Photovoltaic inverter data acquisition control system
By designing the photovoltaic inverter data acquisition control system, using intelligent algorithms and deep learning technology for fault detection and diagnosis, the problems of low fault processing efficiency and insufficient user interface functions in the existing technology are solved, real-time data display and automated faults are realized The processing improves the stability and user experience of the system.
Patent Information
- Application Number
- CN202411108219.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-26
AI Technical Summary
Existing photovoltaic inverters are inefficient in fault detection and processing, with limited user interface functions, making it difficult to realize real-time data display and efficient interaction, resulting in long troubleshooting time and difficulty for non-professional personnel to interpret error codes.
A photovoltaic inverter data acquisition control system is designed, including data acquisition and processing module, fault detection and diagnosis module, control execution module, user interface module and power management module. It uses intelligent algorithms to detect and diagnose faults to provide intuitive users Interface and automation parameter adjustment, deep learning algorithms and CNN are used to identify fault types, and remote monitoring and fault notification are realized through communication modules.
Real-time data acquisition and processing, fast and accurate fault detection and diagnosis, automatic adjustment of operating parameters, improve system maintenance efficiency and user experience, ensure the stable operation of the system and fault prevention, and shorten the fault response time.
Smart Images

Figure CN119030134A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of power supply systems, and more specifically, particularly relates to a photovoltaic inverter data acquisition and control system. Background Art
[0002] With the growing global demand for renewable energy, solar power generation has become one of the important ways to obtain energy. As the core component of the solar power generation system, the photovoltaic inverter is responsible for converting the direct current generated by the solar panels into alternating current that can be used in homes or industries. Therefore, its performance and reliability are crucial to the stable operation of the entire system. Among the many indicators for evaluating inverter performance, fault detection, diagnosis and processing capabilities, as well as the intuitiveness and ease of use of the user interface are key factors in measuring its practicality.
[0003] Most existing photovoltaic inverters use the traditional fault handling method, which is to shut down and display an error code when a fault occurs, and then professionals need to manually check the inverter according to the code to locate and solve the problem. This method is not only time-consuming and labor-intensive, but also difficult for non-professionals to interpret the error code, resulting in low fault handling efficiency and prolonged system recovery time.
[0004] In addition, although existing photovoltaic inverters are generally equipped with user interface modules, these interfaces often only provide basic information display and simple control functions, lacking intuitive display of real-time data and efficient interactive capabilities. It is difficult for users to quickly understand the real-time status and historical data of the system through these interfaces, let alone perform complex parameter adjustments or troubleshooting. Therefore, we propose a photovoltaic inverter data acquisition and control system. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and propose a photovoltaic inverter data acquisition and control system. The system optimizes operating parameters through an intelligent algorithm, and presents real-time status and historical data in an intuitive manner through a user interface module. At the same time, it provides simple operation buttons and touch screen operations, thereby improving the system maintenance efficiency and user experience.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] A photovoltaic inverter data acquisition and control system, comprising:
[0008] Data acquisition and processing module, used to collect voltage, current, power and temperature operating parameters of photovoltaic inverters in real time;
[0009] The fault detection and diagnosis module monitors the operating data of the photovoltaic inverter in real time and uses intelligent algorithms to quickly and accurately detect and diagnose potential equipment faults;
[0010] The control execution module automatically adjusts the operating parameters of the photovoltaic inverter according to the analysis results of the data processing module and the fault detection and diagnosis module to optimize its performance and prevent the occurrence of faults;
[0011] The communication module uses standard communication protocols such as Modbus or CAN to realize data exchange and communication between the photovoltaic inverter data acquisition control system and the remote monitoring center or other equipment;
[0012] The user interface module provides an intuitive display screen and operation buttons, allowing users to easily view the real-time operating status, historical data and fault information of the PV inverter, and perform simple operations and settings;
[0013] The power management module ensures the stable power supply of the photovoltaic inverter data acquisition control system. At the same time, when the photovoltaic inverter is powered off, it can use the backup power supply to maintain the normal operation of the system.
[0014] Preferably, the data acquisition and processing module has a built-in preprocessing module, and the preprocessing module filters and normalizes the collected data to reduce the impact of noise and improve data quality;
[0015] The filtering of the collected data adopts the following calculation formula:
[0016] x k =A k x k-1 +B k u k +w k
[0017] z k =H k x k +v k ;
[0018] In the formula, x k is the state vector, A k is the state transition matrix, u k is the control vector, B k is the control matrix, w k is the process noise, z k is the observation vector, H k is the observation matrix, v k is the observation noise;
[0019] In the filtering process of the collected data, according to the above calculation formula, it is obtained that:
[0020] The state prediction calculation formula is:
[0021] The covariance prediction calculation formula is:
[0022] The gain calculation formula is:
[0023] The state update calculation formula is:
[0024] The covariance update calculation formula is:
[0025] In the above formula, is the state estimate at time k, is the estimated error covariance matrix at time k, K k is the gain, Q k is the process noise covariance matrix, R k is the observation noise covariance matrix and I is the identity matrix.
[0026] Preferably, the fault detection and diagnosis module interacts with the data acquisition and processing module, including:
[0027] Intelligent detection and diagnosis algorithm unit, which is configured based on data-driven deep learning algorithm and CNN fusion long short-term memory network to process data and identify fault types and their causes;
[0028] The fault data set construction and processing unit is responsible for constructing a comprehensive fault data set and performing data cleaning, preprocessing, and enhancement to improve the accuracy and generalization ability of fault detection;
[0029] The fault location and notification unit is used to quickly and accurately locate the fault location when a fault is detected, and to send fault notifications to the operation and maintenance personnel in a timely manner through the integrated communication interface.
[0030] Preferably, the data-driven deep learning algorithm in the intelligent detection and diagnosis algorithm unit is composed of several groups of unsupervised neural networks. By learning the potential representation of the input data, the features of the input data can be extracted. At the same time, through training, the likelihood probability of the input data can be maximized. The expression is:
[0031]
[0032] In the formula, v and h represent the states of the visible layer and the hidden layer respectively, and w ij represents the connection weight between two layers, a i and b j Represent the bias of the visible layer and the hidden layer respectively;
[0033] Data-driven deep learning algorithms initialize network parameters by pre-training unsupervised neural networks layer by layer, and then fine-tune them to optimize the performance of the entire network.
[0034] Preferably, the specific working process of the fault location and notification unit is as follows:
[0035] 1) Analyze the fault code and alarm information provided by the inverter to preliminarily determine the fault type and possible location;
[0036] 2) Check the detailed alarm information and fault location data, and manually determine the possible fault location;
[0037] 3) Manually check the photovoltaic strings one by one, check whether the components, connectors, optimizers, etc. are damaged or have poor contact, and confirm the source of the fault.
[0038] Preferably, the fault location and notification unit further includes determining the fault priority. When a plurality of groups of photovoltaic inverters have fault alarms at the same time, the priority level is determined, and the fault with the highest priority is processed first. The specific priority score is calculated as follows:
[0039] (Severity×40%)+(Occurrence×30%)+(Difficulty×30%);
[0040] In the formula, Severity is the severity score of the fault, ranging from 1 to 10, 10 represents the highest severity, Occurrence is the frequency of the fault, the number of times the PV inverter fault occurred in the past year as a cycle, and Difficulty is the difficulty of handling, ranging from 1 to 10, 1 represents the lowest difficulty of handling, and 10 represents the highest difficulty of handling.
[0041] Preferably, the control execution module includes: a parameter adjustment unit, a fault prevention unit and a fault processing unit;
[0042] The parameter adjustment unit automatically adjusts the operating parameters of the inverter according to the analysis results of the data processing module and the fault detection and diagnosis module. At the same time, it can also optimize the performance of the inverter, ensure that it operates at the optimal working point, and improve the power generation efficiency.
[0043] Preferably, the fault prevention unit is used to implement preventive measures, including soft start, overcurrent protection and fault code analysis, to avoid the occurrence of faults;
[0044] The fault handling unit is used to quickly start a preset fault handling procedure when a fault occurs, including restart, derating operation or safe shutdown, and guide the operation and maintenance personnel to quickly locate and repair the fault.
[0045] A photovoltaic inverter data acquisition and control system according to claim 1, characterized in that the user interface module comprises:
[0046] A display screen is used to display the real-time operating status of the photovoltaic inverter. The display screen can also present historical data and fault records to help users understand the long-term operation of the system;
[0047] Operation button: allows users to perform basic operations on the inverter through physical buttons, including starting, stopping, and parameter setting;
[0048] Communication unit: including bus, serial port and other communication methods, responsible for transmitting data and commands between the inverter and the remote monitoring system.
[0049] The photovoltaic inverter data acquisition and control system provided by the present invention has the following advantages compared with the prior art:
[0050] Real-time data acquisition and processing: The system can collect key operating parameters of photovoltaic inverters in real time, and perform data cleaning and normalization through the built-in pre-processing module to improve data accuracy and reliability;
[0051] Intelligent fault detection and diagnosis: The system can quickly and accurately detect and diagnose potential equipment failures, improving fault handling efficiency and system stability;
[0052] Automatic adjustment and optimization of performance: The control execution module automatically adjusts the inverter operating parameters according to the data analysis results, optimizes the performance, ensures that the system operates at the best working point, and improves power generation efficiency;
[0053] Fault prevention and timely handling: The system implements preventive measures to avoid faults and quickly starts the preset handling procedures when faults occur to reduce the impact of faults on the system;
[0054] Intuitive user interface: The user interface module provides an intuitive display screen and operation buttons, allowing users to easily view real-time operating status, historical data and fault information, and perform simple operations and settings;
[0055] Stable power supply and backup power supply: The power management module ensures stable power supply of the system and uses backup power supply to keep the system running in case of power outage, ensuring system continuity and reliability;
[0056] Fault location and notification: The fault location and notification unit can quickly and accurately locate the fault location, and send fault notifications to operation and maintenance personnel in a timely manner through the communication interface, shortening the fault response time;
[0057] Fault priority determination: The system can prioritize faults in multiple groups of photovoltaic inverters to ensure that the most serious faults are handled first, thereby improving fault management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] Figure 1 This is the architecture diagram of the photovoltaic inverter data acquisition control system of the present invention;
[0059] Figure 2 This is a specific working flow chart of the fault location and notification unit of the present invention. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0061] The present invention provides a photovoltaic inverter data acquisition control system, such as Figure 1 include:
[0062] The data acquisition and processing module is used to collect the voltage, current, power and temperature operating parameters of the photovoltaic inverter in real time; the data acquisition and processing module has a built-in preprocessing module, which filters and normalizes the collected data to reduce the impact of noise and improve data quality;
[0063] The collected data is filtered using the following calculation formula:
[0064] x k =A x x k-1 +B k u k +w k
[0065] z k =H k x k +vk;
[0066] In the formula, x k is the state vector, A k is the state transition matrix, u k is the control vector, B k is the control matrix, w k is the process noise, z k is the observation vector, H k is the observation matrix, v k is the observation noise;
[0067] In filtering the collected data, according to the above calculation formula, it is obtained:
[0068] The state prediction calculation formula is:
[0069] The covariance prediction calculation formula is:
[0070] The gain calculation formula is:
[0071] The state update calculation formula is:
[0072] The covariance update calculation formula is:
[0073] In the above formula, is the state estimate at time k, is the estimated error covariance matrix at time k, K k is the gain, Q k is the process noise covariance matrix, R k is the observation noise covariance matrix and I is the identity matrix.
[0074] The fault detection and diagnosis module monitors the operating data of the photovoltaic inverter in real time and uses intelligent algorithms to quickly and accurately detect and diagnose potential equipment faults. The fault detection and diagnosis module interacts with the data acquisition and processing module, including:
[0075] Intelligent detection and diagnosis algorithm unit, which is configured based on data-driven deep learning algorithm and CNN fusion long short-term memory network to process data and identify fault types and their causes;
[0076] The fault data set construction and processing unit is responsible for constructing a comprehensive fault data set and performing data cleaning, preprocessing, and enhancement to improve the accuracy and generalization ability of fault detection;
[0077] The fault location and notification unit is used to quickly and accurately locate the fault position when a fault is detected, and send a fault notification to the operation and maintenance personnel in a timely manner through the integrated communication interface; the fault location and notification unit also includes the determination of fault priority. When several groups of photovoltaic inverters have fault alarms at the same time, the priority level is determined and the fault with the highest priority is processed first. The specific priority score is calculated as follows:
[0078] (Severity×40%)+(Occurrence×30%)+(Difficulty×30%);
[0079] In the formula, Severity is the severity score of the fault, Occurrence is the frequency of the fault, the past year is the cycle, and the number of times the PV inverter fault occurred in the cycle, Difficulty is the difficulty of handling, ranging from 1 to 10, 1 represents the lowest difficulty of handling, and 10 represents the highest difficulty of handling;
[0080] Furthermore, the fault severity is usually divided into 10 levels, from 1 to 10, where 1 represents the lowest severity and 10 represents the highest severity, and the score corresponds to the level, that is, level 1 is 1 point, specifically:
[0081] Level 1: Slight impact
[0082] Description: The impact of the fault on system functionality is almost negligible;
[0083] Example: Minor performance degradation that does not affect overall operation;
[0084] Level 2: Low Impact
[0085] Description: The failure caused a slight decrease in system performance, but most functions can still be performed normally;
[0086] Example: Some non-critical functions fail, but the main operation is not affected;
[0087] Level 3: Moderate impact
[0088] Description: The fault caused a significant decrease in system performance and some major functions were damaged;
[0089] Example: Some critical functions have degraded performance, requiring monitoring and possible intervention;
[0090] Level 4: Significant impact
[0091] Description: The fault significantly affects the main functions of the system and requires timely intervention;
[0092] Example: The performance of key components is significantly reduced, affecting overall efficiency;
[0093] Level 5: Significant impact
[0094] Description: The fault causes one or more major functions to fail and action must be taken to avoid further problems;
[0095] Example: The main system functions are partially paralyzed and need to be checked and repaired immediately;
[0096] Level 6: Severe Impact
[0097] Description: System functions are severely impaired, affecting most operations of the system;
[0098] Example: Most key functions cannot operate normally, posing safety risks;
[0099] Level 7: High Severity
[0100] Description: The failure jeopardizes the overall stability and safety of the system;
[0101] Example: Almost complete loss of system functionality, emergency response required;
[0102] Level 8: Very high severity
[0103] Description: Failure may cause complete system failure or safety incidents;
[0104] Example: All functions stop and there is an immediate risk of a safety incident;
[0105] Level 9: Extreme Severity
[0106] Description: The failure caused a serious safety incident, with the risk of significant losses and injuries;
[0107] Examples: System crash resulting in severe data loss and equipment damage;
[0108] Level 10: Catastrophic consequences
[0109] Description: The failure causes complete destruction of the system, which may cause significant loss of life and property;
[0110] Example: The entire system is destroyed and requires complete equipment replacement and reconstruction.
[0111] It should be noted that the specific classification of troubleshooting difficulty from 1 to 10, the score corresponds to the level, that is, level 1 is 1 point, specifically:
[0112] Level 1: Very easy
[0113] Description: Troubleshooting is straightforward and usually involves basic diagnosis and operation;
[0114] Example: Resetting a system or replacing a simple part;
[0115] Level 2: Easier
[0116] Description: Requires some technical knowledge, but most technicians can handle it;
[0117] Examples: replacing a damaged cable or a simple software configuration;
[0118] Level 3: Moderately Easy
[0119] Description: Requires specific technical tools and expertise, but carries a lower risk;
[0120] Examples: replacing a damaged connector or updating firmware;
[0121] Level 4: Slightly complex
[0122] Description: May require specialized tools and in-depth technical knowledge;
[0123] Example: Fixing network connectivity issues or complex configuration setup;
[0124] Level 5: Medium difficulty
[0125] Description: Troubleshooting involves multiple steps and requires detailed problem analysis and solution planning;
[0126] Examples: replacing complex hardware components or resolving software compatibility issues;
[0127] Level 6: More complex
[0128] Description: Requires advanced technical expertise and possible system disassembly;
[0129] Examples: data recovery or system security vulnerability repair;
[0130] Level 7: High Difficulty
[0131] Description: Troubleshooting may require the intervention of specialized equipment and technical experts;
[0132] Examples: rebuilding a corrupted database or repairing an advanced cyber attack;
[0133] Level 8: Very difficult
[0134] Description: Involves complex problem diagnosis and high-stakes resolution strategies;
[0135] Examples: replacement of core system components or resolution of advanced encryption issues;
[0136] Level 9: Extremely difficult
[0137] Description: Requires multi-faceted expert collaboration and innovative solutions;
[0138] Examples: Systematic software refactoring or complex hardware design modification;
[0139] Level 10: Extreme Difficulty
[0140] Description: May involve unprecedented technical challenges and large-scale system reconstruction;
[0141] Example: Comprehensive system upgrade or repair of equipment in extreme environments.
[0142] The data-driven deep learning algorithm in the intelligent detection and diagnosis algorithm unit consists of several groups of unsupervised neural networks. By learning the potential representation of the input data, the features of the input data can be extracted. At the same time, through training, the likelihood probability of the input data can be maximized. The expression is:
[0143]
[0144] In the formula, v and h represent the states of the visible layer and the hidden layer respectively, and w ij represents the connection weight between two layers, a i and b j Represent the bias of the visible layer and the hidden layer respectively;
[0145] The data-driven deep learning algorithm initializes the network parameters by pre-training the unsupervised neural network layer by layer, and then fine-tunes it to optimize the performance of the entire network.
[0146] like Figure 2 ,The specific working process of the fault location and notification unit is as follows:
[0147] 1) Analyze the fault code and alarm information provided by the inverter to preliminarily determine the fault type and possible location;
[0148] 2) Check the detailed alarm information and fault location data, and manually determine the possible fault location;
[0149] 3) Manually check the PV strings one by one to see if there is damage or poor contact between the components, connectors, optimizers, etc., and confirm the source of the fault.
[0150] The control execution module automatically adjusts the operating parameters of the photovoltaic inverter according to the analysis results of the data processing module and the fault detection and diagnosis module to optimize its performance and prevent the occurrence of faults; the control execution module includes: a parameter adjustment unit, a fault prevention unit and a fault processing unit;
[0151] The parameter adjustment unit automatically adjusts the operating parameters of the inverter according to the analysis results of the data processing module and the fault detection and diagnosis module. At the same time, it can also optimize the performance of the inverter to ensure that it operates at the optimal working point and improve the power generation efficiency.
[0152] The fault prevention unit is used to implement preventive measures, including soft start, overcurrent protection and fault code analysis, to avoid the occurrence of faults;
[0153] The fault handling unit is used to quickly start the preset fault handling procedures when a fault occurs, including restart, derating or safe shutdown, and guide the operation and maintenance personnel to quickly locate and repair the fault.
[0154] The communication module uses standard communication protocols such as Modbus or CAN to realize data exchange and communication between the photovoltaic inverter data acquisition control system and the remote monitoring center or other equipment;
[0155] The user interface module provides an intuitive display screen and operation buttons, allowing users to easily view the real-time operating status, historical data and fault information of the PV inverter, and perform simple operations and settings; the user interface module includes:
[0156] Display screen, used to show the real-time operating status of the photovoltaic inverter. The display screen can also present historical data and fault records to help users understand the long-term operation of the system;
[0157] Operation button: allows users to perform basic operations on the inverter through physical buttons, including starting, stopping, and parameter setting;
[0158] Communication unit: including bus, serial port and other communication methods, responsible for transmitting data and commands between the inverter and the remote monitoring system.
[0159] The power management module ensures the stable power supply of the photovoltaic inverter data acquisition control system. At the same time, in the event of a power outage of the photovoltaic inverter, the backup power supply can be used to maintain the normal operation of the system.
[0160] Exemplary working principle of the power management module:
[0161] Energy source,The power management module usually obtains energy from a photovoltaic array, because the photovoltaic array can provide enough energy to maintain the operation of the system.
[0162] Energy storage, the module contains energy storage units, usually batteries, which store the energy collected from the photovoltaic panels. When there is sufficient sunlight, the excess energy will be stored for future use.
[0163] Energy regulation and distribution,The power management module is also responsible for energy regulation and distribution.,It ensures that energy first meets the power supply needs of key devices, and the remaining energy is reasonably distributed according to,priority and preset algorithms.
[0164] Functions of backup power supply:
[0165] Power failure detection: When the photovoltaic inverter loses power, the power management module can immediately detect the power failure and quickly switch to the backup power mode.
[0166] Independent operation: After switching to the backup power source, the system can operate independently using the energy stored in the battery until the PV inverter is restored or until another energy source is found.
[0167] Protection mechanism, the power management module also has safety functions such as overload protection and short circuit protection to ensure the safety of equipment and personnel in backup power mode.
[0168] Intelligent power management
[0169] Intelligent monitoring and analysis, equipped with an intelligent monitoring system, can monitor the power status, load conditions, and battery power and health in real time. Through data analysis, the system can predict energy demand and optimize energy efficiency.
[0170] Remote control: With the support of the communication module, the power management module can achieve remote monitoring and control, allowing operation and maintenance personnel to adjust system settings and respond to emergencies remotely, further ensuring the stable operation of the system.
[0171] Automatic maintenance and alarm: the system can perform self-diagnosis based on real-time data, identify potential problems, and automatically take maintenance measures or send alarm information to maintenance personnel when necessary.
[0172] In summary, compared with the prior art, the present invention has the following advantages:
[0173] Real-time data acquisition and processing: The system can collect key operating parameters of photovoltaic inverters in real time, and perform data cleaning and normalization through the built-in pre-processing module to improve data accuracy and reliability;
[0174] Intelligent fault detection and diagnosis: The system can quickly and accurately detect and diagnose potential equipment failures, improving fault handling efficiency and system stability;
[0175] Automatic adjustment and optimization of performance: The control execution module automatically adjusts the inverter operating parameters according to the data analysis results, optimizes the performance, ensures that the system operates at the best working point, and improves power generation efficiency;
[0176] Fault prevention and timely handling: The system implements preventive measures to avoid faults and quickly starts the preset handling procedures when faults occur to reduce the impact of faults on the system;
[0177] Intuitive user interface: The user interface module provides an intuitive display screen and operation buttons, allowing users to easily view real-time operating status, historical data and fault information, and perform simple operations and settings;
[0178] Stable power supply and backup power supply: The power management module ensures stable power supply of the system and uses backup power supply to keep the system running in case of power outage, ensuring system continuity and reliability;
[0179] Fault location and notification: The fault location and notification unit can quickly and accurately locate the fault location, and send fault notifications to operation and maintenance personnel in a timely manner through the communication interface, shortening the fault response time;
[0180] Fault priority determination: The system can prioritize faults in multiple groups of photovoltaic inverters to ensure that the most serious faults are handled first, thereby improving fault management efficiency.
[0181] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A photovoltaic inverter data acquisition and control system, It is characterized in that include: Data acquisition and processing module, used to collect voltage, current, power and temperature operating parameters of photovoltaic inverters in real time; The fault detection and diagnosis module monitors the operating data of the photovoltaic inverter in real time and uses intelligent algorithms to quickly and accurately detect and diagnose potential equipment faults; The control execution module automatically adjusts the operating parameters of the photovoltaic inverter according to the analysis results of the data processing module and the fault detection and diagnosis module to optimize its performance and prevent the occurrence of faults; The communication module uses standard communication protocols such as Modbus or CAN to realize data exchange and communication between the photovoltaic inverter data acquisition control system and the remote monitoring center or other equipment; The user interface module provides an intuitive display screen and operation buttons, allowing users to easily view the real-time operating status, historical data and fault information of the PV inverter, and perform simple operations and settings; The power management module ensures the stable power supply of the photovoltaic inverter data acquisition control system. At the same time, when the photovoltaic inverter is powered off, it can use the backup power supply to maintain the normal operation of the system.
2. A photovoltaic inverter data acquisition and control system according to claim 1, Features: The data acquisition and processing module has a built-in preprocessing module, which filters and normalizes the collected data to reduce noise impact and improve data quality; The filtering of the collected data adopts the following calculation formula: x k =A k x k-1 +B k u k +w k z k =H k x k +v k ; In the formula, x k is the state vector, A k is the state transfer matrix, u k is the control vector, B k is the control matrix, w k is the process noise, z k is the observation vector, H k is the observation matrix, v k is the observation noise; In the filtering process of the collected data, according to the above calculation formula, it is obtained that: The state prediction calculation formula is: The covariance prediction calculation formula is: The gain calculation formula is: The state update calculation formula is: The covariance update calculation formula is: In the above formula, is the state estimate at time k, is the estimated error covariance matrix at time k, K k is the gain, Q k is the process noise covariance matrix, R k is the observation noise covariance matrix and I is the identity matrix.
3. A photovoltaic inverter data acquisition and control system according to claim 1, It is characterized in that The fault detection and diagnosis module interacts with the data acquisition and processing module, including: Intelligent detection and diagnosis algorithm unit, which is configured based on data-driven deep learning algorithm and CNN fusion long short-term memory network to process data and identify fault types and their causes; The fault data set construction and processing unit is responsible for constructing a comprehensive fault data set and performing data cleaning, preprocessing, and enhancement to improve the accuracy and generalization ability of fault detection; The fault location and notification unit is used to quickly and accurately locate the fault location when a fault is detected, and to send fault notifications to the operation and maintenance personnel in a timely manner through the integrated communication interface.
4. A photovoltaic inverter data acquisition and control system according to claim 3, It is characterized in that The data-driven deep learning algorithm in the intelligent detection and diagnosis algorithm unit is composed of several groups of unsupervised neural networks. By learning the potential representation of the input data, the features of the input data can be extracted. At the same time, through training, the likelihood probability of the input data can be maximized. The expression is: In the formula, v and h represent the states of the visible layer and the hidden layer respectively, and w ij represents the connection weight between two layers, a i and b j Represent the bias of the visible layer and the hidden layer respectively; Data-driven deep learning algorithms initialize network parameters by pre-training unsupervised neural networks layer by layer, and then fine-tune them to optimize the performance of the entire network.
5. A photovoltaic inverter data acquisition and control system according to claim 3, It is characterized in that The specific working process of the fault location and notification unit is as follows: 1) Analyze the fault code and alarm information provided by the inverter to preliminarily determine the fault type and possible location; 2) Check the detailed alarm information and fault location data, and manually determine the possible fault location; 3) Manually check the photovoltaic strings one by one, check whether the components, connectors, optimizers, etc. are damaged or have poor contact, and confirm the source of the fault.
6. A photovoltaic inverter data acquisition and control system according to claim 5, It is characterized in that The fault location and notification unit also includes a fault priority determination. When a plurality of groups of photovoltaic inverters have fault alarms at the same time, the priority level is determined and the fault with the highest priority is processed first. The specific priority score is calculated as follows: (Severity×40%)+(Occurrence×30%)+(Difficulty×30%); In the formula, Severity is the severity score of the fault, ranging from 1 to 10, 10 represents the highest severity, Occurrence is the frequency of the fault, the number of times the PV inverter fault occurred in the past year as a cycle, Difficulty is the difficulty of handling, ranging from 1 to 10, 1 represents the lowest difficulty of handling, and 10 represents the highest difficulty of handling.
7. A photovoltaic inverter data acquisition and control system according to claim 1, It is characterized in that The control execution module includes: a parameter adjustment unit, a fault prevention unit and a fault processing unit; The parameter adjustment unit automatically adjusts the operating parameters of the inverter according to the analysis results of the data processing module and the fault detection and diagnosis module. At the same time, it can also optimize the performance of the inverter, ensure that it operates at the optimal working point, and improve the power generation efficiency.
8. A photovoltaic inverter data acquisition and control system according to claim 7, Features: The fault prevention unit is used to implement preventive measures, including soft start, overcurrent protection and fault code analysis, to avoid the occurrence of faults; The fault handling unit is used to quickly start a preset fault handling procedure when a fault occurs, including restart, derating operation or safe shutdown, and guide the operation and maintenance personnel to quickly locate and repair the fault.
9. A photovoltaic inverter data acquisition and control system according to claim 1, It is characterized in that The user interface module comprises: A display screen is used to display the real-time operating status of the photovoltaic inverter. The display screen can also present historical data and fault records to help users understand the long-term operation of the system; Operation button: allows users to perform basic operations on the inverter through physical buttons, including starting, stopping, and parameter setting; Communication unit: including bus, serial port and other communication methods, responsible for transmitting data and commands between the inverter and the remote monitoring system.
Citation Information
Patent Citations
Distributed energy supply system equipment preventive maintenance method based on entropy theory
CN113408759A
Power load prediction method
CN117039843A
Photovoltaic inverter fault prediction method
CN117318614A
Collaborative fusion and grading prediction method for heterogeneous information of typical disaster risk of coal mine
CN117726181A
Power grid infrastructure safety management method and system
CN117835179A
Cited By
Multi-dimensional grid-connected test system for photovoltaic string inverter
CN120703627A
