Multivariable aggregate yield prediction method and system
By weight analysis and inputting prediction models on the historical data of the aggregate production line, the problem of inaccurate aggregate output prediction is solved, fast and accurate output prediction is achieved, and the efficiency of production management is improved.
Patent Information
- Application Number
- CN202411966682.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-28
- Publication Date
- 2025-05-30
AI Technical Summary
The prior art lacks accurate methods to quickly and easily predict aggregate yields, especially when production aggregates of different particle sizes or changes in equipment parameters.
By analyzing the historical data, the weights of each production parameter and the 24-hour output of the aggregate production line are obtained, and the target production parameters are processed and input into the prediction model to complete the accurate prediction of the 24-hour output of the aggregate production line.
It achieves rapid and accurate prediction of the aggregate production line 24-hour output, improves the accuracy of prediction, and facilitates the formulation and management of production plans.
Smart Images
Figure CN120069153A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of production prediction, and particularly to a multi-variable aggregate production prediction method and system. Background Art
[0002] The aggregate production line is a crucial link in fields such as construction engineering and road construction, and is used to produce sand and gravel aggregates of various particle sizes. The quality and supply efficiency of aggregates directly affect the overall quality and progress of construction projects. The aggregate production line usually includes multiple links such as unloading, feeding, crushing, screening, conveying, and washing. Each stage in these links requires special equipment, and the aggregate production is determined based on multiple variables. The selection and parameter configuration of each piece of equipment will affect the performance and output of the production line. The prediction of the production line's output is generally determined by the experience of engineers and the actual production output. When producing aggregates of different particle sizes, using different raw materials, or changing the equipment parameters of the production line, the prediction of the output will not be accurate enough, and there is no accurate method to quickly and conveniently predict the aggregate production. Summary of the Invention
[0003] In order to at least partially solve the problem that there is no accurate method to quickly and conveniently predict the aggregate production at present, the present invention provides a multi-variable aggregate production prediction method and system. The present invention analyzes historical data to obtain the weight of each production parameter and the 24-hour output of the aggregate production line, and then processes the target production parameters before production according to the weight and inputs them into the prediction model to complete the accurate prediction of the 24-hour output of the aggregate production line.
[0004] To achieve the above object, the technical solution of the present invention is:
[0005] The first aspect of the present invention proposes a multi-variable aggregate production prediction method, including:
[0006] Step 1: Collect historical data in the aggregate production line and preprocess the historical data to facilitate the removal of outliers;
[0007] Step 2: Perform weighted calculation on the preprocessed historical data to obtain the weights of the historical data, which is convenient for improving the accuracy of the predicted output;
[0008] Step 3: Preprocess the target data in the aggregate production line, add weights, and then input it into the prediction model to complete the prediction of the 24-hour output of the aggregate production line.
[0009] Further, the collection of historical data in the aggregate production line and the preprocessing of the historical data specifically include:
[0010] Collect the output of the aggregate production line in 24 hours and the corresponding production parameters within 24 hours; the production parameters are collected once every 24 hours; the production parameters include the feeding speed, raw material particle size, hardness of raw material type, power of the crushing equipment, required aggregate particle size, number of sieve layers of the screening equipment, time for cleaning the aggregate, and conveying equipment speed in the aggregate production line;
[0011] Delete the maximum and minimum values in the output of the aggregate production line in 24 hours and the corresponding production parameters within 24 hours to eliminate the influence of extreme values.
[0012] Further, the step two includes:
[0013] Normalize the target data respectively, calculate the information entropy of each production parameter after normalization, and calculate the information entropy weight according to the information entropy;
[0014] Calculate the correlation degree between the production parameters and the output of the aggregate production line in 24 hours respectively;
[0015] Obtain the weight of each production parameter according to the information entropy weight and the correlation degree, which is convenient to improve the accuracy of the weight of each production parameter through the combined weight.
[0016] Further, the correlation degree is expressed by the following formula:
[0017]
[0018] where, X ij is the i-th data in the j-th production parameter, Y is the output of the aggregate production line in 24 hours, n is the total number of data of the j-th production parameter, and β 2j is the correlation degree between the i-th production parameter and the output of the aggregate production line in 24 hours;
[0019] Further, the weight of each production parameter is expressed by the following formula:
[0020]
[0021] where, β 1j is the information entropy weight of the j-th production parameter, β′ j is the intermediate weight of the j-th production parameter, β j is the weight of the j-th production parameter, and k is the total number of types of production parameters.
[0022] Further, the prediction model is expressed by the following formula:
[0023] Q = ρ t (β 1 Z 1 +β 2 Z 2 +...+βk Z k ) + b
[0024]
[0025] Among them, Q is the predicted output, and ρ t is the weight coefficient completed in the t-th training, and β k is the weight of the k-th production parameter, Z k is the k-th production parameter, b is the compensation amount, and ρ t-1 is the weight coefficient of the (t - 1)-th training, and ρ t-2 is the weight coefficient of the (t - 2)-th training, and ρ t-3 is the weight coefficient of the (t - 3)-th training.
[0026] In the second aspect of the present invention, a multi-variable aggregate output prediction system is proposed, including:
[0027] A collection module, which is used to collect historical data in the aggregate production line and preprocess the historical data to facilitate the removal of outliers;
[0028] A weighting module, which is used to perform weighted calculation on the preprocessed historical data to obtain the weights of the historical data, so as to improve the accuracy of the predicted output;
[0029] A prediction module, which is used to preprocess the target data in the aggregate production line, add weights, and then input it into the prediction model to complete the output prediction of the aggregate production line for 24 hours.
[0030] In the third aspect of the present invention, an electronic device is proposed, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a multi-variable aggregate output prediction method as described in the first aspect above.
[0031] In the fourth aspect of the present invention, a computer-readable storage medium is proposed. The storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the storage medium is located to execute a multi-variable aggregate output prediction method as described in the first aspect above.
[0032] Advantages of the present invention:
[0033] (1) The present invention proposes a multi-variable aggregate output prediction method. By solving the weights of the production parameters, combining the target production parameters with the weights, and inputting them into the prediction model, the output prediction of the aggregate production line for 24 hours is completed. The present invention can conveniently and quickly predict the aggregate output in the next 24 hours, and the prediction accuracy is high.
[0034] (2) The present invention combines the information entropy weight and the correlation degree to obtain the weight of each production parameter, and improves the connection between the production parameter and the output of the aggregate production line in 24 hours in the form of combined weights, thereby improving the accuracy of predicting the output of the aggregate production line in 24 hours. Description of the Drawings
[0035] Figure 1 It is a flowchart of a multi-variable aggregate output prediction method provided by an embodiment of the present invention.
[0036] Figure 2 It is an architecture diagram of a multi-variable aggregate output prediction system provided by an embodiment of the present invention. Detailed Embodiments
[0037] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.
[0038] Embodiment 1
[0039] As Figure 1 shown, a multi-variable aggregate output prediction method includes:
[0040] S101: Collect historical data in the aggregate production line and preprocess the historical data.
[0041] Specifically, collect the output of the aggregate production line in 24 hours and the corresponding production parameters within 24 hours. The production parameters are collected once every 24 hours. The production parameters include the feeding speed, raw material particle size, hardness of raw material type, power of the crushing equipment, particle size of the required aggregate, number of sieve layers of the screening equipment, time for cleaning the aggregate, and conveying equipment speed in the aggregate production line.
[0042] Delete the maximum and minimum values in the output of the aggregate production line in 24 hours and the corresponding production parameters within 24 hours to avoid interference of extreme values on the prediction result.
[0043] S102: Perform weighted calculation on the preprocessed historical data to obtain the weight of the historical data.
[0044] Specifically, normalize the target data respectively, calculate the information entropy of each production parameter after normalization, and calculate the information entropy weight according to the information entropy.
[0045] Calculate the correlation degree between the production parameter and the output of the aggregate production line in 24 hours respectively. The correlation degree is expressed by the following formula:
[0046]
[0047] Among them, X ij is the i-th data in the j-th production parameter, Y is the output of the aggregate production line in 24 hours, n is the total number of data of the j-th production parameter, and β 2j is the correlation degree between the i-th production parameter and the output of the aggregate production line in 24 hours.
[0048] The weight of each production parameter is obtained according to the information entropy weight and the correlation degree. The weight of each production parameter is expressed by the following formula:
[0049]
[0050] Among them, β 1j is the information entropy weight of the j-th production parameter, β′ j is the intermediate weight of the j-th production parameter, β j is the weight of the j-th production parameter, and k is the total number of types of production parameters.
[0051] S103: Preprocess the target data in the aggregate production line, add weights, and then input it into the prediction model to complete the prediction of the output of the aggregate production line in 24 hours.
[0052] Specifically, collect the target data in the aggregate production line. Since the output of the aggregate production line in 24 hours is required, the prediction target data includes the target production parameters. Delete the maximum and minimum values in the target production parameters to complete the preprocessing of the target production parameters. Then multiply the weight of each production parameter obtained by the corresponding target production parameter to obtain the weighted target production parameter.
[0053] Input the weighted target production parameter into the prediction model to obtain the predicted value of the output of the aggregate production line in 24 hours.
[0054] Suppose the optimal prediction model is obtained through t times of training. The prediction model is expressed by the following formula:
[0055] Q = ρ t (β 1 Z 1 + β 2 Z 2 +... + β k Z k ) + b
[0056]
[0057] Among them, Q is the predicted output, ρ t is the weight coefficient completed in the t-th training, and β kis the weight of the k-th production parameter, Z k is the k-th production parameter, b is the compensation amount, ρ t-1 is the weight coefficient of the (t - 1)-th training, ρ t-2 is the weight coefficient of the (t - 2)-th training, ρ t-3 is the weight coefficient of the (t - 3)-th training.
[0058] The weight coefficient and the compensation amount are solved by substituting historical data, and the weight coefficient and the compensation amount are continuously iteratively updated to obtain an optimal prediction model, so as to ensure the accuracy of the prediction model.
[0059] The present invention solves the weight of each production parameter through historical data, multiplies the weight by the corresponding production parameter. The present invention combines the information entropy weight and the correlation degree to obtain the weight of each production parameter, and improves the connection between the production parameter and the output of the aggregate production line in 24 hours in the form of combined weights, thereby improving the accuracy of predicting the output of the aggregate production line in 24 hours. Then, the weight is multiplied by the corresponding production parameter and input into the prediction model to obtain the predicted value of the output of the aggregate production line in 24 hours, which is fast and accurate as a whole.
[0060] Embodiment 2
[0061] Based on the above embodiment, the embodiment of the present invention provides a multi-variable aggregate output prediction system, including:
[0062] A collection module, configured to collect historical data in the aggregate production line and preprocess the historical data.
[0063] A weighting module, configured to perform weighted calculation on the preprocessed historical data to obtain the weight of the historical data.
[0064] A prediction module, configured to preprocess the target data in the aggregate production line, add weights and then input them into the prediction model to complete the prediction of the output of the aggregate production line in 24 hours.
[0065] It should be noted that the multi-variable aggregate output prediction system provided by the embodiment of the present invention is to implement the above-mentioned multi-variable aggregate output prediction method, and its functions can be specifically referred to the above-mentioned method embodiments, which will not be elaborated here.
[0066] Embodiment 4
[0067] Based on the above embodiment, the embodiment of the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the above-mentioned multi-variable aggregate output prediction method in the above embodiment.
[0068] The present invention also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the storage medium is located to execute a multi-variable aggregate output prediction method in the above embodiments.
[0069] In summary, the present invention proposes a multi-variable aggregate output prediction method. By solving the weights of production parameters, combining the target production parameters with the weights, and inputting them into the prediction model, the output of the aggregate production line for 24 hours is predicted. The present invention can conveniently and quickly predict the aggregate output for the next 24 hours, and the prediction accuracy is high. The present invention combines information entropy weight and correlation degree to obtain the weight of each production parameter, and improves the connection between the production parameters and the output of the aggregate production line for 24 hours in the form of combined weights, thereby improving the accuracy of predicting the output of the aggregate production line for 24 hours.
[0070] 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 recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A multivariate aggregate production prediction method, characterized in that: include: Step 1: Collect historical data from the aggregate production line and pre-process the historical data; Step 2: Perform weighted calculation on the preprocessed historical data to obtain the weight of the historical data; Step 3: Preprocess the target data in the aggregate production line, add weights, and input them into the prediction model to complete the 24-hour output prediction of the aggregate production line.
2. A multivariate aggregate production prediction method according to claim 1, characterized in that: The collecting of historical data in the aggregate production line and preprocessing of the historical data specifically include: Collect the output of the aggregate production line in 24 hours and the corresponding production parameters within 24 hours; the production parameters are collected once every 24 hours; the production parameters include the feeding speed, raw material particle size, raw material type and hardness, crushing equipment power, required aggregate particle size, number of screening layers of screening equipment, aggregate cleaning time and conveying equipment speed in the aggregate production line; Delete the 24-hour output of the aggregate production line and the maximum and minimum values of the corresponding production parameters within 24 hours.
3. A multivariate aggregate production prediction method according to claim 2, characterized in that: The second step comprises: Normalize the target data respectively, calculate the information entropy of each production parameter after normalization, and calculate the information entropy weight according to the information entropy; Calculate the correlation between production parameters and the 24-hour output of the aggregate production line; The weight of each production parameter is obtained according to the information entropy weight and correlation.
4. A multivariate aggregate production prediction method according to claim 3, characterized in that: The correlation is expressed by the following formula: Among them, X ij is the i-th data of the j-th production parameter, Y is the output of the aggregate production line in 24 hours, n is the total number of data of the j-th production parameter, β 2j is the correlation between the ith production parameter and the 24-hour output of the aggregate production line.
5. A multivariate aggregate production prediction method according to claim 4, characterized in that: The weight of each production parameter is expressed by the following formula: Among them, β 1j is the information entropy weight of the j-th production parameter, β′ j is the intermediate weight of the j-th production parameter, β j is the weight of the j-th production parameter, and k is the total number of production parameter types.
6. A multivariate aggregate production prediction method according to claim 1, characterized in that: The prediction model is expressed as follows: Q=ρ t (β1Z1+β2Z2+...+β k Z k )+b Where Q is the predicted output, ρ t is the weight coefficient completed after the tth training, β k is the weight of the k-th production parameter, Z k is the kth production parameter, b is the compensation amount, ρ t-1 is the weight coefficient of the t-1th training, ρ t-2 is the weight coefficient of the t-2th training, ρ t-3 is the weight coefficient for the t-3th training.
7. A multivariate aggregate production prediction system, characterized in that: include: The collection module is used to collect historical data in the aggregate production line and pre-process the historical data; A weighting module is used to perform weighted calculation on the preprocessed historical data to obtain the weight of the historical data; The prediction module is used to pre-process the target data in the aggregate production line, add weights, and then input them into the prediction model to complete the 24-hour output prediction of the aggregate production line.
8. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a multivariate aggregate production prediction method as claimed in any one of claims 1 to 6 is implemented.
9. A computer-readable storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a multivariate aggregate production prediction method as claimed in any one of claims 1 to 6.