Unit fault diagnosis method and device, computer equipment, computer readable storage medium and computer program product

Abstract

The invention relates to a unit fault diagnosis method and device, computer equipment, a computer readable storage medium and a computer program product, and relates to the technical field of electric power. The method comprises the following steps: acquiring real-time operation data of a unit in a power plant; when it is detected that operation data meeting a preset abnormal condition exists in the real-time operation data, the real-time operation data and historical normal operation data of the unit are compared, and real-time fault operation data with the difference between the real-time fault operation data and the historical normal operation data meeting a preset difference condition are determined in the real-time operation data; and determining a target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit. By adopting the method, the reliability of unit fault diagnosis can be improved.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for diagnosing unit faults. Background Art

[0002] The unit is the core component of the power plant, and its normal operation is crucial to the output of the power plant. Therefore, it is often necessary to perform fault diagnosis on the unit.

[0003] In related technologies, the experience and knowledge of domain experts are usually used to formulate fault diagnosis rules; however, since the unit can often switch between different operating conditions, the unit's fault conditions are more complicated, which leads to low reliability of unit fault diagnosis based on the experience and knowledge of domain experts. Summary of the invention

[0004] Based on this, it is necessary to provide a unit fault diagnosis method, device, computer equipment, computer-readable storage medium and computer program product that can improve reliability in order to address the technical problem of low reliability of the above-mentioned unit fault diagnosis.

[0005] In a first aspect, the present application provides a unit fault diagnosis method, comprising:

[0006] Obtain real-time operating data of units in power plants;

[0007] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies a preset difference condition is determined in the real-time operating data;

[0008] Based on the real-time fault operation data and the historical fault operation data of the unit, a target fault type of the unit is determined.

[0009] In one embodiment, the real-time operation data is a plurality of pieces; the historical normal operation data is a plurality of pieces, and the plurality of pieces of historical normal operation data are divided into a plurality of groups of normal operation data pairs according to the association relationship between the two pieces;

[0010] After obtaining the real-time operating data of the units in the power plant, it also includes:

[0011] According to the correlation between the real-time operation data, multiple groups of real-time operation data pairs are obtained;

[0012] The comparing the real-time operation data with the historical normal operation data of the unit, and determining the real-time fault operation data whose difference with the historical normal operation data satisfies a preset difference condition in the real-time operation data, includes:

[0013] Comparing the multiple sets of real-time operation data pairs with the multiple sets of normal operation data pairs, and determining, among the multiple sets of real-time operation data pairs, real-time fault operation data pairs whose differences with corresponding normal operation data pairs satisfy the preset difference condition;

[0014] The real-time operation data in the real-time fault operation data pair is determined as the real-time fault operation data.

[0015] In one embodiment, determining, from among the plurality of groups of real-time operation data pairs, a real-time fault operation data pair whose difference with a corresponding normal operation data pair satisfies the preset difference condition comprises:

[0016] From the plurality of sets of real-time operation data pairs and the plurality of sets of normal operation data pairs, obtaining real-time operation data pairs and normal operation data pairs corresponding to the same association relationship;

[0017] Determining a difference value between the real-time operation data pair and the normal operation data pair;

[0018] When the difference value is greater than or equal to a preset difference value threshold, the real-time operation data pair is determined as the real-time fault operation data pair.

[0019] In one embodiment, the historical fault operation data is multiple, the multiple historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one historical fault operation data;

[0020] The determining the target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit includes:

[0021] Determine, based on the real-time fault operation data and the historical fault operation data under each fault type, a classification probability of the real-time fault operation data corresponding to each fault type;

[0022] Based on the classification probabilities corresponding to the various fault types, the fault type of the fault currently occurring in the unit is determined among the various fault types to obtain the target fault type.

[0023] In one of the embodiments, after determining the target fault type of the unit, the method further includes:

[0024] Based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0025] In one embodiment, after obtaining the operating data of the units in the power plant, the method further includes:

[0026] When it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data, the real-time operation data is added to the historical normal operation data.

[0027] In a second aspect, the present application also provides a unit fault diagnosis device, comprising:

[0028] A data acquisition module is used to obtain real-time operating data of the units in the power plant;

[0029] A data comparison module is used to compare the real-time operation data with the historical normal operation data of the unit when it is detected that there is operation data satisfying a preset abnormal condition in the real-time operation data, and to determine the real-time fault operation data whose difference with the historical normal operation data satisfies the preset difference condition in the real-time operation data;

[0030] A fault diagnosis module is used to determine a target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit.

[0031] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0032] Obtain real-time operating data of units in power plants;

[0033] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies a preset difference condition is determined in the real-time operating data;

[0034] Based on the real-time fault operation data and the historical fault operation data of the unit, a target fault type of the unit is determined.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0036] Obtain real-time operating data of units in power plants;

[0037] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies a preset difference condition is determined in the real-time operating data;

[0038] Based on the real-time fault operation data and the historical fault operation data of the unit, a target fault type of the unit is determined.

[0039] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0040] Obtain real-time operating data of units in power plants;

[0041] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies a preset difference condition is determined in the real-time operating data;

[0042] Based on the real-time fault operation data and the historical fault operation data of the unit, a target fault type of the unit is determined.

[0043] The above-mentioned unit fault diagnosis method, device, computer equipment, computer-readable storage medium and computer program product first obtain the real-time operation data of the unit in the power plant; then, when it is detected that there is operation data that meets the preset abnormal conditions in the real-time operation data, the real-time operation data is compared with the historical normal operation data of the unit, and the real-time fault operation data whose difference with the historical normal operation data meets the preset difference conditions is determined in the real-time operation data; then, based on the real-time fault operation data and the historical fault operation data of the unit, the target fault type of the unit is determined. In this way, by detecting whether there is preset abnormal operation data in the real-time operation data, it is possible to preliminarily judge whether the unit has a fault, and by comparing the operation data, it is possible to determine the real-time fault operation data whose difference with the historical normal operation data meets the preset difference conditions, and by the real-time fault operation data and the historical fault operation data, the target fault type of the unit can be obtained, and the fault diagnosis of the unit can be realized; the unit fault diagnosis method based on the above process can cover the fault conditions of the unit under various working conditions compared with the experience and knowledge of experts in the field, thereby improving the reliability of the unit fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of a flow chart of a method for diagnosing a unit fault in one embodiment;

[0046] Figure 2 A flowchart of a step of determining, in real-time operation data, real-time fault operation data whose difference with historical normal operation data satisfies a preset difference condition in an embodiment;

[0047] Figure 3 A flowchart of a step of determining, among a plurality of sets of real-time operating data pairs, a pair of real-time fault operating data whose difference with a corresponding pair of normal operating data satisfies a preset difference condition in one embodiment;

[0048] Figure 4 A flowchart of steps for determining a target fault type of a unit based on real-time fault operation data and historical fault operation data of the unit in one embodiment;

[0049] Figure 5 A schematic flow chart of a method for diagnosing a unit fault in another embodiment;

[0050] Figure 6 A schematic flow chart of a method for diagnosing a pumped storage unit fault in another embodiment;

[0051] Figure 7 is a structural block diagram of a unit fault diagnosis device in one embodiment;

[0052] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0055] In one embodiment, Figure 1 As shown, a unit fault diagnosis method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a server and a terminal, and is implemented through the interaction between the server and the terminal; wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services; the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. In this embodiment, the method includes the following steps S102 to S106:

[0056] Step S102, obtaining real-time operating data of the units in the power plant.

[0057] There are multiple units in a power plant, and each unit consists of multiple equipment.

[0058] Among them, the operating data of the unit includes the operating data of each device when the unit is running; the operating data specifically refers to the status signal of the equipment. Taking the generator set as an example, the status signal includes the water inlet valve opening signal, the water inlet valve closing signal, the generator switch opening signal, the generator switch disconnection signal, etc.

[0059] Specifically, the server collects in real time the status signals of the various devices constituting each unit in the power plant when the unit is in operation, and obtains the real-time operation data of each unit.

[0060] For example, the server obtains the status signal of each pumped storage unit in the energy-storage hydropower plant during operation, and obtains the real-time operation data of each pumped storage unit.

[0061] Step S104, when it is detected that there is operating data that meets the preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and the real-time fault operating data whose difference with the historical normal operating data meets the preset difference condition is determined in the real-time operating data.

[0062] The preset abnormal conditions refer to the preset judgment conditions for preliminarily judging whether an abnormality occurs in the unit based on the experience and knowledge of experts in the field.

[0063] In specific applications, different units correspond to different preset abnormal conditions.

[0064] In specific applications, different units have different historical normal operating data.

[0065] Specifically, for each unit, after the server obtains the real-time operating data of the unit, it determines whether there is operating data that meets the preset abnormal conditions corresponding to the unit. If so, the server preliminarily determines that the unit has a fault, and further compares the real-time operating data of the unit with the historical normal operating data of the unit. In the real-time operating data of the unit, it is determined that the difference between the real-time operating data and the historical normal operating data of the unit meets the preset difference condition, such as operating data with a large difference, and the real-time fault operating data of the unit is obtained.

[0066] For example, the server presets some abnormality criteria for each unit. When the status signals corresponding to these abnormality criteria appear in the status signals of the unit, the server can preliminarily determine that the unit is abnormal.

[0067] To give another example, after obtaining the real-time operation data of the unit, the server may further classify the real-time operation data, specifically, the data may be classified according to the equipment to which the real-time operation data belongs.

[0068] Step S106, determining a target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit.

[0069] The target fault type of the unit refers to the fault type of the fault currently occurring in the unit.

[0070] In specific applications, the server has multiple fault types preset.

[0071] There are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple fault types; further, there is at least one piece of historical fault operation data under each fault type.

[0072] In specific applications, different units have different historical fault operation data.

[0073] Specifically, based on pattern recognition theory, the server determines the possibility that the real-time fault operation data belongs to each fault type according to the real-time fault operation data of each unit and the historical fault operation data of the unit, and then determines the fault type of the current fault of the unit among multiple fault types.

[0074] In the above-mentioned unit fault diagnosis method, first, the server obtains the real-time operation data of the unit in the power plant; then, when the server detects that there is operation data that meets the preset abnormal conditions in the real-time operation data, the server compares the real-time operation data with the historical normal operation data of the unit, and determines the real-time fault operation data whose difference with the historical normal operation data meets the preset difference conditions in the real-time operation data; then, the server determines the target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit. In this way, the server can preliminarily judge whether the unit has a fault by detecting whether there is a preset abnormal operation data in the real-time operation data, and can determine the real-time fault operation data whose difference with the historical normal operation data meets the preset difference conditions in the real-time operation data through the comparison of the operation data. Through the real-time fault operation data and the historical fault operation data, the target fault type of the unit can be obtained, and the fault diagnosis of the unit can be realized; the unit fault diagnosis method based on the above process can cover the fault conditions of the unit under various working conditions compared with the experience and knowledge of experts in the field, thereby improving the reliability of the unit fault diagnosis.

[0075] In an exemplary embodiment, there are multiple pieces of real-time operation data.

[0076] There are multiple pieces of historical normal operation data, and the multiple pieces of historical normal operation data are divided into multiple groups of normal operation data pairs according to the correlation between each pair.

[0077] Among them, the association relationship refers to the logical relationship or temporal relationship between operating data.

[0078] There are at least two pieces of historical normal operation data in each set of normal operation data pair; and there are logical relationships or time sequence relationships between the pieces of historical normal operation data in each set of normal operation data pair.

[0079] After the above step S102, in which the real-time operation data of the units in the power plant are obtained, the following contents are specifically included:

[0080] According to the correlation between the real-time operation data, multiple groups of real-time operation data pairs are obtained.

[0081] There are at least two pieces of real-time operation data in each set of real-time operation data pairs; and there are logical relationships or time sequence relationships between the pieces of real-time operation data in each set of real-time operation data pairs.

[0082] Specifically, for each unit, after obtaining multiple real-time operation data of the unit, the server constructs multiple groups of real-time operation data pairs based on the multiple real-time operation data according to at least one of the logical relationship or time sequence relationship between the real-time operation data.

[0083] like Figure 2 As shown, in the above step S104, the real-time operation data is compared with the historical normal operation data of the unit, and the real-time fault operation data whose difference with the historical normal operation data meets the preset difference condition is determined in the real-time operation data, which specifically includes the following steps:

[0084] Step S202 , comparing the multiple sets of real-time operation data pairs with the multiple sets of normal operation data pairs, and determining, among the multiple sets of real-time operation data pairs, real-time fault operation data pairs whose differences with the corresponding normal operation data pairs satisfy a preset difference condition.

[0085] Step S204: determining the real-time operation data in the real-time fault operation data pair as the real-time fault operation data.

[0086] Specifically, the server compares the real-time operation data pair and the normal operation data pair corresponding to the same association relationship. When the difference between the real-time operation data pair and the normal operation data meets the preset difference condition, the real-time operation data pair is determined as a real-time fault operation data pair, and each real-time operation data therein is determined as real-time fault operation data.

[0087] For example, multiple historical normal operating data of the unit are stored in the normal library, and stored in the form of normal operating data pairs according to the corresponding logical relationship or timing relationship; the server stores multiple real-time operating data of the unit in the real-time library, and also stores them in the form of real-time operating data pairs according to the corresponding logical relationship or timing relationship; then, the server uses a library comparison method to compare the normal operating data pairs and real-time operating data pairs corresponding to the same logical relationship or timing relationship in the normal library and the real-time library one by one. When it is found that the difference between the normal operating data pair and the real-time operating data pair is large, the real-time operating data in the real-time operating data pair is determined as real-time fault operating data.

[0088] In practical applications, the library comparison process can be implemented using a variety of algorithms such as polling and cyclic correction.

[0089] In this embodiment, the server manages the operation data according to operation data pairs based on the association relationship, and can determine the real-time fault operation data from multiple real-time operation data by comparing the corresponding real-time operation data pairs with the normal operation data pairs.

[0090] In an exemplary embodiment, Figure 3 As shown, the above step S202, in multiple groups of real-time operation data pairs, determines the real-time fault operation data pairs whose differences with the corresponding normal operation data pairs meet the preset difference condition, specifically includes the following steps:

[0091] Step S302: acquiring real-time operation data pairs and normal operation data pairs corresponding to the same association relationship from among the multiple sets of real-time operation data pairs and the multiple sets of normal operation data pairs.

[0092] Step S304, determining the difference between the real-time operation data pair and the normal operation data pair.

[0093] Step S306: when the difference value is greater than or equal to the preset difference value threshold, the real-time operation data pair is determined as a real-time fault operation data pair.

[0094] In a specific application, the difference value between the real-time operation data pair and the normal operation data pair may be the difference between each real-time operation data in the real-time operation data pair and the corresponding historical normal operation data in the normal operation data pair; for example, the real-time operation data pair is (5, 8), and the normal operation data pair is (6, 8), then the difference values ​​between the two are 5-6=-1 and 8-8=0 respectively.

[0095] In another specific application, the difference value between the real-time operation data pair and the normal operation data pair can also be the difference between the change amount between each real-time operation data in the real-time operation data and the change amount between each historical normal operation data in the normal operation data pair; for example, the real-time operation data pair is (5, 8), and the normal operation data pair is (6, 8), then the change amount between the real-time operation data is 8-5=3, and the change amount between the normal operation data is 8-6=2, and the difference value between the two is 3-2=1.

[0096] The preset difference condition refers to a preset difference value threshold.

[0097] Specifically, the server obtains real-time operation data pairs and normal operation data pairs corresponding to the same logical relationship or timing relationship from multiple groups of real-time operation data pairs and multiple groups of normal operation data pairs; then, the server determines the difference value between the real-time operation data pair and the normal operation data pair, and when the difference value between the two is greater than or equal to a preset difference value threshold, the server determines the real-time operation data pair as a real-time fault operation data pair.

[0098] In this embodiment, the server can determine the real-time fault operation data pairs from multiple groups of real-time operation data pairs by comparing the corresponding real-time operation data pairs with the normal operation data pairs, and further can determine the real-time fault operation data from multiple real-time operation data.

[0099] In an exemplary embodiment, there are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data.

[0100] like Figure 4 As shown, the above step S106, based on the real-time fault operation data and the historical fault operation data of the unit, determines the target fault type of the unit, specifically including the following steps:

[0101] Step S402 : determining the classification probability of the real-time fault operation data corresponding to each fault type based on the real-time fault operation data and the historical fault operation data under each fault type.

[0102] Step S404: Based on the classification probabilities corresponding to the various fault types, the fault type of the fault currently occurring in the unit is determined from among the various fault types to obtain a target fault type.

[0103] Specifically, the server adopts pattern recognition theory to calculate the classification probability of the real-time fault operation data corresponding to each fault type based on the real-time fault operation data and the historical fault operation data under each fault type. Then, the server determines the fault type with the largest corresponding classification probability among each fault type as the fault type of the current fault of the unit, and obtains the target fault type of the unit.

[0104] In a specific application, the server can obtain the current operation vector of the unit based on the real-time fault operation data, obtain the fault vector of each fault type based on the historical fault operation data under each fault type, and then calculate the distance between the current operation state of the unit represented by the real-time fault operation data and each fault type based on the current operation vector of the unit and the fault vector of each fault type, and determine the classification probability of the current operation state of the unit represented by the real-time fault operation data corresponding to each fault type based on the distance.

[0105] In practical applications, the server can use decision theory methods in pattern recognition theory to identify faults, including but not limited to Bayesian decision theory, threshold decision, support vector machine, decision tree, nearest neighbor algorithm, etc.

[0106] In this embodiment, the server can obtain the classification probability of the real-time fault operation data with respect to each fault type through the real-time fault operation data and the historical fault operation data, thereby realizing fault diagnosis of the unit.

[0107] In an exemplary embodiment, in the above step S106, after determining the target fault type of the unit, the following contents are specifically included: based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0108] Specifically, after determining the target fault type of the unit, the server may also use the real-time fault operation data as newly added historical fault operation data under the target fault type to achieve real-time update and maintenance of the historical fault operation data.

[0109] For example, multiple historical fault operation data are stored in the fault library and stored in the form of historical fault operation data under each fault type. The server adds the real-time fault operation data to the fault library storing the historical fault operation data as the newly added historical fault operation data under the target fault type.

[0110] In this embodiment, the server can continuously optimize the accuracy of the process of determining the target fault type by updating and maintaining the historical fault operation data in real time, thereby improving the reliability of the unit fault diagnosis.

[0111] In an exemplary embodiment, in the above step S102, after obtaining the operating data of the units in the power plant, the following content is specifically included: when it is detected that there is no operating data that meets the preset abnormal conditions in the real-time operating data, the real-time operating data is added to the historical normal operating data.

[0112] Specifically, if there is no operation data satisfying the corresponding preset abnormal condition in the real-time operation data of the unit, the server adds the real-time operation data of the unit to the historical normal operation data of the unit to achieve real-time update and maintenance of the historical normal operation data.

[0113] For example, multiple historical normal operation data are stored in the normal database. The server adds the real-time operation data to the normal database as newly added historical normal operation data.

[0114] In this embodiment, the server can continuously optimize the accuracy of determining the real-time fault operation data by updating and maintaining the historical normal operation data in real time, thereby improving the reliability of the unit fault diagnosis.

[0115] In an exemplary embodiment, if Figure 5 As shown, another unit fault diagnosis method is provided, which is described by taking the method applied to a server as an example, and includes the following steps:

[0116] Step S502, obtaining real-time operating data of the units in the power plant.

[0117] Step S504, obtaining multiple groups of real-time operation data pairs according to the association relationship between the two real-time operation data.

[0118] Step S506, when it is detected that there is operation data satisfying the preset abnormal condition in the real-time operation data, real-time operation data pairs and normal operation data pairs corresponding to the same association relationship are obtained from the multiple sets of real-time operation data pairs and the multiple sets of normal operation data pairs.

[0119] Step S508, determining a difference value between the real-time operation data pair and the normal operation data pair, and determining the real-time operation data pair as a real-time fault operation data pair when the difference value is greater than or equal to a preset difference value threshold.

[0120] Step S510: determining the real-time operation data in the real-time fault operation data pair as the real-time fault operation data.

[0121] Step S512: determining the classification probability of the real-time fault operation data corresponding to each fault type based on the real-time fault operation data and the historical fault operation data under each fault type.

[0122] Step S514: Based on the classification probabilities corresponding to the various fault types, the fault type of the fault currently occurring in the unit is determined from among the various fault types to obtain a target fault type.

[0123] Step S516: based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0124] In this embodiment, by detecting whether there is preset abnormal operation data in the real-time operation data, it is possible to preliminarily determine whether a fault occurs in the unit. By comparing the operation data, it is possible to determine in the real-time operation data the real-time fault operation data whose difference from the historical normal operation data satisfies the preset difference condition. Through the real-time fault operation data and the historical fault operation data, the target fault type of the unit can be obtained, thereby realizing fault diagnosis of the unit. Compared with the experience and knowledge of experts in the field, the unit fault diagnosis method based on the above process can cover the fault conditions of the unit under various operating conditions, thereby improving the reliability of the unit fault diagnosis.

[0125] In order to more clearly illustrate the unit fault diagnosis method provided in the embodiment of the present application, the unit fault diagnosis is specifically described below with a specific embodiment, but it should be understood that the embodiment of the present application is not limited thereto. Figure 6 As shown, in one exemplary embodiment, the present application also provides a pumped storage unit fault diagnosis method, which specifically includes the following contents:

[0126] The status signals of each pumped-storage unit at the pumped-storage hydropower plant are continuously transmitted to the server; the server queries the signal, and when it is found that the unit has entered an abnormal operating condition, the status signal is compared and analyzed with the status signal under normal conditions to identify and confirm that the pumped-storage unit is indeed faulty; the server then uses decision theory methods in pattern recognition theory to accurately identify and organize the fault types of the pumped-storage unit, and then the server counts the fault types and related status signals to establish a fault database.

[0127] In this embodiment, the server can analyze the specific cause of the fault after logical judgment based on the fault situation, which speeds up the speed and accuracy of technicians in finding and handling faults and reduces the unit standby time.

[0128] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0129] Based on the same inventive concept, the embodiment of the present application also provides a unit fault diagnosis device for implementing the unit fault diagnosis method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more unit fault diagnosis device embodiments provided below can refer to the limitations of the unit fault diagnosis method above, and will not be repeated here.

[0130] In an exemplary embodiment, Figure 7 As shown, a unit fault diagnosis device is provided, including: a data acquisition module 702, a data comparison module 704 and a fault diagnosis module 706, wherein:

[0131] The data acquisition module 702 is used to acquire the real-time operation data of the units in the power plant.

[0132] The data comparison module 704 is used to compare the real-time operation data with the historical normal operation data of the unit when it is detected that there is operation data that meets the preset abnormal condition in the real-time operation data, and to determine the real-time fault operation data whose difference with the historical normal operation data meets the preset difference condition.

[0133] The fault diagnosis module 706 is used to determine the target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit.

[0134] In an exemplary embodiment, there are multiple pieces of real-time operation data; there are multiple pieces of historical normal operation data, and the multiple pieces of historical normal operation data are divided into multiple groups of normal operation data pairs according to the association relationship between each pair.

[0135] The data acquisition module 702 is further used to obtain multiple groups of real-time operation data pairs according to the association relationship between the real-time operation data.

[0136] The data comparison module 704 is also used to compare multiple groups of real-time operation data pairs with multiple groups of normal operation data pairs, and determine, among the multiple groups of real-time operation data pairs, real-time fault operation data pairs whose differences with the corresponding normal operation data pairs meet preset difference conditions; and determine the real-time operation data in the real-time fault operation data pairs as real-time fault operation data.

[0137] In an exemplary embodiment, the data comparison module 704 is also used to obtain real-time operation data pairs and normal operation data pairs corresponding to the same association relationship among multiple groups of real-time operation data pairs and multiple groups of normal operation data pairs; determine the difference value between the real-time operation data pairs and the normal operation data pairs; and when the difference value is greater than or equal to a preset difference value threshold, determine the real-time operation data pair as a real-time fault operation data pair.

[0138] In an exemplary embodiment, there are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data.

[0139] The fault diagnosis module 706 is also used to determine the classification probability of the real-time fault operation data corresponding to each fault type based on the real-time fault operation data and the historical fault operation data under each fault type; based on the classification probability corresponding to each fault type, the fault type of the current fault of the unit is determined in each fault type to obtain the target fault type.

[0140] In an exemplary embodiment, the unit fault diagnosis device further includes a data updating module for adding the real-time fault operation data to the historical fault operation data based on the real-time fault operation data and the target fault type.

[0141] In an exemplary embodiment, the data updating module is further configured to add the real-time operation data to the historical normal operation data when it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data.

[0142] Each module in the above-mentioned unit fault diagnosis device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0143] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the operating data of the unit. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for diagnosing unit faults is implemented.

[0144] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0145] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0146] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0147] Obtain real-time operating data of units in power plants;

[0148] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies the preset difference condition is determined in the real-time operating data;

[0149] Based on the real-time fault operation data and the historical fault operation data of the unit, the target fault type of the unit is determined.

[0150] In one embodiment, there are multiple pieces of real-time operation data; there are multiple pieces of historical normal operation data, and the multiple pieces of historical normal operation data are divided into multiple groups of normal operation data pairs according to the association relationship between each pair.

[0151] When the processor executes the computer program, the following steps are also implemented: according to the association relationship between the real-time operation data, multiple groups of real-time operation data pairs are obtained.

[0152] When the processor executes the computer program, the following steps are also implemented: comparing multiple groups of real-time operation data pairs with multiple groups of normal operation data pairs, and determining, among the multiple groups of real-time operation data pairs, real-time fault operation data pairs whose differences with the corresponding normal operation data pairs meet preset difference conditions; and determining the real-time operation data in the real-time fault operation data pairs as real-time fault operation data.

[0153] In one embodiment, when the processor executes the computer program, the following steps are also implemented: from multiple groups of real-time operation data pairs and multiple groups of normal operation data pairs, real-time operation data pairs and normal operation data pairs corresponding to the same association relationship are obtained; the difference value between the real-time operation data pairs and the normal operation data pairs is determined; when the difference value is greater than or equal to a preset difference value threshold, the real-time operation data pair is determined as a real-time fault operation data pair.

[0154] In one embodiment, there are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data.

[0155] When the processor executes the computer program, the following steps are also implemented: based on the real-time fault operation data and the historical fault operation data under each fault type, the classification probability of the real-time fault operation data corresponding to each fault type is determined; based on the classification probability corresponding to each fault type, the fault type of the current fault of the unit is determined in each fault type to obtain the target fault type.

[0156] In one embodiment, when the processor executes the computer program, the following steps are further implemented: based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0157] In one embodiment, when the processor executes the computer program, the following steps are further implemented: when it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data, the real-time operation data is added to the historical normal operation data.

[0158] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0159] Obtain real-time operating data of units in power plants;

[0160] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies the preset difference condition is determined in the real-time operating data;

[0161] Based on the real-time fault operation data and the historical fault operation data of the unit, the target fault type of the unit is determined.

[0162] In one embodiment, there are multiple pieces of real-time operation data; there are multiple pieces of historical normal operation data, and the multiple pieces of historical normal operation data are divided into multiple groups of normal operation data pairs according to the association relationship between each pair.

[0163] When the computer program is executed by the processor, the following steps are also implemented: according to the association relationship between the real-time operation data, multiple groups of real-time operation data pairs are obtained.

[0164] When the computer program is executed by the processor, the following steps are also implemented: comparing multiple groups of real-time operation data pairs with multiple groups of normal operation data pairs, and determining, among the multiple groups of real-time operation data pairs, real-time fault operation data pairs whose differences with the corresponding normal operation data pairs meet preset difference conditions; and determining the real-time operation data in the real-time fault operation data pairs as real-time fault operation data.

[0165] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: from multiple groups of real-time operation data pairs and multiple groups of normal operation data pairs, real-time operation data pairs and normal operation data pairs corresponding to the same association relationship are obtained; the difference value between the real-time operation data pairs and the normal operation data pairs is determined; when the difference value is greater than or equal to a preset difference value threshold, the real-time operation data pair is determined as a real-time fault operation data pair.

[0166] In one embodiment, there are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data.

[0167] When the computer program is executed by the processor, the following steps are also implemented: based on the real-time fault operation data and the historical fault operation data under each fault type, the classification probability of the real-time fault operation data corresponding to each fault type is determined; based on the classification probability corresponding to each fault type, the fault type of the current fault of the unit is determined in each fault type to obtain the target fault type.

[0168] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0169] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: when it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data, the real-time operation data is added to the historical normal operation data.

[0170] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0171] Obtain real-time operating data of units in power plants;

[0172] When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies the preset difference condition is determined in the real-time operating data;

[0173] Based on the real-time fault operation data and the historical fault operation data of the unit, the target fault type of the unit is determined.

[0174] In one embodiment, there are multiple pieces of real-time operation data; there are multiple pieces of historical normal operation data, and the multiple pieces of historical normal operation data are divided into multiple groups of normal operation data pairs according to the association relationship between each pair.

[0175] When the computer program is executed by the processor, the following steps are also implemented: according to the association relationship between the real-time operation data, multiple groups of real-time operation data pairs are obtained.

[0176] When the computer program is executed by the processor, the following steps are also implemented: comparing multiple groups of real-time operation data pairs with multiple groups of normal operation data pairs, and determining, among the multiple groups of real-time operation data pairs, real-time fault operation data pairs whose differences with the corresponding normal operation data pairs meet preset difference conditions; and determining the real-time operation data in the real-time fault operation data pairs as real-time fault operation data.

[0177] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: from multiple groups of real-time operation data pairs and multiple groups of normal operation data pairs, real-time operation data pairs and normal operation data pairs corresponding to the same association relationship are obtained; the difference value between the real-time operation data pairs and the normal operation data pairs is determined; when the difference value is greater than or equal to a preset difference value threshold, the real-time operation data pair is determined as a real-time fault operation data pair.

[0178] In one embodiment, there are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data.

[0179] When the computer program is executed by the processor, the following steps are also implemented: based on the real-time fault operation data and the historical fault operation data under each fault type, the classification probability of the real-time fault operation data corresponding to each fault type is determined; based on the classification probability corresponding to each fault type, the fault type of the current fault of the unit is determined in each fault type to obtain the target fault type.

[0180] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: when it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data, the real-time operation data is added to the historical normal operation data.

[0182] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0183] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0184] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A unit fault diagnosis method, characterized in that: The method comprises: Obtain real-time operating data of units in power plants; When it is detected that there is operating data satisfying a preset abnormal condition in the real-time operating data, the real-time operating data is compared with the historical normal operating data of the unit, and real-time fault operating data whose difference with the historical normal operating data satisfies a preset difference condition is determined in the real-time operating data; Based on the real-time fault operation data and the historical fault operation data of the unit, a target fault type of the unit is determined.

2. The method according to claim 1, characterized in that There are multiple real-time operation data; there are multiple historical normal operation data, and the multiple historical normal operation data are divided into multiple groups of normal operation data pairs according to the correlation relationship between each two; After obtaining the real-time operating data of the units in the power plant, it also includes: According to the correlation between the real-time operation data, multiple groups of real-time operation data pairs are obtained; The comparing the real-time operation data with the historical normal operation data of the unit, and determining the real-time fault operation data whose difference with the historical normal operation data satisfies a preset difference condition in the real-time operation data, includes: Comparing the multiple sets of real-time operation data pairs with the multiple sets of normal operation data pairs, and determining, among the multiple sets of real-time operation data pairs, real-time fault operation data pairs whose differences with corresponding normal operation data pairs satisfy the preset difference condition; The real-time operation data in the real-time fault operation data pair is determined as the real-time fault operation data.

3. The method according to claim 2, characterized in that Determining, from among the plurality of groups of real-time operation data pairs, a real-time fault operation data pair whose difference with the corresponding normal operation data pair satisfies the preset difference condition comprises: From the plurality of sets of real-time operation data pairs and the plurality of sets of normal operation data pairs, obtaining real-time operation data pairs and normal operation data pairs corresponding to the same association relationship; Determining a difference value between the real-time operation data pair and the normal operation data pair; When the difference value is greater than or equal to a preset difference value threshold, the real-time operation data pair is determined as the real-time fault operation data pair.

4. The method according to claim 1, characterized in that There are multiple pieces of historical fault operation data, and the multiple pieces of historical fault operation data correspond to multiple preset fault types, and each fault type corresponds to at least one piece of historical fault operation data; The determining the target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit includes: Determine, based on the real-time fault operation data and the historical fault operation data under each fault type, a classification probability of the real-time fault operation data corresponding to each fault type; Based on the classification probabilities corresponding to the various fault types, the fault type of the fault currently occurring in the unit is determined among the various fault types to obtain the target fault type.

5. The method according to any one of claims 1 to 4, characterized in that: After determining the target fault type of the unit, the method further includes: Based on the real-time fault operation data and the target fault type, the real-time fault operation data is added to the historical fault operation data.

6. The method according to any one of claims 1 to 4, characterized in that: After obtaining the operating data of the units in the power plant, it also includes: When it is detected that there is no operation data satisfying the preset abnormal condition in the real-time operation data, the real-time operation data is added to the historical normal operation data.

7. A unit fault diagnosis device, characterized in that: The device comprises: A data acquisition module is used to obtain real-time operating data of the units in the power plant; A data comparison module is used to compare the real-time operation data with the historical normal operation data of the unit when it is detected that there is operation data satisfying a preset abnormal condition in the real-time operation data, and to determine the real-time fault operation data whose difference with the historical normal operation data satisfies the preset difference condition in the real-time operation data; A fault diagnosis module is used to determine a target fault type of the unit based on the real-time fault operation data and the historical fault operation data of the unit.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images