Maintenance and transport vehicle scheduling method for distributed household garbage disposal site network

Abstract

The invention discloses a distributed household garbage disposal site network maintenance and transport vehicle scheduling method, and relates to the technical field of intelligent city management, and the method comprises the steps: monitoring the working state parameters and environment monitoring data of each household garbage disposal site; performing multi-dimensional fault judgment based on the working state parameters and the environment monitoring data to obtain a fault site judgment result; if the fault site is detected, acquiring geographical location information of a plurality of maintenance vehicles in an adjacent area based on the location of the fault site; determining a target maintenance vehicle and an optimal maintenance path based on the geographic position information and the acquired real-time traffic data by adopting a path planning algorithm; obtaining maintenance vehicles, preferably maintenance paths and transport vehicle information of all household garbage disposal site networks, and determining maintenance task priorities and maintenance vehicle scheduling plans by adopting a planning optimization algorithm in combination with historical scheduling and maintenance optimization strategies; according to the invention, the maintenance scheduling efficiency of the household garbage disposal site network is improved.

Description

Technical Field

[0001] This application relates to the field of intelligent urban management technology, and in particular to a method for scheduling maintenance and transport vehicles in a decentralized municipal solid waste treatment site network. Background Technology

[0002] With the acceleration of urbanization, the treatment and collection of household waste has become an important part of urban management.

[0003] In existing technologies, municipal solid waste treatment sites typically employ centralized management. When a site malfunctions, it relies on manual reporting and manual dispatch of maintenance resources, which can easily lead to the following problems: 1. Long maintenance response time causes faulty sites to be unable to operate normally for extended periods; 2. Vehicle dispatching efficiency is low, and it is impossible to dynamically adjust according to real-time traffic conditions and station operating status; Therefore, there is a deficiency in the efficiency of maintenance and scheduling of the municipal solid waste treatment site network, which needs to be improved. Summary of the Invention

[0004] To improve the maintenance and scheduling efficiency of a municipal solid waste treatment site network, this application provides a method for scheduling maintenance and transportation vehicles in a decentralized municipal solid waste treatment site network.

[0005] Firstly, the objective of this invention is achieved through the following technical solution: Methods for maintenance and transportation vehicle scheduling in decentralized municipal solid waste treatment site networks include: Monitor the operational status parameters and environmental monitoring data of each municipal solid waste treatment site; Based on the working status parameters and the environmental monitoring data, a multi-dimensional fault judgment is performed to obtain the fault site judgment result; if a fault site is detected, the geographical location information of multiple maintenance vehicles in the vicinity of the fault site is obtained based on the location of the fault site; a path planning algorithm is used to determine the target maintenance vehicle and the optimal maintenance route based on the geographical location information and the obtained real-time traffic data; Information on maintenance vehicles, optimal maintenance routes, and transport vehicles for the entire municipal solid waste treatment site network is obtained. A planning optimization algorithm is used to determine the priority of maintenance tasks and the scheduling plan for maintenance vehicles with the overall scheduling cost and scheduling efficiency as the co-optimization objectives.

[0006] By adopting the above technical solution, algorithms for real-time monitoring and intelligent identification of faulty sites are used to shorten maintenance response time and quickly restore site operation. By monitoring the operational status parameters of each municipal solid waste treatment site, sites requiring maintenance are identified, i.e., faulty sites are identified through faulty site detection. If a faulty site is detected, the geographical location information of multiple maintenance vehicles in the vicinity is obtained, along with real-time traffic data, including road congestion index, speed limits, and construction zones. Then, a path planning algorithm is used to plan the optimal maintenance route with the shortest distance or fastest path. When formulating the maintenance scheduling plan, based on all target maintenance vehicles and corresponding optimal maintenance routes in the entire municipal solid waste treatment site network, factors such as vehicle travel time, route intersections, and task priority are considered to avoid traffic conflicts and ensure that maintenance vehicles have priority over waste transport vehicles. The vehicle scheduling plan is dynamically adjusted according to real-time traffic conditions and site operational status. In practical applications, for example, allowing maintenance vehicles to make way in route planning and time scheduling, while adjusting the travel order and time intervals of waste transport vehicles, the probability of encounters and conflicts is reduced, improving overall maintenance scheduling efficiency.

[0007] In a preferred embodiment of this application, the steps for generating the historical scheduling and maintenance optimization strategy include: Based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, the system identifies and acquires the equipment failure patterns and waste accumulation status data of each treatment site during operation, and determines the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities, and the treatment site is associated with a site identifier; Based on the site identifier, historical scheduling and maintenance record data of each processing site are obtained. The optimized historical vehicle scheduling and maintenance response model is obtained by training and optimizing the model based on minimizing the overall cost in the preset initial scheduling optimization model. The spatial correlation degree and fault propagation impact factor between each processing site are calculated and determined to obtain the site correlation impact coefficient of all processing sites. In the optimized historical vehicle scheduling and maintenance response model, the minimum maintenance response time and the optimal waste collection frequency of each processing station are determined by combining the site correlation influence coefficients of all processing stations in different operation and maintenance phases, and historical scheduling and maintenance optimization strategies are generated.

[0008] By adopting the above technical solutions, an adaptive optimization model is trained using historical operational data to achieve dynamic updates of the scheduling strategy; by modeling the correlation impact coefficient, the risk of fault propagation between sites is quantified to prevent the spread of cascading faults; and by combining spatial proximity and maintenance priority, a multi-objective collaborative scheduling strategy library is generated to improve the system's flexibility in responding to emergencies.

[0009] In a preferred embodiment, this application involves identifying and acquiring data on equipment failure patterns and waste accumulation status at each treatment site based on historical operational monitoring datasets from a distributed municipal solid waste treatment site network, and determining the operation and maintenance mode information for each treatment site. Specifically, this includes: Based on historical operation monitoring datasets, obtain equipment operation status logs, fault alarm time records, and historical waste storage data for each processing station within the historical monitoring period; Based on the downtime, fault alarm time record, and historical waste storage volume data change trend of the equipment operation status log, multiple historical monitoring time intervals are divided. Based on the site identifier and multiple historical monitoring time intervals, generate equipment health status assessment parameters that include equipment health status intervals and equipment failure occurrence patterns, and waste accumulation status parameters that include waste accumulation level intervals. Based on the equipment health status assessment parameters and waste accumulation status parameters, and in conjunction with the preset maintenance mode determination rules, the operation and maintenance mode information of each processing station is determined.

[0010] By adopting the above technical solution and based on historical operation monitoring datasets, the analysis of equipment health status logs, fault alarm time records, and historical waste storage data at each processing site enables a detailed assessment of equipment health status. This facilitates the early detection of potential problems and the implementation of preventative measures. Dividing the equipment operation status logs into multiple monitoring time intervals based on historical monitoring trends allows for more refined management and facilitates adjustments to maintenance strategies according to the characteristics of different time periods. Furthermore, by dynamically determining the operation and maintenance mode information for each processing site based on equipment health status assessment parameters and waste accumulation status parameters, combined with preset maintenance mode determination rules, the targeted and effective maintenance work is ensured.

[0011] In a preferred embodiment of this application: the calculation of the site correlation impact coefficient is based on geographical proximity, traffic connectivity, and fault propagation correlation; the spatial correlation and fault propagation impact factor between each processing site are calculated and determined to obtain the site correlation impact coefficient of all processing sites, including: The system acquires the geographical distance, road travel time, shared equipment component information, and historical cascading fault records between each processing station; iterates through and calculates the spatial proximity coefficient between adjacent processing stations based on the geographical distance and road travel time, and obtains the spatial correlation based on the spatial proximity coefficient; and calculates the fault propagation impact factor based on the shared equipment component information and historical cascading fault records. Combining the spatial correlation degree and the fault propagation influence factor, a correlation influence weight matrix between processing sites is constructed, and after normalization, the site correlation influence coefficient of all processing sites is obtained.

[0012] By adopting the above technical solution, the correlation influence between sites is quantified. A weight matrix of correlation influence between sites is established by calculating geographical distance, road travel time, and shared equipment component information between sites, enabling quantitative analysis of the spatial correlation between sites and the influencing factors of fault propagation. The site correlation influence coefficients obtained after normalizing the correlation influence weight matrix can more intuitively reflect the degree of mutual influence between sites, which helps to accurately predict fault propagation paths.

[0013] In a preferred embodiment of this application: the preferred maintenance path consists of several trajectory points; the process of obtaining information on maintenance vehicles, preferred maintenance paths, and transport vehicles from the entire network of municipal solid waste treatment sites, and employing a planning optimization algorithm combined with historical scheduling and maintenance optimization strategies to determine maintenance task priorities and maintenance vehicle scheduling plans, specifically includes: The system acquires the location, task status, and estimated arrival time of maintenance vehicles across the entire municipal solid waste treatment network; it also simultaneously collects the geographic coordinates and estimated travel time of each trajectory point along the preferred maintenance route, and integrates the vehicle's driving route, estimated return time, and historical waste collection efficiency information. Load historical scheduling and maintenance optimization strategies based on historical scheduling records; A mixed-integer linear programming algorithm is adopted to minimize the total scheduling cost and maximize the scheduling efficiency. A multi-objective optimization model is constructed by combining real-time multi-source data and historical scheduling and maintenance optimization strategies. Determine the priority of maintenance tasks for each faulty site; The matching score between maintenance vehicles and fault stations is calculated based on vehicle tool matching degree and estimated arrival time; the matching score between transport vehicles and collection stations is calculated based on remaining capacity, load utilization rate and historical collection efficiency of transport vehicles. A multi-objective optimization model is used to determine the optimal matching of maintenance vehicles with fault stations and transport vehicles with waste disposal stations.

[0014] By adopting the above technical solution and using a mixed-integer linear programming algorithm, with the goal of minimizing total scheduling cost and maximizing scheduling efficiency, and combining real-time multi-source data and historical scheduling and maintenance optimization strategies, the system achieves accurate prioritization of maintenance tasks and optimal matching of maintenance vehicles and transport vehicles, which greatly improves operational efficiency and service quality.

[0015] In a preferred embodiment of this application: the multi-dimensional fault judgment based on the operating status parameters and the environmental monitoring data to obtain the fault site judgment result includes: The operating parameters include equipment operating temperature, hydraulic system pressure, motor speed, and waste compression chamber pressure; the environmental monitoring data include waste storage volume, internal temperature and humidity, and concentration of harmful gases. The operating temperature of the equipment, the pressure of the hydraulic system, the speed of the motor, and the pressure of the garbage compression chamber are compared with the corresponding normal operating parameters to determine whether there are any abnormal operating parameters. Calculate the rate of change of waste storage volume and the rate of change of temperature and humidity. Based on the rate of change of waste storage volume, the rate of change of temperature and humidity and the concentration of harmful gases, determine whether there are any abnormal environmental parameters. If there are abnormal operating parameters or abnormal environmental parameters, the fault site judgment result containing fault warning information will be output.

[0016] By adopting the above technical solution, key working status parameters (such as equipment operating temperature, hydraulic system pressure, etc.) are compared with normal operating parameters. At the same time, environmental monitoring data such as the rate of change of waste storage volume and the rate of change of temperature and humidity are taken into account, so as to achieve accurate judgment and timely early warning of faulty sites and reduce the risk of service interruption caused by faults.

[0017] Secondly, the objective of this invention is achieved through the following technical solution: A maintenance and transportation vehicle dispatching system for a decentralized municipal solid waste treatment site network, the system including: The status monitoring module is used to monitor the working status parameters and environmental monitoring data of each municipal solid waste treatment site; The fault diagnosis module is used to perform multi-dimensional fault diagnosis based on the working status parameters and the environmental monitoring data, and output the fault site diagnosis result. The vehicle positioning and route planning module is used to obtain the geographical location information of multiple repair vehicles in the vicinity when a fault site is detected, and combine it with real-time traffic data to determine the target repair vehicle and the preferred repair route to the fault site using a route planning algorithm. The scheduling optimization module is used to obtain information on maintenance vehicles, optimal maintenance routes, and transport vehicles in the entire network of municipal solid waste treatment sites. It uses a planning optimization algorithm combined with pre-stored historical scheduling and maintenance optimization strategies to determine the priority of maintenance tasks and the scheduling plan for maintenance vehicles, thereby realizing the dynamic scheduling of maintenance vehicles.

[0018] In a preferred embodiment of this application, the system further includes: The operation mode recognition unit is used to identify the equipment failure patterns and waste accumulation status data of each treatment site based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, and to determine the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities; The model training and optimization unit is used to obtain historical scheduling and maintenance record data of each processing station based on the station identifier, and to perform training and optimization based on minimizing the overall cost in the preset initial scheduling optimization model to obtain an optimized historical vehicle scheduling and maintenance response model. The correlation impact analysis unit is used to calculate the spatial correlation degree and fault propagation impact factor between each processing site, and generate the site correlation impact coefficient of all processing sites. The strategy generation unit is used to determine the minimum maintenance response time and the optimal waste collection frequency for each processing station in different operation and maintenance stages by combining the site correlation influence coefficient in the optimized historical vehicle scheduling and maintenance response model, and to generate historical scheduling and maintenance optimization strategies.

[0019] Thirdly, the objective of this invention is achieved through the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method for maintenance and transport vehicle scheduling of a distributed municipal solid waste treatment site network.

[0020] Fourthly, the objective of this invention is achieved through the following technical solution: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for maintenance and transport vehicle scheduling in a distributed municipal solid waste treatment site network.

[0021] In summary, this application includes at least one of the following beneficial technical effects: 1. By monitoring station status and environmental data in real time and combining it with a multi-dimensional fault diagnosis model, we can quickly locate faulty stations and classify their risks; dynamic route planning based on real-time traffic data can significantly shorten maintenance response time; and through the synergistic optimization of historical scheduling strategies and maintenance optimization models, we can improve vehicle resource utilization and reduce overall scheduling costs. 2. Based on historical dispatch and maintenance record data of station identifiers, the initial dispatch optimization model is trained and optimized based on the minimization of comprehensive costs to obtain an optimized historical vehicle dispatch and maintenance response model, which improves the scientificity and rationality of dispatch decisions. Attached Figure Description

[0022] Figure 1 This is a flowchart of a maintenance and transportation vehicle scheduling method for a decentralized municipal solid waste treatment site network according to one embodiment of this application; Figure 2 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0023] The present application will be further described in detail below with reference to the accompanying drawings.

[0024] In one embodiment, such as Figure 1 As shown, this application discloses a method for maintenance and transportation vehicle scheduling in a decentralized municipal solid waste treatment site network, specifically including the following steps: S1: Monitor the operational status parameters and environmental monitoring data of each municipal solid waste treatment site.

[0025] In this embodiment, the operating parameters include equipment operating temperature, hydraulic system pressure, motor speed, and waste compression chamber pressure. Equipment operating temperature refers to the surface temperature of key components (such as the compressor cylinder, hydraulic pump, and motor housing). Hydraulic system pressure is the pressure value of the oil in the hydraulic drive system of the waste compression chamber piston, etc. Motor speed is the motor speed of the drive equipment (such as the waste compressor and conveyor belt), which is collected by an encoder or frequency converter. Waste compression chamber pressure is the pressure value inside the waste compression chamber, which is collected by a pressure sensor installed on the chamber wall. Environmental monitoring data includes waste storage volume, temperature and humidity inside the chamber, and concentration of harmful gases. Environmental monitoring data refers to the monitoring data inside the waste temporary storage chamber.

[0026] Specifically, data preprocessing is performed on the working status parameters and environmental monitoring data, including the use of sliding window mean filtering (window size 5s) to eliminate sensor noise; The parameters such as temperature, humidity, and pressure are normalized to the [0, 1] range using the Z-score normalization method.

[0027] S2: Based on working status parameters and environmental monitoring data, perform multi-dimensional fault judgment to obtain the fault site judgment result.

[0028] In this embodiment, step S2 includes: S21: Compare the equipment operating temperature, hydraulic system pressure, motor speed, and garbage compression chamber pressure with the corresponding normal operating parameters to determine if there are any abnormal operating parameters.

[0029] In this embodiment, based on the equipment manufacturer's manual or historical operating data statistics for a specified time period, normal operating parameters are set under normal operating conditions. For example, the equipment operating temperature is 40-80℃; the normal operating pressure of the hydraulic system is 15-20MPa; and the pressure of the garbage compression chamber during the normal compression stage is 0.8-1.5MPa, which can be adjusted according to the garbage composition. When the operating parameters exceed the corresponding normal operating parameters, it is determined that there are abnormal operating parameters.

[0030] For example, warning thresholds and fault thresholds can also be set for each parameter. For instance, the normal operating temperature range for the equipment is 40-80℃, the warning threshold is greater than 85℃, and the fault threshold is greater than 95℃; the normal pressure range for the hydraulic system is 15-20MPa, the warning threshold is <12MPa or >25MPa, and the fault threshold is <10MPa or >30MPa; the normal speed range for the motor is 1450±50RPM, the warning threshold is <1350RPM or >1550RPM, and the fault threshold is <1200RPM or >1700RPM; the normal pressure range for the garbage compression chamber is 0.8-1.5MPa, the warning threshold is <0.5MPa or >2.0MPa, and the fault threshold is <0.3MPa or >2.5MPa.

[0031] S22: Calculate the rate of change of waste storage volume and the rate of change of temperature and humidity. Based on the rate of change of waste storage volume, the rate of change of temperature and humidity and the concentration of harmful gases, determine whether there are any abnormal environmental parameters.

[0032] In this embodiment, the concentration of hazardous gases refers to the volume concentration (ppm) of CH4, H2S, and NH3, and the safety thresholds are CH4 < 1% (lower explosive limit 5%), H2S < 50 ppm (occupational exposure limit), and NH3 < 300 ppm (short-term exposure limit).

[0033] Specifically, time series analysis based on the sliding window difference method is used to calculate the rate of change of waste storage volume, temperature and humidity, and harmful gas concentration, reflecting the severity of environmental changes, so as to obtain the rate of change of waste storage volume, the rate of change of temperature and humidity, and the rate of change of harmful gas concentration.

[0034] Based on the rate of change of various environmental monitoring data and the baseline value under normal conditions, rules for judging environmental anomalies are set. For example, the anomaly judgment condition for the rate of change of waste storage volume is >0.2m. 3 / min (normal ≤0.2m) 3 A temperature change rate >5℃ / h (normal ≤3℃ / h) indicates insufficient waste collection frequency or decreased compression efficiency. A humidity change rate >10% / h (normal ≤5% / h) indicates possible high temperature due to waste fermentation or poor equipment heat dissipation. A humidity change rate >10% / h (normal ≤5% / h) indicates possible entry of humid air due to seal failure. A hazardous gas concentration change rate CH4 >0.1% / min (normal ≤0.05% / min) or H2S >2ppm / min (normal ≤1ppm / min) indicates accelerated waste decomposition.

[0035] S23: If there are abnormal operating parameters or abnormal environmental parameters, output the fault site judgment result containing fault warning information.

[0036] Specifically, the fault site assessment results include fault type and risk level. Fault types include direct equipment faults, environment-induced faults, and combined faults. Direct equipment faults are triggered by abnormal operating parameters, such as hydraulic system pressure failures or abnormal motor speeds. Environment-induced faults are triggered by abnormal environmental parameters, such as high temperature causing hydraulic oil deterioration or high humidity causing short circuits. Combined faults refer to the simultaneous presence of both direct equipment faults and environment-induced faults, such as hydraulic pump cavitation and high internal temperature.

[0037] Furthermore, the risk levels are divided into high risk, medium risk, and low risk. High risk (Level 1) refers to a risk event that is a direct equipment failure that may cause a safety accident, such as hydraulic pressure >30MPa which may cause oil pipe rupture. Medium risk (Level 2) refers to a direct equipment failure or environmental abnormality that may affect operating efficiency, such as abnormal motor speed leading to a decrease in compression efficiency. Low risk (Level 3) refers to an environmental abnormality that does not directly affect equipment operation (such as a slightly higher rate of change in waste storage volume).

[0038] S3: If a faulty site is detected, obtain the geographical location information of multiple repair vehicles in the vicinity of the faulty site; use a path planning algorithm to determine the target repair vehicle and the optimal repair route based on the geographical location information and the obtained real-time traffic data.

[0039] In this embodiment, the location, speed and task status of all maintenance vehicles in the vicinity (e.g., within a radius of 10km) are obtained in real time through a GPS terminal. The task status is divided into idle and task execution.

[0040] Specifically, to balance scheduling efficiency (shortest time) and scheduling cost (lowest fuel consumption), the multi-objective genetic algorithm (NSGA-II) is selected as the core algorithm for path planning. The algorithm parameters of the multi-objective genetic algorithm (NSGA-II) are set as follows: The population size is 100 to ensure solution diversity; The number of iterations is set to 200 to balance computational efficiency with solution quality; The crossover probability is 0.8 to promote the transfer of high-quality solutions; The mutation probability is set to 0.1 to avoid premature convergence. The objective function weights are time cost (0.6, prioritizing response efficiency) and fuel cost (0.4, controlling operating costs). The multi-objective genetic algorithm aims to simultaneously minimize both time cost and fuel cost, where time cost T is the estimated travel time (including waiting at red lights and congestion delays) from the current location to the fault station. The calculation formula is: Where n is the number of segments in the path, i is the segment index; di is the length of the segment, in meters per kilometer; vi is the average speed of the segment (in kilometers per hour), which is dynamically adjusted based on congestion at different times and can be customized based on historical congestion data for the same time period; t 等待，i Waiting time is caused by adverse factors such as red lights and traffic control.

[0041] C = Fuel consumption rate × Mileage × Fuel price. The fuel consumption rate varies depending on the vehicle type.

[0042] The non-dominated sorting of the multi-objective genetic algorithm outputs the top 10 preferred maintenance paths in 40 groups classified by the "time-cost" Pareto front.

[0043] Specifically, real-time traffic data is obtained by accessing the map app's API to obtain real-time traffic conditions. The preferred maintenance route includes multiple trajectory points, the coordinates of each trajectory point, and speed limit prompts.

[0044] S4: Obtain information on maintenance vehicles, optimal maintenance routes, and transport vehicles for the entire municipal solid waste treatment site network. Use a planning optimization algorithm combined with historical scheduling and maintenance optimization strategies to determine the priority of maintenance tasks and the scheduling plan for maintenance vehicles.

[0045] In this embodiment, step S4 includes: S41: Obtain the location, task status, and estimated arrival time of maintenance vehicles for the entire municipal solid waste treatment site network; simultaneously collect the geographical coordinates and estimated travel time of each trajectory point of the preferred maintenance route, and integrate the transportation vehicle's driving route, estimated return time, and historical collection efficiency information.

[0046] In this embodiment, the task status includes idle, running, and fault. The estimated arrival time is calculated based on the distance between the current location and the fault site and the average vehicle speed. Tool matching degree refers to the degree of matching between the tool list retrieved from the vehicle archive and the fault type. For example, if maintenance vehicle V1 carries hydraulic seals and a pressure sensor calibrator, then it matches the fault type of hydraulic leakage 100%.

[0047] Specifically, trajectory points are multiple key nodes on the path, including the starting point, turning points, traffic light waiting points, intersections, and the destination. The estimated travel time for each trajectory point is calculated using geographic coordinates combined with real-time traffic data (such as road segment length, average vehicle speed, and intersection waiting time). For example, if it takes 5 minutes to travel from trajectory point A to trajectory point B, the estimated travel time for the entire path is calculated by summing these values. The shorter the total estimated travel time, the higher the response efficiency of the maintenance task, which can serve as a key indicator for task priority. If the estimated arrival times of two maintenance vehicles overlap, the path or task allocation can be adjusted. The transport vehicle's route is the path planning result from the transport vehicle's current location to the waste treatment plant (or other collection destination), including the geographic coordinate sequence of the path and information on the road segments traversed. The estimated return time is the estimated time, in minutes, for the transport vehicle to return from the waste treatment plant to its starting point after completing the collection task. "Historical waste collection efficiency information" refers to the performance data of transport vehicles in waste collection tasks over the past month / quarter, including average daily collection volume, on-time rate, failure rate, and energy efficiency.

[0048] S42: Load historical scheduling and maintenance optimization strategies based on historical scheduling records.

[0049] Specifically, historical dispatch records include fault type distribution, vehicle assignment patterns, and collection priority rules. The fault type distribution shows the distribution of different fault types. The vehicle assignment pattern prioritizes assigning nearby vehicles with matching tools to emergency faults. The collection priority rule prioritizes high-load accumulation sites (referring to waste storage volume > 80% of design capacity) over routine maintenance sites. Historical dispatch and maintenance optimization strategies include maintenance priority rules, vehicle allocation weights, and route avoidance rules. The maintenance priority rule prioritizes emergency faults (risk level 1) > high-load accumulation (level 2) > routine maintenance (level 3). The vehicle allocation weight prioritizes tool matching degree (weight 0.4) > estimated arrival time (0.3) > historical task completion rate (0.3). The route avoidance rule prioritizes alternative routes, such as rural roads, for congested road sections (e.g., main roads during morning rush hour).

[0050] The historical scheduling and maintenance optimization strategies loaded in step S42 will serve as constraints for the "multi-objective optimization model" in step S43 (such as "prioritizing the assignment of tools to match vehicles in case of emergency failures"), ensuring that the model output conforms to historical experience.

[0051] S43: A mixed-integer linear programming algorithm is adopted, with the objectives of minimizing the total scheduling cost and maximizing the scheduling efficiency. A multi-objective optimization model is constructed by combining real-time multi-source data and historical scheduling and maintenance optimization strategies.

[0052] In this embodiment, the objective function of the Mixed Integer Linear Programming (MILP) algorithm is: min Z = 0.6C + 0.4TD, where C is the total scheduling cost, including fuel costs for maintenance vehicles, fuel costs for transport vehicles, and empty-run penalties for transport vehicles. Fuel costs for maintenance and transport vehicles are proportional to the distance traveled. The empty-run penalty cost is 50 yuan per vehicle if no task is assigned. TD is the scheduling efficiency, including task completion time and vehicle utilization rate. Task completion time is the sum of maintenance time and vehicle round-trip time. Vehicle utilization rate is the actual working time of maintenance vehicles / transport vehicles divided by the total available time. 0.6 and 0.4 are weight values, representing the priority of cost and time, respectively, and can be adjusted according to the needs of the site management.

[0053] Specifically, the constraints of the mixed-integer linear programming algorithm include vehicle resource constraints, time constraints, load constraints, and historical strategy constraints. Among them, the vehicle resource constraint is that each maintenance vehicle / transport vehicle can only perform one task at a time; the time constraint is that emergency fault repair tasks must be completed within 2 hours; the load constraint is that the actual load of the transport vehicle is less than or equal to the rated capacity; and the historical strategy constraint is that vehicles with a tool matching degree of ≥80% should be assigned priority in emergency faults.

[0054] Real-time collected data on maintenance vehicles, tool matching, transport vehicles, routes, and fault sites are used as inputs to a multi-objective optimization model. Maintenance vehicle data represents the estimated arrival time of maintenance vehicles at designated fault sites. By calculating task completion times, vehicles are constrained to perform only one task at a time. Transport vehicle data obtains the remaining capacity of transport vehicles to match the amount of waste requiring collection at each site; the remaining capacity must be greater than or equal to the amount of waste at the site. Route data is used to calculate the estimated travel time between maintenance route points, which is then summed to obtain the total arrival time, serving as input for time constraints. Fault site data includes the urgency level weight of the fault site and the amount of waste requiring collection, used to calculate scheduling priority. Scheduling priority affects the efficiency weight in the objective function.

[0055] Specifically, historical scheduling and maintenance optimization strategies are embedded in the multi-objective optimization model through constraints or objective function weights to ensure that the output conforms to empirical rules. For example, the constraints are mandatory priority rules, which include constraints on the allocation of tool-matching vehicles for emergency tasks and the capacity and efficiency of transport vehicles. Specifically, if the emergency level of faulty site j is level 1 (e.g., S1), the condition for allocating a tool-matching vehicle to maintenance vehicle i must be that the tool matching degree is greater than or equal to 85%. The capacity and efficiency constraints for transport vehicles require that transport vehicle k allocated to collection site l must have a remaining capacity greater than or equal to the amount of garbage to be collected, and vehicles with a historical collection efficiency greater than or equal to 90% are preferred.

[0056] S44: Determine the priority of maintenance tasks for each faulty site.

[0057] In this embodiment, if multiple urgent faults exist and maintenance resources are limited, the priority of maintenance tasks is adjusted by comparing the scope of the fault impact and the degree of equipment aging. For example, if faulty site S3 affects 5 downstream sites and faulty site S4 affects 3 downstream sites, then faulty site S3 has a higher priority. Similarly, regarding the degree of equipment aging, if the faulty equipment at faulty site S3 has been used for 8 years (near the end of its lifespan) and the equipment at faulty site S4 has been used for 5 years, then faulty site S3 has a higher priority.

[0058] S45: Calculate the compatibility score between maintenance vehicles and fault stations based on vehicle tool matching degree and estimated arrival time; calculate the compatibility score between transport vehicles and waste collection stations based on remaining capacity of transport vehicles, load utilization rate and historical waste collection efficiency.

[0059] In this embodiment, the vehicle suitability for repair is calculated as follows: Suitability Score = 0.4 × Tool Matching Degree + 0.3 × (1 / Estimated Arrival Time) + 0.3 × Historical Task Completion Rate. The tool matching degree is a weighted calculation of type matching degree, quantity matching degree, and applicability matching degree. The weights of each dimension can be set based on historical experience, such as 0.5, 0.3, and 0.2 respectively.

[0060] The vehicle suitability is calculated as follows: Suitability score = 0.5 × Remaining capacity ratio + 0.3 × Load utilization rate + 0.2 × Historical collection efficiency, where historical collection efficiency is based on historical on-time collection rate.

[0061] S46: Determine the optimal matching plan for maintenance vehicles based on maintenance vehicles and fault stations, and transport vehicles and waste disposal stations through a multi-objective optimization model.

[0062] Specifically, the preferred maintenance route consists of several trajectory points; the decision variables of the multi-objective optimization model include the binary matching relationship between vehicles and stations, with a value of 1 assigned to a match and 0 otherwise. The requirements of the waste collection stations include the amount of waste collected and time constraints. The optimal matching includes a vehicle-station matching plan that, based on constraints conforming to historical strategies and vehicle resource limitations, achieves the lowest total scheduling cost and / or the shortest task completion time and the highest vehicle utilization rate. The maintenance vehicle scheduling plan is the final output of the multi-objective optimization model, providing a specific plan to guide on-site operations, and must include task allocation, vehicle information, route planning, and time nodes.

[0063] In one embodiment, the step of generating historical scheduling and maintenance optimization strategies includes: S10: Based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, identify and obtain the equipment failure occurrence patterns and waste accumulation status data of each treatment site during operation, and determine the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities, and the site identifier associated with the treatment site.

[0064] In this embodiment, the equipment failure occurrence patterns include the time distribution (e.g., high frequency during the morning peak 8:00-10:00), type distribution (e.g., hydraulic leakage, motor failure), and severity of equipment failures (e.g., compressors, hydraulic systems) at each site in the statistical historical data; the waste accumulation status data records the changes in waste storage volume at each site over time and the storage volume threshold (e.g., 85% of the design capacity); the operation and maintenance mode information is based on the failure patterns and waste accumulation status, dividing different maintenance priority stages, such as "preventive maintenance stage," "emergency repair stage," and "routine inspection stage," and associating them with site identifiers.

[0065] Specifically, equipment failure patterns are identified by using time series analysis (such as the ARIMA model) to pinpoint high-incidence periods, and by using association rule mining (such as the Apriori algorithm) to discover the correlation between "hydraulic leakage" and "motor overheating." Waste accumulation status is assessed by calculating the daily growth rate of waste storage at each site (e.g., an average daily increase of 2 tons in summer), combined with design capacity to determine early warning thresholds; and by plotting storage volume-time curves to identify "high-load accumulation intervals."

[0066] In this embodiment, step S10 includes: S101: Based on the historical operation detection dataset, obtain the equipment operation status logs, fault alarm time records and historical garbage storage data of each processing station within the historical monitoring period.

[0067] Specifically, the historical operational monitoring dataset comprises multi-dimensional operational data collected from a distributed waste treatment site network over a certain period (e.g., one year) through sensors, PLC controllers, and manual inspections. This data is used to analyze equipment status and waste accumulation patterns. Equipment operation status logs, exported from the site's PLC controller, include equipment (compressor, hydraulic system, motor) operating time, downtime, and operating parameters (temperature, pressure, speed). Historical waste storage data is collected from ultrasonic level gauges in the waste storage bins, recording the hourly storage volume.

[0068] Furthermore, the historical operation detection dataset is cleaned and time-aligned, and missing values ​​are filled.

[0069] S102: Based on the downtime, fault alarm time record, and historical waste storage data change trend of the equipment operation status log, divide the data into multiple historical monitoring time intervals.

[0070] In this embodiment, the historical monitoring time period is divided into several consecutive time periods (such as "morning peak period" and "nighttime low load period") based on the equipment operating status, failure frequency and waste accumulation trend, for subsequent analysis of maintenance needs in different time periods.

[0071] Specifically, time periods are divided based on equipment downtime, fault alarm frequency, and changes in waste storage volume to identify periods of high equipment downtime, peak fault periods, and periods of high waste accumulation. During periods of high equipment downtime, equipment maintenance needs are also high. During periods of high waste accumulation, waste collection needs to be initiated earlier.

[0072] S103: Based on the site identifier and multiple historical monitoring time intervals, generate equipment health status assessment parameters that include equipment health status intervals and equipment failure occurrence patterns, and waste accumulation status parameters that include waste accumulation level intervals.

[0073] In this embodiment, equipment health status assessment parameters are indicators used to quantify the current health level of the equipment, such as the "Equipment Health Index (EHI)," calculated by the degree of deviation of equipment operating parameters (temperature, pressure) from historical normal ranges. Waste accumulation status parameters are indicators used to quantify the risk of waste accumulation, such as the "waste accumulation level," which is classified according to the ratio of storage capacity to design capacity.

[0074] Specifically, the calculation of Equipment Health Assessment (EHI) parameters includes: first, data standardization, converting equipment operating parameters (temperature, pressure) into dimensionless values ​​(Z-score), using the formula: Where X is the current parameter value, μ is the historical mean, and σ is the historical standard deviation. The EHI is obtained by combining the Z-scores of all parameters and performing a weighted summation. The weights are set according to the importance of the parameters; for example, EHI = 0.6 × Z_temperature + 0.4 × Z_pressure. At a certain moment, the temperature of compressor S1 is 90℃ (historical mean 80℃, standard deviation 5℃), Z_temperature = (90-80) / 5 = 2; the pressure is 18MPa (historical mean 15MPa, standard deviation 2MPa), Z_pressure = (18-15) / 2 = 1.5; then EHI = 0.6 × 2 + 0.4 × 1.5 = 1.8 (normal range 0-2, >2 is abnormal). The waste accumulation status parameters include a classification based on waste accumulation levels. The classification rules are as follows: Level 1 (Low Risk): Ratio ≤ 50%; Level 2 (Medium Risk): 50% < Ratio ≤ 80%; Level 3 (High Risk): 80% < Ratio ≤ 100%; Level 4 (Urgent): Ratio > 100% (exceeding design capacity). The storage ratio is calculated as: Current storage volume ÷ Design capacity × 100%.

[0075] S104: Based on the equipment health status assessment parameters and waste accumulation status parameters, and in conjunction with the preset maintenance mode determination rules, determine the operation and maintenance mode information of each processing station.

[0076] In this embodiment, the preset maintenance mode determination rules include: Emergency Maintenance (Level 1), triggered by EHI > 2 (equipment abnormal) and accumulation level ≥ 3 (high risk of waste); High Priority Maintenance (Level 2), triggered by EHI > 1.5 (equipment sub-health) and accumulation level ≥ 2 (medium risk of waste); Routine Maintenance (Level 3), triggered by EHI ≤ 1.5 (equipment healthy) and accumulation level ≤ 1 (low risk of waste); and Preventive Maintenance (Level 4), triggered by no fault alarm and accumulation level ≤ 1 (low risk of waste). Operation and maintenance mode information is generated by combining time intervals and parameters. For example, if equipment S1 has an EHI of 2.24 (abnormal) and a waste accumulation level of 3 (high risk) during the "10:00-12:00" period, then "Emergency Maintenance (Level 1)" is triggered.

[0077] Furthermore, if "emergency maintenance" is frequently triggered during a certain period (e.g., 3 times per week), the triggering conditions can be adjusted (e.g., the EHI threshold can be adjusted from 2 to 1.8) to reduce the false alarm rate.

[0078] S20: Obtain historical scheduling and maintenance record data of each processing station based on the station identifier, and perform training optimization based on minimizing comprehensive cost in the preset initial scheduling optimization model to obtain an optimized historical vehicle scheduling and maintenance response model.

[0079] In this embodiment, the initial scheduling optimization model is a machine learning model (such as XGBoost) built based on historical data. The inputs are "fault type, station location, and vehicle availability time", and the outputs are "maintenance vehicle allocation plan and completion time". The objective function for minimizing the overall cost is to minimize the total cost (fuel cost + labor cost + empty run penalty), and the weights are set according to the station management's requirements.

[0080] Specifically, fault characteristics, site characteristics, and vehicle characteristics are obtained from historical scheduling and maintenance records. The initial scheduling optimization model adopts the XGBoost algorithm, based on a loss function defined as the negative of the overall cost (minimizing the cost is equivalent to maximizing the negative value of the loss function). During the hyperparameter optimization process in the training phase, the learning rate is determined to be 0.1, the tree depth to be 5, and the regularization coefficient to be 0.5. The mean absolute error (MAE) of the test set is 12 minutes (the error in predicting maintenance completion time). R... 2 =0.89 (good fit).

[0081] S30: Calculate and determine the spatial correlation degree and fault propagation impact factor between each processing station, and obtain the station correlation impact coefficient of all processing stations.

[0082] In this embodiment, spatial correlation is used to measure the geographical proximity or resource sharing between stations (e.g., stations S1 and S2 share a garbage transportation road, so their spatial correlation is high); the fault propagation impact factor is the probability of a fault at one station affecting other stations (e.g., a hydraulic leak at station S1 causing garbage accumulation may trigger a motor overload fault at station S2, so the impact factor is 0.3); and the station correlation impact coefficient is the weighted value of the combined spatial correlation and fault propagation impact factor (e.g., the correlation coefficient between S1 and S2 = 0.6 × spatial correlation + 0.4 × fault propagation factor).

[0083] Specifically, spatial connectivity is calculated based on geographical proximity and resource sharing. Geographical proximity is calculated using the Euclidean distance formula to determine the straight-line distance between stations, while resource sharing is obtained by counting the number of shared transportation routes between stations. For example, stations S1 and S2 share the G104 main road, so their resource sharing degree is 0.8. The spatial connectivity score is obtained through dimensionality reduction using Principal Component Analysis (PCA).

[0084] The calculation of the fault propagation factor requires first using a Bayesian network model to learn the fault propagation paths between sites based on historical fault data, obtaining causal relationships, such as the probability that "hydraulic leakage at S1 leads to waste accumulation, which will cause motor overload at site S2" is 0.3. Then, Monte Carlo simulation is used to calculate the probability that a fault at one site will cause faults at other sites (e.g., the probability that a fault at S1 will cause a fault at S2 is 0.3, and the probability that it will cause a fault at S3 is 0.1). This quantifies the impact factor of fault propagation.

[0085] After weighting the spatial correlation degree and the fault propagation impact factor, a weighted calculation is performed to obtain the site correlation impact coefficient. For example, the weight of spatial correlation degree is 0.6 and the weight of fault propagation impact factor is 0.4.

[0086] S40: In the optimized historical vehicle scheduling and maintenance response model, the minimum maintenance response time and the optimal waste collection frequency of each processing station are determined by combining the site correlation influence coefficients of all processing stations in different operation and maintenance phases, and a historical scheduling and maintenance optimization strategy is generated.

[0087] In this embodiment, the minimum maintenance response time is the shortest arrival time of maintenance vehicles at adjacent stations when a station fails, taking into account the impact of station correlation. The optimal garbage collection frequency is determined by combining the garbage accumulation status and correlation effects to find the optimal collection frequency for a given station. For example, if S1 has a high correlation with S2, the collection frequency needs to be increased from once a day to twice a day to avoid cascading failures.

[0088] Specifically, the optimized historical vehicle scheduling and maintenance response model is a machine learning model trained on historical operational data, used to predict the scheduling scheme and response time of maintenance vehicles. Its core is to learn the mapping relationship between "fault type - site location - vehicle availability" through historical data, and output the "optimal maintenance vehicle allocation" and "estimated arrival time".

[0089] In this embodiment, the minimum maintenance response time is the shortest arrival time of maintenance vehicles at adjacent or associated stations when a station fails, after considering the associated effects of station failures. This includes the basic response time and the associated adjustment time. The basic response time is the estimated arrival time of the maintenance vehicle without associated effects (e.g., the basic time for V1 to maintain S1 is 15 minutes). The associated adjustment time is the time shortened by the station association coefficient (e.g., the association coefficient between S1 and S2 = 0.54, and the idle vehicle V2 of S2 is only 5km from S1, the adjusted response time = 15 minutes - 0.54 × 5 minutes = 12.3 minutes). For example, when station S1 fails, the basic response time (V1) = 15 minutes; considering the associated effects of S2 (C = 0.54), scheduling V2 of S2 (5km from S1) results in an adjusted response time of 15 - 0.54 × 5 = 12.3 minutes (the actual arrival time of V2 is 12 minutes).

[0090] The optimal garbage collection frequency is determined based on the garbage accumulation status, site maintenance stage, and related impacts. It represents the optimal garbage collection frequency (e.g., once or twice daily) for a given site during different operation and maintenance stages. This includes the garbage accumulation threshold, stage-related adjustments, and related impact corrections. The garbage accumulation threshold is the collection trigger point based on the design capacity. The stage-related adjustments refer to the differences in collection frequency during different maintenance stages (e.g., emergency repairs, high-load accumulation). For example, during emergency repairs, collection is required within 2 hours, while during high-load stages, collection is required twice daily. The related impact corrections refer to the adjustment of the current site's collection frequency based on the garbage accumulation status of related sites. For example, high accumulation in S1 may cause congestion at the S2 entrance, requiring the collection frequency of S1 to be increased from once / day to twice / day.

[0091] The historical scheduling and maintenance optimization strategy integrates the "minimum maintenance response time" and the "optimal waste collection frequency," combined with maintenance phase intervals (such as emergency repairs and high-load collection), to generate specific rules guiding on-site operations. Its core is to use quantifiable parameters to clearly define "when to dispatch which vehicle and at what frequency" for collection, ensuring efficient resource utilization. The historical scheduling and maintenance optimization strategy includes maintenance phase rules, a vehicle allocation table, and a time node table.

[0092] The maintenance phase rules include: Emergency Repair (Level 1): Triggering conditions (e.g., equipment malfunction + high-risk waste), response time ≤ 30 minutes, priority dispatching of idle vehicles from related sites; High-load Cleanup (Level 2): ​​Triggering conditions (e.g., when the capacity is 10 tons, the storage volume is > 8 tons), cleanup frequency ≥ 2 times / day, dispatching vehicles with a load capacity ≥ 5 tons; Routine Maintenance (Level 3): Triggering conditions (e.g., equipment sub-health + low-risk waste), response time ≤ 2 hours, dispatching vehicles with a matching degree of ≥ 80%. The vehicle allocation table clearly defines the maintenance / cleanup vehicles for each site at different stages, and the time node table includes the start / completion time of maintenance and the start / completion time of cleanup.

[0093] In another embodiment, the site association impact coefficient is calculated based on geographical proximity, traffic connectivity, and fault propagation correlation; step S30 includes: S301: Obtain the geographical distance between each processing station, road travel time, shared equipment component information, and historical cascading fault records.

[0094] In this embodiment, the geographical distance between processing stations can be obtained from the latitude and longitude coordinates of each station in the city's GIS system, and the straight-line geographical distance between any two stations can be calculated. Traffic data is obtained from the real-time road traffic time obtained from the traffic management platform. Shared equipment component information is obtained from the equipment management system for the shared equipment components of each station. Historical cascading fault records are extracted from the fault database for cascading fault cases from the past 3 years.

[0095] Specifically, the correlation coefficient is obtained by weighting and integrating the three factors: geographical proximity (reflecting the "physical correlation" of spatial distance), traffic connectivity (reflecting the "traffic correlation" of road efficiency), and fault propagation correlation (reflecting the "logical correlation" of fault propagation). Traffic connectivity represents the traffic efficiency of roads between stations. Fault propagation correlation represents the probability that a fault at one station will trigger a fault at other stations in historical cascading fault records; it is related to shared equipment and maintenance coordination. Traffic connectivity data is obtained from the traffic congestion index platform by acquiring the "congestion index" of roads between stations (e.g., S1-S2 morning peak congestion index = 1.8, evening peak congestion index = 2.2, daily average congestion index = 2.0).

[0096] S302: Traverse and calculate the geographical distance and road travel time between two adjacent processing stations to calculate the spatial proximity coefficient, and obtain the spatial correlation based on the spatial proximity coefficient; calculate the fault propagation impact factor based on the shared equipment component information and historical cascading fault records.

[0097] In this embodiment, the spatial proximity coefficient reflects the combined influence of geographical distance and transportation convenience between stations (value range [0, 1], the larger the value, the closer they are).

[0098] For example, processing the spatial proximity coefficients of sites i and j The weighting is 0.4 for geographical distance and 0.6 for traffic congestion, highlighting the impact of traffic efficiency on proximity.

[0099] Specifically, spatial correlation is a normalized result of spatial proximity, used for horizontal comparison of the proximity between stations (value range [0, 1]), and for all station pairs, D... ij Perform min-max normalization, the calculation formula is as follows: To obtain the spatial correlation R between processing sites i and j ij .

[0100] The fault propagation impact factor reflects the probability that a fault at one site will cause a fault at other sites (the value ranges from [0, 1], and the larger the value, the higher the risk of propagation).

[0101] For example, the failure propagation impact factor F is processed at sites i and j. ij The calculation formula is:

[0102] S303: Combining spatial correlation degree and fault propagation influence factor, construct the correlation influence weight matrix between processing sites, and obtain the site correlation influence coefficient of all processing sites after normalization.

[0103] In this embodiment, the correlation influence weight matrix is ​​composed of the spatial correlation degree R. ijand the failure propagation impact factor F ij It is composed of weighted combinations, with the weights adjusted according to business needs. The correlation influence weight matrix unifies the weight coefficients to the range of [0, 1] using min-max normalization.

[0104] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0105] In one embodiment, a maintenance and transportation vehicle scheduling system for a decentralized municipal solid waste treatment site network is provided, which corresponds to the maintenance and transportation vehicle scheduling method for a decentralized municipal solid waste treatment site network described in the above embodiment.

[0106] The maintenance and transportation vehicle dispatching system for a decentralized municipal solid waste treatment site network includes a status monitoring module, a fault diagnosis module, a vehicle positioning and route planning module, and a dispatch optimization module. Detailed descriptions of each functional module are as follows: The status monitoring module is used to monitor the working status parameters and environmental monitoring data of each municipal solid waste treatment site; The fault diagnosis module is used to perform multi-dimensional fault diagnosis based on working status parameters and environmental monitoring data, and output the fault site diagnosis results. The vehicle positioning and route planning module is used to obtain the geographical location information of multiple repair vehicles in the vicinity when a fault site is detected, and combine it with real-time traffic data to determine the target repair vehicle and the optimal repair route to the fault site using a route planning algorithm. The scheduling optimization module is used to obtain information on maintenance vehicles, optimal maintenance routes, and transport vehicles in the entire network of municipal solid waste treatment sites. It uses a planning optimization algorithm combined with a preset historical vehicle scheduling and maintenance response model to determine the priority of maintenance tasks and the scheduling plan of maintenance vehicles, thereby realizing the dynamic scheduling of maintenance vehicles.

[0107] Optionally, the system may also include: The operation mode recognition unit is used to identify the equipment failure patterns and waste accumulation status data of each treatment site based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, and to determine the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities; The model training and optimization unit is used to obtain historical scheduling and maintenance record data of each processing station based on the station identifier, and to perform training and optimization based on minimizing the overall cost in the preset initial scheduling optimization model to obtain an optimized historical vehicle scheduling and maintenance response model. The correlation impact analysis unit is used to calculate the spatial correlation degree and fault propagation impact factor between each processing site, and generate the site correlation impact coefficient of all processing sites. The strategy generation unit is used to determine the minimum maintenance response time and the optimal waste collection frequency for each processing station in different operation and maintenance stages by combining the site correlation influence coefficient in the optimized historical vehicle scheduling and maintenance response model, and to generate historical scheduling and maintenance optimization strategies.

[0108] Specific limitations regarding the maintenance and transportation vehicle dispatching system for decentralized municipal solid waste treatment site networks can be found in the limitations regarding the maintenance and transportation vehicle dispatching methods for decentralized municipal solid waste treatment site networks mentioned above, and will not be repeated here. Each module in the aforementioned maintenance and transportation vehicle dispatching system for decentralized municipal solid waste treatment site networks can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in a computer device in hardware form, or it can be stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0109] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 2 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores operating status parameters, environmental monitoring data, etc. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for maintenance and transportation vehicle scheduling in a distributed municipal solid waste treatment site network.

[0110] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement steps such as a maintenance and transport vehicle scheduling method for a distributed municipal solid waste treatment site network.

[0111] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements steps of a maintenance and transport vehicle scheduling method, such as that for a distributed municipal solid waste treatment site network.

[0112] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0113] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0114] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network, characterized in that, include: Monitor the operational status parameters and environmental monitoring data of each municipal solid waste treatment site; Based on the working status parameters and the environmental monitoring data, a multi-dimensional fault judgment is performed to obtain the fault site judgment result; If a faulty site is detected, the geographical location information of multiple repair vehicles in the vicinity of the faulty site is obtained; A path planning algorithm is used to determine the target vehicle for repair and the optimal repair route based on the geographical location information and the acquired real-time traffic data; Information on maintenance vehicles, optimal maintenance routes, and transport vehicles for the entire municipal solid waste treatment site network is obtained. A planning optimization algorithm combined with historical scheduling and maintenance optimization strategies is used to determine the priority of maintenance tasks and the scheduling plan for maintenance vehicles.

2. The method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network according to claim 1, characterized in that, The steps for generating the historical scheduling and maintenance optimization strategy include: Based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, the system identifies and acquires the equipment failure patterns and waste accumulation status data of each treatment site during operation, and determines the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities, and the treatment site is associated with a site identifier; Based on the site identifier, historical scheduling and maintenance record data of each processing site are obtained. The optimized historical vehicle scheduling and maintenance response model is obtained by training and optimizing the model based on minimizing the overall cost in the preset initial scheduling optimization model. The spatial correlation degree and fault propagation impact factor between each processing site are calculated and determined to obtain the site correlation impact coefficient of all processing sites. In the optimized historical vehicle scheduling and maintenance response model, the minimum maintenance response time and the optimal waste collection frequency of each processing station are determined by combining the site correlation influence coefficients of all processing stations in different operation and maintenance phases, and historical scheduling and maintenance optimization strategies are generated.

3. The method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network according to claim 2, characterized in that, Based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, the system identifies and acquires data on equipment failure patterns and waste accumulation status during the operation of each treatment site, and determines the operation and maintenance mode information of each treatment site, specifically including: Based on historical operation monitoring datasets, obtain equipment operation status logs, fault alarm time records, and historical waste storage data for each processing station within the historical monitoring period; Based on the downtime, fault alarm time record, and historical waste storage volume data change trend of the equipment operation status log, multiple historical monitoring time intervals are divided. Based on the site identifier and multiple historical monitoring time intervals, generate equipment health status assessment parameters that include equipment health status intervals and equipment failure occurrence patterns, and waste accumulation status parameters that include waste accumulation level intervals. Based on the equipment health status assessment parameters and waste accumulation status parameters, and in conjunction with the preset maintenance mode determination rules, the operation and maintenance mode information of each processing station is determined.

4. The method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network according to claim 2, characterized in that, The calculation of the site association impact coefficient is based on geographical proximity, traffic connectivity, and fault propagation correlation. The spatial correlation and fault propagation impact factors among each processing site are calculated and determined to obtain the site correlation impact coefficients for all processing sites, including: Obtain the geographical distance between each processing station, road travel time, shared equipment component information, and historical cascading failure records; The spatial proximity coefficient is calculated by iterating through and calculating the geographical distance and road travel time between two adjacent processing stations, and the spatial correlation is obtained based on the spatial proximity coefficient; the fault propagation impact factor is calculated based on the shared equipment component information and historical cascading fault records. Combining the spatial correlation degree and the fault propagation influence factor, a correlation influence weight matrix between processing sites is constructed, and after normalization, the site correlation influence coefficient of all processing sites is obtained.

5. The method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network according to claim 1, characterized in that, The preferred maintenance path consists of several trajectory points; the process of obtaining information on maintenance vehicles, preferred maintenance paths, and transport vehicles from the entire municipal solid waste treatment site network, and using a planning optimization algorithm combined with historical scheduling and maintenance optimization strategies to determine maintenance task priorities and maintenance vehicle scheduling plans, specifically includes: The system acquires the location, task status, and estimated arrival time of maintenance vehicles across the entire municipal solid waste treatment network; it also simultaneously collects the geographic coordinates and estimated travel time of each trajectory point along the preferred maintenance route, and integrates the vehicle's driving route, estimated return time, and historical waste collection efficiency information. Load historical scheduling and maintenance optimization strategies based on historical scheduling records; A mixed-integer linear programming algorithm is adopted to minimize the total scheduling cost and maximize the scheduling efficiency. A multi-objective optimization model is constructed by combining real-time multi-source data and historical scheduling and maintenance optimization strategies. Determine the priority of maintenance tasks for each faulty site; The matching score between maintenance vehicles and fault stations is calculated based on vehicle tool matching degree and estimated arrival time; the matching score between transport vehicles and collection stations is calculated based on remaining capacity, load utilization rate and historical collection efficiency of transport vehicles. A multi-objective optimization model is used to determine the optimal matching of maintenance vehicles with fault stations and transport vehicles with waste disposal stations.

6. The method for maintenance and transportation vehicle scheduling of a decentralized municipal solid waste treatment site network according to claim 1, characterized in that, The multi-dimensional fault judgment based on the operating status parameters and the environmental monitoring data, to obtain the fault site judgment result, includes: The operating parameters include equipment operating temperature, hydraulic system pressure, motor speed, and waste compression chamber pressure; the environmental monitoring data include waste storage volume, internal temperature and humidity, and concentration of harmful gases. The operating temperature of the equipment, the pressure of the hydraulic system, the speed of the motor, and the pressure of the garbage compression chamber are compared with the corresponding normal operating parameters to determine whether there are any abnormal operating parameters. Calculate the rate of change of waste storage volume and the rate of change of temperature and humidity. Based on the rate of change of waste storage volume, the rate of change of temperature and humidity and the concentration of harmful gases, determine whether there are any abnormal environmental parameters. If there are abnormal operating parameters or abnormal environmental parameters, the fault site judgment result containing fault warning information will be output.

7. A maintenance and transportation vehicle dispatching system for a decentralized municipal solid waste treatment site network, characterized in that, The system includes: The status monitoring module is used to monitor the working status parameters and environmental monitoring data of each municipal solid waste treatment site; The fault diagnosis module is used to perform multi-dimensional fault diagnosis based on the working status parameters and the environmental monitoring data, and output the fault site diagnosis result. The vehicle positioning and route planning module is used to obtain the geographical location information of multiple repair vehicles in the vicinity when a fault site is detected, and combine it with real-time traffic data to determine the target repair vehicle and the preferred repair route to the fault site using a route planning algorithm. The scheduling optimization module is used to obtain information on maintenance vehicles, optimal maintenance routes, and transport vehicles in the entire network of municipal solid waste treatment sites. It uses a planning optimization algorithm combined with pre-stored historical scheduling and maintenance optimization strategies to determine the priority of maintenance tasks and the scheduling plan for maintenance vehicles, thereby realizing the dynamic scheduling of maintenance vehicles.

8. The maintenance and transportation vehicle dispatching system for a decentralized municipal solid waste treatment site network according to claim 7, characterized in that, The system also includes: The operation mode recognition unit is used to identify the equipment failure patterns and waste accumulation status data of each treatment site based on the historical operation monitoring dataset of the decentralized municipal solid waste treatment site network, and to determine the operation and maintenance mode information of each treatment site; the operation and maintenance mode information includes multiple operation and maintenance stage intervals corresponding to different maintenance priorities; The model training and optimization unit is used to obtain historical scheduling and maintenance record data of each processing station based on the station identifier, and to perform training and optimization based on minimizing the overall cost in the preset initial scheduling optimization model to obtain an optimized historical vehicle scheduling and maintenance response model. The correlation impact analysis unit is used to calculate the spatial correlation degree and fault propagation impact factor between each processing site, and generate the site correlation impact coefficient of all processing sites. The strategy generation unit is used to determine the minimum maintenance response time and the optimal waste collection frequency for each processing station in different operation and maintenance stages by combining the site correlation influence coefficient in the optimized historical vehicle scheduling and maintenance response model, and to generate historical scheduling and maintenance optimization strategies.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the maintenance and transport vehicle scheduling method for a decentralized municipal solid waste treatment site network as described in any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the maintenance and transport vehicle scheduling method for a decentralized municipal solid waste treatment site network as described in any one of claims 1 to 6.

Images