Intelligent equipment operation and maintenance method and system based on knowledge mining

Abstract

The invention discloses an equipment intelligent operation and maintenance method and system based on knowledge mining, and the method comprises the steps: obtaining the historical monitoring data of the operation and maintenance of electromechanical equipment, so as to generate a preliminary data set, and the monitoring data comprise operation data and environment data; the preliminary data set is preprocessed, and a preprocessed data set is generated; mining an association relationship between a potential fault mode and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model to an operation and maintenance knowledge base; and obtaining current monitoring data of equipment operation and maintenance, and performing fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base. By utilizing the embodiment of the invention, the operation and maintenance data of the mining equipment can be efficiently processed and knowledge-mined, and accurate fault mode identification and prediction are realized, so that the intelligent level of operation and maintenance decision is improved.

Description

Technical Field

[0001] The present invention belongs to the field of operation and maintenance technology, and in particular to an equipment intelligent operation and maintenance method and system based on knowledge mining. Background Art

[0002] With the rapid development of industrial technology and the high complexity of industrial equipment, the operation and maintenance of equipment has become an important issue in modern manufacturing and other related industries. Traditional equipment maintenance strategies mainly rely on regular inspections and post-failure repairs, which have limited effects in improving equipment reliability and reducing downtime. Especially when equipment failures occur, they often lead to production stagnation, economic losses and safety hazards. Therefore, traditional operation and maintenance methods are gradually unable to meet the needs of efficient, accurate and intelligent operation and maintenance management in modern industrial environments. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for intelligent equipment operation and maintenance based on knowledge mining to address the deficiencies in the prior art, which can efficiently process and knowledge mine equipment operation and maintenance data, achieve accurate fault mode identification and prediction, and improve the intelligence level of operation and maintenance decision-making.

[0004] An embodiment of the present application provides a device intelligent operation and maintenance method based on knowledge mining, the method comprising:

[0005] Acquire historical monitoring data of mechanical and electrical equipment operation and maintenance to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data;

[0006] Preprocessing the preliminary data set to generate a preprocessed data set;

[0007] Mining the correlation between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model in an operation and maintenance knowledge base;

[0008] Acquire current monitoring data of equipment operation and maintenance, and perform fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0009] Optionally, the method further includes: designing a knowledge search engine based on the operation and maintenance knowledge base to support intelligent answers to operation and maintenance questions based on user queries.

[0010] Optionally, the preliminary data set includes:

[0011] D={(d_1,e_1),(d_2,e_2),...,(d_i,e_i),...,(d_n,e_n)}

[0012] Wherein, d_i is the i-th item of operation data of the electromechanical equipment, e_i is the corresponding environmental data, and n is the number of items;

[0013] The preprocessed data set includes:

[0014] D'={f_1(d_1,e_1),f_2(d_2,e_2),...,f_i(d_i,e_i),...,f_n(d_n,e_n)}

[0015] Wherein, f_i is the feature extraction function of the i-th running data.

[0016] Optionally, the operation and maintenance knowledge base includes:

[0017] {(m_1 rightarrow r_1),...,(m_j rightarrow r_j),...,(m_p rightarrow r_p)}

[0018] Among them, the m_j is the j-th fault mode, the r_j is the equipment performance indicator corresponding to the j-th fault mode, and the rightarrow is the cause-effect relationship mapping.

[0019] Another embodiment of the present application provides an intelligent equipment operation and maintenance system based on knowledge mining, the system comprising:

[0020] An acquisition module is used to acquire historical monitoring data of operation and maintenance of electromechanical equipment to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data;

[0021] A processing module, used for preprocessing the preliminary data set to generate a preprocessed data set;

[0022] A generation module is used to mine the correlation between potential failure modes and equipment performance from the preprocessed data set, generate an operation and maintenance knowledge model, and store the knowledge model in an operation and maintenance knowledge base;

[0023] The prediction module is used to obtain the current monitoring data of equipment operation and maintenance, and perform fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0024] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0025] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0026] Compared with the prior art, the present invention provides an intelligent equipment operation and maintenance method based on knowledge mining, which obtains historical monitoring data of electromechanical equipment operation and maintenance to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; preprocesses the preliminary data set to generate a preprocessed data set; mines the correlation between potential fault modes and equipment performance from the preprocessed data set, and generates an operation and maintenance knowledge model, and stores the knowledge model in an operation and maintenance knowledge base; obtains current monitoring data of equipment operation and maintenance, and performs fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base, thereby being able to efficiently process and knowledge mine equipment operation and maintenance data, achieve accurate fault mode identification and prediction, and improve the intelligence level of operation and maintenance decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A hardware structure block diagram of a computer terminal for a device intelligent operation and maintenance method based on knowledge mining provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of a process flow of a device intelligent operation and maintenance method based on knowledge mining provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of the structure of an equipment intelligent operation and maintenance system based on knowledge mining provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0031] The embodiment of the present invention first provides a device intelligent operation and maintenance method based on knowledge mining, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0032] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of a device intelligent operation and maintenance method based on knowledge mining provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0033] The memory 104 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the equipment intelligent operation and maintenance method based on knowledge mining in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] See also Figure 2 The embodiment of the present invention provides a device intelligent operation and maintenance method based on knowledge mining, which may include the following steps:

[0036] S201, obtaining historical monitoring data of electromechanical equipment operation and maintenance to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; specifically, one implementation method may include:

[0037] Step 1: Data source determination First, it is necessary to determine the historical monitoring data source used for electromechanical equipment operation and maintenance. This may include equipment sensors, operation logs, environmental monitoring equipment, etc. By connecting to the interface of the equipment management system or data acquisition system, ensure that the required operation data and environmental data can be obtained. The selection of data sources should take into account the accuracy, real-time and completeness of the data.

[0038] Step 2: Data collection Use data collection tools or API interfaces to systematically collect historical monitoring data of electromechanical equipment. The specific steps are as follows:

[0039] - Define the time frame for data collection (e.g. data for the past year).

[0040] -Configure the collection frequency (such as hourly, daily, etc.) to ensure that the data covers the key operating cycles.

[0041] -Classify the collected raw data by device for easy subsequent processing.

[0042] Step 3: Data formatting After data collection is completed, use data cleaning and format conversion tools to standardize data from different sources to ensure data consistency. The specific steps are as follows:

[0043] -Define a standard format for data, such as converting timestamps into a unified time format, standardizing numerical units, etc.

[0044] - Remove invalid, duplicate or outlier values ​​to ensure data quality.

[0045] Step 4: Have a preliminary data set. Arrange the formatted data into a preliminary data set D. The specific steps are as follows:

[0046] - According to the data category and source, the operation data and environmental data are paired to form tuples.

[0047] - Ensure that the data set contains the operating data and environmental data of all equipment during the entire monitoring period, such as:

[0048] D={(d_1,e_1),(d_2,e_2),...,(d_i,e_i),...,(d_n,e_n)}

[0049] Among them, d_i is the i-th item of operating data of the electromechanical equipment, e_i is the corresponding environmental data, and n is the number of items.

[0050] Through the above steps, the historical monitoring data of electromechanical equipment operation and maintenance was successfully obtained, and a preliminary data set was generated, laying the foundation for subsequent data preprocessing, fault mode mining and operation and maintenance strategy generation. This process not only ensures the quality and integrity of the data, but also provides the necessary data support for subsequent intelligent operation and maintenance.

[0051] S202, preprocessing the preliminary data set to generate a preprocessed data set; specifically, one implementation may include:

[0052] 1. Data cleaning

[0053] -Remove duplicate data: First, deduplicate the preliminary data set D to detect and remove identical records to ensure the uniqueness of each piece of data.

[0054] -Handling missing values:

[0055] - Use K-nearest neighbor algorithm (KNN) to fill missing values. In the data set, for each sample with missing values, find its nearest K similar samples and fill the missing part by calculating the weighted average of these samples.

[0056] -After missing value filling, outlier detection is performed, such as using the Z-score method to identify and remove outliers to ensure the quality of the dataset.

[0057] 2. Data conversion

[0058] -Feature standardization: Use the Z-score standardization method to convert all operating data and environmental data into a standard normal distribution with a mean of 0 and a variance of 1.

[0059] -Category variable encoding: If there are categorical variables (such as equipment status) in the monitoring data, use One-Hot Encoding to convert them into numerical form to facilitate subsequent algorithm processing.

[0060] 3. Feature extraction

[0061] -Time series feature extraction: For time series data, calculate short-term and long-term statistical features, such as moving average, maximum value, minimum value, standard deviation, etc. For the running data d_i, extract the features within its time window:

[0062] -Define the time window size T and calculate the feature value of each time point within the window.

[0063] - Apply Fast Fourier Transform (FFT) to extract frequency domain features to identify potential periodic fluctuations or anomalies.

[0064] -Environmental variable cross-features: Combine multiple variables in the environmental data e_i to generate cross-features, such as the product of temperature and humidity, to capture more complex device behavior patterns.

[0065] 4. Data Integration

[0066] -Integrate the above processing results to form a new preprocessed data set D', where each data contains structured information such as time series features, standardized values, and cross features. The new data set is constructed as follows:

[0067] D'={f_1(d_1,e_1),f_2(d_2,e_2),...,f_i(d_i,e_i),...,f_n(d_n,e_n)}

[0068] Among them, f_i is the feature extraction function of the i-th running data, which can be specifically described in the above feature extraction steps.

[0069] 5. Save the preprocessing results

[0070] -The generated data set D' will be saved to the local database or cloud storage for subsequent fault mode mining and correlation analysis. At the same time, to ensure repeatability, the parameters and configuration files of all preprocessing steps are recorded.

[0071] Through the above steps, the generated preprocessed data set D' will provide a more accurate and high-quality data foundation for the subsequent fault mode mining and construction of operation and maintenance knowledge models, thereby improving the efficiency and accuracy of equipment intelligent operation and maintenance.

[0072] S203, mining the correlation between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model in an operation and maintenance knowledge base;

[0073] The steps of mining the relationship between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model and storing it in the operation and maintenance knowledge base are mainly aimed at extracting the relationship between valuable failure modes and equipment performance indicators from the cleaned and converted data, so as to build an intelligent operation and maintenance knowledge model that can effectively predict and manage the equipment operation status. This model can not only help predict potential failures, but also optimize maintenance strategies and improve equipment reliability and work efficiency.

[0074] Specifically, the operation and maintenance knowledge base may include:

[0075] {(m_1 rightarrow r_1),...,(m_j rightarrow r_j),...,(m_p rightarrow r_p)}

[0076] Wherein, m_j is the jth fault mode, r_j is the device performance indicator corresponding to the jth fault mode, and rightarrow is a causal relationship mapping. An implementation method may include:

[0077] 1. Feature selection and importance assessment

[0078] -Feature Importance Estimation Using Random Forest:

[0079] - Use the random forest algorithm to train on the preprocessed dataset D' and calculate the contribution of each feature to the model performance. The feature importance of the random forest can be determined by calculating the average information gain of each feature at the splitting node of the tree.

[0080] -Select the top k most important features to ensure that subsequent analysis focuses on the features that have the greatest impact on fault mode identification.

[0081] 2. Failure mode identification

[0082] - Apply clustering algorithms to identify failure modes:

[0083] -Use unsupervised learning algorithms such as K-means or DBSCAN to perform cluster analysis on the preprocessed data set. Different failure modes can be identified by analyzing the center point of each cluster and the distribution of samples.

[0084] -For example, the DBSCAN algorithm is used to find dense clustered areas in the high-dimensional feature space. The clusters corresponding to these areas may represent abnormal operating conditions or failure modes of the equipment.

[0085] -Mode verification and optimization:

[0086] - Validate the identified fault patterns and compare the consistency of clustering results with actual fault records. Use cross-validation and expert knowledge to further validate and optimize the fault patterns.

[0087] 3. Correlation analysis between equipment performance and failure mode

[0088] -Build association rules:

[0089] -Use association rule learning algorithms (such as Apriori or FP-Growth) to mine the association between equipment performance indicators and failure modes. By mining the frequently occurring rules in the data set, strong associations between equipment performance indicators (such as temperature, vibration, etc.) and specific failure modes are discovered.

[0090] - Calculate the conditional probability:

[0091] -For each identified failure mode m_j and equipment performance indicator r_j, calculate the conditional probability P(r_j|m_j). This can be achieved through Bayes' theorem, thereby building a probabilistic relationship model between equipment performance and failure mode.

[0092] 4. Construction of operation and maintenance knowledge model

[0093] -Build a cause-effect diagram:

[0094] -Based on association rules and conditional probabilities, a causal graph is constructed to represent the causal relationship between equipment performance indicators and failure modes. Each node represents a failure mode or equipment performance indicator, and each edge represents the causal relationship between them.

[0095] -Use structural equation modeling (SEM) to model and verify causal relationships to ensure the accuracy and reliability of the graphical model.

[0096] -Generate operation and maintenance knowledge model:

[0097] -Convert the constructed causal relationship graph into an operation and maintenance knowledge model. This model will include the mapping relationship between the failure mode m_j and the equipment performance indicator r_j (m_j rightarrow r_j), and store it in the operation and maintenance knowledge base.

[0098] 5. Knowledge base storage and update

[0099] -Storage Model:

[0100] -Store the generated operation and maintenance knowledge model in the form of structured data in the operation and maintenance knowledge base. The storage format can use database tables, graph databases, or file systems. Select the appropriate storage method based on actual needs.

[0101] -Update and Maintenance:

[0102] -Update the operation and maintenance knowledge base regularly to add newly identified failure modes and equipment performance indicator correlations. Use incremental learning and online learning methods to update the model to adapt to equipment changes and new failure modes.

[0103] Through the above steps, the potential relationship between failure modes and equipment performance can be mined from the preprocessed data set, and a detailed operation and maintenance knowledge model can be generated. This model will provide strong support for the intelligent operation and maintenance of equipment, help predict and manage the operating status of equipment, reduce the probability of failure, and improve maintenance efficiency.

[0104] S204, obtaining the current monitoring data of equipment operation and maintenance, and performing fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0105] 1. Real-time monitoring and early warning: By acquiring current monitoring data and combining it with historical data and failure mode models in the operation and maintenance knowledge base, the equipment status can be monitored in real time and potential failure risks can be discovered in a timely manner. This helps to provide early warning, prevent equipment failures, and reduce downtime and maintenance costs.

[0106] 2. Dynamically adjust the operation and maintenance strategy: Generate the corresponding operation and maintenance strategy based on the current equipment status and fault prediction results. This includes optimizing the maintenance cycle, adjusting the maintenance task priority, formulating a repair plan, etc., to achieve the most effective operation and maintenance management.

[0107] 3. Improve decision support: Combining historical failure modes and performance data in the operation and maintenance knowledge base can provide a scientific basis for operation and maintenance decisions, avoid relying on experience and intuition, and improve the accuracy and effectiveness of decisions.

[0108] Specifically, one implementation may include:

[0109] 1. Current data acquisition and feature extraction

[0110] -Real-time data acquisition:

[0111] -Acquire current operating data and environmental data from equipment sensors and monitoring systems to form the current monitoring data set.

[0112] -Feature extraction and normalization:

[0113] -Perform the same feature extraction and standardization processing on the current monitoring data as the aforementioned preprocessed data set to generate a preprocessed data set of the current data to ensure data consistency and comparability.

[0114] 2. Failure prediction

[0115] -Building prediction models:

[0116] -Build a prediction model based on the correlation between failure modes and equipment performance indicators in the operation and maintenance knowledge base. You can use ensemble learning methods (such as random forests, XGBoost) to fuse different prediction models to improve prediction accuracy.

[0117] - Use the failure mode samples in the historical data to train the model so that it can predict the possible failure mode m_j based on the current data.

[0118] -Failure pattern matching:

[0119] -Match the current data feature vector with the fault mode in the operation and maintenance knowledge base. Use cosine similarity, Euclidean distance and other measurement methods to calculate the similarity between the current data and each fault mode, and select the fault modes with the highest similarity as the prediction results.

[0120] 3. Generation of operation and maintenance strategies

[0121] -Strategy generation algorithm:

[0122] -Based on the fault prediction results and the causal relationship in the operation and maintenance knowledge base, the rule engine is applied to generate operation and maintenance strategies. A decision tree algorithm is used to develop specific operation and maintenance strategies for each failure mode.

[0123] -For each identified fault mode m_j, generate a corresponding operation and maintenance strategy based on the associated equipment performance indicator r_j. The strategy may include equipment maintenance, component replacement, operating parameter adjustment, etc.

[0124] -Optimization strategy adjustment:

[0125] - Use optimization algorithms (such as genetic algorithms and simulated annealing) to optimize the initially generated operation and maintenance strategies to reduce maintenance costs and maximize the operating efficiency of the equipment. Consider various factors such as maintenance time, equipment importance, and resource constraints to adjust the priority and implementation order of the strategies.

[0126] 4. Strategy implementation and feedback

[0127] -Strategy Execution:

[0128] -Apply the generated operation and maintenance strategies to the actual operation and maintenance process, including scheduling maintenance tasks, allocating resources, notifying maintenance personnel, etc.

[0129] -Feedback mechanism:

[0130] -Update the operation and maintenance knowledge base and prediction model through feedback from implementation results. Collect failure data and maintenance records after implementation, adjust and retrain the model to improve the accuracy of future predictions and the effectiveness of strategies.

[0131] Through the above steps, the whole process from obtaining current monitoring data to fault prediction and generating operation and maintenance strategies can be realized. This method can not only provide real-time fault warning and optimized operation and maintenance strategies, but also continuously improve the intelligence level of the system and the efficiency of operation and maintenance management through feedback mechanisms.

[0132] Furthermore, a knowledge search engine can be designed based on the operation and maintenance knowledge base to support intelligent answers to operation and maintenance questions based on user queries. A specific implementation method may include:

[0133] 1. Knowledge base data modeling

[0134] -Build a knowledge graph:

[0135] -Model the knowledge in the operation and maintenance knowledge base in the form of a graph, where each node represents an operation and maintenance problem, solution, or related information, and each edge represents the relationship between these knowledge. Use a graph database (such as Neo4j) to build a knowledge graph to ensure the semantic association and structured storage of knowledge.

[0136] -Define semantic tags:

[0137] - Define semantic labels for nodes and edges in the graph to facilitate semantic search and reasoning. For example, failure modes, equipment performance indicators, and solutions are labeled into different categories and the relationships between them (such as causal relationships, association rules, etc.) are specified.

[0138] 2. Natural Language Processing (NLP) and Query Parsing

[0139] -User query understanding:

[0140] -Use natural language processing technology (such as BERT, GPT) to understand the user's query semantically. First, perform word segmentation, part-of-speech tagging, and named entity recognition, and then use semantic parsing technology to convert the user's natural language query into machine-readable query intent.

[0141] -Intent recognition and slot filling:

[0142] - Based on intent recognition algorithms (such as sequence-to-sequence models), identify the user's query intent, fill in slots, and extract key operation and maintenance problem elements (such as failure modes, equipment components, etc.).

[0143] 3. Information retrieval and reasoning

[0144] -Graph query and reasoning:

[0145] -Query the knowledge graph based on the user's query intent. Use the graph query language of the graph database (such as Cypher) to perform graph queries and find knowledge nodes and relationships related to the user's query.

[0146] -Semantic matching and reasoning:

[0147] -Perform semantic matching and reasoning on the related nodes found. Use the reasoning engine in the knowledge graph (such as OWL, RDF) to expand the query results, mine the deep knowledge related to the user's query, and provide a comprehensive answer.

[0148] 4. Answer generation and optimization

[0149] -Answer sorting and filtering:

[0150] - Sort and filter the retrieved results, and determine the final answer based on relevance and confidence scores (calculated by machine learning models such as RankNet). Comprehensively consider the contextual information of the user's query and provide the best answer.

[0151] -Answer Generation:

[0152] -Use generative models (such as GPT-4) to generate natural language answers from search results, ensuring accuracy and readability of the answers. The system should be able to generate concise or detailed answers based on the complexity of the query, taking into account the user's professional background and needs.

[0153] 5. User feedback and system optimization

[0154] - Collect user feedback:

[0155] -After the user obtains the answer, the system should collect user feedback information, such as accuracy evaluation of the answer, satisfaction survey, etc. Use this feedback data for analysis to identify the strengths and weaknesses of the system.

[0156] -Continuous learning and optimization:

[0157] -Use user feedback data to train and optimize the search engine's natural language processing model and reasoning algorithm. Use incremental learning and model retraining methods to continuously improve the search engine's performance and the quality of answers.

[0158] Through the above steps, a knowledge search engine based on the operation and maintenance knowledge base can be built to provide intelligent answers to user queries. This system not only improves the efficiency and accuracy of user queries, but also adapts to the ever-changing operation and maintenance needs and knowledge base content through continuous optimization and learning, providing more intelligent and efficient services. The significance of this system is:

[0159] 1. Improve user experience: Users can obtain specific and accurate answers to operation and maintenance questions through natural language queries without having to deeply understand the complex operation and maintenance knowledge structure within the system. This can significantly improve user convenience and satisfaction.

[0160] 2. Efficient information retrieval: It can quickly find relevant information in the massive operation and maintenance knowledge base, avoiding the inefficiency of traditional manual retrieval. This intelligent search engine automatically locates relevant operation and maintenance knowledge by understanding the user's query intent, improving the speed and accuracy of information acquisition.

[0161] 3. Automated knowledge management: Intelligent search engines automatically process user queries, reducing the need for human intervention. The system can continuously learn and optimize, providing users with increasingly accurate answers and suggestions.

[0162] It can be seen that historical monitoring data of electromechanical equipment operation and maintenance is obtained to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; the preliminary data set is preprocessed to generate a preprocessed data set; the correlation between potential fault modes and equipment performance is mined from the preprocessed data set, and an operation and maintenance knowledge model is generated, and the knowledge model is stored in an operation and maintenance knowledge base; the current monitoring data of equipment operation and maintenance is obtained, and fault prediction and operation and maintenance strategy generation are performed based on the current monitoring data and the operation and maintenance knowledge base, so that equipment operation and maintenance data can be efficiently processed and knowledge mined, and accurate fault mode identification and prediction can be achieved, so as to improve the intelligence level of operation and maintenance decision-making.

[0163] Another embodiment of the present invention provides an intelligent equipment operation and maintenance system based on knowledge mining, see Figure 3 , the system may include:

[0164] The acquisition module 301 is used to acquire historical monitoring data of operation and maintenance of electromechanical equipment to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data;

[0165] A processing module 302 is used to preprocess the preliminary data set to generate a preprocessed data set;

[0166] A generation module 303 is used to mine the correlation between potential failure modes and equipment performance from the preprocessed data set, generate an operation and maintenance knowledge model, and store the knowledge model in an operation and maintenance knowledge base;

[0167] The prediction module 304 is used to obtain current monitoring data of equipment operation and maintenance, and perform fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0168] It can be seen that historical monitoring data of electromechanical equipment operation and maintenance is obtained to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; the preliminary data set is preprocessed to generate a preprocessed data set; the correlation between potential fault modes and equipment performance is mined from the preprocessed data set, and an operation and maintenance knowledge model is generated, and the knowledge model is stored in an operation and maintenance knowledge base; the current monitoring data of equipment operation and maintenance is obtained, and fault prediction and operation and maintenance strategy generation are performed based on the current monitoring data and the operation and maintenance knowledge base, so that equipment operation and maintenance data can be efficiently processed and knowledge mined, and accurate fault mode identification and prediction can be achieved, so as to improve the intelligence level of operation and maintenance decision-making.

[0169] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0170] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0171] S201, acquiring historical monitoring data of operation and maintenance of electromechanical equipment to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data;

[0172] S202, preprocessing the preliminary data set to generate a preprocessed data set;

[0173] S203, mining the correlation between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model in an operation and maintenance knowledge base;

[0174] S204, obtaining current monitoring data of equipment operation and maintenance, and performing fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0175] It can be seen that historical monitoring data of electromechanical equipment operation and maintenance is obtained to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; the preliminary data set is preprocessed to generate a preprocessed data set; the correlation between potential fault modes and equipment performance is mined from the preprocessed data set, and an operation and maintenance knowledge model is generated, and the knowledge model is stored in an operation and maintenance knowledge base; the current monitoring data of equipment operation and maintenance is obtained, and fault prediction and operation and maintenance strategy generation are performed based on the current monitoring data and the operation and maintenance knowledge base, so that equipment operation and maintenance data can be efficiently processed and knowledge mined, and accurate fault mode identification and prediction can be achieved, so as to improve the intelligence level of operation and maintenance decision-making.

[0176] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0177] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0178] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0179] S201, acquiring historical monitoring data of operation and maintenance of electromechanical equipment to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data;

[0180] S202, preprocessing the preliminary data set to generate a preprocessed data set;

[0181] S203, mining the correlation between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model in an operation and maintenance knowledge base;

[0182] S204, obtaining current monitoring data of equipment operation and maintenance, and performing fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

[0183] It can be seen that historical monitoring data of electromechanical equipment operation and maintenance is obtained to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; the preliminary data set is preprocessed to generate a preprocessed data set; the correlation between potential fault modes and equipment performance is mined from the preprocessed data set, and an operation and maintenance knowledge model is generated, and the knowledge model is stored in an operation and maintenance knowledge base; the current monitoring data of equipment operation and maintenance is obtained, and fault prediction and operation and maintenance strategy generation are performed based on the current monitoring data and the operation and maintenance knowledge base, so that equipment operation and maintenance data can be efficiently processed and knowledge mined, and accurate fault mode identification and prediction can be achieved, so as to improve the intelligence level of operation and maintenance decision-making.

[0184] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A method for intelligent equipment operation and maintenance based on knowledge mining, It is characterized in that The method comprises: Acquire historical monitoring data of mechanical and electrical equipment operation and maintenance to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; Preprocessing the preliminary data set to generate a preprocessed data set; Mining the correlation between potential failure modes and equipment performance from the preprocessed data set, generating an operation and maintenance knowledge model, and storing the knowledge model in an operation and maintenance knowledge base; Acquire current monitoring data of equipment operation and maintenance, and perform fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

2. The method according to claim 1, It is characterized in that The method also includes: designing a knowledge search engine based on the operation and maintenance knowledge base to support intelligent answers to operation and maintenance questions based on user queries.

3. The method according to claim 2, It is characterized in that The preliminary dataset includes: D={(d_1,e_1),(d_2,e_2),...,(d_i,e_i),...,(d_n,e_n)} Wherein, d_i is the i-th item of operation data of the electromechanical equipment, e_i is the corresponding environmental data, and n is the number of items; The preprocessed data set includes: D'={f_1(d_1,e_1),f_2(d_2,e_2),...,f_i(d_i,e_i),...,f_n(d_n,e_n)} Wherein, f_i is the feature extraction function of the i-th running data.

4. The method according to claim 3, It is characterized in that The operation and maintenance knowledge base includes: {(m_1rightarrowr_1),...,(m _jrightarrowr_j),...,(m_p rightarrow r_p)} Among them, the m_j is the j-th fault mode, the r_j is the equipment performance indicator corresponding to the j-th fault mode, and the rightarrow is the cause-effect relationship mapping.

5. An intelligent equipment operation and maintenance system based on knowledge mining, It is characterized in that The system comprises: An acquisition module is used to acquire historical monitoring data of operation and maintenance of electromechanical equipment to generate a preliminary data set, wherein the monitoring data includes: operation data and environmental data; A processing module, used for preprocessing the preliminary data set to generate a preprocessed data set; A generation module is used to mine the correlation between potential failure modes and equipment performance from the preprocessed data set, generate an operation and maintenance knowledge model, and store the knowledge model in an operation and maintenance knowledge base; The prediction module is used to obtain the current monitoring data of equipment operation and maintenance, and perform fault prediction and operation and maintenance strategy generation based on the current monitoring data and the operation and maintenance knowledge base.

6. The system according to claim 5, It is characterized in that The system also includes: a search module, which is used to design a knowledge search engine based on the operation and maintenance knowledge base to support intelligent answers to operation and maintenance problems based on user queries.

7. The system according to claim 6, It is characterized in that The preliminary dataset includes: D={(d_1,e_1),(d_2,e_2),...,(d_i,e_i),...,(d_n,e_n)} Wherein, d_i is the i-th item of operation data of the electromechanical equipment, e_i is the corresponding environmental data, and n is the number of items; The preprocessed data set includes: D'={f_1(d_1,e_1),f_2(d_2,e_2),...,f_i(d_i,e_i),...,f_n(d_n,e_n)} Wherein, f_i is the feature extraction function of the i-th running data.

8. The system according to claim 7, It is characterized in that The operation and maintenance knowledge base includes: {(m_1rightarrowr_1),...,(m_j rightarrow r_j),...,(m_prightarrowr_p)} wherein m_j is the j-th fault mode, r_j is the equipment performance indicator corresponding to the j-th fault mode, and rightarrow is a causal relationship mapping.

9. A storage medium, It is characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, It is characterized in that A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images