Verification method and system for multi-dimensional transformation effect of coal power system

Abstract

The invention relates to the technical field of effect verification, in particular to a verification method and system for the multi-dimensional transformation effect of a coal power system, and the method comprises the steps: defining a verification target of the multi-dimensional transformation of the coal power system, and setting a verification index according to the verification target; constructing a sensor network to monitor the coal power system, and collecting operation performance data of the coal power system; performing multi-dimensional comprehensive evaluation on the coal power system through the operation performance data to obtain a multi-dimensional evaluation result; establishing a stability prediction model of the coal power system, and inputting the operation performance data into the stability prediction model to obtain a stability prediction result; and carrying out collaborative analysis on the multi-dimensional verification result and the stability prediction result to generate a transformation effect verification result of the coal power system. Through the method, the problem that a scientific and systematic verification means is lacked after the coal power system is transformed is effectively solved, comprehensive description of the transformation effect is achieved, and unified verification of short-term performance improvement and long-term operation trend of the system is achieved.

Description

Technical Field

[0001] This invention relates to the field of effect verification technology, and in particular to a method and system for verifying the effects of multi-dimensional transformation of coal-fired power systems. Background Technology

[0002] As a crucial component of my country's power supply system, coal-fired power systems bear the fundamental load of large-scale, continuous power supply. With the development of smart grids, higher demands are being placed on the cleanliness, efficiency, and intelligence of coal-fired power unit operation. To achieve green transformation, many coal-fired power companies are improving unit performance through system upgrades, including control strategy optimization, equipment structure upgrades, combustion efficiency improvement, and pollutant emission reduction. On the other hand, the operation of coal-fired power systems involves numerous complex variables. Their stability is affected by the coupling of multiple factors such as changes in operating conditions, equipment status, and external disturbances, exhibiting strong nonlinearity and high time-varying characteristics. Traditional evaluation methods based on rule thresholds or static models are no longer effective in addressing the operating characteristics of modern coal-fired power systems.

[0003] Currently, the evaluation of these transformation measures lacks scientific and systematic verification methods, making it difficult to accurately quantify the transformation effects and providing insufficient basis for decision-making. Furthermore, while coal-fired power systems generate a large amount of performance data during operation, there is a lack of structured integration and intelligent analysis mechanisms, which fails to effectively support the verification of transformation effects. Therefore, at present, there is still a lack of dedicated methods and system frameworks for systematically verifying the "multi-dimensional transformation effects" of coal-fired power systems. Summary of the Invention

[0004] This invention provides a method and system for verifying the multi-dimensional transformation effect of coal-fired power systems, which can effectively solve the problems in the background art.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for verifying the effects of multi-dimensional retrofitting of a coal-fired power system, the method comprising:

[0007] Define verification objectives for the multi-dimensional transformation of coal-fired power systems, and set verification indicators based on the verification objectives;

[0008] A sensor network is constructed to monitor the coal-fired power system and collect its operational performance data.

[0009] Based on the verification indicators, the coal-fired power system is comprehensively evaluated from multiple dimensions using the operational performance data to obtain multi-dimensional evaluation results.

[0010] A stability prediction model for the coal-fired power system is established, and the operating performance data is input into the stability prediction model to obtain the stability prediction results.

[0011] The multi-dimensional verification results and the stability prediction results are analyzed collaboratively to generate the verification results of the transformation effect of the coal-fired power system.

[0012] Furthermore, the construction of the sensor network to monitor the coal-fired power system and collect its operational performance data includes:

[0013] Design the sensor network as a hybrid architecture and select sensor types for the sensor network;

[0014] The sensor network collects the operating performance data of the coal-fired power system, and the collected operating performance data is transmitted to the central control system by selecting the data transmission method and data communication protocol.

[0015] Furthermore, it also includes configuring several edge computing nodes in the coal-fired power system to perform preliminary processing of the operational performance data.

[0016] Furthermore, the multi-dimensional comprehensive evaluation of the coal-fired power system based on the operational performance data, yielding multi-dimensional evaluation results, includes:

[0017] The operational performance data is preprocessed to calculate the verification metrics for each dimension;

[0018] Set benchmark indicators, and compare and analyze the data of each dimension based on the benchmark indicators and the verification indicators to obtain the comparison and analysis results;

[0019] Weights are assigned to each dimension, the validation metrics for each dimension are scored, and a weighted composite score for each dimension is calculated.

[0020] Furthermore, it also includes: collecting historical operating performance data with a period consistent with the modified operating performance data to generate the benchmark index.

[0021] Furthermore, establishing a stability prediction model for the coal-fired power system includes:

[0022] Construct a historical dataset and divide it into a training set, a validation set, and a test set;

[0023] A deep neural network is selected to construct a stability prediction model. The structure of the deep neural network is designed, and the training parameters are configured.

[0024] Based on the training parameters, the stability prediction model is trained using the training set, and the stability prediction model is tuned using the validation set.

[0025] The performance of the stability prediction model is evaluated using the test set, and the optimized stability prediction model is deployed to the central control system.

[0026] Furthermore, the stability prediction model includes:

[0027] The input layer is used to receive multi-source time series data;

[0028] The temporal modeling layer is designed with a parallel modeling structure, including LSTM channels and CNN channels.

[0029] The attention mechanism layer employs a cross-attention mechanism to fuse feature representations from different channels, thereby obtaining the interaction relationships between multiple variables.

[0030] The feature fusion layer, composed of fully connected layers, abstracts and processes the fused features using fully connected layers.

[0031] The output layer generates results including stability scores, state classifications, and trend predictions.

[0032] A verification system for the multi-dimensional transformation effect of a coal-fired power system, the system comprising:

[0033] The indicator setting module defines the verification objectives for the multi-dimensional transformation of the coal-fired power system and sets the verification indicators based on the verification objectives.

[0034] The data collection module constructs a sensor network to monitor the coal-fired power system and collects the operating performance data of the coal-fired power system.

[0035] The multi-dimensional evaluation module, based on the verification indicators, performs a multi-dimensional comprehensive evaluation of the coal-fired power system using the operational performance data to obtain multi-dimensional evaluation results.

[0036] The stability prediction module establishes a stability prediction model for the coal-fired power system, inputs the operating performance data into the stability prediction model, and obtains the stability prediction results.

[0037] The collaborative analysis module performs collaborative analysis on the multi-dimensional verification results and the stability prediction results to generate verification results of the transformation effect of the coal-fired power system.

[0038] Furthermore, the data collection module includes:

[0039] The network design unit designs the sensor network as a hybrid architecture and selects the sensor type for the sensor network.

[0040] The data transmission unit collects the operating performance data of the coal-fired power system through the sensor network, and selects the data transmission method and data communication protocol to transmit the collected operating performance data to the central control system.

[0041] Furthermore, the multi-dimensional evaluation module includes:

[0042] The indicator calculation unit preprocesses the operational performance data and calculates the verification indicators for each dimension.

[0043] The comparative analysis unit sets benchmark indicators and performs comparative analysis on the data of each dimension based on the benchmark indicators and the verification indicators to obtain comparative analysis results.

[0044] The weighted scoring unit assigns weights to each dimension, scores the validation metrics for each dimension, and calculates the weighted comprehensive score for each dimension.

[0045] The technical solution of this invention can achieve the following technical effects:

[0046] It effectively solves the problem of lacking scientific and systematic verification methods after the transformation of coal-fired power systems. By defining multi-dimensional verification indicators, it achieves a comprehensive characterization of the transformation effect. It integrates multi-dimensional comprehensive evaluation based on operational data with a deep learning-driven stability prediction model to achieve unified verification of the system's short-term performance improvement and long-term operational trend. Moreover, relying on sensor networks, it enables real-time monitoring and intelligent processing of the coal-fired power system's operating status.

[0047] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a method for verifying the effects of multi-dimensional retrofitting of a coal-fired power system;

[0050] Figure 2 A flowchart illustrating the process of obtaining multi-dimensional evaluation results;

[0051] Figure 3 This is a schematic diagram of the stability prediction model.

[0052] Figure 4 This is a schematic diagram of the structure of a verification system for the multi-dimensional transformation effect of a coal-fired power system. Detailed Implementation

[0053] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0055] Example 1

[0056] like Figure 1 As shown, a method for verifying the multi-dimensional transformation effect of a coal-fired power system is provided, the method comprising:

[0057] S1: Define the verification objectives for the multi-dimensional transformation of the coal-fired power system, and set verification indicators based on the verification objectives;

[0058] Specifically, to translate the goals of coal-fired power system retrofitting into actionable and measurable verification indicators, this step defines the core objectives of the retrofitting process. These can include specific objectives across different dimensions, such as improving thermal efficiency, reducing pollution emissions, and lowering operating costs. Having clarified the verification objectives of the coal-fired power system retrofitting, this step sets various key verification indicators based on these objectives. These include energy efficiency-related indicators, such as thermal efficiency and unit electricity cost, and emission control-related indicators, such as SO2 and NO. x By using target-driven verification indicators to measure emission levels of CO2, particulate matter, etc., the verification process can be ensured to have a clear direction and to assess the specific improvements made to the system.

[0059] S2: Construct a sensor network to monitor the coal-fired power system and collect operational performance data of the coal-fired power system;

[0060] In this embodiment, in order to collect real-time operating performance data of the coal-fired power system and provide high-frequency data support to ensure accurate monitoring of various parameters of the coal-fired power system, this step involves installing sensors on key equipment of the coal-fired power system to build a sensor network for real-time monitoring of important parameters such as operating data, emission data, and economic data of the equipment. For example, operating data includes operating parameters of various equipment in the coal-fired power system, such as temperature, pressure, flow rate, power output, and load fluctuations. To facilitate unified management and analysis, the collected data can be aggregated into a data platform.

[0061] S3: Based on the verification indicators, the coal-fired power system is comprehensively evaluated from multiple dimensions using operational performance data to obtain multi-dimensional evaluation results;

[0062] Based on the above embodiments, in order to evaluate the modified coal-fired power system from multiple dimensions and provide data support for subsequent decision-making, this step comprehensively evaluates the modification effect of the coal-fired power system by collecting operational performance data and combining it with preset verification indicators. Multi-dimensional evaluation is to comprehensively evaluate the performance of multiple different aspects, so each indicator can be quantified and compared to show the performance of the coal-fired power system in various aspects and fully reflect the modification effect.

[0063] S4: Establish a stability prediction model for the coal-fired power system, input the operating performance data into the stability prediction model, and obtain the stability prediction results;

[0064] Specifically, to assess the long-term stability and reliability of the coal-fired power system after the retrofit, this step establishes a stability prediction model, such as a machine learning model, time series analysis, or regression model, and uses operational performance data to predict the long-term stability of the coal-fired power system, identify potential equipment failures, operational instability, and economic degradation, assess the long-term reliability of the system, and ensure the stable operation of the coal-fired power system in the future.

[0065] S5: Perform collaborative analysis of multi-dimensional verification results and stability prediction results to generate verification results of the transformation effect of coal-fired power systems.

[0066] This step involves a collaborative analysis of multi-dimensional verification results and stability prediction results. This comprehensive assessment of the short-term and long-term performance of the coal-fired power system provides decision-makers with all-round feedback. Multi-dimensional evaluation focuses on the system's immediate performance, while stability prediction helps assess long-term stability. Combining the two provides a more comprehensive verification of the effects. It is important to note that the multi-dimensional evaluation results and stability prediction results come from different analytical methods and data sources. To facilitate collaborative analysis, these two types of data can be standardized and normalized to ensure that different types of indicators have the same dimensions and comparability. The final collaborative analysis results will generate a detailed report, which includes the overall transformation effect of the coal-fired power system, the evaluation results of each dimension, and a comprehensive assessment of long-term stability prediction. The report should clearly demonstrate the advantages and room for improvement of the coal-fired power system after the transformation.

[0067] This invention effectively solves the problem of lacking scientific and systematic verification methods after the transformation of coal-fired power systems. By defining multi-dimensional verification indicators, it achieves a comprehensive characterization of the transformation effect. It integrates multi-dimensional comprehensive evaluation based on operational data with a deep learning-driven stability prediction model to achieve unified verification of the system's short-term performance improvement and long-term operational trend. Moreover, relying on sensor networks, it enables real-time monitoring and intelligent processing of the coal-fired power system's operating status.

[0068] Based on the above embodiments, a sensor network is constructed to monitor the coal-fired power system and collect operational performance data of the coal-fired power system, including:

[0069] S21: Design the sensor network as a hybrid architecture and select the sensor type for the sensor network;

[0070] Specifically, building a sensor network first requires identifying the devices and parameters that need to be monitored. Different sensors have different measurement ranges, accuracies, and response times. Appropriate sensor types, such as temperature sensors, pressure sensors, and vibration sensors, can be selected based on the devices and parameters to be monitored. To cope with large-scale, complex industrial environments, this step chooses a hybrid architecture as the sensor network architecture. The hybrid architecture combines the advantages of centralized and distributed architectures. Some key parameters are controlled centrally, while some data can be processed through distributed nodes. This can optimize the performance of the coal-fired power system at various levels, while reducing latency, improving data transmission efficiency, and increasing system fault tolerance.

[0071] S22: Collect operating performance data of the coal-fired power system through a sensor network, and select the data transmission method and data communication protocol to transmit the collected operating performance data to the central control system.

[0072] Coal-fired power systems are large-scale with widely distributed equipment. Combining wireless and wired transmission methods ensures data coverage across the entire system and maintains high efficiency. Wireless transmission technologies, such as Wi-Fi, LoRa, ZigBee, and 5G, are suitable for large-scale monitoring of coal-fired power systems, reducing cabling work. Wired transmission technologies, such as Ethernet and industrial buses, are suitable for monitoring applications requiring high transmission speed and stability. Data collected from the operational performance system is transmitted to the central control system. Data from the sensor network needs to be transmitted via communication protocols, ensuring data security and timeliness. Communication protocols such as OPC-UA and Ethernet / IP can be selected to ensure efficient, reliable, and real-time operation of the system.

[0073] Furthermore, it also includes configuring several edge computing nodes in the coal-fired power system to perform preliminary processing of operational performance data.

[0074] As a preferred embodiment, to improve data processing efficiency and reduce the load on the central server, edge nodes can be deployed in various key areas of the coal-fired power system to process data from various devices. Edge nodes process data near the sensors, performing data cleaning, filtering, aggregation, and preliminary analysis. Furthermore, edge nodes can reduce unnecessary data transmission, transmitting only necessary information or pre-processed data, thus reducing bandwidth burden and latency. Data is first collected from sensors and transmitted to edge nodes for preliminary processing and local decision-making, before being transmitted to the central control system for more in-depth analysis and long-term storage. The edge nodes transmitting the pre-processed data to the central control system ensures that the data received by the central system has undergone certain filtering and processing, avoiding the transmission of large amounts of unnecessary data and reducing the burden on the central system.

[0075] As a preferred embodiment of this example, Figure 2 As shown, a multi-dimensional comprehensive evaluation of the coal-fired power system was conducted using operational performance data, yielding the following multi-dimensional evaluation results:

[0076] S31: Preprocess the runtime performance data and calculate the validation metrics for each dimension;

[0077] To ensure data accuracy and comparability, this embodiment preprocesses the collected data, performing data cleaning to remove invalid, missing, or abnormal data, thus ensuring data quality. To eliminate dimensional differences between different indicators, various data types are standardized, and different performance indicators are normalized to the same range, making them comparable. Based on the verification indicators set in the previous steps, this step calculates and evaluates each set indicator, such as calculating the thermal efficiency of the coal-fired power system, unit electricity cost, monitoring emission data, and assessing equipment failure rates.

[0078] S32: Set benchmark indicators, and compare and analyze the data of each dimension based on the benchmark indicators and validation indicators to obtain the comparative analysis results;

[0079] S33: Assign weights to each dimension, score the validation metrics for each dimension, and calculate the weighted composite score for each dimension.

[0080] Building upon the above embodiments, to intuitively reflect the effects of the multi-dimensional transformation of the coal-fired power system, this step sets benchmark indicators. These benchmark indicators are historical indicators and industry standards prior to the multi-dimensional transformation of the coal-fired power system. The calculated verification indicators are data after the multi-dimensional transformation of the coal-fired power system. By comparing the indicators before and after the transformation, the performance improvement of the transformed coal-fired power system compared to before the transformation is verified, and whether the expected effect has been achieved. Simultaneously, the data of the transformed coal-fired power system is compared with industry standards or best practices to verify whether the transformed system has reached an industry-leading level. To further verify the effects of the multi-dimensional transformation, the indicators of each dimension are weighted according to their importance and a comprehensive score is calculated. For example, thermal efficiency and emission control are likely the most important indicators, so they have larger weights. A weighted average method or other methods are used for comprehensive evaluation to obtain a final comprehensive score. This quantifies the performance of each dimension and reflects the overall transformation effect of the coal-fired power system, enabling a systematic and comprehensive assessment of the transformation effect.

[0081] Furthermore, it also includes: generating benchmark indicators from historical operating performance data that are collected periodically in line with the operating performance data after the modification.

[0082] In this preferred embodiment, the benchmark index refers to the performance indicators of the coal-fired power system before the retrofit. This serves as a reference standard for comparison with the verification indicators after the retrofit. To ensure the fairness and effectiveness of the comparative analysis, historical operating performance data and operational performance data can be selected for the same time period and cycle length to ensure data period alignment. Meanwhile, the operating status, load conditions, and seasonal variations of the coal-fired power system may affect the data. Therefore, when selecting historical operating performance data, it should be ensured that the operating status and load patterns of the historical operating performance data match the operating conditions of the post-retrofit operating performance data as closely as possible, ensuring consistent operating conditions and controllable external factors. The benchmark index calculated using historical operating performance data with consistent cycles can more accurately assess the effects of the coal-fired power system before and after the retrofit, providing a scientific basis for subsequent decision-making.

[0083] Based on the above embodiments, establishing a stability prediction model for coal-fired power systems includes:

[0084] S41: Construct a historical dataset, dividing it into a training set, a validation set, and a test set;

[0085] Specifically, the constructed historical dataset includes historical operating performance data and stability output labels of the coal-fired power system, including multi-dimensional features such as load factor, main steam temperature, equipment vibration, current, and emission indicators, organized in a time series structure to reflect the evolution of the system's operating status.

[0086] S42: Select a deep neural network to build a stability prediction model, design the structure of the deep neural network, and configure the training parameters;

[0087] Choose a deep neural network structure suitable for modeling time series data of coal-fired power systems, such as long short-term memory networks, one-dimensional convolutional neural networks, or attention mechanism networks. The neural network structure can be designed in combination with the characteristics of coal-fired power systems, including an input layer, a time coding layer, a feature fusion layer, and an output layer. In order to train the model in the future, this step configures relevant training parameters, such as learning rate, loss function, batch size, regularization strategy, etc.

[0088] S43: Based on the training parameters, train the stability prediction model using the training set, and fine-tune the stability prediction model using the validation set;

[0089] S44: Use the test set to evaluate the performance of the stability prediction model and deploy the optimized stability prediction model to the central control system.

[0090] Based on the set training parameters, the model is trained on the training set to fit the model parameters, enabling it to learn the temporal patterns and feature dependencies in the data. Hyperparameter tuning and early stopping detection are then performed on the validation set to improve the model's generalization ability and select the optimal model structure and parameter combination. After training, the model performance is evaluated using the test set, with evaluation metrics including mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²). 2 The accuracy and stability of the model are verified using methods such as F1-score. Finally, the optimized stability prediction model is deployed to the central control platform of the coal-fired power system, enabling input and prediction of real-time operating data. The model can be used to determine the operational stability trend or failure risk of the coal-fired power system over a certain period, providing quantitative analysis of the long-term stability of the retrofit effect and supporting a comprehensive evaluation of multi-dimensional verification results.

[0091] Furthermore, such as Figure 3 As shown, the stability prediction model includes:

[0092] The input layer is used to receive multi-source time series data;

[0093] The temporal modeling layer is designed with a parallel modeling structure, including LSTM channels and CNN channels. The LSTM channels are two-layer structures and are constructed using bidirectional LSTM units. The CNN channels contain one-dimensional convolutional layers and max pooling layers, and support multi-scale convolutional kernels for feature extraction.

[0094] Specifically, this model combines time-series modeling capabilities, local feature extraction capabilities, and the ability to model interactions between variables. It can comprehensively capture the dynamic behavior and potential abnormal trends in multi-source operating data of coal-fired power systems, thereby outputting system stability scores and future trend judgments. The input data is simultaneously fed into two parallel modeling channels: one is a time-series channel based on a two-layer long short-term memory network (LSTM), used to model the long-term dependencies and hysteresis response characteristics in the system operating data; the other is a local channel based on a one-dimensional convolutional neural network (1D-CNN), used to identify short-term fluctuations, high-frequency disturbances, and abnormal peaks in the operating data.

[0095] The attention mechanism layer uses a cross-attention mechanism to fuse feature representations from different channels to obtain the interaction relationships between multiple variables; the cross-attention mechanism is implemented using self-attention or a Transformer structure.

[0096] The outputs from the two channels are then fed into a multidimensional cross-attention module. This module dynamically adjusts the feature weights between different variables and between channels based on an attention mechanism, thereby uncovering the deep coupling relationships between various operating variables in the coal-fired power system.

[0097] The feature fusion layer, composed of fully connected layers, abstracts and processes the fused features using fully connected layers.

[0098] The feature vectors after attention fusion are input into the feature fusion layer. After a series of fully connected layers and non-linear activation functions, the feature representation capability is further improved and the information dimension is compressed.

[0099] The output layer generates results including stability scores, state classifications, and trend predictions.

[0100] Example 2

[0101] Based on the same inventive concept as the method described in the foregoing embodiments, this invention also provides a verification system for the multi-dimensional transformation effect of a coal-fired power system, such as... Figure 4 As shown, the system includes:

[0102] The indicator setting module defines the verification objectives for the multi-dimensional transformation of the coal-fired power system and sets the verification indicators based on the verification objectives.

[0103] The data collection module constructs a sensor network to monitor the coal-fired power system and collects operational performance data of the coal-fired power system;

[0104] The multi-dimensional evaluation module, based on verification indicators, performs a comprehensive multi-dimensional evaluation of the coal-fired power system using operational performance data to obtain multi-dimensional evaluation results.

[0105] The stability prediction module establishes a stability prediction model for the coal-fired power system. The operating performance data is input into the stability prediction model to obtain the stability prediction results.

[0106] The collaborative analysis module performs collaborative analysis on multi-dimensional verification results and stability prediction results to generate verification results of the transformation effect of the coal-fired power system.

[0107] The adjustment system described above in this invention can effectively realize the verification method of multi-dimensional transformation effect of coal-fired power system. The technical effects it can achieve are as described in the above embodiments, and will not be repeated here.

[0108] Furthermore, the data collection module includes:

[0109] The network design unit designs the sensor network as a hybrid architecture and selects the sensor type for the sensor network;

[0110] The data transmission unit collects operational performance data of the coal-fired power system through a sensor network, and selects the data transmission method and data communication protocol to transmit the collected operational performance data to the central control system.

[0111] Furthermore, the multi-dimensional evaluation module includes:

[0112] The indicator calculation unit preprocesses the operational performance data and calculates the verification indicators for each dimension.

[0113] The comparative analysis unit sets benchmark indicators and compares and analyzes the data of each dimension based on the benchmark indicators and validation indicators to obtain comparative analysis results.

[0114] The weighted scoring unit assigns weights to each dimension, scores the validation metrics for each dimension, and calculates the weighted comprehensive score for each dimension.

[0115] Similarly, the above-mentioned optimization schemes for the system can also achieve the optimization effects corresponding to the methods in Embodiment 1, which will not be repeated here.

[0116] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and accompanying drawings are merely exemplary illustrations of the application as defined herein, and are to be considered as covering any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for verifying the multi-dimensional transformation effect of a coal-fired power system, characterized in that, The method includes: Define verification objectives for the multi-dimensional transformation of coal-fired power systems, and set verification indicators based on the verification objectives; A sensor network is constructed to monitor the coal-fired power system and collect its operational performance data. Based on the verification indicators, the coal-fired power system is comprehensively evaluated from multiple dimensions using the operational performance data to obtain multi-dimensional evaluation results. A stability prediction model for the coal-fired power system is established, and the operating performance data is input into the stability prediction model to obtain the stability prediction results. The multi-dimensional verification results and the stability prediction results are analyzed collaboratively to generate the verification results of the transformation effect of the coal-fired power system.

2. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 1, characterized in that, The construction of a sensor network to monitor the coal-fired power system and collect operational performance data of the coal-fired power system includes: Design the sensor network as a hybrid architecture and select sensor types for the sensor network; The sensor network collects the operating performance data of the coal-fired power system, and the collected operating performance data is transmitted to the central control system by selecting the data transmission method and data communication protocol.

3. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 2, characterized in that, Also includes: Several edge computing nodes are configured in the coal-fired power system to perform preliminary processing on the operational performance data.

4. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 1, characterized in that, The multi-dimensional comprehensive evaluation of the coal-fired power system based on the operational performance data yields the following multi-dimensional evaluation results: The operational performance data is preprocessed to calculate the verification metrics for each dimension; Set benchmark indicators, and compare and analyze the data of each dimension based on the benchmark indicators and the verification indicators to obtain the comparison and analysis results; Weights are assigned to each dimension, the validation metrics for each dimension are scored, and a weighted composite score for each dimension is calculated.

5. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 4, characterized in that, Also includes: The benchmark index is generated by collecting and modifying historical operating performance data that are consistent with the operating performance data period.

6. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 1, characterized in that, The stability prediction model for the coal-fired power system includes: Construct a historical dataset and divide it into a training set, a validation set, and a test set; A deep neural network is selected to construct a stability prediction model. The structure of the deep neural network is designed, and the training parameters are configured. Based on the training parameters, the stability prediction model is trained using the training set, and the stability prediction model is tuned using the validation set. The performance of the stability prediction model is evaluated using the test set, and the optimized stability prediction model is deployed to the central control system.

7. The method for verifying the multi-dimensional transformation effect of a coal-fired power system according to claim 6, characterized in that, The stability prediction model includes: The input layer is used to receive multi-source time series data; The temporal modeling layer is designed with a parallel modeling structure, including LSTM channels and CNN channels. The attention mechanism layer employs a cross-attention mechanism to fuse feature representations from different channels, thereby obtaining the interaction relationships between multiple variables. The feature fusion layer, composed of fully connected layers, abstracts and processes the fused features using fully connected layers. The output layer generates results including stability scores, state classifications, and trend predictions.

8. A verification system for the multi-dimensional transformation effect of a coal-fired power system, characterized in that, The system includes: The indicator setting module defines the verification objectives for the multi-dimensional transformation of the coal-fired power system and sets the verification indicators based on the verification objectives. The data collection module constructs a sensor network to monitor the coal-fired power system and collects the operating performance data of the coal-fired power system. The multi-dimensional evaluation module, based on the verification indicators, performs a multi-dimensional comprehensive evaluation of the coal-fired power system using the operational performance data to obtain multi-dimensional evaluation results. The stability prediction module establishes a stability prediction model for the coal-fired power system, inputs the operating performance data into the stability prediction model, and obtains the stability prediction results. The collaborative analysis module performs collaborative analysis on the multi-dimensional verification results and the stability prediction results to generate verification results of the transformation effect of the coal-fired power system.

9. The verification system for the multi-dimensional transformation effect of a coal-fired power system according to claim 8, characterized in that, The data collection module includes: The network design unit designs the sensor network as a hybrid architecture and selects the sensor type for the sensor network. The data transmission unit collects the operating performance data of the coal-fired power system through the sensor network, and selects the data transmission method and data communication protocol to transmit the collected operating performance data to the central control system.

10. A verification system for the multi-dimensional transformation effect of a coal-fired power system according to claim 8, characterized in that, The multi-dimensional evaluation module includes: The indicator calculation unit preprocesses the operational performance data and calculates the verification indicators for each dimension. The comparative analysis unit sets benchmark indicators and performs comparative analysis on the data of each dimension based on the benchmark indicators and the verification indicators to obtain comparative analysis results. The weighted scoring unit assigns weights to each dimension, scores the validation metrics for each dimension, and calculates the weighted comprehensive score for each dimension.

Images