Photovoltaic operation management system based on big data

Abstract

The invention relates to the technical field of operation management, in particular to a photovoltaic operation management system based on big data, which comprises an initial management module, an intelligent scheduling module, a dynamic inspection module and a maintenance optimization module. According to the invention, by recording the installation demand of the user photovoltaic power station and combining a design scheme provided by a photovoltaic power station design platform, efficient and accurate installation is realized, the installation quality and progress control are ensured, and by monitoring the operation state of the photovoltaic power station in real time, calculating the power generation efficiency and formulating the target scheduling information, the power generation efficiency is improved. Dynamic matching of power generation data and power grid requirements is achieved, power generation parameters are optimized, the overall power generation efficiency and economic benefits are improved, fault risk assessment and high-risk area identification are carried out, the inspection path and time arrangement are optimized, the inspection efficiency and equipment reliability are improved, and by analyzing the health state of photovoltaic power station equipment in real time and making a matching maintenance plan, the maintenance efficiency is improved. And high-efficiency operation and long service life of equipment are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of operation management, and in particular to a photovoltaic operation management system based on big data. Background Art

[0002] The field of operations management technology involves enterprises and organizations improving operational efficiency and reducing costs through effective resource allocation and process optimization. Its core goals include improving productivity, enhancing service quality, optimizing supply chain management, improving customer satisfaction and achieving continuous improvement. This technology field is widely used in many industries, including manufacturing, service, public administration, etc. Common methods and tools include supply chain management systems, enterprise resource planning systems, performance management systems, quality management systems and predictive analysis technologies. Through data-driven decision-making and optimization, operations management technology can provide enterprises and organizations with sustainable competitive advantages.

[0003] Among them, the photovoltaic operation management system based on big data aims to use big data analysis technology to comprehensively monitor and optimize the operation of photovoltaic power stations. Its main uses include real-time monitoring of the operating status of photovoltaic power stations, predicting power generation, diagnosing faults, optimizing maintenance plans, and improving overall operational efficiency. By collecting and analyzing a large amount of operational data, the system realizes refined management of power station operations, helps operators discover and solve problems in a timely manner, maximizes power generation efficiency and economic benefits, and improves the operational effect and reliability of photovoltaic power stations.

[0004] In terms of power generation scheduling, traditional operation and management systems rely on static data and preset parameters, and are unable to adjust and optimize power generation strategies in real time, resulting in reduced power generation efficiency and economic benefits. Inspection arrangements are based on fixed schedules and routes, and do not fully consider the real-time status of equipment and the risk of failure, resulting in a waste of inspection resources and delayed equipment maintenance. In terms of maintenance, there is a lack of real-time monitoring and dynamic analysis of the health status of equipment, and it is impossible to detect potential problems in time and perform preventive maintenance, resulting in frequent equipment failures and increased maintenance costs, limiting the overall operational efficiency and economic benefits of photovoltaic power stations, and failing to meet the requirements of photovoltaic operation management for efficiency, accuracy, and dynamism. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a photovoltaic operation and management system based on big data.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a photovoltaic operation management system based on big data, the system comprising:

[0007] The initial management module inputs user information and signs contracts based on the user's PV power station installation requirements, obtains PV power station design plans through the PV power station design platform, makes construction arrangements, and records the construction process of the PV power station, arranges completion inspections, and obtains initial inspection information;

[0008] The intelligent dispatching module monitors the operation status of the photovoltaic power station in real time based on the initial inspection information, and calculates the power generation efficiency of the photovoltaic power station in combination with the historical power generation data and the current weather data, compares the power generation data with the grid demand, formulates matching power generation parameter adjustment measures, and obtains the target dispatching information;

[0009] The dynamic inspection module, based on the target scheduling information, combines the real-time operation data, environmental data and historical fault location data of the photovoltaic power station to conduct fault risk assessment on the photovoltaic power station equipment, identify the high fault risk areas of the photovoltaic power station, formulate matching inspection paths, adjust the inspection time and personnel allocation, and obtain target inspection information;

[0010] The maintenance optimization module analyzes the operation data of the photovoltaic power station in real time based on the target inspection information, combined with real-time monitoring data and historical fault data, evaluates the current health status of the photovoltaic power station equipment, formulates matching maintenance information, adjusts maintenance time and personnel arrangements, and obtains maintenance arrangement information.

[0011] The present invention is improved in that the method for arranging the construction is:

[0012] Based on the installation requirements of the user's photovoltaic power station, according to the geographical location, installation area and azimuth parameters provided by the user, the photovoltaic power station design plan is obtained through the photovoltaic power station design platform, and the formula is used:

[0013]

[0014] Carry out preliminary allocation of construction resources and obtain preliminary allocation amount of resources;

[0015] Among them, R i is the initial allocation of the i-th resource, A i is the installation area of ​​the ith installation area, θ i is the azimuth angle of the ith installation area, D i is the unit area allocation ratio of the i-th resource demand;

[0016] Based on the preliminary allocation of the resources, combined with the geographical location and construction site conditions, the formula is:

[0017]

[0018] Adjust the allocation of construction resources to obtain the optimal allocation of resources;

[0019] Among them, R i,opt is the optimal allocation of the i-th resource, R i is the initial allocation of the i-th resource, k1 is the weight coefficient of the geographical location, L i is the geographical location influencing factor of the ith installation area, is the average value of the influencing factor of the geographical location of the installation area, k2 is the weight coefficient of the construction conditions, C i is the construction condition influencing factor of the i-th installation area, is the average value of the factors affecting the construction conditions in the installation area;

[0020] Based on the optimized allocation of the resource, compared with the actual available amount of the resource, the formula is:

[0021]

[0022] Calculate the sum of resource allocation deviations and compare the sum of resource allocation deviations with the preset tolerance threshold ∈. If the sum of resource allocation deviations is lower than the preset tolerance threshold ∈, the construction demand is met and the construction arrangement information is obtained.

[0023] Where T is the sum of resource allocation deviations, n is the number of resource types, R i,opt is the optimal allocation of the i-th resource, R i,act is the actual available amount of the i-th resource.

[0024] The present invention is improved in that the method for calculating the power generation efficiency of the photovoltaic power station is:

[0025] Based on the real-time monitoring data of the photovoltaic power station, the real-time power generation energy data and the corresponding timestamp are extracted through the formula:

[0026]

[0027] Calculate real-time power generation data;

[0028] Among them, P t is the real-time power generation at time t, E t is the power generation energy at time t, T t is the time length of time t, k1 is the real-time adjustment coefficient, and k2 is the time square root adjustment coefficient;

[0029] Based on the real-time power generation data, combined with historical power generation data and current weather data, the formula is:

[0030]

[0031] Calculate the theoretical power generation data of photovoltaic power stations;

[0032] Among them, P theo,t is the theoretical power generation at time t, S t is the solar radiation intensity at time t, H t is the illumination time of time t, η is the theoretical conversion efficiency of the photovoltaic power station, k3 is the solar radiation adjustment coefficient, and α is the solar incident angle;

[0033] Based on the theoretical power generation data and the real-time power generation data, the formula is:

[0034]

[0035] Calculate the power generation efficiency of photovoltaic power plants;

[0036] Among them, η t is the power generation efficiency at time t, P t is the real-time power generation at time t, P theo,t is the theoretical power generation at time t, ∈ is a constant term.

[0037] The present invention is improved in that the step of obtaining the target scheduling information is:

[0038] Based on the power generation efficiency of the photovoltaic power station, compared with the grid demand, the formula is:

[0039]

[0040] Calculate grid demand satisfaction;

[0041] Among them, D t is the grid demand satisfaction at time t, η t is the power generation efficiency at time t, N t is the grid demand at time t, ∈ is a constant term;

[0042] Based on the grid demand satisfaction, combined with current weather data and historical power generation data, the formula is:

[0043]

[0044] Calculate optimal scheduling parameters;

[0045] Among them, O t To optimize the scheduling parameters, P t is the real-time power generation at time t, W t is the current weather impact factor at time t, is the historical average weather impact factor, k4 is the weather adjustment coefficient;

[0046] Based on the optimization scheduling parameters and the grid demand satisfaction, the formula is:

[0047]

[0048] Calculate the target dispatch parameters and formulate matching power generation parameter adjustment measures to obtain target dispatch information;

[0049] Among them, M t is the target scheduling parameter at time t, O t is the optimal scheduling parameter at time t, D t is the grid demand satisfaction at time t.

[0050] The present invention is improved in that the method for identifying high fault risk areas of a photovoltaic power station is:

[0051] Based on the target scheduling information, the real-time operation data of the current photovoltaic power station is obtained through the formula:

[0052]

[0053] Calculate the initial risk value R1 i , conduct preliminary risk assessments of multiple areas of the PV plant;

[0054] Among them, R1 i represents the initial risk value of the ith region, w j represents the weight coefficient of the jth parameter, D ij represents the jth parameter data of the i-th region, and n represents the total number of parameters;

[0055] Based on the preliminary risk value R1 i , combined with historical fault location data, through the formula:

[0056]

[0057] Calculate the adjusted risk value R2 i ;

[0058] Among them, R2 i represents the adjusted risk value of the ith region, F k represents the kth historical fault frequency coefficient, H ik represents the kth historical fault data of the i-th area, and m represents the total number of historical fault data;

[0059] Based on the adjusted risk value R2 i , compared with the preset risk threshold T, if R2 i ≥T, the area is marked as a high failure risk area and a high failure risk area mark is generated.

[0060] The present invention is improved in that the step of acquiring the target inspection information is:

[0061] Based on the high failure risk area marking, by formula:

[0062]

[0063] Sum the risk correlations of high fault risk areas, calculate the matching scores of inspection paths, formulate inspection paths, and generate preliminary inspection paths;

[0064] Among them, P i represents the matching score of the i-th inspection path, R ij represents the risk association between the ith region and the jth high failure risk region, α and β are adjustment parameters, and n represents the total number of high failure risk regions.

[0065] Based on the preliminary inspection path, combined with the real-time operation data and environmental data of the photovoltaic power station equipment, the formula is:

[0066] T i =P i ·(1+E i )·γ

[0067] Calculate and optimize inspection time;

[0068] Among them, T i represents the optimized inspection time of the ith high fault risk area, E i represents the environmental impact factor of the ith region, and γ is the optimization coefficient.

[0069] Based on the preliminary inspection path and the optimized inspection time, the inspection personnel allocation is adjusted to obtain target inspection information.

[0070] The present invention is improved in that the method for evaluating the current health status of photovoltaic power station equipment is:

[0071] Based on real-time monitoring data, through the formula:

[0072]

[0073] Calculate the mean and standard deviation of equipment operating parameters and generate statistical values ​​of equipment operating parameters;

[0074] Among them, μ i represents the mean value of the operating parameters of the ith device, σ i represents the standard deviation of the operating parameters of the ith device, D ij represents the jth operating parameter value of the i-th device, and n represents the total number of parameters;

[0075] Based on the statistical values ​​of the equipment operating parameters and the historical fault data, the formula is:

[0076]

[0077] Calculate the fault frequency and fault duration, and generate fault characteristic parameters;

[0078] Among them, F i represents the failure frequency of the ith device, T i represents the fault duration of the ith device, H ik represents the kth fault occurrence record of the ith device, t ik represents the duration of the kth fault of the i-th device, and m represents the total number of fault records;

[0079] Based on the statistical values ​​of the equipment operating parameters and the fault characteristic parameters, the formula is:

[0080]

[0081] Calculate the health score of the equipment and compare the health score of the equipment with the preset health score threshold T. When the health score is greater than or equal to the health score threshold, it is evaluated as a healthy state, and the current health status information of the photovoltaic power station equipment is obtained;

[0082] Among them, S i represents the health score of the ith device, μ i represents the mean value of the operating parameters of the ith device, σ i represents the standard deviation of the operating parameters of the ith device, F i represents the failure frequency of the ith device, T i represents the fault duration of the i-th device, w1, w2 and w3 represent weight parameters, and δ1, δ2 and δ3 are adjustment coefficients.

[0083] The present invention is improved in that the steps of obtaining the maintenance schedule information are:

[0084] Based on the current health status information of the photovoltaic power station equipment, the formula is:

[0085]

[0086] Calculate maintenance priority and generate equipment maintenance priority;

[0087] Among them, P i represents the maintenance priority of the i-th device, S i represents the health score of the ith device, T represents the health score threshold, δ1 is the adjustment coefficient, and α is the adjustment coefficient;

[0088] Based on the equipment maintenance priority and historical maintenance data, the formula is:

[0089]

[0090] Score the maintenance complexity of the equipment, adjust the planning of maintenance tasks according to the maintenance complexity score of the equipment, and generate a maintenance task plan;

[0091] Among them, C i represents the maintenance complexity score of the ith equipment, D ij represents the jth maintenance task of the i-th equipment, W j represents the weight of the jth task, R ij represents the resources available for the i-th device, δ2 is the adjustment coefficient, and n represents the total number of maintenance tasks;

[0092] Based on the maintenance task plan, combined with real-time monitoring data,

[0093]

[0094] Evaluate the total maintenance time, adjust the maintenance time and personnel allocation according to the total maintenance time, and generate maintenance schedule information;

[0095] Among them, T m represents the total maintenance time, C i represents the maintenance complexity score of the i-th equipment, P i represents the priority of the ith device, β is the optimization coefficient, m represents the total number of devices, and N represents the number of maintenance personnel.

[0096] Compared with the prior art, the advantages and positive effects of the present invention are:

[0097] In the present invention, by recording the installation requirements of the user's photovoltaic power station, including the geographical location, installation area and azimuth parameters, combined with the design scheme provided by the photovoltaic power station design platform, efficient and accurate installation, construction arrangement and construction process recording are achieved to ensure the installation quality and progress control. By real-time monitoring of the operating status of the photovoltaic power station, combined with historical power generation data and current weather data, the power generation efficiency is accurately calculated, and target scheduling information is formulated to achieve dynamic matching of power generation data with grid demand, optimize power generation parameters, improve overall power generation efficiency and economic benefits, conduct fault risk assessment and high-risk area identification, optimize inspection paths and time arrangements, improve inspection efficiency and equipment reliability, and formulate matching maintenance plans by real-time analysis of the health status of photovoltaic power station equipment and combining real-time monitoring data and historical fault data to ensure efficient operation and long life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 is a system flow chart of the present invention;

[0099] Figure 2 A flow chart for the construction arrangement of the present invention;

[0100] Figure 3 A flow chart for calculating the power generation efficiency of a photovoltaic power station according to the present invention;

[0101] Figure 4 A flow chart of obtaining target scheduling information for the present invention;

[0102] Figure 5 A flow chart for identifying high failure risk areas of a photovoltaic power plant for the present invention;

[0103] Figure 6 A flow chart of obtaining target inspection information for the present invention;

[0104] Figure 7 A flow chart for evaluating the current health status of photovoltaic power station equipment according to the present invention;

[0105] Figure 8 Flowchart for obtaining maintenance schedule information for the present invention. DETAILED DESCRIPTION

[0106] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0107] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0108] Example

[0109] See also Figure 1 The present invention provides a technical solution: a photovoltaic operation management system based on big data, the system comprising:

[0110] The initial management module inputs user information and signs contracts based on the user's PV power station installation requirements, records the user's geographical location, installation area and azimuth parameters, obtains the PV power station design plan through the PV power station design platform, makes construction arrangements, and records the construction process of the PV power station, arranges completion inspections, and obtains initial inspection information;

[0111] The intelligent dispatching module monitors the operating status of the photovoltaic power station in real time based on the initial inspection information, and calculates the power generation efficiency of the photovoltaic power station by combining the historical power generation data and the current weather data, compares the power generation data with the grid demand, formulates matching power generation parameter adjustment measures, and obtains the target dispatching information;

[0112] Based on the target scheduling information, the dynamic inspection module combines the real-time operation data, environmental data and historical fault location data of the photovoltaic power station to conduct fault risk assessment on the photovoltaic power station equipment, identify the high fault risk areas of the photovoltaic power station, formulate matching inspection routes, adjust the inspection time and personnel allocation, and obtain target inspection information;

[0113] The maintenance optimization module analyzes the operation data of the PV power station in real time based on the target inspection information, combined with real-time monitoring data and historical fault data, calculates the health score of the PV power station equipment, evaluates the current health status of the PV power station equipment, formulates matching maintenance information, adjusts maintenance time and personnel arrangements, and obtains maintenance arrangement information.

[0114] The initial inspection information includes the equipment installation status, the equipment's initial operating status and environmental impact information; the target scheduling information includes power generation allocation, operating time period selection and backup power supply switching strategy; the target inspection information includes inspection sequence, inspection time and inspection personnel allocation; the maintenance arrangement information includes maintenance task allocation, maintenance tool selection and maintenance time schedule.

[0115] See also Figure 2 , the method for construction arrangement is:

[0116] Based on the installation requirements of the user's photovoltaic power station, according to the geographical location, installation area and azimuth parameters provided by the user, the photovoltaic power station design plan is obtained through the photovoltaic power station design platform, and the formula is used:

[0117]

[0118] Carry out preliminary allocation of construction resources and obtain preliminary allocation amount of resources;

[0119] Among them, R i is the initial allocation of the i-th resource, A i is the installation area of ​​the ith installation area, θ i is the azimuth angle of the ith installation area, D i is the unit area allocation ratio of the i-th resource demand;

[0120] Based on the preliminary allocation of resources, combined with the geographical location and construction site conditions, the formula is:

[0121]

[0122] Adjust the allocation of construction resources to obtain the optimal allocation of resources;

[0123] Among them, R i,opt is the optimal allocation of the i-th resource, R i is the initial allocation of the i-th resource, k1 is the weight coefficient of the geographical location, L i is the geographical location influencing factor of the ith installation area, is the average value of the influencing factor of the geographical location of the installation area, k2 is the weight coefficient of the construction conditions, C i is the construction condition influencing factor of the i-th installation area, is the average value of the factors affecting the construction conditions in the installation area;

[0124] Based on the optimal allocation of resources, compared with the actual available amount of resources, the formula is:

[0125]

[0126] Calculate the sum of resource allocation deviations and compare the sum of resource allocation deviations with the preset tolerance threshold ∈. If the sum of resource allocation deviations is lower than the preset tolerance threshold ∈, the construction demand is met and the construction arrangement information is obtained.

[0127] Where T is the sum of resource allocation deviations. If T<∈, the allocation is considered to meet the demand. ∈ is the preset tolerance threshold, n is the number of resource types, and R i,opt is the optimal allocation of the i-th resource, R i,act is the actual available amount of the i-th resource.

[0128] formula:

[0129]

[0130] Parameter meaning and acquisition method:

[0131] A i : The installation area of ​​the ith installation area, which is directly obtained through the installation area parameters provided by the user;

[0132] θ i : The azimuth of the i-th installation area, directly obtained through the azimuth parameters provided by the user;

[0133] D i : The unit area allocation ratio of the ith resource demand is obtained by querying the standard parameter library of the photovoltaic power station design platform.

[0134] k1: weight coefficient of geographical location, set from empirical data;

[0135] L i: The geographical location influencing factor of the i-th installation area is calculated by the photovoltaic power station design platform based on the geographical location data;

[0136] The average value of the geographical location influence factors of all installation areas, calculated by the geographical location influence factors of all installation areas;

[0137] k2: weight coefficient of construction conditions, set from empirical data;

[0138] C i : The construction condition influencing factor of the i-th installation area is calculated by the photovoltaic power station design platform based on the construction site condition data;

[0139] The average value of the construction condition influencing factors of all installation areas is calculated using the construction condition influencing factors of all installation areas.

[0140] n: the number of resource types, determined by the photovoltaic power station design platform;

[0141] R i,act : The actual available quantity of the i-th resource is obtained through the construction resource management system query;

[0142] ∈: preset tolerance threshold, set according to actual construction requirements.

[0143] Calculation example:

[0144] Assume that the user's installation requirements involve three resource types.

[0145] The specific parameters are as follows:

[0146] Installation area A1 = 100 square meters, A2 = 150 square meters, A3 = 200 square meters;

[0147] Azimuth angles θ1 = 30°, θ2 = 45°, θ3 = 60°;

[0148] The resource demand unit area allocation ratio is D1=10, D2=12, D3=15;

[0149] Geographical location influence factors L1 = 1.2, L2 = 0.8, L3 = 1.0;

[0150] Construction condition influence factors C1 = 1.5, C2 = 1.0, C3 = 1.2;

[0151] Weight coefficients k1 = 0.5, k2 = 0.3;

[0152] The preset tolerance threshold ∈=5;

[0153] Actual available quantity R1,act =9, R 2,act =11, R 3,act =13;

[0154] Calculate preliminary construction resource allocations:

[0155]

[0156] The preliminary construction resource allocation results are R1=8.66, R2=8.84, R3=6.67

[0157] Calculate the average for geographic location and construction conditions:

[0158]

[0159] Average geographic location impact factor Average construction condition influencing factors Calculate the optimal allocation of construction resources:

[0160]

[0161]

[0162] Optimize construction resource allocation results R 1,opt =11.08, R 2,opt =10.45, R 3,opt =7.88, evaluate the optimization of construction resource allocation and calculate the sum of resource allocation deviations:

[0163] T=|11.08-9|+|10.45-11|+|7.88-13|

[0164] ≈2.08+0.55+5.12

[0165] ≈7.75

[0166] The sum of resource allocation deviations T = 7.75 determines whether the construction requirements are met:

[0167] Since T=7.75 is greater than the preset tolerance threshold ∈=5, the parameters of the construction plan need to be adjusted and recalculated until T is less than or equal to ∈.

[0168] See also Figure 3 , the method for calculating the power generation efficiency of a photovoltaic power station is:

[0169] Based on the real-time monitoring data of the photovoltaic power station, the real-time power generation energy data and the corresponding timestamp are extracted through the formula:

[0170]

[0171] Calculate real-time power generation data;

[0172] Among them, P t is the real-time power generation at time t, E t is the power generation energy at time t, T t is the time length of time t, k1 is the real-time adjustment coefficient, and k2 is the time square root adjustment coefficient;

[0173] Based on real-time power generation data, combined with historical power generation data and current weather data, the formula is:

[0174] P theo,t =S t ×H t ×η×(1+k3×cos(α))

[0175] Calculate the theoretical power generation data of photovoltaic power stations;

[0176] Among them, P theo,t is the theoretical power generation at time t, S t is the solar radiation intensity at time t, H t is the effective illumination time of time t, η is the theoretical conversion efficiency of the photovoltaic power station, k3 is the solar radiation adjustment coefficient, and α is the solar incident angle;

[0177] Based on theoretical power generation data and real-time power generation data, the formula is:

[0178]

[0179] Calculate the power generation efficiency of photovoltaic power plants;

[0180] Among them, η t is the power generation efficiency at time t, P t is the real-time power generation at time t, P theo,t is the theoretical power generation at time t, ∈ is a constant term.

[0181] formula:

[0182]

[0183] P theo,t =S t ×H t ×η×(1+k3×cos(α))

[0184]

[0185] Parameter meaning and acquisition method:

[0186] E t: The power generation energy at time t is obtained through real-time monitoring data, such as the energy value recorded by the electric energy meter installed in the photovoltaic power station;

[0187] T t : The duration of time t, calculated from the timestamp data, is determined by the time interval between records;

[0188] k1: real-time adjustment coefficient, used to adjust the power generation to reflect the real-time situation, and the data is set based on experience;

[0189] k2: time square root adjustment coefficient, used to reflect the nonlinear effect of time, and is set based on experience;

[0190] S t : The solar radiation intensity at time t is obtained through weather data, which is obtained through real-time data provided by meteorological stations or weather services;

[0191] H t : The effective sunshine time at time t is calculated based on the historical power generation data and sunshine time data;

[0192] η: The theoretical conversion efficiency of a photovoltaic power station, usually determined by the efficiency of the photovoltaic cell and given by the photovoltaic cell manufacturer;

[0193] k3: Solar radiation adjustment coefficient, used to adjust the impact of solar radiation on theoretical power generation, preset by experts;

[0194] α: solar incidence angle, calculated from weather data and installation location, usually determined by the sun’s position and the angle of the photovoltaic panel;

[0195] ∈: a small constant, set to avoid the denominator being zero;

[0196] Calculation example:

[0197] Assume the following data:

[0198] Time length T t =1 hour; power generation energy E t =2.5kWh; solar radiation intensity S t =800W / m 2 ; Effective illumination time H t = 5 hours; conversion efficiency of photovoltaic power station η = 0.18; real-time adjustment coefficient k1 = 1.05; time square root adjustment coefficient k2 = 0.1; solar radiation adjustment coefficient k3 = 0.2; solar incident angle α = 30°; minimum constant ∈ = 0.01;

[0199] Real-time power generation calculation:

[0200]

[0201] Theoretical power generation calculation:

[0202] P theo,t =S t ×H t ×η×(1+k3×cos(α))

[0203] =800×5×0.18×(1+0.2×cos(30°))

[0204] =720×1.173

[0205] ≈844.56W

[0206] ≈0.845kW

[0207] Power generation efficiency calculation:

[0208]

[0209] The power generation efficiency is 180.11%.

[0210] See also Figure 4 , the steps to obtain the target scheduling information are:

[0211] Based on the power generation efficiency of the photovoltaic power station, compared with the grid demand, the formula is:

[0212]

[0213] Calculate grid demand satisfaction;

[0214] Among them, D t is the grid demand satisfaction at time t, η t is the power generation efficiency at time t, N t is the grid demand at time t, ∈ is a constant term;

[0215] Based on the grid demand satisfaction, combined with current weather data and historical power generation data, the formula is:

[0216]

[0217] Calculate optimal scheduling parameters;

[0218] Among them, O t To optimize the scheduling parameters, P t is the real-time power generation at time t, W t is the current weather impact factor at time t, is the historical average weather impact factor, k4 is the weather adjustment coefficient;

[0219] Based on the optimization of dispatching parameters and the satisfaction of power grid demand, the formula is:

[0220]

[0221] Calculate the target dispatch parameters and formulate matching power generation parameter adjustment measures to obtain target dispatch information;

[0222] Among them, M t is the target scheduling parameter at time t, O t is the optimal scheduling parameter at time t, D t is the grid demand satisfaction at time t.

[0223] formula:

[0224]

[0225] Parameter meaning and acquisition method:

[0226] η t : The power generation efficiency at time t is obtained by the power generation efficiency calculation formula in the previous step;

[0227] N t : The grid demand at time t, obtained through the data provided by the grid management system;

[0228] ∈: a small constant, used to avoid the denominator being zero, usually set to 0.01;

[0229] P t : The real-time power generation at time t is obtained by the real-time power generation calculation formula in the previous step;

[0230] W t : The current weather influencing factor at time t, obtained through the current weather data;

[0231] Historical average weather impact factor, calculated using historical weather data;

[0232] k4: Weather adjustment factor, set by experts based on historical data:

[0233] Calculation example:

[0234] Assume the following data:

[0235] Time t = 1 hour; power generation efficiency η t =75%; grid demand N t =100kW; real-time power generation P t =90kW; current weather impact factor W t =1; historical average weather impact factor Small constant ∈ = 0.01; weather adjustment coefficient k4 = 0.2;

[0236] Calculation of grid demand satisfaction:

[0237]

[0238] Optimize scheduling parameter calculation:

[0239]

[0240] Target scheduling parameter calculation:

[0241]

[0242] The target dispatch information is 81.01kW.

[0243] See also Figure 5 , the method to identify high failure risk areas of PV power plants is:

[0244] Based on the target scheduling information, the real-time operation data of the current photovoltaic power station is obtained through the formula:

[0245]

[0246] Calculate the initial risk value R1 i , conduct preliminary risk assessments of multiple areas of the PV plant;

[0247] Among them, R1 i represents the initial risk value of the ith region, w j represents the weight coefficient of the jth parameter, D ij represents the jth parameter data of the i-th region, and n represents the total number of parameters;

[0248] Based on the initial risk value R1 i , combined with historical fault location data, through the formula:

[0249]

[0250] Calculate the adjusted risk value R2 i ;

[0251] Among them, R2 i represents the adjusted risk value of the ith region, F k represents the kth historical fault frequency coefficient, H ik represents the kth historical fault data of the i-th area, and m represents the total number of historical fault data;

[0252] Based on the adjusted risk value R2 i , compared with the preset risk threshold T, if R2 i≥T, the area is marked as a high failure risk area and a high failure risk area mark is generated.

[0253] formula:

[0254]

[0255] Parameter meaning and acquisition method:

[0256] w j : The weight coefficient of the jth parameter, determined by expert scoring or historical data analysis.

[0257] D ij : The jth parameter data of the i-th area includes real-time operation data and environmental data, which are obtained through sensors and monitoring systems, such as temperature, humidity, equipment operation status, etc.

[0258] n: The total number of parameters, determined by the system settings and the types of parameters monitored, for example, 5 parameters: temperature, humidity, light intensity, device voltage, and device current.

[0259] F k : The kth historical fault frequency coefficient, obtained by statistical analysis of past fault data.

[0260] H ik : The kth historical fault data of the ith area is obtained through historical records and fault logs, such as the number of faults, fault types, etc.

[0261] m: Total number of historical fault data, determined by the types of fault data counted, such as the three main fault types: equipment overheating, loose connection, and arc discharge.

[0262] T: The set risk threshold, determined through statistical analysis and expert opinion.

[0263] Calculation example:

[0264] Assume that there are five parameters: temperature, humidity, light intensity, device voltage, and device current. Their weight coefficients are 0.2, 0.2, 0.2, 0.2, 0.2, and the parameter data for a certain area are 30, 40, 50, 220, and 5, respectively.

[0265]

[0266] Assume that there are three historical fault types: equipment overheating, loose connection and arc discharge, and their fault frequency coefficients are 0.1, 0.15, and 0.2 respectively. The historical fault data of a certain area are 5, 2, and 1 respectively.

[0267]

[0268]

[0269] Assume that the risk threshold T is set to 14.0.

[0270] 14.133≥14.0

[0271] Therefore, this area is marked as a high failure risk area.

[0272] See also Figure 6 , the steps to obtain the target inspection information are:

[0273] Based on the high failure risk area marking, the formula is:

[0274]

[0275] Sum the risk correlations of high fault risk areas, calculate the matching scores of inspection paths, formulate inspection paths, and generate preliminary inspection paths;

[0276] Among them, P i represents the matching score of the i-th inspection path, R ij represents the risk association between the ith region and the jth high failure risk region, α and β are adjustment parameters, and n represents the total number of high failure risk regions.

[0277] Based on the preliminary inspection path, combined with the real-time operation data and environmental data of the photovoltaic power station equipment, the formula is:

[0278] T i =P i ·(1+E i )·γ

[0279] Calculate and optimize inspection time;

[0280] Among them, T i represents the optimized inspection time of the ith high fault risk area, E i represents the environmental impact factor of the ith region, and γ is the optimization coefficient.

[0281] Based on the preliminary inspection route and optimized inspection time, the inspection personnel allocation is adjusted to obtain the target inspection information.

[0282] formula:

[0283]

[0284] Parameter meaning and acquisition method:

[0285] R ij: The risk correlation between the ith area and the jth high fault risk area. It is obtained by analyzing the correlation between the historical fault data and operation data of each area. The data sources of the risk correlation include the monitoring system and fault record database of the photovoltaic power station.

[0286] α: Adjustment parameter, used to adjust the calculation of risk association and improve the accuracy of calculation. The parameter is determined by experimental data fitting and expert experience.

[0287] β: Adjustment parameter, used to adjust the denominator to enhance the flexibility of calculation. The parameter is adjusted through the optimization algorithm to ensure the stability and accuracy of risk calculation.

[0288] n: The total number of high failure risk areas, determined by the high risk areas identified in the previous steps.

[0289] E i : Environmental impact factor of the ith region. The parameters are obtained through the real-time monitoring system, including environmental parameters such as temperature, humidity, and light intensity.

[0290] γ: Optimization coefficient, used to improve the calculation accuracy of inspection time. The rationality of the inspection plan is ensured through optimization algorithm adjustment.

[0291] Calculation example:

[0292] Assume that there are five high-failure risk areas, set the adjustment parameters α = 0.3 and β = 2, and the risk correlation data between a certain area and other areas are 4, 5, 3, 2, and 1 respectively.

[0293]

[0294]

[0295] Assume that the optimization coefficient γ = 1 and the environmental impact factor E i =0.2.

[0296]

[0297] See also Figure 7 , the method to evaluate the current health status of photovoltaic power station equipment is:

[0298] Based on real-time monitoring data, through the formula:

[0299]

[0300] Calculate the mean and standard deviation of equipment operating parameters and generate statistical values ​​of equipment operating parameters;

[0301] Among them, μ i represents the mean value of the operating parameters of the ith device, σ irepresents the standard deviation of the operating parameters of the ith device, D ij represents the jth operating parameter value of the i-th device, and n represents the total number of parameters;

[0302] Based on the statistical values ​​of equipment operating parameters and historical fault data, the formula is:

[0303]

[0304] Calculate the fault frequency and fault duration, and generate fault characteristic parameters;

[0305] Among them, F i represents the failure frequency of the ith device, T i represents the fault duration of the ith device, H ik represents the kth fault occurrence record of the ith device, t ik represents the duration of the kth fault of the i-th device, and m represents the total number of fault records;

[0306] Based on the statistical values ​​of equipment operating parameters and fault characteristic parameters, the formula is:

[0307]

[0308] Calculate the health score of the equipment and compare the health score of the equipment with the preset health score threshold T. When the health score is greater than or equal to the health score threshold, it is evaluated as a healthy state, and the current health status information of the photovoltaic power station equipment is obtained;

[0309] Among them, S i represents the health score of the ith device, μ i represents the mean value of the operating parameters of the ith device, σ i represents the standard deviation of the operating parameters of the ith device, F i represents the failure frequency of the ith device, T i represents the fault duration of the i-th device, w1, w2 and w3 represent weight parameters, and δ1, δ2 and δ3 are adjustment coefficients.

[0310] formula:

[0311]

[0312] Parameter meaning and acquisition method:

[0313] D ij : The jth operating parameter value of the ith device is obtained through the real-time monitoring system of the photovoltaic power station.

[0314] n: The total number of parameters, determined by the system settings and the types of parameters monitored.

[0315] H ik : The kth fault occurrence record of the ith device, obtained through historical fault data.

[0316] t ik : The duration of the kth fault of the ith device, obtained through historical fault data.

[0317] m: Total number of fault records, determined by historical fault data.

[0318] w1, w2, and w3: weight parameters, determined by expert experience or data fitting, used to balance the impact of each part on the health score.

[0319] δ1, δ2 and δ3: adjustment coefficients used to improve calculation accuracy and flexibility, determined by experimental data fitting and optimization algorithm.

[0320] T: Health score threshold, determined through expert experience or data analysis, used to evaluate the health status of the device.

[0321] Calculation example:

[0322] Assume that a device has five operating parameters, namely 30, 40, 35, 50, and 45.

[0323] Calculate the mean and standard deviation of the running parameters:

[0324]

[0325] Assume that a device has three fault records, the fault occurrence times are 3, 2, and 4, and the fault durations are 5, 4, and 6 hours, respectively.

[0326]

[0327] Assume that the weight parameters w1 = 0.5, w2 = 0.3, w3 = 0.2, and adjust the coefficient

[0328] δ1=1, δ2=0.1, δ3=0.2.

[0329]

[0330]

[0331] S i =0.5·4.96+0.3·0.32+0.2·0.19

[0332] S i =2.48+0.096+0.038

[0333] S i ≈2.614

[0334] Assume that the health score threshold T = 2.5.

[0335] Due to S i =2.614≥2.5, so it is assessed as a healthy state.

[0336] See also Figure 8 , the steps to obtain maintenance arrangement information are:

[0337] Based on the current health status information of the photovoltaic power station equipment, the formula is:

[0338]

[0339] Calculate maintenance priority and generate equipment maintenance priority;

[0340] Among them, P i represents the maintenance priority of the i-th device, S i represents the health score of the ith device, T represents the health score threshold, δ1 is the adjustment coefficient used to increase the flexibility of calculation, and α is the adjustment coefficient used to correct the impact of the health score;

[0341] Based on equipment maintenance priority and historical maintenance data, the formula is:

[0342]

[0343] Score the maintenance complexity of the equipment, adjust the planning of maintenance tasks according to the maintenance complexity score of the equipment, and generate a maintenance task plan;

[0344] Among them, C i represents the maintenance complexity score of the ith equipment, D ij represents the jth maintenance task of the i-th equipment, W j represents the weight of the jth task, R ij represents the resources available for the i-th device, δ2 is the adjustment coefficient used to increase the flexibility of calculation, and n represents the total number of maintenance tasks;

[0345] Based on maintenance task planning and combined with real-time monitoring data,

[0346]

[0347] Evaluate the total maintenance time, adjust the maintenance time and personnel allocation according to the total maintenance time, and generate maintenance schedule information;

[0348] Among them, T m represents the total maintenance time, C i represents the maintenance complexity score of the i-th equipment, P irepresents the priority of the ith device, β is the optimization coefficient used to adjust the calculation of maintenance time, m represents the total number of devices, and N represents the number of maintenance personnel.

[0349] formula:

[0350]

[0351] Parameter meaning and acquisition method:

[0352] S i : The health score of the ith device, calculated by the previous step.

[0353] T: health score threshold, obtained in the previous step and determined by expert experience or data analysis.

[0354] δ1: adjustment coefficient, used to increase the flexibility of calculation, determined by experimental data fitting and optimization algorithm.

[0355] α: Adjustment coefficient, used to correct the impact of health score, determined by experimental data fitting and optimization algorithm.

[0356] D ij : The jth maintenance task of the ith equipment is determined by historical maintenance data and expert experience.

[0357] W j : The weight of the jth task, determined by expert experience or data fitting.

[0358] R ij : The resources available for the ith device are determined by the device operation data and resource allocation plan.

[0359] δ2: Adjustment coefficient, used to increase the flexibility of calculation, determined by experimental data fitting and optimization algorithm.

[0360] β: Optimization coefficient, used to adjust the calculation of maintenance time, determined by the optimization algorithm.

[0361] m: Total number of equipment, determined through maintenance demand analysis. N: Number of maintenance personnel, determined through maintenance resource planning.

[0362] Calculation example:

[0363] Assume that the health score of a device is S i =6, health score threshold T=10, adjustment coefficient δ1=0.5, adjustment coefficient α=0.3.

[0364]

[0365] P i =0.38095×1.18≈0.45

[0366] Assume that a certain device has three maintenance tasks, namely 20, 15, and 25, with task weights of 0.5, 0.3, and 0.2 respectively, and available resources of 10, 15, and 20 respectively, and the adjustment coefficient δ2 = 0.2.

[0367]

[0368] Substitute the data and calculate:

[0369]

[0370] C i =0.9804+0.2961+0.2475≈1.524

[0371] Assume that there are 4 devices with maintenance complexity scores and maintenance priorities of C1=1.524, P1=0.45, C2=2.1, P2=0.35, C3=1.8, P3=0.5, C4=2.5, P4=0.4, the optimization coefficient β=1, and the number of maintenance personnel N=5.

[0372]

[0373] Substitute the data and calculate:

[0374]

[0375] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A photovoltaic operation and management system based on big data, characterized in that: The system comprises: The initial management module inputs user information and signs contracts based on the user's PV power station installation requirements, obtains PV power station design plans through the PV power station design platform, makes construction arrangements, and records the construction process of the PV power station, arranges completion inspections, and obtains initial inspection information; The intelligent dispatching module monitors the operation status of the photovoltaic power station in real time based on the initial inspection information, and calculates the power generation efficiency of the photovoltaic power station in combination with the historical power generation data and the current weather data, compares the power generation data with the grid demand, formulates matching power generation parameter adjustment measures, and obtains the target dispatching information; The dynamic inspection module, based on the target scheduling information, combines the real-time operation data, environmental data and historical fault location data of the photovoltaic power station to conduct fault risk assessment on the photovoltaic power station equipment, identify the high fault risk areas of the photovoltaic power station, formulate matching inspection paths, adjust the inspection time and personnel allocation, and obtain target inspection information; The maintenance optimization module analyzes the operation data of the photovoltaic power station in real time based on the target inspection information, combined with real-time monitoring data and historical fault data, evaluates the current health status of the photovoltaic power station equipment, formulates matching maintenance information, adjusts maintenance time and personnel arrangements, and obtains maintenance arrangement information.

2. The photovoltaic operation and management system based on big data according to claim 1 is characterized in that: The method for arranging the construction is as follows: Based on the installation requirements of the user's photovoltaic power station, according to the geographical location, installation area and azimuth parameters provided by the user, the photovoltaic power station design plan is obtained through the photovoltaic power station design platform, and the formula is used: Carry out preliminary allocation of construction resources and obtain preliminary allocation amount of resources; Among them, R i is the initial allocation of the i-th resource, A i is the installation area of ​​the ith installation area, θ i is the azimuth angle of the ith installation area, D i is the unit area allocation ratio of the i-th resource demand; Based on the preliminary allocation of the resources, combined with the geographical location and construction site conditions, the formula is: Adjust the allocation of construction resources to obtain the optimal allocation of resources; Among them, R i,opt is the optimal allocation of the i-th resource, R i is the initial allocation of the i-th resource, k1 is the weight coefficient of the geographical location, L i is the geographical location influencing factor of the ith installation area, is the average value of the influencing factor of the geographical location of the installation area, k2 is the weight coefficient of the construction conditions, C i is the construction condition influencing factor of the i-th installation area, is the average value of the factors affecting the construction conditions in the installation area; Based on the optimized allocation of the resource, compared with the actual available amount of the resource, the formula is: Calculate the sum of resource allocation deviations and compare the sum of resource allocation deviations with the preset tolerance threshold ∈. If the sum of resource allocation deviations is lower than the preset tolerance threshold ∈, the construction demand is met and the construction arrangement information is obtained. Where T is the sum of resource allocation deviations, n is the number of resource types, R i,opt is the optimal allocation of the i-th resource, R i,act is the actual available amount of the i-th resource.

3. The photovoltaic operation and management system based on big data according to claim 1 is characterized in that: The method for calculating the power generation efficiency of the photovoltaic power station is: Based on the real-time monitoring data of the photovoltaic power station, the real-time power generation energy data and the corresponding timestamp are extracted through the formula: Calculate real-time power generation data; Among them, P t is the real-time power generation at time t, E t is the power generation energy at time t, T t is the time length of time t, k1 is the real-time adjustment coefficient, and k2 is the time square root adjustment coefficient; Based on the real-time power generation data, combined with historical power generation data and current weather data, the formula is: P theo,t =S t ×H t ×η×(1+k3×cos(α)) Calculate the theoretical power generation data of photovoltaic power stations; Among them, P theo,t is the theoretical power generation at time t, S t is the solar radiation intensity at time t, H t is the illumination time of time t, η is the theoretical conversion efficiency of the photovoltaic power station, k3 is the solar radiation adjustment coefficient, and α is the solar incident angle; Based on the theoretical power generation data and the real-time power generation data, the formula is: Calculate the power generation efficiency of photovoltaic power plants; Among them, η t is the power generation efficiency at time t, P t is the real-time power generation at time t, P theo,t is the theoretical power generation at time t, ∈ is a constant term.

4. The photovoltaic operation and management system based on big data according to claim 3 is characterized in that: The steps for obtaining the target scheduling information are as follows: Based on the power generation efficiency of the photovoltaic power station, compared with the grid demand, the formula is: Calculate grid demand satisfaction; Among them, D t is the grid demand satisfaction at time t, η t is the power generation efficiency at time t, N t is the grid demand at time t, ∈ is a constant term; Based on the grid demand satisfaction, combined with current weather data and historical power generation data, the formula is: Calculate optimal scheduling parameters; Among them, O t To optimize the scheduling parameters, P t is the real-time power generation at time t, W t is the current weather impact factor at time t, is the historical average weather impact factor, k4 is the weather adjustment coefficient; Based on the optimization scheduling parameters and the grid demand satisfaction, the formula is: Calculate the target dispatch parameters and formulate matching power generation parameter adjustment measures to obtain target dispatch information; Among them, M t is the target scheduling parameter at time t, O t is the optimal scheduling parameter at time t, D t is the grid demand satisfaction at time t.

5. The photovoltaic operation and management system based on big data according to claim 1 is characterized in that: The method for identifying high failure risk areas of a photovoltaic power station is: Based on the target scheduling information, the real-time operation data of the current photovoltaic power station is obtained through the formula: Calculate the initial risk value R1 i , conduct preliminary risk assessments of multiple areas of the PV plant; Among them, R1 i represents the initial risk value of the ith region, w j represents the weight coefficient of the jth parameter, D ij represents the jth parameter data of the i-th region, and n represents the total number of parameters; Based on the preliminary risk value R1 i , combined with historical fault location data, through the formula: Calculate the adjusted risk value R2 i ; Among them, R2 i represents the adjusted risk value of the ith region, F k represents the kth historical fault frequency coefficient, H ik represents the kth historical fault data of the i-th area, and m represents the total number of historical fault data; Based on the adjusted risk value R2 i , compared with the preset risk threshold T, if R2 i ≥T, the area is marked as a high failure risk area and a high failure risk area mark is generated.

6. The photovoltaic operation and management system based on big data according to claim 5 is characterized in that: The steps for obtaining the target inspection information are as follows: Based on the high failure risk area marking, the formula is: Sum the risk correlations of high fault risk areas, calculate the matching scores of inspection paths, formulate inspection paths, and generate preliminary inspection paths; Among them, P i represents the matching score of the i-th inspection path, R ij represents the risk association between the ith region and the jth high failure risk region, α and β are adjustment parameters, and n represents the total number of high failure risk regions. Based on the preliminary inspection path, combined with the real-time operation data and environmental data of the photovoltaic power station equipment, the formula is: T i =P i ·(1+E i )·γ Calculate and optimize inspection time; Among them, T i represents the optimized inspection time of the ith high fault risk area, E i represents the environmental impact factor of the ith region, and γ is the optimization coefficient. Based on the preliminary inspection path and the optimized inspection time, the inspection personnel allocation is adjusted to obtain target inspection information.

7. The photovoltaic operation and management system based on big data according to claim 1 is characterized in that: The method for evaluating the current health status of photovoltaic power station equipment is: Based on real-time monitoring data, through the formula: Calculate the mean and standard deviation of equipment operating parameters and generate statistical values ​​of equipment operating parameters; Among them, μ i represents the mean value of the operating parameters of the ith device, σ i represents the standard deviation of the operating parameters of the ith device, D ij represents the jth operating parameter value of the i-th device, and n represents the total number of parameters; Based on the statistical values ​​of the equipment operating parameters and the historical fault data, the formula is: Calculate the fault frequency and fault duration, and generate fault characteristic parameters; Among them, F i represents the failure frequency of the ith device, T i represents the fault duration of the ith device, H ik represents the kth fault occurrence record of the ith device, t ik represents the duration of the kth fault of the i-th device, and m represents the total number of fault records; Based on the statistical values ​​of the equipment operating parameters and the fault characteristic parameters, the formula is: Calculate the health score of the equipment and compare the health score of the equipment with the preset health score threshold T. When the health score is greater than or equal to the health score threshold, it is evaluated as a healthy state, and the current health status information of the photovoltaic power station equipment is obtained; Among them, S i represents the health score of the ith device, μ i represents the mean value of the operating parameters of the ith device, σ i represents the standard deviation of the operating parameters of the ith device, F i represents the failure frequency of the ith device, T i represents the fault duration of the i-th device, w1, w2 and w3 represent weight parameters, and δ1, δ2 and δ3 are adjustment coefficients.

8. The photovoltaic operation and management system based on big data according to claim 7 is characterized in that: The steps for obtaining the maintenance schedule information are as follows: Based on the current health status information of the photovoltaic power station equipment, the formula is: Calculate maintenance priority and generate equipment maintenance priority; Among them, P i represents the maintenance priority of the i-th device, S i represents the health score of the ith device, T represents the health score threshold, δ1 is the adjustment coefficient, and α is the adjustment coefficient; Based on the equipment maintenance priority and historical maintenance data, the formula is: Score the maintenance complexity of the equipment, adjust the planning of maintenance tasks according to the maintenance complexity score of the equipment, and generate a maintenance task plan; Among them, C i represents the maintenance complexity score of the i-th equipment, D ij represents the jth maintenance task of the i-th equipment, W j represents the weight of the jth task, R ij represents the resources available for the i-th device, δ2 is the adjustment coefficient, and n represents the total number of maintenance tasks; Based on the maintenance task plan, combined with real-time monitoring data, Evaluate the total maintenance time, adjust the maintenance time and personnel allocation according to the total maintenance time, and generate maintenance schedule information; Among them, T m represents the total maintenance time, C i represents the maintenance complexity score of the i-th equipment, P i represents the priority of the ith device, β is the optimization coefficient, m represents the total number of devices, and N represents the number of maintenance personnel.

Images