A smart photovoltaic production operation and maintenance management method and system

Abstract

The present invention discloses a method and system for intelligent photovoltaic production operation and maintenance management, which relates to the field of big data analysis technology, including building a system architecture, collecting station data; identifying abnormal non-alarm data through discrete rate analysis, and judging the fault type through a decision tree algorithm; and realizing operation and maintenance function management based on data analysis. The method described in the present invention realizes unmanned or less-manned duty of photovoltaic stations through technical means such as drone inspections and big data analysis, reduces labor costs, and improves operation and maintenance efficiency; judges the fault type through discrete rate analysis and decision tree algorithms, timely discovers and solves equipment failures, and avoids power generation losses caused by failures; conducts in-depth mining of station data through a variety of data analysis methods, optimizes operation strategies, and improves power generation efficiency; and improves the scalability and flexibility of the system through a microservice architecture with front-end and back-end separation.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and specifically to a smart photovoltaic production operation and maintenance management method and system. Background Art

[0002] In recent years, in the field of new energy photovoltaic power generation, with the opening of a favorable market environment, the number and scale of newly built photovoltaic power stations have increased year by year. However, there are still many problems in the development of the photovoltaic power generation industry, especially the operation and maintenance management of photovoltaic power stations under the jurisdiction of power generation companies after they are put into operation.

[0003] At present, most domestic photovoltaic enterprises still use the traditional production and operation and maintenance management mode. The operation and maintenance management level is difficult to meet the unmanned and undermanned operation and operation and maintenance management requirements of photovoltaic power stations. The production management capabilities of photovoltaic power stations of various photovoltaic power generation enterprise groups are insufficient, the power generation efficiency of photovoltaic power stations is low, and the production safety and efficient operation of power generation enterprises are difficult to obtain reliable guarantees. There is a lack of production and operation and maintenance platforms and functional applications for photovoltaic sites, and no applications related to automatic data collection, big data analysis, equipment fault diagnosis and predictive maintenance are adopted. The operation of photovoltaic sites mainly relies on human monitoring, operation decisions rely on conventional reports, and operation and maintenance rely on manual inspections. On-site duty personnel face the common problems of poor working environment, high inspection intensity and low work efficiency. With the development of drone intelligent inspection flight, intelligent image recognition, big data analysis and artificial intelligence technology, the use of intelligent equipment and digital technology, and the use of intelligent production and operation information management system to realize unmanned and undermanned inspection and operation of photovoltaic sites have become a research hotspot and industry technology and development direction at home and abroad. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: the existing photovoltaic station operation and maintenance management methods are inefficient, lack intelligence and automation, and have limited data processing and analysis capabilities, as well as how to improve the operating efficiency of photovoltaic stations and realize intelligent and automated management of photovoltaic stations.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a smart photovoltaic production operation and maintenance management method, including building a system architecture and collecting site data; identifying abnormal non-alarm data through discrete rate analysis and determining the fault type through a decision tree algorithm; and realizing operation and maintenance function management based on data analysis.

[0007] As a preferred solution of the smart photovoltaic production operation and maintenance management method described in the present invention, the system architecture is constructed by adopting a front-end and back-end separation architecture, the front-end adopts the react technology stack, and the back-end adopts SpringCloudAlibaba as the basic framework.

[0008] As a preferred solution of the smart photovoltaic production operation and maintenance management method described in the present invention, wherein: the collection of site data includes using a multispectral camera carried by a drone to conduct inspections, collect image data, and obtain drone inspection data through image segmentation and labeling; collecting site equipment and booster station equipment data through an edge gateway and a data acquisition device; the system processes the data after receiving the data; the system records the data generated by the site, and before using or storing the data, screens the data and removes unnecessary data with obvious errors; data storage includes using sharding technology to perform horizontal slicing according to the site and vertical slicing according to time, and storing the sliced ​​data in a database; the system stores the equipment data in different database instances through Mysql+ShadingSphere sub-library and table slicing; the database instance includes historical data and near real-time data.

[0009] As a preferred solution of the smart photovoltaic production operation and maintenance management method described in the present invention, the abnormal non-alarm data includes evaluating the operation stability of the photovoltaic string branch through discrete rate analysis, assuming that N is the total number of photovoltaic strings, , discrete rate It is expressed as:

[0010] ,

[0011] in, represents the power of the nth string at time t, It represents the average power output of the string at time t. The average power calculation formula is expressed as:

[0012] ,

[0013] when Value ≤ Threshold When , it means that the power output of the strings is relatively concentrated at time t, and the system operates stably; when Value > Threshold When , it means that the power output difference between the strings is large and the system is unstable.

[0014] As a preferred solution of the smart photovoltaic production operation and maintenance management method of the present invention, the fault type determination includes processing the data through a data processing algorithm, converting the data into an analyzable data structure, generating readable rules and decision trees using an inductive algorithm, and analyzing the data using a decision, which is expressed as:

[0015] ,

[0016] in, Represents the photovoltaic string fault assessment index, Indicates The actual power of each string, Indicates the rated power of the string. Indicates The actual irradiance of each string, represents the reference irradiance of the string, Indicates the total number of PV strings; when When , it indicates that the string power and irradiance are consistent with the expected values ​​and there is no fault; when When , it means that the string power decreases more seriously than the irradiance decreases, and there is an inefficiency fault; when When , it means that the irradiance of the string drops more seriously than the power drops, and there is a shading problem.

[0017] As a preferred solution of the smart photovoltaic production operation and maintenance management method described in the present invention, the data analysis includes system efficiency analysis, segment loss analysis, equipment comparison analysis, irradiation power consistency analysis, light resource comparison analysis, and inverter comparison analysis.

[0018] As a preferred solution of the smart photovoltaic production operation and maintenance management method described in the present invention, wherein: the implementation of operation and maintenance function management includes realizing operation functions on the company side, realizing operation and maintenance functions on the station side, and realizing mobile approval functions through mobile applications; the company side operation functions include company cockpit, regional dashboard, station monitoring, three-dimensional visualization, operation benchmarking analysis, performance appraisal analysis, power generation plan appraisal, power generation efficiency appraisal and operating cost appraisal; the station side operation and maintenance functions include station monitoring, operation management, equipment management, material management, safety management, and daily office.

[0019] Another object of the present invention is to provide a smart photovoltaic production operation and maintenance management system, which can realize operation and maintenance management functions and mobile approval functions through a microservice architecture with separated front-end and back-end, thereby solving the problems of low efficiency, lack of intelligence and automation in the existing technology.

[0020] As a preferred solution of the smart photovoltaic production operation and maintenance management system described in the present invention, it includes: a data acquisition module, a fault judgment module, and an operation and maintenance management module; the data acquisition module is used to build a system architecture and collect site data; the fault judgment module is used to identify abnormal non-alarm data through discrete rate analysis, and to determine the fault type through a decision tree algorithm; the operation and maintenance management module is used to implement operation and maintenance function management based on data analysis.

[0021] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a smart photovoltaic production operation and maintenance management method.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a smart photovoltaic production operation and maintenance management method.

[0023] Beneficial effects of the present invention: The intelligent photovoltaic production operation and maintenance management method provided by the present invention realizes unmanned or less-manned photovoltaic stations through technical means such as drone inspection and big data analysis, reduces labor costs, and improves operation and maintenance efficiency; the discrete rate analysis and decision tree algorithm are used to judge the fault type, and equipment failures are discovered and solved in time to avoid power generation losses caused by failures; a variety of data analysis methods are used to deeply mine the station data, optimize the operation strategy, and improve the power generation efficiency; the microservice architecture with front-end and back-end separation is used to improve the scalability and flexibility of the system; the automatic data collection, analysis and processing reduce manual intervention and improve management efficiency; the mobile terminal approval function facilitates operation and maintenance personnel to handle work anytime and anywhere, and improves work efficiency. The present invention has achieved better results in improving operation and maintenance efficiency, automation, and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 An overall flow chart of a smart photovoltaic production operation and maintenance management method provided for the first embodiment of the present invention.

[0026] Figure 2 A data panel diagram in a company-side area dashboard interface of a smart photovoltaic production operation and maintenance management method provided in the second embodiment of the present invention.

[0027] Figure 3An overall flow chart of a smart photovoltaic production operation and maintenance management system provided for the third embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a smart photovoltaic production operation and maintenance management method, including:

[0030] S1: Build system architecture and collect site data.

[0031] Furthermore, the system architecture is built by using a front-end and back-end separation architecture, with the front-end using the react technology stack and the back-end using SpringCloudAlibaba as the basic framework.

[0032] It should be noted that collecting site data includes using multispectral cameras carried by drones to conduct inspections, collect image data, and obtain drone inspection data through image segmentation and labeling; collecting site equipment and booster station equipment data through edge gateways and data acquisition devices; the system processes the data after receiving it; the system records the data generated by the site, and filters the data before using or storing it, and removes unnecessary data with obvious errors; data storage includes using sharding technology to perform horizontal segmentation according to the site and vertical segmentation according to time, and storing the segmented data in the database; the system uses Mysql+ShadingSphere to divide the equipment data into different database instances; the database instance includes historical data and near real-time data.

[0033] It should also be noted that data processing includes validity checks on measured values, validity checks on telesignal quantities, and false telesignal processing.

[0034] Effective checks on measured values ​​include data filtering, zero drift processing, limit checking, dead zone setting, multi-source data processing, correlation testing, mean and standard deviation testing, etc.

[0035] The purpose of checking the validity of telesignal quantities and handling false telesignals is to correctly judge and upload accident telesignal changes and normal operation telesignal changes.

[0036] S2: Identify abnormal data without warning through discrete rate analysis and determine the fault type through decision tree algorithm.

[0037] Furthermore, the abnormal non-alarm data includes evaluating the operational stability of the PV string branch through discrete rate analysis. Let N be the total number of PV strings, , discrete rate It is expressed as:

[0038] ,

[0039] in, represents the power of the nth string at time t, It represents the average power output of the string at time t. The average power calculation formula is expressed as:

[0040] ,

[0041] when Value ≤ Threshold When , it means that the power output of the strings is relatively concentrated at time t, and the system operates stably; when Value > Threshold When , it means that the power output difference between the strings is large and the system is unstable.

[0042] It should be noted that determining the fault type includes processing the data through a data processing algorithm, converting the data into an analyzable data structure, generating readable rules and decision trees using an inductive algorithm, and analyzing the data using a decision tree, which can be expressed as:

[0043] ,

[0044] in, Represents the photovoltaic string fault assessment index, Indicates The actual power of each string, Indicates the rated power of the string. Indicates The actual irradiance of each string, represents the reference irradiance of the string, Indicates the total number of PV strings; when When , it indicates that the string power and irradiance are consistent with the expected values ​​and there is no fault; when When , it means that the string power decreases more seriously than the irradiance decreases, and there is an inefficiency fault; when When , it means that the irradiance of the string drops more seriously than the power drops, and there is a shading problem.

[0045] S3: Realize operation and maintenance function management based on data analysis.

[0046] Furthermore, data analysis includes system efficiency analysis, segment loss analysis, equipment comparison analysis, irradiated power consistency analysis, optical resource comparison analysis, and inverter comparison analysis.

[0047] It should be noted that the realization of operation and maintenance function management includes realizing operation functions on the company side, realizing operation and maintenance functions on the station side, and realizing mobile approval functions through mobile applications; the operation functions on the company side include the company cockpit, regional dashboards, station monitoring, three-dimensional visualization, operation benchmarking analysis, performance appraisal analysis, power generation plan appraisal, power generation efficiency appraisal and operating cost appraisal; the operation and maintenance functions on the station side include station monitoring, operation management, equipment management, material management, safety management, and daily office work.

[0048] It should also be noted that the regional dashboard presents important information about the power station that the power station personnel are concerned about, and actively and promptly reminds users when an abnormality occurs in the power station; the content presented in the regional dashboard includes the completion of the online power plan, actual power, installed capacity and power station statistics, the power station capacity of each power station under the regional center, real-time power, daily power generation, monthly power generation, cumulative power generation, environmental parameters, etc.

[0049] It should also be noted that three-dimensional visualization is based on the big data resources of the production operation intelligent management system. Combined with the interactive display effects in the virtual three-dimensional scene, it provides a convenient and easy-to-use human-computer interaction method, and can perform all-round visual management of statistical data, personnel data, equipment data, etc. during the operation process.

[0050] It should also be noted that site monitoring includes power station-level monitoring, primary main wiring diagram monitoring, photovoltaic array monitoring, box transformer monitoring, inverter monitoring, string monitoring, power forecast data, etc.; material management includes material categories, storage locations, material items, supplier management, procurement management, inventory management; safety management includes production safety goals, organizational structure and responsibilities, laws, regulations and system management, education and training, hidden danger investigation and control, emergency management, etc.; intelligent analysis includes system efficiency, segmented loss, equipment comparison, discrete rate diagnosis, inefficiency diagnosis, box transformer heat dissipation abnormality, and string shading analysis; daily office includes document management, task management, notification announcements, plan management, employee management, and team management included in daily office.

[0051] It should also be noted that the operational benchmarking analysis is to find the gaps and causes by comparing the equivalent utilization hours, system efficiency, conversion efficiency, failure rates of various equipment, etc. with benchmark power stations; the performance appraisal analysis is to formulate ideal standards through personnel appraisal, indicator appraisal, operation appraisal, knowledge appraisal and other means, clarify the target status, clarify the gaps, and find out the causes; the power generation plan appraisal is to formulate the power generation plan for the year, such as monthly planned power generation and annual planned power generation, and analyze and appraise the completion of the power generation situation; the power generation efficiency assessment is to statistically analyze the power generation efficiency of the current subordinate power stations, to view the power generation efficiency comparison of the power stations connected to the grid in the same year, and to analyze and appraise the power generation efficiency; the operating cost assessment is to conduct statistical analysis by fully recording the three major categories of costs of each power station: labor cost, operation and maintenance cost, and management cost.

[0052] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides a smart photovoltaic production operation and maintenance management method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0053] like Figure 2 The figure shows a specific simulation example. The figure shows a group-level large-screen interface of a regional dashboard. The content in the figure presents important information about the power station that the power station personnel are concerned about, reflecting the intelligence and automation of the centralized maintenance center. The content in the figure presents the completion of the online power plan, actual power, installed capacity and power station statistics as well as social contribution.

[0054] This simulation embodiment not only realizes real-time monitoring and remote management of photovoltaic station data, greatly improves the level of intelligent management and realizes predictive maintenance, but also reduces manpower requirements and improves management efficiency through automated and intelligent management, effectively solving the problems of low efficiency, lack of intelligence and automation in existing photovoltaic station operation and maintenance management methods.

[0055] Example 3, reference Figure 3 , which is an embodiment of the present invention, provides a smart photovoltaic production operation and maintenance management system, including a data acquisition module, a fault judgment module, and an operation and maintenance management module.

[0056] The data acquisition module is used to build the system architecture and collect site data; the fault judgment module is used to identify abnormal non-alarm data through discrete rate analysis and determine the fault type through the decision tree algorithm; the operation and maintenance management module is used to implement operation and maintenance function management based on data analysis.

[0057] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0058] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0059] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0060] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logical function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A smart photovoltaic production operation and maintenance management method, characterized in that: include: Build system architecture and collect station data; Identify abnormal data without warning through discrete rate analysis, and determine the fault type through decision tree algorithm; Realize operation and maintenance function management based on data analysis; Determining the fault type includes processing the data through a data processing algorithm, converting the data into an analyzable data structure, using an inductive algorithm to generate readable rules and decision trees, and using decisions to analyze the data, expressed as: Among them, F(P,T,I) represents the photovoltaic string fault assessment index, P n Indicates the actual power of the nth string, P nom Indicates the rated power of the string, I n Indicates the actual irradiance of the nth string, I ref represents the reference irradiance of the string, and N represents the total number of photovoltaic strings; When F(P,T,I)≈0, it means that the string power and irradiance are consistent with the expected values ​​and there is no fault; When F(P,T,I)>0, it means that the string power decrease is more serious than the irradiance decrease, and there is an inefficiency fault; When F(P,T,I)<0, it means that the irradiance of the string decreases more seriously than the power decreases, and there is a shading problem; Data analysis includes system efficiency analysis, segment loss analysis, equipment comparison analysis, irradiation power consistency analysis, optical resource comparison analysis, and inverter comparison analysis; The realization of operation and maintenance function management includes the realization of operation functions on the company side, the realization of operation and maintenance functions on the station side, and the realization of mobile terminal approval functions through mobile applications; The company-side operation functions include company cockpit, regional dashboard, station monitoring, 3D visualization, operation benchmarking analysis, performance evaluation analysis, power generation plan evaluation, power generation efficiency evaluation and operation cost evaluation; The operation and maintenance functions on the station side include station monitoring, operation management, equipment management, material management, safety management, and daily office work.

2. The smart photovoltaic production operation and maintenance management method according to claim 1, characterized in that: The construction system architecture includes that the system adopts a front-end and back-end separation architecture, the front-end adopts the react technology stack, and the back-end adopts SpringCloudAlibaba as the basic framework.

3. The smart photovoltaic production operation and maintenance management method according to claim 2, characterized in that: The collecting of site data includes using a multispectral camera carried by a drone to conduct inspections, collect image data, and obtain drone inspection data through image segmentation and labeling; Collect data from field station equipment and booster station equipment through edge gateways and data acquisition devices; After receiving the data, the system processes the data; The system generates data at the recording station and screens the data before using or storing it, removing unnecessary data with obvious errors; Data storage includes using sharding technology to perform horizontal sharding based on stations and vertical sharding based on time, and storing the sharded data in a database; The system uses Mysql+ShadingSphere to distribute and store device data in different database instances; The database instance includes historical data and near real-time data.

4. The smart photovoltaic production operation and maintenance management method according to claim 3, characterized in that: The abnormal non-alarm data includes evaluating the operation stability of the photovoltaic string branch through discrete rate analysis. Let N be the total number of photovoltaic strings, D(t) be the discrete rate at time t, and the discrete rate D(t) be expressed as: Among them, P n (t) represents the power of the nth string at time t, It represents the average power output of the string at time t. The average power calculation formula is expressed as: When the D(t) value is ≤ the threshold δ, it means that the power output of the strings is relatively concentrated at time t and the system operates stably; When the D(t) value is greater than the threshold δ, it indicates that the power output differences between the strings are large and the system is unstable.

5. A system using the intelligent photovoltaic production operation and maintenance management method according to any one of claims 1 to 4, characterized in that: Including data acquisition module, fault diagnosis module, operation and maintenance management module; The data acquisition module is used to build a system architecture and collect station data; The fault judgment module is used to identify abnormal non-alarm data through discrete rate analysis and determine the fault type through a decision tree algorithm; The operation and maintenance management module is used to implement operation and maintenance function management based on data analysis.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the smart photovoltaic production operation and maintenance management method described in any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the smart photovoltaic production operation and maintenance management method described in any one of claims 1 to 4 is implemented.

Images