Production plan optimization model construction method and system for cement plant

Abstract

The invention provides a production plan optimization model construction method and system for a cement plant, and the method comprises the steps: obtaining the related data of the cement plant, carrying out the preprocessing, and constructing a photovoltaic power generation power prediction model, a waste heat power generation power prediction model, and an electrical load prediction model according to the processed data; respectively obtaining a cement plant photovoltaic power generation power prediction result, a waste heat power generation power prediction result and an electrical load prediction result through the three prediction models; and constructing a production plan optimization model of the cement plant based on the photovoltaic power generation power prediction result, the waste heat power generation power prediction result and the electrical load prediction result. The cement plant production plan optimization method based on photovoltaic, waste heat and electrical load prediction and monitoring is realized through the model, the clean energy utilization rate of the cement plant can be effectively improved, the production cost is reduced, the production stability is improved, and technical support is provided for realizing green and low-carbon development of the cement industry.

Description

Technical Field

[0001] The present invention relates to the technical field of cement production optimization, and particularly to a method and system for constructing a production plan optimization model for a cement plant. Background Art

[0002] The cement industry is a major energy consumer, especially with high electricity demand. In the traditional cement production process, it usually relies on fossil fuel power generation, which has problems such as low energy utilization efficiency and high carbon emissions. With the proposal of the "dual carbon" goal, the cement industry is facing huge pressure on energy conservation and emission reduction. At the same time, cement plants generally have clean energy utilization methods such as photovoltaic power generation and waste heat power generation. However, due to the lack of effective prediction and optimization means, the utilization rate of these clean energies is low, and their energy conservation and emission reduction benefits cannot be fully exerted. Therefore, it is particularly crucial to develop an optimization method that comprehensively considers various energy forms such as photovoltaic and waste heat and conducts precise load management. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for constructing a production plan optimization model for a cement plant, aiming to solve the above problems in the prior art.

[0004] An embodiment of the present invention provides a method for constructing a production plan optimization model for a cement plant, including:

[0005] Obtaining relevant data of the cement plant, preprocessing the relevant data, and respectively constructing a photovoltaic power generation prediction model, a waste heat power generation prediction model, and an electricity load prediction model according to the processed data;

[0006] Respectively obtaining a photovoltaic power generation prediction result, a waste heat power generation prediction result, and an electricity load prediction result of the cement plant through the photovoltaic power generation prediction model, the waste heat power generation prediction model, and the electricity load prediction model;

[0007] Constructing a production plan optimization model of the cement plant based on the photovoltaic power generation prediction result, the waste heat power generation prediction result, and the electricity load prediction result.

[0008] An embodiment of the present invention provides a system for constructing a production plan optimization model for a cement plant, including:

[0009] A prediction model construction module, configured to obtain relevant data of the cement plant, preprocess the relevant data, and respectively construct a photovoltaic power generation prediction model, a waste heat power generation prediction model, and an electricity load prediction model according to the processed data;

[0010] A prediction module, configured to obtain the predicted photovoltaic power generation result, the predicted waste heat power generation result, and the predicted electricity load result of the cement plant through the photovoltaic power generation prediction model, the waste heat power generation prediction model, and the electricity load prediction model respectively;

[0011] An optimization model construction module, configured to construct an optimization model for the production plan of the cement plant based on the predicted photovoltaic power generation result, the predicted waste heat power generation result, and the predicted electricity load result.

[0012] An embodiment of the present invention further provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, the steps of the above-mentioned method for constructing an optimization model for the production plan of the cement plant are implemented.

[0013] An embodiment of the present invention further provides a computer-readable storage medium, on which a program for realizing information transmission is stored. When the program is executed by a processor, the steps of the above-mentioned method for constructing an optimization model for the production plan of the cement plant are implemented.

[0014] The adoption of the embodiment of the present invention may include the following beneficial effects: The embodiment of the present invention proposes an optimization method for the production plan of a cement plant. This method combines photovoltaic power generation, waste heat recovery, and electricity load prediction and monitoring technologies, can dynamically adjust the operation mode of the production line, maximize the use of renewable energy, and reduce the dependence on traditional electricity, thereby achieving the goals of energy conservation, emission reduction, and cost reduction. Description of the Drawings

[0015] In order to more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this specification. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of the method for constructing an optimization model for the production plan of the cement plant according to the embodiment of the present invention;

[0017] Figure 2 It is a schematic diagram of the system for constructing an optimization model for the production plan of the cement plant according to the embodiment of the present invention. Detailed Embodiments

[0018] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will, in conjunction with the accompanying drawings in one or more embodiments of this specification, clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this document.

[0019] Method Embodiment

[0020] According to an embodiment of the present invention, there is provided a method for constructing a production plan optimization model for a cement plant. Figure 1 It is a flowchart of the method for constructing a production plan optimization model for a cement plant according to an embodiment of the present invention, as Figure 1 shown. The method for constructing a production plan optimization model for a cement plant according to an embodiment of the present invention specifically includes:

[0021] Step S101: Obtain relevant data of the cement plant, preprocess the relevant data, and respectively construct a photovoltaic power generation prediction model, a waste heat power generation prediction model, and an electricity load prediction model according to the processed data.

[0022] The relevant data includes the historical meteorological data of the cement plant, photovoltaic module parameters, historical power generation data, current power generation data, current meteorological data, production process parameters, equipment operation parameters, production plan data, historical electricity load data, current electricity load data, and equipment operation status data.

[0023] Step S102: Obtain the photovoltaic power generation prediction result, waste heat power generation prediction result, and electricity load prediction result of the cement plant through the photovoltaic power generation prediction model, waste heat power generation prediction model, and electricity load prediction model respectively.

[0024] Step S103: Construct a production plan optimization model for the cement plant based on the photovoltaic power generation prediction result, waste heat power generation prediction result, and electricity load prediction result.

[0025] The production plan optimization model is an objective function with the photovoltaic power generation prediction result, waste heat power generation prediction result, and electricity load prediction result as inputs, equipment operation constraints, production process constraints, and market demand constraints as constraint conditions, and maximizing the clean energy utilization rate and minimizing the externally purchased electricity as the objectives.

[0026] The method further includes:

[0027] Dynamically adjust the current production plan of the cement plant through the production plan optimization model; and

[0028] Real-time monitor and obtain the actual photovoltaic power generation, waste heat power generation, and electricity consumption load of the cement plant. Compare the actual photovoltaic power generation, waste heat power generation, and electricity consumption load with the predicted results of photovoltaic power generation, waste heat power generation, and electricity consumption load, and dynamically adjust the current production plan of the cement plant according to the comparison results.

[0029] The following details the above technical solutions of the embodiments of the present invention in combination with the specific situation of the method for constructing a production plan optimization model for a cement plant according to the embodiments of the present invention.

[0030] The technical solutions of the embodiments of the present invention are as follows:

[0031] 1. Data collection and preprocessing

[0032] Real-time collect the photovoltaic power generation data, waste heat power generation data, electricity consumption load data, production plan data, and equipment operation status data of the cement plant, etc. Among them, the photovoltaic power generation data includes the temperature of photovoltaic modules, light intensity, power generation power, etc., the waste heat power generation data includes the flue gas temperature, flow rate, power generation power of the kiln head and kiln tail, etc., the electricity consumption load data includes the electricity consumption of each workshop and equipment, etc., the production plan data includes production tasks, equipment start-stop plans, etc., and the equipment operation status data includes equipment operation parameters, fault information, etc.

[0033] The data collection methods include sensor collection, DCS system interface, manual entry, etc. The data collection frequency can be dynamically adjusted according to the actual situation and requirements on site. The collected data needs to be encrypted and stored and permission management is set to ensure that only the corresponding management personnel have the only data access and editing permissions.

[0034] Perform preprocessing operations such as cleaning, denoising, and normalization on the collected data to eliminate random noise interference and dimension effects, improve the model training efficiency, and provide a high-quality data basis for subsequent analysis.

[0035] 2. Photovoltaic power generation prediction

[0036] Based on historical meteorological data, photovoltaic module parameters, photovoltaic power generation data, etc., use machine learning algorithms (such as LSTM, XGBoost, etc.) to construct a photovoltaic power generation prediction model. Among them, the historical meteorological data includes temperature, humidity, wind speed, irradiance, etc., and the photovoltaic module parameters include installation angle, tilt angle, conversion efficiency, etc. The model input includes historical meteorological data, photovoltaic module parameters, historical power generation data, etc., and the output is the predicted value of photovoltaic power generation in the future for a period of time.

[0037] At the same time, combined with weather forecast data, predict the photovoltaic power generation in the next period of time. The rolling prediction method can be adopted, that is, according to the latest meteorological data and historical data, continuously update the prediction results to improve the prediction accuracy. The specific steps are as follows:

[0038] (1) Data preparation

[0039] Collect historical data: Extract the power consumption records, photovoltaic power generation, waste heat recovery, and environmental parameters (such as temperature, humidity, wind speed, etc.) in the past period of time from the historical database of the cement factory, ensuring that the time resolution of the data is high enough to capture fine-grained changes.

[0040] Obtain real-time data: Deploy a sensor network to collect the operation parameters of each link of the current production line and external meteorological conditions in real time. These data will be used as the basic input for rolling prediction.

[0041] (2) Build an initial prediction model

[0042] Select a suitable algorithm: Select a suitable machine learning or deep learning algorithm according to the data characteristics, such as long short-term memory network (LSTM), recurrent neural network (RNN), or other time series prediction models. Considering the periodic and seasonal characteristics of cement production, a time series decomposition method with seasonal components can be selected.

[0043] Train the model: Use historical data to conduct the initial training of the selected model to obtain a preliminary prediction model. At this time, techniques such as cross-validation can be used to evaluate the model performance and adjust the hyperparameters to obtain a better fitting effect.

[0044] (3) Set the rolling window

[0045] Determine the rolling step: Define the time span (such as every hour, every day) advanced each time when rolling and updating, which is determined according to the specific requirements of the application scenario.

[0046] Set the prediction range: Clearly define the time period covered by each prediction (such as the next 24 hours, 7 days). Generally, the prediction range should not be too long to avoid the accumulation of errors affecting the accuracy.

[0047] (4) Perform rolling prediction

[0048] Update data daily: Import the latest day's data into the existing dataset every day (or more frequently), replacing the earliest day's data to keep the time length of the dataset unchanged.

[0049] Retrain the model: Retrain the prediction model based on the updated dataset to ensure that it can adapt to the latest trends and pattern changes.

[0050] Generate new predictions: Use the updated model to make new predictions for electricity demand, photovoltaic power generation, and waste heat recovery during the future time period.

[0051] (5) Evaluation and feedback

[0052] Compare actual values with predicted values: Compare the results of each prediction with the actual situation, and calculate error metrics (such as root mean square error RMSE, mean absolute percentage error MAPE, etc.) to measure the prediction accuracy.

[0053] Adjust the strategy: If it is found that the prediction deviation is large under certain specific conditions, the model structure can be improved or additional influencing factors can be introduced to further improve the prediction quality.

[0054] Optimize the scheduling decision: Adjust the production plan according to the latest prediction results, give priority to arranging high-energy-consuming operations during the time period with sufficient clean energy supply, and at the same time formulate emergency response measures to deal with emergencies.

[0055] (6) Visualization display

[0056] Create a dashboard: Develop a user-friendly interface to display the latest prediction curves, actual measurement values, and the differences between the two in real time.

[0057] Provide explanations: Provide clear chart annotations and text descriptions for users to help them understand the logic and technical details behind the predictions.

[0058] Support mobile access: It can be conveniently viewed through various terminal devices such as mobile phones and tablets, facilitating managers to keep abreast of the latest information and make quick responses at any time.

[0059] Through the above steps, the rolling prediction method can continuously optimize the prediction results in the iterative process, enabling the cement plant to better utilize clean energy such as photovoltaic and waste heat, and achieving the goals of energy conservation, emission reduction, and cost control.

[0060] 3. Waste heat power generation prediction

[0061] Based on cement production process parameters, equipment operation parameters, waste heat power generation data, etc., use machine learning algorithms to construct a waste heat power generation prediction model. Among them, cement production process parameters include raw material ratio, clinker output, kiln speed, etc., and equipment operation parameters include fan speed, valve opening, etc. The model inputs include production process parameters, equipment operation parameters, historical power generation data, etc., and the output is the predicted value of waste heat power generation in the future period.

[0062] Combined with production plan data, predict the waste heat power generation for a period of time in the future. The method of combining mechanism model and data-driven model can be adopted to improve the prediction accuracy. Among them, the type selection of the combination of mechanism model and data-driven model depends on the actual acquired data conditions. The specific implementation methods are mainly as follows:

[0063] A. Series combination: First, use the mechanism model for preliminary prediction, and then use the data-driven model to correct the error, so as to make full use of the physical meaning of the mechanism model and improve the accuracy by using the data-driven model at the same time. The steps are as follows:

[0064] ① Use the mechanism model to generate preliminary prediction results.

[0065] ② Correct the error of the mechanism model through a data-driven model (such as a neural network).

[0066] B. Parallel combination: The mechanism model and the data-driven model make predictions simultaneously, and then fuse the results through weighting or other methods, combining the advantages of both to improve the prediction robustness. The steps are as follows:

[0067] ① The mechanism model and the data-driven model make predictions respectively.

[0068] ② Fuse the results through weighted average, voting, etc.

[0069] C. Embedded combination: Embed the data-driven model into the mechanism model, or vice versa, so as to achieve deep fusion and improve the model performance. The steps are as follows:

[0070] ① Embed the data-driven model into the mechanism model (such as replacing some modules with a neural network).

[0071] ② Or introduce the constraint conditions of the mechanism model into the data-driven model.

[0072] D. Hybrid combination: Combine the series, parallel and embedded methods and apply them flexibly to adapt to various problems. The steps are as follows:

[0073] ① Select the appropriate combination method according to the specific problem.

[0074] ② Design the hybrid model structure.

[0075] 4. Electric load prediction

[0076] Based on historical electric load data, production plan data, equipment operation status data, etc., use machine learning algorithms to construct an electric load prediction model.

[0077] Combined with production plan data, predict the electric load for a period of time in the future. The method of predicting by time period can be adopted, that is, according to the electricity consumption characteristics of different time periods, establish prediction models respectively to improve the prediction accuracy. Specifically include:

[0078] ① Determine the time - segmented strategy

[0079] Analyze the electricity consumption pattern: According to historical data, analyze the electricity consumption law of the cement plant within a day or a week, and identify the electricity consumption characteristics in different time periods. For example, during the day, the electricity consumption may be high due to the full - load operation of the production line; at night, it is relatively low.

[0080] Set time - period division: Divide a day into several time periods according to the electricity consumption characteristics, such as:

[0081] Peak time period (e.g., 8:00 - 12:00, 14:00 - 18:00): Equipment operates at full load, and the electricity demand is large.

[0082] Flat - peak time period (e.g., 12:00 - 14:00, 18:00 - 20:00): Some equipment stops working, and the electricity demand is moderate.

[0083] Valley time period (e.g., 20:00 - 8:00 the next day): Most equipment shuts down, and the electricity demand is small.

[0084] ② Build a time - segmented prediction model

[0085] Select an algorithm: Select a suitable machine learning or deep - learning algorithm according to the characteristics of each time period. For example, in the peak time period, a more complex model (such as an LSTM neural network) can be used because the data changes greatly and there are many influencing factors in this period; while in the valley time period, a simple linear regression model can be selected.

[0086] Train the model: Use the historical data of the corresponding time period to conduct the initial training of the selected model to obtain a preliminary prediction model.

[0087] Save the model: Save the trained model separately for each time period for subsequent use.

[0088] 5. Optimization of production plan

[0089] Objective function: Build an optimization model for the production plan of the cement plant with the goal of maximizing the utilization rate of clean energy and minimizing the purchased electricity.

[0090] Constraint conditions: ① Equipment operation constraints: including the maximum / minimum production capacity of equipment, equipment start - up and shutdown times, etc. ② Production process constraints: including raw material ratio, clinker output, kiln speed, etc. ③ Market demand constraints: including product types, output, delivery time, etc.

[0091] Take the prediction results of photovoltaic power generation, waste - heat power generation, and electricity load as inputs, and use optimization algorithms (such as genetic algorithm, particle swarm algorithm, etc.) to solve the optimal production plan.

[0092] The optimized production plan should consider factors such as equipment operation constraints, production process constraints, and market demand constraints. The optimized production plan should include the start and stop times, operating parameters, etc. of each workshop and equipment.

[0093] 6. Real-time Monitoring and Dynamic Adjustment

[0094] Real-time monitor data such as photovoltaic power generation, waste heat power generation, electricity consumption load, and equipment operation status, and compare and analyze the actual data with the predicted data to promptly detect deviations and make dynamic adjustments.

[0095] When the actual photovoltaic power generation or waste heat power generation is lower than the predicted value, the production plan can be appropriately adjusted to reduce the electricity consumption load; when the actual photovoltaic power generation or waste heat power generation is higher than the predicted value, the production plan can be appropriately increased to improve the utilization rate of clean energy. Similarly, the rolling optimization method can be adopted, that is, according to the latest data and prediction results, continuously adjust the production plan to improve the optimization effect.

[0096] To implement the above technical solutions, the specific implementation steps of the embodiments of the present invention are as follows:

[0097] 1. Multi-source Energy Integration

[0098] Photovoltaic power generation system: Installed on the roof of the cement factory or other suitable locations, using solar panels to convert light energy into electrical energy to provide power for some production equipment.

[0099] Waste heat recovery device: Extract heat from the high-temperature waste gas discharged from the kiln to preheat raw materials or generate steam to drive a turbine generator to further supplement the power supply.

[0100] 2. Intelligent Electricity Consumption Load Prediction

[0101] Historical data analysis: Collect power consumption records over a past period of time and analyze their changing patterns.

[0102] Real-time monitoring: Deploy a sensor network to collect parameters such as current and voltage at each link of the production line in real time.

[0103] Machine learning algorithm: Adopt advanced machine learning models (such as LSTM neural network) to accurately predict the electricity demand in the next few days or even hours.

[0104] 3. Adaptive Production Scheduling

[0105] Flexibly adjust production tasks: Reasonably arrange the task volume in different time periods according to the prediction results, and try to avoid operating during peak electricity price periods.

[0106] Give priority to using clean energy: When the photovoltaic power generation is sufficient, start the relevant equipment preferentially; while at night or on cloudy days, rely on energy storage batteries and the flat-price power grid for power supply.

[0107] Emergency response mechanism: Set up an automatic protection strategy to quickly switch to the backup power supply in case of extreme weather or equipment failure, ensuring the continuity and stability of production.

[0108] 4. Visual management and decision support

[0109] User interface design: Build an intuitive and easy-to-use operation platform to display information such as the current energy status, estimated power consumption, and potential savings amount.

[0110] Remote monitoring and maintenance: Allow managers to access system data anytime and anywhere, and receive alarm notifications through mobile applications to handle abnormal situations in a timely manner.

[0111] The production plan optimization method proposed in the embodiment of the present invention realizes refined power consumption load prediction by introducing artificial intelligence technology, organically combines distributed energy sources such as photovoltaic and waste heat, and forms a closed-loop energy management. It is not only applicable to the design and planning stage of new cement plants, but also can be applied to the technical transformation projects of existing factories. By implementing this optimization plan, enterprises can significantly reduce operating costs, enhance market competitiveness, and actively respond to the policy orientation of low-carbon development.

[0112] System embodiment

[0113] According to an embodiment of the present invention, there is provided a system for constructing a production plan optimization model for a cement plant. Figure 2 It is a schematic diagram of the system for constructing a production plan optimization model for a cement plant according to an embodiment of the present invention, as Figure 2 shown. The system for constructing a production plan optimization model for a cement plant according to an embodiment of the present invention specifically includes:

[0114] A prediction model construction module 20, configured to obtain relevant data of the cement plant, preprocess the relevant data, and respectively construct a photovoltaic power generation prediction model, a waste heat power generation prediction model, and a power consumption load prediction model according to the processed data;

[0115] The relevant data includes historical meteorological data of the cement plant, photovoltaic module parameters, historical power generation power data, current power generation power data, current meteorological data, production process parameters, equipment operation parameters, production plan data, historical power consumption load data, current power consumption load data, and equipment operation status data;

[0116] A prediction module 22, configured to respectively obtain a photovoltaic power generation prediction result, a waste heat power generation prediction result, and a power consumption load prediction result of the cement plant through the photovoltaic power generation prediction model, the waste heat power generation prediction model, and the power consumption load prediction model;

[0117] An optimization model construction module 24, configured to construct an optimized production plan model for a cement plant based on the photovoltaic power generation prediction result, the waste heat power generation prediction result, and the electricity load prediction result;

[0118] The optimized production plan model takes the photovoltaic power generation prediction result, the waste heat power generation prediction result, and the electricity load prediction result as inputs, takes equipment operation constraints, production process constraints, and market demand constraints as constraint conditions, and has an objective function with the goal of maximizing the utilization rate of clean energy and minimizing the externally purchased electricity;

[0119] The system further includes:

[0120] A prediction optimization module, configured to dynamically adjust the current production plan of the cement plant through the optimized production plan model; and

[0121] A monitoring optimization module, configured to monitor and obtain the actual photovoltaic power generation, waste heat power generation, and electricity load of the cement plant in real time, compare the actual photovoltaic power generation, waste heat power generation, and electricity load with the photovoltaic power generation prediction result, the waste heat power generation prediction result, and the electricity load prediction result, and dynamically adjust the current production plan of the cement plant according to the comparison result.

[0122] The embodiment of the present invention is a system embodiment corresponding to the above method embodiment. The specific operations of each module can be understood with reference to the description of the method embodiment and will not be elaborated here.

[0123] In summary, the embodiment of the present invention proposes a method and system for constructing an optimized production plan model for a cement plant. Through the constructed optimized production plan model, the optimization of the production plan of the cement plant based on photovoltaic, waste heat, and electricity load prediction and monitoring can be realized. This method collects data such as photovoltaic power generation, waste heat power generation, and electricity load, uses machine learning algorithms for prediction, and constructs the final optimized production plan model to realize the intelligent optimization of the production plan of the cement plant, so as to improve the utilization rate of clean energy, reduce production costs, and improve production stability. The embodiment of the present invention specifically includes the following beneficial effects:

[0124] 1. Improve the utilization rate of clean energy: Through the accurate prediction and optimized scheduling of photovoltaic power generation and waste heat power generation, clean energy can be utilized to the maximum extent, the externally purchased electricity can be reduced, and carbon emissions can be reduced.

[0125] 2. Reduce production costs: By optimizing the production plan, the electricity cost can be reduced, the production efficiency can be improved, and thus the production costs can be reduced.

[0126] 3. Improve production stability: Through the accurate prediction and dynamic adjustment of the electricity load, the power shortage during peak electricity consumption periods can be avoided, and the production stability can be improved.

[0127] 4. Achieve intelligent production: In the embodiments of the present invention, artificial intelligence technology is applied to the cement production process, which can realize the intelligent optimization of production plans and improve production efficiency and management levels.

[0128] Embodiment 1 of the device

[0129] The embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it realizes the steps described in the method embodiments.

[0130] Embodiment 2 of the device

[0131] The embodiments of the present invention provide a computer-readable storage medium, on which an implementation program for information transmission is stored. When the program is executed by a processor, it realizes the steps described in the method embodiments.

[0132] The computer-readable storage medium described in this embodiment includes, but is not limited to: ROM, RAM, magnetic disk, optical disc, etc.

[0133] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a production planning optimization model for a cement plant, characterized in that include: Acquire relevant data of the cement plant, pre-process the relevant data, and respectively construct a photovoltaic power generation prediction model, a waste heat power generation prediction model, and a power load prediction model according to the processed data; The photovoltaic power generation prediction model, the waste heat power generation prediction model and the power load prediction model are used to respectively obtain the photovoltaic power generation prediction result, the waste heat power generation prediction result and the power load prediction result of the cement plant; A production plan optimization model for a cement plant is constructed based on the photovoltaic power generation prediction results, the waste heat power generation prediction results and the power load prediction results.

2. The method according to claim 1, characterized in that: The method further comprises: Dynamically adjusting the current production plan of the cement plant through the production plan optimization model; and The actual photovoltaic power generation power, waste heat power generation power and power load of the cement plant are monitored and obtained in real time, and the actual photovoltaic power generation power, waste heat power generation power and power load are compared with the photovoltaic power generation power prediction results, waste heat power generation power prediction results and power load prediction results, and the current production plan of the cement plant is dynamically adjusted according to the comparison results.

3. The method according to claim 1, characterized in that The relevant data include the cement plant's historical meteorological data, photovoltaic module parameters, historical power generation data, current power generation data, current meteorological data, production process parameters, equipment operating parameters, production plan data, historical power load data, current power load data and equipment operating status data.

4. The method according to claim 1, characterized in that: The production plan optimization model takes the photovoltaic power generation power prediction results, the waste heat power generation power prediction results and the power load prediction results as inputs, takes equipment operation constraints, production process constraints and market demand constraints as constraints, and has an objective function with the goal of maximizing the utilization rate of clean energy and minimizing the amount of purchased electricity.

5. A production planning optimization model building system for cement plants, characterized in that include: A prediction model building module is used to obtain cement plant related data, pre-process the related data, and build a photovoltaic power generation prediction model, a waste heat power generation prediction model and a power load prediction model according to the processed data; A prediction module, used to obtain the photovoltaic power generation prediction result, the waste heat power generation prediction result and the power load prediction result of the cement plant respectively through the photovoltaic power generation prediction model, the waste heat power generation prediction model and the power load prediction model; The optimization model building module is used to build a production plan optimization model of a cement plant based on the photovoltaic power generation power prediction results, the waste heat power generation power prediction results and the power load prediction results.

6. The system according to claim 5, characterized in that The system further comprises: A prediction and optimization module, used for dynamically adjusting the current production plan of the cement plant through the production plan optimization model; and The monitoring and optimization module is used to monitor and obtain the actual photovoltaic power generation power, waste heat power generation power and power load of the cement plant in real time, compare the actual photovoltaic power generation power, waste heat power generation power and power load with the photovoltaic power generation power prediction results, waste heat power generation power prediction results and power load prediction results, and dynamically adjust the current production plan of the cement plant according to the comparison results.

7. The system according to claim 5, characterized in that The relevant data include the cement plant's historical meteorological data, photovoltaic module parameters, historical power generation data, current power generation data, current meteorological data, production process parameters, equipment operating parameters, production plan data, historical power load data, current power load data and equipment operating status data.

8. The system according to claim 5, characterized in that The production plan optimization model takes the photovoltaic power generation power prediction results, the waste heat power generation power prediction results and the power load prediction results as inputs, takes equipment operation constraints, production process constraints and market demand constraints as constraints, and has an objective function with the goal of maximizing the utilization rate of clean energy and minimizing the amount of purchased electricity.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for constructing a production plan optimization model for a cement plant as described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by the processor, the steps of the method for constructing a production plan optimization model for a cement plant as described in any one of claims 1 to 4 are implemented.

Images