Intelligent scheduling control system and method for garbage power plant based on big data analysis

Abstract

The present application relates to power generation control technical field, specifically to a kind of intelligent scheduling control system and method of garbage power plant based on big data analysis;Method includes: setting up prediction time period, collection last prediction time period's garbage power plant multidimensional operation data, and extract key influence characteristics from multidimensional operation data;Garbage incineration efficiency, equipment failure early warning, power grid load matching data are respectively predicted according to key influence characteristics in current prediction time period, and dynamically adjust prediction time period;Real-time analysis prediction data, and carry out equipment real-time scheduling;System includes: multidimensional key feature extraction module, load dynamic matching scheduling module, real-time analysis scheduling module;Through above-mentioned mode, accurate extraction characteristics are realized, and load dynamic matching and real-time scheduling are carried out, so as to improve power plant operation efficiency.

Description

Technical Field

[0001] This invention relates to the field of power generation control technology, and in particular to an intelligent dispatch control system and method for waste-to-energy plants based on big data analysis. Background Technology

[0002] With the acceleration of urbanization, the amount of urban domestic waste has increased significantly. Waste incineration power generation, as a waste treatment method that reduces volume, renders harmless, and recovers resources, has been widely used.

[0003] Waste-to-energy plants need to balance waste treatment efficiency, equipment stability, and grid load demand during operation. However, there are three major problems: First, the composition of waste fluctuates greatly, and traditional scheduling relies on manual experience, which cannot accurately extract key characteristics that affect incineration efficiency. Second, the grid load changes in real time, and the existing scheduling method has a slow response and low load matching degree, resulting in energy waste.

[0004] Therefore, it is essential to propose an intelligent dispatch control system and method for waste-to-energy plants that accurately extracts features and performs dynamic load matching and real-time scheduling to improve the operating efficiency of power plants. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent scheduling and control system and method for waste-to-energy plants based on big data analysis, which aims to accurately extract features and perform dynamic load matching and real-time scheduling, thereby improving the operating efficiency of the power plant.

[0006] To achieve the above objectives, this invention employs an intelligent scheduling and control method for waste-to-energy plants based on big data analysis, comprising the following steps: Set a forecast period, collect multi-dimensional operational data of the waste-to-energy plant from the previous forecast period, and extract key influencing features from the multi-dimensional operational data; Based on key influencing characteristics, predict the waste incineration efficiency, equipment failure warning, and power grid load matching data for the current forecast period, and dynamically adjust the forecast period. Real-time analysis and prediction of data, and real-time scheduling of equipment.

[0007] Among the steps, the following steps are involved: setting a prediction time period, collecting multi-dimensional operational data of the waste-to-energy plant from the previous prediction time period, and extracting key influencing features from the multi-dimensional operational data: Obtain data on the waste feeding cycle of waste-to-energy plants and the update frequency of grid load data, and establish a prediction time period based on the obtained data; Collect multi-dimensional operational data from the previous forecast period and preprocess the multi-dimensional operational data; the multi-dimensional operational data includes data on waste characteristics, equipment operation, environment and power grid. Extract key impact features from preprocessed multi-dimensional runtime data.

[0008] The process of collecting multi-dimensional operational data from the previous prediction period and preprocessing this data, including data on waste characteristics, equipment operation, and environmental and power grid dimensions, involves the following steps: Remove missing, outlier, and duplicate values ​​from the data; Missing values ​​are filled with the average of historical data within the same time period, and outliers are identified and removed by comparing with the normal operating range of the equipment. Duplicate values ​​are removed based on the collection timestamp; Data from different sources and in different formats are standardized and transformed into structured data.

[0009] Following the step of extracting key impact features from the preprocessed multi-dimensional runtime data: Explore the relationships between various features to form a set of key influencing features.

[0010] Among them, the steps of predicting waste incineration efficiency, equipment fault warning, and power grid load matching data for the current prediction period based on key influencing characteristics, and dynamically adjusting the prediction period: Predict waste incineration efficiency, equipment failure warnings, and power grid load matching data for the current forecast period; Preset deviation thresholds are used to dynamically adjust the length of the next prediction period based on incineration efficiency prediction deviation, equipment fault warning, and grid load matching.

[0011] Among the steps involved in predicting waste incineration efficiency, equipment fault warnings, and grid load matching data for the current forecast period: Based on the characteristics of waste and the operating parameters of the incinerator in the key influencing features, predict the waste incineration efficiency; Based on the changing trends of equipment operating parameters, early warning of equipment failure can be issued. Match the grid load based on grid load data and generator power characteristics.

[0012] Among them, in the steps of dynamically adjusting the length of the next prediction period based on the prediction deviation of incineration efficiency, equipment fault early warning, and grid load matching, respectively, within the preset deviation threshold: Establish a first deviation value and a second deviation value for incineration efficiency. Compare the deviation between the predicted incineration efficiency value for the current time period and the actual value for the previous time period, the first deviation value for incineration efficiency, and the second deviation value for incineration efficiency. Adjust the length of the next prediction time period based on the comparison results.

[0013] Among them, in the steps of dynamically adjusting the length of the next prediction period based on the prediction deviation of incineration efficiency, equipment fault early warning, and grid load matching, respectively, within the preset deviation threshold: Establish a first probability value, a second probability value, and a third probability value for equipment failure. Compare the current time period's core equipment failure probability, the first probability value, the second probability value, and the third probability value with these values, and adjust the length of the next prediction time period based on the comparison results.

[0014] Among them, in the steps of dynamically adjusting the length of the next prediction period based on the prediction deviation of incineration efficiency, equipment fault early warning, and grid load matching, respectively, within the preset deviation threshold: Establish a first load matching interval and a second load matching interval. Compare the load matching degree of the current time period with the first load matching interval and the second load matching interval. Adjust the length of the next forecast time period based on the comparison results.

[0015] This invention also provides an intelligent dispatch and control system for waste-to-energy plants based on big data analysis, including a multi-dimensional key feature extraction module, a load dynamic matching dispatch module, and a real-time analysis dispatch module; wherein: The multi-dimensional key feature extraction module is used to set a prediction time period, collect multi-dimensional operation data of the waste-to-energy plant in the previous prediction time period, and extract key influencing features from the multi-dimensional operation data. The load dynamic matching and scheduling module is used to predict the waste incineration efficiency, equipment fault warning, and power grid load matching data for the current prediction period based on key influencing characteristics, and to dynamically adjust the prediction period. The real-time analysis and scheduling module is used to analyze and predict data in real time and to perform real-time equipment scheduling.

[0016] This invention discloses an intelligent scheduling and control system and method for waste-to-energy plants based on big data analysis. The system employs a multi-dimensional key feature extraction module, a load dynamic matching scheduling module, and a real-time analysis scheduling module to perform the following steps: establishing a prediction time period; collecting multi-dimensional operational data of the waste-to-energy plant from the previous prediction time period; extracting key influencing features from the multi-dimensional operational data; predicting waste incineration efficiency, equipment fault warnings, and grid load matching data for the current prediction time period based on the key influencing features, and dynamically adjusting the prediction time period; analyzing the prediction data in real time and performing real-time equipment scheduling; through the above methods, accurate feature extraction and dynamic load matching and real-time scheduling are achieved, thereby improving the operating efficiency of the power plant. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the intelligent scheduling and control method for waste-to-energy plants based on big data analysis according to the present invention.

[0019] Figure 2 This is a flowchart of steps S100 of the present invention.

[0020] Figure 3 This is a flowchart of steps S200 of the present invention.

[0021] Figure 4 This is a flowchart of steps S300 of the present invention.

[0022] Figure 5 This is a schematic diagram of the intelligent scheduling and control system for waste-to-energy plants based on big data analysis, as described in this invention.

[0023] Figure 6 This is a schematic diagram of the electronic device of the present invention.

[0024] 401 - Multi-dimensional key feature extraction module, 402 - Load dynamic matching and scheduling module, 403 - Real-time analysis and scheduling module. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0026] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0027] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0028] Please see Figures 1-4 This invention provides an intelligent scheduling and control method for waste-to-energy plants based on big data analysis, comprising the following steps: S100: Set a prediction time period, collect multi-dimensional operation data of the waste-to-energy plant in the previous prediction time period, and extract key influencing features from the multi-dimensional operation data.

[0029] In this implementation, a prediction time period is established, multi-dimensional operational data of the waste-to-energy plant for the previous prediction time period is collected, and key influencing features are extracted from the multi-dimensional operational data. The specific process is as follows: S101: Obtain data on the waste feeding cycle of the waste-to-energy plant and the update frequency of grid load data, and establish a prediction time period based on the obtained data; S102: Collect multi-dimensional operational data from the previous forecast period and preprocess the multi-dimensional operational data; the multi-dimensional operational data includes data on waste characteristics, equipment operation, and environment and power grid. S103: Extract key impact features from the preprocessed multi-dimensional running data, and explore the correlation between the features to form a key impact feature set.

[0030] In the above process, a prediction time period is set: combining the waste feeding cycle of the waste-to-energy plant (usually one batch of waste is fed per hour) and the update frequency of the power grid load data (updated once every 15 to 30 minutes), the basic prediction time period is set to 1 hour; at the same time, flexible adjustment space is reserved, which can be dynamically shortened or extended according to the accuracy of the prediction data, with a minimum of 30 minutes and a maximum of 2 hours.

[0031] Multi-dimensional operational data is collected for the previous forecast period: From the perspective of waste characteristics, the types of waste (such as the proportion of kitchen waste, plastic, paper, etc.), moisture content, and calorific value are collected from the previous period through waste sorting equipment, moisture detectors, and calorific value analyzers, and are recorded once every 10 minutes and the average value is summarized; From the perspective of equipment operation, the incinerator temperature, pressure, turbine speed, generator output power, fan air volume, and water pump flow are collected once per second through the corresponding sensors, and the average value is calculated in 5-minute units; From the perspective of environment and power grid, the concentration of pollutants in flue gas, temperature and humidity of the plant area, and real-time load data of the power grid are collected, and are obtained through flue gas analyzers, environmental sensors, and the power grid dispatch center interface, respectively. The pollutant concentration and environmental data are recorded once every 5 minutes, and the power grid load data is collected synchronously according to the power grid update frequency.

[0032] The collected multi-dimensional operational data is preprocessed to remove missing values, outliers, and duplicates. Missing values ​​are filled with the average value of historical data in the same time period, outliers are identified and removed by comparing with the normal operating range of the equipment, and duplicates are deduplicated based on the collection timestamp. Then, data from different sources and in different formats are unified into a structured data that is easy to analyze.

[0033] Feature selection: The random forest algorithm is used to sort the features of the original data by importance, and redundant features (such as features whose influence on incineration efficiency is less than 5%) are removed. The top 8 high-impact features are retained, including: average calorific value of waste, average temperature of incinerator, average speed of steam turbine, average power of generator, average real-time load of power grid, moisture content of waste, pressure of incinerator, and concentration of nitrogen oxides in flue gas.

[0034] Feature fusion: Based on the temporal characteristics of equipment operation data, a convolutional neural network (CNN) is used to fuse 5-minute data sequences of incinerator temperature and turbine speed to extract the "temperature-speed synchronous change trend" feature (such as the corresponding increase in speed when the temperature increases by 50°C); based on the correlation between waste characteristics and incineration efficiency, Pearson correlation analysis is used to extract the "waste calorific value-incineration efficiency coupling coefficient" feature (a strong correlation feature with an absolute value of correlation coefficient ≥ 0.8).

[0035] Feature verification: The extracted key features are substituted into the historical database (operational data of the past year) for verification. The proportion of the variance explained by the features for incineration efficiency, equipment failure and load matching is calculated to ensure that the proportion of the variance explained by the core features is ≥90%, and finally the key impact feature set of the previous prediction period is formed.

[0036] S200: Based on key influencing characteristics, predict waste incineration efficiency, equipment fault warning, and power grid load matching data for the current forecast period, and dynamically adjust the forecast period.

[0037] In this embodiment, waste incineration efficiency, equipment fault warning, and power grid load matching data are predicted based on key influencing characteristics for the current prediction period, and the prediction period is dynamically adjusted. The specific process is as follows: S201: Predict waste incineration efficiency based on waste characteristics and incinerator operating parameters in the key influencing features; S202: Provide early warning of equipment malfunctions based on the changing trends of equipment operating parameters; S203: Match the grid load based on grid load data and generator power characteristics; S204: Establish a first deviation value and a second deviation value for incineration efficiency, compare the deviation of the predicted incineration efficiency value for the current time period with the actual value for the previous time period, the first deviation value for incineration efficiency, and the second deviation value for incineration efficiency, and adjust the length of the next prediction time period based on the comparison results; S205: Establish a first probability value, a second probability value, and a third probability value for equipment failure. Compare the current time period's core equipment failure probability, the first probability value, the second probability value, and the third probability value with these values. Adjust the length of the next prediction time period based on the comparison results. S206: Establish a first load matching interval and a second load matching interval, compare the load matching degree of the current time period with the first load matching interval and the second load matching interval, and adjust the length of the next forecast time period based on the comparison results.

[0038] In the above process, waste incineration efficiency prediction is achieved by constructing a prediction model using a Long Short-Term Memory (LSTM) network. The input layer consists of four key features: average calorific value of waste, average incinerator temperature, waste moisture content, and incinerator pressure. The output layer is the waste incineration efficiency for the current prediction period. The model is trained using historical data from the past six months (4320 sets of data), with 70% used for training and 30% for validation. By adjusting the number of hidden layer nodes (64) and the learning rate (0.001), the prediction error is controlled within 3%. For example, if the average calorific value of waste in the previous period was 2200 kJ / kg and the average incinerator temperature was 950℃, the predicted incineration efficiency for the current period would be 91%.

[0039] Equipment Fault Early Warning and Prediction: An early warning model is constructed using the Gradient Boosting Tree (XGBoost) algorithm. The input layer consists of three time-series features: turbine speed fluctuation, generator power fluctuation, and incinerator pressure deviation (e.g., the maximum fluctuation amplitude of speed and the standard deviation of power in the previous time period). The output layer is the failure probability (range 0-1) of the core equipment (incinerator, turbine, and generator) within the current prediction time period. A failure probability threshold of 0.7 is set. If the model predicts a turbine failure probability of 0.75, a "high turbine failure risk" warning is issued; if the predicted failure probability is below 0.3, the equipment is considered to be operating stably.

[0040] Grid load matching forecasting: A support vector machine (SVM) is used to construct the matching model. The input layer consists of three features: the real-time average grid load, the load change trend, and the average generator power. The output layer is the load matching degree for the current forecast period. The model is trained using grid and generation data from the past three months (a total of 2160 data sets). The optimized kernel function is the RBF kernel, and the prediction error is less than 2%. For example, if the current predicted grid load is 8.5MW and the predicted generator power is 8.2MW, the load matching degree is -3.5%.

[0041] A preset deviation threshold is used to dynamically adjust the length of the next prediction period. Adjustment based on incineration efficiency prediction deviation: Establish a first deviation value and a second deviation value for incineration efficiency, compare the deviation of the predicted value of incineration efficiency in the current time period with the actual value in the previous time period, the first deviation value of incineration efficiency, and the second deviation value of incineration efficiency, and adjust the length of the next prediction time period based on the comparison results.

[0042] For example, if the deviation between the predicted incineration efficiency for the current time period and the actual value for the previous time period is ≤2% (e.g., predicted 91%, actual 90.5%), then the basic prediction time period (1 hour / segment) will be maintained. If the deviation is greater than 5% (e.g., 91% predicted, 85% actual), then the next time period should be shortened to 30 minutes per segment, increasing the frequency of data collection and model correction.

[0043] Based on equipment failure early warning adjustment: Establish a first probability value, a second probability value, and a third probability value for equipment failure. Compare the current time period's core equipment failure probability, the first probability value, the second probability value, and the third probability value with these values, and adjust the length of the next prediction time period based on the comparison results.

[0044] For example: if the failure probability of all core equipment in the current time period is <0.5, then the basic time period is maintained; if the failure probability of a certain equipment is >0.6, then the next time period is shortened to 45 minutes / segment to strengthen the real-time monitoring of equipment operation data. If the failure probability is greater than 0.8, an emergency adjustment will be triggered, shortening the time period to 15 minutes per segment and activating the backup equipment plan.

[0045] Based on power grid load matching adjustment: establish a first load matching interval and a second load matching interval, compare the load matching degree of the current time period, the first load matching interval, and the second load matching interval, and adjust the length of the next prediction time period according to the comparison results.

[0046] If the load matching rate for the current time period is within the range of -5% to 5% (e.g., -3.5%), then the base time period will be maintained. If the matching degree is <-8% (generator power is much lower than the load) or >8% (power is much higher than the load), the next time period will be extended to 1.5 hours / segment to allow enough time to adjust the power generation and avoid frequent scheduling.

[0047] S300: Analyzes and predicts data in real time and performs real-time equipment scheduling.

[0048] In this embodiment, prediction data is analyzed and predicted in real time, and equipment is scheduled in real time. The specific process is as follows: S301: Link the predicted incineration efficiency with equipment fault warning and load matching prediction values ​​for cross-validation and priority ranking. S302: Based on the analysis results and priorities, formulate targeted scheduling plans, send them to the corresponding execution devices, and monitor the execution effect in real time.

[0049] In the above process, a multi-dimensional data linkage analysis matrix is ​​constructed to perform cross-validation and priority ranking on the prediction data obtained in step S200: Data cross-validation: The predicted incineration efficiency is linked with the equipment fault warning and load matching prediction values ​​for analysis. For example, if the predicted incineration efficiency is lower than the preset threshold (90%) and the turbine fault probability is greater than 0.6, it is determined that the incineration efficiency is low and the equipment risk is high, and the equipment operating parameters need to be adjusted first. If the load matching degree is -4% and the predicted incineration efficiency is 92%, it is determined that the load is slightly insufficient but the incineration state is stable, and the problem can be solved by fine-tuning the power generation.

[0050] Dispatch Priority Ranking: A three-tier dispatch priority system is set: Tier 1 (Emergency): Equipment failure probability > 0.7 or load matching degree < -10% / > 10%; Tier 2 (Important): Incineration efficiency < 88% or load matching degree between -8% and -5% / 5% and 8%; Tier 3 (Normal): All predicted data are within the normal range. For example, if a turbine failure probability of 0.75 (Tier 1) and a load matching degree of -3.5% (Tier 3) occur simultaneously, the equipment failure warning will be processed first.

[0051] Based on the analysis results and priorities, a targeted scheduling plan is developed, sent to the corresponding execution devices, and the execution effect is monitored in real time. Level 1 Priority Dispatch (Emergency): If the equipment fault warning is Level 1 (e.g., turbine fault probability 0.75), immediately initiate emergency dispatch: reduce turbine speed (from 2900 r / min to 2800 r / min), reduce generator power output (from 8.5 MW to 7.8 MW), and simultaneously notify maintenance personnel to come to the site for troubleshooting; if the load matching degree is -12% (generator power is far below the load), then initiate emergency power boost: increase the amount of waste fed (from 20 tons / hour in the previous period to 22 tons / hour), increase the incinerator temperature (from 950℃ to 980℃), and simultaneously increase turbine speed, so that the generator power is increased to the grid load demand within 30 minutes.

[0052] Second-level priority scheduling (important): If the predicted incineration efficiency is 87% (below the threshold of 90%), initiate incineration efficiency optimization scheduling: analyze key influencing characteristics (such as high waste moisture content of 35%), reduce waste feed rate (from 20 tons / hour to 18 tons / hour), increase auxiliary fuel supply to the incinerator (from 50L / h to 60L / h), maintain the incinerator temperature at 960℃, and ensure that the incineration efficiency is increased to above 89% in the current time period; if the load matching degree is 7% (power slightly higher than load), then fine-tune the turbine speed (from 2900r / min to 2880r / min) to reduce the generator power from 8.8MW to 8.5MW to match the grid load.

[0053] Level 3 Priority Scheduling (Regular): If all predicted data are normal (incineration efficiency 91%, equipment failure probability 0.2, load matching degree -2%), then regular stable scheduling is initiated: maintain the waste feed rate (20 tons / hour), incinerator temperature (950℃), and turbine speed (2900r / min) unchanged, and collect equipment operation feedback data every 20 minutes to ensure that all parameters remain stable within the preset range.

[0054] After the current forecast period ends, collect actual equipment operating data (such as actual incineration efficiency, equipment failure status, and actual load matching degree) and compare it with the forecast data: If the actual incineration efficiency after scheduling deviates from the predicted value by ≤2%, the equipment is fault-free, and the load matching degree is between -5% and 5%, then the scheduling is deemed effective and the existing model parameters are maintained. If the actual data deviates from the predicted value by more than 5% (e.g., the predicted incineration efficiency is 91% while the actual efficiency is 86%), the deviation data will be added to the historical dataset, and the three prediction models will be retrained (e.g., the learning rate of LSTM will be adjusted to 0.0008). The weights for extracting key features will be optimized to ensure improved prediction accuracy in the next time period.

[0055] Corresponding to the aforementioned embodiments of the intelligent scheduling and control method for waste-to-energy plants based on big data analysis, this application also provides embodiments of an intelligent scheduling and control system for waste-to-energy plants based on big data analysis.

[0056] Figure 5 This is a block diagram illustrating an intelligent scheduling and control system for a waste-to-energy plant based on big data analytics, according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a multi-dimensional key feature extraction module 401, a load dynamic matching and scheduling module 402, and a real-time analysis and scheduling module 403, wherein: The multi-dimensional key feature extraction module 401 is used to set a prediction time period, collect multi-dimensional operation data of the waste-to-energy plant in the previous prediction time period, and extract key influencing features from the multi-dimensional operation data. The load dynamic matching and scheduling module 402 is used to predict the waste incineration efficiency, equipment fault warning, and power grid load matching data for the current prediction period based on key influencing characteristics, and to dynamically adjust the prediction period. The real-time analysis and scheduling module 403 is used to analyze and predict data in real time and perform real-time equipment scheduling.

[0057] In this embodiment, the multi-dimensional key feature extraction module 401 sets a prediction time period, collects multi-dimensional operating data of the waste-to-energy plant from the previous prediction time period, and extracts key influencing features from the multi-dimensional operating data; the load dynamic matching and scheduling module 402 predicts the waste incineration efficiency, equipment fault warning, and grid load matching data for the current prediction time period based on the key influencing features, and dynamically adjusts the prediction time period; the real-time analysis and scheduling module 403 analyzes the prediction data in real time and performs real-time equipment scheduling; through the above methods, accurate feature extraction and dynamic load matching and real-time scheduling are achieved, thereby improving the operating efficiency of the power plant.

[0058] Regarding the system in the above embodiments, the specific manner in which each module performs its operations has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0059] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0060] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described intelligent scheduling and control method for waste-to-energy plants based on big data analysis. Figure 6 The diagram shown is a hardware structure diagram of any data processing-capable device within a waste-to-energy plant intelligent dispatch and control system based on big data analysis, provided by an embodiment of the present invention. (Except for...) Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0061] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned intelligent scheduling and control method for waste-to-energy plants based on big data analysis. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0062] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0063] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A smart scheduling and control method for waste-to-energy plants based on big data analysis, characterized in that, Includes the following steps: Set a forecast period, collect multi-dimensional operational data of the waste-to-energy plant from the previous forecast period, and extract key influencing features from the multi-dimensional operational data; Based on key influencing characteristics, predict the waste incineration efficiency, equipment failure warning, and power grid load matching data for the current forecast period, and dynamically adjust the forecast period. Real-time analysis and prediction of data, and real-time scheduling of equipment.

2. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 1, characterized in that, In the steps of setting the prediction period, collecting multi-dimensional operational data of the waste-to-energy plant from the previous prediction period, and extracting key influencing features from the multi-dimensional operational data: Obtain data on the waste feeding cycle of waste-to-energy plants and the update frequency of grid load data, and establish a prediction time period based on the obtained data; Collect multi-dimensional operational data from the previous prediction period and preprocess the multi-dimensional operational data; The multi-dimensional operational data includes data on waste characteristics, equipment operation, and the environment and power grid. Extract key impact features from preprocessed multi-dimensional runtime data.

3. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 2, characterized in that, The process involves collecting multi-dimensional operational data from the previous forecast period and preprocessing this data, including data on waste characteristics, equipment operation, and environmental and power grid dimensions. Remove missing, outlier, and duplicate values ​​from the data; Missing values ​​are filled with the average of historical data within the same time period, and outliers are identified and removed by comparing with the normal operating range of the equipment. Duplicate values ​​are removed based on the collection timestamp; Data from different sources and in different formats are standardized and transformed into structured data.

4. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 2, characterized in that, After the step of extracting key impact features from the preprocessed multidimensional running data: Explore the relationships between various features to form a set of key influencing features.

5. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 1, characterized in that, In the steps of predicting waste incineration efficiency, equipment fault warning, and power grid load matching data for the current forecast period based on key influencing characteristics, and dynamically adjusting the forecast period: Predict waste incineration efficiency, equipment failure warnings, and power grid load matching data for the current forecast period; Preset deviation thresholds are used to dynamically adjust the length of the next prediction period based on incineration efficiency prediction deviation, equipment fault warning, and grid load matching.

6. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 5, characterized in that, In the steps of predicting waste incineration efficiency, equipment fault warning, and power grid load matching data for the current forecast period: Based on the characteristics of waste and the operating parameters of the incinerator in the key influencing features, predict the waste incineration efficiency; Based on the changing trends of equipment operating parameters, early warning of equipment failure can be issued. Match the grid load based on grid load data and generator power characteristics.

7. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 6, characterized in that, In the steps of dynamically adjusting the length of the next prediction period based on the preset deviation threshold, incineration efficiency prediction deviation, equipment fault early warning, and grid load matching, respectively: Establish a first deviation value and a second deviation value for incineration efficiency. Compare the deviation between the predicted incineration efficiency value for the current time period and the actual value for the previous time period, the first deviation value for incineration efficiency, and the second deviation value for incineration efficiency. Adjust the length of the next prediction time period based on the comparison results.

8. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 6, characterized in that, In the steps of dynamically adjusting the length of the next prediction period based on the preset deviation threshold, incineration efficiency prediction deviation, equipment fault early warning, and grid load matching, respectively: Establish a first probability value, a second probability value, and a third probability value for equipment failure. Compare the current time period's core equipment failure probability, the first probability value, the second probability value, and the third probability value with these values, and adjust the length of the next prediction time period based on the comparison results.

9. The intelligent scheduling and control method for waste-to-energy plants based on big data analysis as described in claim 6, characterized in that, In the steps of dynamically adjusting the length of the next prediction period based on the preset deviation threshold, incineration efficiency prediction deviation, equipment fault early warning, and grid load matching, respectively: Establish a first load matching interval and a second load matching interval. Compare the load matching degree of the current time period with the first load matching interval and the second load matching interval. Adjust the length of the next forecast time period based on the comparison results.

10. A smart scheduling and control system for waste-to-energy plants based on big data analytics, applied to the smart scheduling and control method for waste-to-energy plants based on big data analytics as described in claim 1, characterized in that, It includes a multi-dimensional key feature extraction module, a load dynamic matching and scheduling module, and a real-time analysis and scheduling module; among which: The multi-dimensional key feature extraction module is used to set a prediction time period, collect multi-dimensional operation data of the waste-to-energy plant in the previous prediction time period, and extract key influencing features from the multi-dimensional operation data. The load dynamic matching and scheduling module is used to predict the waste incineration efficiency, equipment fault warning, and power grid load matching data for the current prediction period based on key influencing characteristics, and to dynamically adjust the prediction period. The real-time analysis and scheduling module is used to analyze and predict data in real time and to perform real-time equipment scheduling.

Images