A method and system for operation and maintenance scheduling of water supply facilities in mountainous rural areas based on water quality risk classification

Abstract

The present application relates to the field of mountainous rural water supply facilities operation and maintenance scheduling, and particularly relates to a mountainous rural water supply facilities operation and maintenance scheduling method and system based on water quality risk classification. The method comprises collecting water supply facility basic data and operation data; constructing a facility risk classification model according to the collected data, calculating the risk index of each water supply facility; constructing a passing cost matrix between facilities in mountainous and hilly areas; according to the facility risk level, maintenance cycle, alarm state and task time limit, screening and generating a current to-be-executed operation and maintenance task set, establishing a risk-time coupling scheduling optimization model and solving; finally outputting the current inspection sequence, scheduling path and estimated completion time. The present application is suitable for mountainous rural water supply facility operation and maintenance scheduling.

Description

Technical Field

[0001] This invention relates to the field of operation and maintenance scheduling of water supply facilities in mountainous rural areas, and specifically to a method and system for operation and maintenance scheduling of water supply facilities in mountainous rural areas based on water quality risk classification. Background Technology

[0002] Rural water supply facilities in mountainous and hilly areas are characterized by their numerous and widespread distribution, scattered locations, complex road conditions, limited operation and maintenance resources, significant differences in the impact of different facilities on water supply security, and frequent occurrence of abnormal events. Existing technologies typically have the following drawbacks:

[0003] The current inspection and maintenance of rural water supply facilities mainly relies on fixed-cycle inspections or manual experience, making it difficult to implement differentiated priority maintenance based on the degree of impact of facilities on water supply security. As a result, high-risk facilities cannot be identified and dealt with in a priority manner.

[0004] Existing general route planning or equipment inspection and scheduling methods are mostly aimed at the shortest distance, shortest time, or lowest travel cost, without taking into account specific factors such as water quality risks, the degree of exposure of the service population, and the criticality of water supply in rural water supply scenarios. Therefore, it is difficult to balance water supply security and operation and maintenance efficiency.

[0005] Existing scheduling methods typically solve paths based on planar traffic networks, failing to fully consider practical constraints such as low road grade, steep slopes, and significant seasonal changes in road capacity in mountainous and hilly areas, resulting in planning results that do not match real-world operation and maintenance scenarios.

[0006] Existing static inspection schemes lack a dynamic replanning mechanism based on risk-benefit and scheduling costs when faced with new alarms, road blockages, sudden facility anomalies, or task execution deviations during implementation, thus failing to achieve efficient response to abnormal operating conditions.

[0007] In summary, existing technologies lack an integrated rural water supply operation and maintenance scheduling technology solution that can simultaneously achieve facility risk classification, mountain access cost modeling, task generation, path optimization, and dynamic replanning. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification, thereby realizing intelligent scheduling of rural water supply facilities and improving the operation and maintenance efficiency of rural water supply facilities.

[0009] The present invention achieves the above objectives by adopting the following technical solution: Firstly, the present invention provides a method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification, comprising the following steps:

[0010] S1. Collect basic and operational data of water supply facilities;

[0011] S2. Construct a facility risk classification model based on the collected data and calculate the risk index of each water supply facility;

[0012] The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply critical risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index.

[0013] The facilities are classified into risk levels based on the range of the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization.

[0014] S3. Construct a cost matrix for access between facilities in mountainous and hilly areas;

[0015] Based on the geographical relationships between facilities, road grade, slope conditions, seasonal traffic capacity, travel time and accessibility status, a traffic cost model between facilities in mountainous and hilly areas is established, and a traffic cost matrix is ​​generated. The traffic cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas.

[0016] After calculating the passage cost between all facilities, a passage cost matrix is ​​generated as the basic input for scheduling optimization.

[0017] S4. Generate a set of operation and maintenance tasks to be executed;

[0018] Based on facility risk level, maintenance cycle, alarm status and task timeliness requirements, a set of current maintenance tasks to be executed is selected and generated. Each task in the task set includes at least the task object, task priority, task type, estimated operation time and latest completion time.

[0019] S5. Establish and solve the risk-time coupled scheduling optimization model;

[0020] Using the total passage cost, high-risk facility waiting penalty, and task timeliness breach penalty as the joint optimization objective function, the set of maintenance tasks to be executed is optimized in sequence and path to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path, and estimated completion time.

[0021] S6. Output the current inspection sequence, scheduling path, and estimated completion time.

[0022] Furthermore, in step S1, the collection of basic and operational data of the water supply facilities specifically includes:

[0023] Acquire basic information on water supply facilities, equipment operation status information, maintenance records, water quality monitoring information, service population information, and road network information. The basic information includes at least facility number, facility location, facility type, and service area. The operation data includes at least fault records, maintenance cycles, alarm status, and water quality monitoring results. The road network information includes at least the distance between facilities, road grade, slope, seasonal traffic conditions, and accessibility status.

[0024] Furthermore, in step S2, calculating the risk index of each water supply facility specifically includes:

[0025] For water supply facility i, the following risk indicators are established:

[0026] Equipment Abnormal Risk Indicators :

[0027] The number of failures, downtimes, critical component anomalies, or alarm frequencies within the facility's preset time window is determined.

[0028]

[0029] in, This represents the normalized value of the number of failures. This represents the normalized value of the number of downtimes. This represents the normalized value of a critical anomaly event. , , These are the weighting coefficients, and =1;

[0030] Water quality anomaly risk indicators :

[0031] The determination is based on the degree of deviation between the monitoring results of the process effluent, treated water, or tap water quality of the corresponding facility and the preset water quality threshold.

[0032] =

[0033] in, This indicates the degree of normalized anomaly of the nth water quality indicator. For the corresponding weights;

[0034] The exposure risk indicator for the service population is determined based on the number of the population served by the facility, the number of villages or groups served, or the scale of affected users.

[0035] The maintenance overdue risk indicator is determined based on the difference between the cumulative operating time and cumulative operating days since the last maintenance and the preset maintenance cycle.

[0036] Key risk indicators for water supply are determined based on the importance of the facility in the water supply system. This importance is at least related to whether it is a main water supply node, whether there are alternative water supply routes, whether it serves high-risk areas at the end of the supply chain, and whether it affects the water supply of multiple villages and groups.

[0037] The risk assessment module performs dimensionless processing on each indicator and calculates the comprehensive risk index for facility i. The comprehensive risk index is expressed as:

[0038] ;

[0039] in, , , , , This is the risk weighting coefficient.

[0040] Furthermore, in step S3, the inter-facility toll cost model is established based on the geographical relationship between facilities, road grade, slope conditions, seasonal traffic capacity, travel time, and accessibility status. This specifically includes:

[0041] For any two facilities i and j, first obtain the basic distance between facility i and facility j. Road grade factors Slope factor Seasonal travel factors Accessibility factors and driving time factor ;

[0042] The road grade factor is used to characterize the differences in traffic efficiency among different roads, such as expressways, national highways, provincial highways, county roads, township roads, and village roads; the gradient factor is used to characterize the additional travel costs caused by mountainous undulations, curves, and climbs; the seasonal travel factor is used to characterize the impact of rainy seasons, freezing, or landslides; the accessibility factor is used to characterize whether a road is closed or temporarily inaccessible; and the travel time factor is used to characterize the travel time under actual traffic conditions.

[0043] Comprehensive transit cost from facility i to facility j Represented as:

[0044] ;

[0045] in, The adjustment coefficient is n∈[1,5].

[0046] Furthermore, step S5, which involves optimizing the order and solving the path for the set of maintenance tasks to be executed, specifically includes:

[0047] The initial access sequence is generated based on the facility risk level, task timeliness, and current location.

[0048] Constraint loading: The upper limit of the working hours of operation and maintenance personnel, the task time window constraint, the unreachable node constraint, the unique access constraint of the task, and the necessary continuity constraints are loaded into the optimization model.

[0049] Candidate path iterative optimization employs heuristic optimization algorithms, swarm intelligence optimization algorithms, integer programming methods, or combinations thereof, to iteratively adjust the initial access sequence;

[0050] The optimal or near-optimal path is output. After the iteration, the access order with the smallest joint objective function value is selected as the current optimal or near-optimal scheduling scheme, and the estimated arrival time, estimated job completion time and total scheduling cost of each task node are calculated.

[0051] Furthermore, the method also includes:

[0052] S7, Dynamic Replanning;

[0053] During the execution of the current scheduling scheme, dynamic replanning is performed based on the received feedback information, which includes new abnormal events in facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status.

[0054] The newly added abnormal events are evaluated, and the marginal risk reduction benefit brought about by including the task corresponding to the abnormal event in the current scheduling process is calculated, as well as the resulting increase in scheduling costs. The increase in scheduling costs includes one or more of the following: additional detour costs, time delay costs, and task order adjustment costs.

[0055] Based on the relationship between the marginal risk reduction benefit and the increase in scheduling cost, it is determined whether dynamic replanning needs to be triggered. If the risk reduction benefit brought by the new abnormal event reaches a preset threshold, or if the relationship between the risk reduction benefit and the increase in cost meets a preset criterion, dynamic replanning is triggered, the task set or path is updated and the solution is recalculated; otherwise, the current scheduling scheme is maintained and continues to be executed.

[0056] Secondly, the present invention provides an operation and maintenance scheduling system for rural water supply facilities in mountainous areas based on water quality risk classification, comprising:

[0057] The data acquisition module is used to collect basic and operational data of water supply facilities;

[0058] The risk assessment module is used to build a facility risk classification model based on the collected data and calculate the risk index of each water supply facility.

[0059] The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply critical risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index.

[0060] The facilities are classified into risk levels based on the range of the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization.

[0061] The mountainous terrain access cost modeling module is used to establish an access cost model between facilities based on the geographical relationship between facilities, road grade, slope conditions, seasonal access capacity, travel time and accessibility status, and generate an access cost matrix. The access cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas.

[0062] After calculating the passage cost between all pairs of facilities, a passage cost matrix is ​​generated, which serves as the basic input for the scheduling optimization module.

[0063] The task generation module is used to filter and generate a set of maintenance tasks to be executed based on facility risk level, maintenance cycle, alarm status and task timeliness requirements. Each task in the task set includes at least a task object, task priority, task type, estimated operation time and latest completion time.

[0064] The scheduling optimization module is used to perform sequence optimization and path solving on the set of maintenance tasks to be executed, with the total passage cost, high-risk facility waiting penalty and task timeliness breach penalty as joint optimization objective functions, to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path and expected completion time.

[0065] The result output and execution feedback module is used to output the scheduling plan to the operation and maintenance management platform, map interface or mobile inspection terminal for operation and maintenance personnel to execute, and to receive feedback information in real time. The feedback information includes new abnormal events of facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status.

[0066] The dynamic replanning module is used to perform dynamic replanning based on received feedback information during the execution of the current scheduling scheme.

[0067] The beneficial effects of this invention are as follows:

[0068] Compared with fixed-cycle manual inspection, this invention can implement differentiated priority maintenance based on the risk level of the facilities, instead of applying equal effort to all facilities, thus more effectively ensuring water supply security.

[0069] Compared with general path optimization schemes, this invention does not simply pursue the shortest distance, but incorporates water supply security risks, service population exposure, and mountain traffic characteristics into the scheduling decision, making it more suitable for actual rural water supply operation and maintenance scenarios.

[0070] Compared with general equipment risk maintenance solutions, this invention adds special factors such as abnormal water quality, critical water supply and mountainous access constraints, and introduces a dynamic replanning mechanism to form a complete integrated water supply operation and maintenance scheduling solution.

[0071] In summary, this invention improves the response priority of high-risk facilities and the actual feasibility of inspection routes, reduces the cost of ineffective driving and repeated inspections, enhances the ability to handle dynamic abnormal events, and improves the safety and economy of rural water supply system operation. Attached Figure Description

[0072] Figure 1 This is a flowchart of an operation and maintenance scheduling method for rural water supply facilities in mountainous areas based on water quality risk classification, provided by an embodiment of the present invention. Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings.

[0074] This invention provides a method for operation and maintenance scheduling of water supply facilities in mountainous rural areas based on water quality risk classification, such as... Figure 1 As shown, it specifically includes:

[0075] S1. Collect basic and operational data of water supply facilities;

[0076] Acquire basic information on water supply facilities, equipment operating status information, maintenance records, water quality monitoring information, service population information, and road network information. Basic information must include at least the facility number, facility location, facility type, and service area; operating data must include at least fault records, maintenance cycles, alarm status, and water quality monitoring results; and road information must include at least the distance between facilities, road grade, slope, seasonal traffic conditions, and accessibility status.

[0077] S2. Construct a facility risk classification model based on the collected data and calculate the risk index of each water supply facility;

[0078] The risk index comprehensively represents at least the risks of equipment malfunction, water quality malfunction, exposure of the service population, maintenance overdue, and critical water supply risks. Facilities are classified into different risk levels based on the magnitude of the risk index, which serves as the basis for subsequent task generation and scheduling optimization.

[0079] The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply criticality risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index.

[0080] Specifically, the equipment anomaly risk sub-model is used to assess the degree of operational anomalies of key equipment in water supply facilities. Its inputs include equipment failure rate, equipment aging degree, deviation of real-time monitoring parameters such as equipment vibration, temperature or current, as well as equipment maintenance frequency and the time of the most recent maintenance. During calculation, the corresponding inputs can be selected according to actual needs.

[0081] In one embodiment of the present invention, equipment anomaly risk sub-indicators Calculate as follows:

[0082] ;

[0083] Where F represents the normalized equipment failure rate, A represents the normalized equipment aging coefficient, and D represents the normalized deviation of real-time monitoring parameters. , , These represent the corresponding weighting coefficients, which can be dynamically adjusted according to the equipment type.

[0084] The water quality anomaly risk sub-model is used to assess the degree of exceedance or anomaly in water supply quality. Its inputs include real-time monitoring values ​​of various water quality indicators (residual chlorine, turbidity, pH, total bacterial count, heavy metals, etc.), the multiple of exceedance of water quality indicators relative to national / industry standards, the duration of water quality anomalies, and the frequency of historical water quality anomaly events.

[0085] Water quality anomaly risk sub-indicators Calculate as follows:

[0086] ;

[0087] in, This represents the measured value of the i-th water quality indicator. This represents the standard limit value of the i-th indicator. This represents the upper limit of the warning level for the i-th indicator.

[0088] The maximum value among all the indicators that exceed the standard is taken as the comprehensive water quality risk.

[0089] The service population exposure risk sub-model is used to assess the potential impact on the population size and the level of exposure of sensitive groups in the event of water supply facility failure. Its inputs include the number of the service population, the number of sensitive locations such as schools, hospitals, and nursing homes within the service area, population density, and the availability of alternative water sources.

[0090] Service population exposure risk sub-indicators Calculate as follows:

[0091] ;

[0092] Where P represents the number of people served. This represents the preset population threshold. Indicates the number of sensitive locations. This indicates the total number of venues.

[0093] The maintenance overdue risk sub-model is used to assess whether facilities and equipment have exceeded their prescribed maintenance cycles. Specifically, the maintenance overdue risk sub-indicators... Determined based on the proportion of overdue period:

[0094] Not expired: ;

[0095] Overdue period less than 10% of the cycle: ;

[0096] Overdue period: 10%~30% ;

[0097] Overdue period of 30%~50%: ;

[0098] Overdue period greater than 50%: .

[0099] The critical risk sub-model for water supply is used to assess the importance of the water supply facility within the overall water supply system.

[0100] Key Risk Items in Water Supply Based on the facility's importance level:

[0101] Primary facilities (source water plant, main water plant): ;

[0102] Secondary facilities (booster pump stations, main pipeline nodes): ;

[0103] Tertiary facilities (general pipe network, secondary water supply in residential areas): ;

[0104] Level 4 facilities (endpoint, non-critical nodes): .

[0105] Facilities are classified into risk levels based on the range of values ​​for the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization.

[0106] Specifically, for any water supply facility i, the following risk indicators are constructed:

[0107] Equipment Abnormal Risk Indicators :

[0108] The frequency of failures, downtimes, critical component anomalies, or alarms within the facility's preset time window is determined.

[0109] In one implementation, the equipment anomaly risk index can be expressed as:

[0110]

[0111] in, This represents the normalized value of the number of failures. This represents the normalized value of the number of downtimes. This represents the normalized value of a critical anomaly event. , , These are the weighting coefficients, and =1;

[0112] Water quality anomaly risk indicators :

[0113] The determination is based on the degree of deviation between the monitoring results of the process effluent, treated water, or tap water quality of the corresponding facility and the preset water quality threshold.

[0114] In one implementation, residual chlorine, turbidity, pH, or other representative indicators can be selected, the degree of exceedance of each indicator can be calculated, and a weighted sum can be obtained:

[0115] =

[0116] in, This indicates the degree of normalized anomaly of the nth water quality indicator. For the corresponding weights;

[0117] Service population exposure risk indicators The value is determined based on the number of people served by the facility, the number of villages or groups served, or the scale of affected users. Preferably, to avoid scale imbalance caused by excessive differences in population size, the service population can be logarithmically transformed or normalized after being assigned hierarchical values.

[0118] Maintain overdue risk indicators The indicator is determined based on the difference between the cumulative operating time and cumulative operating days since the last maintenance and the preset maintenance cycle. In one implementation, when the facility has not exceeded the maintenance cycle, the indicator takes a lower value; when the facility exceeds the maintenance cycle, the maintenance overdue risk indicator gradually increases with the increase of the overdue time.

[0119] Key risk indicators for water supply The importance of a facility is determined based on its position within the water supply system. This importance is at least related to whether it is a primary water supply node, whether alternative water supply routes exist, whether it serves high-risk areas at the grassroots level, and whether it affects the water supply to multiple villages. Preferably, this determination can be made through expert scoring, rule assignment, or methods based on the topological characteristics of the water supply network.

[0120] After obtaining the above risk sub-indicators, each indicator is dimensionless, and the comprehensive risk index of facility i is calculated. The comprehensive risk index is expressed as:

[0121] ;

[0122] in, , , , , This is the risk weighting coefficient.

[0123] Furthermore, based on the comprehensive risk index The range of values ​​is used to classify the risk of facilities.

[0124] In one implementation, when ≥ Facilities were identified as high-risk at the time; ≤ < The facility was initially classified as a medium-risk facility; when < Facilities were identified as low-risk at the time, among which and This is a preset risk threshold.

[0125] The risk classification results serve as the input for subsequent task generation and scheduling optimization.

[0126] S3. Construct a cost matrix for access between facilities in mountainous and hilly areas;

[0127] Based on the geographical relationships between facilities, road grade, slope conditions, seasonal traffic capacity, travel time and accessibility status, a traffic cost model between facilities in mountainous and hilly areas is established, and a traffic cost matrix is ​​generated. The traffic cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas.

[0128] Specifically, for any two facilities i and j, first obtain the basic distance from facility i to facility j. Road grade factors Slope factor Seasonal travel factors Accessibility factors and driving time factor .

[0129] Among them, the road grade factor is used to characterize the differences in traffic efficiency of different roads such as expressways, national highways, provincial highways, county roads, township roads, and village roads; the gradient factor is used to characterize the additional traffic costs caused by mountain undulations, curves, and climbs; the seasonal traffic factor is used to characterize the impact of special seasons such as rainy season, freezing, or landslides; the accessibility factor is used to characterize whether the road is closed or temporarily inaccessible; and the travel time factor is used to characterize the travel time under actual traffic conditions.

[0130] In one implementation, the combined toll cost from facility i to facility j It can be represented as:

[0131] ;

[0132] in, This is the adjustment coefficient.

[0133] In another implementation, a weighted summation method can be used to construct the comprehensive toll cost model.

[0134] After calculating the passage cost between all pairs of facilities, a passage cost matrix is ​​generated as the basic input for scheduling optimization.

[0135] S4. Generate a set of operation and maintenance tasks to be executed;

[0136] Based on facility risk level, maintenance cycle, alarm status and task timeliness requirements, a set of current maintenance tasks to be executed is selected and generated. Each task in the task set includes at least the task object, task priority, task type, estimated operation time and latest completion deadline.

[0137] S5. Establish and solve the risk-time coupled scheduling optimization model;

[0138] Using the total passage cost, high-risk facility waiting penalty, and task timeliness breach penalty as the joint optimization objective function, the set of maintenance tasks to be executed is optimized in sequence and path to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path, and expected completion time.

[0139] For any task node, let its risk index be... The task waiting time is The level of breach of contract due to task timeout is: Then, the following joint objective function is established:

[0140] ;

[0141] in, This represents the total cost of the route. This indicates that high-risk facilities are awaiting penalties. This represents the penalty for breach of task deadline, with μ and ν being adjustment coefficients.

[0142] Furthermore, the sequence optimization and path solving process includes:

[0143] ① Initial solution generation.

[0144] An initial access sequence is generated based on the facility risk level, task timeliness, and current location.

[0145] In one implementation, the initial task access order is generated according to the rule of "high risk priority, urgent task priority, and distance second best".

[0146] ②Constraint loading.

[0147] The upper limit of working hours for operation and maintenance personnel, task time window constraints, unreachable node constraints, unique access constraints for tasks, and necessary continuity constraints are loaded into the optimization model.

[0148] ③ Iterative optimization of candidate paths.

[0149] The initial access sequence is iteratively adjusted using heuristic optimization algorithms, swarm intelligence optimization algorithms, integer programming methods, or combinations thereof.

[0150] In one implementation, a genetic algorithm is used for path finding, and the specific steps are as follows:

[0151] a. Encode the access order of each task as a chromosome;

[0152] b. Generate the initial population;

[0153] c. Calculate fitness based on the joint objective function;

[0154] d. Generate a new generation of candidate paths through selection, crossover, and mutation operations;

[0155] e. Continue iterating until the preset termination condition is met.

[0156] In another implementation, ant colony optimization, simulated annealing, tabu search, particle swarm optimization, or a hybrid algorithm combining local and global search can be used to achieve sequence optimization and path finding.

[0157] ④ Output the optimal or near-optimal path.

[0158] After the iteration, the access order with the smallest joint objective function value is selected as the current optimal or near-optimal scheduling scheme, and the estimated arrival time, estimated job completion time and total scheduling cost of each task node are calculated.

[0159] Through the above-mentioned sequence optimization and path solving process, the scheduling result is no longer solely based on the shortest distance, but prioritizes high-risk facilities and time-sensitive tasks while controlling the total operation and maintenance cost.

[0160] S6. Output the current inspection sequence, scheduling path, and estimated completion time.

[0161] The scheduling plan is output to the operation and maintenance management platform, map interface or mobile inspection terminal for operation and maintenance personnel to execute.

[0162] S7, Dynamic Replanning.

[0163] During the execution of the current scheduling scheme, dynamic replanning is performed based on the received feedback information, which includes new abnormal events in facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status.

[0164] The newly added abnormal events are evaluated, and the marginal risk reduction benefit brought about by including the task corresponding to the abnormal event in the current scheduling process is calculated, as well as the resulting increase in scheduling costs. The increase in scheduling costs includes one or more of the following: additional detour costs, time delay costs, and task order adjustment costs.

[0165] Based on the relationship between the marginal risk reduction benefit and the increase in scheduling cost, it is determined whether dynamic replanning needs to be triggered. If the risk reduction benefit brought by the new abnormal event reaches a preset threshold, or if the relationship between the risk reduction benefit and the increase in cost meets a preset criterion, dynamic replanning is triggered, the task set or path is updated and the solution is recalculated; otherwise, the current scheduling scheme is maintained and continues to be executed.

[0166] This invention also provides an operation and maintenance scheduling system for rural water supply facilities in mountainous areas based on water quality risk classification. The system includes:

[0167] The data acquisition module is used to collect basic and operational data of water supply facilities;

[0168] The risk assessment module is used to build a facility risk classification model based on the collected data and calculate the risk index of each water supply facility.

[0169] The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply critical risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index.

[0170] The facilities are classified into risk levels based on the range of the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization.

[0171] The mountainous terrain access cost modeling module is used to establish an access cost model between facilities based on the geographical relationship between facilities, road grade, slope conditions, seasonal access capacity, travel time and accessibility status, and generate an access cost matrix. The access cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas.

[0172] After calculating the passage cost between all pairs of facilities, a passage cost matrix is ​​generated, which serves as the basic input for the scheduling optimization module.

[0173] The task generation module is used to filter and generate a set of maintenance tasks to be executed based on facility risk level, maintenance cycle, alarm status and task timeliness requirements. Each task in the task set includes at least a task object, task priority, task type, estimated operation time and latest completion time.

[0174] The scheduling optimization module is used to perform sequence optimization and path solving on the set of maintenance tasks to be executed, with the total passage cost, high-risk facility waiting penalty and task timeliness breach penalty as joint optimization objective functions, to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path and expected completion time.

[0175] The result output and execution feedback module is used to output the scheduling plan to the operation and maintenance management platform, map interface or mobile inspection terminal for operation and maintenance personnel to execute, and to receive feedback information in real time. The feedback information includes new abnormal events of facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status.

[0176] The dynamic replanning module is used to perform dynamic replanning based on received feedback information during the execution of the current scheduling scheme.

[0177] Specifically, the dynamic replanning module evaluates newly added abnormal events, calculates the marginal risk reduction benefit of including the corresponding task in the current scheduling process, and the resulting increase in scheduling costs. The increased scheduling costs include one or more of the following: additional detour costs, time delay costs, and task order adjustment costs.

[0178] The dynamic replanning module determines whether to trigger dynamic replanning based on the relationship between the marginal risk reduction benefit and the increase in scheduling cost. If the risk reduction benefit brought about by the abnormal event reaches a preset threshold, or if the relationship between the risk reduction benefit and the increase in cost meets a preset criterion, dynamic replanning is triggered; otherwise, the current scheduling scheme is maintained and continues to be executed.

[0179] If triggered, the task set or path is updated and the solution is recalculated; if not triggered, the current scheduling scheme continues to be executed.

[0180] When an abnormal event causes a change in the set of tasks to be executed, the dynamic replanning module returns the updated task information to the task generation module and the scheduling optimization module, regenerates the task set, and solves the path. When an abnormal event only causes a change in the toll cost without changing the task set, the dynamic replanning module can directly send the updated constraints to the scheduling optimization module to solve the path again based on the original task set. If the dynamic replanning trigger condition is not met, the system maintains the current inspection order and scheduling path and continues to execute the current scheduling scheme.

[0181] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification, characterized in that, Includes the following steps: S1. Collect basic and operational data of water supply facilities; S2. Construct a facility risk classification model based on the collected data and calculate the risk index of each water supply facility; The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply critical risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index. The facilities are classified into risk levels based on the range of the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization. S3. Construct a cost matrix for access between facilities in mountainous and hilly areas; Based on the geographical relationships between facilities, road grade, slope conditions, seasonal traffic capacity, travel time and accessibility status, a traffic cost model between facilities in mountainous and hilly areas is established, and a traffic cost matrix is ​​generated. The traffic cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas. After calculating the passage cost between all facilities, a passage cost matrix is ​​generated as the basic input for scheduling optimization. S4. Generate a set of operation and maintenance tasks to be executed; Based on facility risk level, maintenance cycle, alarm status and task timeliness requirements, a set of current maintenance tasks to be executed is selected and generated. Each task in the task set includes at least the task object, task priority, task type, estimated operation time and latest completion time. S5. Establish and solve the risk-time coupled scheduling optimization model; Using the total passage cost, high-risk facility waiting penalty, and task timeliness breach penalty as the joint optimization objective function, the set of maintenance tasks to be executed is optimized in sequence and path to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path, and expected completion time. S6. Output the current inspection sequence, scheduling path, and estimated completion time.

2. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 1, characterized in that, In step S1, the collection of basic and operational data of the water supply facilities specifically includes: Acquire basic information on water supply facilities, equipment operation status information, maintenance records, water quality monitoring information, service population information, and road network information. The basic information includes at least facility number, facility location, facility type, and service area. The operation data includes at least fault records, maintenance cycles, alarm status, and water quality monitoring results. The road network information includes at least the distance between facilities, road grade, slope, seasonal traffic conditions, and accessibility status.

3. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 1, characterized in that, In step S2, calculating the risk index of each water supply facility specifically includes: For water supply facility i, the following risk indicators are established: Equipment Abnormal Risk Indicators : The number of failures, downtimes, critical component anomalies, or alarm frequencies within the facility's preset time window is determined. in, This represents the normalized value of the number of failures. This represents the normalized value of the number of downtimes. This represents the normalized value of a critical anomaly event. , , These are the weighting coefficients, and =1; Water quality anomaly risk indicators : The determination is based on the degree of deviation between the monitoring results of the process effluent, treated water, or tap water quality of the corresponding facility and the preset water quality threshold. = ； in, This indicates the degree of normalized anomaly of the nth water quality indicator. For the corresponding weights; Service population exposure risk indicators The number of people served by the facility, the number of villages or groups served, or the scale of users affected shall be determined accordingly. Maintain overdue risk indicators It is determined based on the difference between the cumulative operating time and cumulative operating days since the last maintenance and the preset maintenance cycle; Key risk indicators for water supply The importance of the facility is determined based on its significance within the water supply system. This significance is at least related to whether it is a primary water supply node, whether there are alternative water supply routes, whether it serves high-risk areas at the grassroots level, and whether it affects the water supply of multiple villages and groups. Each indicator is dimensionless, and the comprehensive risk index of facility i is calculated. The comprehensive risk index is expressed as: ； in, , , , , This is the risk weighting coefficient.

4. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 1, characterized in that, In step S3, the toll cost model between facilities is established based on the geographical relationship between facilities, road grade, slope conditions, seasonal traffic capacity, travel time, and accessibility status. This specifically includes: For any two facilities i and j, first obtain the basic distance between facility i and facility j. Road grade factors Slope factor Seasonal travel factors Accessibility factors and driving time factor ; The road grade factor is used to characterize the differences in traffic efficiency among different roads, such as expressways, national highways, provincial highways, county roads, township roads, and village roads; the gradient factor is used to characterize the additional travel costs caused by mountainous undulations, curves, and climbs; the seasonal travel factor is used to characterize the impact of rainy seasons, freezing, or landslides; the accessibility factor is used to characterize whether a road is closed or temporarily inaccessible; and the travel time factor is used to characterize the travel time under actual traffic conditions. Comprehensive transit cost from facility i to facility j Represented as: ； in, The adjustment coefficient is n∈[1,5].

5. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 1, characterized in that, Step S5, specifically the optimization of the order and path finding of the set of operation and maintenance tasks to be executed, includes: The initial access sequence is generated based on the facility risk level, task timeliness, and current location. Constraint loading: The upper limit of the working hours of operation and maintenance personnel, the task time window constraint, the unreachable node constraint, the unique access constraint of the task, and the necessary continuity constraints are loaded into the optimization model. Candidate path iterative optimization employs heuristic optimization algorithms, swarm intelligence optimization algorithms, integer programming methods, or combinations thereof, to iteratively adjust the initial access sequence; The optimal or near-optimal path is output. After the iteration, the access order with the smallest joint objective function value is selected as the current optimal or near-optimal scheduling scheme, and the estimated arrival time, estimated job completion time and total scheduling cost of each task node are calculated.

6. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 5, characterized in that, The method also includes: S7, Dynamic Replanning; During the execution of the current scheduling scheme, dynamic replanning is performed based on the received feedback information, which includes new abnormal events in facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status.

7. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 6, characterized in that, Dynamic reprogramming also includes: The newly added abnormal events are evaluated, and the marginal risk reduction benefit brought about by including the task corresponding to the abnormal event in the current scheduling process is calculated, as well as the resulting increase in scheduling costs. The increase in scheduling costs includes one or more of the following: additional detour costs, time delay costs, and task order adjustment costs.

8. The method for operation and maintenance scheduling of rural water supply facilities in mountainous areas based on water quality risk classification according to claim 7, characterized in that, Dynamic reprogramming also includes: Based on the relationship between the marginal risk reduction benefit and the increase in scheduling cost, it is determined whether dynamic replanning needs to be triggered. If the risk reduction benefit brought by the new abnormal event reaches a preset threshold, or if the relationship between the risk reduction benefit and the increase in cost meets a preset criterion, dynamic replanning is triggered, the task set or path is updated and the solution is recalculated; otherwise, the current scheduling scheme is maintained and continues to be executed.

9. A water quality risk classification-based operation and maintenance scheduling system for rural water supply facilities in mountainous areas, used to implement the water quality risk classification-based operation and maintenance scheduling method for rural water supply facilities in mountainous areas as described in any one of claims 1-8, characterized in that, The system includes: The data acquisition module is used to collect basic and operational data of water supply facilities; The risk assessment module is used to build a facility risk classification model based on the collected data and calculate the risk index of each water supply facility. The facility risk classification model includes at least the equipment anomaly risk sub-model, the water quality anomaly risk sub-model, the service population exposure risk sub-model, the maintenance overdue risk sub-model, and the water supply critical risk sub-model. Each sub-model outputs corresponding risk sub-indicators, which are then normalized to form a comprehensive facility risk index. The facilities are classified into risk levels based on the range of the comprehensive risk index, and the risk classification results serve as the input for subsequent task generation and scheduling optimization. The mountainous terrain access cost modeling module is used to establish an access cost model between facilities based on the geographical relationship between facilities, road grade, slope conditions, seasonal access capacity, travel time and accessibility status, and generate an access cost matrix. The access cost matrix is ​​used to characterize the comprehensive scheduling cost required to get from one facility to another during the actual operation and maintenance process in mountainous and hilly areas. After calculating the passage cost between all pairs of facilities, a passage cost matrix is ​​generated, which serves as the basic input for the scheduling optimization module. The task generation module is used to filter and generate a set of maintenance tasks to be executed based on facility risk level, maintenance cycle, alarm status and task timeliness requirements. Each task in the task set includes at least a task object, task priority, task type, estimated operation time and latest completion time. The scheduling optimization module is used to perform sequence optimization and path solving on the set of maintenance tasks to be executed, with the total passage cost, high-risk facility waiting penalty and task timeliness breach penalty as joint optimization objective functions, to obtain the current scheduling scheme. The scheduling scheme includes at least the inspection sequence, scheduling path and expected completion time.

10. The operation and maintenance scheduling system for rural water supply facilities in mountainous areas based on water quality risk classification according to claim 9, characterized in that, The system also includes: The result output and execution feedback module is used to output the scheduling plan to the operation and maintenance management platform, map interface or mobile inspection terminal for operation and maintenance personnel to execute, and to receive feedback information in real time. The feedback information includes new abnormal events of facilities, changes in road traffic conditions, task execution timeouts, and sudden changes in equipment status. The dynamic replanning module is used to perform dynamic replanning based on received feedback information during the execution of the current scheduling scheme.

Images