Nuclear power equipment fault detection method, device, equipment, medium and product

Abstract

The invention discloses a nuclear power equipment fault detection method, device and equipment, a medium and a product, and belongs to the technical field of data processing. The method comprises the following steps: determining a stage identifier of a current operation stage of the nuclear power equipment, an operation duration in the current operation stage, and at least two previous stages corresponding to the stage identifier; obtaining a first parameter data combination for the target parameter in each of the at least two previous stages; determining a predicted time length, and determining a target operation time length of the nuclear power equipment in the current operation stage according to the operated time length and the predicted time length; according to target parameter data corresponding to the target operation duration in the previous stage corresponding to each first parameter data combination, determining prediction data of the nuclear power equipment for the target parameter; and according to the prediction data, determining whether the nuclear power equipment has a fault when the nuclear power equipment operates to the target operation duration at the current operation stage. According to the technical scheme provided by the embodiment of the invention, the technical effect of predicting the fault of the nuclear power equipment can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, equipment, medium and product for detecting nuclear power equipment faults. Background Art

[0002] At present, the operation status of nuclear power equipment is usually inspected at the scheduled quality control time, and whether there is any abnormality in the nuclear power equipment is determined based on the operation data of the nuclear power equipment. If there is an abnormality, it is determined that the nuclear power equipment has a fault. If there is no abnormality, it is determined that the nuclear power equipment is normal.

[0003] Therefore, although existing nuclear power equipment fault detection methods can detect some faults of nuclear power equipment, they usually have a lag. Summary of the Invention

[0004] The present invention provides a nuclear power equipment fault detection method, device, equipment, medium and product to solve the problem of hysteresis in existing nuclear power equipment fault detection methods.

[0005] According to one aspect of the present invention, a method for detecting a nuclear power equipment fault is provided, comprising:

[0006] Determining a stage identifier of a current operating stage of the nuclear power equipment, an elapsed operating time in the current operating stage, and at least two past stages corresponding to the stage identifier;

[0007] Obtaining a first parameter data combination for the target parameter in each of the at least two past stages;

[0008] Determining a predicted duration, and determining a target operating duration of the nuclear power equipment in the current operating phase based on the actual operating duration and the predicted duration;

[0009] determining, based on the target parameter data corresponding to the target operating duration in the past stages corresponding to each of the first parameter data combinations, predicted data for the target parameter when the nuclear power equipment operates for the target operating duration in the current operating stage;

[0010] Determine whether a fault occurs when the nuclear power equipment runs for the target operating time in the current operating stage based on the prediction data.

[0011] According to another aspect of the present invention, there is provided a device for predicting operating parameters of nuclear power equipment, comprising:

[0012] a stage determination module, configured to determine a stage identifier of a current operating stage of the nuclear power equipment, an elapsed operating time in the current operating stage, and at least two past stages corresponding to the stage identifier;

[0013] a data acquisition module, configured to acquire a first parameter data combination for the target parameter in each of the at least two past stages;

[0014] a prediction duration module, configured to determine a predicted duration, and determine a target operating duration of the nuclear power equipment in the current operating phase based on the actual operating duration and the predicted duration;

[0015] a prediction module, configured to determine, based on target parameter data corresponding to the target operating duration in past stages corresponding to each of the first parameter data combinations, predicted data for the target parameter when the nuclear power equipment operates for the target operating duration in the current operating stage;

[0016] A fault detection module is used to determine whether a fault occurs when the nuclear power equipment runs for the target operating time in the current operating stage based on the prediction data.

[0017] According to another aspect of the present invention, an electronic device is provided, comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the nuclear power equipment fault detection method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the nuclear power equipment fault detection method according to any embodiment of the present invention when executed.

[0022] According to another aspect of the present invention, there is provided a computer program product comprising a computer program, wherein when the computer program is executed by a processor, the method for detecting a nuclear power equipment fault according to any embodiment of the present invention is implemented.

[0023] The technical solution provided by the embodiment of the present invention determines the stage identifier of the current operation stage of the nuclear power equipment, the operating time in the current operation stage, and at least two past stages corresponding to the stage identifier; obtains a first parameter data combination for the target parameter in each past stage in the at least two past stages; determines the predicted duration, and determines the target operating time of the nuclear power equipment in the current operation stage based on the operating time and the predicted duration; because the past stage and the current operation stage belong to the same operation stage, the predicted data for the target parameter when the nuclear power equipment runs to the target operating time in the current operation stage is determined based on the target parameter data corresponding to the target operating time in the past stage corresponding to each first parameter data combination, thereby achieving the technical effect of using past data in the same state as a certain moment in the future to predict the target parameter data at that moment in the future, thereby improving the accuracy of the target parameter data prediction; based on the predicted data, determining whether the nuclear power equipment has a fault when it runs to the target operating time in the current operation stage, thereby achieving the technical effect of predicting the fault of the nuclear power equipment, so that when the fault prediction result shows that the nuclear power equipment has a fault, the nuclear power equipment can be checked for abnormalities in advance, thereby improving the safety and service life of the nuclear power equipment operation.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 is a flow chart of a method for detecting nuclear power equipment failure according to an embodiment of the present invention;

[0027] Figure 2 is another flow chart of a nuclear power equipment fault detection method provided according to an embodiment of the present invention;

[0028] Figure 3 2. It is a schematic diagram of the change of weight with the past time provided by an embodiment of the present invention;

[0029] Figure 4 is a flow chart of a weight correction method provided according to an embodiment of the present invention;

[0030] Figure 5A 2 is a schematic structural diagram of a nuclear power equipment fault detection device provided according to an embodiment of the present invention;

[0031] Figure 5B This is another structural diagram of a nuclear power equipment fault detection device provided by an embodiment of the present invention;

[0032] Figure 5C This is another structural diagram of a nuclear power equipment fault detection device provided by an embodiment of the present invention;

[0033] Figure 6 It is a structural diagram of an electronic device for implementing the nuclear power equipment fault detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Figure 1 This is a flowchart of a method for detecting a nuclear power equipment fault provided by an embodiment of the present invention. This embodiment is applicable to the case of automatically determining target parameter data of a nuclear power equipment when the predicted duration is reached. This method can be executed by a nuclear power equipment fault detection device, which can be implemented in the form of hardware and / or software. The nuclear power equipment fault detection device can be configured in a processor of an electronic device. Figure 1 As shown, the method includes:

[0037] S110: Determine a stage identifier of a current operation stage of the nuclear power equipment, an operating time in the current operation stage, and at least two past stages corresponding to the stage identifier.

[0038] Among them, nuclear power equipment can be a piece of equipment in a nuclear power plant, or it can be a general term for multiple pieces of equipment in a nuclear power plant.

[0039] The current operating stage of the nuclear power equipment can be understood as the current operating stage of the nuclear power equipment, such as nuclear reaction, cooling, steam generation, steam power generation, etc.

[0040] Obtain operating parameter data of the nuclear power equipment within a predetermined time window, and determine the current operating stage of the nuclear power equipment and the operating time in the current operating stage based on the operating parameter data. The deadline of the predetermined time window is the current moment.

[0041] In one embodiment, the operating parameter data is analyzed based on a pre-trained stage recognition model to determine the current operating stage of the nuclear power equipment and the operating time it has run in the current operating stage. This embodiment can simply and quickly determine the current stage of the nuclear power equipment and the operating time it has run in the current operating stage, but it requires the training of the stage recognition model to be completed in advance.

[0042] In one embodiment, based on the corresponding range between the predetermined change trend and the state identifier, the state identifier corresponding to the change trend corresponding to the operating parameter data is determined, and the state identifier is used as the target state identifier; based on the corresponding relationship between the predetermined state identifier and the stage-duration, the stage-duration corresponding to the target state identifier is determined, and based on the stage-duration, the current operating stage of the nuclear power equipment and the operating time in the current operating stage are determined.

[0043] The length of time the nuclear power equipment has been in operation in the current operation stage can be understood as the length of time the nuclear power equipment has been in operation in the current operation stage.

[0044] Since the stage identifier in this step is the stage identifier of the current operation stage, the at least two past stages corresponding to the stage identifier are the same operation stage as the current operation stage. For example, if the current operation stage is the cooling stage, then the at least two past stages are also cooling stages.

[0045] S120: Obtain a first parameter data combination for the target parameter in each of the at least two past stages.

[0046] The first parameter data combination includes target parameter data corresponding to a past stage.

[0047] During nuclear power equipment operation, all operating parameters are collected in real time to form a parameter set. Based on the stage identifier, target parameter, and predetermined duration, target parameter data for each past stage corresponding to the stage identifier within the predetermined duration is extracted from the parameter set to obtain a first parameter data combination for each past stage.

[0048] In one embodiment, the current operating parameters of the nuclear power equipment are determined, and the health description data of the nuclear power equipment is determined based on the current operating parameters and the predetermined parameter allowable range; if the health description data corresponds to a first fault, a maintenance work order corresponding to the first fault is output; if the health description data does not correspond to the first fault, S130 is executed.

[0049] The first fault is a major fault. If the health description data corresponds to the first fault, a maintenance work order corresponding to the first fault is directly output. If the health description data corresponds to the second fault or no fault is present, S130 is executed. The second fault is a minor fault. The nuclear power equipment can operate with this minor fault for a certain period of time, but this fault will cause a major fault at some point in the future.

[0050] Regarding maintenance work orders, solution configuration files for different fault types are pre-stored. When a first fault is detected, the fault type of the first fault is determined, and a corresponding maintenance solution is extracted from the solution configuration file based on the fault type. The maintenance solution is then added to a pre-defined template to generate a maintenance work order. The maintenance work order is then displayed in a visual interface. This embodiment allows for the rapid and accurate generation of maintenance work orders for different faults.

[0051] S130: Determine the predicted duration, and determine the target operating duration of the nuclear power equipment in the current operating phase based on the actual operating duration and the predicted duration.

[0052] The predicted duration is an integer multiple of the predicted unit time; the difference between the average operating time of nuclear power equipment in the current operating stage and the predicted unit time is greater than the target operating time and less than the sum of the target operating time and the predicted unit time.

[0053] t i +n*h≤VT-h≤t i +(n+1)*h;

[0054] Among them, t i is the running time mentioned above; n can be understood as the number of predictions or an integer multiple; VT is the average running time of the corresponding time of at least two past stages; nh is the predicted time, t i +nh is the target runtime.

[0055] It is understandable that one prediction duration corresponds to one prediction data. If the prediction data of nuclear power equipment at multiple future moments are to be predicted, it is necessary to set prediction durations corresponding to the multiple future moments respectively.

[0056] In one embodiment, in response to the first prediction operation, upon detecting a predicted duration input or selected by the user, a target runtime corresponding to the predicted duration is determined, where the target runtime is an integer multiple of the predicted unit time. This embodiment can automatically determine a single target runtime.

[0057] In one embodiment, in response to the second prediction operation, the longest prediction duration is obtained, and a prediction duration combination is determined based on the longest prediction duration, the prediction duration combination including at least two linearly increasing prediction durations, and the slopes corresponding to the at least two linearly increasing prediction durations are the prediction unit time; the target operating duration combination of the nuclear power equipment in the current operating stage is determined based on the already operated duration and the prediction duration combination, the target operating duration combination including at least two target operating durations.

[0058] Specifically, when the longest predicted duration input or selected by the user is detected, a predicted duration combination is generated, which includes a first predicted duration, a second predicted duration, and up to the Pth predicted duration (the longest predicted duration), wherein the first predicted duration is the predicted unit time, the second predicted duration is 2 times the predicted unit time, and the Pth predicted duration is P times the predicted unit time, wherein P is the ratio of the predicted duration to the predicted unit time; a target run duration combination corresponding to the predicted duration combination is determined, and the target run duration combination includes a first target run duration corresponding to the first predicted duration, a second target run duration corresponding to the second predicted duration, and a Pth target run duration corresponding to the Pth predicted duration. This embodiment can automatically and quickly determine multiple target run durations.

[0059] S140. Determine, based on the target parameter data corresponding to the target operating duration in the past stages corresponding to each first parameter data combination, predicted data for the target parameter when the nuclear power equipment runs to the target operating duration in the current operating stage.

[0060] The target parameter data corresponding to the target operating time in the past stage corresponding to the first parameter data combination is the target parameter data when the nuclear power equipment operates for the target operating time in the past stage corresponding to the first parameter data combination.

[0061] During nuclear power plant operation, data acquisition equipment collects operating parameter data, such as target parameter data, at predetermined intervals. Ideally, the target parameter data corresponding to the same operating duration of nuclear power equipment during the same operating phase should be the same. For example, the target parameter data for a nuclear power plant operating for one hour in the first cooling phase should be the same as the target parameter data for the second cooling phase.

[0062] In one embodiment, the average of the target parameter data corresponding to the target operating duration in the past phases corresponding to all first parameter data combinations is used as the predicted data for the target parameter when the nuclear power plant reaches the target operating duration in the current operating phase. This embodiment can simply and quickly determine the predicted data for the target parameter when the nuclear power plant reaches the target operating duration in the current operating phase.

[0063] The details are as follows:

[0064]

[0065] Among them, YC nh is the predicted data of the target parameter α when the nuclear power equipment is at the target operating time (or at the future nh time), h is the prediction unit time, such as hours; A is the number of the at least two past stages, CS anh is the actual detected value of the target parameter α corresponding to the target operating time in the ath first parameter data combination, wherein the target parameter α can be reactor temperature, steam flow rate, reactor pressure, cooling tower temperature, etc.

[0066] The forecast unit time is configurable. You can set it based on the desired forecast accuracy. The smaller the forecast unit time, the higher the forecast accuracy.

[0067] In one embodiment, the weighted sum of the target parameter data corresponding to the target operating duration in all past phases corresponding to the first parameter data combination is used as the predicted data for the target parameter of the nuclear power plant at the predicted time. The weight of past phases closer to the current time is greater, and vice versa. The sum of the weights of all past phases is equal to one-half A, where A is the number of past phases included in the at least two past phases. This embodiment can simply and quickly determine the predicted data for the target parameter when the nuclear power plant runs to the target operating duration in the current operating phase.

[0068] It is understandable that if a target operating time combination including at least two target operating times is currently determined, it is necessary to determine prediction data for target parameters when the nuclear power equipment runs to each target operating time in the current operating stage.

[0069] S150. Determine, based on the prediction data, whether a fault occurs when the nuclear power equipment runs for the target operating time in the current operating phase.

[0070] Once the predicted data is determined, the permissible range of the target parameter data corresponding to the target operating time in the current operating phase is obtained. Based on whether the predicted data is within this permissible range, it is determined whether the nuclear power equipment has a fault. This achieves the technical effect of predicting nuclear power equipment failures in advance.

[0071] It can be understood that when the nuclear power equipment runs to each target operating time in the current operating stage, after the prediction data for the target parameters is determined, it is necessary to determine whether there is a fault when the nuclear power equipment runs to each target operating time in the current operating stage based on the prediction data corresponding to each target operating time.

[0072] If the nuclear power equipment currently has a second fault and / or has any type of fault during the target operating time, a maintenance work order for the nuclear power equipment is generated.

[0073] Specifically, if a nuclear power device currently has a second fault, it will also have a fault when it runs to the target operating time during the current operation phase. Therefore, a maintenance work order corresponding to the fault type of the second fault needs to be generated. If the nuclear power device currently has no fault but has a fault at any target operating time, a maintenance work order corresponding to the fault type is generated. This embodiment can detect potential faults in advance and generate a maintenance work order corresponding to the fault type. In this way, operation and maintenance personnel can promptly conduct hidden danger inspections on nuclear power equipment based on the maintenance work order, detect and resolve problems in advance, and improve the safety and service life of nuclear power equipment.

[0074] The technical solution provided by the embodiment of the present invention determines the stage identifier of the current operation stage of the nuclear power equipment, the operating time in the current operation stage, and at least two past stages corresponding to the stage identifier; obtains a first parameter data combination for the target parameter in each past stage in the at least two past stages; determines the predicted duration, and determines the target operating time of the nuclear power equipment in the current operation stage based on the operating time and the predicted duration; because the past stage and the current operation stage belong to the same operation stage, the predicted data for the target parameter when the nuclear power equipment runs to the target operating time in the current operation stage is determined based on the target parameter data corresponding to the target operating time in the past stage corresponding to each first parameter data combination, thereby achieving the technical effect of using past data in the same state as a certain moment in the future to predict the target parameter data at that moment in the future, thereby improving the accuracy of the target parameter data prediction; based on the predicted data, determining whether the nuclear power equipment has a fault when it runs to the target operating time in the current operation stage, thereby achieving the technical effect of predicting the fault of the nuclear power equipment, so that when the fault prediction result shows that the nuclear power equipment has a fault, the nuclear power equipment can be checked for abnormalities in advance, thereby improving the safety and service life of the nuclear power equipment operation.

[0075] Figure 2 This is another flow chart of a method for detecting nuclear power equipment failures provided by an embodiment of the present invention. This embodiment adds a prediction data correction step based on the above embodiment. Figure 2 As shown, the method includes:

[0076] S210: Determine the stage identifier of the current operation stage of the nuclear power equipment, the operating time in the current operation stage, and at least two past stages corresponding to the stage identifier.

[0077] S220: Obtain a first parameter data combination for the target parameter in each of the at least two past stages.

[0078] S230: Determine the predicted duration, and determine the target operating duration of the nuclear power equipment in the current operating stage based on the actual operating duration and the predicted duration.

[0079] S2401. Determine, based on the target parameter data corresponding to the target operating duration in the past stages corresponding to each first parameter data combination, predicted data for the target parameter when the nuclear power equipment runs to the target operating duration in the current operating stage.

[0080] S2402: Obtain a second parameter data combination for the target parameter within the running time.

[0081] The second parameter data combination includes target parameter data of the nuclear power equipment at each collection moment within the operating time in the current operating stage.

[0082] S2403: Determine a past parameter-time fitting function for the target parameter data corresponding to each first parameter data combination, and a current parameter-time fitting function for the target parameter data corresponding to the second parameter data combination.

[0083] Fit the relationship between each target parameter data in each first parameter data combination and the acquisition time to obtain Y1=F1(t), Y2=F2(t), ...Y a =F a (t).

[0084] Wherein, Y1 is the fitting value of the target parameter data in the first parameter data combination identified as 1, and F1(t) is the past parameter-time fitting function of the target parameter data in the first parameter data combination identified as 1 and the running time t. a is the fitted value of the target parameter data in the first target parameter data combination identified as a, F a (t) is the target parameter data in the first target parameter data combination identified as a and the past parameter-time fitting function of the running time t.

[0085] For example, the reactor temperature is used as the target parameter. a (t) is used to fit the reactor temperature data at each moment of the ath startup phase.

[0086] Among them, Y1 to Y aThe fitting model used is the same, and the difference between the functional relationships is only the specific value of the coefficient. For example, if the fitting model uses linear regression, then Y1=t*c1+b1, Y a =t*c a +b a ; c1, b1, c a 、b a are all coefficient values in the fitting results, and their specific values are determined according to the corresponding first target parameter data combination.

[0087] According to Y1 to Y a The type of fitting model used determines the current parameter-time fitting function of the target parameter data corresponding to the second parameter data combination, which is recorded as: Y now =F now (t). In this way, all parameter-time fitting functions are based on the same fitting model.

[0088] S2404. Determine the contribution, weight, and product of the contribution and the weight of each past stage in the at least two past stages, wherein the contribution corresponding to each past stage includes the target index result corresponding to each collection moment within the running time, and the target index result is an index result of the difference between the fitting data determined by the current parameter-time fitting function and the past parameter-time fitting function at the corresponding moment. The weight is determined based on a linear function, and the independent variable of the linear function is the past time of the corresponding past stage from the current moment.

[0089] Specifically, the product of the contribution and weight of each of the at least two past stages is determined by the following formula:

[0090]

[0091] Among them, k a is the weight, YC nh For forecast data, is the contribution of the corresponding past stage; where D1 is the target parameter fitting value at the previous acquisition moment determined by the current parameter-time fitting function, x is the number of acquisition moments included in the running time in the current operation stage, e is a natural constant, and D x D is the target parameter fitting value at the first x acquisition moments determined using the current parameter-time fitting function; a1 is the target parameter fitting value at the previous acquisition moment determined using a past parameter-time fitting function, wherein the past parameter-time fitting function is determined based on the first parameter data combination identified as a; D axIt is the target parameter fitting value at the previous x acquisition moments determined using the past parameter-time fitting function, where the past parameter-time fitting function is determined based on the first parameter data combination identified as a; the previous acquisition moment refers to the acquisition moment before the current moment; and the previous x acquisition moments refer to the x acquisition moments before the current moment.

[0092] The previous collection time is the time corresponding to the current time minus one parameter update interval. For example, if the current time is M and the parameter update interval is 0.5, then the collection time before the current time is M-0.5, and the collection time two times before the current time is M-1.

[0093] The weight can be expressed as:

[0094] k a =K1hour a +K2;

[0095] Among them, hour a is the past duration between the past stage marked as a and the current moment, K1 is the independent variable coefficient, and K2 is the constant corresponding to the past stage.

[0096] In one embodiment,

[0097]

[0098] Among them, Δhour is the total time from the earliest past stage in the at least two past stages to the current moment. This embodiment combines the past duration and the total past duration to determine the weight, which can fully reflect that the longer the past duration corresponding to the past stage, the smaller its corresponding weight, and its impact on the accuracy of the predicted data is small, such as Figure 3 shown.

[0099] S250: Correct the predicted data according to the mean of the products corresponding to all past stages to obtain target predicted data.

[0100] The details are as follows:

[0101]

[0102] Here, A is the number of past stages included in the at least two past stages, that is, the number of first target parameter data combinations.

[0103] In an embodiment of the present invention, a target index result of the difference between the fitting data at each sampling moment within the running time of the current running stage determined by the past parameter-time fitting function and the current parameter-time fitting function is obtained; the sum of the target index results at all sampling moments can accurately reflect the contribution of each past stage to the prediction result; the weight of each past stage is determined using a linear function of the past time, so that the longer the past stage is, the smaller the impact on the predicted data is, and vice versa, the greater the impact is, and the accuracy is also higher; the predicted data is corrected by taking the average of the product of the contribution and the weight under all past stages, so as to ensure the accuracy of the correction of the predicted data.

[0104] Figure 4 This is a flow chart of a weight updating method provided by an embodiment of the present invention, which is used to update the weights determined in the above embodiment. Figure 4 As shown, the method includes:

[0105] S310: For the weight of each past stage, based on the past parameter-time fitting function corresponding to each collection moment, determine the fitting parameter data at the corresponding collection moment, and use the summary result of the fitting parameter data corresponding to all collection moments of the current past stage as the fitting parameter data combination.

[0106] It can be understood that the fitting parameter data combination includes the fitting parameter data at all acquisition moments in the current past stage.

[0107] S320. Determine the predicted offset corresponding to each target parameter data in the first parameter data combination in the current past stage, and the sum of the predicted offsets corresponding to all target parameter data in the first parameter data combination. The predicted offset is the square of the ratio of the first difference to the second difference. The first difference is the difference between the target parameter data and the closest fitting parameter data in the fitting parameter data combination. The second difference is the difference between the target parameter data and the corresponding means of the fitting parameter data combination.

[0108] Specifically: Among them, ce z is the target parameter data actually collected at the zth collection moment in the current past stage; ce z For the fitting parameter data combination with ce z The closest fitting parameter data, VCE is the mean of all fitting parameter data in the fitting parameter data combination.

[0109] S330. The weight is modified according to the sum of the predicted offsets and the similarity index data to update the weight. The similarity index is the average of the sub-similarity corresponding to all the acquisition moments in the running time. The sub-similarity is the inverse of the target offset absolute value index result. The target offset is the difference between the target parameter data at the corresponding moment in the current past stage and the target parameter data at the corresponding moment in the running time.

[0110] The difference between 1 and the sum of the predicted offsets is determined, and then the weight is corrected according to twice the difference multiplied by the similarity index data to update the weight.

[0111] The details are as follows:

[0112]

[0113] Among them, SIM a is the similarity index data, which can be expressed as:

[0114]

[0115] Among them, I is the number of collection moments included in the running time in the current running stage, past i is the i-th target parameter data in the second parameter data combination, ce i is the target parameter data at the i-th collection moment in the current past stage.

[0116] The embodiment of the present invention takes into account the impact of the newness of the target parameter data on the accuracy of the predicted data, as well as the gap between the fitting parameter data at each collection moment in the past stage and the target parameter data, which can further improve the accuracy of the weight, thereby improving the accuracy of the predicted data.

[0117] Figure 5A A schematic structural diagram of a nuclear power equipment fault detection device provided in an embodiment of the present invention.

[0118] like Figure 5A As shown, the device includes:

[0119] The stage determination module 41 is configured to determine a stage identifier of a current operation stage of the nuclear power equipment, an elapsed operation time in the current operation stage, and at least two past stages corresponding to the stage identifier;

[0120] A data acquisition module 42 is configured to acquire a first parameter data combination for the target parameter in each of the at least two past stages;

[0121] The prediction duration module 43 is configured to determine the predicted duration, and determine the target operating duration of the nuclear power equipment in the current operating phase according to the actual operating duration and the predicted duration;

[0122] a prediction module 44 configured to determine, based on target parameter data corresponding to the target operating duration in past stages corresponding to each of the first parameter data combinations, predicted data for the target parameter when the nuclear power equipment operates for the target operating duration in the current operating stage;

[0123] The fault detection module 45 is configured to determine, based on the prediction data, whether a fault occurs when the nuclear power equipment runs for the target operating time in the current operating phase.

[0124] In one embodiment, Figure 5B The device further includes a prediction data correction module 46 disposed after the prediction module 44, and the prediction data correction module 46 includes:

[0125] an acquiring unit, configured to acquire a second parameter data combination for the target parameter within the running time;

[0126] a fitting function unit, configured to determine a past parameter-time fitting function for the target parameter data corresponding to each of the first parameter data combinations, and a current parameter-time fitting function for the target parameter data corresponding to the second parameter data combinations;

[0127] A multiplication unit is used to determine the contribution, weight and product of the contribution and weight of each past stage in the at least two past stages, wherein the contribution corresponding to each past stage includes the sum of the target index results at all acquisition moments within the running time, and the target index result is an index result of the difference between the fitting data determined by the current parameter-time fitting function and the past parameter-time fitting function at the corresponding moment, and the weight is determined based on a linear function, and the independent variable of the linear function is the past time of the corresponding past stage from the current moment.

[0128] The correction unit is used to correct the predicted data according to the average of the products corresponding to all the past stages to update the predicted data.

[0129] In one embodiment, the product unit completes the weight update through a weight update unit, which is used to:

[0130] For the weight of each past stage, based on the past parameter-time fitting function corresponding to each collection moment, determining the fitting parameter data at the corresponding collection moment, and summarizing the fitting parameter data corresponding to all the collection moments in the current past stage as a fitting parameter data combination;

[0131] Determine a predicted offset corresponding to each target parameter data in the first parameter data combination in the current past stage, and a sum of the predicted offsets corresponding to all target parameter data in the first parameter data combination, wherein the predicted offset is the square of the ratio of a first difference to a second difference, wherein the first difference is the difference between the target parameter data and the closest fitting parameter data in the fitting parameter data combination, and the second difference is the difference between the target parameter data and the corresponding means of the fitting parameter data combination;

[0132] The weight is corrected according to the sum of the predicted offsets and the similarity index data to update the weight, where the similarity index is the average of the sub-similarity corresponding to all acquisition moments in the running time, the sub-similarity is the inverse of the target offset absolute value index result, and the target offset is the difference between the target parameter data at the corresponding moment in the current past stage and the target parameter data at the corresponding moment in the running time.

[0133] In one embodiment, the duration prediction module 43 is specifically configured to:

[0134] Determining current operating parameters of the nuclear power equipment, and determining health description data of the nuclear power equipment based on the current operating parameters and a predetermined parameter allowable range;

[0135] If the health description data corresponds to a first fault, outputting a maintenance work order corresponding to the first fault;

[0136] If the health description data does not correspond to the first fault, the predicted duration is determined, and the target operating duration of the nuclear power equipment in the current operating stage is determined based on the actual operating duration and the predicted duration.

[0137] In one embodiment, Figure 5C As shown, the device further includes a maintenance work order module 47, which is further used to:

[0138] If the nuclear power equipment currently has a second fault and / or has any type of fault during the target operating time, a maintenance work order for the corresponding fault is generated.

[0139] In one embodiment, the prediction duration is an integer multiple of the prediction unit time;

[0140] The difference between the average operating time of the nuclear power equipment in the current operating stage and the predicted unit time is greater than the target operating time and less than the sum of the target operating time and the predicted unit time.

[0141] In one embodiment, the prediction duration module 43 is used to obtain a maximum prediction duration, and determine a prediction duration combination based on the maximum prediction duration, wherein the prediction duration combination includes at least two linearly increasing prediction durations, and the slopes corresponding to the at least two linearly increasing prediction durations are prediction unit times; determine a target operating duration combination for the nuclear power equipment in the current operating stage based on the already operated duration and the prediction duration combination, wherein the target operating duration combination includes at least two target operating durations;

[0142] The prediction module is configured to determine, for each target operating duration in the target operating duration combination, predicted data for the target parameter when the nuclear power equipment operates in the current operating phase to the current target operating duration based on target parameter data corresponding to the current target operating duration in a past phase corresponding to each first parameter data combination;

[0143] The fault detection module is used to determine whether a fault occurs when the nuclear power equipment runs for each target operating time in the current operating stage based on the prediction data.

[0144] The technical solution provided by the embodiment of the present invention determines the stage identifier of the current operation stage of the nuclear power equipment, the operating time in the current operation stage, and at least two past stages corresponding to the stage identifier; obtains a first parameter data combination for the target parameter in each past stage in the at least two past stages; determines the predicted duration, and determines the target operating time of the nuclear power equipment in the current operation stage based on the operating time and the predicted duration; because the past stage and the current operation stage belong to the same operation stage, the predicted data for the target parameter when the nuclear power equipment runs to the target operating time in the current operation stage is determined based on the target parameter data corresponding to the target operating time in the past stage corresponding to each first parameter data combination, thereby achieving the technical effect of using past data in the same state as a certain moment in the future to predict the target parameter data at that moment in the future, thereby improving the accuracy of the target parameter data prediction; based on the predicted data, determining whether the nuclear power equipment has a fault when it runs to the target operating time in the current operation stage, thereby achieving the technical effect of predicting the fault of the nuclear power equipment, so that when the fault prediction result shows that the nuclear power equipment has a fault, the nuclear power equipment can be checked for abnormalities in advance, thereby improving the safety and service life of the nuclear power equipment operation.

[0145] The nuclear power equipment fault detection device provided in the embodiment of the present invention can execute the nuclear power equipment fault detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0146] Figure 6 A schematic diagram of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0147] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0148] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0149] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the nuclear power equipment fault detection method.

[0150] In some embodiments, the nuclear power equipment fault detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the nuclear power equipment fault detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the nuclear power equipment fault detection method in any other appropriate manner (e.g., by means of firmware).

[0151] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0152] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0153] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0154] To provide interaction with a user, the systems and techniques described herein 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 input, voice input, or tactile input).

[0155] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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.

[0156] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0157] An embodiment of the present invention further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the nuclear power equipment fault detection method provided in any embodiment of the present application.

[0158] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0159] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0160] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for detecting a nuclear power equipment fault, characterized in that: include: Determining a stage identifier of a current operating stage of the nuclear power equipment, an elapsed operating time in the current operating stage, and at least two past stages corresponding to the stage identifier; Obtaining a first parameter data combination for a target parameter in each of the at least two past stages; Determining a predicted duration, and determining a target operating duration of the nuclear power equipment in the current operating phase based on the actual operating duration and the predicted duration; determining, based on the target parameter data corresponding to the target operating duration in the past stages corresponding to each of the first parameter data combinations, predicted data for the target parameter when the nuclear power equipment operates for the target operating duration in the current operating stage; Determine whether a fault occurs when the nuclear power equipment runs for the target operating time in the current operating stage based on the prediction data.

2. The method according to claim 1, characterized in that Before determining, based on the prediction data, whether the nuclear power equipment has a fault when it runs for the target operating time, the method further includes: Acquire a second parameter data combination for the target parameter within the running time; Determining a past parameter-time fitting function for the target parameter data corresponding to each of the first parameter data combinations, and a current parameter-time fitting function for the target parameter data corresponding to the second parameter data combinations; Determining a contribution, a weight, and a product of the contribution and the weight for each of the at least two past stages, wherein the contribution corresponding to each past stage includes the sum of target index results at all acquisition moments within the elapsed time, the target index result being an index result of a difference between fitting data determined by the current parameter-time fitting function and the past parameter-time fitting function at the corresponding moment, the weight being determined based on a linear function, the independent variable of the linear function being the past duration of the corresponding past stage from the current moment; The predicted data is corrected according to the average of the products corresponding to all the past stages to update the predicted data.

3. The method according to claim 2, characterized in that The weight update is completed by the following steps: For the weight of each past stage, based on the past parameter-time fitting function corresponding to each collection moment, determining the fitting parameter data at the corresponding collection moment, and summarizing the fitting parameter data corresponding to all the collection moments in the current past stage as the fitting parameter data combination; Determine a predicted offset corresponding to each target parameter data in the first parameter data combination in the current past stage, and a sum of the predicted offsets corresponding to all target parameter data in the first parameter data combination, wherein the predicted offset is the square of the ratio of a first difference to a second difference, wherein the first difference is the difference between the target parameter data and the closest fitting parameter data in the fitting parameter data combination, and the second difference is the difference between the target parameter data and the corresponding means of the fitting parameter data combination; The weight is modified according to the sum of the predicted offsets and the similarity index data to update the weight, where the similarity index is the average of the sub-similarity corresponding to all acquisition moments in the running time, the sub-similarity is the inverse of the target offset absolute value index result, and the target offset is the difference between the target parameter data at the corresponding moment in the current past stage and the target parameter data at the corresponding moment in the running time.

4. The method according to claim 1, wherein The determining of the predicted time and the target operating time of the nuclear power equipment in the current operating phase when the predicted time arrives also includes: Determining current operating parameters of the nuclear power equipment, and determining health description data of the nuclear power equipment based on the current operating parameters and a predetermined parameter allowable range; If the health description data corresponds to a first fault, outputting a maintenance work order corresponding to the first fault; If the health description data does not correspond to the first fault, the predicted duration is determined, and the target operating duration of the nuclear power equipment in the current operating stage is determined based on the actual operating duration and the predicted duration.

5. The method according to any one of claims 1 to 4, characterized in that: After determining, based on the prediction data, whether the nuclear power equipment has a fault when it runs for the target operating time in the current operating phase, the method further includes: If the nuclear power equipment currently has a second fault and / or has any type of fault during the target operating time, a maintenance work order for the corresponding fault is generated.

6. The method according to claim 1, characterized in that The prediction duration is an integer multiple of the prediction unit time; The difference between the average operating time of the nuclear power equipment in the current operating stage and the predicted unit time is greater than the target operating time and less than the sum of the target operating time and the predicted unit time.

7. The method according to claim 6, characterized in that Determining the predicted duration, and determining the target operating duration of the nuclear power equipment in the current operating phase based on the actual operating duration and the predicted duration, includes: Obtaining a longest predicted duration, and determining a predicted duration combination based on the longest predicted duration, wherein the predicted duration combination includes at least two linearly increasing predicted durations, and the slopes corresponding to the at least two linearly increasing predicted durations are predicted unit times; Determining a target operating time combination of the nuclear power equipment in the current operating stage according to the combination of the actual operating time and the predicted operating time, wherein the target operating time combination includes at least two target operating time combinations; The determining, based on the target parameter data corresponding to the target operating duration in the past stages corresponding to each of the first parameter data combinations, predicted data for the target parameter when the nuclear power equipment operates for the target operating duration in the current operating stage includes: For each target operating time in the target operating time combination, determining, based on the target parameter data corresponding to the current target operating time in the past stage corresponding to each first parameter data combination, predicted data for the target parameter when the nuclear power equipment operates in the current operating stage to the current target operating time; Determining, based on the prediction data, whether the nuclear power equipment has a fault when it runs in the current operation phase for the target operation time includes: Determine whether a fault occurs when the nuclear power equipment runs for each target operating time in the current operating stage based on the prediction data.

8. An electronic device, characterized in that: The electronic device comprises: 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, and the computer program is executed by the at least one processor so that the at least one processor can execute the nuclear power equipment fault detection method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the nuclear power equipment fault detection method according to any one of claims 1 to 7 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the nuclear power equipment fault detection method according to any one of claims 1 to 7.

Images