Method and device for predicting power consumption and computer program product
By establishing an exponential relationship model between the historical production plan and power consumption of the steel rolling system, the short-term power consumption of the steel rolling system is accurately predicted, and the problem of inaccurate prediction in the existing technology is solved, and the reliability of production plans and the efficiency of energy management is improved.
Patent Information
- Application Number
- CN202510306654.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-14
- Publication Date
- 2025-05-30
AI Technical Summary
The prior art is difficult to accurately predict the short-term power consumption of steel rolling systems, especially in the week before the release of production plans.
By obtaining the historical production plan data and historical energy consumption data of the steel rolling system, the target production parameters of each historical production plan are determined as independent variables and the power consumption is used as the dependent variables, and an exponential relationship model between the target production parameters and power consumption is established, and the power consumption is predicted based on the production plan on the forecast date.
Accurate prediction of the power consumption of steel rolling systems is achieved, the problem of inaccurate prediction results in the prior art is solved, and the reliability of production plans and the efficiency of energy management is improved.
Smart Images
Figure CN120069223A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of energy, and in particular, to a method, apparatus, and computer program product for predicting power consumption. Background Art
[0002] For industrial users, short-term power load forecasting helps to reduce energy consumption costs. By accurately predicting power consumption requirements, production plans can be reasonably arranged, production processes can be optimized, and energy waste can be reduced. Existing forecasting methods usually rely on trend forecasting algorithm models, which can learn the general patterns of long-term energy consumption data. In the steel production process, the production volume of steel rolling depends on the production plan. Generally, the production plan is released one week before production, and the content includes information such as the steel grade to be produced, the set thickness, and length. The formulation of the production plan has nothing to do with time series and only depends on sales. Therefore, it is difficult to obtain accurate power consumption forecasting results by directly using time series trend forecasting algorithms for short-term load forecasting of the steel rolling system.
[0003] Therefore, in the related art, there is a problem of how to accurately predict the power consumption of the steel rolling system.
[0004] In view of the problem in the related art of how to accurately predict the power consumption of the steel rolling system, no effective solution has been proposed yet.
[0005] Therefore, it is necessary to improve the related art to overcome the defects in the related art. Summary of the Invention
[0006] Embodiments of the present application provide a method, apparatus, and computer program product for predicting power consumption to at least solve the problem in the related art of how to accurately predict the power consumption of the steel rolling system.
[0007] According to one aspect of the embodiments of the present application, a method for predicting power consumption is provided, including: obtaining historical production plan data and historical energy consumption data of a steel rolling system, where the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters; determining the target production parameters of each historical production plan as independent variables, and determining the power consumption of each historical production plan extracted from the historical energy consumption data as dependent variables, and establishing an exponential relationship model between the target production parameters and the power consumption according to the independent variables and the dependent variables; and determining the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0008] In an exemplary embodiment, extracting the power consumption of each historical production plan from the historical energy consumption data includes: when the deviation value of the target production parameter of the historical production plan in the historical production plan data is less than a preset deviation value within a preset time period, determining the power consumption of each historical production plan within the preset time period according to the quotient of the total power consumption within the preset time period and the number of historical production plans within the preset time period; when the deviation value of the target production parameter of the historical production plan in the historical production plan data is greater than the preset deviation value within the preset time period, proportionally allocating the total power consumption within the preset time period according to the proportion of the production duration of each historical production plan within the preset time period to the preset time period, to obtain the power consumption of each historical production plan within the preset time period.
[0009] In an exemplary embodiment, establishing an exponential relationship model between the target production parameter and the power consumption according to the independent variable and the dependent variable includes: determining a data set including the independent variable and the dependent variable from the historical production plan data and the historical energy consumption data; performing data fitting calculation on the data set according to a preset fitting algorithm and a preset exponential function model to obtain the model parameters of the preset exponential function model; determining the exponential relationship model according to the preset exponential function model and the model parameters.
[0010] In an exemplary embodiment, after determining the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model, the method further includes: evaluating the exponential relationship model according to a preset period to obtain a model evaluation result; when it is determined that the model evaluation result is unqualified, updating the data set according to the production plan data and the energy consumption data within the preset period to obtain an updated data set; performing re-fitting calculation according to the updated data set to obtain updated model parameters; calibrating the parameters of the exponential relationship model according to the updated model parameters.
[0011] In an exemplary embodiment, evaluating the exponential relationship model according to a preset period to obtain a model evaluation result includes: calculating the coefficient of determination and the mean absolute percentage error of the exponential relationship model according to the true predicted power consumption within the preset period and the predicted power consumption within the preset period; when it is determined that the coefficient of determination is less than a first preset value and / or the mean absolute percentage error is greater than a second preset value, determining that the model evaluation result is unqualified; when it is determined that the coefficient of determination is greater than the first preset value and the mean absolute percentage error is less than the second preset value, determining that the model evaluation result is qualified.
[0012] In an exemplary embodiment, determining the predicted power consumption on the prediction date according to the production plan on the prediction date and the exponential relationship model includes: calling the exponential relationship model to predict the power consumption of each production plan in the production plan on the prediction date to obtain a plurality of predicted power consumptions; summing the plurality of predicted power consumptions to obtain the predicted power consumption on the prediction date.
[0013] According to another aspect of the embodiments of the present application, there is also provided a prediction device for power consumption, including: an acquisition module, configured to acquire historical production plan data and historical energy consumption data of a rolling mill system, where the historical production plan data includes a plurality of historical production plans, and each historical production plan includes a plurality of production parameters; a establishment module, configured to establish an exponential relationship model between the target production parameter and the power consumption according to the target production parameter of each historical production plan as the independent variable and the power consumption of each historical production plan extracted from the historical energy consumption data as the dependent variable; a prediction module, configured to determine the predicted power consumption on the prediction date according to the production plan on the prediction date and the exponential relationship model.
[0014] According to still another aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the above-mentioned power consumption prediction method when running.
[0015] According to still another aspect of the embodiments of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the above-mentioned processor executes the above-mentioned power consumption prediction method through the computer program.
[0016] According to still another aspect of the embodiments of the present application, there is also provided a computer program product, including a computer program, where the steps of the methods in the various embodiments of the present application are implemented when the computer program is executed by a processor.
[0017] Through the present application, the target production parameter of each production plan can be extracted from the historical production plan data and historical energy consumption data of the rolling mill system as the independent variable, and the power consumption of each historical production plan can be extracted from the historical energy consumption data as the dependent variable, so as to establish an exponential relationship model according to the independent variable and the dependent variable, and predict the power consumption on the day based on the exponential relationship model and the production plan on the prediction date. Thus, the problem of how to accurately predict the power consumption of the rolling mill system in the related art is solved, and the effect of accurately predicting the power consumption of the rolling mill system is achieved. Description of the Drawings
[0018] The accompanying drawings here are incorporated into and form a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.
[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0020] Figure 1 It is a hardware structure block diagram of a computer terminal for a power consumption prediction method according to an embodiment of this application;
[0021] Figure 2 It is a flowchart of a power consumption prediction method according to an embodiment of this application;
[0022] Figure 3 It is a schematic diagram of historical production plan data of a rolling mill system according to an embodiment of this application;
[0023] Figure 4 It is a schematic diagram of historical energy consumption data of a rolling mill system according to an embodiment of this application;
[0024] Figure 5 It is a scatter plot of set thickness and power consumption according to an embodiment of this application;
[0025] Figure 6 It is a fitting curve graph of set thickness and power consumption according to an embodiment of this application;
[0026] Figure 7 It is a schematic diagram of a power consumption prediction method according to an embodiment of this application;
[0027] Figure 8 It is a power consumption prediction curve graph according to an embodiment of this application;
[0028] Figure 9 It is a structure block diagram of a power consumption prediction device according to an embodiment of this application. Detailed implementation manners
[0029] To enable those skilled in the art to better understand the solutions of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts should fall within the scope of protection of this application.
[0030] It should be noted that the terms "first", "second", etc. in the description, claims, and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.
[0031] The method embodiments provided in the embodiments of the present application can be executed on a computer terminal or a similar computing device. Taking the operation on a computer terminal as an example, Figure 1 is a hardware structure block diagram of a computer terminal for a power consumption prediction method according to an embodiment of the present application. As Figure 1 shown, the computer terminal may include one or more ( Figure 1 only one is shown in the figure) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor (Central Processing Unit, MCU) or a field programmable gate array (Field Programmable Gate Array, FPGA)) and a memory 104 for storing data. Among them, the above-mentioned computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those of ordinary skill in the art can understand that Figure 1 the structure shown is only illustrative and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may further include more or fewer components than those shown in Figure 1 the figure, or have a configuration different from that shown in Figure 1 the figure.
[0032] The memory 104 can be used to store computer programs, such as software programs and modules of application software, like the computer program corresponding to the power consumption prediction method in the embodiments of the present application. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implements the above-mentioned method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory 104 may further include memories remotely set relative to the processor 102, and these remote memories can be connected to the computer terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and their combinations.
[0033] The wireless network provided by the communication provider of the computer terminal. In one instance, the transmission device 106 includes a network adapter (Network Interface Controller, abbreviated as NIC), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device 106 can be a radio frequency (RadioFrequency, abbreviated as RF) module, which is used to communicate with the Internet wirelessly.
[0034] In this embodiment, a power consumption prediction method is provided. Figure 2 It is a flowchart of a power consumption prediction method according to an embodiment of the present application, as Figure 2 shown, and this process includes the following steps:
[0035] Step S202, obtain the historical production plan data and historical energy consumption data of the rolling mill system, where the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters;
[0036] In an optional embodiment, Figure 3 shows the historical production plan data in the rolling mill system. The production parameters of each historical production plan include slab number, coil number, order number, material, output date, output time, set thickness, upper limit of output thickness, lower limit of output thickness, actual nominal thickness, target thickness hit rate, set width, upper limit of output width, lower limit of output width, actual nominal width, coil weight, coil length, etc. Figure 4 shows the historical energy consumption data in the rolling mill system.
[0037] Step S204: Determine the target production parameters of each historical production plan as independent variables, determine the power consumption of each historical production plan extracted from the historical energy consumption data as dependent variables, and establish an exponential relationship model between the target production parameters and the power consumption based on the independent variables and the dependent variables.
[0038] Optionally, in the above step S204, before feeding materials into the rolling system, among the production parameters of the above historical production plans, the known production parameters include material, set thickness, and set width. Other production parameters can be obtained only after the rolling system completes production. By constructing a three-dimensional scatter plot of set thickness - set width - power consumption, it can be determined that the set thickness has a greater impact on energy consumption, and the set width has a smaller impact on energy consumption. By analyzing the power consumption of each historical production plan, it can be determined that under the condition of the same set thickness, whether it is the steel grade of the same material or different materials, their energy consumption levels are similar. Therefore, it can be determined that the set thickness is the key factor affecting production energy consumption. In the embodiment of the present application, the independent variable for determining the exponential relationship model is the set thickness. At the same time, in order to reflect the energy consumption situation of each historical production plan, the power consumption of each historical production plan is used as the dependent variable.
[0039] Step S206: Determine the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0040] Through the above steps, the target production parameters of each production plan can be extracted from the historical production plan data and historical energy consumption data of the rolling system as independent variables, and the power consumption of each historical production plan can be extracted from the historical energy consumption data as dependent variables. Thus, an exponential relationship model is established based on the independent variables and the dependent variables, and the power consumption of the current day is predicted based on the exponential relationship model and the production plan of the prediction day. Thereby, the problem of how to accurately predict the power consumption of the rolling system in the related art is solved, and the effect of accurately predicting the power consumption of the rolling system is achieved.
[0041] In an exemplary embodiment, extracting the power consumption of each historical production plan from the historical energy consumption data includes: when the deviation value of the target production parameters of the historical production plans in the historical production plan data is less than the preset deviation value within the preset time period, determining the power consumption of each historical production plan within the preset time period according to the quotient of the total power consumption within the preset time period and the number of historical production plans within the preset time period; when the deviation value of the target production parameters of the historical production plans in the historical production plan data is greater than the preset deviation value within the preset time period, proportionally allocate the total power consumption within the preset time period according to the proportion of the production duration of each historical production plan within the preset time period to the preset time period, and obtain the power consumption of each historical production plan within the preset time period.
[0042] Optionally, in the above embodiments, the method for the factory to collect power consumption is to collect power consumption once every preset time period, for example, collect power consumption once per hour. Since the rolling mill system has a relatively fast production operation speed each time, it can complete the operation in a few minutes, and the rolling mill system operates in a pipeline form, that is, the system can simultaneously carry out multiple production plans. Therefore, it is impossible to directly obtain the power consumption of each historical production plan. Therefore, in this embodiment, the power consumption of each historical production plan can be extracted by two methods: the direct extrapolation method and the indirect apportionment method.
[0043] Direct extrapolation method: Assume that the rolling mill system collects power consumption once per hour. First, select from the historical production plan data the historical production plan data that produces the same kind of steel within a whole hour and has relatively close set thicknesses. For example, during the period from 12:00 to 13:00, all the produced steel is type A steel, and the deviation range of the steel thickness is less than 0.03 mm. There are a total of 20 operations, and the total power consumption is 20,000 kWh. Divide the total power consumption by the number of operations to obtain the power consumption per single operation as 1,000 kWh.
[0044] Indirect apportionment method: Assume that the rolling mill system collects power consumption once per hour. During the period from 12:00 to 13:00, there are a total of 3 operations, and the total power consumption is 3,600 kWh. The operation time of historical production plan A (equivalent to the production duration) is from 12:05 to 12:10, the operation time of historical production plan B is from 12:20 to 12:27, and the operation time of historical production plan C is from 12:40 to 12:46. The operation time ratios of historical production plan A, historical production plan B, and historical production plan C are 1:3:6. By proportional apportionment calculation, the power consumption of historical production plan A is 1,000 kWh, the power consumption of historical production plan B is 1,400 kWh, and the power consumption of historical production plan C is 1,200 kWh.
[0045] In an exemplary embodiment, establishing an exponential relationship model between the target production parameter and the power consumption according to the independent variable and the dependent variable includes: determining a data set including the independent variable and the dependent variable from the historical production plan data and the historical energy consumption data; performing data fitting calculation on the data set according to a preset fitting algorithm and a preset exponential function model to obtain the model parameters of the preset exponential function model; and determining the exponential relationship model according to the preset exponential function model and the model parameters.
[0046] In an alternative embodiment, as Figure 5 shown Figure 5It is a scatter distribution diagram of the set thickness and power consumption. From the diagram, it can be clearly seen that as the set thickness of the rolling steel system decreases, the power consumption shows a gradually increasing trend, and there is a significant correlation between the two. By fitting the set thickness and power consumption data with an exponential function, a curve relationship diagram and the corresponding exponential function model can be obtained.
[0047] Exponential function fitting is a method widely used in data analysis, mainly used to describe and predict the exponential growth or decay trend of data as it changes over time or with another variable. By constructing an exponential function model, this model can best describe and predict the relationship between the independent variable (x) and the dependent variable (y) in a given dataset. The exponential function usually has the form y = a * exp(b * x), where a and b are fitting parameters, and exp() represents the natural exponential function.
[0048] In an optional embodiment, the modeling process of the exponential relationship model is described, which specifically includes the following steps:
[0049] 1. Data preparation: Collect the dataset to be fitted, including the values of the independent variable x and the dependent variable y. Ensure that the data is accurate, complete, and representative.
[0050] 2. Model selection: Select a suitable exponential function model according to the characteristics of the data and the fitting goal. Common exponential function models include single exponential fitting (y = a * exp(b * x)), double exponential fitting (y = a * exp(b * x) + c * exp(d * x)), etc. In this embodiment, single exponential fitting is selected.
[0051] 3. Parameter determination: Use fitting algorithms (such as the least squares method, non-linear least squares method, etc.) to determine the parameters in the model. The above algorithms solve the parameters by minimizing the error between the observed values and the fitted values (such as the sum of squared residuals).
[0052] In an optional embodiment, according to the above modeling process, with the set thickness of the rolling steel system as the independent variable and the power consumption as the dependent variable, exponential function fitting is performed to obtain the fitting curve as Figure 6 shown, and the expression of the corresponding exponential function model is: Power consumption = 1103.5085 * e^(-0.0884 * Set thickness).
[0053] In an exemplary embodiment, after determining the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model, the method further includes: evaluating the exponential relationship model at a preset period to obtain a model evaluation result; in the case where it is determined that the model evaluation result is unqualified, updating the data set according to the production plan data and the energy consumption data within the preset period to obtain an updated data set; re-fitting and calculating according to the updated data set to obtain updated model parameters; and calibrating the parameters of the exponential relationship model according to the updated model parameters.
[0054] In an exemplary embodiment, evaluating the exponential relationship model at a preset period to obtain a model evaluation result includes: calculating the coefficient of determination and the mean absolute percentage error of the exponential relationship model according to the true predicted power consumption within the preset period and the predicted power consumption within the preset period; in the case where it is determined that the coefficient of determination is less than a first preset value and / or the mean absolute percentage error is greater than a second preset value, determining that the model evaluation result is unqualified; and in the case where it is determined that the coefficient of determination is greater than the first preset value and the mean absolute percentage error is less than the second preset value, determining that the model evaluation result is qualified.
[0055] Optionally, in the above embodiment, the coefficient of determination (R 2 ) represents the degree of explanation of the variability of the dependent variable by the independent variable in the model. The value of R 2 is between 0 and 1. The closer the value of R 2 is to 1, the stronger the explanatory ability of the model to the data, that is, the independent variable in the model can well explain the variation of the dependent variable. The higher the value of R 2 , the better the fitting degree of the model, that is, the more accurate the prediction of the model to the data. The mean absolute percentage error (MAPE) is a performance evaluation index widely used in prediction and regression analysis, mainly used to measure the relative error between the predicted value and the true value. Its calculation method is to calculate the average value of the absolute error between the predicted value and the true value. The value range of MAPE is from 0 to positive infinity. The closer it is to 0, the more consistent the predicted value is with the true value, indicating that the prediction effect of the model is more ideal.
[0056] In an exemplary embodiment, determining the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model includes: calling the exponential relationship model to predict the power consumption of each production plan in the production plan of the prediction day respectively to obtain a plurality of predicted power consumptions; and summing the plurality of predicted power consumptions to obtain the predicted power consumption of the prediction day.
[0057] Obviously, the embodiments described above are only a part of the embodiments of this application, rather than all of them. To better understand the above method for determining the power generation area, the following will illustrate the above process in combination with embodiments, but it is not used to limit the technical solutions of the embodiments of this application. Specifically:
[0058] In an alternative embodiment, in combination with Figure 7 the power consumption prediction method of this application will be further described. As Figure 7 shown, it specifically includes the following steps:
[0059] 1. Read the data set: Read the historical production data files of the rolling mill system, including historical production plan data and historical energy consumption data.
[0060] 2. Data collation: Sort the historical production plan data according to the production time, and sort the historical energy consumption data according to the statistical time for subsequent data analysis and processing.
[0061] 3. Calculate the power consumption: Extract the power consumption of each historical production plan according to the direct extrapolation method or the indirect allocation method in the above embodiments.
[0062] 4. Classification of production plans: Classify the production plans according to the thickness and steel type set for rolling.
[0063] 5. Draw a 3D graph: Draw a 3D graph of the set thickness, width and power consumption of each steel type, and determine the production parameters with a high correlation with the power consumption as independent variables by analyzing the 3D graph.
[0064] 6. Eliminate outliers: Use the quartiles of the box plot method to determine the data within the normal range, and the data outside this range is regarded as potential outliers and excluded from the original data set.
[0065] 7. Function fitting: Fit the set thickness and power consumption data through an exponential function to obtain a curve relationship graph and the corresponding exponential function model.
[0066] 8. Predict the power consumption according to the production plan: According to the production plan of the rolling mill system, use the above exponential function model to calculate the power consumption of each production plan, sum it up daily, and predict the daily power consumption.
[0067] 9. Model evaluation: Draw a deviation graph of the true value and the model predicted value of the power consumption, calculate the model error rate, the determination coefficient R 2 and the mean absolute percentage error MAPE.
[0068] In an alternative embodiment, Figure 8It is a deviation graph of the real power consumption value and the model prediction value obtained by testing the prediction model (equivalent to the above exponential relationship model) constructed in the embodiment of the present application according to the actual 21-day rolling mill system data. Among them, the solid line represents the actual power consumption of daily production behavior, the dotted line represents the predicted daily power consumption of the model, and the bar graph represents the difference between the predicted curve and the actual curve. After calculation, the model R 2 score reaches 86.68%, and the MAPE is only 9.74%, with good results.
[0069] Through the above embodiments, by analyzing the relationship between historical production plans and actual energy consumption, a power consumption prediction model can be constructed. This model can accurately predict power demand according to production plans, conform to the actual situation of steel production, has high prediction accuracy, and can effectively support enterprises to optimize production plans and energy management, thereby improving production efficiency and economic benefits.
[0070] Through the description of the above implementation manners, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation manner. Based on such an understanding, the technical solution of the present application, in essence or the part that makes contributions to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present application.
[0071] In this embodiment, a power consumption prediction device is also provided. This device is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.
[0072] Figure 9 It is a structural block diagram of a power consumption prediction device according to an embodiment of the present application. This device includes:
[0073] An acquisition module 92, configured to acquire historical production plan data and historical energy consumption data of a rolling mill system, where the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters;
[0074] A building module 94 is configured to establish an exponential relationship model between the target production parameters and the power consumption based on the target production parameters of each historical production plan as independent variables and the power consumption of each historical production plan extracted from the historical energy consumption data as dependent variables.
[0075] A prediction module 96 is configured to determine the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0076] Through the above device, the target production parameters of each production plan can be extracted from the historical production plan data and historical energy consumption data of the rolling mill system as independent variables, and the power consumption of each historical production plan can be extracted from the historical energy consumption data as dependent variables, so as to establish an exponential relationship model based on the independent variables and dependent variables, and predict the power consumption of the current day based on the exponential relationship model and the production plan of the prediction day. Thus, the problem of how to accurately predict the power consumption of the rolling mill system in the related art is solved, and the effect of accurately predicting the power consumption of the rolling mill system is achieved.
[0077] In an exemplary embodiment, the building module 94 is further configured to, within a preset time period, when the deviation value of the target production parameters of the historical production plans in the historical production plan data is less than a preset deviation value, determine the power consumption of each historical production plan within the preset time period according to the quotient of the total power consumption within the preset time period and the number of historical production plans within the preset time period; within the preset time period, when the deviation value of the target production parameters of the historical production plans in the historical production plan data is greater than the preset deviation value, proportionally allocate the total power consumption within the preset time period according to the proportion of the production duration of each historical production plan within the preset time period to the preset time period, so as to obtain the power consumption of each historical production plan within the preset time period.
[0078] In an exemplary embodiment, the building module 94 is further configured to determine a data set including the independent variables and the dependent variables from the historical production plan data and the historical energy consumption data; perform data fitting calculation on the data set according to a preset fitting algorithm and a preset exponential function model to obtain the model parameters of the preset exponential function model; and determine the exponential relationship model according to the preset exponential function model and the model parameters.
[0079] In an exemplary embodiment, the establishing module 94 is further configured to evaluate the exponential relationship model at a preset period to obtain a model evaluation result; in the case that the model evaluation result is determined to be unqualified, update the data set according to the production plan data and the energy consumption data within the preset period to obtain an updated data set; re-fit and calculate according to the updated data set to obtain updated model parameters; and calibrate the parameters of the exponential relationship model according to the updated model parameters.
[0080] In an exemplary embodiment, the establishing module 94 is further configured to calculate the coefficient of determination and the mean absolute percentage error of the exponential relationship model according to the true predicted power consumption within the preset period and the predicted power consumption within the preset period; in the case that the coefficient of determination is determined to be less than a first preset value and / or the mean absolute percentage error is greater than a second preset value, determine that the model evaluation result is unqualified; in the case that the coefficient of determination is determined to be greater than the first preset value and the mean absolute percentage error is less than the second preset value, determine that the model evaluation result is qualified.
[0081] In an exemplary embodiment, the prediction module 96 is further configured to call the exponential relationship model to predict the power consumption of each production plan in the production plan of the prediction day respectively to obtain a plurality of predicted power consumptions; and sum the plurality of predicted power consumptions to obtain the predicted power consumption of the prediction day.
[0082] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.
[0083] Optionally, in this embodiment, the above storage medium may be configured to store a computer program for executing the following steps:
[0084] S1, obtain historical production plan data and historical energy consumption data of a rolling mill system, where the historical production plan data includes a plurality of historical production plans, and each historical production plan includes a plurality of production parameters;
[0085] S2, determine the target production parameters of each historical production plan as independent variables, determine the power consumption of each historical production plan extracted from the historical energy consumption data as dependent variables, and establish an exponential relationship model between the target production parameters and the power consumption according to the independent variables and the dependent variables;
[0086] S3, determine the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0087] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: various media such as USB flash drives, read-only memory (ROM for short), random access memory (RAM for short), external hard drives, magnetic disks, or optical discs that can store computer programs.
[0088] Specific examples in this embodiment may refer to the examples described in the above embodiments and exemplary embodiments, and will not be elaborated here.
[0089] An embodiment of the present application also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0090] Optionally, in this embodiment, the above processor may be configured to execute the following steps through a computer program:
[0091] S1. Obtain historical production plan data and historical energy consumption data of the rolling mill system. Among them, the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters;
[0092] S2. Determine the target production parameters of each historical production plan as independent variables, and determine the power consumption of each historical production plan extracted from the historical energy consumption data as dependent variables. Establish an exponential relationship model between the target production parameters and the power consumption according to the independent variables and the dependent variables;
[0093] S3. Determine the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0094] In an exemplary embodiment, the above electronic device may further include a transmission device and input / output devices. Among them, the transmission device is connected to the above processor, and the input / output devices are connected to the above processor.
[0095] An embodiment of the present application also provides a computer program product, including a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program product, and the steps of the methods described in various embodiments of the present application are implemented when the computer program is executed by a processor.
[0096] Optionally, in this embodiment, the above computer program may be configured to implement the following steps when executed by a processor:
[0097] S1. Obtain the historical production plan data and historical energy consumption data of the rolling mill system, where the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters;
[0098] S2. Determine the target production parameters of each historical production plan as independent variables, determine the power consumption of each historical production plan extracted from the historical energy consumption data as the dependent variable, and establish an exponential relationship model between the target production parameters and the power consumption according to the independent variables and the dependent variables;
[0099] S3. Determine the predicted power consumption of the prediction day according to the production plan of the prediction day and the exponential relationship model.
[0100] The specific examples in this embodiment can refer to the examples described in the above embodiments and exemplary embodiments, and will not be repeated here.
[0101] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present application can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. They can be implemented by program codes executable by the computing device. Thus, they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order than here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the present application is not limited to any specific combination of hardware and software.
[0102] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.
Claims
1. A method for predicting power consumption, characterized in that: include: Acquire historical production plan data and historical energy consumption data of the steel rolling system, wherein the historical production plan data includes multiple historical production plans, and each historical production plan includes multiple production parameters; Determine the target production parameter of each historical production plan as an independent variable, determine the power consumption of each historical production plan extracted from the historical energy consumption data as a dependent variable, and establish an exponential relationship model between the target production parameter and the power consumption according to the independent variable and the dependent variable; The predicted power consumption for the predicted day is determined according to the production plan for the predicted day and the exponential relationship model.
2. The method according to claim 1, characterized in that Extracting the power consumption of each historical production plan from the historical energy consumption data includes: In a preset time period, when the deviation value of the target production parameter of the historical production plan in the historical production plan data is less than the preset deviation value, the power consumption of each historical production plan in the preset time period is determined according to the quotient of the total power consumption in the preset time period and the number of historical production plans in the preset time period; Within the preset time period, when the deviation value of the target production parameter of the historical production plan in the historical production plan data is greater than the preset deviation value, the total power consumption of the preset time period is apportioned in direct proportion to the proportion of the production duration of each historical production plan within the preset time period to the preset time period, so as to obtain the power consumption of each historical production plan within the preset time period.
3. The method according to claim 1, characterized in that Establishing an exponential relationship model between the target production parameter and the power consumption according to the independent variable and the dependent variable includes: Determine a data set including the independent variable and the dependent variable from the historical production plan data and the historical energy consumption data; Performing data fitting calculation on the data set according to a preset fitting algorithm and a preset exponential function model to obtain model parameters of the preset exponential function model; The exponential relationship model is determined according to the preset exponential function model and the model parameters.
4. The method according to claim 3, characterized in that After determining the predicted power consumption for the predicted day according to the production plan for the predicted day and the exponential relationship model, the method further includes: Evaluate the exponential relationship model according to a preset period to obtain a model evaluation result; When it is determined that the model evaluation result is unqualified, the data set is updated according to the production plan data and energy consumption data within the preset period to obtain an updated data set; Refitting and calculating according to the updated data set to obtain updated model parameters; The exponential relationship model is calibrated according to the updated model parameters.
5. The method according to claim 4, characterized in that The exponential relationship model is evaluated according to a preset period to obtain a model evaluation result, including: Calculate the coefficient of determination and the mean absolute percentage error of the exponential relationship model according to the actual predicted power consumption within the preset period and the predicted power consumption within the preset period; In the case where it is determined that the coefficient of determination is less than a first preset value and / or the mean absolute percentage error is greater than a second preset value, determining that the model evaluation result is unqualified; When it is determined that the determination coefficient is greater than a first preset value and the mean absolute percentage error is less than a second preset value, the model evaluation result is determined to be qualified.
6. The method according to claim 1, characterized in that Determining the predicted power consumption for the predicted day according to the production plan for the predicted day and the exponential relationship model includes: The exponential relationship model is called to predict the power consumption of each production plan in the production plan of the forecast day, and a plurality of predicted power consumptions are obtained; The multiple predicted power consumptions are summed to obtain the predicted power consumption for the predicted day.
7. A device for predicting power consumption, characterized in that: include: An acquisition module, used to acquire historical production plan data and historical energy consumption data of a steel rolling system, wherein the historical production plan data includes a plurality of historical production plans, and each historical production plan includes a plurality of production parameters; An establishment module is used to determine the target production parameter of each historical production plan as an independent variable, determine the power consumption of each historical production plan extracted from the historical energy consumption data as a dependent variable, and establish an exponential relationship model between the target production parameter and the power consumption according to the independent variable and the dependent variable; The prediction module is used to determine the predicted power consumption on the prediction day according to the production plan on the prediction day and the exponential relationship model.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.
9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.