Multi-source building solid waste processing control system and method

Abstract

The invention relates to the technical field of building solid waste processing, in particular to a multi-source building solid waste processing control system and method, and the system comprises a server side and a production side corresponding to a solid waste recycled aggregate production line. The server side comprises a data acquisition module, a prediction module, a solid waste type identification module and a processing parameter adjustment module, and the processing parameter adjustment module is used for processing a certain batch of building solid waste according to the identified solid waste type of the corresponding batch of building solid waste before the solid waste recycled aggregate production line processes the certain batch of building solid waste. And adjusting the processing parameters corresponding to the solid waste recycled aggregate production line and feeding back the adjusted processing parameters to the production end corresponding to the solid waste recycled aggregate production line based on the particle size of the recycled aggregate required by road construction corresponding to the next time period and the quantitative proportion corresponding to each particle size.

Description

Technical Field

[0001] The present invention relates to the technical field of construction solid waste processing, and in particular to a multi-source construction solid waste processing control system and method. Background Art

[0002] With the acceleration of urbanization, the amount of construction solid waste has increased dramatically, becoming a major problem in urban development. Traditional treatment methods such as landfill and stacking not only occupy a large amount of land resources, but also cause environmental pollution. Therefore, converting construction solid waste into recycled aggregates for road construction projects has become an environmentally friendly and economical choice.

[0003] However, there are still some common problems in the existing solid waste recycled aggregate production lines:

[0004] The existing system is difficult to accurately predict the demand and particle size requirements for recycled aggregates in the future, resulting in overproduction or underproduction.

[0005] Due to the wide variety of construction solid waste, different types of solid waste correspond to different processing parameters, which requires manual adjustment of processing parameters during specific processing, resulting in low processing efficiency. Summary of the invention

[0006] One of the purposes of the present invention is to provide a multi-source construction solid waste processing control system and method, which can quickly determine the construction solid waste processing needs and corresponding processing parameters, greatly improve the processing efficiency while also avoiding the problem of overproduction.

[0007] In order to achieve the above-mentioned purpose, a multi-source construction solid waste processing control system is provided, including a service end and a production end corresponding to a solid waste recycled aggregate production line;

[0008] The server includes:

[0009] The data acquisition module is used to obtain the road construction data corresponding to the current time period and the geological data corresponding to the road when processing the recycled aggregate for each batch of construction solid waste in the next time period;

[0010] A prediction module is used to predict the road construction length corresponding to the next time period based on the current road construction data and the corresponding geological data and based on a preset road construction prediction model, and to determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size according to the predicted road construction length of the next time period;

[0011] The solid waste type identification module is used to identify the solid waste type corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line within the next time period;

[0012] The processing parameter adjustment module is used to adjust the processing parameters corresponding to the solid waste recycled aggregate production line before the solid waste recycled aggregate production line processes a batch of construction solid waste, based on the solid waste type of the corresponding batch of construction solid waste identified, based on the particle size of recycled aggregate required for road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, and feed back the adjusted processing parameters to the production end corresponding to the solid waste recycled aggregate production line;

[0013] The production end is used to adjust the solid waste recycled aggregate production line according to the adjusted processing parameters, and to process the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line.

[0014] Technical principles and effects of this scheme: In this scheme, when it is necessary to process recycled aggregates for each batch of construction solid waste in the next time period, the road construction data of the current time period and the geological data corresponding to the road will be obtained. Through these acquired data, based on the pre-set road construction prediction model, the road construction length corresponding to the next time period is predicted. The prediction results can be used to more intuitively and accurately know the specific situation of the road construction in the next time period. Then, according to the predicted road construction length of the next time period, the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size can be determined.

[0015] After that, when the next time period arrives, the solid waste types corresponding to the batches of construction solid waste on the solid waste recycled aggregate production line within the time period are identified, and then before the solid waste recycled aggregate production line processes a batch of construction solid waste in the next time period, the solid waste recycled aggregate production line first uses the solid waste type of the corresponding batch, the particle size of the recycled aggregate required for the road construction corresponding to the next time period, and the quantity ratio corresponding to each particle size to adjust the processing parameters corresponding to the solid waste recycled aggregate production line, so that the adjusted processing parameters can accurately process the corresponding batch of construction solid waste and obtain recycled aggregate that meets the requirements. After the adjustment is completed, the corresponding processing parameters are fed back to the production end corresponding to the solid waste recycled aggregate production line. Finally, the production end will adjust the entire production line after receiving the adjusted processing parameters, and then the corresponding batch of construction solid waste is processed into recycled aggregate through the adjusted solid waste recycled aggregate production line.

[0016] 1. Through the pre-built road construction prediction model, the road construction situation in the future can be predicted in advance and accurately, so as to prepare the types and proportions of recycled aggregates required in advance and improve the accuracy of production plans.

[0017] 2. Taking into full consideration the wide variety of solid waste types corresponding to the construction solid waste to be processed by the solid waste aggregate production line, the processing of the solid waste aggregate production line needs to be dynamically adjusted. This solution uses the type of construction solid waste to be processed, combined with the particle size of the recycled aggregate required in the next time period and the quantity ratio of each particle size, to accurately and reliably determine the processing parameters of the solid waste aggregate production line, and then realize that each batch of construction solid waste has its own corresponding processing parameters when it is processed in the next time period, ensuring that when facing different types of construction solid waste, recycled aggregates that meet the requirements can be processed, thereby improving product quality and production efficiency.

[0018] Furthermore, the server also includes:

[0019] The historical data collection module is used to obtain the historical road construction data, the corresponding historical geological data and the corresponding historical road construction length corresponding to the current road in each historical time period, form a corresponding historical data set, and divide the data in the historical data set into a training set and a test set;

[0020] Model building module, used to build road construction prediction model;

[0021] The training module is used to randomly generate several hyperparameter groups corresponding to the hyperparameters of the road construction prediction model according to the constructed road construction prediction model, form a corresponding hyperparameter set, and identify the optimal hyperparameter combination based on the data in the training set and the improved optimization algorithm.

[0022] Beneficial effects: Use historical data to train the model, ensuring that the model's predictive ability is based on a rich data foundation. By randomly generating hyperparameter combinations and improved optimization algorithms, the optimal hyperparameter combination can be efficiently found to improve the model's prediction accuracy. The improved optimization algorithm can find the optimal solution under limited computing resources, saving time and computing costs. By dividing the training set and the test set, the generalization ability and reliability of the model are ensured.

[0023] Furthermore, the training module includes:

[0024] A data generation module is used to randomly generate a plurality of hyperparameter groups corresponding to various hyperparameters corresponding to the road construction prediction models to form a corresponding initial population;

[0025] It is also used to obtain the road planning data corresponding to the current road, select the road planning data corresponding to other roads that have been completed from the database based on the road planning data of the current road, calculate the road planning similarity between the current road and other roads that have been completed based on a preset road planning similarity calculation formula, and sort the other roads that have been completed in order of road planning similarity from large to small to form a corresponding similarity arrangement table, select the corresponding roads that have been completed from the similarity arrangement table based on a preset selection ratio and retrieve the corresponding hyperparameter group, and merge the retrieved hyperparameter group into the initial population;

[0026] The preliminary screening module is used to perform preliminary screening and judgment on the initial population according to the corresponding initial population based on the preset restriction conditions. If the restriction conditions are met, the corresponding initial population is a feasible solution, otherwise it is an infeasible solution;

[0027] The loss calculation module is used to form a road construction prediction model corresponding to each hyperparameter group in the population according to the selected population, and input the historical road construction data and the corresponding historical geological data in the training set as input data into the road construction prediction model corresponding to each hyperparameter group, and output the corresponding predicted road construction length;

[0028] According to the predicted road construction length and the historical road construction length, the loss value corresponding to each hyperparameter group is calculated based on the preset loss calculation formula;

[0029] The preset loss calculation formula is:

[0030]

[0031] In the formula, S i is the loss value corresponding to the i-th hyperparameter group, m is the total number of hyperparameter groups, L ij is the historical road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, is the predicted road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, N i is the total number of input data corresponding to the i-th hyperparameter group;

[0032] A processing module is used to sort the calculated loss values ​​corresponding to each hyperparameter group in ascending order to obtain a corresponding loss value arrangement table; according to the loss value arrangement table, identify the number of hyperparameter groups in the loss value arrangement table and the loss values ​​corresponding to the preset selection ranking; based on the number of hyperparameter groups and the loss values ​​corresponding to the preset selection ranking, calculate the actual selection ranking corresponding to this iteration, and based on the determined actual selection ranking, select and identify the corresponding loss value arrangement table to identify the hyperparameter groups corresponding to each selected loss value;

[0033] The parameter adjustment module is used to identify the hyperparameter groups corresponding to the selected loss values, perform hybridization and mutation on each hyperparameter group, and obtain the corresponding offspring population;

[0034] A loop module is used to continue executing the loss calculation module after obtaining the offspring population until a preset number of iterations is met;

[0035] The output module is used to output the offspring population as the optimal solution set for multi-objective optimization.

[0036] Beneficial effects: In this solution, there are two main ways to generate hyperparameter groups: one is to generate them randomly, and the other is to introduce hyperparameter combinations of similar roads, which enriches the diversity of the initial population and increases the possibility of finding a better solution. Selecting hyperparameter combinations based on road planning similarity makes model training more targeted, improves the prediction accuracy of the model, and greatly improves the convergence speed.

[0037] By calculating the loss value, the predictive performance of each hyperparameter combination can be quantitatively evaluated. The loss value provides a basis for the subsequent optimization process and helps identify hyperparameter combinations with better performance. According to the calculated loss values ​​corresponding to each hyperparameter group, sort them in order from small to large to obtain the corresponding loss value arrangement table. Identify the number of hyperparameter groups in the loss value arrangement table and the loss values ​​corresponding to the preset selection ranking. Based on the number of hyperparameter groups and the loss values ​​corresponding to the preset selection ranking, calculate the actual selection ranking corresponding to this iteration and select the corresponding hyperparameter group. Through sorting and selection, it is ensured that the best performing hyperparameter combination is selected, and the dynamic adjustment of the actual selection ranking is realized in each iteration, which greatly improves the reliability and flexibility of the selection in each iteration. Increase the diversity of the population through hybridization and mutation, increase the chance of finding the optimal solution, and then improve the stability and robustness of the optimization process. Through multiple iterative training, continuously optimize the hyperparameter combination and gradually approach the optimal solution

[0038] Furthermore, the calculation formula for calculating the actual selected ranking corresponding to this iteration based on the number of hyperparameter groups and the loss value corresponding to the preset selected ranking is:

[0039]

[0040] Where M is the actual selected ranking corresponding to this iteration, To round up the ranking calculated by K+∝(NK)×(2U-1), K is the preset ranking, N is the number of hyperparameter groups, and S K is the loss value corresponding to the preset ranking, S Y is the preset loss threshold, P is a random positive integer from 0 to N, U is a random variable from 0 to 1, and ∝ is an adjustment factor ranging from 0 to 1.

[0041] Beneficial effects: In this scheme, firstly, the actual selected ranking corresponding to each iteration is associated with the number of hyperparameter groups and the loss value corresponding to the preset selected ranking, which realizes the dynamic change of the actual selected ranking and improves the reliability and feasibility of the actual selected ranking in each iteration. Secondly, when calculating the actual selected ranking, by introducing random variables and random positive integers, the randomness of the determination of the actual selected ranking is increased, making the exploration process more diversified, avoiding over-reliance on the preset selected ranking, and being more flexible and reliable.

[0042] Finally, the degree of random disturbance can be controlled by adjusting the factor, making the fluctuation range of the actual selected ranking controllable, which helps to flexibly adjust the balance between exploration and utilization in different iteration stages.

[0043] Furthermore, the server also includes a verification module, which is used to input the historical road construction data and historical geological data in the test set as input data into the road construction prediction model corresponding to each hyperparameter group according to the output hyperparameter groups corresponding to the offspring population, output the prediction data corresponding to each hyperparameter, and based on the historical road construction length corresponding to the input data in the test set and the prediction data corresponding to each hyperparameter, select the hyperparameter group with the smallest loss value from the offspring population as the optimal hyperparameter group.

[0044] Beneficial effects: By verifying the test set data, we can ensure that the model not only performs well on the training set, but also maintains a high prediction accuracy on unseen data. This can more accurately evaluate the performance of the model, avoid overfitting, and ensure the reliability and robustness of the model.

[0045] The present invention also provides a multi-source construction solid waste processing control method, using the multi-source construction solid waste processing control system mentioned above, comprising the following steps:

[0046] S1. When processing recycled aggregates for each batch of construction solid waste in the next time period, obtain the road construction data corresponding to the current time period and the geological data corresponding to the road;

[0047] S2. According to the current road construction data and the corresponding geological data, based on a preset road construction prediction model, predict the road construction length corresponding to the next time period, and according to the predicted road construction length of the next time period, determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size;

[0048] S3. In the next time period, identify the solid waste types corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line;

[0049] S4. Before the solid waste recycled aggregate production line processes a batch of construction solid waste, according to the solid waste type of the corresponding batch of construction solid waste identified, based on the particle size of recycled aggregate required for road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, the processing parameters corresponding to the solid waste recycled aggregate production line are adjusted and the adjusted processing parameters are fed back to the production end corresponding to the solid waste recycled aggregate production line;

[0050] S5. The production end adjusts the solid waste recycled aggregate production line according to the adjusted processing parameters, and processes the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a logic block diagram of a multi-source construction solid waste processing control system in Embodiment 1 of the present invention;

[0052] Figure 2 This is a flow chart of the multi-source construction solid waste processing control method in the first embodiment of the invention. DETAILED DESCRIPTION

[0053] The following is further described in detail through specific implementation methods:

[0054] Embodiment 1

[0055] A multi-source construction solid waste processing control system, basically as follows Figure 1 As shown, it includes the service end and the production end corresponding to the solid waste recycled aggregate production line;

[0056] The server includes:

[0057] The data acquisition module is used to obtain the road construction data corresponding to the current time period and the geological data corresponding to the road when processing recycled aggregates for each batch of construction solid waste in the next time period; in this embodiment, the road construction data includes road construction length, road construction environment data, road construction progress and road construction difficulty, etc.

[0058] A prediction module is used to predict the road construction length corresponding to the next time period based on the current road construction data and the corresponding geological data and based on a preset road construction prediction model, and to determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size according to the predicted road construction length of the next time period;

[0059] The solid waste type identification module is used to identify the solid waste types corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line within the next time period; in this embodiment, the solid waste types include brick-concrete type, concrete type, and waste cement stabilized type, etc.

[0060] In this embodiment, the particle size of the recycled aggregate is set according to demand. For example, in a certain demand, when processing construction solid waste corresponding to brick and concrete, the required particle sizes are 20 to 40 mm, 10 to 20 mm, 5 to 10 mm and less than 5 mm; after subsequent processing, the mass proportions of different types of aggregates obtained are as shown in the following table, among which the mass proportions of crushed stone, mortar blocks and red brick blocks exceed 95%.

[0061]

[0062] Table 1 Mass proportion of different types of recycled aggregates in each particle size range for brick-concrete

[0063] The processing parameter adjustment module is used to adjust the processing parameters corresponding to the solid waste recycled aggregate production line according to the identified solid waste type of the corresponding batch of construction solid waste, based on the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, and feed back the adjusted processing parameters to the production end corresponding to the solid waste recycled aggregate production line before the solid waste recycled aggregate production line processes a batch of construction solid waste. In this embodiment, for example, when the particle size of the recycled aggregate that can be processed by a solid waste recycled aggregate production line is divided into four types, then a processing parameter table corresponding to the quantity ratio of each particle size corresponding to each solid waste type is stored in the database, and the processing parameter table includes the processing parameters generated by the solid waste recycled aggregate corresponding to all quantity ratios of each particle size for all solid waste types. Then, after determining the solid waste type, the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, the processing parameters associated with the quantity ratio of the particle size corresponding to the corresponding solid waste type can be selected from the processing parameter table and fed back to the solid waste recycled aggregate production line.

[0064] The production end is used to adjust the solid waste recycled aggregate production line according to the adjusted processing parameters, and to process the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line.

[0065] The server also includes:

[0066] The historical data collection module is used to obtain the historical road construction data, the corresponding historical geological data and the corresponding historical road construction length corresponding to the current road in each historical time period, form a corresponding historical data set, and divide the data in the historical data set into a training set and a test set;

[0067] Model building module, used to build road construction prediction model;

[0068] The training module is used to randomly generate several hyperparameter groups corresponding to the hyperparameters of the road construction prediction model according to the constructed road construction prediction model, form a corresponding hyperparameter set, and identify the optimal hyperparameter combination based on the data in the training set and the improved optimization algorithm.

[0069] The training module includes:

[0070] A data generation module is used to randomly generate a plurality of hyperparameter groups corresponding to various hyperparameters corresponding to the road construction prediction models to form a corresponding initial population;

[0071] It is also used to obtain the road planning data corresponding to the current road, select the road planning data corresponding to other roads that have been completed from the database based on the road planning data of the current road, calculate the road planning similarity between the current road and other roads that have been completed based on a preset road planning similarity calculation formula, and sort the other roads that have been completed in order of road planning similarity from large to small to form a corresponding similarity arrangement table, select the corresponding roads that have been completed from the similarity arrangement table based on a preset selection ratio and retrieve the corresponding hyperparameter group, and merge the retrieved hyperparameter group into the initial population;

[0072] The preliminary screening module is used to perform preliminary screening and judgment on the initial population according to the corresponding initial population based on the preset restriction conditions. If the restriction conditions are met, the corresponding initial population is a feasible solution, otherwise it is an infeasible solution;

[0073] The loss calculation module is used to form a road construction prediction model corresponding to each hyperparameter group in the population according to the selected population, and input the historical road construction data and the corresponding historical geological data in the training set as input data into the road construction prediction model corresponding to each hyperparameter group, and output the corresponding predicted road construction length;

[0074] According to the predicted road construction length and the historical road construction length, the loss value corresponding to each hyperparameter group is calculated based on the preset loss calculation formula;

[0075] The preset loss calculation formula is:

[0076]

[0077] In the formula, S i is the loss value corresponding to the i-th hyperparameter group, m is the total number of hyperparameter groups, L ij is the historical road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, is the predicted road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, N i is the total number of input data corresponding to the i-th hyperparameter group;

[0078] A processing module is used to sort the calculated loss values ​​corresponding to each hyperparameter group in ascending order to obtain a corresponding loss value arrangement table; according to the loss value arrangement table, identify the number of hyperparameter groups in the loss value arrangement table and the loss values ​​corresponding to the preset selection ranking; based on the number of hyperparameter groups and the loss values ​​corresponding to the preset selection ranking, calculate the actual selection ranking corresponding to this iteration, and based on the determined actual selection ranking, select and identify the corresponding loss value arrangement table to identify the hyperparameter groups corresponding to each selected loss value;

[0079] The calculation formula for calculating the actual selected ranking corresponding to this iteration based on the number of hyperparameter groups and the loss value corresponding to the preset selected ranking is:

[0080]

[0081] Where M is the actual selected ranking corresponding to this iteration, To round up the ranking calculated by K+∝(NK)×(2U-1), K is the preset ranking, N is the number of hyperparameter groups, and S K is the loss value corresponding to the preset ranking, S Y is the preset loss threshold, P is a random positive integer from 0 to N, U is a random variable from 0 to 1, and ∝ is an adjustment factor ranging from 0 to 1.

[0082] The parameter adjustment module is used to identify the hyperparameter groups corresponding to the selected loss values, perform hybridization and mutation on each hyperparameter group, and obtain the corresponding offspring population;

[0083] A loop module is used to continue executing the loss calculation module after obtaining the offspring population until a preset number of iterations is met;

[0084] The output module is used to output the offspring population as the optimal solution set for multi-objective optimization.

[0085] The server also includes a verification module, which is used to input the historical road construction data and historical geological data in the test set as input data into the road construction prediction model corresponding to each hyperparameter group according to the output hyperparameter groups corresponding to the offspring population, output the prediction data corresponding to each hyperparameter, and based on the historical road construction length corresponding to the input data in the test set and the prediction data corresponding to each hyperparameter, select the hyperparameter group with the smallest loss value from the offspring population as the optimal hyperparameter group.

[0086] like Figure 2 As shown, this embodiment also discloses a multi-source construction solid waste processing control method, using the multi-source construction solid waste processing control system mentioned above, including the following steps:

[0087] S1. When processing recycled aggregates for each batch of construction solid waste in the next time period, obtain the road construction data corresponding to the current time period and the geological data corresponding to the road;

[0088] S2. According to the current road construction data and the corresponding geological data, based on a preset road construction prediction model, predict the road construction length corresponding to the next time period, and according to the predicted road construction length of the next time period, determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size;

[0089] S3. In the next time period, identify the solid waste types corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line;

[0090] S4. Before the solid waste recycled aggregate production line processes a batch of construction solid waste, according to the solid waste type of the corresponding batch of construction solid waste identified, based on the particle size of recycled aggregate required for road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, the processing parameters corresponding to the solid waste recycled aggregate production line are adjusted and the adjusted processing parameters are fed back to the production end corresponding to the solid waste recycled aggregate production line;

[0091] S5. The production end adjusts the solid waste recycled aggregate production line according to the adjusted processing parameters, and processes the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line.

[0092] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is described too much here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A multi-source construction solid waste processing control system, characterized by: Including the service end and the production end corresponding to the solid waste recycled aggregate production line; The server includes: The data acquisition module is used to obtain the road construction data corresponding to the current time period and the geological data corresponding to the road when processing the recycled aggregate for each batch of construction solid waste in the next time period; A prediction module is used to predict the road construction length corresponding to the next time period based on the current road construction data and the corresponding geological data and based on a preset road construction prediction model, and to determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size according to the predicted road construction length of the next time period; The solid waste type identification module is used to identify the solid waste type corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line within the next time period; The processing parameter adjustment module is used to adjust the processing parameters corresponding to the solid waste recycled aggregate production line before the solid waste recycled aggregate production line processes a batch of construction solid waste, based on the solid waste type of the corresponding batch of construction solid waste identified, based on the particle size of recycled aggregate required for road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, and feed back the adjusted processing parameters to the production end corresponding to the solid waste recycled aggregate production line; The production end is used to adjust the solid waste recycled aggregate production line according to the adjusted processing parameters, and to process the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line.

2. A multi-source construction solid waste processing control system according to claim 1, characterized in that: The server also includes: The historical data collection module is used to obtain the historical road construction data, the corresponding historical geological data and the corresponding historical road construction length corresponding to the current road in each historical time period, form a corresponding historical data set, and divide the data in the historical data set into a training set and a test set; Model building module, used to build road construction prediction model; The training module is used to randomly generate several hyperparameter groups corresponding to the hyperparameters of the road construction prediction model according to the constructed road construction prediction model, form a corresponding hyperparameter set, and identify the optimal hyperparameter combination based on the data in the training set and the improved optimization algorithm.

3. A multi-source construction solid waste processing control system according to claim 2, characterized in that: The training module includes: A data generation module is used to randomly generate a plurality of hyperparameter groups corresponding to various hyperparameters corresponding to the road construction prediction models to form a corresponding initial population; It is also used to obtain the road planning data corresponding to the current road, select the road planning data corresponding to other roads that have been completed from the database based on the road planning data of the current road, calculate the road planning similarity between the current road and other roads that have been completed based on a preset road planning similarity calculation formula, and sort the other roads that have been completed in order of road planning similarity from large to small to form a corresponding similarity arrangement table, select the corresponding roads that have been completed from the similarity arrangement table based on a preset selection ratio and retrieve the corresponding hyperparameter group, and merge the retrieved hyperparameter group into the initial population; The preliminary screening module is used to perform preliminary screening and judgment on the initial population according to the corresponding initial population based on the preset restriction conditions. If the restriction conditions are met, the corresponding initial population is a feasible solution, otherwise it is an infeasible solution; The loss calculation module is used to form a road construction prediction model corresponding to each hyperparameter group in the population according to the selected population, and input the historical road construction data and the corresponding historical geological data in the training set as input data into the road construction prediction model corresponding to each hyperparameter group, and output the corresponding predicted road construction length; According to the predicted road construction length and the historical road construction length, the loss value corresponding to each hyperparameter group is calculated based on the preset loss calculation formula; The preset loss calculation formula is: In the formula, S i is the loss value corresponding to the i-th hyperparameter group, m is the total number of hyperparameter groups, L ij is the historical road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, is the predicted road construction length corresponding to the jth input data corresponding to the i-th hyperparameter group, N i is the total number of input data corresponding to the i-th hyperparameter group; A processing module is used to sort the calculated loss values ​​corresponding to each hyperparameter group in ascending order to obtain a corresponding loss value arrangement table; according to the loss value arrangement table, identify the number of hyperparameter groups in the loss value arrangement table and the loss values ​​corresponding to the preset selection ranking; based on the number of hyperparameter groups and the loss values ​​corresponding to the preset selection ranking, calculate the actual selection ranking corresponding to this iteration, and based on the determined actual selection ranking, select and identify the corresponding loss value arrangement table to identify the hyperparameter groups corresponding to each selected loss value; The parameter adjustment module is used to identify the hyperparameter groups corresponding to the selected loss values, perform hybridization and mutation on each hyperparameter group, and obtain the corresponding offspring population; A loop module is used to continue executing the loss calculation module after obtaining the offspring population until a preset number of iterations is met; The output module is used to output the offspring population as the optimal solution set for multi-objective optimization.

4. A multi-source construction solid waste processing control system according to claim 3, characterized in that: The calculation formula for calculating the actual selected ranking corresponding to this iteration based on the number of hyperparameter groups and the loss value corresponding to the preset selected ranking is: Where M is the actual selected ranking corresponding to this iteration, To round up the ranking calculated by K+∝(NK)×(2U-1), K is the preset ranking, N is the number of hyperparameter groups, and S K is the loss value corresponding to the preset ranking, S Y is the preset loss threshold, P is a random positive integer from 0 to N, U is a random variable from 0 to 1, and ∝ is an adjustment factor ranging from 0 to 1.

5. A multi-source construction solid waste processing control system according to claim 4, characterized in that: The server also includes a verification module, which is used to input the historical road construction data and historical geological data in the test set as input data into the road construction prediction model corresponding to each hyperparameter group according to the output hyperparameter groups corresponding to the offspring population, output the prediction data corresponding to each hyperparameter, and based on the historical road construction length corresponding to the input data in the test set and the prediction data corresponding to each hyperparameter, select the hyperparameter group with the smallest loss value from the offspring population as the optimal hyperparameter group.

6. A multi-source construction solid waste processing control method, using a multi-source construction solid waste processing control system according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. When processing recycled aggregates for each batch of construction solid waste in the next time period, obtain the road construction data corresponding to the current time period and the geological data corresponding to the road; S2. According to the current road construction data and the corresponding geological data, based on a preset road construction prediction model, predict the road construction length corresponding to the next time period, and according to the predicted road construction length of the next time period, determine the particle size of the recycled aggregate required for the road construction corresponding to the next time period and the quantity ratio corresponding to each particle size; S3. In the next time period, identify the solid waste types corresponding to each batch of construction solid waste on the solid waste recycled aggregate production line; S4. Before the solid waste recycled aggregate production line processes a batch of construction solid waste, according to the solid waste type of the corresponding batch of construction solid waste identified, based on the particle size of recycled aggregate required for road construction corresponding to the next time period and the quantity ratio corresponding to each particle size, the processing parameters corresponding to the solid waste recycled aggregate production line are adjusted and the adjusted processing parameters are fed back to the production end corresponding to the solid waste recycled aggregate production line; S5. The production end adjusts the solid waste recycled aggregate production line according to the adjusted processing parameters, and processes the corresponding batches of construction solid waste into recycled aggregate based on the adjusted solid waste recycled aggregate production line.

Images