing coal power equipment diagnosis has realized intelligent demand to some extent, there are still problems of low diagnosis efficiency and insufficient diagnosis accuracy in the actual fault diagnosis process, which cannot meet the diagnosis scene demand of high safety, complex working conditions and multiple fault types of coal power equipment. SUMMARY

[0004] The present application provides a coal power equipment fault intelligent diagnosis method, device, equipment, medium and product to improve the intelligent diagnosis efficiency and accuracy of coal power equipment failure in power grid scenarios, so as to meet the diagnosis scene demand of high safety, complex working conditions and multiple fault types of coal power equipment.

[0005] According to an aspect of the present application, a coal power equipment fault intelligent diagnosis method is provided, which comprises:

[0006] Obtaining the running state data of the target coal power equipment, and determining the equipment characteristic data according to the running state data;

[0007] Inputting the equipment characteristic data into the pre-trained intelligent diagnosis model to obtain the first fault mode and its corresponding mode prediction similarity output by the model; and,

[0008] Inputting the equipment characteristic data into the pre-constructed expert rule base for fault mode matching to obtain the second fault mode and its corresponding mode matching confidence;

[0009] According to the first fault mode and the corresponding mode prediction similarity thereof and the second fault mode and the corresponding mode matching confidence thereof, a device fault diagnosis result of the target coal power equipment is generated.

[0010] According to another aspect of the present application, a coal power equipment fault intelligent diagnosis device is provided, the device comprising:

[0011] a state data acquisition module, configured to acquire operation state data of a target coal power equipment, and determine device feature data according to the operation state data;

[0012] a first fault prediction module, configured to input the device feature data into a pre-trained intelligent diagnosis model to obtain a first fault mode and a corresponding mode prediction similarity thereof output by the model; and

[0013] a second fault prediction module, configured to input the device feature data into a pre-constructed expert rule base to perform fault mode matching to obtain a second fault mode and a corresponding mode matching confidence thereof;

[0014] a device fault diagnosis module, configured to generate a device fault diagnosis result of the target coal power equipment according to the first fault mode and the corresponding mode prediction similarity thereof and the second fault mode and the corresponding mode matching confidence thereof.

[0015] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory in communication connection with the at least one processor; wherein

[0018] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the coal power equipment fault intelligent diagnosis method according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium storing computer instructions for enabling a processor to execute the coal power equipment fault intelligent diagnosis method according to any one of the embodiments of the present application.

[0020] According to another aspect of the present application, a computer program product is provided, the computer program product comprising a computer program, and the computer program is executed by a processor to implement the coal power equipment fault intelligent diagnosis method according to any one of the embodiments of the present application.

[0021] The technical scheme of the embodiment of the present application obtains the running state data of the target coal power equipment, determines the equipment characteristic data according to the running state data, inputs the equipment characteristic data into the intelligent diagnosis model obtained by pre-training, obtains the first fault mode and the corresponding mode prediction similarity output by the model, inputs the equipment characteristic data into the expert rule base constructed in advance to perform fault mode matching, obtains the second fault mode and the corresponding mode matching confidence, and generates the equipment fault diagnosis result of the target coal power equipment according to the first fault mode, the corresponding mode prediction similarity, the second fault mode and the corresponding mode matching confidence. The above technical scheme considers both the fault prediction result of the intelligent diagnosis model and the fault matching result of the expert rule base in the process of coal power equipment fault diagnosis, realizes the prediction of the coal power equipment fault mode from multiple dimensions, improves the intelligent diagnosis efficiency and diagnosis accuracy of the coal power equipment in the power grid scene, and thus meets the diagnosis scene demand of high safety, complex working conditions and multiple fault types of the coal power equipment.

[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0024] Figure 1 is a flow chart of a coal power equipment fault intelligent diagnosis method according to the first embodiment of the present application;

[0025] Figure 2 is a flow chart of a coal power equipment fault intelligent diagnosis method according to the second embodiment of the present application;

[0026] Figure 3 is a structural schematic diagram of a coal power equipment fault intelligent diagnosis device according to the third embodiment of the present application;

[0027] Figure 4 is a structural schematic diagram of an electronic device for implementing the coal power equipment fault intelligent diagnosis method of the present application. DETAILED DESCRIPTION

[0028] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0029] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0030] Embodiment one

[0031] Figure 1 A flowchart of a coal power equipment fault intelligent diagnosis method provided by the first embodiment of the present application is provided. The present embodiment can be applicable to the case of intelligent diagnosis of coal power equipment fault in the power grid scene. The method can be executed by a coal power equipment fault intelligent diagnosis device. The coal power equipment fault intelligent diagnosis device can be realized in the form of hardware and / or software, and can be configured in an electronic device. As shown in the figure, the method comprises: Figure 1

[0032] S110, obtaining the running state data of the target coal power equipment, and determining the equipment characteristic data according to the running state data.

[0033] S120A, inputting the equipment characteristic data into the intelligent diagnosis model obtained by pre-training to obtain the first fault mode and its corresponding mode prediction similarity output by the model.

[0034] S120B, inputting the equipment characteristic data into the pre-constructed expert rule base to perform fault mode matching, and obtaining the second fault mode and its corresponding mode matching confidence.

[0035] S130, generating the equipment fault diagnosis result of the target coal power equipment according to the first fault mode and its corresponding mode prediction similarity and the second fault mode and its corresponding mode matching confidence. ​

[0036] The target coal power equipment can be a coal power equipment to be detected for faults, and the number of target coal power equipment can be one or more, specifically, all coal power equipment in a corresponding power grid region that needs to be monitored for faults in real time. The target coal power equipment can be different types of equipment, for example, the target coal power equipment can be a steam turbine generator unit, a boiler, a water supply pump, an induced draft fan, and a supply fan, etc.

[0037] The running state data of different types of target coal power equipment can be the same or different. For example, the running state data corresponding to the steam turbine generator unit bearing seat, the fan impeller, and the water pump bearing can include mechanical vibration data, and the core detection parameters can include vibration displacement, vibration speed, vibration acceleration, and shaft center trajectory. The running state data corresponding to the rotating equipment bearing, the motor, and the boiler of the coal power equipment can include temperature data, including bearing temperature, motor winding temperature, medium temperature, and component surface temperature, etc. The running state data of the boiler, the steam turbine oil system, and the water supply pump of the coal power equipment can include pressure data, and the core detection parameters can include medium pressure, oil system pressure, and wind pressure, etc. The running state data of the boiler water supply system, the flue gas system, and the coal mill coal supply system can include flow data, and the core detection parameters can include medium flow, gas flow, and fuel flow, etc. The running state data of all electric auxiliary machines, such as coal mills, pumps, and fans, can include electrical parameter data, and the core detection parameters can include motor current, motor voltage, power factor, and insulation resistance, etc. The running state data of the steam turbine rotor and the boiler pipeline of the coal power equipment can include auxiliary monitoring data, and the core detection parameters can include acoustic emission signal, oil parameter, rotating speed, and displacement, etc.

[0038] It should be noted that the obtained original running state data of the target coal power equipment usually has noise interference, such as power grid fluctuation, equipment vibration superposition, repeated data, and inconsistent format, etc. Therefore, the obtained running state data needs to be pre-processed, and the specific processing methods can include data cleaning, noise suppression, data resampling, and data segmentation, etc. The running state data after pre-processing is subjected to feature extraction to obtain equipment feature data.

[0039] Specifically, the device feature data capable of accurately reflecting the fault state is extracted from the pre-processed operating state data, such as time-frequency features, frequency domain features, and time-frequency domain features. Among them, the time domain features can reflect the overall intensity and fluctuation of the data, such as peak value, effective value, pulse index, and mean value. Coal power equipment faults such as bearing and rotor faults are often accompanied by signal enhancement at specific frequencies, such as BPFO (Ball Pass Frequency of Outer Race, outer race rolling element passing frequency) frequency corresponding to bearing outer ring fault, and 2 times frequency corresponding to rotor misalignment. Fourier transform (FFT) can be used to convert time domain data into frequency domain data, such as frequency spectrum, to extract frequency-related features, including feature frequency replication, frequency peak ratio, spectral barycenter, and harmonic content. When coal power equipment starts and stops, the load is adjusted, the speed and load change with time, and the data is non-stationary, such as when the speed increases from 0 to 3000r / min, the frequency changes with the speed. At this time, the Fourier transform will be distorted, and the wavelet transform (WT) and Hilbert-Huang transform (HHT) can be used to extract time-frequency domain features to capture fault signals under dynamic working conditions. Time-frequency domain features can include wavelet energy entropy, marginal spectrum peak value, and instantaneous frequency.

[0040] Optionally, a single parameter such as vibration may not be able to fully reflect the fault, such as normal vibration but sudden temperature rise may be bearing lubrication failure, therefore, multiple single parameters can be fused in multiple dimensions to form a fusion feature parameter, and the fusion feature parameter is also used as the device feature data. For example, the fusion feature parameter can include a feature vector combination obtained by vector fusion of time domain, frequency domain, and auxiliary parameters; and a correlation coefficient between two parameters is determined to obtain a correlation coefficient.

[0041] The device feature data is input into the pre-trained intelligent diagnosis model to obtain a first fault mode predicted by the model and a model prediction similarity corresponding to the first fault mode. The intelligent diagnosis model can be pre-trained by a related technical personnel, and the intelligent diagnosis model is used for fault mode prediction of the target coal power equipment. The model prediction similarity is the degree of certainty of the model for the output first fault mode, when the model prediction similarity is low, it means that the certainty of the intelligent diagnosis model for the predicted fault mode is not high, that is, the first fault mode may not be accurate, and it may be a new type of fault that the model has not trained.

[0042] The embodiment also provides a model training method of an intelligent diagnosis model. In an optional embodiment, the model training method of the intelligent diagnosis model is as follows:

[0043] The historical feature data of the historical coal power equipment in the historical time period is acquired, and a real fault mode corresponding thereto is determined; the historical feature data of the historical coal power equipment and the real fault mode corresponding thereto are input into a network model selected in advance, to obtain a predicted fault mode output by the model; and the network model is trained according to the real fault mode and the predicted fault mode, until a preset model training end condition is met, to obtain an intelligent diagnosis model.

[0044] The network model can be selected in advance by a person skilled in the relevant field, for example, the network model can be an LSTM (Long Short-Term Memory, long short-term memory network).

[0045] For example, the historical feature data of the historical coal power equipment and the real fault mode corresponding thereto are input into the network model selected in advance, to obtain a predicted fault mode output by the model and a predicted fault similarity. According to the real fault mode and the predicted fault mode, a current loss value in the current iteration time period is determined based on a preset loss function. If the current loss value reaches a preset loss threshold or the current loss value tends to be stable or the current iteration number reaches a set iteration number threshold, it is indicated that the model training is ended, and the intelligent diagnosis model is obtained.

[0046] The expert rule base stores fault modes for diagnosing faults, which can be derived from expert knowledge, and the fault modes recorded in the expert rule base can be edited and expanded according to the actual diagnosis experience of experts, so as to continuously optimize and accumulate knowledge of the expert rule base. Specifically, the expert rule base is essentially a knowledge-based reasoning system, and the correspondence between coal power equipment faults and features has formed a mature theory. For example, a fault of misalignment corresponds to a 2-fold frequency peak value increase, which can be converted into an explicit logical rule. The rule base supports editing and expansion, and new fault rules such as new composite faults can be manually entered to realize knowledge iteration, which meets the flexible configuration requirements of the industrial coal power scene.

[0047] Specifically, the equipment feature data is matched with the features recorded in the expert rule base, so as to select the feature with the highest similarity matching, and the fault corresponding to the feature is taken as the second fault mode. The expert rule base generates the mode matching confidence while generating the second fault mode. That is, the expert rule base gives the confidence degree of the second fault mode. When the mode matching confidence is higher, it indicates that the confidence degree of the result of the second fault mode output by the expert rule base is higher; when the mode matching confidence is lower, it indicates that the confidence degree of the result of the second fault mode output by the expert rule base is lower.

[0048] According to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence, a device fault diagnosis result of the target coal power equipment is generated. Specifically, if the first fault mode and the second fault mode are the same, and the mode prediction similarity is greater than a preset similarity threshold, and the mode matching confidence is greater than a preset confidence threshold, the first fault mode or the second fault mode is taken as the device fault diagnosis result of the target coal power equipment. The similarity threshold and the confidence threshold can be preset by a related technical person, and the similarity threshold and the confidence threshold can be set to be the same or different, for example, the similarity threshold and the confidence threshold can be set to 90%.

[0049] If the first fault mode and the second fault mode are different, and the mode prediction similarity is greater than the mode matching confidence, and the mode prediction similarity is greater than the preset similarity threshold, the first fault mode is determined as the device fault diagnosis result of the target coal power equipment. If the first fault mode and the second fault mode are different, and the mode prediction similarity is greater than the mode matching confidence, but the mode prediction similarity is not greater than the preset similarity threshold, the first fault mode is reviewed by a related technical person, and if the review is passed, the first fault mode is determined as the device fault diagnosis result of the target coal power equipment.

[0050] If the first fault mode and the second fault mode are different, and the mode matching confidence is greater than the mode prediction similarity, and the mode matching confidence is greater than the preset confidence threshold, the second fault mode is determined as the device fault diagnosis result of the target coal power equipment. If the first fault mode and the second fault mode are different, and the mode matching confidence is greater than the mode prediction similarity, but the mode matching confidence is not greater than the preset confidence threshold, the second fault mode is reviewed by a related technical person, and if the review is passed, the second fault mode is determined as the device fault diagnosis result of the target coal power equipment.

[0051] The technical scheme of the embodiment of the present application obtains the running state data of the target coal power equipment, determines the equipment characteristic data according to the running state data, inputs the equipment characteristic data into the intelligent diagnosis model obtained by pre-training, obtains the first fault mode output by the model and the corresponding mode prediction similarity, inputs the equipment characteristic data into the expert rule library constructed in advance to perform fault mode matching, obtains the second fault mode and the corresponding mode matching confidence, and generates the equipment fault diagnosis result of the target coal power equipment according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence. The above technical scheme considers both the fault prediction result of the intelligent diagnosis model and the fault matching result of the expert rule library in the process of coal power equipment fault diagnosis, realizes the prediction of the coal power equipment fault mode from multiple dimensions, improves the intelligent diagnosis efficiency and diagnosis accuracy of the coal power equipment in the power grid scene, and thus meets the diagnosis scene demand of high safety, complex working conditions and multiple fault types of the coal power equipment.

[0052] Embodiment two

[0053] Figure 2 A flowchart of a coal power equipment fault intelligent diagnosis method provided by the second embodiment of the present application is provided, and the present embodiment is optimized and improved on the basis of the above technical solutions.

[0054] Further, the step of "generating the equipment fault diagnosis result of the target coal power equipment according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence" is refined as "determining the target fault mode according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence; obtaining the scene environment information of the target coal power equipment, and determining the equipment fault level according to the running state data and the scene environment information; performing fault case matching on the target coal power equipment based on the pre-constructed fault case matching library according to the running state data and the target fault mode of the target coal power equipment, to obtain a fault case matching result; and taking the fault case matching result and the equipment fault level as the equipment fault diagnosis result of the target coal power equipment." to perfect the generation mode of the equipment fault diagnosis result of the target coal power equipment.

[0055] It should be noted that the parts not described in detail in the embodiments of the present application can be referred to the descriptions of other embodiments. For example, Figure 2 As shown in the figure, the method comprises the following specific steps:

[0056] S210, obtaining the running state data of the target coal power equipment, and determining the equipment characteristic data according to the running state data.

[0057] S220A, input the equipment feature data into the pre-trained intelligent diagnosis model to obtain a first fault mode and a corresponding mode prediction similarity output by the model.

[0058] S220B, input the equipment feature data into the pre-constructed expert rule base to perform fault mode matching to obtain a second fault mode and a corresponding mode matching confidence.

[0059] S230, determine a target fault mode according to the first fault mode and the corresponding mode prediction similarity, and the second fault mode and the corresponding mode matching confidence.

[0060] S240, obtain scene environment information of the target coal power equipment, and determine an equipment fault level according to the running state data and the scene environment information.

[0061] S250, perform fault case matching on the target coal power equipment based on a pre-constructed fault case matching library according to the running state data and the target fault mode of the target coal power equipment to obtain a fault case matching result.

[0062] S260, take the fault case matching result and the equipment fault level as an equipment fault diagnosis result of the target coal power equipment.

[0063] In an optional embodiment, determining the target fault mode according to the first fault mode and the corresponding mode prediction similarity, and the second fault mode and the corresponding mode matching confidence includes: if the first fault mode is different from the second fault mode, obtaining scene environment information of the target coal power equipment, and determining a historical model prediction accuracy of the intelligent diagnosis model under a corresponding scene environment and a historical rule matching accuracy of the expert rule base under the corresponding scene environment according to the scene environment information; determining a model weight parameter according to the historical model prediction accuracy, and determining a rule weight parameter according to the historical rule matching accuracy; determining a model prediction confidence score according to the model weight parameter and the mode prediction similarity, and determining a rule prediction confidence score according to the rule weight parameter and the mode matching confidence; and determining the target fault mode based on a pre-set second confidence score threshold according to the model prediction confidence score and the rule prediction confidence score.

[0064] The scene environment information can be the operation condition environment of the target coal power equipment. It should be noted that the intelligent diagnosis model predicts the fault mode a different number of times for the coal power equipment in different scene environments in a historical time period, and thus the accuracy of the intelligent diagnosis model in predicting the fault mode of the coal power equipment in the corresponding scene environment can be obtained. Similarly, the accuracy of the expert rule base in predicting the fault mode of the corresponding scene environment can also be determined. Therefore, the historical model prediction accuracy of the intelligent diagnosis model in different scene environments can be obtained, and the historical rule matching accuracy of the expert rule base in different scene environments can be obtained.

[0065] For example, the scene environment information of the target coal power equipment is determined, and the historical model prediction accuracy of the intelligent diagnosis model in the corresponding scene environment and the historical rule matching accuracy of the expert rule base in the corresponding scene environment are determined according to the scene environment information. According to the historical model prediction accuracy, the model weight parameter can be determined, and according to the historical rule matching accuracy, the rule weight parameter can be determined. The higher the historical model prediction accuracy, the greater the corresponding model weight parameter setting; the lower the historical model prediction accuracy, the smaller the corresponding model weight parameter setting. Similarly, the higher the historical rule matching accuracy, the greater the corresponding rule weight parameter setting; the lower the historical rule matching accuracy, the smaller the corresponding rule weight parameter setting.

[0066] The model prediction confidence score can be obtained by weighted summation according to the model weight parameter and the model prediction similarity; and the rule prediction confidence score can be obtained by weighted summation according to the rule weight parameter and the pattern matching confidence. According to the model prediction confidence score and the rule prediction confidence score, the target fault mode is determined based on a preset second confidence score threshold,

[0067] In an optional embodiment, according to the model prediction confidence score and the rule prediction confidence score, the target fault mode is determined based on a preset second confidence score threshold, which includes: if the model prediction confidence score is greater than the rule prediction confidence score, and the model prediction confidence score is greater than the second confidence score threshold, the first fault mode is determined as the target fault mode; or, if the rule prediction confidence score is greater than the model prediction confidence score, and the rule prediction confidence score is greater than the second confidence score threshold, the second fault mode is determined as the target fault mode.

[0068] If the model prediction credibility score is equal to the rule prediction credibility score, a fault mode result review is performed by a relevant technical personnel, and the target fault mode is determined according to the review result. If the model prediction credibility score is greater than the rule prediction credibility score but the model prediction credibility score is not greater than the second credibility score threshold, or if the rule prediction credibility score is greater than the model prediction credibility score but the rule prediction credibility score is not greater than the second credibility score threshold, a fault mode result review is performed by a relevant technical personnel, and the target fault mode is determined according to the review result.

[0069] The scene environment information of the target coal power equipment is acquired, and the equipment fault level is determined according to the running state data and the scene environment information. The scene environment information can include the equipment type information corresponding to the coal power equipment.

[0070] In an optional embodiment, the equipment fault level is determined according to the running state data and the scene environment information, including: determining the equipment criticality score of the target coal power equipment according to the scene environment information; determining the parameter overrun amplitude score of the target coal power equipment according to the running state data; determining the fault diffusion risk score of the target coal power equipment according to the first fault mode or the second fault mode; and determining the equipment fault level according to the equipment criticality score, the parameter overrun amplitude score and the fault diffusion risk score.

[0071] For example, the equipment criticality of the target coal power equipment can be determined according to the scene environment information. The equipment criticality represents the core degree of the equipment in the coal power system or the coal power scene. For example, if the shutdown of the equipment affects the power generation or the safety, it can be considered that the core degree of the coal power equipment is high. Different equipment criticalities can correspond to different equipment criticality scores. For example, the main shaft bearing and the turbine rotor are core equipment, and the corresponding equipment criticality score is 40 points; the auxiliary fan or the coal feeder is non-core equipment, and the corresponding equipment criticality score is 10 points.

[0072] The parameter overrun amplitude score of the target coal power equipment is determined according to the running state data of the target coal power equipment. For example, the proportion of the vibration data, the pressure data and the temperature data in the running state data exceeding the rated value of the equipment, such as vibration exceeding threshold value 80%, temperature exceeding threshold value 20%, corresponding to the parameter overrun amplitude score of 30 points; vibration exceeding threshold value 10%, temperature exceeding threshold value 5%, corresponding to the parameter overrun amplitude score of 5 points.

[0073] According to the first failure mode or the second failure mode, a failure diffusion risk score of the target coal power equipment is determined. For example, according to the failure mode, it can be determined whether the failure will quickly deteriorate to cause a secondary failure. For example, a rotor crack failure can cause a short shaft, and oil film whirling can cause a rubbing between a rotor and a stator, and the corresponding failure diffusion risk score can be 30 points; for example, slight misalignment does not cause a secondary failure, or the probability of causing a secondary failure is small, and the corresponding failure diffusion risk score can be 5 points.

[0074] According to the equipment criticality score, the parameter overrun amplitude score, and the failure diffusion risk score, a device failure level is determined. Specifically, the weight parameters corresponding to the equipment criticality, the parameter overrun amplitude, and the failure diffusion risk can be pre-configured, and the severity score can be obtained by weighting and summing the equipment criticality score, the parameter overrun amplitude score, and the failure diffusion risk score based on the weight parameters corresponding to the equipment criticality, the parameter overrun amplitude, and the failure diffusion risk, respectively. According to the severity score, the equipment failure level is determined. For example, if the severity score is greater than or equal to 70, the equipment failure level is a serious failure. If the severity score is between 40 and 70, the equipment failure level is an abnormal failure. If the severity score is less than 40, the equipment failure level is a fault that needs attention.

[0075] The fault case matching library stores at least one fault case. The fault case matching library can be pre-constructed by a related technical personnel. Specifically, the fault case matching library can be constructed based on power plant operation and maintenance records, equipment manufacturer technical manuals, coal power industry public data such as coal power equipment failure statistical reports and academic papers, and newly diagnosed cases of an intelligent diagnosis model.

[0076] According to the operation state data, the operation state feature field is encoded to obtain a feature vector index. According to the target failure mode, the target failure mode is encoded based on a pre-prepared coal power equipment failure mode coding system to obtain a failure mode coding index. Based on the double-index mechanism, a case matching is performed in the fault case matching library to obtain a fault case matching result. The fault case matching result and the equipment failure level are used as the equipment failure diagnosis result of the target coal power equipment.

[0077] The technical scheme of the embodiment determines a target fault mode according to a first fault mode and a corresponding mode prediction similarity and a second fault mode and a corresponding mode matching confidence, obtains scene environment information of a target coal power equipment, determines an equipment fault level according to operation state data and the scene environment information, performs fault case matching on the target coal power equipment based on a pre-constructed fault case matching library according to the operation state data and the target fault mode of the target coal power equipment, obtains a fault case matching result, and takes the fault case matching result and the equipment fault level as an equipment fault diagnosis result of the target coal power equipment. The technical scheme determines the target fault mode based on the double basis of the fault mode and the corresponding prediction similarity or matching confidence, rather than a single dimension judgment, avoids the current situation of a single model or rule, ensures the consistency and standardization of the diagnosis result under different working conditions, determines the equipment fault level by combining the operation state data and the scene environment information, realizes accurate determination of the fault judgment level, avoids the risk of missing the report of a slight fault of a core equipment, takes the target fault level and the fault case matching result as the final equipment fault diagnosis result, improves the accuracy and comprehensiveness of the determination of the equipment fault diagnosis result, further improves the diagnosis reliability, reduces misjudgment and missed judgment, shortens the processing time, reduces trial and error, and thus reduces the operation and maintenance cost, and ensures the safe and efficient operation of the coal power equipment.

[0078] Embodiment three

[0079] Figure 3 A structural schematic diagram of a coal power equipment fault intelligent diagnosis device provided by the embodiment three of the present application. The coal power equipment fault intelligent diagnosis device provided by the embodiment of the present application can be applied to the case of intelligent diagnosis of a coal power equipment in a power grid scene. The coal power equipment fault intelligent diagnosis device can be realized in the form of hardware and / or software. As shown in the figure, the device comprises a state data acquisition module 301, a first fault prediction module 302, a second fault prediction module 303, and an equipment fault diagnosis module 304. Among them, Figure 3

[0080] The state data acquisition module 301 is configured to acquire operation state data of a target coal power equipment and determine equipment characteristic data according to the operation state data.

[0081] The first fault prediction module 302 is configured to input the equipment characteristic data into a pre-trained intelligent diagnosis model to obtain a first fault mode and a corresponding mode prediction similarity output by the model.

[0082] The second fault prediction module 303 is configured to input the equipment characteristic data into a pre-constructed expert rule library to perform fault mode matching and obtain a second fault mode and a corresponding mode matching confidence. ​

[0083] The device fault diagnosis module 304 is configured to generate a device fault diagnosis result of the target coal power plant according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence.

[0084] The technical scheme of the embodiment of the present application obtains the running state data of the target coal power plant, determines the device feature data according to the running state data, inputs the device feature data into the intelligent diagnosis model trained in advance to obtain the first fault mode and the corresponding mode prediction similarity output by the model, and inputs the device feature data into the expert rule library constructed in advance to perform fault mode matching to obtain the second fault mode and the corresponding mode matching confidence, and generates the device fault diagnosis result of the target coal power plant according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence. The technical scheme above considers both the fault prediction result of the intelligent diagnosis model and the fault matching result of the expert rule library in the process of coal power plant fault diagnosis, realizes the prediction of the coal power plant fault mode from multiple dimensions, improves the intelligent diagnosis efficiency and diagnosis accuracy of the coal power plant fault in the power grid scene, and thus meets the diagnosis scene demand of the coal power plant in high safety, complex working conditions and multiple fault types.

[0085] Optionally, the device fault diagnosis module 304 comprises:

[0086] The target fault mode determination unit is configured to determine a target fault mode according to the first fault mode and the corresponding mode prediction similarity and the second fault mode and the corresponding mode matching confidence.

[0087] The fault level determination unit is configured to obtain scene environment information of the target coal power plant, and determine a device fault level according to the running state data and the scene environment information.

[0088] The fault case matching unit is configured to perform fault case matching on the target coal power plant based on a pre-constructed fault case matching library according to the running state data of the target coal power plant and the target fault mode, to obtain a fault case matching result.

[0089] The device fault diagnosis unit is configured to take the fault case matching result and the device fault level as the device fault diagnosis result of the target coal power plant.

[0090] Optionally, the fault level determination unit is specifically configured to:

[0091] determine a device criticality score of the target coal power plant according to the scene environment information.

[0092] determine a parameter over-limit amplitude score of the target coal power equipment according to the operation state data;

[0093] determine a fault diffusion risk score of the target coal power equipment according to the first fault mode or the second fault mode;

[0094] determine the equipment fault level according to the equipment criticality score, the parameter over-limit amplitude score and the fault diffusion risk score.

[0095] Optionally, the target fault mode determining unit comprises:

[0096] The matching accuracy determining sub-unit is configured to, if the first fault mode is different from the second fault mode, acquire scene environment information of the target coal power equipment, and determine a historical model prediction accuracy of the intelligent diagnosis model in a corresponding scene environment and a historical rule matching accuracy of the expert rule base in the corresponding scene environment according to the scene environment information;

[0097] The weight parameter determining sub-unit is configured to determine a model weight parameter according to the historical model prediction accuracy, and determine a rule weight parameter according to the historical rule matching accuracy;

[0098] The credibility score determining sub-unit is configured to determine a model prediction credibility score according to the model weight parameter and the mode prediction similarity, and determine a rule prediction credibility score according to the rule weight parameter and the mode matching credibility;

[0099] The target fault mode determining sub-unit is configured to determine a target fault mode based on a preset second credibility score threshold according to the model prediction credibility score and the rule prediction credibility score.

[0100] Optionally, the target fault mode determining sub-unit is specifically configured to:

[0101] if the model prediction credibility score is greater than the rule prediction credibility score, and the model prediction credibility score is greater than the second credibility score threshold, determine the first fault mode as the target fault mode; or,

[0102] if the rule prediction credibility score is greater than the model prediction credibility score, and the rule prediction credibility score is greater than the second credibility score threshold, determine the second fault mode as the target fault mode.

[0103] Optionally, the model training manner of the intelligent diagnosis model is as follows:

[0104] Obtain historical feature data of the historical coal power equipment in a historical time period, and determine a corresponding real fault mode thereof;

[0105] Input the historical feature data of the historical coal power equipment and the corresponding real fault mode thereof into a pre-selected network model, to obtain a predicted fault mode output by the model;

[0106] According to the real fault mode and the predicted fault mode, model training is performed on the network model until a preset model training end condition is met, to obtain an intelligent diagnosis model.

[0107] The coal power equipment fault intelligent diagnosis device provided in the embodiments of the present application can execute the coal power equipment fault intelligent diagnosis method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0108] Embodiment four

[0109] Figure 4 A structural schematic diagram of an electronic device 40 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0110] As shown in Figure 4 The electronic device 40 includes at least one processor 41, and a memory, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., which is communicatively connected to the at least one processor 41, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 into the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0111] A plurality of components in the electronic device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0112] The processor 41 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 41 performs various methods and processes described above, such as the coal power plant fault intelligent diagnosis method.

[0113] In some embodiments, the coal power plant fault intelligent diagnosis method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded onto the RAM 43 and executed by the processor 41, one or more steps of the coal power plant fault intelligent diagnosis method described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to perform the coal power plant fault intelligent diagnosis method by any other appropriate means, such as by means of firmware.

[0114] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0115] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, enables the functions / acts specified in the flowcharts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0116] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0118] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0119] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0120] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in different orders, as long as the desired results of the technical solutions of the present disclosure can be achieved, and the present disclosure is not limited herein.

[0121] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for intelligent fault diagnosis of coal-fired power equipment, characterized in that, include: Acquire the operating status data of the target coal-fired power equipment, and determine the equipment characteristic data based on the operating status data; The device feature data is input into a pre-trained intelligent diagnostic model to obtain the first fault mode output by the model and its corresponding mode prediction similarity. as well as, The device feature data is input into a pre-built expert rule base for fault mode matching to obtain the second fault mode and its corresponding pattern matching confidence. Based on the first fault mode and its corresponding pattern prediction similarity and the second fault mode and its corresponding pattern matching confidence, a fault diagnosis result for the target coal-fired power equipment is generated.

2. The method according to claim 1, characterized in that, The step of generating equipment fault diagnosis results for the target coal-fired power equipment based on the first fault mode and its corresponding pattern prediction similarity and the second fault mode and its corresponding pattern matching confidence includes: The target fault mode is determined based on the first fault mode and its corresponding pattern prediction similarity and the second fault mode and its corresponding pattern matching confidence. Obtain the scene environment information of the target coal-fired power equipment, and determine the equipment fault level based on the operating status data and the scene environment information; Based on the operating status data of the target coal-fired power equipment and the target fault mode, fault cases are matched against the target coal-fired power equipment using a pre-built fault case matching library to obtain fault case matching results. The fault case matching results and the equipment fault level are used as the equipment fault diagnosis results of the target coal-fired power equipment.

3. The method according to claim 2, characterized in that, The step of determining the equipment fault level based on the operating status data and the scenario environment information includes: Based on the scenario environment information, determine the equipment criticality score of the target coal-fired power equipment; Based on the operating status data, determine the parameter over-limit score of the target coal-fired power equipment; Determine the fault propagation risk score of the target coal-fired power equipment based on the first fault mode or the second fault mode; The equipment failure level is determined based on the equipment criticality score, the parameter exceedance score, and the failure propagation risk score.

4. The method according to claim 2, characterized in that, The step of determining the target fault mode based on the first fault mode and its corresponding pattern prediction similarity and the second fault mode and its corresponding pattern matching confidence includes: If the first fault mode is different from the second fault mode, then the scene environment information of the target coal-fired power equipment is obtained, and based on the scene environment information, the historical model prediction accuracy of the intelligent diagnostic model in the corresponding scene environment is determined, as well as the historical rule matching accuracy of the expert rule base in the corresponding scene environment is determined. Based on the historical model prediction accuracy, determine the model weight parameters, and based on the historical rule matching accuracy, determine the rule weight parameters; The model prediction confidence score is determined based on the model weight parameters and the pattern prediction similarity, and the rule prediction confidence score is determined based on the rule weight parameters and the pattern matching confidence. Based on the confidence score predicted by the model and the confidence score predicted by the rules, the target failure mode is determined based on a preset second confidence score threshold.

5. The method according to claim 4, characterized in that, The step of determining the target failure mode based on the confidence score predicted by the model and the confidence score predicted by the rules, and based on a preset second confidence score threshold, includes: If the model prediction confidence score is greater than the rule prediction confidence score, and the model prediction confidence score is greater than the second confidence score threshold, then the first fault mode is determined as the target fault mode; or, If the rule prediction confidence score is greater than the model prediction confidence score, and the rule prediction confidence score is greater than the second confidence score threshold, then the second fault mode is determined as the target fault mode.

6. The method according to claim 1, characterized in that, The training method for the intelligent diagnostic model is as follows: Acquire historical characteristic data of coal-fired power equipment over historical time periods and determine its corresponding actual failure modes; The historical characteristic data of the historical coal-fired power equipment and its corresponding actual fault modes are input into a pre-selected network model to obtain the predicted fault modes output by the model. Based on the actual fault modes and the predicted fault modes, the network model is trained until the preset model training termination condition is met, thus obtaining an intelligent diagnostic model.

7. An intelligent fault diagnosis device for coal-fired power equipment, characterized in that, include: The status data acquisition module is used to acquire the operating status data of the target coal-fired power equipment and determine the equipment characteristic data based on the operating status data. The first fault prediction module is used to input the device feature data into a pre-trained intelligent diagnostic model to obtain the first fault mode output by the model and its corresponding mode prediction similarity. as well as, The second fault prediction module is used to input the device feature data into a pre-built expert rule base for fault mode matching to obtain the second fault mode and its corresponding pattern matching confidence. The equipment fault diagnosis module is used to generate equipment fault diagnosis results for the target coal-fired power equipment based on the first fault mode and its corresponding pattern prediction similarity and the second fault mode and its corresponding pattern matching confidence.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the intelligent fault diagnosis method for coal-fired power equipment as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the intelligent fault diagnosis method for coal-fired power equipment as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the intelligent fault diagnosis method for coal-fired power equipment according to any one of claims 1-6.

Images