Intelligent coal blending scheduling system and optimization method thereof

Abstract

The invention discloses an intelligent coal blending scheduling system and an optimization method thereof, the system comprises a data acquisition and preprocessing module, an intelligent proportioning optimization module, an intelligent scheduling module and a real-time feedback and control module, the coal blending precision and the stability of the coal quality are improved, the efficiency and the response capability of transportation scheduling are improved, and the transportation scheduling efficiency is improved. The system achieves the functions of whole-process real-time feedback and closed-loop control, fault prediction and early warning, reduces the risk of coal blending interruption or quality fluctuation caused by equipment faults, and effectively solves the problem of insufficient fault prediction capability in a traditional coal blending system. According to the intelligent coal blending scheduling system, through organic integration of the data real-time acquisition module, the proportion optimization module, the intelligent scheduling module, the closed-loop feedback module, the fault prediction module and the like, the coal blending precision and the stability of the coal quality can be remarkably improved, the scheduling efficiency and the system stability are remarkably improved, and multiple problems in the background technology are effectively solved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent coal blending and scheduling, and in particular to an intelligent coal blending and scheduling system and an optimization method thereof. Background Art

[0002] In the production and supply chain of the coal industry, coal blending and scheduling is a complex and critical link. Existing coal blending systems are mostly manually controlled or semi-automatically controlled based on fixed parameters, which are difficult to cope with complex coal combinations and rapidly fluctuating market demands, resulting in low coal blending accuracy and unstable coal quality. At the same time, traditional coal blending systems have limitations in responding to resource changes, transportation scheduling, and coal quality monitoring, which are specifically manifested in the following aspects:

[0003] Insufficient coal blending accuracy: Traditional coal blending methods make it difficult to monitor and dynamically adjust coal composition (such as ash content, sulfur content and calorific value) in real time, resulting in fluctuations in coal quality and making it difficult to meet the coal quality requirements of different users.

[0004] Low scheduling efficiency: Due to the lack of support for intelligent scheduling algorithms, traditional coal distribution scheduling methods mainly rely on manual decision-making or static path planning, which cannot efficiently adapt to real-time traffic and demand changes. This method is prone to transportation delays, resource waste, and inventory management problems, affecting the delivery timeliness of coal and supply chain efficiency.

[0005] Lack of real-time feedback and closed-loop control: Existing systems usually lack real-time feedback mechanisms and cannot make timely adjustments when there are ratio deviations or transportation delays. Failures or delays in coal transportation are difficult to detect in time and often require manual intervention, which reduces the response efficiency of the entire system.

[0006] Lack of fault prediction capabilities: Traditional systems lack fault prediction capabilities, and equipment monitoring and maintenance mainly rely on manual inspections. It is difficult to provide timely warnings of equipment failures, resulting in coal blending interruptions or quality fluctuations.

[0007] Based on the above background technical problems, there is an urgent need for an intelligent coal blending and scheduling system that can monitor in real time, optimize the ratio, intelligently schedule, and have real-time feedback and fault prediction capabilities to improve coal blending accuracy, transportation efficiency and system stability. Summary of the invention

[0008] The present application provides an intelligent coal blending scheduling system and an optimization method thereof, aiming to solve the problem that traditional coal blending methods are difficult to monitor and dynamically adjust coal composition in real time, resulting in fluctuations in coal quality and difficulty in meeting the coal quality requirements of different users.

[0009] In a first aspect, an intelligent coal blending and scheduling system is provided, wherein the method comprises:

[0010] The system comprises:

[0011] Data collection and preprocessing module, used to collect real-time composition data of coal through sensors, and to clean and standardize the data;

[0012] Intelligent proportion optimization module, which is used to generate the optimal proportion scheme based on coal composition data, historical data and market demand using multi-objective genetic algorithm and deep learning model;

[0013] Intelligent dispatch module, which is used to optimize transportation routes and vehicle dispatch sequence based on coal demand level, inventory status and real-time traffic data;

[0014] The real-time feedback and control module is used to monitor the coal blending effect and transportation status, and send out early warning signals when the deviation exceeds the preset value to achieve closed-loop control.

[0015] In the above scheme, optionally, the data acquisition and preprocessing module includes an ash sensor, a sulfur content detector, a calorific value detector and a particle size sensor, and the sensors transmit data to a central data processing system through the Internet of Things.

[0016] In the above solution, optionally, the intelligent ratio optimization module includes:

[0017] Multi-objective genetic algorithm module, used to generate the optimal ratio scheme under the premise of meeting the requirements of coal calorific value, composition, cost and environmental protection;

[0018] The deep learning prediction module is used to adaptively adjust the ratio scheme based on historical data and market demand.

[0019] In the above solution, optionally, the intelligent scheduling module includes:

[0020] The route optimization unit is used to dynamically plan the transportation route based on the GIS geographic information system and real-time traffic data, using the Dijkstra algorithm combined with the ant colony algorithm;

[0021] Priority allocation unit, used to automatically adjust the priority of transportation tasks according to task urgency, inventory status and customer demand.

[0022] In the above solution, optionally, the real-time feedback and control module includes:

[0023] Feedback control unit, used to adjust coal composition data in real time according to PID control algorithm to ensure accuracy and stability of the proportion;

[0024] Intelligent early warning unit, used to send out multi-channel early warning signals in case of coal composition deviation, equipment failure or transportation delay.

[0025] In a second aspect, a method for optimizing intelligent coal blending scheduling and coal blending is provided, the method comprising the following steps:

[0026] Data collection and preprocessing: Collect real-time composition data of coal through sensors, and clean and standardize the data;

[0027] Optimization calculation of coal blending ratio: Utilize multi-objective genetic algorithm and deep learning model to calculate the optimal coal blending scheme, and make adaptive adjustments based on real-time data;

[0028] Route optimization and dispatch execution: Dynamically optimize transportation routes and vehicle dispatch based on GIS geographic information, real-time traffic data and vehicle status data;

[0029] Real-time monitoring and feedback adjustment: monitor the coal blending effect and make fine adjustments when necessary, and issue warnings when deviations exceed thresholds.

[0030] In the above scheme, optionally, a multi-objective genetic algorithm module is introduced into the ratio optimization calculation step to comprehensively consider the calorific value, ash content, sulfur content, environmental protection and cost of coal to generate an optimal ratio scheme that meets production requirements.

[0031] In the above scheme, optionally, the path optimization and scheduling execution step adopts a combined optimization of the Dijkstra algorithm and the ant colony algorithm to dynamically adjust the transportation plan based on vehicle priority and real-time traffic data.

[0032] In the above scheme, optionally, a feedback mechanism based on a PID control algorithm is adopted in the real-time monitoring and feedback adjustment step to adjust the coal blending ratio in real time to ensure the accuracy and stability of the coal blending effect.

[0033] In the above scheme, optionally, the real-time monitoring and feedback adjustment step includes a fault prediction function based on the RNN sequence model, which is used to predict the operating status of the equipment and issue a warning signal before the abnormality occurs.

[0034] Compared with the prior art, this application has at least the following beneficial effects:

[0035] Based on further analysis and research of existing technical problems, this application recognizes that it is difficult for traditional coal blending methods to monitor and dynamically adjust coal composition in real time, resulting in fluctuations in coal quality and difficulty in meeting the requirements of different users for coal quality. This application provides an intelligent coal blending scheduling system, including a data acquisition and preprocessing module, an intelligent ratio optimization module, an intelligent scheduling module, and a real-time feedback and control module, thereby achieving the following technical effects:

[0036] Improve the accuracy of coal blending and the stability of coal quality: The data acquisition and preprocessing module collects coal ash, sulfur content, calorific value, particle size and other component data in real time through the sensor network, and cleans and standardizes the data. This real-time data acquisition and preprocessing mechanism enables the system to quickly and accurately analyze the coal composition. The intelligent proportion optimization module uses multi-objective genetic algorithms and deep learning models to generate the optimal proportioning scheme based on coal composition and market demand, and dynamically adjusts the proportion according to real-time data. This optimization mechanism effectively improves the accuracy of coal blending, ensures stable coal quality, and can meet the requirements of different users for coal composition, solving the problems of inaccurate proportioning and large fluctuations in coal quality in traditional methods.

[0037] Improve the efficiency and responsiveness of transportation scheduling: The intelligent scheduling module dynamically optimizes the transportation route through GIS geographic information and real-time traffic data, combined with path optimization algorithms (such as Dijkstra algorithm and ant colony algorithm), and automatically schedules vehicles according to coal demand level, inventory status and priority. This intelligent scheduling module not only reduces the impact of traffic congestion on transportation, but also can schedule transportation resources in real time according to changes in demand, improves the response speed and scheduling efficiency of the coal supply chain, and effectively solves the problems of low efficiency of manual scheduling and frequent transportation delays in the background technology.

[0038] Realize real-time feedback and closed-loop control of the entire process: The real-time feedback and control module monitors the coal blending process in real time through the PID control algorithm to ensure the accuracy of the blending scheme and the stability of the composition. At the same time, the module also has an intelligent early warning function. When there is a component deviation, equipment failure or transportation delay, the system can automatically issue an early warning signal. This closed-loop control mechanism can effectively solve the problem of lack of real-time feedback and reliance on manual intervention in traditional systems, thereby improving the stability and reliability of the system.

[0039] Fault prediction and early warning function: The real-time feedback and control module can predict the potential failure risk of equipment through deep learning and sequence analysis models (such as RNN), issue early warning signals in advance, and remind operators to check and maintain. This function significantly enhances the safety and stability of the system, reduces the risk of coal blending interruption or quality fluctuation due to equipment failure, and effectively compensates for the problem of insufficient fault prediction ability in traditional coal blending systems.

[0040] The intelligent coal blending and scheduling system of the present application can not only significantly improve the coal blending accuracy and the stability of coal quality, but also significantly improve the scheduling efficiency and system stability, and effectively solve many problems in the background technology through the organic integration of modules such as real-time data collection, ratio optimization, intelligent scheduling, closed-loop feedback and fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1A block diagram of the module architecture of an intelligent coal blending and scheduling device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] In one embodiment, Figure 1 As shown, an intelligent coal blending scheduling system is provided, the system comprising:

[0044] Data collection and preprocessing module, used to collect real-time composition data of coal through sensors, and to clean and standardize the data;

[0045] Intelligent proportion optimization module, which is used to generate the optimal proportion scheme based on coal composition data, historical data and market demand using multi-objective genetic algorithm and deep learning model;

[0046] Intelligent dispatch module, which is used to optimize transportation routes and vehicle dispatch sequence based on coal demand level, inventory status and real-time traffic data;

[0047] The real-time feedback and control module is used to monitor the coal blending effect and transportation status, and send out early warning signals when the deviation exceeds the preset value to achieve closed-loop control.

[0048] This embodiment provides an intelligent coal blending scheduling system, including a data acquisition and preprocessing module, an intelligent proportioning optimization module, an intelligent scheduling module and a real-time feedback and control module, thereby achieving the following technical effects:

[0049] Improve the accuracy of coal blending and the stability of coal quality: The data acquisition and preprocessing module collects coal ash, sulfur content, calorific value, particle size and other component data in real time through the sensor network, and cleans and standardizes the data. This real-time data acquisition and preprocessing mechanism enables the system to quickly and accurately analyze the coal composition. The intelligent proportion optimization module uses multi-objective genetic algorithms and deep learning models to generate the optimal proportioning scheme based on coal composition and market demand, and dynamically adjusts the proportion according to real-time data. This optimization mechanism effectively improves the accuracy of coal blending, ensures stable coal quality, and can meet the requirements of different users for coal composition, solving the problems of inaccurate proportioning and large fluctuations in coal quality in traditional methods.

[0050] Improve the efficiency and responsiveness of transportation scheduling: The intelligent scheduling module dynamically optimizes the transportation route through GIS geographic information and real-time traffic data, combined with path optimization algorithms (such as Dijkstra algorithm and ant colony algorithm), and automatically schedules vehicles according to coal demand level, inventory status and priority. This intelligent scheduling module not only reduces the impact of traffic congestion on transportation, but also can schedule transportation resources in real time according to changes in demand, improves the response speed and scheduling efficiency of the coal supply chain, and effectively solves the problems of low efficiency of manual scheduling and frequent transportation delays in the background technology.

[0051] Realize real-time feedback and closed-loop control of the entire process: The real-time feedback and control module monitors the coal blending process in real time through the PID control algorithm to ensure the accuracy of the blending scheme and the stability of the composition. At the same time, the module also has an intelligent early warning function. When there is a component deviation, equipment failure or transportation delay, the system can automatically issue an early warning signal. This closed-loop control mechanism can effectively solve the problem of lack of real-time feedback and reliance on manual intervention in traditional systems, thereby improving the stability and reliability of the system.

[0052] Fault prediction and early warning function: The real-time feedback and control module can predict the potential failure risk of equipment through deep learning and sequence analysis models (such as RNN), issue early warning signals in advance, and remind operators to check and maintain. This function significantly enhances the safety and stability of the system, reduces the risk of coal blending interruption or quality fluctuation due to equipment failure, and effectively compensates for the problem of insufficient fault prediction ability in traditional coal blending systems.

[0053] The intelligent coal blending and scheduling system of this embodiment can not only significantly improve the coal blending accuracy and the stability of coal quality, but also significantly improve the scheduling efficiency and system stability, and effectively solve many problems in the background technology through the organic integration of modules such as real-time data collection, ratio optimization, intelligent scheduling, closed-loop feedback and fault prediction.

[0054] In this embodiment, the data acquisition and preprocessing module includes an ash sensor, a sulfur content detector, a calorific value detector and a particle size sensor, and the sensors transmit data to a central data processing system through the Internet of Things.

[0055] This embodiment describes the specific composition of the data acquisition and preprocessing module, including an ash sensor, a sulfur content detector, a calorific value detector, and a particle size sensor, and transmits data to a central data processing system through the Internet of Things. This technical solution enables more efficient and real-time data acquisition and analysis for the system, bringing the following technical effects:

[0056] By installing a variety of sensors, the system can monitor the core components of coal in real time, including ash, sulfur content, calorific value and particle size. This multi-dimensional data collection method significantly improves the accuracy and comprehensiveness of the data, ensuring that key indicators of coal composition and physical properties can be obtained in real time and completely. Compared with the traditional method that relies on manual sampling and detection, the automated collection of sensors can avoid human errors and update data in real time, greatly improving the reliability and response speed of the system.

[0057] The data acquisition module transmits sensor data to the central data processing system in real time through the Internet of Things technology. The real-time data transmission technology enables the system to achieve seamless connection in the process of data acquisition and data transmission, which not only improves the data transmission efficiency, but also shortens the time difference between data acquisition and analysis. This function greatly improves the system's response speed to data, allowing the proportion adjustment to be carried out in the first time, providing data support for the optimization of coal blending quality and the continuity of production.

[0058] Various sensors are centralized to the central data processing system through the Internet of Things, which enables unified data management and real-time processing. Compared with the traditional decentralized data management model, the centralized data processing system can integrate and analyze the data of different sensors, and then make the best decision based on multi-dimensional data. Unified management not only simplifies the data processing process, but also improves the speed of data processing and analysis, thereby ensuring the efficiency of proportion calculation and coal blending production.

[0059] Based on the data collection and transmission mode of the Internet of Things, the system has good scalability. In practical applications, the type and number of sensors can be increased or decreased according to demand to adapt to changes in different types of coal and demand scenarios. At the same time, the Internet of Things architecture facilitates remote monitoring and diagnosis, and can quickly locate and solve data transmission problems when they occur, improving the maintenance convenience and long-term stability of the system.

[0060] The data acquisition and preprocessing module in this embodiment realizes real-time and accurate collection of coal composition through precise detection of multiple sensors and Internet of Things data transmission technology, ensuring the comprehensiveness and timeliness of data and the scalability of the system, greatly improving the data analysis accuracy and production continuity of the entire system.

[0061] In this embodiment, the intelligent ratio optimization module includes:

[0062] Multi-objective genetic algorithm module, used to generate the optimal ratio scheme under the premise of meeting the requirements of coal calorific value, composition, cost and environmental protection;

[0063] The deep learning prediction module is used to adaptively adjust the ratio scheme based on historical data and market demand.

[0064] This embodiment describes in detail the composition of the intelligent ratio optimization module, including a multi-objective genetic algorithm module and a deep learning prediction module. These algorithm modules are used in combination to achieve optimization and dynamic adjustment of the ratio scheme, producing the following technical effects:

[0065] The multi-objective genetic algorithm module comprehensively considers multiple key factors of coal when generating a blending scheme, including calorific value, composition, cost, and environmental friendliness. Through multiple generations of evolution and iterative solutions of the genetic algorithm, it generates an optimal blending scheme that balances various indicators. This multi-objective optimization technology can effectively reduce production costs while ensuring coal quality, and realize an efficient and low-cost coal blending production plan to meet the diverse needs of different customers and application scenarios.

[0066] The deep learning prediction module predicts future coal demand based on historical data and market demand trends, and dynamically adjusts the proportioning scheme based on the prediction results. Through the adaptive adjustment function, the system can respond to market demand fluctuations in real time, quickly adjust the proportioning to meet actual production needs, and improve the flexibility and adaptability of the system. Compared with the traditional static proportioning scheme, this module significantly improves the system's real-time response capability and effectively solves the industry pain points of long production cycles and fast demand changes.

[0067] The deep learning prediction module can identify complex patterns and nonlinear relationships in coal proportioning, and improve the accuracy of forecasting future demand and composition changes by analyzing trends and patterns in historical data. This module provides a more accurate decision-making basis for proportioning schemes, can more accurately meet production standards and customer needs, and improve the scientificity and rationality of proportioning.

[0068] Through the combination of multi-objective genetic algorithms and deep learning models, the system's proportioning scheme generation and adjustment process is highly automated, reducing manual intervention. Automated proportioning optimization improves operational efficiency and stability, reduces the possibility of manual errors, enables the system to operate more efficiently, and brings significant economic benefits to coal enterprises.

[0069] The intelligent proportioning optimization module in this embodiment provides a dynamic and flexible proportioning optimization solution through the combination of multi-objective genetic algorithm and deep learning model, improves the proportioning accuracy and cost-effectiveness, and significantly enhances the real-time response capability of the system.

[0070] In this embodiment, the intelligent scheduling module includes:

[0071] The route optimization unit is used to dynamically plan the transportation route based on the GIS geographic information system and real-time traffic data, using the Dijkstra algorithm combined with the ant colony algorithm;

[0072] Priority allocation unit, used to automatically adjust the priority of transportation tasks according to task urgency, inventory status and customer demand.

[0073] This embodiment describes an intelligent scheduling module, including a path optimization unit and a priority allocation unit, which specifically improves the efficiency and response speed of transportation through dynamic optimization of paths and task priorities. The technical effects are as follows:

[0074] The path optimization unit combines the Dijkstra algorithm and the ant colony algorithm. Based on the GIS geographic information system and real-time traffic data, it can dynamically plan the transportation path and select the optimal transportation route. This path optimization method not only shortens the transportation time, but also effectively reduces the transportation cost and maximizes the use of transportation resources. By avoiding congested routes and optimizing the distance, the transportation efficiency is improved, the risk of delays caused by traffic factors is reduced, and the defects of unreasonable path planning in traditional scheduling methods are solved.

[0075] The priority allocation unit dynamically allocates task priorities according to task urgency, inventory status, and customer demand, and reasonably adjusts the order of transportation tasks and resource allocation. This module can flexibly adjust the order of tasks according to changes in demand, ensuring that important tasks are completed first, effectively improving the timeliness of coal delivery and customer satisfaction, especially in response to sudden demand or special customer needs, providing flexible scheduling support and solving the problem of slow response of traditional systems.

[0076] Through the optimal combination of routes and priorities, the intelligent scheduling module can maximize the optimization of transportation resources, reduce vehicle idleness and fuel waste, and reduce transportation operating costs. Especially in the case of demand fluctuations or limited transportation resources, the module can reasonably allocate resources, achieve efficient transportation, and improve the efficiency of the entire supply chain.

[0077] In this embodiment, the path optimization unit and the priority allocation unit can adjust the transportation plan at any time to adapt to changes in the external environment by combining real-time traffic data. Compared with the static scheduling mode, this module realizes dynamic scheduling through intelligent algorithms, which not only improves the system's adaptability to complex environments, but also significantly improves the flexibility and reliability of system operation.

[0078] The intelligent scheduling module of this embodiment improves transportation efficiency, delivery timeliness and system flexibility through path optimization and priority allocation, and effectively solves the problems of inefficiency and inflexibility in traditional transportation scheduling methods.

[0079] In this embodiment, the real-time feedback and control module includes:

[0080] Feedback control unit, used to adjust coal composition data in real time according to PID control algorithm to ensure accuracy and stability of the proportion;

[0081] Intelligent early warning unit, used to send out multi-channel early warning signals in case of coal composition deviation, equipment failure or transportation delay.

[0082] This embodiment involves the specific composition of the real-time feedback and control module, including a feedback control unit and an intelligent early warning unit, which are used to monitor the ratio accuracy and system status and issue early warnings in time when problems such as ratio deviation, equipment failure or transportation delay occur. This module produces the following technical effects through a closed-loop control mechanism and intelligent early warning:

[0083] The feedback control unit is based on the PID control algorithm to achieve real-time monitoring and dynamic adjustment of coal composition data. Compared with the traditional open system, PID control can form a closed loop for the proportioning process, correct the deviation in real time in each proportioning cycle, and ensure the stability of the output coal composition and the proportioning accuracy. This real-time feedback enables the system to respond quickly when a composition deviation is detected, and by adjusting the proportioning parameters appropriately, it eliminates errors caused by external factors or equipment status, greatly improving the accuracy of the system and the uniformity of coal composition.

[0084] The intelligent early warning unit monitors each link in the system and issues multi-channel early warnings for key deviations or abnormal signals (such as coal composition deviations, equipment abnormalities, or transportation delays), ensuring that operators are notified immediately when problems first occur. By integrating the intelligent early warning module, the system can significantly shorten the response time and avoid the risks caused by human negligence. At the same time, the early warning function can effectively reduce production losses caused by equipment failures or transportation delays, and improve the reliability of the system and the continuity of production.

[0085] Feedback control and early warning functions complement each other. Through real-time monitoring, deviation correction and early warning alarm, a complete safety management and quality control system has been formed. In particular, early prediction and risk intervention of fault problems can effectively reduce production interruptions caused by equipment failure or transportation delays, ensuring the long-term stable operation of the system. In addition, by recording and analyzing feedback and early warning data, the system can further optimize future operating parameters and improve adaptive capabilities.

[0086] The feedback control unit and intelligent early warning unit operate in an automated mode. The system can detect and adjust itself in real time during operation without human intervention. By reducing the number of manual inspections and human decision-making, the system not only improves production efficiency, but also reduces the possibility of human error, making the entire system more continuous and consistent.

[0087] The real-time feedback and control module in this embodiment forms an efficient closed-loop management system through the combined application of PID control algorithm and intelligent early warning, improves the production stability, accuracy and responsiveness of the system, and solves the problems of data monitoring lag, untimely adjustment and insufficient risk management in traditional systems.

[0088] The specific implementation content of each module can be found in the above definition of the intelligent coal blending scheduling method, which will not be repeated here.

[0089] In one embodiment, a coal blending optimization method for an intelligent coal blending scheduling system is provided, wherein the method comprises the following steps:

[0090] Data collection and preprocessing: Collect real-time composition data of coal through sensors, and clean and standardize the data;

[0091] Optimization calculation of coal blending ratio: Utilize multi-objective genetic algorithm and deep learning model to calculate the optimal coal blending scheme, and make adaptive adjustments based on real-time data;

[0092] Route optimization and dispatch execution: Dynamically optimize transportation routes and vehicle dispatch based on GIS geographic information, real-time traffic data and vehicle status data;

[0093] Real-time monitoring and feedback adjustment: monitor the coal blending effect and make fine adjustments when necessary, and issue warnings when deviations exceed thresholds.

[0094] In this embodiment, a multi-objective genetic algorithm module is introduced into the ratio optimization calculation step to comprehensively consider the calorific value, ash content, sulfur content, environmental protection and cost of coal to generate an optimal ratio scheme that meets production requirements.

[0095] In this embodiment, the path optimization and scheduling execution step adopts a combined optimization of the Dijkstra algorithm and the ant colony algorithm, and dynamically adjusts the transportation plan based on vehicle priority and real-time traffic data.

[0096] In this embodiment, a feedback mechanism based on a PID control algorithm is used in the real-time monitoring and feedback adjustment step to adjust the coal blending ratio in real time to ensure the accuracy and stability of the coal blending effect.

[0097] In this embodiment, the real-time monitoring and feedback adjustment step includes a fault prediction function based on the RNN sequence model, which is used to predict the operating status of the equipment and issue a warning signal before an abnormality occurs.

[0098] This embodiment integrates data collection, preprocessing, ratio optimization and path scheduling into a systematic method, which effectively realizes the automation of coal blending scheduling. The entire optimization process is seamlessly connected, and the coal composition data is analyzed and processed immediately after being collected to ensure the efficiency of ratio optimization. Compared with the traditional segmented operation process, this method reduces human intervention and time delay, improves the system's response speed to real-time data, and ensures the smoothness and continuity of the production process.

[0099] In the ratio optimization calculation, the multi-objective genetic algorithm and deep learning model are used to dynamically optimize the ratio scheme, taking into account multiple factors such as coal calorific value, composition, cost and environmental protection. This method can not only achieve a balance between multiple objectives, but also adapt to changes in market demand through adaptive learning functions and dynamically adjust the ratio parameters. Compared with the traditional static ratio scheme, the adaptive function of this method effectively improves the flexibility of the ratio, can meet the needs of different customers and scenarios, and solves the problem of lagging traditional ratio adjustment.

[0100] By applying Dijkstra algorithm and ant colony algorithm in path optimization and scheduling execution, the system can perform dynamic path planning based on real-time traffic information and inventory data to ensure efficient transportation. Different from the static method of traditional path planning, this method updates traffic information in real time and adjusts the path in time, which improves transportation efficiency, reduces the impact of traffic factors on delivery time, and ensures the timeliness and accuracy of coal distribution.

[0101] The real-time monitoring and feedback adjustment steps are based on the PID control algorithm and intelligent early warning mechanism to dynamically monitor the coal blending process and automatically adjust when the deviation exceeds the threshold to ensure the stability of the system. Through closed-loop control, this method can minimize the deviation in the production process and ensure the uniformity of coal blending quality and the stability of its composition. In addition, through intelligent early warning, equipment failures and delays are warned in advance, so that the system can respond in time when abnormalities occur to ensure the continuity of production.

[0102] The coal blending optimization method of this embodiment realizes the intelligent control of the system from data collection to feedback monitoring through the coordinated work of various steps, significantly improves the system's automation level, real-time response capability and production stability, and solves the problems of low efficiency and slow response of traditional coal blending scheduling.

[0103] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. An intelligent coal blending and dispatching system, characterized in that: The system comprises: Data collection and preprocessing module, used to collect real-time composition data of coal through sensors, and to clean and standardize the data; Intelligent proportion optimization module, which is used to generate the optimal proportion scheme based on coal composition data, historical data and market demand using multi-objective genetic algorithm and deep learning model; Intelligent dispatch module, which is used to optimize transportation routes and vehicle dispatch sequence based on coal demand level, inventory status and real-time traffic data; The real-time feedback and control module is used to monitor the coal blending effect and transportation status, and send out early warning signals when the deviation exceeds the preset value to achieve closed-loop control.

2. The intelligent coal blending and dispatching system according to claim 1 is characterized in that: The data acquisition and preprocessing module includes an ash sensor, a sulfur content detector, a calorific value detector and a particle size sensor, and the sensors transmit data to a central data processing system through the Internet of Things.

3. The intelligent coal blending and dispatching system according to claim 1 is characterized in that: The intelligent ratio optimization module includes: Multi-objective genetic algorithm module, used to generate the optimal ratio scheme under the premise of meeting the requirements of coal calorific value, composition, cost and environmental protection; The deep learning prediction module is used to adaptively adjust the ratio scheme based on historical data and market demand.

4. The intelligent coal blending and dispatching system according to claim 1 is characterized in that: The intelligent scheduling module includes: The route optimization unit is used to dynamically plan the transportation route based on the GIS geographic information system and real-time traffic data, using the Dijkstra algorithm combined with the ant colony algorithm; Priority allocation unit, used to automatically adjust the priority of transportation tasks according to task urgency, inventory status and customer demand.

5. The intelligent coal blending and dispatching system according to claim 1 is characterized in that: The real-time feedback and control module includes: Feedback control unit, used to adjust coal composition data in real time according to PID control algorithm to ensure accuracy and stability of the proportion; Intelligent early warning unit, used to send out multi-channel early warning signals in case of coal composition deviation, equipment failure or transportation delay.

6. A coal blending optimization method based on the intelligent coal blending scheduling system according to any one of claims 1 to 5, characterized in that: The method comprises the following steps: Data collection and preprocessing: Collect real-time composition data of coal through sensors, and clean and standardize the data; Optimization calculation of coal blending ratio: Utilize multi-objective genetic algorithm and deep learning model to calculate the optimal coal blending scheme, and make adaptive adjustments based on real-time data; Route optimization and dispatch execution: Dynamically optimize transportation routes and vehicle dispatch based on GIS geographic information, real-time traffic data and vehicle status data; Real-time monitoring and feedback adjustment: monitor the coal blending effect and make fine adjustments when necessary, and issue warnings when deviations exceed thresholds.

7. The coal blending optimization method according to claim 6, characterized in that: A multi-objective genetic algorithm module is introduced into the ratio optimization calculation step, which comprehensively considers the calorific value, ash content, sulfur content, environmental protection and cost of coal to generate an optimal ratio scheme that meets production requirements.

8. The coal blending optimization method according to claim 6, characterized in that: The path optimization and scheduling execution steps adopt the combined optimization of Dijkstra algorithm and ant colony algorithm, and dynamically adjust the transportation plan based on vehicle priority and real-time traffic data.

9. The coal blending optimization method according to claim 6, characterized in that: The real-time monitoring and feedback adjustment step adopts a feedback mechanism based on a PID control algorithm to adjust the coal blending ratio in real time to ensure the accuracy and stability of the coal blending effect.

10. The coal blending optimization method according to claim 6, characterized in that: The real-time monitoring and feedback adjustment step includes a fault prediction function based on the RNN sequence model, which is used to predict the operating status of the equipment and issue a warning signal before an abnormality occurs.

Images