Intelligent system of mixing station

Abstract

The invention belongs to the field of engineering construction, and relates to a mixing station intelligent system, which comprises a production control module used for controlling production equipment according to a production plan and a preset raw material mixing ratio and monitoring the raw material ratio; the transportation management module is used for optimizing a vehicle transportation route and task allocation based on a genetic algorithm when the vehicle is transported, taking an optimized parameter as a transportation route and an allocation result, and generating vehicle transportation information according to a vehicle transportation condition; the material management module is used for analyzing the material use condition according to the mixing station production information and the construction site information; the data management and information sharing module is used for collecting mixing station production information, construction site information and material use conditions, and generating a section exceeding report and a daily production accounting report; and the report query and message pushing module is used for querying reports and pushing matching early warning, vehicle transportation information, mixing station production progress information and construction progress information to corresponding personnel. The problems of low production efficiency and high cost are solved.

Description

Technical Field

[0001] The present invention belongs to the field of engineering construction, and particularly relates to an intelligent system for a mixing plant. Background Art

[0002] A mixing plant is a core facility in the concrete construction process, mainly used for the production, mixing, and transportation of concrete. It plays a crucial role in infrastructure construction (such as roads, bridges, tunnels, building construction, etc.). With the continuous expansion of the scale of engineering construction and the continuous improvement of technical requirements, the management efficiency and construction quality of the mixing plant directly affect the overall progress and cost control of the project.

[0003] Traditional management of mixing plants mainly relies on manual operations, including the formulation of production plans, the recording and reporting of data, the statistics and analysis of reports, etc. However, with the expansion of the project scale and the increase in construction complexity, traditional management methods have gradually revealed problems such as low efficiency, data distortion, and cost out of control, making it difficult to meet the needs of modern construction. All types of business management, such as plan formulation, scheduling arrangement, operation execution, and approval processes, rely on manual operations. The processes are cumbersome, error-prone, consume a large amount of manpower and material resources, and the data sharing among multiple departments is not smooth, resulting in information asymmetry. Production scheduling is prone to errors, leading to problems such as low production efficiency; in terms of cost and quality monitoring, there is a lack of real-time monitoring of material usage and operation processes, which easily leads to abnormal costs such as leakage, as well as problems such as material loss, low equipment utilization rate, and unnecessary losses, resulting in difficult cost control. Summary of the Invention

[0004] The present invention provides an intelligent system for a mixing plant to solve the problems of low production efficiency caused by difficult production scheduling and high costs caused by lack of control.

[0005] The basic solution provided by the present invention: An intelligent system for a mixing plant includes:

[0006] A production control module, used to control production equipment according to a production plan and a preset raw material mixing ratio, monitor the raw material mixing ratio, and generate a mixing ratio warning message;

[0007] A transportation management module, used to optimize the vehicle transportation route and task allocation based on a genetic algorithm when the vehicle is transporting, use the optimized parameters as the transportation route and allocation result, and generate vehicle transportation information according to the vehicle transportation situation;

[0008] A material management module, used to analyze the material usage situation according to the production information of the mixing plant and the construction site information, where the construction site information includes the construction site requirements and the construction progress;

[0009] The data management and information sharing module is used to collect the production information of the batching plant, the construction site information, and the material usage situation, and generate over-saving reports and daily production accounting reports.

[0010] The report query and message push module is used to query reports and push proportion warnings, vehicle transportation information, batching plant production progress information, and construction progress information to corresponding personnel.

[0011] The principle and advantages of the present invention are as follows: By using the production control module, the production equipment is automatically controlled, manual intervention is reduced, human errors are decreased, the production efficiency of the batching plant is improved, and the quality of concrete is ensured to be stable. Moreover, the raw material proportion is monitored in real time to generate proportion warning information, preventing quality accidents and risks. In the transportation management module, the genetic algorithm is used to optimize the vehicle transportation routes and task allocation, reducing transportation costs and time costs. At the same time, vehicle transportation information is generated according to the vehicle transportation situation, realizing the visualization management of the transportation process and eliminating the generation of abnormal costs such as running, leaking, etc. The material management module analyzes the material usage situation based on the production information of the batching plant and the construction site information, ensuring sufficient material supply, predicting material requirements according to the construction site needs and construction progress, avoiding material shortages or overstocking, thereby optimizing material usage, reducing material waste, and controlling project costs. The data management and information sharing module collects the production information of the batching plant, the construction site information, and the material usage situation, realizing the comprehensive integration of data. At the same time, over-saving reports and daily production accounting reports are automatically generated, not only reducing the workload of manually preparing reports, but also realizing the real-time sharing of data and improving management efficiency. Through the report query and message push module, users can be supported to query various reports, facilitating managers to understand the production, transportation, materials, etc. situations, and pushing proportion warnings, vehicle transportation information, production progress information, and construction progress information to corresponding personnel, enabling staff to timely understand the production information of the batching plant, discover problems in a timely manner and take measures, improving management efficiency and response speed, and ensuring the smooth progress of production operations.

[0012] Preferably, the transportation management module includes a vehicle positioning and control module, a transportation monitoring module, and a vehicle scheduling module. The vehicle transportation information includes vehicle position information and vehicle load information.

[0013] The vehicle positioning and control module is used to obtain the real-time position information of the transportation vehicle, record the driving track, and is also provided with an electronic fence area. When the vehicle enters or leaves the set area, vehicle position information is generated.

[0014] The transportation monitoring module is used to judge the overloading situation of the vehicle according to the weighing system measurement information and generate vehicle load information.

[0015] The vehicle scheduling module is used to run the genetic algorithm.

[0016] Beneficial effects: By obtaining the location information of transportation vehicles in real time and recording the driving trajectories, it provides accurate location data support for transportation management. Managers can always know the specific locations of the vehicles, which is convenient for real-time monitoring and dispatching of the transportation process. At the same time, it provides a basis for optimizing transportation routes and strengthening vehicle management; through the electronic fence, regional management of vehicles is realized, effectively preventing vehicles from deviating from the specified routes or entering unauthorized areas, and improving the safety and controllability of the transportation process; using the transportation monitoring module to judge the overloading situation of vehicles based on the weighing system measurement information and generate vehicle load information helps to ensure transportation safety and the integrity of road facilities, thereby reducing the risk of traffic accidents, minimizing damage to roads, and avoiding economic losses such as fines that may be faced due to overloading, safeguarding the interests and image of the enterprise;

[0017] The vehicle scheduling module runs a genetic algorithm to optimize the vehicle transportation routes and task assignments. Considering various factors (such as road conditions, transportation distance, delivery time, etc.), it finds the optimal or near-optimal vehicle scheduling plan, enabling more reasonable allocation of vehicle resources, improving transportation efficiency, and reducing transportation costs. Compared with traditional manual scheduling or simple rule-based scheduling, genetic algorithm-based vehicle scheduling can better adapt to complex and changeable transportation environments, achieving the maximization of the utilization of transportation resources and the maximization of transportation benefits.

[0018] Further preferably, the formula for calculating the fitness value is as follows:

[0019] Fitness = w1·C Tr + w2·C Ti + w3·C VU + w4·C Pe

[0020] In the formula, Fitness is the fitness value, w1, w2, w3, w4 are weight coefficients, and C Tr is the transportation cost, C Ti is the time cost, C VU is the vehicle utilization rate, C Pe is the constraint condition penalty term;

[0021] Among them, the weight coefficients are predicted using a BP neural network. Taking the transportation cost, time cost, vehicle utilization rate, and constraint condition penalty term as inputs and the fitness value as the output, the ReLU is used as the activation function for the hidden layer, and the mean squared error is used as the loss function.

[0022] Beneficial effects: The calculation of the fitness value comprehensively considers multiple key factors such as transportation costs, time costs, vehicle utilization rates, and constraint condition penalty terms, and balances the importance of each factor through weight coefficients. This method can comprehensively evaluate the advantages and disadvantages of transportation routes and task allocation schemes, avoiding the one-sidedness of decision-making caused by only considering a single factor, making the generated scheduling scheme more in line with actual needs, and contributing to the comprehensive optimization of transportation efficiency, cost control, and resource utilization; Using a BP neural network to predict the weight coefficients can dynamically adjust the weights of each factor according to different transportation scenarios and actual data. Compared with the method of fixed weights, the BP neural network can learn and adapt to the influence degree of each factor on the fitness value in different situations, improving the accuracy and flexibility of the fitness value calculation, making the scheduling scheme more inclined to choose routes with shorter times, and thus better coping with complex and changeable actual transportation situations.

[0023] Further preferably, the preset number of iterations is adjusted according to a preset dynamic adjustment rule, and the preset dynamic adjustment rule includes

[0024] If the change in the fitness value for ten consecutive generations is less than 0.01, then increase the number of iterations by 30%;

[0025] If the similarity of individuals in the population is greater than 90%, then increase the number of iterations by 30%;

[0026] If the utilization rate of computing resources is lower than 50%, then increase the number of iterations by 20%.

[0027] Beneficial effects: Dynamically adjust the number of iterations according to the algorithm running state and computing resource situation, ensure that the algorithm can run efficiently in different situations, avoid unnecessary waste of computing resources, improve the algorithm efficiency, enhance the robustness of the algorithm, and ensure that a better solution can be found in different situations.

[0028] Preferably, it further includes an environmental protection control module, and the environmental protection control module includes a pollution source monitoring sub-module and an energy conservation and emission reduction sub-module.

[0029] The pollution source monitoring sub-module uses a clustering algorithm to monitor the pollution sources generated by the mixing plant and vehicles in real time, analyzes the monitoring data, clusters the data with similar pollution characteristics into one category, and identifies the pollution type and source;

[0030] The energy conservation and emission reduction sub-module is used to optimize the production process and equipment operation parameters according to the monitored production process and equipment operation parameters.

[0031] Beneficial effects: By using a clustering algorithm to conduct real-time monitoring and data analysis of pollution sources, data with similar pollution characteristics can be clustered into one category, thereby accurately identifying the pollution type and source. This method can help the managers of the mixing plant quickly locate pollution problems, take targeted measures for treatment, and improve the accuracy and effectiveness of environmental protection management; Optimizing the production process and equipment operation parameters based on the monitored production process and equipment operation parameters helps improve energy utilization efficiency, reduce energy consumption and pollutant emissions. Through the refined management of the production process, the goal of energy conservation and emission reduction can be achieved while ensuring production quality, reducing production costs, and at the same time reducing the impact on the environment; Through intelligent monitoring and analysis means, real-time monitoring and dynamic management of the environmental protection status of the mixing plant are realized. Compared with the traditional manual monitoring and management methods, the work efficiency is greatly improved, the interference of human factors is reduced, environmental protection problems can be discovered and solved in a timely manner, and the environmental protection management level of the mixing plant is improved, meeting the requirements of sustainable development.

[0032] Preferably, the material management module includes a material inventory management sub-module, a material quality monitoring sub-module, and a material trend analysis sub-module.

[0033] The material inventory management sub-module is used to monitor the inventory status of various materials in the mixing plant in real time.

[0034] The material quality monitoring sub-module is used to monitor the material quality, record the material quality inspection results, and generate a material quality monitoring report.

[0035] The material trend analysis sub-module is used to predict the material usage trend information based on the production information of the mixing plant and the construction site information, and generate material requirements according to the material usage trend information and the construction site information.

[0036] Beneficial effects: Monitoring the inventory status of various materials in the mixing plant in real time allows managers to understand the reserve quantity of materials at any time. This helps avoid production stagnation caused by material shortages, or capital backlogs and resource waste caused by excessive inventory, realizing reasonable control of material inventory and ensuring the continuity and stability of production; The material quality monitoring sub-module monitors the material quality, details the material quality inspection results, and generates a material quality monitoring report to ensure that the materials put into production meet the quality requirements, guarantee product quality, and provide a basis for subsequent quality traceability. Once a quality problem occurs, the problematic material can be quickly located and corresponding measures can be taken to reduce the quality risk; Predicting the material usage trend information based on the production information of the mixing plant and the construction site information, and generating material requirements accordingly. This prediction method based on actual production and construction conditions can more accurately grasp the material requirements, make the procurement plan more scientific and reasonable, reduce material waste and backlogs, improve the efficiency and effectiveness of material management, and at the same time help optimize supply chain management and reduce procurement costs.

[0037] Preferably, it further includes a work order generation and push module, which is used to generate an application work order according to the input work plan, and is also used to push the application work order to the corresponding reviewer for review, and send the reviewed work order to the production control module to control the production equipment.

[0038] Beneficial effects: By automatically generating work orders, it ensures the standardization of the work order format and content, and pushes the generated work orders to the corresponding reviewers in real time to ensure the timely processing of work orders and improve management efficiency; sends the reviewed work orders to the production control module in real time to ensure the timely response of production equipment, and through the message push function, ensures that relevant personnel can timely understand the work order status and processing results; realizes the efficient management of the production process through the automatic generation, review and push of work orders, reducing manual intervention. Error reduction: Through the automated process, human errors are reduced, and the accuracy and compliance of work orders are improved; through real-time push and feedback, it ensures the timely response of production equipment to work orders, improves production efficiency, and through the message push function, ensures that relevant personnel can timely understand the work order status and processing results, improving information transparency.

[0039] Preferably, the production control module is further used to monitor the operating status of production equipment and analyze the equipment operating performance.

[0040] Beneficial effects: By real-time monitoring the operating status of production equipment, potential equipment failure hazards can be detected in a timely manner, avoiding production interruption caused by sudden equipment failures, thus ensuring the continuity of the mixing plant production and reducing economic losses caused by production stagnation; analyzing the equipment operating performance can deeply understand the operating conditions and performance change trends of the equipment, reducing the subjectivity and limitations of manual inspections and judgments, improving the automation and intelligent level of equipment management, promoting the development of the mixing plant towards digital and intelligent directions, and enhancing the overall management level and market competitiveness of the enterprise.

[0041] Preferably, it further includes a monitoring terminal, which is used to display proportion warning information, vehicle transportation information, mixing plant production progress information, and construction progress information.

[0042] Beneficial effects: By displaying vehicle transportation information through the monitoring terminal, dispatchers can real-time master the location, driving status, transportation progress, etc. of vehicles, so as to reasonably arrange vehicle dispatching, improve the transportation efficiency of vehicles, reduce vehicle waiting time and empty driving mileage, and reduce transportation costs; the rich and real-time information display provides strong support for managers to make decisions. Managers can, according to various information displayed on the monitoring terminal, timely discover bottleneck problems and potential risks in the production and construction processes, and thus make scientific and reasonable decisions, such as adjusting the production plan, optimizing resource allocation, solving problems such as lagging construction progress, etc., to ensure that the entire engineering project can be completed on time and with high quality. Brief Description of the Drawings

[0043] Figure 1 is the system block diagram of the present invention;

[0044] Figure 2 is the structure diagram of the vehicle management module of the present invention;

[0045] Figure 3 is the structure diagram of the vehicle scheduling module of the present invention;

[0046] Figure 4 is the structure diagram of the material management of the present invention. Detailed Description of the Invention

[0047] The following is a further detailed description through specific embodiments:

[0048] The specific implementation process is as follows: Refer to Figures 1 to 4 , a mixing plant intelligent system, including:

[0049] A production control module, used to control production equipment such as mixers according to the production plan and the preset raw material ratio, monitor the raw material ratio, and generate ratio warning information;

[0050] A transportation management module, used to optimize the vehicle transportation route and task assignment based on the genetic algorithm when the vehicle is transporting, use the optimization parameters as the transportation route and distribution result, and generate vehicle transportation information according to the vehicle transportation situation;

[0051] A material management module, used to analyze the material usage situation according to the production information of the mixing plant and the construction site information, and the construction site information includes the construction site requirements and the construction progress;

[0052] A data management and information sharing module, used to collect the production information of the mixing plant, the construction site information, and the material usage situation, and generate over - saving reports and daily production accounting reports;

[0053] A report query and message push module, used to query reports and push ratio warnings, vehicle transportation information, mixing plant production progress information, and construction progress information to the corresponding personnel.

[0054] Preferably, the production control module is also used to monitor the operating status of production equipment and analyze the equipment operating performance. Specifically, the production control module analyzes the historical equipment operation duration data through an autoregressive integrated moving average (ARIMA) model to predict the operation duration of the mixing equipment and raw material conveying equipment at different future time periods. For example, it predicts that within the next week, the operation duration of the mixing equipment will reach 3 to 4 hours every morning, which helps to arrange the equipment maintenance plan in advance, perform maintenance during the low operation period of the equipment, ensure the normal operation of the equipment, and avoid affecting production due to equipment failures; it is also used to predict the frequency of transport vehicles entering and leaving the batching plant in the future, so as to reasonably allocate vehicle resources. For example, the ARIMA model predicts that during the upcoming weekend, due to the concentrated construction of multiple surrounding projects, the frequency of transport vehicles entering and leaving will increase from 10 trips per hour on weekdays to 15 trips per hour. The batching plant can contact the transport fleet in advance and increase the vehicle input to ensure that the concrete is delivered to the construction site in a timely manner to meet the project progress requirements; the ARIMA model also combines the equipment operation duration and the vehicle entry and exit frequency to predict the change trend of the production load and production capacity of the batching plant. If it is predicted that within a certain period in the future, the equipment operation duration continues to increase and the vehicle entry and exit frequency rises synchronously, indicating an increase in production load and an increase in production capacity demand, the batching plant can adjust the raw material procurement plan accordingly and reserve sufficient raw materials such as cement and aggregates in advance to ensure the smooth progress of production.

[0055] Preferably, the transportation management module includes a vehicle positioning and control module, a transportation monitoring module, and a vehicle scheduling module. The vehicle transportation information includes vehicle location information and vehicle load information.

[0056] The vehicle positioning and control module is used to obtain the real-time position information of the transport vehicle, record the driving trajectory, and is also provided with an electronic fence area. When the vehicle enters or leaves the set area, vehicle position information is generated.

[0057] The transportation monitoring module is used to judge the overloading situation of the vehicle according to the weighing system measurement information and generate vehicle load information; the transportation monitoring module stores a vehicle rated load table formulated according to information such as the vehicle model, vehicle capacity, and driving route. When the vehicle weighing value exceeds the rated load, the rated load is found corresponding to the driving information such as the vehicle type, vehicle capacity, and driving route. When the vehicle exceeds the rated load, the system generates an overloading warning information.

[0058] The vehicle scheduling module is used to run the genetic algorithm.

[0059] The vehicle scheduling module includes

[0060] Data acquisition and preprocessing sub-module: It is used to collect vehicle transportation information, construction site demand information, and road condition information, and preprocess the collected data; the construction site demand information includes concrete demand, construction progress, and construction location information, and the intersection information includes route congestion, traffic restrictions, speed limits, etc.;

[0061] Initialization sub-module: It is used to randomly generate an initial population according to the traversed route and screen the population according to the constraint conditions, and the constraint conditions include vehicle capacity, time window, task completion, vehicle route continuity, road conditions, vehicle availability, and concrete supply continuity;

[0062] Fitness calculation sub-module: Evaluate and grade the transportation routes and task assignments in the initial population, and calculate the fitness value;

[0063] The formula for calculating the fitness value is as follows:

[0064] Fitness = w1·C Tr +w2·C Ti +w3·C VU +w4·C Pe

[0065] In the formula, Fitness is the fitness value, w1, w2, w3, w4 are weight coefficients, C Tr is the transportation cost, C Ti is the time cost, C VU is the vehicle utilization rate, C Pe is the constraint condition penalty term;

[0066] Among them, the weight coefficients are predicted using a BP neural network. The transportation cost, time cost, vehicle utilization rate, and constraint condition penalty term are used as inputs, so the number of input layer neurons is 4, and the fitness value is used as the output, and the number of output layer neurons is 1. The ReLU is used as the activation function for the hidden layer, and the hidden layer has two layers. The first hidden layer has 12 neurons, the second hidden layer has 8 neurons, and the loss function is the mean squared error;

[0067] Selection operation sub-module: Obtain the offspring population by selection, crossover, and mutation of the genetic algorithm for the population that has achieved grading;

[0068] Iterative control sub-module: Combine the parent population and the offspring population, perform fast non-dominated sorting, calculate the crowding degree of individuals in each non-dominated layer, and select appropriate individuals according to the non-dominated relationship, the crowding degree of individuals, and the objective function to form a new parent population; generate a new offspring population until the preset number of iterations is met;

[0069] The preset number of iterations is adjusted according to the preset dynamic adjustment rule, and the preset dynamic adjustment rule includes

[0070] If the change in fitness value for ten consecutive generations is less than 0.01, increase the number of iterations by 30%;

[0071] If the similarity between individuals in the population is greater than 90%, increase the number of iterations by 30%;

[0072] If the computing resource utilization rate is lower than 50%, increase the number of iterations by 20%.

[0073] Result output and feedback sub-module: Output the final non-dominated solution set as the optimal transportation route and task allocation plan, and feedback the result to the vehicle scheduling module to achieve dynamic scheduling and allocation;

[0074] The vehicle scheduling module further includes a transportation duration and distance statistics module, and a trajectory playback and query module;

[0075] The transportation duration and distance statistics module: Utilize the positioning system data to real-time statistically calculate the duration and actual driving distance during the vehicle transportation process; this data helps to analyze the transportation efficiency, evaluate the transportation costs of different routes, and provide data support for subsequent optimization of the transportation plan;

[0076] The trajectory playback and query module: Used for trajectory playback, and can query the driving trajectory of the vehicle within a specific past time period. When there is a transportation anomaly or the transportation process needs to be traced, this module can provide detailed vehicle driving trajectory information, facilitating the identification of the cause and responsibility tracing.

[0077] The batching plant intelligent system further includes an environmental protection control module, and the environmental protection control module includes a pollution source monitoring sub-module and an energy conservation and emission reduction sub-module,

[0078] The pollution source monitoring sub-module uses a clustering algorithm to real-time monitor the pollution sources generated by the batching plant and vehicles, and analyzes the monitoring data, clustering the data with similar pollution characteristics into one category to identify the pollution type and source;

[0079] The energy conservation and emission reduction sub-module is used to optimize the production process and equipment operation parameters according to the monitored production process and equipment operation parameters.

[0080] Preferably, the material management module includes a material inventory management sub-module, a material quality monitoring sub-module, and a material trend analysis sub-module,

[0081] The material inventory management sub-module is used to real-time monitor the inventory status of various materials in the batching plant;

[0082] The material quality monitoring sub-module is used to monitor the material quality, record the material quality inspection results, and generate a material quality monitoring report;

[0083] The material trend analysis sub-module is used to predict material usage trend information based on the production information of the batching plant and the construction site information, and generate material requirements according to the material usage trend information and the construction site information.

[0084] The material trend analysis sub-module is expressed as:

[0085] h t = LSTM(x t , h t-1 , C t-1 )

[0086]

[0087] Wherein, h t is the hidden state at time t, x t is the input feature at time t, C t-1 is the memory cell state at time t-1, is the predicted material usage at time t, W y is the weight matrix of the output layer, b y is the bias term of the output layer;

[0088] The input features include historical material usage data, inventory information, construction site progress, construction site requirements, construction parts, and production plans.

[0089] The intelligent batching plant system further includes a work order generation and push module, which is used to generate application work orders according to the input work plan, and is also used to push the application work orders to the corresponding auditors for review, and send the reviewed work orders to the production control module to control the production equipment.

[0090] The intelligent batching plant system further includes a monitoring terminal, and the monitoring terminal is used to display ratio warning information, vehicle transportation information, batching plant production progress information, and construction progress information.

[0091] The above are only embodiments of the present invention. Specific structures and common knowledge such as characteristics that are well-known in the art are not described in detail herein. Those of ordinary skill in the art know all the common general technical knowledge in the technical field to which the invention pertains before the filing date or the priority date, can acquire all the prior art in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, complete and implement this solution in combination with their own abilities. Some typical well-known structures or well-known methods should not become an obstacle for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can also be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners described in the specification can be used to interpret the content of the claims.

Claims

1. An intelligent system for a mixing plant, characterized in that, Including: A production control module, which is used to control production equipment according to a production plan and a preset raw material mixing ratio, monitor the raw material mixing ratio, and generate a mixing ratio warning message; A transportation management module, which is used to optimize the vehicle transportation route and task allocation based on a genetic algorithm when the vehicle is in transportation, use the optimized parameters as the transportation route and allocation result, and generate vehicle transportation information according to the vehicle transportation situation; A material management module, which is used to analyze the material usage situation according to the production information of the mixing plant and the construction site information, and the construction site information includes the construction site requirements and the construction progress; A data management and information sharing module, which is used to collect the production information of the mixing plant, the construction site information, and the material usage situation, and generate a savings and overspending report and a daily production accounting report; A report query and message push module, which is used to query reports and push the mixing ratio warning, vehicle transportation information, mixing plant production progress information, and construction progress information to the corresponding personnel.

2. The intelligent system of the mixing plant according to claim 1, wherein: The transportation management module includes a vehicle positioning and control module, a transportation monitoring module, and a vehicle scheduling module. The vehicle transportation information includes vehicle position information and vehicle load information. The vehicle positioning and control module is used to obtain the real-time position information of the transportation vehicle, record the driving track, and is also provided with an electronic fence area. When the vehicle enters or leaves the set area, vehicle position information is generated; The transportation monitoring module is used to judge the overloading situation of the vehicle according to the weighing system measurement information and generate vehicle load information; The vehicle scheduling module is used to run the genetic algorithm.

3. The intelligent system of the mixing plant according to claim 2, wherein: The vehicle scheduling module includes A data collection and preprocessing sub-module: which is used to collect vehicle transportation information, construction site requirement information, and road condition information, and preprocess the collected data; An initialization sub-module: which is used to randomly generate an initial population according to the experienced route and screen the population according to the constraint conditions. The constraint conditions include vehicle capacity, time window, task completion, vehicle route continuity, road conditions, vehicle availability, and concrete supply continuity; A fitness calculation sub-module: which evaluates and grades the transportation routes and task allocations in the initial population and calculates the fitness value; A selection operation sub-module: which obtains a child population by selection, crossover, and mutation of the graded population through a genetic algorithm; An iterative control sub-module: which merges the parent population and the child population, performs fast non-dominated sorting, calculates the crowding degree of individuals in each non-dominated layer, and selects appropriate individuals according to the non-dominated relationship, the crowding degree of individuals, and the objective function to form a new parent population; generates a new child population until the preset number of iterations is satisfied; A result output and feedback sub-module: which outputs the final non-dominated solution set as the optimal transportation route and task allocation plan, and feeds the result back to the vehicle scheduling module to achieve dynamic scheduling and allocation.

4. The batching plant intelligent system according to claim 3, wherein: The formula for calculating the fitness value is as follows: Fitness = w1·C Tr + w2·C Ti + w3·C VU + w4·C Pe Where Fitness is the fitness value, w1, w2, w3, and w4 are weight coefficients, C Tr is the transportation cost, C Ti is the time cost, C VU is the vehicle utilization rate, C Pe is the constraint condition penalty term; Among them, the weight coefficient is predicted using a BP neural network. The transportation cost, time cost, vehicle utilization rate, and constraint condition penalty term are used as inputs, and the fitness value is used as the output. The ReLU is used as the activation function for the hidden layer, and the loss function is the mean square error.

5. The intelligent system of the mixing plant according to claim 3, wherein: The preset number of iterations is adjusted according to a preset dynamic adjustment rule. The preset dynamic adjustment rule includes If the change in fitness value for ten consecutive generations is less than 0.01, increase the number of iterations by 30%; If the similarity of individuals in the population is greater than 90%, increase the number of iterations by 30%; If the utilization rate of computing resources is lower than 50%, increase the number of iterations by 20%.

6. The intelligent system of the batching plant according to claim 1, wherein: It further includes an environmental protection control module, and the environmental protection control module includes a pollution source monitoring sub-module and an energy conservation and emission reduction sub-module. The pollution source monitoring sub-module uses a clustering algorithm to monitor the pollution sources generated by the mixing plant and vehicles in real time, analyzes the monitoring data, clusters the data with similar pollution characteristics into one category, and identifies the pollution type and source. The energy conservation and emission reduction sub-module is used to optimize the production process and equipment operation parameters according to the monitored production process and equipment operation parameters.

7. The intelligent system of the mixing plant according to claim 1, wherein: The material management module includes a material inventory management sub-module, a material quality monitoring sub-module, and a material trend analysis sub-module. The material inventory management sub-module is used to monitor the inventory status of various materials in the mixing plant in real time. The material quality monitoring sub-module is used to monitor the material quality, record the material quality inspection results, and generate a material quality monitoring report. The material trend analysis sub-module is used to predict the material usage trend information based on the production information of the mixing plant and the construction site information, and generate the material demand based on the material usage trend information and the construction site information.

8. The intelligent system of the batching plant according to claim 1, characterized in that: It further includes a work order generation and push module, which is used to generate an application work order according to the input work plan, and is also used to push the application work order to the corresponding reviewer for review, and send the reviewed work order to the production control module to control the production equipment.

9. The intelligent system of the mixing plant according to claim 1, characterized in that: The production control module is also used to monitor the operation status of the production equipment and analyze the equipment operation performance.

10. The intelligent system for batching plant according to claim 1, wherein: It further includes a monitoring terminal, which is used to display the proportion warning information, vehicle transportation information, mixing plant production progress information, and construction progress information.

Images