Primary frequency modulation performance evaluation method and system based on multi-source data fusion

Abstract

The present invention discloses a primary frequency regulation performance evaluation method and system based on multi-source data fusion, which relates to the relevant fields of industrial automation. The method comprises: connecting the monitoring system of a thermal power unit, acquiring DCS and DEH source data from the monitoring system; performing data fusion to obtain multi-source fusion data; performing edge computing to obtain multiple primary frequency regulation performance indicators; constructing multiple primary frequency regulation performance evaluation sub-models; adaptively weighting and integrating multiple primary frequency regulation performance evaluation sub-models to obtain a primary frequency regulation performance evaluation model; performing a primary frequency regulation response capability evaluation on multiple primary frequency regulation performance indicators, and outputting a primary frequency regulation performance evaluation result. The method solves the technical problem of insufficient accuracy of the existing primary frequency regulation performance evaluation, and achieves the technical effect of improving the accuracy of the primary frequency regulation performance evaluation of thermal power units.

Description

Technical Field

[0001] The present application relates to the field of industrial automation, and in particular to a method and system for evaluating primary frequency modulation performance based on multi-source data fusion. Background Art

[0002] In the power system, thermal power units are one of the main sources of power supply, and their operating stability and regulation capabilities are directly related to the safety and stability of the power grid. Among them, primary frequency regulation is an important function of thermal power units to automatically adjust the load when the power grid frequency fluctuates to maintain the stability of the power grid frequency. With the development of smart grid and big data technology, the demand for the evaluation of the primary frequency regulation performance of thermal power units is increasing, so as to ensure that the units can respond quickly and accurately to changes in the power grid frequency and ensure the overall stability and reliability of the power system. The traditional method for evaluating the primary frequency regulation performance of thermal power units mainly relies on a single data source and a single evaluation dimension for analysis. However, due to the limitations of the data source and evaluation dimension, the accuracy of the evaluation results of the traditional method is often questioned, and it is difficult to serve as a reliable basis for unit optimization and fault diagnosis.

[0003] In the current related technologies, there is a technical problem of insufficient accuracy in primary frequency modulation performance evaluation. Summary of the invention

[0004] The present application provides a primary frequency regulation performance evaluation method and system based on multi-source data fusion, adopts an all-in-one device to integrate data acquisition and edge computing capabilities, collects multiple data sources in real time from the monitoring system of the thermal power unit, fuses the collected DCS and DEH source data to obtain multi-source fused data containing rich information, performs edge computing on the fused data based on the all-in-one device, quickly extracts multiple primary frequency regulation performance indicators, constructs an independent primary frequency regulation performance evaluation sub-model for each evaluation dimension, adaptively weights multiple evaluation sub-models to form a primary frequency regulation performance evaluation model, uses the primary frequency regulation performance evaluation model to evaluate multiple primary frequency regulation performance indicators in real time, outputs primary frequency regulation performance evaluation results and other technical means, and achieves the technical effect of improving the accuracy of primary frequency regulation performance evaluation of thermal power units through comprehensive data acquisition and evaluation in multiple dimensions.

[0005] This application provides a primary frequency modulation performance evaluation method based on multi-source data fusion, including:

[0006] A monitoring system connected to a thermal power unit is used to collect and acquire DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device that integrates data collection and edge computing; data fusion is performed on the DCS and DEH source data to obtain multi-source fusion data; edge computing is performed on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency regulation performance indicators; multiple primary frequency regulation performance evaluation sub-models are constructed, wherein each primary frequency regulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency regulation performance evaluation sub-model outputs a result of qualified or unqualified; adaptively weight-integrate the multiple primary frequency regulation performance evaluation sub-models to obtain a primary frequency regulation performance evaluation model; primary frequency regulation response capability is evaluated on the multiple primary frequency regulation performance indicators through the primary frequency regulation performance evaluation model, and a primary frequency regulation performance evaluation result is output.

[0007] In a possible implementation, a primary frequency modulation response capability evaluation is performed on the multiple primary frequency modulation performance indicators through a primary frequency modulation performance evaluation model, and after the primary frequency modulation performance evaluation result is output, the following processing is performed:

[0008] Based on the pass rate, a primary frequency regulation performance alarm threshold is preset. If the primary frequency regulation performance evaluation result is lower than the primary frequency regulation performance alarm threshold, a fault warning signal is generated; a correlation analysis of the multiple primary frequency regulation performance indicators is performed based on the fault warning signal to generate a fault diagnosis result; and an advance warning for accident prevention is performed based on the fault diagnosis result.

[0009] In a possible implementation, the multiple primary frequency modulation performance evaluation sub-models are adaptively weighted to obtain a primary frequency modulation performance evaluation model, and the following processing is performed:

[0010] Extract multiple historical multi-source fusion data and multiple historical primary frequency modulation performance results from the SIS system, wherein each historical multi-source fusion data corresponds to a historical primary frequency modulation performance result; use the primary frequency modulation performance evaluation model to perform a primary frequency modulation response capability evaluation on the multiple historical multi-source fusion data to obtain multiple primary frequency modulation performance evaluation results; verify the accuracy of the primary frequency modulation performance evaluation model based on the multiple historical primary frequency modulation performance results and the multiple primary frequency modulation performance evaluation results; if the accuracy verification fails, optimize the primary frequency modulation performance evaluation model until the preset accuracy requirement is met.

[0011] In a possible implementation, the multi-source fusion data is edge-calculated based on the all-in-one device to obtain multiple primary frequency modulation performance indicators, and the following processing is performed:

[0012] Based on the all-in-one device, the DCS output data, DEH output data and DCS power generation data are called from the multi-source fusion data; the first-order response actual load adjustment amount, the second-order response actual load adjustment amount and the actual maximum output adjustment amount are calculated according to the DCS output data and the DEH output data, wherein the first-order response and the second-order response respectively correspond to different time stages of the primary frequency regulation response; the actual contribution power is calculated according to the DCS power generation data; the first-order response actual load adjustment amount, the second-order response actual load adjustment amount, the actual maximum output adjustment amount and the actual contribution power are integrated to obtain multiple primary frequency regulation performance indicators.

[0013] In a possible implementation, multiple primary frequency modulation performance evaluation sub-models are constructed to perform the following processing:

[0014] According to the actual load adjustment of the first-order response and the preset maximum load adjustment, a performance evaluation sub-model of the first-order output response index of the primary frequency regulation is constructed; according to the actual load adjustment of the second-order response and the preset maximum load adjustment, a performance evaluation sub-model of the second-order output response index of the primary frequency regulation is constructed; according to the actual maximum output adjustment and the preset maximum output adjustment, a performance evaluation sub-model of the maximum output response index of the primary frequency regulation is constructed; according to the actual contribution power and the preset contribution power, a performance evaluation sub-model of the primary frequency regulation power contribution index is constructed.

[0015] In a possible implementation, the multiple primary frequency modulation performance evaluation sub-models are adaptively weighted to obtain a primary frequency modulation performance evaluation model, and the following processing is performed:

[0016] A primary frequency modulation comprehensive performance evaluation submodel is constructed, wherein the primary frequency modulation comprehensive performance evaluation submodel is used to make a comprehensive judgment on the eligibility of a primary frequency modulation action according to the primary frequency modulation first-order output response index performance evaluation submodel, the primary frequency modulation second-order output response index performance evaluation submodel, the primary frequency modulation maximum output response index performance evaluation submodel and the primary frequency modulation electric quantity contribution index performance evaluation submodel, and output a primary frequency modulation performance evaluation result; based on a genetic algorithm, the weights of the primary frequency modulation performance evaluation submodel are adaptively adjusted, and the multiple primary frequency modulation performance evaluation submodels are connected in parallel and then connected to the primary frequency modulation comprehensive performance evaluation submodel to obtain a primary frequency modulation performance evaluation model.

[0017] In a possible implementation, multiple primary frequency modulation performance evaluation sub-models are constructed, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified, and performs the following processing:

[0018] Based on the actual primary frequency modulation performance index and the preset primary frequency modulation performance index, a plurality of qualified judgment conditions are constructed, wherein when the actual primary frequency modulation performance index reaches the qualified percentage threshold of the preset primary frequency modulation performance index, the actual primary frequency modulation performance index is judged to be qualified, and the plurality of qualified judgment conditions correspond one-to-one to the plurality of primary frequency modulation performance evaluation sub-models; if the primary frequency modulation performance index satisfies the qualified judgment conditions, the output result of the primary frequency modulation performance evaluation sub-model is qualified; if the primary frequency modulation performance index does not satisfy the qualified judgment conditions, the output result of the primary frequency modulation performance evaluation sub-model is unqualified.

[0019] The present application also provides a primary frequency modulation performance evaluation system based on multi-source data fusion, including:

[0020] A source data acquisition module, the source data acquisition module is used to connect to the monitoring system of the thermal power unit, and acquire DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data acquisition and edge computing; a data fusion module, the data fusion module is used to perform data fusion on the DCS and DEH source data to obtain multi-source fusion data; an edge computing module, the edge computing module is used to perform edge computing on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency regulation performance indicators; a primary frequency regulation performance evaluation sub-model construction module, the primary frequency regulation performance evaluation sub-model construction module Used to construct multiple primary frequency modulation performance evaluation sub-models, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified; a primary frequency modulation performance evaluation model construction module, the primary frequency modulation performance evaluation model construction module is used to adaptively weight the multiple primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model; a primary frequency modulation response capability evaluation module, the primary frequency modulation response capability evaluation module is used to perform a primary frequency modulation response capability evaluation on the multiple primary frequency modulation performance indicators through the primary frequency modulation performance evaluation model, and output a primary frequency modulation performance evaluation result.

[0021] The present application also provides an electronic device, including:

[0022] A memory for storing executable instructions;

[0023] The processor is used to implement a primary frequency modulation performance evaluation method based on multi-source data fusion when executing the executable instructions stored in the memory.

[0024] The present application also provides a computer-readable storage medium, comprising:

[0025] A computer program is stored thereon, and when the program is executed by a processor, a primary frequency modulation performance evaluation method based on multi-source data fusion is implemented.

[0026] The primary frequency regulation performance evaluation method and system based on multi-source data fusion proposed in this application are first connected to the monitoring system of the thermal power unit, and the DCS and DEH source data are collected from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data acquisition and edge computing. Then, the DCS and DEH source data are fused to obtain multi-source fused data, and then edge computing is performed on the multi-source fused data based on the all-in-one device to obtain multiple primary frequency regulation performance indicators. Then, multiple primary frequency regulation performance evaluation sub-models are constructed, wherein each primary frequency regulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency regulation performance evaluation sub-model outputs a result as qualified or unqualified. Then, multiple primary frequency regulation performance evaluation sub-models are adaptively weighted to obtain a primary frequency regulation performance evaluation model. Finally, the primary frequency regulation performance evaluation model is used to evaluate the primary frequency regulation response capability of multiple primary frequency regulation performance indicators, and the primary frequency regulation performance evaluation result is output, thereby achieving the technical effect of improving the accuracy of primary frequency regulation performance evaluation of thermal power units. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0028] Figure 1 A flowchart of a method for evaluating primary frequency modulation performance based on multi-source data fusion provided in an embodiment of the present application.

[0029] Figure 2 A schematic diagram of the structure of a primary frequency modulation performance evaluation system based on multi-source data fusion provided in an embodiment of the present application.

[0030] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0031] Explanation of the accompanying drawings: source data acquisition module 10, data fusion module 20, edge computing module 30, primary frequency modulation performance evaluation sub-model construction module 40, primary frequency modulation performance evaluation model construction module 50, primary frequency modulation response capability evaluation module 60. DETAILED DESCRIPTION

[0032] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0033] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0034] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0035] The present application embodiment provides a method for evaluating primary frequency modulation performance based on multi-source data fusion, such as Figure 1 As shown, the method includes:

[0036] Step S100, connect the monitoring system of the thermal power unit, and collect and obtain DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data collection and edge computing. Specifically, the all-in-one device is a hardware device that integrates multiple functions such as data collection, processing, and edge computing, and is used to obtain data from multiple data sources and perform preliminary processing. Preferably, the all-in-one device has data collection functions in different ways such as Ethernet and hard wiring, supports multiple collection and export protocols such as PMU protocol, IEC104 (TCP / UDP) protocol, MODBUS (TCP / RTU) protocol, and supports recording and edge computing functions. Connect the all-in-one device to the monitoring system of the thermal power unit through an appropriate interface, configure the parameters of data collection on the all-in-one device, including the data source address, collection frequency, data type, etc. of DCS (distributed control system) and DEH (digital electro-hydraulic control system), start the data collection function of the all-in-one device, and collect DCS and DEH source data from the monitoring system in real time or on demand. Among them, DCS is a system used to monitor and control the operating parameters of thermal power units and provide real-time data on unit operation; DEH is a digital control system used to control turbine speed and load.

[0037] Step S200, the DCS and DEH source data are fused to obtain multi-source fused data. Specifically, the collected DCS and DEH source data are cleaned to remove noise, error values, etc. to ensure the accuracy and reliability of the data. Since the DCS and DEH systems have inconsistent sampling rates, data synchronization processing is performed to ensure the consistency of the data in the time dimension. The Kalman filter algorithm is used to fuse the DCS and DEH data to obtain multi-source fused data.

[0038] Step S300, edge computing is performed on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency regulation performance indicators. Specifically, an edge computing algorithm is deployed on the all-in-one device, and the fused data is calculated in real time using the edge computing capability of the all-in-one device to extract multiple primary frequency regulation performance indicators, which are parameters that measure the ability of the thermal power unit to automatically adjust power to maintain the stability of the grid frequency when the grid frequency fluctuates, such as frequency regulation response time, frequency regulation accuracy, etc.

[0039] In a possible implementation, the multi-source fusion data is edge-calculated based on the all-in-one device to obtain a plurality of primary frequency regulation performance indicators, and step S300 further includes step S310, based on the all-in-one device, calling DCS output data, DEH output data and DCS power generation data from the multi-source fusion data. Specifically, the all-in-one device retrieves DCS output data, DEH output data and DCS power generation data from the multi-source fusion data according to a preset data interface and protocol. Among them, DCS output data is the real-time output data of the thermal power unit recorded by the DCS system, which reflects the power generation capacity of the unit; DEH output data is the turbine speed and load data controlled by the DEH system; DCS power generation data is the power generation of the thermal power unit within a certain period of time recorded by the DCS system, which is used to evaluate the actual power generation changes of the unit. Step S320, according to the DCS output data and DEH output data, the first-order response actual load adjustment, the second-order response actual load adjustment and the actual maximum output adjustment are calculated, wherein the first-order response and the second-order response correspond to different time stages of a frequency modulation response respectively. Specifically, according to the output data of DCS and DEH, the adjustment amount of the actual load of the unit from the time when the grid frequency crosses the dead zone to a certain time threshold is calculated, that is, the first-order response actual load adjustment amount. Continue to calculate the further adjustment amount of the actual load of the unit from the time when the grid frequency crosses the dead zone to another time threshold, that is, the second-order response actual load adjustment amount. The time interval span of the second-order response is greater than the time interval span of the first-order response. The distinction between the first-order and second-order responses is used to more carefully analyze the regulation ability of the unit at different time stages. For example, the first-order response actual load adjustment amount is a 15-second actual load adjustment amount, and the second-order response actual load adjustment amount is a 30-second actual load adjustment amount. The actual maximum output adjustment is the actual maximum compensation load value of the unit in the direction of reducing the frequency deviation during the frequency regulation action time, starting from when the grid frequency crosses the dead zone (such as ±0.033Hz). It reflects the unit's ability to compensate for grid frequency fluctuations. The calculation formula is: ,in, Indicates the actual maximum output adjustment range of a frequency modulation. Indicates the actual output of the unit when the grid frequency changes beyond the unit's primary frequency regulation dead zone (to shield power fluctuations and prevent measurement errors, The average value of the frequency within 10 seconds before the dead zone is reached can be taken). It indicates the actual output of the unit at time t during a frequency modulation operation period.

[0040] Step S330, calculate the actual contribution power according to the DCS power generation data. Specifically, the actual contribution power is an indicator to measure the change in actual power generation of the unit during the primary frequency regulation process, that is, the actual compensation power of the unit during the primary frequency regulation. From the time when the frequency deviation exceeds the dead zone to the time when the frequency deviation returns to the dead zone range is the primary frequency regulation action time. The actual active power generation during the primary frequency regulation action period is the part that increases (or decreases) compared to the power generation before the primary frequency regulation action, that is, the actual contribution power. High-frequency less power generation or low-frequency more power generation is positive, and high-frequency more power generation or low-frequency less power generation is negative. If the actual contribution power during the primary frequency regulation action period is positive, it is a positive contribution power; otherwise, it is a negative contribution power. The calculation formula is: ,in, Indicates the actual power contribution of the unit's primary frequency regulation. Indicates the start time of a frequency modulation evaluation, which is the time when the frequency deviation crosses the frequency modulation dead zone when a frequency modulation effective disturbance occurs. Indicates the end time of the primary frequency regulation evaluation. Step S340, integrate the first-order response actual load adjustment, the second-order response actual load adjustment, the actual maximum output adjustment and the actual contributed electricity to obtain multiple primary frequency regulation performance indicators. Specifically, the first-order response actual load adjustment, the second-order response actual load adjustment, the actual maximum output adjustment and the actual contributed electricity data are integrated to generate multiple primary frequency regulation performance indicators, which are used for subsequent performance evaluation. This implementation method generates multiple primary frequency regulation performance indicators by integrating multiple key data points, which provides strong support for comprehensive and accurate evaluation of the primary frequency regulation performance of the unit.

[0041] Step S400, construct multiple primary frequency regulation performance evaluation sub-models, wherein each primary frequency regulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency regulation performance evaluation sub-model outputs a result of qualified or unqualified. Specifically, according to the characteristics of the primary frequency regulation performance of the thermal power unit, multiple evaluation dimensions are determined to evaluate different aspects of the primary frequency regulation performance of the thermal power unit (such as response speed, regulation accuracy, stability, etc.). For each evaluation dimension, an independent primary frequency regulation performance evaluation sub-model is constructed based on a statistical method.

[0042] In a possible implementation, the construction of multiple primary frequency regulation performance evaluation sub-models, step S400 further includes step S410, constructing a primary frequency regulation first-order output response index performance evaluation sub-model according to the first-order response actual load adjustment and the preset maximum load adjustment. Specifically, the preset maximum load adjustment is the maximum load adjustment preset by the unit in the design to deal with the primary frequency regulation event, and the first-order response actual load adjustment is the load actually adjusted by the unit in response to the frequency change in the early stage of the power grid frequency fluctuation. The actual load adjustment of the first-order response is divided by the preset maximum load adjustment to obtain the actual adjustment ratio of the first-order response. According to this actual adjustment ratio, combined with the design parameters and performance standards of the unit, a primary frequency regulation first-order output response index performance evaluation sub-model is constructed, which is used to quantify the performance of the first-order response. Step S420, constructing a primary frequency regulation second-order output response index performance evaluation sub-model according to the second-order response actual load adjustment and the preset maximum load adjustment. Specifically, the second-order response actual load adjustment is the load adjustment made by the unit after the first-order response to further stabilize the power grid frequency. This step is similar to S410, but is for the second-order response stage. According to the actual load adjustment of the second-order response and the preset maximum load adjustment, the actual adjustment ratio is calculated, and a sub-model for the performance evaluation of the primary frequency modulation second-order output response index is constructed.

[0043] Step S430, construct a sub-model for performance evaluation of the maximum output response index of the primary frequency modulation according to the actual maximum output adjustment and the preset maximum output adjustment. Specifically, the actual maximum output adjustment is the maximum output adjustment actually achieved by the unit during the primary frequency modulation process; the preset maximum output adjustment is the maximum output adjustment preset by the unit in the design to cope with the primary frequency modulation, that is, the theoretical maximum compensation load value of the unit's primary frequency modulation corresponding to the maximum frequency deviation at the moment of the frequency fluctuation period starting from the time when the frequency deviation exceeds the dead zone, and the calculation formula is: ,in, It indicates the maximum adjustment of the theoretical output of the unit during the period of frequency regulation of the unit. It indicates the actual maximum frequency deviation during a frequency regulation action period, taking into account the frequency regulation dead zone, that is, for thermal power units: = Actual maximum frequency deviation - 0.033 (when the actual maximum frequency deviation ≥ 0.033Hz), = Actual maximum frequency deviation + 0.033 (when the actual maximum frequency deviation ≤ -0.033Hz), Indicates the rated active output of the unit. Indicates the rated frequency of the unit. Indicates the theoretical setting value of the speed inequality, take 5%, Indicates the maximum output limit of the unit. The upper limit of the frequency regulation load change range of the unit participating in the primary frequency regulation can be limited, but the limit range should not be too small. The regulations are as follows: a) 250MW> For thermal power units, the limit is ≥10% ; b) 350MW ≥ For thermal power units ≥250MW, the limit is ≥8% ; c) 500MW ≥ For thermal power units with a capacity of >350MW, the limit range is ≥7%PN; d) For thermal power units with a capacity of >500MW, the limit amplitude is ≥6%PN. When the units operating at rated load participate in primary frequency regulation, the maximum frequency regulation load increment amplitude in the load increase direction shall not be less than 5% . Calculate the deviation between the actual maximum output adjustment and the preset maximum output adjustment. Based on this deviation, combined with the technical specifications and performance requirements of the unit, construct a primary frequency regulation maximum output response index performance evaluation sub-model, which is used to evaluate the accuracy and reliability of the unit in maximum output adjustment. Step S440, construct a primary frequency regulation power contribution index performance evaluation sub-model based on the actual contribution power and the preset contribution power. Specifically, the actual contribution power is the power actually emitted by the unit during the primary frequency regulation process that helps to stabilize the grid frequency; the preset contribution power is the power contribution that should be achieved during the primary frequency regulation process, which is preset according to the unit performance and grid demand, that is, from the time the frequency deviation exceeds the dead zone until the frequency deviation returns to the dead zone range, the theoretical compensation power of the unit during the primary frequency regulation action period is calculated as follows: ,in, Indicates the theoretical contribution of the unit to primary frequency regulation, which is always positive. It represents the adjustment amount corresponding to the theoretical output of the unit at time t during the unit's primary frequency regulation action period. The difference between the actual contribution power and the preset contribution power is calculated. Based on this difference, combined with the operation requirements of the power grid and the performance characteristics of the unit, a primary frequency regulation power contribution index performance evaluation sub-model is constructed. This model is used to evaluate the actual contribution of the unit to the power grid during the primary frequency regulation process. This implementation method comprehensively and meticulously evaluates the various performance indicators of the unit during the primary frequency regulation process by constructing multiple specific performance evaluation sub-models. Each sub-model targets a specific response stage or performance indicator. By comparing and quantitatively analyzing the actual value with the preset value, it accurately determines whether the performance of the unit meets the standard, providing strong data support for evaluating the primary frequency regulation performance of the unit.

[0044] In a possible implementation, multiple primary frequency modulation performance evaluation sub-models are constructed, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified. Step S400 further includes step S450, constructing multiple qualified judgment conditions based on the actual primary frequency modulation performance index and the preset primary frequency modulation performance index, wherein when the actual primary frequency modulation performance index reaches the qualified percentage threshold of the preset primary frequency modulation performance index, the actual primary frequency modulation performance index is judged to be qualified, and the multiple qualified judgment conditions correspond to the multiple primary frequency modulation performance evaluation sub-models one by one. Specifically, for each evaluation dimension, a reasonable preset performance index is set according to industry standards, historical experience and expert opinions. For each preset performance index, a qualified percentage threshold is defined, which indicates how much proportion of the preset index the actual performance index needs to reach to be considered qualified, and a specific qualified judgment condition is constructed for each evaluation dimension according to the preset index and the qualified percentage threshold. For example, the actual load adjustment of the first-order response of the unit should reach 75% of the preset maximum load adjustment within the first-order response time, otherwise the unit's primary frequency regulation is judged as unqualified; the actual load adjustment of the second-order response of the unit should reach 90% of the preset maximum load adjustment within the second-order response time, otherwise the unit's primary frequency regulation is judged as unqualified; the actual contribution of the unit must reach 65% of the preset contribution, otherwise the unit's primary frequency regulation is judged as unqualified. Step S460, if the primary frequency regulation performance index meets the qualified judgment condition, the output result of the primary frequency regulation performance evaluation submodel is qualified; step S470, if the primary frequency regulation performance index does not meet the qualified judgment condition, the output result of the primary frequency regulation performance evaluation submodel is unqualified. Specifically, the actual performance index of each evaluation dimension is calculated in real time or regularly, and the calculated actual performance index is compared with the corresponding qualified judgment condition. If the actual performance index meets the qualified judgment condition, the corresponding primary frequency regulation performance evaluation submodel output result is "qualified"; if the actual performance index does not meet the qualified judgment condition, the corresponding primary frequency regulation performance evaluation submodel output result is "unqualified". This implementation method simplifies the output results of each primary frequency modulation performance evaluation sub-model into "qualified" or "unqualified", comprehensively and accurately evaluating the primary frequency modulation performance. By setting the qualified percentage threshold, it takes into account both the absolute value of the performance indicator and its fluctuation within a certain range, making the evaluation result more flexible and reasonable.

[0045] Step S500, adaptively weighting and integrating the multiple primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model. Specifically, according to the importance and relevance of each evaluation dimension, an adaptive weight is assigned to each primary frequency modulation performance evaluation sub-model based on a machine learning algorithm. The adaptive weight is a weight value dynamically adjusted according to actual conditions, and is used to balance the influence of different sub-models in the comprehensive evaluation. Multiple primary frequency modulation performance evaluation sub-models are integrated according to the assigned weights to form a comprehensive primary frequency modulation performance evaluation model.

[0046] In a possible implementation, the multiple primary frequency regulation performance evaluation sub-models are adaptively weighted to obtain a primary frequency regulation performance evaluation model, and step S500 further includes step S510, constructing a primary frequency regulation comprehensive performance evaluation sub-model, the primary frequency regulation comprehensive performance evaluation sub-model is used to make a comprehensive judgment on the qualification of the primary frequency regulation action according to the primary frequency regulation first-order output response index performance evaluation sub-model, the primary frequency regulation second-order output response index performance evaluation sub-model, the primary frequency regulation maximum output response index performance evaluation sub-model and the primary frequency regulation power contribution index performance evaluation sub-model, and output the primary frequency regulation performance evaluation result. Specifically, the primary frequency regulation comprehensive performance evaluation sub-model is based on weighted summation decision logic, and is used to integrate the outputs of multiple primary frequency regulation performance evaluation sub-models to form a comprehensive evaluation of the primary frequency regulation performance. The primary frequency regulation comprehensive performance evaluation sub-model receives outputs from sub-models of different evaluation dimensions, and calculates a comprehensive evaluation result based on these outputs.

[0047] Step S520, based on the genetic algorithm, the weights of the primary frequency modulation performance evaluation submodels are adaptively adjusted, and the multiple primary frequency modulation performance evaluation submodels are connected in parallel and then connected to the primary frequency modulation comprehensive performance evaluation submodel to obtain the primary frequency modulation performance evaluation model. Specifically, an initial weight is assigned to each primary frequency modulation performance evaluation submodel, and these weights are equal. The genetic algorithm is used for iteration, and the process of selection, crossover, mutation, evaluation and replacement is repeated until the predetermined number of iterations is reached. After the iteration is completed, the weight combination that can make the primary frequency modulation performance evaluation model perform best is selected as the final weight, which is used in the primary frequency modulation performance evaluation model. The final weight is applied to each primary frequency modulation performance evaluation submodel, and these submodels are connected in parallel and then connected to the primary frequency modulation comprehensive performance evaluation submodel to form a complete primary frequency modulation performance evaluation model. This implementation method comprehensively and accurately evaluates the performance of the primary frequency modulation by constructing a primary frequency modulation comprehensive performance evaluation submodel and integrating multiple primary frequency modulation performance evaluation submodels through adaptive weights. The genetic algorithm is used for weight adaptive adjustment to automatically find the optimal weight combination, avoiding the subjectivity and uncertainty of artificially set weights. In addition, connecting the sub-models in parallel improves the efficiency of the evaluation, allowing the model to respond to real-time data more quickly and give evaluation results. This implementation method improves the accuracy and efficiency of the evaluation.

[0048] In a possible implementation, the multiple primary frequency regulation performance evaluation sub-models are adaptively weighted integrated to obtain a primary frequency regulation performance evaluation model, and step S500 further includes step S530, extracting multiple historical multi-source fusion data and multiple historical primary frequency regulation performance results from the SIS system, wherein each historical multi-source fusion data corresponds to a historical primary frequency regulation performance result. Specifically, historical data related to primary frequency regulation performance is extracted from the SIS (supervision information system) system, including operation data of thermal power units, power grid load data, frequency regulation instruction data, etc., and multi-source fusion processing is performed. For each historical multi-source fusion data, a corresponding historical primary frequency regulation performance result is found, and these performance results are obtained based on expert judgment. Step S540, the primary frequency regulation performance evaluation model is used to evaluate the primary frequency regulation response capability of the multiple historical multi-source fusion data to obtain multiple primary frequency regulation performance evaluation results. Specifically, the extracted historical multi-source fusion data is passed as input to the primary frequency regulation performance evaluation model, and the model executes its internal logic and algorithm according to the input data, evaluates the response capability of the primary frequency regulation, and generates a primary frequency regulation performance evaluation result. Step S550, verify the accuracy of the primary frequency modulation performance evaluation model according to the multiple historical primary frequency modulation performance results and the multiple primary frequency modulation performance evaluation results. Specifically, compare the primary frequency modulation performance evaluation results generated by the primary frequency modulation performance evaluation model with the corresponding historical primary frequency modulation performance results one by one, calculate the error between the model evaluation result and the historical result through the mean square error, and compare the error with the preset threshold based on the error calculation result to evaluate whether the accuracy of the primary frequency modulation performance evaluation model meets the requirements. Step S560, if the accuracy verification fails, optimize the primary frequency modulation performance evaluation model until the preset accuracy requirements are met. Specifically, if the accuracy of the primary frequency modulation performance evaluation model does not meet the requirements, analyze the causes of the errors, and optimize the model according to the results of the error analysis. The optimization measures include adjusting model parameters, improving model structure, optimizing data processing flow, etc. The optimized model is reapplied to the historical multi-source fusion data, re-evaluated, and verified whether its accuracy meets the preset requirements. If the accuracy still does not meet the requirements, continue to optimize and verify the model until the preset accuracy requirements are met. This implementation method provides a reliable data basis for the accuracy verification of the primary frequency modulation performance evaluation model by extracting multi-source fusion data and corresponding historical performance results from historical data. The accuracy of the model is accurately evaluated by comparing the evaluation results of historical data with the actual results. When the accuracy of the model does not meet the requirements, the model is optimized to ensure that the final primary frequency modulation performance evaluation model has sufficient accuracy and reliability, improve the scientificity and objectivity of the model evaluation, and enhance the practicality and application value of the model.

[0049] Step S600, a primary frequency regulation response capability evaluation is performed on the multiple primary frequency regulation performance indicators through a primary frequency regulation performance evaluation model, and a primary frequency regulation performance evaluation result is output. Specifically, the primary frequency regulation performance indicators extracted in step S300 are input into the integrated primary frequency regulation performance evaluation model, and the model is calculated based on the input indicator values ​​and the assigned weights to evaluate the primary frequency regulation response capability of the thermal power unit, and a primary frequency regulation performance evaluation result is output. The embodiment of the present application adopts an all-in-one device to integrate data acquisition and edge computing capabilities, collects multiple data sources in real time from the monitoring system of the thermal power unit, fuses the collected DCS and DEH source data to obtain multi-source fused data containing rich information, performs edge computing on the fused data based on the all-in-one device, quickly extracts multiple primary frequency regulation performance indicators, constructs an independent primary frequency regulation performance evaluation sub-model for each evaluation dimension, adaptively weights the multiple evaluation sub-models to form a primary frequency regulation performance evaluation model, uses the primary frequency regulation performance evaluation model to perform real-time evaluation of multiple primary frequency regulation performance indicators, outputs the primary frequency regulation performance evaluation results and other technical means, and achieves the technical effect of improving the accuracy of primary frequency regulation performance evaluation of thermal power units through comprehensive data acquisition and evaluation in multiple dimensions.

[0050] In a possible implementation, the method further includes step S700, based on the qualified rate, presetting the primary frequency regulation performance alarm threshold value for the multiple primary frequency regulation performance indicators, and generating a fault warning signal if the primary frequency regulation performance evaluation result is lower than the primary frequency regulation performance alarm threshold value. Specifically, the qualified rate refers to the proportion of each evaluation dimension in the primary frequency regulation performance evaluation result that meets the qualified standard. Based on the qualified rate, a primary frequency regulation performance alarm threshold value is set, and this threshold value is used to judge whether the primary frequency regulation performance has reached the preset safety standard. The evaluation result output by the primary frequency regulation performance evaluation model is compared with the preset alarm threshold value. If the evaluation result is lower than the alarm threshold value, it indicates that there is a problem with the primary frequency regulation performance, and a fault warning signal needs to be generated. Step S800, performing correlation analysis of the multiple primary frequency regulation performance indicators according to the fault warning signal, and generating a fault diagnosis result. Specifically, after receiving the fault warning signal, multiple indicator data related to the primary frequency regulation performance are collected, including but not limited to the speed of the thermal power unit, the load change, the execution of the frequency regulation instruction, etc. Using data mining methods, correlation analysis is performed on multiple collected primary frequency regulation performance indicators to find out the key factors that lead to performance degradation. Based on the results of the correlation analysis, a specific fault diagnosis report is generated, including the specific location, cause, impact range and possible solutions of the fault. Step S900, a pre-warning for accident prevention is performed according to the fault diagnosis results. Specifically, according to the fault diagnosis results, the risks existing in the current system and the types of accidents that may be caused are evaluated, and based on the risk assessment results, corresponding accident prevention measures are generated, including adjusting equipment operating parameters, strengthening maintenance, updating equipment or systems, etc. Preventive measures and possible accident risks are issued to relevant personnel in the form of early warning notifications. This implementation method helps relevant personnel take measures in advance to prevent accidents by setting alarm thresholds, performing correlation analysis and issuing pre-warnings, effectively improving the monitoring and management level of primary frequency regulation performance, and improving the overall operating efficiency and stability of the power system and related equipment.

[0051] In the above, refer to Figure 1 The primary frequency modulation performance evaluation method based on multi-source data fusion according to an embodiment of the present invention is described in detail. Figure 2 A primary frequency modulation performance evaluation system based on multi-source data fusion according to an embodiment of the present invention is described.

[0052] The primary frequency regulation performance evaluation system based on multi-source data fusion according to an embodiment of the present invention is used to solve the technical problem of insufficient accuracy in the existing primary frequency regulation performance evaluation, and achieve the technical effect of improving the accuracy of the primary frequency regulation performance evaluation of thermal power units. The primary frequency regulation performance evaluation system based on multi-source data fusion includes: a source data acquisition module 10, a data fusion module 20, an edge computing module 30, a primary frequency regulation performance evaluation sub-model construction module 40, a primary frequency regulation performance evaluation model construction module 50, and a primary frequency regulation response capability evaluation module 60.

[0053] The source data acquisition module 10 is used to connect to the monitoring system of the thermal power unit, and acquire DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data acquisition and edge computing; the data fusion module 20 is used to perform data fusion on the DCS and DEH source data to obtain multi-source fusion data; the edge computing module 30 is used to perform edge computing on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency regulation performance indicators; the primary frequency regulation performance evaluation sub-model construction module 40 is used to construct multiple primary frequency regulation performance evaluation sub-models, wherein each primary frequency regulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency regulation performance evaluation sub-model outputs a result of qualified or unqualified; the primary frequency regulation performance evaluation model construction module 50 is used to perform adaptive weight integration on the multiple primary frequency regulation performance evaluation sub-models to obtain a primary frequency regulation performance evaluation model; the primary frequency regulation response capability evaluation module 60 is used to perform a primary frequency regulation response capability evaluation on the multiple primary frequency regulation performance indicators through the primary frequency regulation performance evaluation model, and output a primary frequency regulation performance evaluation result.

[0054] Among them, after the primary frequency regulation response capability is evaluated on the multiple primary frequency regulation performance indicators through the primary frequency regulation performance evaluation model and the primary frequency regulation performance evaluation result is output, the system can further include: a fault warning signal generation module is used to preset a primary frequency regulation performance alarm threshold based on the pass rate, and if the primary frequency regulation performance evaluation result is lower than the primary frequency regulation performance alarm threshold, a fault warning signal is generated; a correlation analysis module is used to perform correlation analysis on the multiple primary frequency regulation performance indicators according to the fault warning signal to generate a fault diagnosis result; and an advance warning module is used to perform advance warning for accident prevention according to the fault diagnosis result.

[0055] The specific configuration of the primary frequency regulation performance evaluation model construction module 50 will be described in detail below. As described above, the multiple primary frequency regulation performance evaluation sub-models are adaptively weighted integrated to obtain a primary frequency regulation performance evaluation model. The primary frequency regulation performance evaluation model construction module 50 may further include: a historical data extraction unit for extracting multiple historical multi-source fusion data and multiple historical primary frequency regulation performance results from the SIS system, wherein each historical multi-source fusion data corresponds to a historical primary frequency regulation performance result; a primary frequency regulation response capability evaluation unit for using the primary frequency regulation performance evaluation model to perform a primary frequency regulation response capability evaluation on the multiple historical multi-source fusion data to obtain multiple primary frequency regulation performance evaluation results; an accuracy verification unit for verifying the accuracy of the primary frequency regulation performance evaluation model based on the multiple historical primary frequency regulation performance results and the multiple primary frequency regulation performance evaluation results; and a model optimization unit for optimizing the primary frequency regulation performance evaluation model if the accuracy verification fails until the preset accuracy requirement is reached.

[0056] The specific configuration of the edge computing module 30 will be described in detail below. As described above, the edge computing of the multi-source fusion data is performed based on the all-in-one device to obtain multiple primary frequency regulation performance indicators. The edge computing module 30 may further include: a data calling unit is used to call DCS output data, DEH output data and DCS power generation data from the multi-source fusion data based on the all-in-one device; a data calculation unit is used to calculate the first-order response actual load adjustment, the second-order response actual load adjustment and the actual maximum output adjustment according to the DCS output data and DEH output data, wherein the first-order response and the second-order response correspond to different time stages of the primary frequency regulation response, respectively, and the actual contribution power is calculated according to the DCS power generation data; a primary frequency regulation performance indicator generation unit is used to integrate the first-order response actual load adjustment, the second-order response actual load adjustment, the actual maximum output adjustment and the actual contribution power to obtain multiple primary frequency regulation performance indicators.

[0057] The specific configuration of the primary frequency regulation performance evaluation sub-model construction module 40 will be described in detail below. As described above, multiple primary frequency regulation performance evaluation sub-models are constructed, and the primary frequency regulation performance evaluation sub-model construction module 40 may further include: a primary frequency regulation first-order output response index performance evaluation sub-model construction unit is used to construct a primary frequency regulation first-order output response index performance evaluation sub-model according to the actual load adjustment amount of the first-order response and the preset maximum load adjustment amount; a primary frequency regulation second-order output response index performance evaluation sub-model construction unit is used to construct a primary frequency regulation second-order output response index performance evaluation sub-model according to the actual load adjustment amount of the second-order response and the preset maximum load adjustment amount; a primary frequency regulation maximum output response index performance evaluation sub-model construction unit is used to construct a primary frequency regulation maximum output response index performance evaluation sub-model according to the actual maximum output adjustment amount and the preset maximum output adjustment amount; a primary frequency regulation power contribution index performance evaluation sub-model construction unit is used to construct a primary frequency regulation power contribution index performance evaluation sub-model according to the actual contribution power and the preset contribution power.

[0058] Among them, the multiple primary frequency modulation performance evaluation sub-models are adaptively weighted integrated to obtain a primary frequency modulation performance evaluation model, and the primary frequency modulation performance evaluation model construction module 50 may further include: a primary frequency modulation comprehensive performance evaluation sub-model construction unit is used to construct a primary frequency modulation comprehensive performance evaluation sub-model, and the primary frequency modulation comprehensive performance evaluation sub-model is used to perform a comprehensive judgment on the qualification of a primary frequency modulation action according to the primary frequency modulation first-order output response index performance evaluation sub-model, the primary frequency modulation second-order output response index performance evaluation sub-model, the primary frequency modulation maximum output response index performance evaluation sub-model and the primary frequency modulation power contribution index performance evaluation sub-model, and output a primary frequency modulation performance evaluation result; a primary frequency modulation performance evaluation model generation unit is used to perform an adaptive adjustment of the weight of the primary frequency modulation performance evaluation sub-model based on a genetic algorithm, and the multiple primary frequency modulation performance evaluation sub-models are connected in parallel and then connected to the primary frequency comprehensive performance evaluation sub-model to obtain a primary frequency modulation performance evaluation model.

[0059] Among them, multiple primary frequency modulation performance evaluation sub-models are constructed, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result that is qualified or unqualified. The primary frequency modulation performance evaluation sub-model construction module 40 may further include: a qualified judgment condition construction unit is used to construct multiple qualified judgment conditions based on the actual primary frequency modulation performance index and the preset primary frequency modulation performance index, wherein when the actual primary frequency modulation performance index reaches the qualified percentage threshold of the preset primary frequency modulation performance index, the actual primary frequency modulation performance index is judged to be qualified, and the multiple qualified judgment conditions correspond one-to-one to the multiple primary frequency modulation performance evaluation sub-models; the qualified judgment unit is used to determine that if the primary frequency modulation performance index meets the qualified judgment condition, the output result of the primary frequency modulation performance evaluation sub-model is qualified, and if the primary frequency modulation performance index does not meet the qualified judgment condition, the output result of the primary frequency modulation performance evaluation sub-model is unqualified.

[0060] The primary frequency modulation performance evaluation system based on multi-source data fusion provided in the embodiment of the present invention can execute the primary frequency modulation performance evaluation method based on multi-source data fusion provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0061] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0062] Based on the foregoing embodiments, the embodiments of the present application further provide an electronic device and a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of the electronic device, it can implement the method described in any of the foregoing embodiments.

[0063] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing an implementation of the present invention. Figure 3The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The electronic device is in the form of a general computing device, and its components may include but are not limited to an input device 301, a processor 302, a memory 303, and an output device 304. Among them, the processor 302 may be one or more; the memory 303 may include a computer-readable medium and at least one program product, and the program product has a set (at least one) of program modules, which are configured to perform the functions of each embodiment of the present application.

[0064] The memory 303 shown in the embodiment of the present invention may adopt any combination of one or more computer-readable media; the computer-readable storage medium may be, but is not limited to, an infrared, semiconductor system, device or component, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the primary frequency modulation performance evaluation method based on multi-source data fusion in the embodiment of the present invention. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 303, thereby realizing the above-mentioned primary frequency modulation performance evaluation method based on multi-source data fusion.

[0065] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A primary frequency modulation performance evaluation method based on multi-source data fusion, characterized in that: The method comprises: Connecting to the monitoring system of the thermal power unit, acquiring DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data acquisition and edge computing; Performing data fusion on the DCS and DEH source data to obtain multi-source fusion data; Perform edge computing on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency modulation performance indicators; Construct multiple primary frequency modulation performance evaluation sub-models, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified; Adaptively weighting the plurality of primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model; A primary frequency modulation response capability evaluation is performed on the multiple primary frequency modulation performance indicators through a primary frequency modulation performance evaluation model, and a primary frequency modulation performance evaluation result is output.

2. The primary frequency modulation performance evaluation method based on multi-source data fusion according to claim 1, characterized in that: After the primary frequency modulation response capability is evaluated on the multiple primary frequency modulation performance indicators by using the primary frequency modulation performance evaluation model and the primary frequency modulation performance evaluation result is output, the method further includes: Based on the qualified rate, a primary frequency regulation performance alarm threshold is preset, and if the primary frequency regulation performance evaluation result is lower than the primary frequency regulation performance alarm threshold, a fault warning signal is generated; Performing correlation analysis on the plurality of primary frequency modulation performance indicators according to the fault warning signal to generate a fault diagnosis result; An advance warning for accident prevention is performed based on the fault diagnosis result.

3. The primary frequency modulation performance evaluation method based on multi-source data fusion according to claim 1, characterized in that: The step of adaptively weighting and integrating the plurality of primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model further includes: Extracting multiple historical multi-source fusion data and multiple historical primary frequency regulation performance results from the SIS system, wherein each historical multi-source fusion data corresponds to one historical primary frequency regulation performance result; Using the primary frequency modulation performance evaluation model to perform a primary frequency modulation response capability evaluation on the plurality of historical multi-source fusion data to obtain a plurality of primary frequency modulation performance evaluation results; Verifying the accuracy of the primary frequency modulation performance evaluation model according to the multiple historical primary frequency modulation performance results and the multiple primary frequency modulation performance evaluation results; If the accuracy verification fails, the primary frequency modulation performance evaluation model is optimized until the preset accuracy requirement is met.

4. The primary frequency modulation performance evaluation method based on multi-source data fusion according to claim 1, characterized in that: The edge computing is performed on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency modulation performance indicators, including: Based on the all-in-one device, DCS output data, DEH output data and DCS power generation data are called from the multi-source fusion data; The first-order response actual load adjustment, the second-order response actual load adjustment and the actual maximum output adjustment are calculated according to the DCS output data and the DEH output data, wherein the first-order response and the second-order response correspond to different time stages of the primary frequency modulation response respectively; Calculate the actual contribution power according to the DCS power generation data; The first-order response actual load adjustment amount, the second-order response actual load adjustment amount, the actual maximum output adjustment amount and the actual contributed power are integrated to obtain a plurality of primary frequency regulation performance indicators.

5. The primary frequency modulation performance evaluation method based on multi-source data fusion according to claim 4 is characterized in that: The constructing of multiple primary frequency modulation performance evaluation sub-models includes: According to the actual load adjustment of the first-order response and the preset maximum load adjustment, a sub-model for evaluating the performance of the first-order output response index of primary frequency regulation is constructed; According to the actual load adjustment of the second-order response and the preset maximum load adjustment, a sub-model for evaluating the performance of the second-order output response index of the primary frequency regulation is constructed; According to the actual maximum output adjustment and the preset maximum output adjustment, a sub-model for performance evaluation of the primary frequency modulation maximum output response index is constructed; According to the actual contribution power and the preset contribution power, a sub-model for evaluating the performance of the primary frequency regulation power contribution index is constructed.

6. The primary frequency modulation performance evaluation method based on multi-source data fusion as claimed in claim 5, characterized in that: The step of adaptively weighting and integrating the plurality of primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model comprises: Constructing a primary frequency modulation comprehensive performance evaluation submodel, the primary frequency modulation comprehensive performance evaluation submodel is used to perform a comprehensive judgment on the qualification of a primary frequency modulation action according to the primary frequency modulation first-order output response index performance evaluation submodel, the primary frequency modulation second-order output response index performance evaluation submodel, the primary frequency modulation maximum output response index performance evaluation submodel and the primary frequency modulation power contribution index performance evaluation submodel, and output a primary frequency modulation performance evaluation result; Based on the genetic algorithm, the weights of the primary frequency modulation performance evaluation sub-models are adaptively adjusted, and the multiple primary frequency modulation performance evaluation sub-models are connected in parallel and then connected to the primary frequency modulation comprehensive performance evaluation sub-model to obtain a primary frequency modulation performance evaluation model.

7. The primary frequency modulation performance evaluation method based on multi-source data fusion according to claim 1, characterized in that: The constructing of multiple primary frequency modulation performance evaluation sub-models, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified, includes: Based on the actual primary frequency modulation performance index and the preset primary frequency modulation performance index, a plurality of qualified judgment conditions are constructed, wherein when the actual primary frequency modulation performance index reaches the qualified percentage threshold of the preset primary frequency modulation performance index, the actual primary frequency modulation performance index is judged to be qualified, and the plurality of qualified judgment conditions correspond one-to-one to the plurality of primary frequency modulation performance evaluation sub-models; If the primary frequency regulation performance index meets the qualified judgment condition, the primary frequency regulation performance evaluation sub-model outputs a qualified result; If the primary frequency modulation performance index does not meet the qualified judgment condition, the primary frequency modulation performance evaluation sub-model outputs a result that is unqualified.

8. A primary frequency modulation performance evaluation system based on multi-source data fusion, characterized in that: The system is used to implement the primary frequency modulation performance evaluation method based on multi-source data fusion according to any one of claims 1 to 7, and the system comprises: A source data acquisition module, the source data acquisition module is used to connect to the monitoring system of the thermal power unit, and acquire DCS and DEH source data from the monitoring system through an all-in-one device, wherein the all-in-one device is a device integrating data acquisition and edge computing; A data fusion module, the data fusion module is used to fuse the DCS and DEH source data to obtain multi-source fusion data; An edge computing module, the edge computing module is used to perform edge computing on the multi-source fusion data based on the all-in-one device to obtain multiple primary frequency modulation performance indicators; A primary frequency modulation performance evaluation sub-model construction module, wherein the primary frequency modulation performance evaluation sub-model construction module is used to construct a plurality of primary frequency modulation performance evaluation sub-models, wherein each primary frequency modulation performance evaluation sub-model corresponds to an evaluation dimension, and each primary frequency modulation performance evaluation sub-model outputs a result of qualified or unqualified; A primary frequency modulation performance evaluation model construction module, wherein the primary frequency modulation performance evaluation model construction module is used to adaptively weight the multiple primary frequency modulation performance evaluation sub-models to obtain a primary frequency modulation performance evaluation model; A primary frequency modulation response capability evaluation module is used to perform a primary frequency modulation response capability evaluation on the multiple primary frequency modulation performance indicators through a primary frequency modulation performance evaluation model, and output a primary frequency modulation performance evaluation result.

9. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the primary frequency modulation performance evaluation method based on multi-source data fusion as described in any one of claims 1 to 7 when executing the executable instructions stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a primary frequency modulation performance evaluation method based on multi-source data fusion as described in any one of claims 1 to 7 is implemented.

Images