A method and system for optimizing the operation of coal-fired power generating units based on industrial big data

Abstract

This invention discloses a method and system for optimizing the operation of coal-fired power generating units based on industrial big data, belonging to the field of industrial technology. The startup priority analysis module dynamically adjusts the unit startup sequence by analyzing real-time data sets and grid load demand to obtain unit startup priorities. The system can quickly determine the startup sequence of units based on the magnitude of the data and effectively identify units with potential fault risks. The fault identification module combines real-time and historical data sets to assess the unit operating status and equipment status data, calculating the current fault assessment index. By comprehensively analyzing historical trends and real-time status, the system can accurately determine whether unit maintenance is required, thereby achieving early prediction and timely intervention for potential faults. The effect feedback and optimization module evaluates the feedback data of actual operating effects, constructs a performance feedback index, and realizes dynamic adjustment and optimization of unit load distribution.

Description

Technical Field

[0001] This invention relates to the field of industrial technology, specifically to a method and system for optimizing the operation of coal-fired power generating units based on industrial big data. Background Technology

[0002] Coal-fired power generating units, as a crucial component of global power production, are widely used in traditional energy sectors and are core to the stable operation of power grids. With continuous advancements in industrial technology, industrial big data has become a key technology driving energy management and optimization, injecting new vitality into the traditional energy industry through real-time monitoring, data analysis, and intelligent optimization. In the integration of industrial big data and coal-fired power generating units, intelligent optimization of unit operation based on massive amounts of real-time and historical data has become a hot topic in both academic research and industrial applications. Specifically, optimizing the start-up and shutdown sequence and load distribution of units based on real-time grid load data and the operating status of coal-fired power generating units can significantly improve grid load response capabilities, reduce energy consumption, and enhance the economic efficiency of unit operation. This big data-based optimization technology effectively integrates data analysis and system scheduling, providing solutions for the intelligent, green, and efficient development of coal-fired power generation.

[0003] In current coal-fired power unit operation and management, traditional start-up and shutdown sequences and load allocation strategies often rely on manual experience or simple rules, lacking the ability to dynamically adjust based on real-time data. This management model may lead to response delays when load demand fluctuates significantly, making it difficult to quickly allocate resources to meet grid demands. Furthermore, due to the lack of in-depth analysis of historical operating data, the economic efficiency and availability of the units cannot be optimally guaranteed under complex operating conditions, resulting in excessive fuel consumption and decreased power generation efficiency. Especially for potential unit failures, traditional methods rely on periodic inspections or equipment alarms, making it difficult to perform trend prediction and early intervention, often leading to delayed or excessive equipment maintenance. Therefore, the current system has significant shortcomings in optimizing efficiency, grid load response capabilities, and fault prediction capabilities, urgently requiring an intelligent optimization system based on industrial big data for improvement. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for optimizing the operation of coal-fired power generating units based on industrial big data, thus solving the problems mentioned in the background.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: a coal-fired power generation unit operation optimization system based on industrial big data, including a data acquisition module, a data processing module, a start-up priority analysis module, a fault identification module, and an effect feedback and optimization module;

[0006] The data acquisition module is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments, generate real-time data sets, and acquire historical data sets of each coal-fired power generating unit within historical time periods based on big data technology.

[0007] The data processing module is used to preprocess the relevant data in the real-time data group, remove noise, remove outliers and fill in missing values, and construct the processed real-time data group after dimensionless processing.

[0008] The startup priority analysis module is used to analyze and determine the startup order of each unit based on the processed real-time data group and the grid load demand Dfyq, so as to obtain the startup priority Qyxj of the unit. Based on the value of the startup priority Qyxj, the startup order of each unit and whether there is a fault risk are determined. If there is a fault risk, a trend analysis command is triggered.

[0009] The fault identification module is used to receive trend analysis commands and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled;

[0010] The effect feedback and optimization module is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, obtain relevant feedback data, evaluate the balance between grid load response capability and unit operating efficiency based on the relevant feedback data, construct a performance feedback index Xfzs, and adjust and optimize the load of the corresponding unit based on the performance feedback index Xfzs.

[0011] Preferably, the data acquisition module includes a real-time monitoring unit and a historical data extraction unit;

[0012] The real-time monitoring unit is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments. The relevant unit operation data includes the unit's fuel consumption per unit time Rxz, load output value Fsz, availability coefficient Kyz of the corresponding unit at each time moment, unit load fluctuation factor Fbyz, and the target value of the corresponding unit's maximum generating load Fbz. max The relevant equipment status data includes boiler pressure fluctuation factor Ybyz1 and steam pipeline pressure fluctuation factor Ybyz2; multiple monitoring instruments include laser coal flow meter, power monitoring instrument and unit performance testing instrument; the real-time data group includes relevant unit operation data and relevant equipment status data;

[0013] The historical extraction unit is used to acquire relevant unit operation data and relevant equipment status data of each coal-fired power generating unit in the industrial park during a historical period using big data technology. The historical data group includes relevant unit operation data and relevant equipment status data during a historical period.

[0014] Preferably, the data processing module includes a preprocessing unit and a normalization unit;

[0015] The preprocessing unit is used to preprocess the relevant data within the real-time data group. The preprocessing includes noise removal, missing value filling, outlier removal, and data smoothing. The missing value filling methods include mean filling, median filling, interpolation filling, and regression filling.

[0016] The normalization unit is used to eliminate unit differences in the relevant data within the preprocessed real-time data group using dimensionless processing technology, so that the range of the relevant data within the preprocessed real-time data group falls within [0, 1].

[0017] Preferably, the startup priority analysis module includes a running status analysis unit, a priority unit, and a preliminary judgment unit;

[0018] The operation status analysis unit is used to extract the unit-time fuel consumption Rxz and load output value Fsz of each unit from the relevant unit operation data in the processed real-time data group. Based on the unit-time fuel consumption Rxz and load output value Fsz of each unit, the economic index Jzb of each unit is calculated. Specifically, the economic index Jzb of each unit is obtained according to the following formula:

[0019]

[0020] Based on the economic indicators Jzb and grid load demand Dfyq of each generating unit, the target power generation load value Fbz for each generating unit in different monitoring periods is calculated. Specifically, the target power generation load value Fbz for each generating unit in different monitoring periods is obtained according to the following formula:

[0021]

[0022] In the formula, Fbz(t) represents the target power generation load of the corresponding unit at time t, Dfyq(t) represents the grid load demand at time t, and Jzb -1 This represents the economic weight of the corresponding unit; n represents the number of units, i = 1, 2, 3, ..., n.

[0023] Preferably, the priority unit is used to analyze and determine the current startup sequence of each unit based on the processed real-time data group and the relevant unit operation data, combined with the current grid load demand, so as to obtain the unit startup priority Qyxj. The unit startup priority Qyxj is specifically obtained by the following formula:

[0024]

[0025] In the formula, Qyxj(t) represents the unit startup priority at time t, Kyz(t) represents the availability coefficient of the corresponding unit at time t, and Fbz... max denoted as the target value of the maximum generating load of the corresponding unit, and ∈ represents the correction constant.

[0026] Preferably, the preliminary judgment unit is used to obtain the unit startup priority Qyxj of each unit according to the method of obtaining the unit startup priority Qyxj in the priority unit, and sort them to generate a sequence group; based on the historical data group, it determines the unit startup priority Qyxj of the corresponding unit in the historical period, and obtains the average unit startup priority Qyxj of the corresponding unit by combining the statistical mean algorithm. avg By comparing the current unit's startup priority Qyxj with the average unit startup priority Qyxj of the corresponding units... avg A comparison will be conducted to determine the startup sequence of the corresponding units and whether there is a risk of failure. The specific preliminary assessment is as follows:

[0027] If the current unit's startup priority Qyxj is greater than or equal to the corresponding unit's average startup priority Qyxj avg If it is initially determined that there is no risk of failure in the corresponding unit, then the trend analysis command will not be triggered externally, the corresponding unit will be kept in the sequence group, and the corresponding unit will be marked as a normal unit.

[0028] If the current unit's startup priority Qyxj is less than the average unit startup priority Qyxj of the corresponding unit avg When it is initially determined that the corresponding unit has a risk of failure, a trend analysis command is triggered to remove the corresponding unit from the sequence group and mark it as an abnormal unit.

[0029] Based on the preliminary assessment, the normal generating units are counted and reordered to generate an optimized sequence group. Based on the optimized sequence group, the startup order of each normal generating unit is determined.

[0030] Preferably, the fault identification module includes a fault analysis unit and an identification unit;

[0031] The fault analysis unit, upon receiving a trend analysis command, analyzes the current fault assessment index Ggzs of each abnormal unit during operation based on the processed real-time data group's relevant equipment status data and after dimensionless processing. c The current fault assessment index Ggzs c Obtain it using the following formula:

[0032]

[0033] In the formula, ΔQyxj represents the unit start-up priority difference, Ybyz1 represents the boiler pressure fluctuation factor, Ybyz2 represents the steam pipeline pressure fluctuation factor, Fbyz represents the unit load fluctuation factor, and α, β, γ and All represent weight values, where 0 < α < 1, 0 < β < 1, 0 < γ < 1. α, β, γ and The specific values ​​are set by the user according to the situation;

[0034] The identification unit is used to determine the time point when the corresponding abnormal unit was last marked as an abnormal unit, using the mark as the start timestamp and the current time as the end timestamp. Based on the start and end timestamps, the time interval is obtained and used as the comparison period. Based on the start timestamp, the fault assessment index Ggzs at that start timestamp is extracted from the historical data group. h By using the current fault assessment index Ggzs of each unit during operation... c Fault assessment index Ggzs at the start timestamp h A comparison is performed to determine whether the corresponding abnormal units require maintenance work. The specific details are as follows:

[0035] If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs exceeding the start timestamp h At this time, a maintenance order will be issued, and maintenance personnel will be arranged to carry out on-site maintenance work;

[0036] If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs not exceeding the start timestamp h At this time, maintenance instructions will not be issued.

[0037] Preferably, the effect feedback and optimization module includes an effect feedback unit and an optimization unit;

[0038] The effect feedback unit is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, and to obtain relevant feedback data. This relevant feedback data includes the number of normal units (m), the load output value of each normal unit at each time moment, the target power generation load value of each normal unit at each time moment, and the fuel consumption of each normal unit at each time moment. Through this relevant feedback data, the balance between grid load response capability and unit operating efficiency is evaluated, and after dimensionless processing, a performance feedback index Xfzs is constructed. The performance feedback index Xfzs is obtained using the following formula:

[0039]

[0040] In the formula, k = 1, 2, ..., m, m represents the number of normal generating units, Xfzs(t) represents the performance feedback index at time t, and Fsz k (t) represents the load output value of the kth normal unit at time t, Fbz k (t) represents the target power generation load of the kth normal generating unit at time t, Rxz k (t) represents the fuel consumption of the kth normal unit at time t, and ω represents the weighting coefficient.

[0041] Preferably, the optimization unit is used to adjust and optimize the load of the corresponding unit using the gradient descent method and in conjunction with the performance feedback index Xfzs, so as to obtain the load adjustment amount Ft of the corresponding unit at subsequent time points:

[0042]

[0043] In the formula, Xfzs(t) represents the performance feedback exponent at time t, and η represents the learning rate; It represents the partial derivative of the performance feedback index with respect to the load output value of the unit at time t.

[0044] A method for optimizing the operation of coal-fired power generating units based on industrial big data includes the following steps:

[0045] S1. Utilize multiple sets of monitoring instruments to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time, generate real-time data sets, and obtain historical data sets of each coal-fired power generating unit within historical time periods based on big data technology.

[0046] S2. Perform data preprocessing on the relevant data in the real-time data group, including noise removal, outlier removal, and missing value imputation. After dimensionless processing, construct the processed real-time data group.

[0047] S3. Based on the processed real-time data of relevant units within the data group and combined with the grid load demand Dfyq, analyze and determine the current start-up sequence of each unit to obtain the unit start-up priority Qyxj. Based on the value of the unit start-up priority Qyxj, determine the start-up sequence of each unit and whether there is a fault risk. If there is a fault risk, trigger the trend analysis command.

[0048] S4. Receive trend analysis instructions and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled;

[0049] S5. Feedback is generated based on the actual effects of the start-up sequence of each unit, relevant feedback data is obtained, and the balance between the grid load response capability and the unit operating efficiency is evaluated based on the relevant feedback data to construct the performance feedback index Xfzs. Based on the performance feedback index Xfzs, the load of the corresponding unit is adjusted and optimized.

[0050] This invention provides a method and system for optimizing the operation of coal-fired power generating units based on industrial big data, which has the following beneficial effects:

[0051] (1) Through multiple monitoring instruments in the data acquisition module, the system can collect the unit's operating status and equipment data in real time, forming a real-time data set. Simultaneously, combined with historical data sets, the system analyzes the long-term operating status of the units based on big data technology, comprehensively understanding the unit's operating patterns and load characteristics. This combination of real-time and historical data not only improves the completeness of data analysis but also provides reliable data support for the accuracy of subsequent optimization strategies. The start-up priority analysis module dynamically adjusts the unit start-up sequence by analyzing the real-time data set and grid load demand, obtaining the unit start-up priority. The system can quickly determine the unit start-up sequence based on the numerical value and effectively identify units with potential fault risks, further triggering trend analysis commands. This module ensures grid load response capability while reducing the blindness of start-up and shutdown decisions, improving the economic efficiency of unit operation. The fault identification module combines real-time and historical data sets to assess the unit's operating status and equipment status data for fault evaluation, calculating the current fault assessment index. By comprehensively analyzing historical trends and real-time status, the system can accurately determine whether maintenance work on the generating units is necessary, thereby enabling early prediction and timely intervention of potential faults. This function effectively reduces the risk of unplanned unit shutdowns and ensures the stability of system operation. The effect feedback and optimization module evaluates feedback data on actual operating effects and constructs a performance feedback index, realizing dynamic adjustment and optimization of unit load distribution. Based on this, the system can continuously optimize the balance between grid load response capacity and unit operating efficiency, ensuring that the units operate with the lowest fuel consumption while meeting grid demand. This closed-loop optimization mechanism allows the system to continuously adjust optimization strategies based on actual results, thereby achieving continuous improvement in operating efficiency.

[0052] (2) The priority unit dynamically calculates the starting priority Qyxj of each unit by combining the unit operating status and grid load demand in the real-time data set. It comprehensively considers the unit's availability coefficient, maximum power generation load target value, and correction constant to ensure the accuracy and robustness of the calculation. This module can quickly adjust the start-up and shutdown sequence of units according to the real-time grid load demand, prioritizing the start-up of units with high availability and strong power generation capacity, effectively improving the grid's load response capability. At the same time, it further avoids resource waste and economic decline caused by low-priority units participating in operation. The preliminary judgment unit uses a statistical mean algorithm to calculate the average starting priority of each unit in combination with historical data sets, and further compares and verifies the currently calculated unit starting priority Qyxj. If the current priority Qyxj is lower than the historical mean, the system can preliminarily judge that the unit has a fault risk and promptly trigger a trend analysis command to remove potentially faulty units from the sequence set. This mechanism achieves accurate identification of potential faults by dynamically comparing historical and current data, improving the efficiency of fault detection, preventing faulty units from participating in grid operation, and ensuring system stability. After sorting the unit priorities Qyxj, the preliminary judgment unit generates a sequence group, eliminates potentially faulty units, optimizes the unit sequence, and redetermines the start-up order of normal units based on the optimized sequence group to ensure that the system prioritizes the activation of units with good operating status and strong power generation capacity.

[0053] (3) Upon receiving the trend analysis command, the fault analysis unit combines the relevant equipment status data within the processed real-time data set and calculates the fault assessment index for each abnormal unit after dimensionless processing. Through accurate calculation of the fault assessment index, the system can quantify the degree of abnormal unit operation from multiple dimensions, significantly improving the accuracy of fault assessment and providing a scientific basis for subsequent fault identification and decision-making. The identification unit accurately records the duration of the abnormal state by marking the start and end timestamps of the abnormal units and dynamically analyzes the development trend of the fault using time intervals as comparison periods. By extracting the fault assessment index at the start timestamp from the historical data set and comparing it with the current fault assessment index, the system can dynamically judge the severity and development trend of the fault: if the current fault assessment index exceeds the assessment value at the start timestamp, it indicates that the fault is intensifying, and the system immediately triggers a maintenance command to arrange on-site maintenance work to ensure timely handling of the problem. If the current fault assessment index does not exceed the historical value, it indicates that the fault is under control, and the system temporarily does not issue a maintenance command to avoid unnecessary maintenance operations and reduce maintenance costs. The fault identification module effectively avoids resource waste and fault escalation caused by over-maintenance or maintenance delays through real-time and historical data linkage analysis.

[0054] (4) The construction of the performance feedback index Xfzs, through comprehensive analysis of load error and fuel economy, realizes the quantitative evaluation of grid load response capability and unit operating efficiency, which greatly improves the operability and evaluation accuracy of the system. Combined with the dynamic optimization unit of the gradient descent method, the system can reduce the impact of grid load fluctuations on unit operation, reduce fuel waste, and improve power generation efficiency through scientific load allocation strategies. Attached Figure Description

[0055] Figure 1 This is a block diagram of a coal-fired power generating unit operation optimization system based on industrial big data according to the present invention;

[0056] Figure 2 This is a schematic diagram of the operation optimization method for coal-fired power generating units based on industrial big data according to the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0058] Example 1

[0059] Please see Figure 1 This invention provides a coal-fired power generation unit operation optimization system based on industrial big data, including a data acquisition module, a data processing module, a start-up priority analysis module, a fault identification module, and an effect feedback and optimization module;

[0060] The data acquisition module is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments, generate real-time data sets, and acquire historical data sets of each coal-fired power generating unit within historical time periods based on big data technology.

[0061] The data processing module is used to preprocess the relevant data in the real-time data group, remove noise, remove outliers and fill in missing values, and construct the processed real-time data group after dimensionless processing.

[0062] The startup priority analysis module is used to analyze and determine the startup order of each unit based on the processed real-time data group and the grid load demand Dfyq, so as to obtain the startup priority Qyxj of the unit. Based on the value of the startup priority Qyxj, the startup order of each unit and whether there is a fault risk are determined. If there is a fault risk, a trend analysis command is triggered.

[0063] The fault identification module is used to receive trend analysis commands and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled;

[0064] The effect feedback and optimization module is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, obtain relevant feedback data, evaluate the balance between grid load response capability and unit operating efficiency based on the relevant feedback data, construct a performance feedback index Xfzs, and adjust and optimize the load of the corresponding unit based on the performance feedback index Xfzs.

[0065] During operation, this system monitors unit operation data and equipment status data in real time through the data acquisition module. Combined with historical data mining and analysis, it can grasp the dynamic changes in grid load demand (Dfyq) and unit status. Based on the start-up priority analysis module, the system can dynamically calculate the start-up priority (Qyxj) of units and perform relatively optimal start-up and shutdown scheduling based on its value. This improves the unit's responsiveness to grid load demand fluctuations, avoids the delay problems in traditional start-up and shutdown scheduling, and effectively ensures the stability of grid operation. The data processing module preprocesses the real-time data sets (including noise reduction, outlier removal, missing value imputation, and dimensionless conversion), ensuring data quality and providing accurate input for subsequent optimization analysis. Combining the processed real-time data sets with grid load demand, the start-up priority analysis module can prioritize the scheduling of units with high operating efficiency and good economic performance. By accurately calculating the load allocation of units, energy waste and unnecessary fuel consumption are avoided, thereby reducing the overall operating cost of the units and improving power generation efficiency. The fault identification module, through trend analysis commands, utilizes equipment status data from real-time and historical data sets to calculate a fault assessment index during unit operation and predict potential risks based on historical operating trends. This module not only accurately determines whether unit maintenance is required but also helps maintenance personnel develop maintenance plans in advance, preventing unplanned downtime due to sudden faults. Intelligent fault identification and prediction significantly improve unit availability and reduce downtime and maintenance costs. The performance feedback and optimization module, based on the actual operating effects of each unit's startup sequence, constructs a performance feedback index (Xfzs) to dynamically assess the balance between grid load response capability and unit operating efficiency. The system can adjust and optimize the load allocation of corresponding units based on feedback data, forming a closed-loop control process and achieving continuous improvement in start-up and shutdown scheduling and load allocation. In summary, this method, through the deep application of industrial big data technology combined with intelligent start-up priority analysis and fault prediction mechanisms, significantly improves the operating efficiency and economy of coal-fired power generating units, enhances grid load response capability, and reduces economic losses caused by fault downtime. This optimization system injects intelligent and green concepts into the traditional coal-fired power generation industry, providing strong technical support for energy management and sustainable development.

[0066] Example 2

[0067] Please refer to Figure 1 Specifically: the data acquisition module includes a real-time monitoring unit and a historical data extraction unit;

[0068] The real-time monitoring unit is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments. The relevant unit operation data includes the unit's fuel consumption per unit time Rxz, load output value Fsz, availability coefficient Kyz of the corresponding unit at each time moment, unit load fluctuation factor Fbyz, and the target value of the corresponding unit's maximum generating load Fbz. max The relevant equipment status data includes boiler pressure fluctuation factor Ybyz1 and steam pipeline pressure fluctuation factor Ybyz2; multiple monitoring instruments include laser coal flow meter, power monitoring instrument and unit performance testing instrument; the real-time data group includes relevant unit operation data and relevant equipment status data;

[0069] The historical extraction unit is used to acquire relevant unit operation data and relevant equipment status data of each coal-fired power generating unit in the industrial park during a historical period using big data technology. The historical data group includes relevant unit operation data and relevant equipment status data during a historical period.

[0070] The data processing module includes a preprocessing unit and a normalization unit;

[0071] The preprocessing unit is used to preprocess the relevant data within the real-time data group. The preprocessing includes noise removal, missing value filling, outlier removal, and data smoothing. The missing value filling methods include mean filling, median filling, interpolation filling, and regression filling.

[0072] The normalization unit is used to eliminate unit differences in the relevant data within the preprocessed real-time data group using dimensionless processing technology, so that the range of the relevant data within the preprocessed real-time data group falls within [0, 1].

[0073] In this embodiment, the real-time monitoring unit in the data acquisition module monitors unit operation data and equipment status data in real time through multiple sets of monitoring instruments (including boilers, steam pipelines, etc.), generating real-time data sets. This real-time data can comprehensively reflect the unit's immediate operating status and equipment health. Simultaneously, the historical data extraction unit extracts historical operation data and equipment status data from each unit within the industrial park using big data technology, forming historical data sets. This combination of real-time and historical data provides multi-dimensional reference for analyzing unit operating patterns, predicting trends, and optimizing operating strategies, enhancing the depth and comprehensiveness of data analysis. The preprocessing unit in the data processing module significantly improves the quality and completeness of real-time data through denoising, outlier removal, data smoothing, and missing value imputation operations. Specifically: denoising effectively eliminates random noise interference during monitoring, ensuring data accuracy. Outlier removal avoids the impact of extreme values ​​on data analysis and optimization results. Missing value imputation provides multiple imputation methods (mean imputation, median imputation, interpolation imputation, and regression imputation), flexibly adapting to the processing needs of different data types, further ensuring data completeness. Data smoothing eliminates drastic fluctuations in data, improves data continuity and trend representation, and provides stable foundational data for subsequent optimization analysis. The normalization unit in the data processing module uses dimensionless processing technology to eliminate unit differences in preprocessed real-time data sets, unifying data with different dimensions to the same range. For example, after dimensionless processing of fuel consumption per unit time and load output values, comparisons and optimization calculations can be performed under the same standard. This process eliminates the limitations of physical units on data analysis, significantly improving data comparability and the accuracy of model analysis. Through the combination of real-time monitoring and historical data extraction units, the system can comprehensively monitor the operating status and equipment condition of coal-fired power generating units in real time, and conduct in-depth analysis based on historical data, thereby providing data support for optimizing unit operation.

[0074] Example 3

[0075] Please refer to Figure 1 Specifically: the startup priority analysis module includes a running status analysis unit, a priority unit, and a preliminary judgment unit;

[0076] The operation status analysis unit is used to extract the unit-time fuel consumption Rxz and load output value Fsz of each unit from the relevant unit operation data in the processed real-time data group. Based on the unit-time fuel consumption Rxz and load output value Fsz of each unit, the economic index Jzb of each unit is calculated. Specifically, the economic index Jzb of each unit is obtained according to the following formula:

[0077]

[0078] The economic performance index Jzb for each generating unit refers to the unit's cost of generating electricity per unit time (usually expressed in yuan / kWh). It reflects the economic efficiency of the unit's operation, specifically the fuel and operating costs required to produce 1 kWh of electricity. A lower Jzb indicates lower operating costs and better economic performance, while a higher Jzb indicates higher operating costs and poorer economic performance.

[0079] The fuel consumption per unit time, Rxz, of each unit can be monitored and obtained using a laser-type coal flow meter.

[0080] The load output value Fsz refers to the generating power of the unit, which can be obtained through power monitoring instruments;

[0081] Based on the economic indicators Jzb and grid load demand Dfyq of each generating unit, the target power generation load value Fbz for each generating unit in different monitoring periods is calculated. Specifically, the target power generation load value Fbz for each generating unit in different monitoring periods is obtained according to the following formula:

[0082]

[0083] In the formula, Fbz(t) represents the target power generation load of the corresponding unit at time t, Dfyq(t) represents the grid load demand at time t, and Jzb -1 This represents the economic weight of the corresponding unit, which is the reciprocal of the economic index Jzb of the corresponding unit; n represents the number of units, i = 1, 2, 3, ..., n.

[0084] At any given time, Dfyq monitors the real-time load demand of the entire power grid through the power grid monitoring system, including the changing trend of load demand and peak-valley load.

[0085] In this embodiment, the operation status analysis unit in the priority analysis module can extract the unit-time fuel consumption and load output value of each unit from the real-time data set, and calculate the economic index, i.e., the unit-time power generation cost, from both. The economic index precisely quantifies the operating cost of each unit, reflecting the economic differences among different units. By prioritizing units with lower operating costs and better economic performance, the system achieves a scientific ranking of unit start-up and shutdown priorities, reducing the adverse effects of indiscriminate start-up and shutdown on fuel consumption and operating efficiency. The system analyzes the economic index and the real-time load demand of the power grid, and calculates the target power generation load value for each unit according to a formula to ensure accurate allocation of power grid load demand. Specifically, the system allocates load according to the economic weight of each unit; units with lower economic indicators (lower operating costs) will be prioritized for higher target power generation load values. This load allocation mechanism significantly improves the overall economic efficiency of the power generation system, reduces fuel consumption and power generation costs, and optimizes the dynamic response capability of the power grid load. The optimized allocation of multi-unit load targets not only meets the power grid demand but also avoids the problem of excessive load or idle operation of individual units, improving the utilization efficiency of unit resources.

[0086] Example 4

[0087] Please refer to Figure 1 Specifically: the priority unit is used to analyze and determine the current startup sequence of each unit based on the processed real-time data group's relevant unit operating data and in conjunction with the current grid load demand, in order to obtain the unit startup priority Qyxj. The unit startup priority Qyxj is specifically obtained through the following formula:

[0088]

[0089] In the formula, Qyxj(t) represents the unit startup priority at time t, Kyz(t) represents the availability coefficient of the corresponding unit at time t, and Fbz... max This represents the target value of the maximum generating load of the corresponding unit, and ∈ represents a correction constant, a constant used to avoid division by zero errors;

[0090] The target value of the maximum generating load of the corresponding unit is Fbz max The output of the unit under rated conditions can be tested using unit performance testing instruments to obtain the maximum load output value of the unit.

[0091] The availability coefficient Kyz(t) of the corresponding unit at time t is determined according to the operating status of the unit, which includes whether it is under maintenance, whether a fault has occurred, and whether it is in standby status. When the unit is in standby status, the corresponding availability coefficient = 1; if the unit is not in standby status, the corresponding availability coefficient = 0.

[0092] The preliminary judgment unit is used to obtain the unit startup priority Qyxj of each unit according to the method of obtaining the unit startup priority Qyxj in the priority unit, and sort them to generate a sequence group; based on the historical data group, it determines the unit startup priority Qyxj of the corresponding unit within the historical period, and obtains the average unit startup priority Qyxj of the corresponding unit by combining statistical mean calculation algorithm. avg By comparing the current unit's startup priority Qyxj with the average unit startup priority Qyxj of the corresponding units... avg A comparison will be conducted to determine the startup sequence of the corresponding units and whether there is a risk of failure. The specific preliminary assessment is as follows:

[0093] If the current unit's startup priority Qyxj is greater than or equal to the corresponding unit's average startup priority Qyxj avg If it is initially determined that there is no risk of failure in the corresponding unit, then the trend analysis command will not be triggered externally, the corresponding unit will be kept in the sequence group, and the corresponding unit will be marked as a normal unit.

[0094] If the current unit's startup priority Qyxj is less than the average unit startup priority Qyxj of the corresponding unit avg When it is initially determined that the corresponding unit has a risk of failure, a trend analysis command is triggered to remove the corresponding unit from the sequence group and mark it as an abnormal unit.

[0095] Based on the preliminary assessment, the normal generating units are counted and reordered to generate an optimized sequence group. Based on the optimized sequence group, the startup order of each normal generating unit is determined.

[0096] In this embodiment, the priority unit dynamically calculates the unit startup priority Qyxj of each unit by combining key parameters such as the availability coefficient and maximum load output value of the units in the real-time data group with the grid load demand. This calculation method ensures that units with good status and high operating economy are prioritized for startup while meeting the grid load demand. Through statistical analysis of historical data groups, the system obtains the average startup priority of each unit and accurately identifies whether the current startup status of the unit meets expectations by comparing the current priority with the historical average priority, thereby further optimizing the startup sequence of the units. The preliminary judgment unit quickly identifies abnormal status of the units by calculating the startup priority Qyxj of the units in real time and comparing it with the historical average priority: when the startup priority Qyxj is lower than the average startup priority, it is preliminarily determined that the unit has a fault risk and a trend analysis command is triggered in time to further confirm the source of the problem; when the startup priority Qyxj is higher than or equal to the average startup priority, the unit is determined to be in normal status, avoiding unnecessary maintenance or interruption. This mechanism realizes early warning of potential faults, effectively reduces the risk of unplanned equipment downtime, and extends the service life of equipment. Based on the initial assessment, the system automatically eliminates abnormal generating units and reorders the normal units, generating an optimized unit startup sequence. This optimized sequence further enhances the grid load response capability, ensuring that economically efficient and stable units are prioritized for startup, avoiding the commissioning of inefficient or risky units, and reducing fuel consumption and operating costs.

[0097] Example 5

[0098] Please refer to Figure 1 Specifically: the fault identification module includes a fault analysis unit and an identification unit;

[0099] The fault analysis unit, upon receiving a trend analysis command, analyzes the current fault assessment index Ggzs of each abnormal unit during operation based on the processed real-time data group's relevant equipment status data and after dimensionless processing. c The current fault assessment index Ggzs c Obtain it using the following formula:

[0100]

[0101] In the formula, ΔQyxj represents the unit start-up priority difference, Ybyz1 represents the boiler pressure fluctuation factor, Ybyz2 represents the steam pipeline pressure fluctuation factor, Fbyz represents the unit load fluctuation factor, and α, β, γ and All represent weight values, where 0 < α < 1, 0 < β < 1, 0 < γ < 1. α, β, γ and The specific values ​​are set by the user according to the situation;

[0102] The aforementioned unit start-up priority difference ΔQyxj refers to the difference between the current start-up priority of the corresponding unit and the start-up priority obtained from the previous monitoring.

[0103] The boiler pressure fluctuation factor Ybyz1 and the steam pipeline pressure fluctuation factor Ybyz2 will be calculated based on the standard deviation. The standard deviation reflects the dispersion of the pressure signal, that is, the deviation of the pressure value from its average value.

[0104] The identification unit is used to determine the time point when the corresponding abnormal unit was last marked as an abnormal unit, using the mark as the start timestamp and the current time as the end timestamp. Based on the start and end timestamps, the time interval is obtained and used as the comparison period. Based on the start timestamp, the fault assessment index Ggzs at that start timestamp is extracted from the historical data group. h By using the current fault assessment index Ggzs of each unit during operation... c Fault assessment index Ggzs at the start timestamp h A comparison is performed to determine whether the corresponding abnormal units require maintenance work. The specific details are as follows:

[0105] If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs exceeding the start timestamp h At this time, a maintenance order will be issued, and maintenance personnel will be arranged to carry out on-site maintenance work;

[0106] If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs not exceeding the start timestamp h At this time, maintenance instructions will not be issued.

[0107] In this embodiment, after receiving the trend analysis command, the fault analysis unit utilizes the equipment status data in the real-time data group and eliminates data dimension differences through dimensionless processing to ensure that fault characteristic parameters of different natures can be analyzed under the same standard. The current fault assessment index is calculated using a formula, combining multi-dimensional data such as the unit start-up priority difference, boiler pressure fluctuation factor, steam pipeline pressure fluctuation factor, and unit load fluctuation factor, and assigning different weights to each item to comprehensively assess the current fault risk of the unit. This fault assessment method comprehensively considers multiple core parameters affecting the unit's operational stability, avoiding misjudgments or omissions that may result from judging a single parameter, achieving quantitative analysis of the fault risk of abnormal units, and significantly improving the scientificity and accuracy of fault assessment. The identification unit dynamically tracks the fault change trend of abnormal units by combining the current time point and historical data. Specifically, the time point when the abnormal unit was last marked as abnormal is used as the starting timestamp, and the current time is marked as the ending timestamp. The time interval is calculated, historical data within this time period is extracted, and by comparing the current fault assessment index with the fault assessment index at the starting timestamp, the development trend of the unit's fault risk is accurately determined. If the fault assessment index continues to increase and exceeds historical values, the system immediately issues a maintenance command to ensure that the fault can be addressed in a timely manner. If the fault assessment index does not exceed historical values, the system suspends the maintenance command to avoid unnecessary maintenance work. This dynamic fault analysis method based on time intervals can significantly reduce the waste of resources caused by over-maintenance, while ensuring that potential faults can be addressed in a timely manner before the problem worsens.

[0108] Example 6

[0109] Please refer to Figure 1 Specifically: the effect feedback and optimization module includes an effect feedback unit and an optimization unit;

[0110] The effect feedback unit is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, and to obtain relevant feedback data. This relevant feedback data includes the number of normal units (m), the load output value of each normal unit at each time moment, the target power generation load value of each normal unit at each time moment, and the fuel consumption of each normal unit at each time moment. Through this relevant feedback data, the balance between grid load response capability and unit operating efficiency is evaluated, and after dimensionless processing, a performance feedback index Xfzs is constructed. The performance feedback index Xfzs is obtained using the following formula:

[0111]

[0112] In the formula, k = 1, 2, ..., m, m represents the number of normal generating units, Xfzs(t) represents the performance feedback index at time t, and Fsz k(t) represents the load output value of the kth normal unit at time t, Fbz k (t) represents the target power generation load of the kth normal generating unit at time t, Rxz k (t) represents the fuel consumption of the k-th normal generating unit at time t, and ω represents the weighting coefficient used to balance the relationship between load error and fuel consumption; |Fsz k (t)-Fbz k (t) represents the deviation between the actual load output and the target load; It reflects fuel economy; the smaller the value, the less fuel is consumed per unit of electricity generated, and the better the economy.

[0113] The optimization unit is used to adjust and optimize the load of the corresponding unit using the gradient descent method and in conjunction with the performance feedback index Xfzs, so as to obtain the load adjustment amount Ft of the corresponding unit at each subsequent time.

[0114]

[0115] In the formula, Xfzs(t) represents the performance feedback exponent at time t, and η represents the learning rate, which is used to control the magnitude of the adjustment. It represents the partial derivative of the performance feedback index with respect to the load output value of the unit at time t.

[0116] In this embodiment, the performance feedback unit comprehensively evaluates the balance between grid load response capability and unit operating efficiency by real-time acquisition and dimensionless processing of the operating data of each normal generating unit (including load output value, target power generation load value, and fuel consumption). The performance feedback index Xfzs, constructed using a formula, comprehensively considers the deviation between the unit's load output and the target load, as well as fuel economy (fuel consumption per unit of power generation), providing a scientific quantitative standard for optimizing unit operation. This index not only reflects the current operating status of the unit but also helps analyze the efficiency of the load allocation strategy, providing important input for the gradient adjustment of the optimization unit. By calculating the partial derivative of the performance feedback index with respect to the unit's load output value, key variables affecting operating efficiency are accurately located. The adjustment amplitude is controlled by the learning rate to avoid instability caused by over-adjustment. Through the gradient descent algorithm, the load allocation is gradually optimized. The system can dynamically adjust the unit's load Ft at subsequent times, ensuring that the load allocation meets grid demand while achieving optimal economy, significantly improving the adjustment efficiency and accuracy of load allocation. The effect feedback unit and the optimization unit form a closed-loop feedback mechanism. Through real-time calculation of the performance feedback index Xfzs and dynamic adjustment using the gradient descent method, the system ensures that it can continuously optimize the load allocation strategy based on operational performance. This closed-loop mechanism effectively avoids the limitations of static parameters in traditional load allocation strategies, enabling the system to flexibly respond to grid load fluctuations and dynamic changes in unit operating status, thus improving overall operational stability and economy. This invention, through the construction of the performance feedback index Xfzs, achieves the scientific quantification of unit operating efficiency and grid load response capability, and uses this as a basis for dynamic optimization of unit load allocation, significantly improving the economy and flexibility of coal-fired power generating units. The gradient descent optimization strategy can quickly respond to changes in operating status and dynamically adjust unit load allocation, avoiding over-adjustment or delayed adjustment problems in traditional strategies, and enhancing the accuracy and flexibility of load allocation.

[0117] Example 7

[0118] Please refer to Figure 2 Specifically: A method for optimizing the operation of coal-fired power generating units based on industrial big data includes the following steps:

[0119] S1. Utilize multiple sets of monitoring instruments to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time, generate real-time data sets, and obtain historical data sets of each coal-fired power generating unit within historical time periods based on big data technology.

[0120] S2. Perform data preprocessing on the relevant data in the real-time data group, including noise removal, outlier removal, and missing value imputation. After dimensionless processing, construct the processed real-time data group.

[0121] S3. Based on the processed real-time data of relevant units within the data group and combined with the grid load demand Dfyq, analyze and determine the current start-up sequence of each unit to obtain the unit start-up priority Qyxj. Based on the value of the unit start-up priority Qyxj, determine the start-up sequence of each unit and whether there is a fault risk. If there is a fault risk, trigger the trend analysis command.

[0122] S4. Receive trend analysis instructions and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled;

[0123] S5. Feedback is generated based on the actual effects of the start-up sequence of each unit, relevant feedback data is obtained, and the balance between the grid load response capability and the unit operating efficiency is evaluated based on the relevant feedback data to construct the performance feedback index Xfzs. Based on the performance feedback index Xfzs, the load of the corresponding unit is adjusted and optimized.

[0124] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A coal-fired power generating unit operation optimization system based on industrial big data, characterized in that: It includes a data acquisition module, a data processing module, a startup priority analysis module, a fault identification module, and an effect feedback and optimization module; The data acquisition module is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments, generate real-time data sets, and acquire historical data sets of each coal-fired power generating unit within historical time periods based on big data technology. The data processing module is used to preprocess the relevant data in the real-time data group, remove noise, remove outliers and fill in missing values, and construct the processed real-time data group after dimensionless processing. The startup priority analysis module is used to analyze and determine the startup order of each unit based on the processed real-time data group and the grid load demand Dfyq, so as to obtain the startup priority Qyxj of the unit. Based on the value of the startup priority Qyxj, the startup order of each unit and whether there is a fault risk are determined. If there is a fault risk, a trend analysis command is triggered. The fault identification module is used to receive trend analysis commands and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled; The effect feedback and optimization module is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, obtain relevant feedback data, evaluate the balance between grid load response capability and unit operating efficiency based on the relevant feedback data, construct a performance feedback index Xfzs, and adjust and optimize the load of the corresponding unit based on the performance feedback index Xfzs.

2. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 1, characterized in that: The data acquisition module includes a real-time monitoring unit and a historical extraction unit; The real-time monitoring unit is used to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time using multiple sets of monitoring instruments. The relevant unit operation data includes the unit's fuel consumption per unit time Rxz, load output value Fsz, availability coefficient Kyz of the corresponding unit at each time moment, unit load fluctuation factor Fbyz, and the target value of the corresponding unit's maximum generating load Fbz. max The relevant equipment status data includes boiler pressure fluctuation factor Ybyz1 and steam pipeline pressure fluctuation factor Ybyz2; multiple monitoring instruments include laser coal flow meter, power monitoring instrument and unit performance testing instrument; the real-time data group includes relevant unit operation data and relevant equipment status data; The historical extraction unit is used to acquire relevant unit operation data and relevant equipment status data of each coal-fired power generating unit in the industrial park during a historical period using big data technology. The historical data group includes relevant unit operation data and relevant equipment status data during a historical period.

3. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 2, characterized in that: The data processing module includes a preprocessing unit and a normalization unit; The preprocessing unit is used to preprocess the relevant data within the real-time data group. The preprocessing includes noise removal, missing value filling, outlier removal, and data smoothing. The missing value filling methods include mean filling, median filling, interpolation filling, and regression filling. The normalization unit is used to eliminate unit differences in the relevant data within the preprocessed real-time data group using dimensionless processing technology, so that the range of the relevant data within the preprocessed real-time data group falls within [0, 1].

4. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 3, characterized in that: The startup priority analysis module includes a running status analysis unit, a priority unit, and a preliminary judgment unit; The operation status analysis unit is used to extract the unit-time fuel consumption Rxz and load output value Fsz of each unit from the relevant unit operation data in the processed real-time data group. Based on the unit-time fuel consumption Rxz and load output value Fsz of each unit, the economic index Jzb of each unit is calculated. Specifically, the economic index Jzb of each unit is obtained according to the following formula: Based on the economic indicators Jzb and grid load demand Dfyq of each generating unit, the target power generation load value Fbz for each generating unit in different monitoring periods is calculated. Specifically, the target power generation load value Fbz for each generating unit in different monitoring periods is obtained according to the following formula: In the formula, Fbz(t) represents the target power generation load of the corresponding unit at time t, Dfyq(t) represents the grid load demand at time t, and Jzb -1 This represents the economic weight of the corresponding unit; n represents the number of units, i = 1, 2, 3, ..., n.

5. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 4, characterized in that: The priority unit is used to analyze and determine the current startup sequence of each unit based on the processed real-time data group and the relevant unit operation data, combined with the current grid load demand, in order to obtain the unit startup priority Qyxj. The unit startup priority Qyxj is specifically obtained through the following formula: In the formula, Qyxj(t) represents the unit startup priority at time t, Kyz(t) represents the availability coefficient of the corresponding unit at time t, and Fbz... max denoted as the target value of the maximum generating load of the corresponding unit, and ∈ represents the correction constant.

6. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 5, characterized in that: The preliminary judgment unit is used to obtain the unit startup priority Qyxj of each unit according to the method of obtaining the unit startup priority Qyxj in the priority unit, and sort them to generate a sequence group; based on the historical data group, it determines the unit startup priority Qyxj of the corresponding unit within the historical period, and obtains the average unit startup priority Qyxj of the corresponding unit by combining statistical mean calculation algorithm. avg By comparing the current unit's startup priority Qyxj with the average unit startup priority Qyxj of the corresponding units... avg A comparison will be conducted to determine the startup sequence of the corresponding units and whether there is a risk of failure. The specific preliminary assessment is as follows: If the current unit's startup priority Qyxj is greater than or equal to the corresponding unit's average startup priority Qyxj avg If it is initially determined that there is no risk of failure in the corresponding unit, then the trend analysis command will not be triggered externally, the corresponding unit will be kept in the sequence group, and the corresponding unit will be marked as a normal unit. If the current unit's startup priority Qyxj is less than the average unit startup priority Qyxj of the corresponding unit avg When it is initially determined that the corresponding unit has a risk of failure, a trend analysis command is triggered to remove the corresponding unit from the sequence group and mark it as an abnormal unit. Based on the preliminary assessment, the normal generating units are counted and reordered to generate an optimized sequence group. Based on the optimized sequence group, the startup order of each normal generating unit is determined.

7. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 3, characterized in that: The fault identification module includes a fault analysis unit and an identification unit; The fault analysis unit, upon receiving a trend analysis command, analyzes the current fault assessment index Ggzs of each abnormal unit during operation based on the processed real-time data group's relevant equipment status data and after dimensionless processing. c The current fault assessment index Ggzs c Obtain it using the following formula: In the formula, ΔQyxj represents the unit start-up priority difference, Ybyz1 represents the boiler pressure fluctuation factor, Ybyz2 represents the steam pipeline pressure fluctuation factor, Fbyz represents the unit load fluctuation factor, and α, β, γ and All represent weight values, where 0 < α < 1, 0 < β < 1, 0 < γ < 1. α, β, γ and The specific values ​​are set by the user according to the situation; The identification unit is used to determine the time point when the corresponding abnormal unit was last marked as an abnormal unit, using the mark as the start timestamp and the current time as the end timestamp. Based on the start and end timestamps, the time interval is obtained and used as the comparison period. Based on the start timestamp, the fault assessment index Ggzs at that start timestamp is extracted from the historical data group. h By using the current fault assessment index Ggzs of each unit during operation... c Fault assessment index Ggzs at the start timestamp h A comparison is performed to determine whether the corresponding abnormal units require maintenance work. The specific details are as follows: If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs exceeding the start timestamp h At this time, a maintenance order will be issued, and maintenance personnel will be arranged to carry out on-site maintenance work; If the current fault assessment index Ggzs of each unit during operation c Fault assessment index Ggzs not exceeding the start timestamp h At this time, maintenance instructions will not be issued.

8. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 1, characterized in that: The effect feedback and optimization module includes an effect feedback unit and an optimization unit; The effect feedback unit is used to provide feedback based on the actual effect formed by the start-up sequence of each unit, and to obtain relevant feedback data. This relevant feedback data includes the number of normal units (m), the load output value of each normal unit at each time moment, the target power generation load value of each normal unit at each time moment, and the fuel consumption of each normal unit at each time moment. Through this relevant feedback data, the balance between grid load response capability and unit operating efficiency is evaluated, and after dimensionless processing, a performance feedback index Xfzs is constructed. The performance feedback index Xfzs is obtained using the following formula: In the formula, k = 1, 2, ..., m, m represents the number of normal generating units, Xfzs(t) represents the performance feedback index at time t, and Fsz k (t) represents the load output value of the kth normal unit at time t, Fbz k (t) represents the target power generation load of the kth normal generating unit at time t, Rxz k (t) represents the fuel consumption of the kth normal unit at time t, and ω represents the weighting coefficient.

9. The coal-fired power generating unit operation optimization system based on industrial big data according to claim 8, characterized in that: The optimization unit is used to adjust and optimize the load of the corresponding unit using the gradient descent method and in conjunction with the performance feedback index Xfzs, so as to obtain the load adjustment amount Ft of the corresponding unit at each subsequent time. In the formula, Xfzs(t) represents the performance feedback exponent at time t, and η represents the learning rate; It represents the partial derivative of the performance feedback index with respect to the load output value of the unit at time t.

10. A method for optimizing the operation of coal-fired power generating units based on industrial big data, used to implement the coal-fired power generating unit operation optimization system based on industrial big data as described in any one of claims 1 to 9, characterized in that: Includes the following steps, S1. Utilize multiple sets of monitoring instruments to monitor the relevant unit operation data and related equipment status data of each coal-fired power generating unit in real time, generate real-time data sets, and obtain historical data sets of each coal-fired power generating unit within historical time periods based on big data technology. S2. Perform data preprocessing on the relevant data in the real-time data group, including noise removal, outlier removal, and missing value imputation. After dimensionless processing, construct the processed real-time data group. S3. Based on the processed real-time data of relevant units within the data group and combined with the grid load demand Dfyq, analyze and determine the current start-up sequence of each unit to obtain the unit start-up priority Qyxj. Based on the value of the unit start-up priority Qyxj, determine the start-up sequence of each unit and whether there is a fault risk. If there is a fault risk, trigger the trend analysis command. S4. Receive trend analysis instructions and, based on the processed real-time data group's relevant equipment status data, analyze the current fault assessment index Ggzs of each unit during operation. c And by combining historical data sets, it is determined whether the corresponding units need to be overhauled; S5. Feedback is generated based on the actual effects of the start-up sequence of each unit, relevant feedback data is obtained, and the balance between the grid load response capability and the unit operating efficiency is evaluated based on the relevant feedback data to construct the performance feedback index Xfzs. Based on the performance feedback index Xfzs, the load of the corresponding unit is adjusted and optimized.

Images