Monitoring method and device based on data asset management platform, equipment and medium

Abstract

The invention discloses a monitoring method and device based on a data asset management platform, equipment and a medium. The method comprises the steps of obtaining power plant data of a plurality of power plants from a data asset management platform; the power plant data comprises equipment operation data, production log data and financial index data; the equipment operation data comprises sensor real-time monitoring parameters, the production log data comprises unstructured operation and maintenance records, and the financial index data comprises structured economic parameters; performing time sequence feature extraction and reconstruction error analysis on the equipment operation data and the production log data to obtain a progressive degradation trend; according to the equipment operation data and the financial index data, constructing a dynamic association relationship between an equipment state and a financial index, and according to the dynamic association relationship, calculating a risk conduction probability value; and generating monitoring information according to the risk conduction probability value and the equipment degradation trend, and if it is determined that corresponding power plant data is abnormal and early warning information is generated according to the monitoring information, completing monitoring of each power plant data.

Description

Technical Field

[0001] This application relates to the technical field of asset management, and particularly to a monitoring method, device, equipment and medium based on a data asset management platform. Background Art

[0002] In the power industry, the equipment operation, production logs and financial indicators of power plants are important data sources reflecting the operation status of power plants. Traditional power plant data monitoring methods mainly rely on sensors to monitor equipment operation parameters in real time, combined with manual inspections and simple data analysis tools for equipment status assessment. However, with the expansion of power plant scale and the increase in equipment complexity, traditional monitoring methods have problems such as single data source, lack of dynamic correlation analysis and limited risk warning capabilities.

[0003] In recent years, with the rapid development of big data technology, artificial intelligence and time series analysis technology, more and more research has begun to focus on how to improve the accuracy and comprehensiveness of power plant data monitoring through multi-source data fusion and intelligent analysis methods. However, there are still technical gaps in the fusion analysis of equipment operation data and unstructured production log data, the dynamic correlation modeling of equipment status and financial indicators, and the calculation of risk conduction probability in the existing technology. There is an urgent need for a more intelligent and comprehensive monitoring method to solve the above problems. Summary of the Invention

[0004] This application provides a monitoring method, device, equipment and medium based on a data asset management platform, aiming to solve the problem that there are still technical gaps in the fusion analysis of equipment operation data and unstructured production log data, the dynamic correlation modeling of equipment status and financial indicators, and the calculation of risk conduction probability in the existing technology.

[0005] In a first aspect, this application provides a monitoring method based on a data asset management platform, and the method includes:

[0006] Obtain power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data and financial indicator data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial indicator data includes structured economic parameters;

[0007] Extract time series features and reconstruct error analysis for the equipment operation data and production log data to obtain a progressive degradation trend;

[0008] Construct a dynamic correlation relationship between equipment status and financial indicators according to the equipment operation data and financial indicator data, and calculate a risk conduction probability value according to the dynamic correlation relationship;

[0009] Generate monitoring information based on the risk conduction probability value and the equipment deterioration trend. If it is determined that the corresponding power plant data is abnormal according to the monitoring information, generate a warning message to complete the monitoring of each piece of power plant data.

[0010] In some embodiments, the extracting temporal characteristics and reconstructing error analysis of the equipment operation data and production log data to obtain a progressive deterioration trend includes: preprocessing the equipment operation data and production log data respectively; extracting operation temporal characteristics and production temporal characteristics from the preprocessed equipment operation data and production log data respectively; reconstructing the operation temporal characteristics and production temporal characteristics to obtain the reconstruction errors corresponding to the operation temporal characteristics and production temporal characteristics; determining the positions of abnormal points in the equipment operation data and production log data according to the reconstruction errors; obtaining abnormal data from the equipment operation data and production log data according to the positions of the abnormal points; and obtaining the progressive deterioration trend according to the abnormal data.

[0011] Exemplarily, the equipment operation data is time series data, and the production log data is unstructured data; the preprocessing of the equipment operation data and production log data respectively includes: performing data cleaning and standardization on the equipment operation data to remove noise and outliers in the equipment operation data; and performing text preprocessing on the production log data, where the text preprocessing includes word segmentation, stop word removal, and word vectorization.

[0012] Exemplarily, the extracting operation temporal characteristics and production temporal characteristics from the preprocessed equipment operation data and production log data respectively includes: based on the sliding window technique, extracting in the equipment operation data according to a preset length and a preset time window to obtain the operation temporal characteristics; in the production log data, obtaining the keyword frequency and semantic change information corresponding to a preset keyword; and constructing the production temporal characteristics according to the keyword frequency and semantic change information.

[0013] In some embodiments, the constructing a dynamic association relationship between the equipment state and financial indicators based on the equipment operation data and financial indicator data includes: aligning the time of the equipment operation data and financial indicator data; extracting equipment state characteristics from the equipment operation data and financial indicator characteristics from the financial operation data; obtaining the dynamic association relationship corresponding to the equipment state characteristics and the financial indicator characteristics according to a preset analysis algorithm; and the analysis algorithm includes one or more of a multiple regression analysis algorithm, a time series analysis algorithm, a graph model analysis algorithm, and a causal relationship analysis algorithm.

[0014] In some embodiments, generating the monitoring information according to the risk conduction probability value and the equipment deterioration trend includes: standardizing the risk conduction probability value and the equipment deterioration trend to obtain a risk conduction coefficient and an equipment deterioration coefficient within a preset value range; calculating an anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient, and generating the monitoring information according to the anomaly coefficient.

[0015] Exemplarily, calculating the anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient includes: performing exponential transformation on the risk conduction coefficient and the equipment deterioration coefficient; the exponential transformation intensities of the risk conduction coefficient and the equipment deterioration coefficient are different; calculating the anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient after exponential transformation; the expression of the anomaly coefficient includes:

[0016] where C is the anomaly coefficient, γ is a preset weight, d is the equipment deterioration coefficient, r is the risk conduction coefficient, and α and β are intensity coefficients corresponding to the transformation intensities.

[0017] In a second aspect, the present application provides a monitoring device based on a data asset management platform, including:

[0018] A data acquisition module, configured to acquire power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data, and financial indicator data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial indicator data includes structured economic parameters;

[0019] An error analysis module, configured to perform time series feature extraction and reconstruction error analysis on the equipment operation data and the production log data to obtain a progressive deterioration trend;

[0020] A conduction calculation module, configured to construct a dynamic association relationship between the equipment state and the financial indicator according to the equipment operation data and the financial indicator data, and calculate a risk conduction probability value according to the dynamic association relationship;

[0021] A monitoring completion module, configured to generate monitoring information according to the risk conduction probability value and the equipment deterioration trend, and generate a warning information if it is determined according to the monitoring information that the corresponding power plant data is abnormal, and complete the monitoring of each piece of the power plant data.

[0022] In a third aspect, the present application provides a computer device, including a memory and a processor; the memory is used to store a computer program; the processor is configured to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0023] Fourthly, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes one or more processors to execute the method provided in any embodiment of the present application.

[0024] The present application discloses a monitoring method, device, equipment and medium based on a data asset management platform. The core of this method lies in comprehensively analyzing multi-dimensional data of power plants through the data asset management platform, specifically including the following steps:

[0025] Data acquisition: Obtain power plant data of multiple power plants from the data asset management platform, including equipment operation data, production log data and financial indicator data. Equipment operation data mainly refers to parameters monitored in real time by sensors, production log data includes unstructured operation and maintenance records, and financial indicator data are structured economic parameters.

[0026] Time series feature extraction and reconstruction error analysis: Extract time series features from equipment operation data and production log data, and identify the progressive degradation trend of equipment through reconstruction error analysis. This step helps to detect potential problems of equipment in advance.

[0027] Dynamic correlation relationship construction: Construct a dynamic correlation relationship between equipment status and financial indicators according to equipment operation data and financial indicator data. This correlation relationship can help to understand the impact of equipment status changes on financial indicators.

[0028] Risk conduction probability calculation: Based on the above dynamic correlation relationship, calculate the risk conduction probability value. This helps to evaluate the financial risks that may be brought about by equipment status changes.

[0029] Monitoring information generation and early warning: Generate monitoring information according to the risk conduction probability value and the equipment degradation trend. If the monitoring information shows that the power plant data is abnormal, the system will generate early warning information, thereby realizing real-time monitoring of the data of each power plant.

[0030] The method provided has at least the following beneficial effects:

[0031] 1. Multi-dimensional data fusion analysis: This method conducts fusion analysis on equipment operation data, production log data and financial indicator data, overcomes the limitations of traditional methods in analyzing single data types, and provides a more comprehensive monitoring perspective.

[0032] 2. Early warning: Through time series feature extraction and reconstruction error analysis, it is possible to identify the progressive degradation trend of equipment in advance, so as to give an early warning before the equipment has serious problems and reduce the losses caused by equipment failures.

[0033] 3. Dynamic association modeling: Construct a dynamic association relationship between device status and financial indicators, enabling changes in device status to be promptly reflected in financial indicators, which helps enterprises conduct more accurate financial planning and risk management.

[0034] 4. Risk quantification: By calculating the risk conduction probability value, the impact of changes in device status on financial risk is quantified, enabling enterprises to more scientifically evaluate and manage risks.

[0035] 5. Automated monitoring: The entire monitoring process is automated, reducing manual intervention, improving monitoring efficiency and accuracy, and lowering labor costs.

[0036] In summary, through multi-dimensional data fusion analysis, early warning, dynamic association modeling, risk quantification, and automated monitoring, this method significantly improves the comprehensiveness, accuracy, and efficiency of power plant data monitoring, and has important practical application value.

[0037] In summary, through data alignment, federated learning, association analysis, and cross-domain knowledge graph construction, this method solves the problem of data dimension fragmentation in energy enterprises, improves data utilization efficiency, reveals potential relationships between data, and enhances the enterprise's data management ability. It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a schematic flowchart of the steps of a monitoring method based on a data asset management platform provided by an embodiment of this application;

[0040] Figure 2 is a schematic diagram of the interface of a data asset management platform provided by an embodiment of this application;

[0041] Figure 3 is a schematic structural diagram of a monitoring device based on a data asset management platform provided by an embodiment of this application;

[0042] Figure 4 is a schematic block diagram of the structure of a computer device provided by an embodiment of this application.

[0043] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. Detailed implementation manners

[0044] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0045] The flowcharts shown in the accompanying drawings are only illustrative examples, which do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may be changed according to the actual situation.

[0046] It should be understood that, in order to facilitate the clear description of the technical solutions in the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and roles. Those skilled in the art can understand that the terms "first", "second", etc. do not limit the quantity and execution order, and the terms "first", "second", etc. do not necessarily mean different.

[0047] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0048] It should also be understood that the term " / and" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0049] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0050] In the power industry, the equipment operation, production logs, and financial indicators of power plants are important data sources for reflecting the operation status of power plants. Traditional power plant data monitoring methods mainly rely on sensors to monitor equipment operation parameters in real time, combined with manual inspections and simple data analysis tools to evaluate equipment status. However, with the expansion of power plant scale and the increase in equipment complexity, traditional monitoring methods have problems such as single data source, lack of dynamic correlation analysis, and limited risk warning capabilities.

[0051] In recent years, with the rapid development of big data technology, artificial intelligence, and time series analysis technology, more and more research has begun to focus on how to improve the accuracy and comprehensiveness of power plant data monitoring through multi-source data fusion and intelligent analysis methods. However, there are still technical gaps in the fusion analysis of equipment operation data and unstructured production log data, the dynamic correlation modeling of equipment status and financial indicators, and the calculation of risk conduction probability. There is an urgent need for a more intelligent and comprehensive monitoring method to solve the above problems.

[0052] To solve the above problems, please refer to Figure 1 , Figure 1 is a schematic flowchart of a monitoring method based on a data asset management platform provided by an embodiment of the present application. The execution device of the method is a monitoring device applied to a data asset management platform. The device includes a computer device, and also includes an endoscope module and an electromagnetic tracking module. The front end of the endoscope module is used to extend into the nasal cavity of a fresh cadaver head to be measured, and the electromagnetic tracking module is arranged at the front end of the endoscope module for measuring the magnetic field information of the nasal cavity.

[0053] To solve the above problems, please refer to Figure 1 . Specifically, as Figure 1 shown, the provided method includes steps S101 to S104. Among them, the computer device of the provided device can be a handheld terminal, a laptop, a wearable device, or a robot, etc. It is used to implement steps S101 to S105 and their corresponding embodiments.

[0054] Among them, the interface of the data asset platform applied by the method is as Figure 2 shown. This platform can integrate and display data from different power plants, provide data query, analysis, and visualization functions, and help enterprises better manage data assets.

[0055] The steps are detailed as follows:

[0056] S101. Obtain power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data, and financial indicator data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial indicator data includes structured economic parameters.

[0057] Specifically, during the operation of a power plant, equipment operation data, production log data, and financial indicator data are the core data sources reflecting the overall operation status of the power plant. Traditional data monitoring methods usually rely on a single data source (such as sensor data), lacking comprehensive analysis and utilization of multi-source data. The core goal of this step is to obtain multi-source data from the data asset management platform, including equipment operation data, production log data, and financial indicator data, to provide a comprehensive data basis for subsequent intelligent analysis and monitoring.

[0058] Device operation data collection: Through the sensor network deployed on power plant equipment, the operation parameters of the equipment, such as temperature, pressure, vibration, current, voltage, etc., are collected in real time. The sensor data is stored in the form of a time series and uploaded to the data asset management platform through the data collection system. The data collection frequency can be dynamically adjusted according to the importance and operation status of the equipment to ensure the timeliness and accuracy of the data.

[0059] Production log data extraction: Extract unstructured operation and maintenance records from the power plant's production management system, such as equipment maintenance records, operation logs, fault reports, etc. Use natural language processing (NLP) technology to preprocess the unstructured log data, extract key information (such as fault type, maintenance time, operator, etc.), and convert it into structured data. Correlate the processed log data with the device operation data to form a complete device operation and maintenance history record.

[0060] Financial indicator data acquisition: Obtain structured economic parameters from the power plant's financial system, such as production costs, revenues, asset depreciation, maintenance costs, etc. Financial data is usually stored on a monthly or quarterly basis and needs to be time-aligned with the device operation data and production log data for dynamic correlation analysis. Through data cleaning and standardization processing, ensure the accuracy and consistency of the financial data.

[0061] Multi-source data fusion: By integrating device operation data, production log data, and financial indicator data, a comprehensive view of power plant operation data is constructed, providing a rich data foundation for subsequent intelligent analysis and monitoring.

[0062] The above power plant data covers all aspects of power plant operation, including equipment status, operation and maintenance history, and economic benefits, improving the comprehensiveness and reliability of the monitoring system. Through the cleaning and standardization processing of multi-source data, ensure the consistency and availability of the data, providing high-quality data input for subsequent analysis.

[0063] S102. Perform time series feature extraction and reconstruction error analysis on the device operation data and production log data to obtain a progressive deterioration trend.

[0064] Specifically, the operation status of power plant equipment usually has time dependence, and its deterioration process often shows a progressive trend. The core goal of this step is to identify the progressive deterioration trend of the equipment through time series feature extraction and reconstruction error analysis, providing support for the health status assessment and fault warning of the equipment.

[0065] Temporal feature extraction: Use time series analysis methods (such as Fourier transform, wavelet transform, ARIMA model, etc.) to process the device operation data and extract the periodic, trend, and random features from it. For production log data, through time alignment and event sequence analysis, extract the time distribution features of device operation and maintenance events (such as mean time between failures, maintenance frequency, etc.). Associate the extracted temporal features with the operation parameters of the device to form the health status feature vector of the device.

[0066] Reconstruction error analysis: Use deep learning models (such as autoencoders, LSTM networks, etc.) to reconstruct the device operation data and calculate the error between the original data and the reconstructed data. The reconstruction error reflects the degree of abnormality of the device operation state, and the larger the error, the more the device state deviates from the normal range. By analyzing the time variation trend of the reconstruction error, identify the progressive deterioration process of the device.

[0067] Deterioration trend identification: Based on the temporal features and reconstruction error, construct a health status evaluation model for the device to quantify the degree of device deterioration. Use trend prediction algorithms (such as exponential smoothing method, Prophet model, etc.) to predict the deterioration trend of the device and identify potential failure risks. Compare the deterioration trend with the operation and maintenance history of the device to verify the accuracy and reliability of the model.

[0068] By identifying the progressive deterioration trend of the device, achieve early fault warning and reduce the losses caused by sudden failures. Through temporal feature extraction and reconstruction error analysis, deeply mine the potential information in the data and improve the accuracy of the monitoring system. Based on the deterioration trend prediction, provide data support for the device maintenance plan and optimize the operation and maintenance strategy of the power plant.

[0069] S103. Construct a dynamic correlation relationship between the device state and financial indicators according to the device operation data and financial indicator data, and calculate the risk conduction probability value according to the dynamic correlation relationship.

[0070] Specifically, there is a close correlation between the operation state of power plant equipment and its economic benefits. The core goal of this step is to construct a dynamic correlation model between the device state and financial indicators, quantify the impact of device failures on financial indicators, calculate the risk conduction probability, and provide support for the operation decision-making of the power plant.

[0071] Associated model construction: Use regression analysis, machine learning (such as random forest, XGBoost, etc.) or deep learning (such as neural network) methods to establish the dynamic association relationship between equipment status (such as failure rate, operating efficiency) and financial indicators (such as production cost, revenue). Train the model with historical data to verify the accuracy and generalization ability of the model. Align the equipment operation data and financial indicator data in time to ensure the dynamics and real-time nature of the associated model. Based on the associated model, calculate the risk conduction probability of equipment failure on financial indicators. For example, equipment failure may lead to production interruption, which in turn affects the power plant's revenue. Use probability graph models (such as Bayesian networks) or Monte Carlo simulation methods to quantify the uncertainty in the risk conduction process. Combine the risk conduction probability with the deterioration trend of the equipment to evaluate the potential economic losses. Update the association relationship between equipment status and financial indicators in real time to reflect the changes in the power plant's operation status. Display the risk conduction probability and the results of association analysis through visualization tools (such as dashboards, heat maps, etc.) to provide intuitive data support for decision-makers.

[0072] By calculating the risk conduction probability, quantify the impact of equipment failure on financial indicators, and provide data support for the operation decision-making of the power plant. Establish the dynamic association relationship between equipment status and financial indicators, realize real-time risk assessment, and improve the timeliness of the monitoring system. Through visualizing the results of association analysis, help decision-makers quickly identify potential risks and optimize the operation strategy of the power plant.

[0073] S104. Generate monitoring information based on the risk conduction probability value and the equipment deterioration trend. If it is determined that the corresponding power plant data is abnormal according to the monitoring information, generate a warning message to complete the monitoring of each power plant's data.

[0074] Specifically, the core goal of this step is to generate comprehensive monitoring information based on the risk conduction probability value and the equipment deterioration trend, and generate a warning message when an abnormality is detected to achieve comprehensive monitoring of the power plant's data.

[0075] Combine the risk conduction probability value and the equipment deterioration trend to generate comprehensive monitoring information and evaluate the overall operation status of the power plant. Use a weighted scoring method or a machine learning model to quantitatively score the operation status of the power plant and form a monitoring report. Compare the monitoring information with historical data to identify abnormal changes.

[0076] Identify abnormal points in the monitoring information by setting thresholds or using anomaly detection algorithms (such as isolation forest, LOF, etc.). Conduct association analysis on the abnormal points with the operation status and financial indicators of the equipment to determine the cause and scope of the anomaly.

[0077] When an anomaly is detected, warning information is generated and relevant personnel are notified to take countermeasures. The warning information includes the type of anomaly, the affected scope, recommended measures, etc., and is sent to relevant personnel through multiple channels (such as text messages, emails, mobile applications, etc.). The warning information is updated in real time to ensure the timeliness and reliability of the monitoring system. By comprehensively monitoring information, a comprehensive monitoring of the power plant's operation status is achieved, improving the operation efficiency. When an anomaly is detected, warning information is generated in a timely manner to reduce the losses caused by failures and ensure the safe operation of the power plant. Through an automated monitoring and warning mechanism, the cost of manual intervention is reduced and the intelligent management level of the power plant is improved.

[0078] Through the above steps, this method realizes the comprehensive monitoring and intelligent analysis of multi-source data in the power plant, and solves the problems of single data source, lack of dynamic correlation analysis and limited risk warning ability in traditional monitoring methods.

[0079] By integrating equipment operation, production logs and financial data, a comprehensive view of the power plant's operation is provided. Through time series feature extraction and reconstruction error analysis, the progressive deterioration trend of equipment is identified to achieve early warning. By constructing the dynamic correlation relationship between equipment status and financial indicators, the risk conduction probability is quantified and the potential economic losses are evaluated. Based on the risk conduction probability value and the equipment deterioration trend, monitoring information is generated, and warning information is generated when an anomaly is detected, realizing the comprehensive monitoring of power plant data.

[0080] The implementation of steps S101 to S104 not only improves the accuracy and comprehensiveness of power plant data monitoring, but also provides strong support for the intelligent operation and risk management of the power plant, promoting the digital transformation and intelligent upgrading of the power industry.

[0081] In some embodiments, the extracting time series features and reconstruction error analysis of the equipment operation data and production log data to obtain the progressive deterioration trend includes: respectively preprocessing the equipment operation data and production log data; respectively extracting operation time series features and production time series features from the preprocessed equipment operation data and production log data; reconstructing the operation time series features and production time series features to obtain the reconstruction errors corresponding to the operation time series features and production time series features; determining the positions of anomaly points in the equipment operation data and production log data according to the reconstruction errors; obtaining anomaly data in the equipment operation data and production log data according to the positions of the anomaly points; and obtaining the progressive deterioration trend according to the anomaly data.

[0082] Clean and standardize the time series data to remove noise and outliers, ensuring the accuracy and consistency of the data. Perform word segmentation, stop word removal, and word vectorization on the unstructured text data to convert it into structured data for subsequent analysis. Based on the sliding window technique, extract the running time series features such as mean, variance, peak value, etc. from the device operation data according to the preset length and time window. Extract the frequency and semantic change information of the preset keywords to construct the production time series features, reflecting the time distribution of the device operation and maintenance events. Use autoencoders or LSTM networks to reconstruct the running time series features and production time series features, and calculate the error between the original data and the reconstructed data. The reconstruction error reflects the abnormal points in the data, and the larger the error, the more the device state deviates from the normal range. Determine the positions of the abnormal points in the device operation data and production log data according to the reconstruction error, and extract the abnormal data. Based on the abnormal data, analyze the progressive degradation trend of the device and predict potential failures.

[0083] By identifying the progressive degradation trend of the device, early fault warning is realized, and the losses caused by sudden failures are reduced. Through time series feature extraction and reconstruction error analysis, the potential information in the data is deeply mined, and the accuracy of the monitoring system is improved. Based on the degradation trend prediction, data support is provided for the device maintenance plan, and the operation and maintenance strategy of the power plant is optimized.

[0084] Exemplarily, the device operation data is time series data, and the production log data is unstructured data; the preprocessing of the device operation data and production log data respectively includes: performing data cleaning and standardization on the device operation data to remove the noise and outliers of the device operation data; performing text preprocessing on the production log data, and the text preprocessing includes word segmentation, stop word removal, and word vectorization.

[0085] Preprocessing of device operation data: Clean the time series data to remove noise and outliers. Standardize the data to make it conform to the preset numerical range for subsequent analysis.

[0086] Preprocessing of production log data: Perform word segmentation on the unstructured text data to split it into independent lexical units. Remove stop words (such as meaningless words like "de", "shi", etc.) and retain the key information. Use word vectorization techniques (such as Word2Vec, BERT) to convert the text data into numerical vectors for easy processing by machine learning models.

[0087] Through data cleaning and standardization, the accuracy and consistency of the device operation data are ensured. Through word segmentation and word vectorization, the unstructured log data is converted into structured data for subsequent analysis. The standardization and vectorization processing make the data more suitable for machine learning models, improving the training efficiency and accuracy of the models.

[0088] Exemplarily, extracting the operation time series features and production time series features from the preprocessed device operation data and production log data respectively includes: based on the sliding window technique, extracting according to a preset length and a preset time window in the device operation data to obtain the operation time series features; in the production log data, obtaining the keyword frequency and semantic change information corresponding to the preset keywords; constructing the production time series features according to the keyword frequency and semantic change information.

[0089] Based on the sliding window technique, features such as mean, variance, peak value, etc. are extracted from the device operation data according to a preset length and time window. The length and time interval of the sliding window can be dynamically adjusted according to the importance and operation status of the device. In the preprocessed production log data, the frequency and semantic change information of the preset keywords are extracted. According to the keyword frequency and semantic change information, the production time series features are constructed to reflect the time distribution of device operation and maintenance events. Feature diversity: Through the sliding window and keyword extraction, diverse time series features are obtained to comprehensively reflect the operation status of the device. Event correlation: Through the production time series features, the device operation status is correlated with the operation and maintenance events to improve the comprehensive analysis ability of the monitoring system. Dynamic adjustment: The sliding window and keyword extraction can be dynamically adjusted according to actual needs to adapt to the monitoring requirements of different scenarios.

[0090] In some embodiments, constructing the dynamic association relationship between the device state and the financial indicators according to the device operation data and the financial indicator data includes: aligning the device operation data and the financial indicator data in time; extracting the device state features from the device operation data and extracting the financial indicator features from the financial operation data; obtaining the dynamic association relationship corresponding to the device state features and the financial indicator features according to a preset analysis algorithm; the analysis algorithm includes one or more of a multiple regression analysis algorithm, a time series analysis algorithm, a graph model analysis algorithm, and a causal relationship analysis algorithm.

[0091] Align the device operation data and the financial indicator data along the time axis to ensure the time consistency of the data. Extract the device state features from the device operation data, such as the failure rate, operation efficiency, etc. Extract the financial indicator features from the financial indicator data, such as the production cost, revenue, etc. Use algorithms such as multiple regression analysis, time series analysis, graph model analysis, or causal relationship analysis to construct the dynamic association relationship between the device state features and the financial indicator features. Train the model based on historical data to verify the accuracy and generalization ability of the model.

[0092] Through dynamic correlation analysis, quantify the impact of equipment status on financial indicators to provide data support for decision-making. The dynamic correlation model can be updated in real time to reflect the changes in the operation status of the power plant and improve the timeliness of the monitoring system. Through a variety of analysis algorithms, reveal the relationship between equipment status and financial indicators from different dimensions to improve the comprehensiveness of the analysis.

[0093] Among them, the content of each algorithm is as follows:

[0094] Multiple regression analysis: Analyze the linear or non-linear relationship between equipment status characteristics and financial indicators.

[0095] Time series models (such as ARIMA, LSTM): Capture the time series dependence relationship between equipment status and financial indicators.

[0096] Graph models (such as Markov chains): Construct the state transition relationship between equipment status and financial indicators.

[0097] Causality analysis: Use methods such as Granger causality test to analyze whether the change in equipment status has a causal impact on financial indicators.

[0098] One or more algorithms can be used for combined prediction, and this application does not limit this.

[0099] At the same time, for the calculation of the risk conduction probability value: Quantify the dynamic correlation relationship between equipment status and financial indicators into a mathematical expression. For example, when the equipment status changes from "normal" to "deteriorated", calculate its impact probability on financial indicators (such as cost increase, revenue decrease). Train the model through historical data to quantify the probability relationship between changes in equipment status and changes in financial indicators.

[0100] In some embodiments, generating monitoring information according to the risk conduction probability value and the equipment deterioration trend includes: standardizing the risk conduction probability value and the equipment deterioration trend to obtain a risk conduction coefficient and an equipment deterioration coefficient within a preset value range; calculating an anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient, and generating the monitoring information according to the anomaly coefficient.

[0101] Standardize the risk conduction probability value and the equipment deterioration trend so that they conform to the preset value range. Generate monitoring information based on the anomaly coefficient and evaluate the overall operation status of the power plant. When an anomaly is detected, generate a warning message to notify relevant personnel to take countermeasures. Through the anomaly coefficient, comprehensively evaluate the risk conduction and equipment deterioration status of the power plant and provide comprehensive monitoring information. Generate a warning message in a timely manner when an anomaly is detected to reduce the losses caused by faults and ensure the safe operation of the power plant. Dynamically adjust the calculation method of the anomaly coefficient through exponential transformation and weight setting to adapt to the monitoring requirements of different scenarios. Perform exponential transformation on the risk conduction coefficient and the equipment deterioration coefficient to enhance their discrimination.

[0102] Exemplarily, calculating the anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient includes: performing exponential transformation on the risk conduction coefficient and the equipment deterioration coefficient; the exponential transformation intensities of the risk conduction coefficient and the equipment deterioration coefficient are different; calculating the indicated anomaly coefficient according to the risk conduction coefficient and the equipment deterioration coefficient after exponential transformation; the expression of the anomaly coefficient includes:

[0103] where C is the anomaly coefficient, γ is the preset weight, d is the equipment deterioration coefficient, r is the risk conduction coefficient, α and β are the intensity coefficients corresponding to the transformation intensity, and α + β = 1. The formula comprehensively uses various mathematical operations such as exponential functions, weighted combinations, and normalization processing, and can more comprehensively reflect the comprehensive risk of equipment state changes and financial impacts, providing an intelligent warning ability for the data asset management platform.

[0104] At the same time, according to the value range of the anomaly coefficient C C set a warning threshold. For example:

[0105] Low risk: C < 0.3;

[0106] Medium risk: 0.3 ≤ C < 0.7;

[0107] High risk: C ≥ 0.7;

[0108] When C reaches or exceeds the high-risk threshold, generate a warning message to remind relevant personnel to take measures.

[0109] Through exponential transformation, enhance the discrimination of the risk conduction coefficient and the equipment deterioration coefficient, and improve the accuracy of the anomaly coefficient. By adjusting the transformation intensity coefficient and the weight, flexibly control the calculation method of the anomaly coefficient to adapt to the requirements of different scenarios. The anomaly coefficient comprehensively considers the risk conduction and equipment deterioration status and provides comprehensive data support for generating monitoring information.

[0110] Please refer to Figure 3 as shown Figure 3FIG. 0 is a schematic structural diagram of a monitoring device 200 based on a data asset management platform provided by an embodiment of the present application. The monitoring device 200 based on the data asset management platform is used to execute the steps of the monitoring method based on the data asset management platform shown in the above embodiments. The monitoring device 200 based on the data asset management platform may be a single server or a server cluster, or the monitoring device 200 based on the data asset management platform may be a terminal, and the terminal may be a handheld terminal, a laptop computer, a wearable device, or a robot, etc.

[0111] As Figure 3 shown, the monitoring device 200 based on the data asset management platform includes:

[0112] A data acquisition module 201, configured to acquire power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data, and financial index data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial index data includes structured economic parameters;

[0113] An error analysis module 202, configured to perform time series feature extraction and reconstruction error analysis on the equipment operation data and production log data to obtain a progressive degradation trend;

[0114] A conduction calculation module 203, configured to construct a dynamic association relationship between the equipment state and the financial index according to the equipment operation data and the financial index data, and calculate a risk conduction probability value according to the dynamic association relationship;

[0115] A monitoring completion module 204, configured to generate monitoring information according to the risk conduction probability value and the equipment degradation trend, and generate a warning information if it is determined according to the monitoring information that the corresponding power plant data is abnormal, and complete the monitoring of each piece of the power plant data.

[0116] It should be noted that those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described monitoring device based on the data asset management platform and each unit can refer to the corresponding processes in the monitoring embodiments based on the data asset management platform described in the above embodiments, and will not be elaborated herein.

[0117] The above-mentioned monitoring based on the data asset management platform can be implemented in the form of a computer program, and the computer program can run on a device as Figure 3 shown.

[0118] Please refer to Figure 4 , Figure 4It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory may include a storage medium and an internal memory.

[0119] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can be made to execute any kind of monitoring based on the data asset management platform.

[0120] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0121] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can be made to execute any kind of monitoring based on the data asset management platform.

[0122] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0123] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] Among them, in one embodiment, the processor is used to run the computer program stored in the memory to implement the following steps:

[0125] Obtain power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data, and financial indicator data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial indicator data includes structured economic parameters;

[0126] Extract the time series features and reconstruction error analysis of the device operation data and production log data to obtain the progressive degradation trend;

[0127] Construct the dynamic correlation between the device status and financial indicators based on the device operation data and financial indicator data, and calculate the risk conduction probability value according to the dynamic correlation;

[0128] Generate monitoring information based on the risk conduction probability value and the device degradation trend. If it is determined that the corresponding power plant data is abnormal according to the monitoring information, generate a warning message to complete the monitoring of each power plant data.

[0129] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described processor can refer to the corresponding process in the monitoring embodiments based on the data asset management platform described in the above embodiments, and will not be elaborated here.

[0130] An embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. The processor executes the program instructions to implement the steps of the monitoring method based on the data asset management platform provided in the above embodiments of the present application.

[0131] Among them, the computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device.

[0132] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present application, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A monitoring method for a data asset management platform, characterized in that, The method includes: Obtaining power plant data of multiple power plants from the data asset management platform; the power plant data includes equipment operation data, production log data, and financial indicator data; the equipment operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial indicator data includes structured economic parameters; Performing time series feature extraction and reconstruction error analysis on the equipment operation data and production log data to obtain a progressive deterioration trend; Constructing a dynamic correlation relationship between the equipment state and financial indicators based on the equipment operation data and financial indicator data, and calculating a risk conduction probability value according to the dynamic correlation relationship; Generating monitoring information based on the risk conduction probability value and the equipment deterioration trend, and generating a warning message if it is determined according to the monitoring information that the corresponding power plant data is abnormal, thereby completing the monitoring of each piece of power plant data.

2. The method according to claim 1, characterized in that, The performing time series feature extraction and reconstruction error analysis on the equipment operation data and production log data to obtain a progressive deterioration trend includes: Performing preprocessing on the equipment operation data and production log data respectively; Extracting operation time series features and production time series features from the preprocessed equipment operation data and production log data respectively; Reconstructing the operation time series features and production time series features to obtain the reconstruction errors corresponding to the operation time series features and production time series features; Determining the positions of abnormal points in the equipment operation data and production log data according to the reconstruction errors; Obtaining abnormal data from the equipment operation data and production log data according to the positions of the abnormal points; Obtaining the progressive deterioration trend according to the abnormal data.

3. The method according to claim 2, wherein The equipment operation data is time series data, and the production log data is unstructured data; the performing preprocessing on the equipment operation data and production log data respectively includes: Performing data cleaning and standardization on the equipment operation data to remove the noise and outliers in the equipment operation data; Performing text preprocessing on the production log data, and the text preprocessing includes word segmentation, stop word removal, and word vectorization.

4. The method according to claim 2, characterized in that The extracting operation time series features and production time series features from the preprocessed equipment operation data and production log data respectively includes: Based on the sliding window technique, extracting in the equipment operation data according to a preset length and a preset time window to obtain the operation time series features; In the production log data, obtaining the keyword frequency and semantic change information corresponding to a preset keyword; Constructing the production time series features according to the keyword frequency and semantic change information.

5. The method according to claim 1, wherein The constructing a dynamic correlation relationship between the equipment state and financial indicators based on the equipment operation data and financial indicator data includes: Performing time alignment on the equipment operation data and financial indicator data; Extracting equipment state features from the equipment operation data and extracting financial indicator features from the financial operation data; Obtain the dynamic correlation relationship corresponding to the device status feature and the financial index feature according to a preset analysis algorithm; the analysis algorithm includes one or more of a multiple regression analysis algorithm, a time series analysis algorithm, a graph model analysis algorithm, and a causal relationship analysis algorithm.

6. The method according to claim 1, characterized in that Generating the monitoring information according to the risk conduction probability value and the device deterioration trend includes: Standardize the risk conduction probability value and the device deterioration trend to obtain a risk conduction coefficient and a device deterioration coefficient within a preset value range; Calculate an anomaly coefficient according to the risk conduction coefficient and the device deterioration coefficient, and generate the monitoring information according to the anomaly coefficient.

7. The method according to claim 6, characterized in that, Calculating the anomaly coefficient according to the risk conduction coefficient and the device deterioration coefficient includes: Perform exponential transformation on the risk conduction coefficient and the device deterioration coefficient; the exponential transformation intensities of the risk conduction coefficient and the device deterioration coefficient are different; Calculate the anomaly coefficient according to the risk conduction coefficient and the device deterioration coefficient after exponential transformation; the expression of the anomaly coefficient includes: Where C is the anomaly coefficient, γ is a preset weight, d is the device deterioration coefficient, r is the risk conduction coefficient, and α and β are the intensity coefficients corresponding to the transformation intensity.

8. A monitoring device based on a data asset management platform, characterized in that, The device includes: A data acquisition module for acquiring power plant data of multiple power plants from the data asset management platform; the power plant data includes device operation data, production log data, and financial index data; the device operation data includes sensor real-time monitoring parameters, the production log data includes unstructured operation and maintenance records, and the financial index data includes structured economic parameters; An error analysis module for performing time series feature extraction and reconstruction error analysis on the device operation data and the production log data to obtain a progressive deterioration trend; A conduction calculation module for constructing a dynamic correlation relationship between the device status and the financial index according to the device operation data and the financial index data, and calculating a risk conduction probability value according to the dynamic correlation relationship; A monitoring completion module for generating monitoring information according to the risk conduction probability value and the device deterioration trend, and generating a warning information if it is determined according to the monitoring information that the corresponding power plant data is abnormal, and completing the monitoring of each piece of the power plant data.

9. A computer device, characterized in that, It includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer-readable instructions are executed by the processor, one or more processors are caused to execute the steps of the method according to any one of claims 1 to 7.

Images