Intelligent coal fuel dispatching dynamic early warning system and method

Abstract

The invention provides an intelligent coal fuel scheduling dynamic early warning system and method, and belongs to the technical field of resource scheduling and logistics management, and the system comprises a data acquisition module which carries out the real-time monitoring of each node in a coal fuel supply chain through a preset multi-sensor network, and obtains the dynamic change data in the coal fuel supply chain; the historical analysis module is used for acquiring and analyzing historical scheduling data of the coal fuel supply chain; the scheme acquisition module is used for constructing a multi-level scheduling model and performing local scheduling at different levels in combination with an analysis result based on historical scheduling data and dynamic change data of a supply chain to generate an overall scheduling scheme and an overall alternative scheduling scheme; the scheme reconstruction module is used for executing coal fuel scheduling based on the overall scheduling scheme and obtaining real-time scheduling data to reconstruct the overall scheduling scheme; and the dispatching early warning module is used for constructing a multi-level early warning mechanism based on the coal fuel real-time dispatching data and carrying out early warning, so that the dispatching efficiency and the supply chain stability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource scheduling and logistics management, and in particular to an intelligent coal fuel scheduling dynamic early warning system and method. Background Art

[0002] With the widespread use of coal as an important energy source in the global economy, how to effectively manage the supply chain and scheduling of coal fuel has become a major challenge faced by major coal companies. Traditional coal fuel scheduling methods mostly rely on manual experience and static data, which is difficult to cope with the complex and changeable dynamic changes in the supply chain. In the prior art, there are coal scheduling management systems based on informatization and intelligence. For example, some systems can monitor the status of supply chain nodes through sensors and generate scheduling plans. However, these systems are mostly focused on static data analysis, lack the ability to flexibly respond to real-time changes, and lack an early warning mechanism based on a multi-level scheduling model. They cannot adjust the scheduling plan in time, which reduces the scheduling efficiency and the stability of the supply chain. The existing technical solutions have the following main defects: the existing system cannot effectively respond to dynamic changes in the supply chain, lacks full use of real-time scheduling data and early warning mechanisms, resulting in untimely updates of scheduling plans, affecting the continuity and optimization of coal fuel supply.

[0003] Therefore, the present invention provides an intelligent coal fuel scheduling dynamic early warning system and method. Summary of the invention

[0004] The present invention provides an intelligent coal fuel scheduling dynamic early warning system to solve the defects of the prior art, such as the inability to flexibly respond to the dynamic changes of the coal fuel supply chain and the lack of an effective real-time early warning mechanism. By monitoring the dynamic data of supply chain nodes through a multi-sensor network and combining historical scheduling analysis results, a multi-level scheduling model and early warning mechanism are generated to achieve dynamic optimization and early warning of coal fuel scheduling, thereby improving scheduling efficiency and supply chain stability.

[0005] The present invention provides an intelligent coal fuel dispatching dynamic early warning system, comprising: Data acquisition module: real-time monitoring of each node in the coal fuel supply chain through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; historical analysis module: obtain historical scheduling data of the coal fuel supply chain and analyze it; Solution acquisition module: Based on the coal fuel supply chain, a multi-level scheduling model is built to combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Scheme reconstruction module: executes coal fuel scheduling based on the overall scheduling plan, and obtains real-time scheduling data to reconstruct the overall scheduling plan; Dispatching and early warning module: Build a multi-level early warning mechanism based on real-time dispatching data of coal fuel and issue early warnings.

[0006] The present invention provides an intelligent coal fuel dispatching dynamic early warning system, a historical analysis module, comprising: History extraction unit: extracts the scheduling data in the coal fuel supply chain from the history database to obtain the historical scheduling data; Historical classification unit: classifies historical dispatch data according to preset time periods to form historical dispatch archives within different time periods; Historical analysis unit: Based on the preset analysis algorithm, it analyzes the data of key factors related to scheduling in the historical scheduling archives in different time periods; Bottleneck determination unit: Analyze the data of key factors related to scheduling in different time periods to determine the historical scheduling bottlenecks of the coal fuel supply chain, and combine the data of key factors related to scheduling in different time periods to determine the impact coefficient of each historical scheduling bottleneck on scheduling efficiency: ; in, is the influence coefficient of the i-th historical scheduling bottleneck on scheduling efficiency, To preset the benchmark scheduling efficiency, is the influence coefficient of the jth key factor related to scheduling on scheduling efficiency in the bth time period, is the weight of the impact coefficient of the jth key factor related to scheduling in the bth time period, is the empirical weight of the historical scheduling bottleneck, is the sensitivity coefficient to the real-time scheduling change, is the elastic adjustment coefficient between the scheduling efficiency and the actual scheduling completion amount, is the scheduling efficiency without bottleneck, is the scheduling efficiency under the i-th historical scheduling bottleneck, m is the number of time periods, is the number of key factors related to scheduling in the bth time period, is the actual scheduling completion amount under the i-th historical scheduling bottleneck, is the planned scheduling completion amount under the i-th historical scheduling bottleneck; A historical scheduling bottleneck whose impact coefficient on scheduling efficiency is greater than a preset impact coefficient threshold is determined as a bottleneck state, and the bottleneck state value is determined based on the data of key factors related to scheduling in different time periods corresponding to the historical scheduling bottleneck greater than the preset impact coefficient threshold and the impact coefficient of the historical scheduling bottleneck on scheduling efficiency: ;in, is the bottleneck state value of the i-th historical scheduling bottleneck, To preset the impact coefficient threshold, is the weight coefficient of the i-th historical scheduling bottleneck.

[0007] The present invention provides an intelligent coal fuel scheduling dynamic early warning system, a scheme acquisition module, comprising: Model building unit: Obtain the structural characteristics of the coal fuel supply chain to build a multi-level scheduling model; State determination unit: integrates the analysis results of historical scheduling data with the dynamic change data of the real-time supply chain to analyze the current state value of the coal fuel supply chain; Strategy determination unit: Based on the current status of the coal fuel supply chain, local scheduling optimization is performed at each level to determine the optimal scheduling strategy for each level; Scheme determination unit: constructs an overall scheduling scheme and several alternative overall scheduling schemes based on the optimal scheduling strategies at all levels.

[0008] The present invention provides an intelligent coal fuel scheduling dynamic early warning system, wherein the levels of the multi-level scheduling model include: a production level, a transportation level, a storage level and a demand level.

[0009] The present invention provides an intelligent coal fuel scheduling dynamic early warning system, a strategy determination unit, comprising: State judgment subunit: judge whether the current state value of the coal fuel supply chain is greater than the bottleneck state value; Scheduling determination subunit: If the current state value of the coal fuel supply chain is greater than the bottleneck state value, scheduling is performed based on the preset scheduling plan for each level; if the current state of the coal fuel supply chain is not greater than the bottleneck state value, the scheduling target for each level is determined based on the current state value: Function acquisition subunit: determines the scheduling optimization function of each level based on the scheduling target of each level and the preset function; Domain determination subunit: determines the initial solution of the scheduling optimization function at each level based on preset rules, and performs neighborhood search based on the initial solution and a preset optimization algorithm to obtain the first candidate solution set of the scheduling optimization function at each level; Strategy determination subunit: Generates corresponding scheduling strategies based on the solutions in the first candidate solution set, and selects the scheduling strategy with the best corresponding objective function value as the optimal scheduling strategy, and the rest as candidate scheduling strategies.

[0010] The present invention provides an intelligent coal fuel dispatching dynamic early warning system, a neighborhood determination subunit, comprising: First search block: based on the initial solution of the scheduling optimization function at each level, determine the task allocation order of the devices at each level, and exchange the task allocation order two by two, and the task allocation order of each device is exchanged only once, and each exchange generates a corresponding neighborhood solution, and then determines several first neighborhood solutions corresponding to the initial solution; The second search block: insert each task of each device in each first domain solution into the task queue of any device in turn, and then generate several second neighborhood solutions. At the same time, substitute each second neighborhood solution into the objective function to determine the corresponding objective function value, select several second neighborhood solutions with the best objective value as the candidate solution set, and continue to update the candidate solution set until the preset search times are reached, then stop the task insertion operation, and finally determine the first candidate solution set.

[0011] The present invention provides an intelligent coal fuel dispatching dynamic early warning system, a scheme reconstruction module, comprising: Dispatching monitoring unit: dispatches according to the generated overall dispatching plan, monitors the dispatching process in real time, and obtains real-time monitoring data; Strategy adjustment unit: compares the real-time monitoring data with the preset plan in the overall scheduling plan. If the real-time monitoring data indicates that the current scheduling plan has a bottleneck, the alternative scheduling plan is called to adjust the local scheduling strategy; Scheme reconstruction unit: If bottlenecks still occur after the execution of the alternative scheduling scheme, the overall scheduling scheme is reconstructed based on the change data of the real-time monitoring data after the execution of the alternative scheme. The present invention provides an intelligent coal fuel scheduling dynamic early warning method, comprising: Step 1: Monitor each node in the coal fuel supply chain in real time through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; Step 2: Obtain historical scheduling data of the coal fuel supply chain and analyze it; Step 3: Construct a multi-level scheduling model based on the coal fuel supply chain, combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Step 4: Execute coal fuel scheduling based on the overall scheduling plan, and obtain real-time scheduling data to reconstruct the overall scheduling plan; Step 5: Build a multi-level early warning mechanism based on real-time coal fuel dispatch data and issue early warnings.

[0012] Compared with the prior art, the present invention has the following beneficial effects: To address the shortcomings of existing technologies such as the inability to flexibly respond to dynamic changes in the coal fuel supply chain and the lack of an effective real-time early warning mechanism, a multi-sensor network is used to monitor the dynamic data of supply chain nodes, and combined with historical scheduling analysis results, a multi-level scheduling model and early warning mechanism are generated to achieve dynamic optimization and early warning of coal fuel scheduling, thereby improving scheduling efficiency and supply chain stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 It is a structural schematic diagram of an intelligent coal fuel scheduling dynamic early warning system provided by an embodiment of the present invention.

[0015] Figure 2 It is a flow chart of an intelligent coal fuel scheduling dynamic early warning system method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, such as Figure 1 As shown, including: Data acquisition module: real-time monitoring of each node in the coal fuel supply chain through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; historical analysis module: obtain historical scheduling data of the coal fuel supply chain and analyze it; Solution acquisition module: Based on the coal fuel supply chain, a multi-level scheduling model is built to combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Scheme reconstruction module: executes coal fuel scheduling based on the overall scheduling plan, and reconstructs the overall scheduling plan by obtaining real-time scheduling data; Dispatching and early warning module: Build a multi-level early warning mechanism based on real-time dispatching data of coal fuel and issue early warnings.

[0018] In this embodiment, the preset multi-sensor network is a network composed of multiple sensors, which can monitor various key variables in the coal fuel supply chain in real time, such as temperature, humidity, transportation status, inventory changes, etc. Through this network, the status information of each link in the coal supply chain can be obtained in real time. For example, during the coal transportation process, the sensor network will monitor the location, temperature and humidity of the coal trucks. If the temperature of a truck is too high, it may trigger an early warning to remind the system to take cooling measures; In this embodiment, each node in the coal fuel supply chain refers to each link of coal production, transportation, storage to final use. The equipment, personnel, or materials in each link can be regarded as a node of the supply chain. The nodes of the coal supply chain may include mines (coal production), transport vehicles (transportation), ports (transit), power plants (coal use), etc. In this embodiment, dynamically changing data in the coal fuel supply chain refers to real-time information that changes over time in the coal fuel supply chain, such as inventory changes, transportation status, weather impacts, etc. For example, during transportation, a coal truck may be delayed due to traffic jams, and the sensor network will update the current location of the truck in real time. This is a type of dynamically changing data.

[0019] In this embodiment, historical scheduling data refers to the records and data of past coal fuel scheduling collected and stored by the system, including scheduling time, transportation routes, usage, etc. For example, the coal consumption data of a power plant in the past year, or the time records of coal transportation routes in the past period of time, are all historical scheduling data.

[0020] In this embodiment, the multi-level scheduling model is combined to make hierarchical scheduling plans based on different levels in the supply chain (such as production, transportation, storage and use), and perform local optimization according to different conditions of each level, while coordinating the overall supply chain scheduling. For example, at the production level, it is necessary to ensure the stability of mining in the mine, while at the transportation level, it is necessary to dispatch enough vehicles to meet the needs of the power plant. The multi-level scheduling model can combine the needs of these two levels for overall optimization; In this embodiment, local scheduling refers to making scheduling decisions at a specific link or node in the coal supply chain, rather than managing the entire chain. For example, if a shortage of trucks is found at the transportation level during a certain period of time, local scheduling can be performed to solve the problem in the transportation link by adding more dispatched vehicles. In this embodiment, the overall scheduling plan refers to comprehensively considering all links of the coal supply chain and formulating a global scheduling plan covering production to use. Assuming that a power plant needs a large amount of coal, the overall scheduling plan will make overall arrangements from multiple angles such as coal mining plan, transportation arrangement, storage conditions, and final power plant use to ensure smooth coordination of all links; In this embodiment, the alternative scheduling plan refers to a backup plan developed on the basis of the overall scheduling plan to deal with emergencies (such as transportation delays, equipment failures). If an accident occurs on the main transportation route, the alternative scheduling plan may activate a backup route or urgently call for more transportation vehicles to ensure that the power plant will not be out of coal.

[0021] In this embodiment, reconstructing the overall scheduling plan means dynamically adjusting and optimizing the plan based on the execution of the original overall scheduling plan in combination with real-time data to ensure the flexibility and adaptability of the scheduling. If there is a delay in the production of the coal mine, the system will automatically adjust the overall scheduling plan, such as modifying the transportation schedule or mobilizing spare vehicles, and reconstructing the scheduling plan.

[0022] In this embodiment, the early warning mechanism will make risk predictions and early warnings based on real-time data from different levels (such as the production level, transportation level, and usage level), and promptly alert potential problems. If the sensor detects that the coal inventory of the power plant has dropped to the warning line, or that traffic on a certain route in the transportation level is severely congested, the multi-level early warning mechanism will automatically issue an alarm, prompting the system or relevant personnel to take corresponding measures.

[0023] The beneficial effects of the above technical solution are: through the multi-sensor network monitoring the dynamic data of the supply chain nodes, combined with the historical scheduling analysis results, a multi-level scheduling model and early warning mechanism are generated to achieve dynamic optimization and early warning of coal fuel scheduling, and improve scheduling efficiency and supply chain stability.

[0024] Example 2 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, a historical analysis module, including: History extraction unit: extracts the scheduling data in the coal fuel supply chain from the history database to obtain the historical scheduling data; Historical classification unit: classifies historical dispatch data according to preset time periods to form historical dispatch archives within different time periods; Historical analysis unit: Based on the preset analysis algorithm, it analyzes the data of key factors related to scheduling in the historical scheduling archives in different time periods; Bottleneck determination unit: Analyze the data of key factors related to scheduling in different time periods to determine the historical scheduling bottlenecks of the coal fuel supply chain, and combine the data of key factors related to scheduling in different time periods to determine the impact coefficient of each historical scheduling bottleneck on scheduling efficiency: ; in, is the influence coefficient of the i-th historical scheduling bottleneck on scheduling efficiency, To preset the benchmark scheduling efficiency, is the influence coefficient of the jth key factor related to scheduling on scheduling efficiency in the bth time period, is the weight of the impact coefficient of the jth key factor related to scheduling in the bth time period, is the empirical weight of the historical scheduling bottleneck, is the sensitivity coefficient to the real-time scheduling change, is the elastic adjustment coefficient between the scheduling efficiency and the actual scheduling completion amount, is the scheduling efficiency without bottleneck, is the scheduling efficiency under the i-th historical scheduling bottleneck, m is the number of time periods, is the number of key factors related to scheduling in the bth time period, is the actual scheduling completion amount under the i-th historical scheduling bottleneck, is the planned scheduling completion amount under the i-th historical scheduling bottleneck; A historical scheduling bottleneck whose impact coefficient on scheduling efficiency is greater than a preset impact coefficient threshold is determined as a bottleneck state, and the bottleneck state value is determined based on the data of key factors related to scheduling in different time periods corresponding to the historical scheduling bottleneck greater than the preset impact coefficient threshold and the impact coefficient of the historical scheduling bottleneck on scheduling efficiency: ;in, is the bottleneck state value of the i-th historical scheduling bottleneck, To preset the impact coefficient threshold, is the weight coefficient of the i-th historical scheduling bottleneck.

[0025] In this embodiment, different time periods refer to dividing the data according to preset time periods (such as daily, weekly, monthly, quarterly, etc.), so that the data in different periods can be analyzed and processed separately. For example, the system classifies the data of the coal fuel supply chain by month, such as January, February, etc., so as to analyze the differences in scheduling efficiency in different months; In this embodiment, the preset analysis algorithm refers to an algorithm set in advance by the system for analyzing historical scheduling data, including statistical analysis, machine learning models, etc., which are used to find out the key factors affecting scheduling efficiency. For example, regression analysis is used to determine the impact of factors such as coal transportation speed and weather changes on monthly scheduling efficiency, and future scheduling bottlenecks are predicted through a preset machine learning algorithm.

[0026] In this embodiment, the key factors related to scheduling refer to various variables that affect the efficiency of coal fuel scheduling, such as weather, traffic conditions, availability of transportation tools, equipment failures, inventory levels, etc. When analyzing scheduling data, key factors may include transportation time, mine production capacity, coal consumption demand, etc. These factors directly affect the scheduling of the entire supply chain.

[0027] In this embodiment, the historical scheduling bottleneck refers to the main problem or obstacle that limits or affects the efficiency of coal fuel scheduling reflected in the historical data. For example, the historical data of the past year shows that a certain transportation route is often delayed due to snow in winter, resulting in a decrease in scheduling efficiency. This phenomenon is a historical scheduling bottleneck.

[0028] In this embodiment, the impact coefficient is used to quantify the impact of a certain scheduling bottleneck or key factor on the scheduling efficiency, reflecting its impact. For example, the impact coefficient of traffic congestion is 0.7. In certain circumstances, traffic congestion will cause the scheduling efficiency to decrease by 30%; In this embodiment, the elastic adjustment coefficient refers to the adjustment flexibility of the scheduling efficiency relative to the planned completion amount, reflecting the adjustment ability of the scheduling in the face of sudden changes. Assuming that a coal transportation can only complete 80% of the plan due to unexpected reasons, the elastic adjustment coefficient can reflect the system's response ability to such changes. If the elastic adjustment coefficient is large, it means that the system can flexibly adjust to deal with these unexpected situations; In this embodiment, the actual dispatch completion amount refers to the amount of tasks actually completed during the dispatch process, such as the actual number of tons of coal transported. For example, in a certain transportation cycle, it is planned to transport 1,000 tons of coal, but only 800 tons are actually completed, then 800 tons is the actual dispatch completion amount; In this embodiment, the planned scheduling completion volume is the target task volume pre-set in the scheduling plan, that is, the scheduling task volume planned to be completed within a certain time period. For example, in a certain time period, it is planned to transport 1,000 tons of coal, and these 1,000 tons are the planned scheduling completion volume.

[0029] In this embodiment, the preset impact coefficient threshold refers to a judgment standard set in a system. When the impact coefficient of a scheduling bottleneck exceeds this threshold, the system will consider that the bottleneck has a significant impact on the scheduling efficiency and regard it as a problem that requires special attention. Assuming that the impact coefficient threshold is set to 0.6, when the impact coefficient of a factor (such as traffic congestion) reaches 0.7, the system will consider that the impact of the factor on the scheduling efficiency exceeds the tolerance range, thereby triggering a bottleneck warning.

[0030] In this embodiment, the bottleneck status value is calculated based on the historical scheduling bottleneck and its impact coefficient, and is used to measure the severity of the bottleneck that may occur at present or in the future, reflecting the system's prediction and early warning of the bottleneck. For example, a historical bottleneck (such as low port loading and unloading efficiency) is determined to be the current bottleneck. The system will calculate the bottleneck status value based on its historical data. If the status value is too high (such as 0.8), it means that the bottleneck is very likely to affect the smooth progress of the current scheduling and immediate measures need to be taken.

[0031] The beneficial effects of the above technical solution are: by extracting and classifying the historical scheduling data of the coal fuel supply chain, analyzing the scheduling bottlenecks and their impact coefficients on the scheduling efficiency based on key factors, combining the scheduling key factor data of different time periods, dynamically determining the bottleneck status and its impact, providing in-depth analysis and quantitative evaluation of historical bottlenecks, improving the accuracy of scheduling efficiency prediction and the targeted scheduling optimization, and effectively reducing potential risks and delays in the supply chain.

[0032] Example 3 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, a solution acquisition module, including: Model building unit: Obtain the structural characteristics of the coal fuel supply chain to build a multi-level scheduling model; State determination unit: integrates the analysis results of historical scheduling data with the dynamic change data of the real-time supply chain to analyze the current state value of the coal fuel supply chain; Strategy determination unit: Based on the current status of the coal fuel supply chain, local scheduling optimization is performed at each level to determine the optimal scheduling strategy for each level; Scheme determination unit: constructs an overall scheduling scheme and several alternative overall scheduling schemes based on the optimal scheduling strategies at all levels.

[0033] In this embodiment, the structural characteristics of the coal fuel supply chain refer to the different links and elements of the entire process from the production source to the end user, including mining, transportation, storage, processing and use, as well as the dependencies, constraints and operation processes between these links. For example, the coal fuel supply chain includes mining in the mine, transporting coal to the port by rail or road, storing and loading at the port, and finally delivering it to the power plant. Each link has different operating characteristics. For example, the transportation link needs to consider road conditions and climate factors, while the storage link needs to consider storage capacity and environmental protection requirements.

[0034] In this embodiment, the multi-level scheduling model divides the different links of the coal fuel supply chain into multiple levels, and each level has its own independent scheduling plan and optimization process. Through this layered approach, each link can be optimized independently and coordinated between different levels to achieve efficient operation of the overall supply chain. For example, in the multi-level scheduling model, the production layer is responsible for the mining volume scheduling of the mine area, the transportation layer is responsible for the logistics arrangement of coal, the storage layer is responsible for warehouse management and storage planning, and the use layer (such as power plants) is responsible for coal combustion scheduling. Each level optimizes its scheduling plan according to its own needs and constraints, such as optimizing transportation routes in the transportation layer to reduce costs; In this embodiment, the optimal scheduling strategy is the best operation plan obtained through scheduling optimization for each specific level under the current supply chain state. This plan is usually the result of trade-offs and selections under the goals of ensuring efficiency, reducing costs, and improving response speed. For example, at the transportation level, the optimal scheduling strategy may be to choose the route with the most unobstructed traffic during a specific time period, or to arrange a specific type of transportation tool under specific weather conditions to maximize transportation efficiency. At the production level, the optimal scheduling strategy may be to adjust production according to market demand and storage capacity to ensure the balance of the supply chain.

[0035] In this embodiment, the overall scheduling scheme and several alternative overall scheduling schemes are constructed based on the optimal scheduling strategies of all levels. The optimal scheduling strategies of each level are integrated to form a scheduling plan suitable for the entire supply chain. This plan coordinates the actions of each level to ensure the overall optimization of the supply chain. In addition, the system usually constructs several alternative plans so that the strategy can be adjusted quickly in the event of accidents or changes. Assume that the optimal strategy of the production layer is to produce 5,000 tons of coal per day, the strategy of the transportation layer is to arrange 15 trucks for transportation every day, and the strategy of the storage layer is to keep the inventory of the warehouse below 10,000 tons. These optimal strategies will be combined into an overall scheduling plan. If there are delays in transportation or the storage facilities are full, the alternative plan may be to adjust the transportation time or increase the transportation vehicles, or to transport directly from the production site to the use site to bypass the storage facilities.

[0036] The beneficial effects of the above technical solution are: by combining historical scheduling data with real-time dynamic data, building a multi-level scheduling model, dynamically analyzing the supply chain status, and combining the local optimization strategies at each level with the global scheduling solution, the flexibility and accuracy of scheduling are achieved. By providing the optimal scheduling solution and alternative solutions, the adaptability and emergency handling capabilities of the system are enhanced, and the overall scheduling efficiency and stability of the coal fuel supply chain are effectively improved.

[0037] Example 4 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, and the levels of the multi-level scheduling model include: production level, transportation level, storage level and demand level.

[0038] In this embodiment, the production layer: determines the production plan according to the coal mine production capacity and the resource mining progress, the transportation layer: optimizes the transportation route according to the traffic conditions, transportation tools and routes, the storage layer: determines a reasonable storage strategy based on inventory capacity and demand fluctuations, and the demand layer: balances supply and demand according to the dynamic changes in fuel demand.

[0039] The beneficial effects of the above technical solution are: through a multi-level scheduling model, the production layer, transportation layer, storage layer and demand layer are innovatively integrated into the coal fuel scheduling system, achieving efficient coordination and dynamic optimization among the various levels, comprehensively considering all links in the supply chain, improving the accuracy and response speed of the overall scheduling, ensuring the rational allocation of resources, reducing bottlenecks and delays in the supply chain, and enhancing the stability and flexibility of the system.

[0040] Example 5 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, a strategy determination unit, including: State judgment subunit: judge whether the current state value of the coal fuel supply chain is greater than the bottleneck state value; Scheduling determination subunit: If the current state value of the coal fuel supply chain is greater than the bottleneck state value, scheduling is performed based on the preset scheduling plan for each level; if the current state of the coal fuel supply chain is not greater than the bottleneck state value, the scheduling target for each level is determined based on the current state value: Function acquisition subunit: determines the scheduling optimization function of each level based on the scheduling target of each level and the preset function; Domain determination subunit: determines the initial solution of the scheduling optimization function at each level based on preset rules, and performs neighborhood search based on the initial solution and a preset optimization algorithm to obtain the first candidate solution set of the scheduling optimization function at each level; Strategy determination subunit: Generates corresponding scheduling strategies based on the solutions in the first candidate solution set, and selects the scheduling strategy with the best corresponding objective function value as the optimal scheduling strategy, and the rest as candidate scheduling strategies.

[0041] In this embodiment, the preset scheduling scheme is a standard scheduling scheme designed in advance for each level (such as production, transportation, storage, and use) by the system based on historical data and structural characteristics of the coal fuel supply chain. This scheme specifies how each level is scheduled under normal circumstances. For example, the preset scheduling scheme of the production layer may specify that the mine produces 5,000 tons of coal per day, the scheme of the transportation layer may specify that 10 trucks are arranged for transportation every day, and the scheme of the storage layer specifies that the warehouse can hold a maximum of 20,000 tons of coal; In this embodiment, the scheduling target of each level is a specific scheduling task set by the system for each level according to the current status of the supply chain. It is adjusted on the basis of the preset plan to adapt to the current actual situation. For example, during the peak coal consumption period, the scheduling target may require the production layer to increase production to 7,000 tons, the transportation layer to arrange more vehicles for transportation, and the storage layer to minimize storage to ensure supply.

[0042] In this embodiment, the preset function is a formula or algorithm used by the system to measure the scheduling effect. It is used to calculate the scheduling efficiency, cost, time and other factors at each level to help the system make optimization decisions. For example, the preset function of the transportation layer is a formula for calculating the transportation time, which takes into account factors such as transportation distance, traffic conditions and number of vehicles; In this embodiment, the scheduling optimization function is based on the scheduling objectives of each level, and the scheduling plan is optimized through a functional expression, which needs to minimize cost, time, or maximize efficiency. For example, the scheduling optimization function of the transportation layer may be a "transportation time minimization" function, whose goal is to reduce the vehicle's in-transit time and queue waiting time.

[0043] In this embodiment, the preset rules are restrictions or constraints set by the system for scheduling optimization to ensure that the scheduling plan is within the feasible range. For example, the rules may stipulate that the scheduling of a certain level cannot exceed a specific production capacity or transportation capacity. For example, the system may stipulate that a maximum of 15 trucks can be arranged in a day at the transportation level, and this limit cannot be exceeded; In this embodiment, the initial solution refers to a scheduling plan first generated by the system based on the current state and preset rules before optimization. This is the starting point of the optimization process. Subsequent optimization is gradually improved on the basis of the initial solution. The initial solution may be a scheduling plan given according to the normal working state, such as producing 5,000 tons of coal and arranging 8 trucks for transportation; In this embodiment, the preset optimization algorithm is an algorithm for solving the scheduling optimization function, which helps the system to find a better scheduling solution from the initial solution, including genetic algorithm, simulated annealing, particle swarm algorithm, etc. For example, the genetic algorithm is used to find the optimal scheduling solution by continuously adjusting and screening the parameters of the scheduling solution (such as transportation time and number of vehicles); In this embodiment, neighborhood search refers to the process of starting from an initial solution or a current solution in an optimization algorithm, generating a new solution by making small adjustments to certain variables, and gradually exploring a better solution. For example, the transportation route or departure time is adjusted through neighborhood search to try to find a solution to reduce the transportation time, for example, changing the departure time of a truck or changing the transportation route to test whether the efficiency can be improved; In this embodiment, the first candidate solution set is a set of multiple possible optimized scheduling schemes generated by the system after a neighborhood search. Each scheme may be a different optimization result for scheduling efficiency, time or cost. For example, after a neighborhood search, the system generates several candidate solutions, such as arranging 8, 9, or 10 trucks for transportation, or changing different departure times. Each solution is a candidate solution.

[0044] In this embodiment, the optimal scheduling strategy is the best scheduling solution selected from the first candidate solution set under the current circumstances, that is, the solution with the best objective function value. It is the best solution selected from multiple alternative solutions by measuring indicators such as scheduling efficiency, time and cost. For example, after calculation, the system selects the solution of arranging 9 trucks and starting transportation at 8 am as the optimal scheduling strategy because it is the most effective in reducing transportation time and cost. In this embodiment, alternative scheduling strategies refer to other candidate solutions that have not been selected as the optimal solution. They serve as backup solutions. Once the optimal strategy cannot be implemented (such as in an emergency), the system can switch to these alternative strategies for execution. For example, if the optimal scheduling strategy arranges 9 trucks for transportation, but only 8 vehicles can be used due to vehicle failures, the system can switch to the alternative strategy and execute the plan of 8 trucks for transportation.

[0045] The beneficial effects of the above technical solution are: dynamic optimization of intelligent coal fuel scheduling is achieved through the strategy determination unit, whether there is a bottleneck is determined according to the supply chain status value, the scheduling strategy is flexibly adjusted, and the scheduling optimization function and neighborhood search technology are combined to generate the optimal scheduling plan and retain alternative strategies, which effectively improves the intelligence and adaptability of the scheduling process, ensures the efficient and smooth operation of the supply chain, and reduces resource waste and scheduling bottlenecks.

[0046] Example 6 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning system, the neighborhood determination subunit includes: First search block: based on the initial solution of the scheduling optimization function at each level, determine the task allocation order of the devices at each level, and exchange the task allocation order two by two, and the task allocation order of each device is exchanged only once, and each exchange generates a corresponding neighborhood solution, and then determines several first neighborhood solutions corresponding to the initial solution; The second search block: insert each task of each device in each first domain solution into the task queue of any device in turn, and then generate several second neighborhood solutions. At the same time, substitute each second neighborhood solution into the objective function to determine the corresponding objective function value, select several second neighborhood solutions with the best objective value as the candidate solution set, and continue to update the candidate solution set until the preset search times are reached, then stop the task insertion operation, and finally determine the first candidate solution set.

[0047] In this embodiment, the task allocation order refers to the execution order in which the system assigns tasks to each device (such as transport vehicles, production equipment, storage facilities, etc.) according to the scheduling optimization function. Each device needs to complete its own tasks in this order to achieve the overall optimization goal. Assuming there are three transport trucks (A, B, C) and five transport tasks (T1, T2, T3, T4, T5), the task allocation order may be that truck A performs tasks T1 and T3, truck B performs tasks T2 and T4, and truck C performs task T5. In this way, the tasks of each vehicle have an execution order, and the task allocation order of truck A is "T1 ->T3"; In this embodiment, the first neighborhood solution is a new solution generated by slightly adjusting the task allocation order of the equipment (for example, exchanging the task order two by two). In the scheduling optimization process, a set of new solutions generated by this simple exchange of the initial solution is the first neighborhood solution. Assuming that the task allocation order of truck A is "T1 ->T3", if the order of these two tasks is exchanged to "T3 ->T1", then this new allocation method is the first neighborhood solution of truck A. Similarly, the task order of truck B can be changed from "T2 ->T4" to "T4 ->T2", which is also a first neighborhood solution.

[0048] In this embodiment, the second neighborhood solution is a new solution generated by inserting the task of a certain device into the task queue of another device based on the first neighborhood solution. Compared with the simple two-by-two exchange of the first neighborhood solution, the second neighborhood solution is a cross-device task rearrangement method. If in the first neighborhood solution, the task sequence of truck A is "T3 ->T1" and the task sequence of truck B is "T4 ->T2", then we can insert truck A's task T3 into the task queue of truck B, for example, between T4 and T2, then this new arrangement is a second neighborhood solution. That is, truck A's task becomes "T1" and truck B's task sequence becomes "T4 ->T3 ->T2"; In this embodiment, the candidate solution set is a set of alternative scheduling solutions generated through the neighborhood search process, which are evaluated and the better solutions are selected based on the objective function value. The solutions in the candidate solution set are constantly updated to approach the optimal solution. For example, after multiple neighborhood searches, the system may generate multiple different scheduling solutions, such as: Solution 1: Truck A executes "T1 ->T3", Truck B executes "T4 ->T2", and Truck C executes "T5"; Solution 2: Truck A executes "T1", Truck B executes "T4 ->T3 ->T2", and Truck C executes "T5".

[0049] In this embodiment, the first candidate solution set is a set of optimal or near-optimal scheduling solutions determined by the neighborhood search process. These solutions are screened out from the candidate solution set, have relatively good objective function values, and are considered as priority scheduling alternatives. Assume that after several task allocation order adjustments (first neighborhood solutions) and task queue insertion operations (second neighborhood solutions), the system generates several scheduling solutions, of which three solutions have the highest efficiency or the lowest cost. These three solutions are determined as the first candidate solution set. For example: Solution 1: Truck A executes "T1 -> T3", Truck B executes "T4 -> T2", and Truck C executes "T5"; Solution 2: Truck A executes "T1", Truck B executes "T4 -> T3 -> T2", and Truck C executes "T5"; Solution 3: Truck A executes "T3 -> T1", Truck B executes "T2 -> T4", and Truck C executes "T5".

[0050] The beneficial effects of the above technical solution are: through the dual search strategy, the order of equipment task allocation is innovatively optimized, neighborhood solutions are generated through task exchange and insertion, and the optimal candidate solution set is screened in combination with the objective function, which significantly improves the global optimization capability of the scheduling scheme, effectively improves the flexibility and accuracy of task allocation, reduces scheduling conflicts and resource waste, and ensures maximum system operation efficiency.

[0051] Example 7 Dispatching monitoring unit: dispatches according to the generated overall dispatching plan, monitors the dispatching process in real time, and obtains real-time monitoring data; Strategy adjustment unit: compares the real-time monitoring data with the preset plan in the overall scheduling plan. If the real-time monitoring data indicates that the current scheduling plan has a bottleneck, the alternative scheduling plan is called to adjust the local scheduling strategy; Scheme reconstruction unit: If bottlenecks still occur after the execution of the alternative scheduling scheme, the overall scheduling scheme is reconstructed based on the change data of the real-time monitoring data after the execution of the alternative scheme. In this embodiment, the preset plan in the overall scheduling scheme refers to the ideal scheduling scheme formulated in advance before the execution of the scheduling, based on factors such as the demand, resource distribution and time arrangement of the coal supply chain. This plan is the basis for the operation of the system under normal circumstances, and aims to optimize the task execution sequence and time arrangement of each link. Assuming that a coal transportation plan includes multiple steps from the mining area to the power plant, the preset plan may stipulate that 5,000 tons of coal are transported every day, 10 trucks are dispatched from the mining area to the storage warehouse every hour, and the train transports the coal in the warehouse to the power plant every 8 hours. This preset plan assumes that under normal circumstances, the capacity, route and time arrangement of trucks and trains are stable and there will be no sudden problems.

[0052] In this embodiment, reconstructing the overall scheduling plan means that when the original scheduling plan cannot adapt to the current changes, based on the latest monitoring data and feedback information, a new scheduling plan is readjusted and designed. This new plan takes into account the bottlenecks and problems encountered during the execution process, and globally optimizes tasks, resource allocation, etc. Assume that in the above preset plan, due to severe congestion on a major transportation road, the original plan of 10 trucks cannot be completed on time. The system will first call the alternative plan, which may be adjusted to enable an alternative route or increase the number of trucks. However, if the congestion continues or the alternative route also has problems, resulting in the alternative plan being unable to solve the problem, the system will reconstruct the overall scheduling plan, such as adjusting the transportation frequency between the warehouse and the power plant, or rearranging the mining volume of the mining area, reducing the pressure on the supply chain, and finally designing a new scheduling plan that adapts to the current situation.

[0053] The beneficial effects of the above technical solution are: by real-time monitoring of the scheduling process, automatic identification of bottlenecks and calling of alternative plans, the flexibility and adaptability of scheduling are significantly improved, and the overall scheduling plan can be dynamically reconstructed based on real-time data when the alternative plan fails, ensuring the continuous and efficient operation of the system in a complex environment and reducing the risk of stagnation and waste of resources.

[0054] Example 8 The embodiment of the present invention provides an intelligent coal fuel scheduling dynamic early warning method, comprising: Step 1: Monitor each node in the coal fuel supply chain in real time through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; Step 2: Obtain historical scheduling data of the coal fuel supply chain and analyze it; Step 3: Construct a multi-level scheduling model based on the coal fuel supply chain, combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Step 4: Execute coal fuel scheduling based on the overall scheduling plan, and reconstruct the overall scheduling plan by obtaining real-time scheduling data; Step 5: Build a multi-level early warning mechanism based on real-time coal fuel dispatch data and issue early warnings.

[0055] The beneficial effects of the above technical solution are: through the multi-sensor network monitoring the dynamic data of the supply chain nodes, combined with the historical scheduling analysis results, a multi-level scheduling model and early warning mechanism are generated to achieve dynamic optimization and early warning of coal fuel scheduling, and improve scheduling efficiency and supply chain stability.

[0056] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0057] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent coal fuel dispatching dynamic early warning system, characterized in that: include: Data acquisition module: Real-time monitoring of each node in the coal fuel supply chain through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; Historical analysis module: obtains and analyzes historical scheduling data of the coal fuel supply chain; Solution acquisition module: Based on the coal fuel supply chain, a multi-level scheduling model is built to combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Scheme reconstruction module: executes coal fuel scheduling based on the overall scheduling plan, and obtains real-time scheduling data to reconstruct the overall scheduling plan; Dispatching and early warning module: Build a multi-level early warning mechanism based on real-time dispatching data of coal fuel and issue early warnings.

2. According to claim 1, an intelligent coal fuel scheduling dynamic early warning system is characterized in that: Historical analysis module, including: History extraction unit: extracts the scheduling data in the coal fuel supply chain from the history database to obtain the historical scheduling data; Historical classification unit: classifies historical dispatch data according to preset time periods to form historical dispatch archives within different time periods; Historical analysis unit: Based on the preset analysis algorithm, it analyzes the data of key factors related to scheduling in the historical scheduling archives in different time periods; Bottleneck determination unit: Analyze the data of key factors related to scheduling in different time periods to determine the historical scheduling bottlenecks of the coal fuel supply chain, and combine the data of key factors related to scheduling in different time periods to determine the impact coefficient of each historical scheduling bottleneck on scheduling efficiency: ； in, is the influence coefficient of the i-th historical scheduling bottleneck on scheduling efficiency, To preset the benchmark scheduling efficiency, is the influence coefficient of the jth key factor related to scheduling on scheduling efficiency in the bth time period, is the weight of the impact coefficient of the jth key factor related to scheduling in the bth time period, is the empirical weight of the historical scheduling bottleneck, is the sensitivity coefficient to the real-time scheduling change, is the elastic adjustment coefficient between the scheduling efficiency and the actual scheduling completion amount, For the scheduling efficiency without bottleneck, is the scheduling efficiency under the i-th historical scheduling bottleneck, m is the number of time periods, is the number of key factors related to scheduling in the bth time period, is the actual scheduling completion amount under the i-th historical scheduling bottleneck, is the planned scheduling completion amount under the i-th historical scheduling bottleneck; A historical scheduling bottleneck whose impact coefficient on scheduling efficiency is greater than a preset impact coefficient threshold is determined as a bottleneck state, and the bottleneck state value is determined based on the data of key factors related to scheduling in different time periods corresponding to the historical scheduling bottleneck greater than the preset impact coefficient threshold and the impact coefficient of the historical scheduling bottleneck on scheduling efficiency: ;in, is the bottleneck state value of the i-th historical scheduling bottleneck, To preset the impact coefficient threshold, is the weight coefficient of the i-th historical scheduling bottleneck.

3. According to claim 1, an intelligent coal fuel scheduling dynamic early warning system is characterized in that: Solution acquisition module, including: Model building unit: Obtain the structural characteristics of the coal fuel supply chain to build a multi-level scheduling model; State determination unit: integrates the analysis results of historical scheduling data with the dynamic change data of the real-time supply chain to analyze the current state value of the coal fuel supply chain; Strategy determination unit: Based on the current status of the coal fuel supply chain, local scheduling optimization is performed at each level to determine the optimal scheduling strategy for each level; Scheme determination unit: constructs an overall scheduling scheme and several alternative overall scheduling schemes based on the optimal scheduling strategies at all levels.

4. According to claim 3, an intelligent coal fuel scheduling dynamic early warning system is characterized in that: The levels of the multi-level scheduling model include: production level, transportation level, storage level, and demand level.

5. The intelligent coal fuel dispatching dynamic early warning system according to claim 3 is characterized in that: A policy determination unit, comprising: State judgment subunit: judge whether the current state value of the coal fuel supply chain is greater than the bottleneck state value; Scheduling determination subunit: If the current state value of the coal fuel supply chain is greater than the bottleneck state value, scheduling is performed based on the preset scheduling plan for each level; if the current state of the coal fuel supply chain is not greater than the bottleneck state value, the scheduling target for each level is determined based on the current state value: Function acquisition subunit: determines the scheduling optimization function of each level based on the scheduling target of each level and the preset function; Domain determination subunit: determines the initial solution of the scheduling optimization function at each level based on preset rules, and performs neighborhood search based on the initial solution and a preset optimization algorithm to obtain the first candidate solution set of the scheduling optimization function at each level; Strategy determination subunit: Generates corresponding scheduling strategies based on the solutions in the first candidate solution set, and selects the scheduling strategy with the best corresponding objective function value as the optimal scheduling strategy, and the rest as candidate scheduling strategies.

6. The intelligent coal fuel dispatching dynamic early warning system according to claim 5 is characterized in that: The neighborhood determination subunit includes: First search block: based on the initial solution of the scheduling optimization function at each level, determine the task allocation order of the devices at each level, and exchange the task allocation order two by two, and the task allocation order of each device is exchanged only once, and each exchange generates a corresponding neighborhood solution, and then determines several first neighborhood solutions corresponding to the initial solution; The second search block: insert each task of each device in each first domain solution into the task queue of any device in turn, and then generate several second neighborhood solutions. At the same time, substitute each second neighborhood solution into the objective function to determine the corresponding objective function value, select several second neighborhood solutions with the best objective value as the candidate solution set, and continue to update the candidate solution set until the preset search times are reached, then stop the task insertion operation, and finally determine the first candidate solution set.

7. The intelligent coal fuel dispatching dynamic early warning system according to claim 1 is characterized in that: Solution reconstruction module, including: Dispatching monitoring unit: dispatches according to the generated overall dispatching plan, monitors the dispatching process in real time, and obtains real-time monitoring data; Strategy adjustment unit: compares the real-time monitoring data with the preset plan in the overall scheduling plan. If the real-time monitoring data indicates that the current scheduling plan has a bottleneck, the alternative scheduling plan is called to adjust the local scheduling strategy; Scheme reconstruction unit: If bottlenecks still occur after the execution of the alternative scheduling scheme, the overall scheduling scheme is reconstructed based on the change data of the real-time monitoring data after the execution of the alternative scheme.

8. An intelligent coal fuel scheduling dynamic early warning method, characterized in that: include: Step 1: Monitor each node in the coal fuel supply chain in real time through a preset multi-sensor network to obtain dynamic change data in the coal fuel supply chain; Step 2: Obtain historical scheduling data of the coal fuel supply chain and analyze it; Step 3: Construct a multi-level scheduling model based on the coal fuel supply chain, combine the analysis results based on historical scheduling data and the dynamic change data of the supply chain to perform local scheduling at different levels, and then generate an overall scheduling plan and an overall alternative scheduling plan; Step 4: Execute coal fuel scheduling based on the overall scheduling plan, and obtain real-time scheduling data to reconstruct the overall scheduling plan; Step 5: Build a multi-level early warning mechanism based on real-time coal fuel dispatch data and issue early warnings.

Images