Equipment maintenance guidance strategy generation method and device, equipment, medium and product

Abstract

The invention discloses an equipment maintenance guidance strategy generation method and apparatus, equipment, a medium and a product. The method comprises the steps of obtaining a to-be-consulted entry based on a power plant equipment maintenance consultation instruction; determining to-be-maintained equipment and first fault information of the to-be-maintained equipment based on the to-be-consulted entry; determining associated equipment of the to-be-maintained equipment, and screening out target associated maintenance equipment from the associated equipment based on the first fault information; obtaining equipment operation information of the target associated maintenance equipment, carrying out fault analysis on the target associated maintenance equipment based on the equipment operation information, obtaining second fault information, inputting the first fault information and the second fault information into a consultation guidance model, obtaining maintenance guidance reply information, and generating an equipment maintenance guidance strategy based on the guidance reply information, according to the invention, intelligent equipment maintenance guidance is realized, and the fault equipment is accurately positioned, so that the fault equipment and the equipment maintenance guidance strategy associated with the fault equipment are accurately generated, and the equipment maintenance efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power plants, and in particular to a method, device, equipment, medium and product for generating equipment maintenance guidance strategy. Background Art

[0002] As the main energy supply industry, the power industry has been under increasing load on power plant equipment as the demand for electricity continues to increase. In recent years, due to the chaotic management of power plant personnel and the rough management of power plant equipment, safety accidents have occurred frequently. Since there are correlations between the equipment in the power plant in terms of materials and communications, when a power plant fails, it is usually not caused by a single device. At present, it is impossible to accurately locate the fault. Only a single analysis of the reported faulty equipment is performed, and the cause of the fault is not deeply analyzed. The equipment related to the faulty equipment cannot be identified, resulting in inaccurate maintenance guidance, and the failure of power plant production cannot be completely solved, resulting in repeated and frequent failures. Summary of the invention

[0003] The main purpose of the present invention is to provide a method, device, equipment, medium and product for generating equipment maintenance guidance strategy, aiming to solve the technical problem that the prior art cannot accurately locate faults, only analyzes the reported faulty equipment, fails to deeply analyze the cause of the fault, and fails to identify equipment related to the faulty equipment, resulting in inaccurate maintenance guidance.

[0004] To achieve the above object, the present invention provides a method for generating an equipment maintenance guidance strategy, the method comprising the following steps:

[0005] In response to the power plant equipment maintenance consultation instruction, obtaining a to-be-consulted term based on the power plant equipment maintenance consultation instruction;

[0006] Determine the device to be repaired and the first fault information of the device to be repaired based on the term to be consulted;

[0007] Determine associated equipment of the equipment to be repaired, and select target associated repair equipment from the associated equipment based on the first fault information;

[0008] Acquire equipment operation information of the target associated maintenance equipment, and perform fault analysis on the target associated maintenance equipment based on the equipment operation information to acquire second fault information of the target associated maintenance equipment;

[0009] The first fault information and the second fault information are input into a pre-built consulting guidance model, maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment is obtained, and an equipment maintenance guidance strategy is generated based on the guidance reply information.

[0010] Optionally, before inputting the first fault information and the second fault information into a pre-built consultation guidance model, obtaining maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generating an equipment maintenance guidance strategy based on the guidance reply information, the method further includes:

[0011] Obtain process description information and maintenance specification information for power plant equipment;

[0012] Generate a training data set based on the process description information and the maintenance specification information;

[0013] Training the original model according to the training data set to obtain a candidate model;

[0014] Obtain historical violation logs for power plant equipment;

[0015] Generate a test data set according to the historical violation log, and test the candidate model based on the test data set;

[0016] The candidate model is iteratively optimized based on the test results until the iteratively optimized candidate model meets the preset guidance conditions, thereby obtaining a consulting guidance model.

[0017] Optionally, generating a test data set according to the historical violation log, and testing the candidate model based on the test data set includes:

[0018] Acquire historical violation operation information based on the historical violation log, and historical maintenance information corresponding to the historical violation operation information;

[0019] Generate a consulting test text and a guiding test text according to the historical illegal operation information and the historical maintenance information;

[0020] A test data set is generated according to the consultation test text and the guidance test text, and the candidate model is tested based on the test data set.

[0021] Optionally, the obtaining the term to be consulted based on the power plant equipment maintenance consultation instruction includes:

[0022] Acquiring maintenance consultation corpus based on the power plant equipment maintenance consultation instruction;

[0023] Obtaining byte information of the maintenance consultation corpus;

[0024] Determining the byte sequence of the maintenance consultation corpus and the consultation characters contained in the maintenance consultation corpus based on the byte information;

[0025] Determine a corpus segmentation path according to the byte sequence and the consultation character;

[0026] Segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain multiple candidate words;

[0027] A target word that meets preset conditions is screened out from the plurality of candidate words according to the rule word library, and a term to be consulted is generated based on the target word.

[0028] Optionally, determining a corpus segmentation path according to the byte sequence and the consultation character includes:

[0029] Get the power plant production specification dictionary;

[0030] Determining a character weight of each consulting character based on the power plant production field dictionary;

[0031] Determining the segmentation length of the maintenance consultation corpus according to the character weight;

[0032] Traversing each consulting character based on the byte sequence and the segmentation length;

[0033] Based on the traversal results, segmentation planning is carried out to determine the corpus segmentation path.

[0034] Optionally, the segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain a plurality of candidate words includes:

[0035] Segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain a plurality of initial words;

[0036] Determine the string length and character frequency of each initial word;

[0037] determining repeated words in the initial words based on the character string length and the character frequency;

[0038] Obtaining the semantic feature vector of each initial word;

[0039] Matching the semantic feature vector based on a preset sensitive word library, and determining the sensitive words in the initial word based on the matching result;

[0040] The repeated words and the sensitive words are removed from the initial words to obtain a plurality of candidate words.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a device for generating a device maintenance guidance strategy, the device for generating a device maintenance guidance strategy comprising:

[0042] A consultation response module, used to respond to the power plant equipment maintenance consultation instruction and obtain the to-be-consulted terms based on the power plant equipment maintenance consultation instruction;

[0043] A first fault location module, used for determining the device to be repaired and first fault information of the device to be repaired based on the term to be consulted;

[0044] An associated fault analysis module, used to determine associated devices of the device to be repaired, and screen out target associated repair devices from the associated devices based on the first fault information;

[0045] A second fault location module is used to obtain equipment operation information of the target associated maintenance equipment, and perform fault analysis on the target associated maintenance equipment based on the equipment operation information to obtain second fault information of the target associated maintenance equipment;

[0046] A maintenance guidance module is used to input the first fault information and the second fault information into a pre-built consulting guidance model, obtain maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generate an equipment maintenance guidance strategy based on the guidance reply information.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes an equipment maintenance guidance strategy generation device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the equipment maintenance guidance strategy generation method as described above.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the equipment maintenance guidance strategy generation method as described above are implemented.

[0049] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the equipment maintenance guidance strategy generation method as described above.

[0050] The present invention responds to a power plant equipment maintenance consultation instruction, obtains a to-be-consulted term based on the power plant equipment maintenance consultation instruction, determines the equipment to be maintained and first fault information of the equipment to be maintained based on the to-be-consulted term, determines associated equipment of the equipment to be maintained, and selects target associated maintenance equipment from the associated equipment based on the first fault information, obtains equipment operation information of the target associated maintenance equipment, performs fault analysis on the target associated maintenance equipment based on the equipment operation information, obtains second fault information of the target associated maintenance equipment, inputs the first fault information and the second fault information into a pre-constructed consultation guidance model, obtains maintenance guidance reply information of the equipment to be maintained and the target associated maintenance equipment, and generates an equipment maintenance guidance strategy based on the guidance reply information; Ming obtains consulting terms by responding to power plant equipment maintenance consulting instructions, locates the faulty equipment to be repaired and fault information reported by the user based on the consulting terms, locates the target associated maintenance equipment with fault-related equipment to be repaired and the second fault information of the target associated maintenance equipment through correlation analysis and fault analysis, inputs the first fault information and the second fault information into a pre-built consulting guidance model, obtains maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generates equipment maintenance guidance strategies based on the guidance reply information, thereby locating the faulty equipment and the associated faulty equipment, accurately generating equipment maintenance guidance strategies, and realizing intelligent maintenance guidance, which not only helps users solve reported explicit faults, but also helps users solve undetected invisible faults, thereby effectively avoiding the problem of frequent faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 It is a structural schematic diagram of a device for generating a device maintenance guidance strategy for a hardware operating environment involved in an embodiment of the present invention;

[0054] Figure 2 It is a flow chart of the first embodiment of the method for generating a device maintenance guidance strategy according to the present invention;

[0055] Figure 3A schematic diagram of a flow chart of a second embodiment of a method for generating a device maintenance guidance strategy according to the present invention;

[0056] Figure 4 This is a structural block diagram of the first embodiment of the device for generating equipment maintenance guidance strategy according to the present invention.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0059] Reference Figure 1 , Figure 1 A device structure diagram is generated for a device maintenance guidance strategy of a hardware operating environment involved in an embodiment of the present invention.

[0060] like Figure 1 As shown, the equipment maintenance guidance strategy generation device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0061] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the equipment maintenance guidance strategy generating device, and may include more or less components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0062] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and an equipment maintenance guidance strategy generation program.

[0063] exist Figure 1 In the equipment maintenance guidance strategy generating device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the equipment maintenance guidance strategy generating device of the present invention can be set in the equipment maintenance guidance strategy generating device, and the equipment maintenance guidance strategy generating device calls the equipment maintenance guidance strategy generating program stored in the memory 1005 through the processor 1001, and executes the equipment maintenance guidance strategy generating method provided by the embodiment of the present invention.

[0064] The embodiment of the present invention provides a method for generating a device maintenance guidance strategy, referring to Figure 2 , Figure 2 It is a flowchart of the first embodiment of the method for generating equipment maintenance guidance strategy of the present invention.

[0065] In this embodiment, the method for generating a device maintenance guidance strategy includes the following steps:

[0066] Step S10: In response to the power plant equipment maintenance consultation instruction, obtaining the term to be consulted based on the power plant equipment maintenance consultation instruction.

[0067] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic terminal device capable of realizing the above functions, etc. The following takes the terminal device as an example to illustrate this embodiment and the following embodiments.

[0068] In order to improve information processing capabilities, in some embodiments, an intelligent assistant can be installed on the terminal device. The intelligent assistant can be a program built based on natural language processing technology of the Generative Pre-trained Transformer (GPT) model. The intelligent assistant can receive user input text, parse the input text into a computer-understandable data format, and then use a pre-trained neural network model to generate response text.

[0069] In the specific implementation, the intelligent assistant uses the neural network in deep learning technology and is trained through a large amount of corpus data, so that it can learn the structure, grammatical rules and semantic information of the language. After the user enters the text, the intelligent assistant will first segment and parse the text, convert it into a computer-readable vector form, and then send it to the pre-trained neural network model for inference. During the inference process, the intelligent assistant will predict the most likely next response based on the text entered by the user and the previous context. This prediction process is based on the model's learning of a large amount of corpus data, so it can largely restore the way humans express natural language and generate highly coherent and natural response text. Finally, the intelligent assistant returns the generated response text to the user to complete a dialogue interaction. Throughout the process, the intelligent assistant will continue to learn and optimize to provide more accurate and user-friendly answers.

[0070] It should be noted that the power plant equipment maintenance consultation instruction may be a consultation instruction sent by a user regarding the repair, maintenance, and detection of power plant equipment. For example, the power plant equipment maintenance consultation instruction may be how to repair the faulty device A. The power plant equipment maintenance consultation instruction may include information such as the device identification, device model, fault cause, and maintenance requirements of the device to be repaired.

[0071] It should be noted that the term to be consulted may be a term containing key maintenance information obtained after processing the power plant equipment maintenance consultation instruction, for example, the term to be consulted may be "how to repair boiler control equipment".

[0072] It is understandable that in order to accurately obtain the information that the user needs to consult, the terminal device can perform word segmentation on the received power plant equipment maintenance consultation instructions to obtain the terms to be consulted, thereby converting the instructions into natural language terms that can be processed by the language processing model.

[0073] Furthermore, in order to accurately obtain the term to be consulted, the above step S10 may include:

[0074] Step S101: Acquire maintenance consultation corpus based on the power plant equipment maintenance consultation instruction.

[0075] It should be noted that the terminal device parses the collected maintenance consultation instructions and extracts key information, such as equipment type, fault description, consultation content, etc., so as to obtain the maintenance consultation corpus.

[0076] Step S102: Acquire the byte information of the maintenance consultation corpus.

[0077] It is understandable that the terminal device can convert the text data of the maintenance consultation corpus into binary form, for example, by character encoding, and convert the maintenance consultation corpus into byte information.

[0078] Step S103: determining the byte sequence of the maintenance consultation corpus and the consultation characters contained in the maintenance consultation corpus based on the byte information.

[0079] It should be noted that the byte information may be byte sequence information of the maintenance consultation corpus, including, for example, bytes, byte order, byte quantity, and byte length.

[0080] Step S104: determining a corpus segmentation path according to the byte sequence and the consultation character.

[0081] It should be noted that the corpus segmentation path may be one or more paths for segmenting the maintenance consultation corpus into vocabulary.

[0082] In some embodiments, the terminal device may select the path with the highest probability from all possible segmentation paths as the optimal word segmentation result, for example, by planning the corpus segmentation path through dynamic programming, greedy algorithm or Viterbi algorithm.

[0083] Furthermore, in order to accurately plan the corpus segmentation path, the above step S104 may include:

[0084] Step S1041: Obtain the power plant production specification dictionary;

[0085] Step S1042: determining the character weight of each consulting character based on the power plant production field dictionary;

[0086] Step S1043: determining the segmentation length of the maintenance consultation corpus according to the character weight;

[0087] Step S1044: traverse each consulting character based on the byte sequence and the segmentation length;

[0088] Step S1045: Perform segmentation planning based on the traversal results and determine the corpus segmentation path.

[0089] It should be noted that the power plant production specification dictionary may be a dictionary containing vocabulary in the field of power plant production specification.

[0090] It is understandable that the terminal device can match each consulting character based on the power plant production field dictionary, determine the importance of each consulting character, and thus set the character weight.

[0091] In some embodiments, the terminal device may calculate the weights using factor analysis, which may extract the main factors and calculate the variance explanation rate of each factor, thereby determining the weight of each consulting character.

[0092] It is understandable that the terminal device can determine the segmentation length of the corpus according to the character weight and the word segmentation result. In the word segmentation process, characters or vocabulary units with higher weights will be given priority, thereby affecting the segmentation path and the final segmentation length.

[0093] It should be understood that the terminal device can traverse each character from the beginning of the byte sequence according to the determined segmentation length. For example, if the segmentation length is 3, then 3 characters are taken from the beginning of the sequence, then move to the next character, and then take 3 characters, and so on. During the traversal process, each segmentation point is recorded, and these segmentation points will be used for subsequent corpus segmentation. At the same time, semantic integrity and grammatical correctness are considered to avoid incorrect segmentation of phrases or sentences.

[0094] Step S105: Segment the maintenance consultation corpus based on the corpus segmentation path to obtain multiple candidate words.

[0095] It is understandable that the terminal device can determine the segmentation length, byte segmentation position, etc. based on the corpus segmentation path to segment the maintenance consultation corpus and obtain multiple candidate words, thereby realizing semantic analysis of the maintenance consultation corpus.

[0096] Furthermore, in order to improve the accuracy of word segmentation, the above step S105 may include:

[0097] Step S1051: segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain a plurality of initial words;

[0098] Step S1052: Determine the character string length and character frequency of each initial word;

[0099] Step S1053: determining repeated words in the initial words based on the character string length and the character frequency;

[0100] Step S1054: Obtaining the semantic feature vector of each initial word;

[0101] Step S1055: matching the semantic feature vector based on a preset sensitive word library, and determining the sensitive word in the initial word based on the matching result;

[0102] Step S1056: remove the repeated words and the sensitive words from the initial words to obtain multiple candidate words.

[0103] It is understood that the terminal device can identify repeated words by traversing all initial words and using the string length and character frequency information. For each word, it is compared with other words in the list, and if words with the same string length and the same character frequency distribution are found, they are considered to be repeated.

[0104] In a specific implementation, for the detected repeated words, deduplication processing is performed according to actual needs. For example, you can choose to keep one instance and delete other repeated instances, or merge them to analyze the frequency of the repeated words.

[0105] It should be understood that the terminal device can convert the preset sensitive word library into a semantic feature vector and then match it with the semantic feature vector of the initial word. The matching can be based on a measurement method such as cosine similarity.

[0106] Step S106: Filtering out a target word that meets a preset condition from the plurality of candidate words according to the rule word library, and generating a term to be consulted based on the target word.

[0107] It should be noted that the rule word library may be a pre-constructed vocabulary list, dictionary, etc. of domain-specific vocabulary in the field of power plants.

[0108] It is understandable that the terminal device can match the candidate words based on the rule word library to determine the field-related words in the candidate words.

[0109] Step S20: Determine the equipment to be repaired and the first fault information of the equipment to be repaired based on the term to be consulted.

[0110] It should be noted that the equipment to be repaired may be a faulty equipment that needs to be repaired, or may be equipment that needs maintenance, inspection, or repair. This embodiment is described by taking the equipment to be repaired as a faulty equipment that needs to be repaired as an example.

[0111] It should be noted that the first fault information may be relevant information of the equipment to be repaired. For example, the first fault information may include the equipment identification, fault manifestation status, operating parameters, abnormal status, fault time, etc. of the equipment to be repaired.

[0112] Step S30: determining the associated devices of the device to be repaired, and selecting target associated repair devices from the associated devices based on the first fault information.

[0113] It should be noted that the associated equipment may be equipment associated with the equipment to be repaired in the power plant, that is, the associated equipment has communication association, connection association and / or operation association with the equipment to be repaired. The above-mentioned target associated repair equipment may be an associated equipment with potential safety and fault hazards caused by the failure of the equipment to be repaired. The failure of the target associated repair equipment may be a hidden failure, that is, it cannot be detected on the surface, but there may be problems with its operation and function.

[0114] It is understandable that the terminal device can obtain the fault manifestation of the device to be repaired based on the first fault information, and determine the target associated repair device that causes the fault manifestation in the associated devices based on the fault manifestation and the historical repair log of the device to be repaired. For example, the associated devices associated with the device to be repaired include device A, device B, and device C. The fault manifestation obtained based on the first fault information of the device to be repaired matches device B. Therefore, it may be that there is a hidden danger in device B, which causes the device to be repaired to fail, and device B is used as the target associated repair device.

[0115] In some embodiments, the terminal device can determine the association type between each associated device and the device to be repaired, determine the fault type of the device to be repaired based on the first fault information, and filter out the target associated repair device based on the fault type and the association type. For example, the association type between the C device and the device to be repaired is a communication association type, and the fault type of the device to be repaired is a communication fault. Therefore, the C device is selected as the target associated repair device because the communication fault of the device to be repaired may cause a fault hazard in the communication-associated C device.

[0116] In some embodiments, the terminal device can analyze the equipment structure network of the power plant and construct an association tree structure of the power plant equipment based on the analysis results, thereby characterizing the association relationship between the power plant equipment. The nodes of the association tree structure are the power plant equipment, and the association relationship between the power plant equipment is the edge of the association tree structure. The associated equipment of the equipment to be repaired is determined based on the association tree structure.

[0117] Step S40: Acquire the equipment operation information of the target associated maintenance equipment, and perform a fault analysis on the target associated maintenance equipment based on the equipment operation information to acquire second fault information of the target associated maintenance equipment.

[0118] It should be understood that the fault existing in the equipment to be repaired may be an explicit fault, that is, the fault of the equipment to be repaired may be in a fault manifestation state, while the fault of the target associated repair equipment may be a hidden fault, that is, the fault of the target associated repair equipment may not have a fault manifestation, but there may be problems with its operation and function.

[0119] It should be noted that the second fault information may be the fault information of the hidden fault of the target associated maintenance equipment, and the second fault information may include the hidden fault type and fault cause of the target associated maintenance equipment. The above-mentioned equipment operation information may include the operation parameters, status information, operation record information, maintenance information, repair information, fault diagnosis information, etc. of the target associated maintenance equipment.

[0120] It can be understood that this embodiment can collect equipment data of the target associated equipment, pre-process the equipment data, obtain equipment operation information, perform feature extraction based on the equipment operation information, obtain equipment feature information of the target associated maintenance equipment, perform fault analysis on the target associated maintenance equipment based on the equipment feature information, and obtain second fault information of the target associated maintenance equipment.

[0121] Step S50: input the first fault information and the second fault information into a pre-built consulting guidance model, obtain maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generate an equipment maintenance guidance strategy based on the guidance reply information.

[0122] It should be noted that the equipment maintenance guidance strategy can be fault diagnosis, fault response measures, maintenance plan formulation, equipment maintenance plan, etc. for the equipment to be maintained and target-related maintenance equipment.

[0123] It is understandable that the consulting guidance model can be a pre-built deep learning model. In some embodiments, the terminal device can build an original model and fine-tune the original model using historical fault data and maintenance records so that it can understand the specific failure mode and maintenance process of the power plant equipment, thereby obtaining a consulting guidance model. The consulting guidance model can use its natural language processing capabilities to generate a preliminary maintenance strategy. This may include recommended inspection steps, spare parts that may be required, and estimated maintenance time.

[0124] This embodiment responds to a power plant equipment maintenance consultation instruction, obtains a to-be-consulted term based on the power plant equipment maintenance consultation instruction, determines the equipment to be maintained based on the to-be-consulted term, and the first fault information of the equipment to be maintained, determines the associated equipment of the equipment to be maintained, and selects a target associated maintenance equipment from the associated equipment based on the first fault information, obtains equipment operation information of the target associated maintenance equipment, performs fault analysis on the target associated maintenance equipment based on the equipment operation information, obtains second fault information of the target associated maintenance equipment, inputs the first fault information and the second fault information into a pre-constructed consultation guidance model, obtains maintenance guidance reply information of the equipment to be maintained and the target associated maintenance equipment, and generates an equipment maintenance guidance strategy based on the guidance reply information; The embodiment obtains consulting terms by responding to the power plant equipment maintenance consulting instruction, locates the faulty equipment to be repaired and the fault information reported by the user based on the consulting terms, locates the target associated maintenance equipment with fault association with the equipment to be repaired and the second fault information of the target associated maintenance equipment through correlation analysis and fault analysis, inputs the first fault information and the second fault information into a pre-built consulting guidance model, obtains the maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generates an equipment maintenance guidance strategy based on the guidance reply information, thereby locating the faulty equipment and the associated faulty equipment, accurately generating the equipment maintenance guidance strategy, and realizing intelligent maintenance guidance, which not only helps users solve the reported explicit faults, but also helps users solve the undetected invisible faults, thereby effectively avoiding the problem of frequent faults.

[0125] refer to Figure 3 , Figure 3 It is a flow chart of the second embodiment of the method for generating equipment maintenance guidance strategy of the present invention.

[0126] Based on the first embodiment above, in this embodiment, before step S50, the following steps are further included:

[0127] Step S51: Acquire process description information and maintenance specification information of power plant equipment.

[0128] It should be noted that the process description information and maintenance specification information may be information described in detail in the maintenance manual or operating procedures of the power plant, which is used to guide maintenance personnel in their daily work. The above process description information may include description information such as operating procedures, maintenance procedures, fault handling procedures, and maintenance procedures. The above maintenance specification information may include information such as safety specifications, preventive maintenance specifications, quality control specifications, and technical specifications.

[0129] It is understandable that the terminal device can collect process description information and maintenance specification information from the operation log, maintenance record, fault report and operation manual of the power plant equipment.

[0130] Step S52: Generate a training data set based on the process description information and the maintenance specification information.

[0131] It should be understood that the terminal device can clean the collected text data, including removing irrelevant content, formatting and standardizing, so as to pre-process the data and obtain pre-processed data. The pre-processed data is converted into structured data, such as converting process descriptions and maintenance specifications into labeled data.

[0132] It can be understood that after the terminal device preprocesses and structures the process description information and the maintenance specification information, it obtains candidate data, performs feature extraction on the candidate data, extracts key features from the annotated data, such as equipment type, fault type, maintenance steps, safety specifications, etc., and uses natural language processing techniques such as word embedding, sentence embedding, etc. to convert text data into numerical features that can be processed by the model, thereby generating a training data set.

[0133] Step S53: training the original model according to the training data set to obtain a candidate model.

[0134] It is understandable that this embodiment can select a suitable machine learning or deep learning algorithm, such as random forest, support vector machine, neural network, etc., and then use the training set data to train the model and adjust the model parameters to optimize performance.

[0135] Step S54: Obtain the historical violation log of the power plant equipment.

[0136] It should be noted that historical violation logs are obtained from the maintenance record system of power plant equipment, which may include detailed information on events such as operating errors, equipment misuse, and violations of safety regulations.

[0137] Step S55: Generate a test data set according to the historical violation log, and test the candidate model based on the test data set.

[0138] It can be understood that this embodiment can clean the collected historical violation logs, including removing irrelevant information, formatting text, processing missing values ​​and duplicate records to improve data quality, and then parse the pre-processed violation logs, for example, using log parsing technology to convert text-based logs into structured data, and extract key information such as time, device identification, violation type, violation description, etc.

[0139] It should be understood that the terminal device performs feature extraction on the preprocessed and formatted log data, extracts features from the structured log data that help the model understand the violation, such as operation type, device status, operator, etc., annotates the extracted features, and determines whether each log entry represents a violation, as well as the severity or type of the violation.

[0140] In the specific implementation, the terminal device preprocesses, structures, extracts features, and labels the historical violation logs to generate a test data set, and tests the candidate model based on the test data set to evaluate the performance indicators of the candidate model, such as accuracy and recall rate, such as comparing the consistency between the violations predicted by the model and the actual labeled violations.

[0141] Furthermore, in order to effectively test the model and ensure model performance, the above step S55 may include:

[0142] Step S551: acquiring historical illegal operation information and historical maintenance information corresponding to the historical illegal operation information based on the historical illegal operation log;

[0143] Step S552: Generate a consulting test text and a guiding test text according to the historical illegal operation information and the historical maintenance information;

[0144] Step S553: ​​Generate a test data set according to the consultation test text and the guidance test text, and test the candidate model based on the test data set.

[0145] It is understandable that the terminal device can pre-process the collected historical violation logs to remove irrelevant information, and then parse the pre-processed logs to extract historical violation operation information and historical maintenance information corresponding to the historical violation operation information.

[0146] In some embodiments, the terminal device can collect historical violation logs from the maintenance record system of the power plant. These logs may include detailed information on events such as operational errors, equipment misuse, and violations of safety regulations. The collected log data is cleaned, including removing irrelevant information, formatting text, and processing missing values ​​and duplicate records to improve data quality. Log parsing technology is used to convert text-based logs into structured data, and key information such as time, equipment identification, violation type, and violation description are extracted. Violation operation information such as operators, violations, and consequences of violations are extracted from the structured log data, and classified and labeled. The violation operation information is associated with historical maintenance records through equipment identification and timestamps, and detailed maintenance records after each violation operation are obtained, including maintenance steps, replacement parts, maintenance personnel, and other information. The extracted violation operation information and corresponding maintenance information are integrated into a unified format to generate consulting test texts and guiding test texts.

[0147] Step S56: iteratively optimize the candidate model based on the test result until the iteratively optimized candidate model meets the preset guidance condition, thereby obtaining a consulting guidance model.

[0148] It should be noted that the preset guidance condition may include that the model output result matches the input violation behavior or fault information, that is, the model output result can respond to the violation behavior or provide a corresponding maintenance strategy based on the fault information. The above preset guidance condition may also be that the candidate model iterative optimization times reach a preset number, for example, the candidate model iterative optimization times reach 100 times, at which point the optimization is stopped.

[0149] This embodiment obtains process description information and maintenance specification information of power plant equipment, generates a training data set based on the process description information and the maintenance specification information, trains the original model according to the training data set to obtain a candidate model, obtains historical violation logs of power plant equipment, generates a test data set according to the historical violation logs, and tests the candidate model based on the test data set, iteratively optimizes the candidate model based on the test result until the iteratively optimized candidate model meets the preset guidance conditions, and obtains the consulting guidance model, thereby realizing automatic and intelligent generation of maintenance guidance strategies. Through automatic and intelligent strategy generation, it is possible to quickly respond to equipment failures, reduce decision-making time, and improve maintenance efficiency. By using historical data and machine learning algorithms, the model can provide accurate fault diagnosis and maintenance suggestions, making the maintenance strategy more scientific.

[0150] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a device maintenance guidance strategy generation program is stored. When the device maintenance guidance strategy generation program is executed by a processor, the steps of the device maintenance guidance strategy generation method described above are implemented.

[0151] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0152] The computer-readable storage medium may be included in the equipment maintenance guidance strategy generation device; or may exist independently without being assembled into the equipment maintenance guidance strategy generation device.

[0153] In addition, an embodiment of the present invention further proposes a computer program product, including an equipment maintenance guidance strategy generation program, which implements the steps of the equipment maintenance guidance strategy generation method as described above when executed by a processor.

[0154] The specific implementation methods of the computer program product of the present invention are basically the same as the various embodiments of the above-mentioned equipment maintenance guidance strategy generation method, and will not be repeated here.

[0155] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the device for generating equipment maintenance guidance strategy according to the present invention.

[0156] like Figure 4 As shown, the device for generating equipment maintenance guidance strategy proposed in the embodiment of the present invention includes:

[0157] The consultation response module 10 is used to respond to the power plant equipment maintenance consultation instruction and obtain the to-be-consulted terms based on the power plant equipment maintenance consultation instruction;

[0158] A first fault location module 20, used to determine the device to be repaired and first fault information of the device to be repaired based on the term to be consulted;

[0159] An associated fault analysis module 30, used to determine associated devices of the device to be repaired, and select target associated repair devices from the associated devices based on the first fault information;

[0160] A second fault location module 40 is used to obtain equipment operation information of the target associated maintenance equipment, and perform fault analysis on the target associated maintenance equipment based on the equipment operation information to obtain second fault information of the target associated maintenance equipment;

[0161] The maintenance guidance module 50 is used to input the first fault information and the second fault information into a pre-built consulting guidance model, obtain maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generate an equipment maintenance guidance strategy based on the guidance reply information.

[0162] Furthermore, the equipment maintenance guidance strategy generating device further includes:

[0163] The model training module 60 is used to obtain process description information and maintenance specification information of power plant equipment; generate a training data set based on the process description information and the maintenance specification information; train the original model according to the training data set to obtain a candidate model; obtain the historical violation log of the power plant equipment; generate a test data set according to the historical violation log, and test the candidate model based on the test data set; iteratively optimize the candidate model based on the test results until the iteratively optimized candidate model meets the preset guidance conditions, thereby obtaining a consulting guidance model.

[0164] Furthermore, the model training module 60 is also used to obtain historical violation operation information based on the historical violation log, and historical maintenance information corresponding to the historical violation operation information; generate a consulting test text and a guiding test text according to the historical violation operation information and the historical maintenance information; generate a test data set according to the consulting test text and the guiding test text, and test the candidate model based on the test data set.

[0165] Furthermore, the equipment maintenance guidance strategy generating device further includes:

[0166] The language processing module 70 is used to obtain maintenance consultation corpus based on the power plant equipment maintenance consultation instruction; obtain byte information of the maintenance consultation corpus; determine the byte sequence of the maintenance consultation corpus and the consultation characters contained in the maintenance consultation corpus based on the byte information; determine the corpus segmentation path according to the byte sequence and the consultation characters; segment the maintenance consultation corpus based on the corpus segmentation path to obtain multiple candidate words; filter out target words that meet preset conditions from the multiple candidate words according to the rule word library, and generate a to-be-consulted term based on the target word.

[0167] Furthermore, the language processing module 70 is also used to obtain a power plant production specification dictionary; determine the character weight of each consulting character based on the power plant production field dictionary; determine the segmentation length of the maintenance consulting corpus according to the character weight; traverse each consulting character based on the byte sequence and the segmentation length; perform segmentation planning based on the traversal results and determine the corpus segmentation path.

[0168] Furthermore, the language processing module 70 is also used to segment the maintenance consultation corpus based on the corpus segmentation path to obtain multiple initial words; determine the string length and character frequency of each initial word; determine the repeated words in the initial words based on the string length and the character frequency; obtain the semantic feature vector of each initial word; match the semantic feature vector based on a preset sensitive word library, and determine the sensitive words in the initial words based on the matching results; remove the repeated words and the sensitive words from the initial words to obtain multiple candidate words.

[0169] This embodiment responds to a power plant equipment maintenance consultation instruction, obtains a to-be-consulted term based on the power plant equipment maintenance consultation instruction, determines the equipment to be maintained based on the to-be-consulted term, and the first fault information of the equipment to be maintained, determines the associated equipment of the equipment to be maintained, and selects a target associated maintenance equipment from the associated equipment based on the first fault information, obtains equipment operation information of the target associated maintenance equipment, performs fault analysis on the target associated maintenance equipment based on the equipment operation information, obtains second fault information of the target associated maintenance equipment, inputs the first fault information and the second fault information into a pre-constructed consultation guidance model, obtains maintenance guidance reply information of the equipment to be maintained and the target associated maintenance equipment, and generates an equipment maintenance guidance strategy based on the guidance reply information; The embodiment obtains consulting terms by responding to the power plant equipment maintenance consulting instruction, locates the faulty equipment to be repaired and the fault information reported by the user based on the consulting terms, locates the target associated maintenance equipment with fault association with the equipment to be repaired and the second fault information of the target associated maintenance equipment through correlation analysis and fault analysis, inputs the first fault information and the second fault information into a pre-built consulting guidance model, obtains the maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generates an equipment maintenance guidance strategy based on the guidance reply information, thereby locating the faulty equipment and the associated faulty equipment, accurately generating the equipment maintenance guidance strategy, and realizing intelligent maintenance guidance, which not only helps users solve the reported explicit faults, but also helps users solve the undetected invisible faults, thereby effectively avoiding the problem of frequent faults.

[0170] The device for generating equipment maintenance guidance strategy provided by the present application adopts the method for generating equipment maintenance guidance strategy in the above-mentioned embodiment, and can solve the technical problem of generating equipment maintenance guidance strategy. Compared with the prior art, the beneficial effect of the device for generating equipment maintenance guidance strategy provided by the present application is the same as the beneficial effect of the method for generating equipment maintenance guidance strategy provided by the above-mentioned embodiment, and other technical features in the device for generating equipment maintenance guidance strategy are the same as the features disclosed in the method in the above-mentioned embodiment, and will not be described in detail here.

[0171] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0172] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0173] In addition, for technical details that are not described in detail in this embodiment, reference can be made to the equipment maintenance guidance strategy generation method provided in any embodiment of the present invention, and will not be repeated here.

[0174] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0175] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0176] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0177] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for generating equipment maintenance guidance strategy, characterized in that: The equipment maintenance guidance strategy generation method comprises: In response to the power plant equipment maintenance consultation instruction, obtaining a to-be-consulted term based on the power plant equipment maintenance consultation instruction; Determine the device to be repaired and the first fault information of the device to be repaired based on the term to be consulted; Determine associated equipment of the equipment to be repaired, and select target associated repair equipment from the associated equipment based on the first fault information; Acquire equipment operation information of the target associated maintenance equipment, and perform fault analysis on the target associated maintenance equipment based on the equipment operation information to acquire second fault information of the target associated maintenance equipment; The first fault information and the second fault information are input into a pre-built consulting guidance model, maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment is obtained, and an equipment maintenance guidance strategy is generated based on the guidance reply information.

2. The method for generating equipment maintenance guidance strategy according to claim 1, characterized in that: Before inputting the first fault information and the second fault information into a pre-built consultation guidance model, obtaining the maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generating the equipment maintenance guidance strategy based on the guidance reply information, the method further includes: Obtain process description information and maintenance specification information for power plant equipment; Generate a training data set based on the process description information and the maintenance specification information; Training the original model according to the training data set to obtain a candidate model; Obtain historical violation logs for power plant equipment; Generate a test data set according to the historical violation log, and test the candidate model based on the test data set; The candidate model is iteratively optimized based on the test results until the iteratively optimized candidate model meets the preset guidance conditions, thereby obtaining a consulting guidance model.

3. The method for generating equipment maintenance guidance strategy according to claim 2, characterized in that: The step of generating a test data set according to the historical violation log and testing the candidate model based on the test data set includes: Acquire historical violation operation information based on the historical violation log, and historical maintenance information corresponding to the historical violation operation information; Generate a consulting test text and a guiding test text according to the historical illegal operation information and the historical maintenance information; A test data set is generated according to the consultation test text and the guidance test text, and the candidate model is tested based on the test data set.

4. The method for generating equipment maintenance guidance strategy according to any one of claims 1 to 3, characterized in that: The obtaining of the to-be-consulted terms based on the power plant equipment maintenance consultation instruction includes: Acquiring maintenance consultation corpus based on the power plant equipment maintenance consultation instruction; Obtaining byte information of the maintenance consultation corpus; Determining the byte sequence of the maintenance consultation corpus and the consultation characters contained in the maintenance consultation corpus based on the byte information; Determine a corpus segmentation path according to the byte sequence and the consultation character; Segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain multiple candidate words; A target word that meets preset conditions is screened out from the plurality of candidate words according to the rule word library, and a term to be consulted is generated based on the target word.

5. The method for generating equipment maintenance guidance strategy according to claim 4, characterized in that: The determining of the corpus segmentation path according to the byte sequence and the consultation character comprises: Get the power plant production specification dictionary; Determining a character weight of each consulting character based on the power plant production field dictionary; Determining the segmentation length of the maintenance consultation corpus according to the character weight; Traversing each consulting character based on the byte sequence and the segmentation length; Based on the traversal results, segmentation planning is carried out to determine the corpus segmentation path.

6. The method for generating equipment maintenance guidance strategy according to claim 5, characterized in that: The word segmentation of the maintenance consultation corpus based on the corpus segmentation path to obtain multiple candidate words includes: Segmenting the maintenance consultation corpus based on the corpus segmentation path to obtain a plurality of initial words; Determine the string length and character frequency of each initial word; determining repeated words in the initial words based on the character string length and the character frequency; Obtaining the semantic feature vector of each initial word; Matching the semantic feature vector based on a preset sensitive word library, and determining the sensitive words in the initial word based on the matching result; The repeated words and the sensitive words are removed from the initial words to obtain a plurality of candidate words.

7. A device for generating equipment maintenance guidance strategy, characterized in that: The equipment maintenance guidance strategy generating device comprises: A consultation response module, used to respond to the power plant equipment maintenance consultation instruction and obtain the to-be-consulted terms based on the power plant equipment maintenance consultation instruction; A first fault location module, used to determine the device to be repaired and first fault information of the device to be repaired based on the term to be consulted; An associated fault analysis module, used to determine associated devices of the device to be repaired, and screen out target associated repair devices from the associated devices based on the first fault information; A second fault location module is used to obtain equipment operation information of the target associated maintenance equipment, and perform fault analysis on the target associated maintenance equipment based on the equipment operation information to obtain second fault information of the target associated maintenance equipment; A maintenance guidance module is used to input the first fault information and the second fault information into a pre-built consulting guidance model, obtain maintenance guidance reply information of the equipment to be repaired and the target associated maintenance equipment, and generate an equipment maintenance guidance strategy based on the guidance reply information.

8. A device for generating equipment maintenance guidance strategy, characterized in that: The equipment maintenance guidance strategy generation device includes: a memory, a processor, and an equipment maintenance guidance strategy generation program stored in the memory and executable on the processor, wherein the equipment maintenance guidance strategy generation program is configured to implement the equipment maintenance guidance strategy generation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an equipment maintenance guidance strategy generation program, and when the equipment maintenance guidance strategy generation program is executed by the processor, the equipment maintenance guidance strategy generation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises an equipment maintenance guidance strategy generation program, and when the equipment maintenance guidance strategy generation program is executed by a processor, the steps of the equipment maintenance guidance strategy generation method according to any one of claims 1 to 6 are implemented.

Images