Photovoltaic energy storage equipment health state intelligent diagnosis system and method based on Internet of Things

Abstract

The invention discloses a photovoltaic energy storage equipment health state intelligent diagnosis system and method based on the Internet of Things. Comprising a photovoltaic module monitoring module, an energy storage battery health monitoring module, an inverter operation monitoring module, an environmental data acquisition and analysis module, a fault early warning and prediction module, an energy management and optimization module, an equipment remote control and management module and a system self-learning and optimization module. The photovoltaic module monitoring module is used for monitoring the working state and the performance index of the photovoltaic module in real time, efficient and stable operation of the photovoltaic energy storage system is ensured through the comprehensive functions of data acquisition, intelligent analysis, fault early warning, optimal scheduling, remote control, self-learning optimization and the like, and the system can be used for monitoring the working state and the performance index of the photovoltaic module through data driving and an intelligent algorithm. The operation state of each device can be accurately monitored and optimized, potential faults are warned in advance, the occurrence frequency and the operation risk of the device faults are reduced, meanwhile, the energy utilization efficiency is improved, the operation and maintenance cost is reduced, and the reliability and the adaptability of the system are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic energy storage equipment, and in particular to an intelligent diagnosis system and method for the health status of photovoltaic energy storage equipment based on the Internet of Things. Background Art

[0002] Solar energy has become the focus of attention due to its unique advantages. The abundant solar radiation is an important energy source, which is inexhaustible, pollution-free, cheap, and freely available to humans. The energy of solar energy reaching the ground every second is as high as 800 megawatt-hours. If 0.1% of the solar energy on the earth's surface is converted into electrical energy, with a conversion rate of 5%, the annual power generation can reach 5.6X1012 kilowatt-hours, which is equivalent to 40 times the world's energy consumption. It is precisely because of these unique advantages of solar energy that after the 1980s, the types of solar cells have continued to increase, the scope of application has become increasingly broad, and the market scale has gradually expanded.

[0003] Photovoltaic power generation is a technology that uses the photovoltaic effect of semiconductor interfaces to directly convert light energy into electrical energy. It is mainly composed of three parts: solar panels (modules), controllers and inverters, and the main components are composed of electronic components. After the solar cells are connected in series and packaged for protection, they can form a large-area solar cell module, and then combined with power controllers and other components to form a photovoltaic power generation device. Photovoltaic power station refers to a photovoltaic power generation system that uses solar energy and special materials such as crystalline silicon panels, inverters and other electronic components to form a power generation system that is connected to the power grid and transmits electricity to the power grid. Photovoltaic power stations are the green power development energy projects that the country encourages the most. Photovoltaic energy storage equipment is an important component of photovoltaic power stations.

[0004] Traditionally, the health status diagnosis of photovoltaic energy storage equipment adopts the method of manual inspection, which regularly checks the operating status of photovoltaic modules, batteries, inverters and other equipment. Although this method can detect the obvious faults of the equipment, it cannot obtain data in real time and is prone to miss potential problems. Some equipment monitors the status by installing basic sensors (such as voltage, current, and temperature sensors), but these sensors usually only provide a single physical quantity data and lack comprehensive analysis and intelligent judgment of multi-dimensional data. In addition, traditional methods can only detect existing faults and cannot foresee potential performance degradation or hidden faults. Therefore, we propose an intelligent diagnosis system and method for the health status of photovoltaic energy storage equipment based on the Internet of Things. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent diagnosis system and method for the health status of photovoltaic energy storage equipment based on the Internet of Things to solve the problems raised in the above background technology.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things, including a photovoltaic component monitoring module, an energy storage battery health monitoring module, an inverter operation monitoring module, an environmental data collection and analysis module, a fault warning and prediction module, an energy management and optimization module, an equipment remote control and management module, and a system self-learning and optimization module;

[0007] The photovoltaic module monitoring module is used to monitor the working status and performance indicators of the photovoltaic modules in real time;

[0008] The energy storage battery health monitoring module is used to monitor the health status of the battery in the energy storage system;

[0009] The inverter operation monitoring module is used to monitor the operating status of the inverter to ensure that the inverter can normally convert the direct current generated by the photovoltaic panel into alternating current;

[0010] The environmental data collection and analysis module is used to collect various data related to the environment;

[0011] The fault warning and prediction module is used to identify potential faults or performance degradation trends in advance based on the real-time data of each module in the system in combination with machine learning or statistical analysis methods;

[0012] The energy management and optimization module is responsible for managing and scheduling energy flows such as photovoltaic power generation, energy storage, and grid load, and optimizing energy storage and use;

[0013] The equipment remote control and management module is used to allow remote monitoring and control of the photovoltaic system, energy storage system and inverter;

[0014] The system self-learning and optimization module is used based on machine learning and big data analysis. The system can self-learn according to historical data, automatically optimize operation strategies, and adapt to different environmental changes and demand fluctuations.

[0015] Preferably, the photovoltaic module monitoring module includes a photovoltaic module voltage and current monitoring unit and a photovoltaic module temperature monitoring unit;

[0016] The photovoltaic module voltage and current monitoring unit is used to monitor the output voltage and current of the photovoltaic module in real time and detect the power generation status of the photovoltaic module;

[0017] The photovoltaic module temperature monitoring unit is used to monitor the temperature of the photovoltaic module and determine whether abnormal phenomena such as overheating occur.

[0018] Preferably, the energy storage battery health monitoring module includes a battery voltage and current monitoring unit and a battery temperature and SOC monitoring unit;

[0019] The battery voltage and current monitoring unit is used to monitor the charging and discharging voltage and current of the battery pack in real time and analyze the health status of the battery;

[0020] The battery temperature and charging state monitoring unit is used to monitor the temperature and charging state of the battery to prevent the battery from overheating or over-discharging.

[0021] Preferably, the inverter operation monitoring module includes an inverter output power monitoring unit and an inverter fault diagnosis unit;

[0022] The inverter output power monitoring unit is used to monitor the output power of the inverter and determine whether there is power loss or abnormality;

[0023] The inverter fault diagnosis unit is used to detect whether the inverter has overload and overheat faults.

[0024] Preferably, the environmental data collection and analysis module includes a meteorological data monitoring unit and a light intensity monitoring unit;

[0025] The meteorological data monitoring unit is used to collect environmental data such as light intensity, temperature, humidity, etc., and evaluate the impact of the external environment on the photovoltaic system;

[0026] The light intensity monitoring unit is used to monitor the ambient light intensity in real time and evaluate the photovoltaic power generation potential.

[0027] Preferably, the fault warning and prediction module includes a fault pattern recognition unit based on data mining and a fault warning and decision support unit;

[0028] The data mining-based fault mode identification unit is used to identify potential fault modes of equipment through big data analysis;

[0029] The fault warning and decision support unit is used to combine the fault mode recognition results, issue equipment health status warnings, and provide decision support.

[0030] Preferably, the energy management and optimization module includes an energy storage and power generation optimization scheduling unit and a load prediction and energy allocation unit;

[0031] The energy storage and power generation optimization scheduling unit is used to optimize the energy storage and power generation scheduling strategy based on real-time data and predictive analysis;

[0032] The load prediction and energy allocation unit is used to predict load demand and intelligently allocate energy storage and photovoltaic power resources.

[0033] Preferably, the equipment remote control and management module includes a remote fault diagnosis and recovery unit and an equipment status monitoring and automatic adjustment unit;

[0034] The remote fault diagnosis and recovery unit is used to remotely monitor the equipment through the Internet of Things, diagnose faults in real time, and perform remote repairs or adjustments;

[0035] The equipment status monitoring and automatic adjustment unit is used to monitor the operating status of the equipment and automatically adjust the equipment operating parameters according to real-time data.

[0036] Preferably, the system self-learning and optimization module includes an intelligent self-learning algorithm unit and a device interaction and collaborative optimization unit;

[0037] The intelligent self-learning algorithm unit is used to continuously optimize the operation strategy of the equipment through a self-learning algorithm based on historical operation data and real-time data;

[0038] The device interaction and collaborative optimization unit is used for collaborative work among multiple devices to improve the overall efficiency of the system through information sharing and collaborative optimization.

[0039] The working method of the intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things according to any of the above items comprises the following steps:

[0040] S1. The system obtains different types of data through multiple monitoring modules: the photovoltaic module monitoring module monitors the voltage, current and temperature of the photovoltaic modules in real time; the energy storage battery health monitoring module monitors the voltage, current, temperature and charging status of the battery pack; the inverter operation monitoring module ensures the normal operation of the inverter by monitoring the output power of the inverter and whether there are faults such as overload and overheating, and evaluates the impact of the external environment on the performance of the photovoltaic power generation system through the environmental data collection and analysis module, and monitors the light intensity in real time to determine the power generation potential of the photovoltaic system;

[0041] S2. The system inputs the collected data into the fault warning and prediction module for processing: the fault pattern recognition unit uses data mining technology to analyze the real-time data of the equipment and identify potential fault patterns; the fault warning and decision support unit issues fault warnings based on the results of fault pattern recognition and provides decision support for operation and maintenance personnel to ensure timely handling of equipment problems;

[0042] S3. The system performs intelligent scheduling and optimization through the energy management and optimization module: the energy storage and power generation optimization scheduling unit optimizes the energy storage and power generation scheduling strategy based on real-time monitoring data and forecast analysis results; the load forecasting and energy allocation unit predicts the load demand in different time periods based on historical data and environmental forecasts, and intelligently allocates photovoltaic power generation and energy storage power resources according to load demand, thereby optimizing energy utilization efficiency;

[0043] S4. Remote control and management module realizes remote monitoring and adjustment of equipment: remote fault diagnosis and recovery unit uses Internet of Things technology, the system can remotely monitor, diagnose photovoltaic system faults in real time, and even remotely recover or adjust. The system monitors the operating status of the equipment and automatically adjusts the equipment operating parameters according to real-time data to ensure that the system is always in the optimal operating state;

[0044] S5. The system self-learning and optimization module continuously adjusts the optimization strategy based on historical data and real-time data: Through machine learning algorithms, the system can continuously optimize the equipment operation strategy based on the equipment's historical operation data and real-time operation data, and gradually improve the system efficiency; in a multi-device environment, the system can achieve collaborative work between devices, and improve the efficiency of the entire system through information sharing and collaborative optimization;

[0045] S6. The system continuously optimizes the operation of the equipment through self-diagnosis and automatic adjustment functions: the system automatically optimizes the operation strategy through self-learning algorithms based on sensor data, equipment status, fault warning information, etc., thereby ensuring that photovoltaic, energy storage, inverter and other equipment can operate efficiently and stably under various environmental conditions.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. Based on the Internet of Things technology, the system can realize real-time monitoring of photovoltaic modules, energy storage batteries, inverters and other equipment, provide detailed performance data, and ensure the health status of the equipment. Real-time data feedback helps to quickly identify potential problems in the system, improve equipment operation efficiency, and avoid system failures.

[0048] 2. The system of the present invention integrates fault warning and prediction modules, combines machine learning, statistical analysis and other methods, and can identify the trend of equipment failure or performance degradation in advance, so that maintenance can be carried out before the equipment fails, reducing the occurrence of sudden failures and improving the reliability and availability of the system.

[0049] 3. The energy management and optimization module in the system of the present invention can dispatch the energy flow between photovoltaic power generation, energy storage batteries and power grid according to real-time data, and optimize energy storage and power generation strategies. This can not only improve the efficiency of energy utilization, but also dynamically adjust according to load demand to reduce energy waste.

[0050] 4. The present invention uses the equipment remote control and management module, and the system supports remote fault diagnosis and equipment management. It can remotely adjust the equipment operating parameters, reduce manual intervention and on-site maintenance costs, and improve the intelligent management level of the system. The system self-learning and optimization module can continuously optimize the equipment's operating strategy through machine learning algorithms based on historical operating data and real-time data, adapt to different environmental changes and demand fluctuations, and improve the adaptability of the entire system.

[0051] 5. The environmental data acquisition and analysis module of the present invention can monitor meteorological conditions and light intensity in real time, and provide valuable background information for the operation of the photovoltaic system. This enables the system to adjust the operation strategy according to environmental changes, thereby optimizing the photovoltaic power generation effect. Through health status monitoring, fault prediction, real-time adjustment and other means, the system can effectively extend the service life of photovoltaic energy storage equipment, reduce downtime, and reduce maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a system principle diagram of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 The present invention provides a technical solution: an intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things, including a photovoltaic component monitoring module, a storage battery health monitoring module, an inverter operation monitoring module, an environmental data acquisition and analysis module, a fault warning and prediction module, an energy management and optimization module, an equipment remote control and management module, and a system self-learning and optimization module.

[0055] The photovoltaic module monitoring module is used to monitor the working status and performance indicators of the photovoltaic module in real time. The photovoltaic module monitoring module includes a photovoltaic module voltage and current monitoring unit and a photovoltaic module temperature monitoring unit; the photovoltaic module voltage and current monitoring unit is used to monitor the output voltage and current of the photovoltaic module in real time and detect the power generation status of the photovoltaic module; the photovoltaic module temperature monitoring unit is used to monitor the temperature of the photovoltaic module and determine whether abnormal phenomena such as overheating occur.

[0056] The photovoltaic module voltage and current monitoring unit uses data processing based on the "Kalman filter algorithm" to eliminate noise data, improve data accuracy, and accurately diagnose whether the photovoltaic module has electrical faults (such as low voltage, abnormal current, etc.);

[0057] For the voltage and current data of photovoltaic modules, the Kalman filter algorithm can usually be implemented through the following steps:

[0058] 1. Define state variables

[0059] Assume that the voltage or current at a certain moment (denoted as x k), which may be affected by the state x at the previous moment k-1 and the influence of noise. The state variable x k It may be voltage or current; the observed value z k is the measured voltage or current value, usually including noise. The output voltage and current model of the photovoltaic module can be expressed as a first-order linear dynamic system:

[0060] x k =Fx k-1 +w k ,

[0061] z k =Hx k +v k ,

[0062] Where: x k is the estimated state (voltage or current) at time k; z k is the observed data at time k (voltage or current value with noise); F is the state transfer matrix, which describes the state change model from k-1 to k; H is the observation matrix, which describes how to map from state to observation; w k is the process noise, usually assumed to be zero-mean Gaussian noise with covariance Q; v k is the observation noise, usually assumed to be zero-mean Gaussian noise with a covariance of R;

[0063] 2. Initialization parameters

[0064] Before starting filtering, you first need to initialize the following parameters:

[0065] A is estimated in the initial state An estimate can be made using the initial voltage or current value;

[0066] B initial estimated covariance P 0 : Indicates the uncertainty of state estimation, usually taking a larger value;

[0067] C state transfer matrix F and observation matrix H: These matrices depend on the specific model of the PV module. Generally speaking, assuming that the system is static, F = 1 may be set (i.e. the state remains unchanged at each moment);

[0068] D process noise covariance Q and observation noise covariance R: These parameters can be determined through experiments or adjusted according to actual conditions;

[0069] 3. Prediction step: At time k, based on the estimated state at the previous time k-1, the state prediction is performed:

[0070]

[0071] in: is the predicted state at time k; is the covariance of the predicted states;

[0072] 4. Update step: Once we have new observation data z k , the estimated value can be updated by the Kalman gain:

[0073]

[0074] Where: K k is the Kalman gain, which determines the weighted ratio of the predicted value and the observed value. k , update the state estimate:

[0075]

[0076] Update the covariance of the state estimate:

[0077]

[0078] in: is the updated estimate at time k; P k is the updated covariance matrix;

[0079] 5. Repeat the prediction and update process: For each new moment k, repeat the above prediction and update process, gradually filter out the noise through the Kalman filter algorithm, and improve the measurement accuracy of voltage and current;

[0080] 6. Adjust Kalman filter parameters: Process noise covariance Q and observation noise covariance R have a great impact on the performance of Kalman filter. If the process noise Q is set too large, the filter may over-rely on the predicted value and ignore the observed data; if the observation noise R is set too large, the filter may ignore the effective information of the observed data, resulting in low accuracy.

[0081] Therefore, Kalman filtering can effectively remove the noise in the voltage and current measurement data of photovoltaic modules. By defining a suitable state space model and combining the prediction and update steps, Kalman filtering can provide more accurate estimates than the original measurement data while taking into account process and observation noise.

[0082] The energy storage battery health monitoring module is used to monitor the health of the battery in the energy storage system. The energy storage battery health monitoring module includes a battery voltage and current monitoring unit and a battery temperature and SOC monitoring unit; the battery voltage and current monitoring unit is used to monitor the charge and discharge voltage and current of the battery pack in real time and analyze the health of the battery; the battery temperature and charging status monitoring unit is used to monitor the temperature and charging status of the battery to prevent the battery from overheating or over-discharge. The battery temperature and SOC monitoring unit uses a fuzzy control algorithm to adjust the battery temperature and SOC in real time, optimize the battery charge and discharge process, and avoid battery damage due to excessive temperature or low SOC.

[0083] In order to perform fuzzy control, it is necessary to first establish a battery model, which usually includes the following aspects:

[0084] 1. SOC model: Indicates the remaining power of the battery. SOC can usually be estimated by the current integration method:

[0085]

[0086] Where I(t) is the instantaneous charge and discharge current of the battery; Δt is the sampling time; C battery is the capacity of the battery;

[0087] 2. Fuzzy control system design

[0088] The fuzzy control system mainly includes the following parts:

[0089] 1) Input variables: variables that need to be regulated, such as SOC error (e SOC ) and temperature error (e T );

[0090] SOC error: e SOC =SOC target -SOC current ; Temperature error: e T =T target -T current ;

[0091] 2) Output variable: Output control signal (such as charge / discharge current or power adjustment) according to the control target; the output is usually to control the charge / discharge power or current I control , thereby controlling the charging and discharging process of the battery;

[0092] 3) Fuzzy rules: Establish control rules through experience and expert knowledge. Fuzzy rules are usually based on the changing trend of input variables, and the following fuzzy rules are constructed:

[0093] If the SOC error is large and the temperature error is large, the charging current is greatly reduced; if the SOC error is small and the temperature error is small, the normal charging current is used; if the temperature error is large, the charging current is adjusted to reduce the temperature rise;

[0094] 3. Fuzzy reasoning process: The core of fuzzy control is the fuzzy reasoning process. It includes the following steps:

[0095] 1) Fuzzification: Fuzzify the input variables (SOC error and temperature error), that is, convert these inputs into fuzzy sets. For example, SOC error can be divided into fuzzy sets such as "high", "medium", and "low", and temperature error can be divided into fuzzy sets such as "temperature is too high" and "temperature is normal";

[0096] 2) Rule base application: Based on the fuzzy input, the preset fuzzy rule base is applied for reasoning. According to the fuzzy rule base, the system will deduce the appropriate output (control current) based on the input fuzzy value (such as SOC error and temperature error);

[0097] 3) Defuzzification: Defuzzify the control result obtained by fuzzy reasoning to obtain the actual control value (charging current or power). Common defuzzification methods include the centroid method and the maximum membership method.

[0098] 4. Output of fuzzy controller: The output control quantity (charging and discharging current or power) obtained by fuzzy reasoning can control the charging process of the battery. When adjusting the control quantity, it is necessary to ensure that the charging and discharging current of the battery does not exceed the safe operating range of the battery to avoid overcharging, over-discharging or overheating.

[0099] 5. Actual calculation process

[0100] Assume that the battery SOC target value is SOC target , the current value is SOC current The target temperature of the battery is T target , the current value is T current .,but:

[0101] SOC error: e SOC =SOC target -SOC current ,

[0102] Temperature error: eT = T target -T current According to the fuzzy rule base and fuzzy reasoning process, the charge and discharge current control signal I is obtained. control , and then adjust the battery's charging current or power. This process needs to be constantly updated in a real-time control system.

[0103] 6. Optimization strategy: When regulating the battery charging and discharging process through fuzzy control algorithm, it is necessary to optimize the fuzzy rules according to the specific characteristics of the battery and the requirements of the actual application, for example:

[0104] Temperature optimization: Adjust the charging current through fuzzy control to reduce the heat inside the battery, avoid overheating, and ensure that the battery temperature is within a safe range.

[0105] SOC optimization: Regulate the charging strategy through fuzzy control to avoid SOC being too low or too high, ensuring that the battery is always in a relatively ideal working state, thereby improving the battery life and performance;

[0106] 7. Fuzzy control is a closed-loop control system that requires real-time feedback of the battery's SOC and temperature data and adjusts the control strategy based on the current error value. Through this real-time adjustment, the battery's charging and discharging process can be effectively optimized.

[0107] The inverter operation monitoring module is used to monitor the operating status of the inverter to ensure that the inverter can normally convert the direct current generated by the photovoltaic panel into alternating current. The inverter operation monitoring module includes an inverter output power monitoring unit and an inverter fault diagnosis unit; the inverter output power monitoring unit is used to monitor the output power of the inverter to determine whether there is power loss or abnormality; the inverter fault diagnosis unit is used to detect whether the inverter is overloaded or overheated.

[0108] The environmental data collection and analysis module is used to collect various data related to the environment. The environmental data collection and analysis module includes a meteorological data monitoring unit and a light intensity monitoring unit; the meteorological data monitoring unit is used to collect environmental data such as light intensity, temperature, humidity, etc., and evaluate the impact of the external environment on the photovoltaic system; the light intensity monitoring unit is used to monitor the ambient light intensity in real time and evaluate the photovoltaic power generation potential.

[0109] The fault warning and prediction module is used to identify potential faults or performance degradation trends in advance based on the real-time data of each module in the system, combined with machine learning or statistical analysis methods. The fault warning and prediction module includes a fault pattern recognition unit based on data mining and a fault warning and decision support unit; the fault pattern recognition unit based on data mining is used to identify potential failure modes of equipment through big data analysis; the fault warning and decision support unit is used to combine the fault pattern recognition results, issue equipment health status warnings, and provide decision support.

[0110] The energy management and optimization module is responsible for managing and scheduling energy flows such as photovoltaic power generation, energy storage, and grid load, and optimizing energy storage and use. The energy management and optimization module includes an energy storage and power generation optimization scheduling unit and a load prediction and energy allocation unit; the energy storage and power generation optimization scheduling unit is used to optimize energy storage and power generation scheduling strategies based on real-time data and predictive analysis; the load prediction and energy allocation unit is used to predict load demand and intelligently allocate energy storage and photovoltaic power resources.

[0111] The equipment remote control and management module is used to allow remote monitoring and control of photovoltaic systems, energy storage systems and inverters. The equipment remote control and management module includes a remote fault diagnosis and recovery unit and an equipment status monitoring and automatic adjustment unit; the remote fault diagnosis and recovery unit is used to remotely monitor the equipment through the Internet of Things, diagnose faults in real time, and perform remote repairs or adjustments; the equipment status monitoring and automatic adjustment unit is used to monitor the operating status of the equipment and automatically adjust the equipment operating parameters according to real-time data.

[0112] The system self-learning and optimization module is used based on machine learning and big data analysis. The system can self-learn according to historical data, automatically optimize operation strategies, and adapt to different environmental changes and demand fluctuations. The system self-learning and optimization module includes an intelligent self-learning algorithm unit and a device interaction and collaborative optimization unit; the intelligent self-learning algorithm unit is used to continuously optimize the operation strategy of the equipment through self-learning algorithms based on historical operation data and real-time data; the device interaction and collaborative optimization unit is used for collaborative work among multiple devices to improve the overall efficiency of the system through information sharing and collaborative optimization.

[0113] The working method of the intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things according to any of the above items comprises the following steps:

[0114] S1. The system obtains different types of data through multiple monitoring modules: the photovoltaic module monitoring module monitors the voltage, current and temperature of the photovoltaic modules in real time; the energy storage battery health monitoring module monitors the voltage, current, temperature and charging status of the battery pack; the inverter operation monitoring module ensures the normal operation of the inverter by monitoring the output power of the inverter and whether there are faults such as overload and overheating, and evaluates the impact of the external environment on the performance of the photovoltaic power generation system through the environmental data collection and analysis module, and monitors the light intensity in real time to determine the power generation potential of the photovoltaic system;

[0115] S2. The system inputs the collected data into the fault warning and prediction module for processing: the fault pattern recognition unit uses data mining technology to analyze the real-time data of the equipment and identify potential fault patterns; the fault warning and decision support unit issues fault warnings based on the results of fault pattern recognition and provides decision support for operation and maintenance personnel to ensure timely handling of equipment problems;

[0116] S3. The system performs intelligent scheduling and optimization through the energy management and optimization module: the energy storage and power generation optimization scheduling unit optimizes the energy storage and power generation scheduling strategy based on real-time monitoring data and forecast analysis results; the load forecasting and energy allocation unit predicts the load demand in different time periods based on historical data and environmental forecasts, and intelligently allocates photovoltaic power generation and energy storage power resources according to load demand, thereby optimizing energy utilization efficiency;

[0117] S4. Remote control and management module realizes remote monitoring and adjustment of equipment: remote fault diagnosis and recovery unit uses Internet of Things technology, the system can remotely monitor, diagnose photovoltaic system faults in real time, and even remotely recover or adjust. The system monitors the operating status of the equipment and automatically adjusts the equipment operating parameters according to real-time data to ensure that the system is always in the optimal operating state;

[0118] S5. The system self-learning and optimization module continuously adjusts the optimization strategy based on historical data and real-time data: Through machine learning algorithms, the system can continuously optimize the equipment operation strategy based on the equipment's historical operation data and real-time operation data, and gradually improve the system efficiency; in a multi-device environment, the system can achieve collaborative work between devices, and improve the efficiency of the entire system through information sharing and collaborative optimization;

[0119] S6. The system continuously optimizes the operation of the equipment through self-diagnosis and automatic adjustment functions: the system automatically optimizes the operation strategy through self-learning algorithms based on sensor data, equipment status, fault warning information, etc., thereby ensuring that photovoltaic, energy storage, inverter and other equipment can operate efficiently and stably under various environmental conditions.

[0120] In summary: The present invention ensures the efficient and stable operation of the photovoltaic energy storage system through comprehensive data collection, intelligent analysis, fault warning, optimized scheduling, remote control and self-learning optimization. The system can accurately monitor and optimize the operating status of each device through data-driven and intelligent algorithms, warn of potential faults in advance, reduce the frequency of equipment failures and operating risks, improve energy efficiency, reduce operation and maintenance costs, and enhance the reliability and adaptability of the system.

[0121] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things is characterized by: It includes photovoltaic module monitoring module, energy storage battery health monitoring module, inverter operation monitoring module, environmental data collection and analysis module, fault warning and prediction module, energy management and optimization module, equipment remote control and management module and system self-learning and optimization module; The photovoltaic module monitoring module is used to monitor the working status and performance indicators of the photovoltaic modules in real time; The energy storage battery health monitoring module is used to monitor the health status of the battery in the energy storage system; The inverter operation monitoring module is used to monitor the operating status of the inverter to ensure that the inverter can normally convert the direct current generated by the photovoltaic panel into alternating current; The environmental data collection and analysis module is used to collect various data related to the environment; The fault warning and prediction module is used to identify potential faults or performance degradation trends in advance based on the real-time data of each module in the system in combination with machine learning or statistical analysis methods; The energy management and optimization module is responsible for managing and scheduling energy flows such as photovoltaic power generation, energy storage, and grid load, and optimizing energy storage and use; The equipment remote control and management module is used to allow remote monitoring and control of the photovoltaic system, energy storage system and inverter; The system self-learning and optimization module is used based on machine learning and big data analysis. The system can self-learn according to historical data, automatically optimize operation strategies, and adapt to different environmental changes and demand fluctuations.

2. The intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things according to claim 1 is characterized in that: The photovoltaic module monitoring module includes a photovoltaic module voltage and current monitoring unit and a photovoltaic module temperature monitoring unit; The photovoltaic module voltage and current monitoring unit is used to monitor the output voltage and current of the photovoltaic module in real time and detect the power generation status of the photovoltaic module; The photovoltaic module temperature monitoring unit is used to monitor the temperature of the photovoltaic module and determine whether an abnormal phenomenon such as overheating occurs.

3. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The energy storage battery health monitoring module includes a battery voltage and current monitoring unit and a battery temperature and SOC monitoring unit; The battery voltage and current monitoring unit is used to monitor the charging and discharging voltage and current of the battery pack in real time and analyze the health status of the battery; The battery temperature and charging state monitoring unit is used to monitor the temperature and charging state of the battery to prevent the battery from overheating or over-discharging.

4. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The inverter operation monitoring module includes an inverter output power monitoring unit and an inverter fault diagnosis unit; The inverter output power monitoring unit is used to monitor the output power of the inverter and determine whether there is power loss or abnormality; The inverter fault diagnosis unit is used to detect whether the inverter has an overload or overheat fault.

5. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The environmental data collection and analysis module includes a meteorological data monitoring unit and a light intensity monitoring unit; The meteorological data monitoring unit is used to collect environmental data such as light intensity, temperature, humidity, etc., and evaluate the impact of the external environment on the photovoltaic system; The light intensity monitoring unit is used to monitor the ambient light intensity in real time and evaluate the photovoltaic power generation potential.

6. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The fault warning and prediction module includes a fault pattern recognition unit based on data mining and a fault warning and decision support unit; The data mining-based fault mode identification unit is used to identify potential fault modes of equipment through big data analysis; The fault warning and decision support unit is used to combine the fault mode recognition results, issue equipment health status warnings, and provide decision support.

7. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The energy management and optimization module includes an energy storage and power generation optimization scheduling unit and a load prediction and energy allocation unit; The energy storage and power generation optimization scheduling unit is used to optimize the energy storage and power generation scheduling strategy based on real-time data and predictive analysis; The load prediction and energy allocation unit is used to predict load demand and intelligently allocate energy storage and photovoltaic power resources.

8. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The equipment remote control and management module includes a remote fault diagnosis and recovery unit and an equipment status monitoring and automatic adjustment unit; The remote fault diagnosis and recovery unit is used to remotely monitor the equipment through the Internet of Things, diagnose faults in real time, and perform remote repairs or adjustments; The equipment status monitoring and automatic adjustment unit is used to monitor the operating status of the equipment and automatically adjust the equipment operating parameters according to real-time data.

9. The photovoltaic energy storage equipment health status intelligent diagnosis system based on the Internet of Things according to claim 1 is characterized by: The system self-learning and optimization module includes an intelligent self-learning algorithm unit and a device interaction and collaborative optimization unit; The intelligent self-learning algorithm unit is used to continuously optimize the operation strategy of the equipment through a self-learning algorithm based on historical operation data and real-time data; The device interaction and collaborative optimization unit is used for collaborative work among multiple devices to improve the overall efficiency of the system through information sharing and collaborative optimization.

10. The working method of the intelligent diagnosis system for the health status of photovoltaic energy storage equipment based on the Internet of Things according to any one of claims 1 to 9, characterized in that: The steps include: S1. The system obtains different types of data through multiple monitoring modules: the photovoltaic module monitoring module monitors the voltage, current and temperature of the photovoltaic modules in real time; the energy storage battery health monitoring module monitors the voltage, current, temperature and charging status of the battery pack; the inverter operation monitoring module ensures the normal operation of the inverter by monitoring the output power of the inverter and whether there are faults such as overload and overheating, and evaluates the impact of the external environment on the performance of the photovoltaic power generation system through the environmental data collection and analysis module, and monitors the light intensity in real time to determine the power generation potential of the photovoltaic system; S2. The system inputs the collected data into the fault warning and prediction module for processing: the fault pattern recognition unit uses data mining technology to analyze the real-time data of the equipment and identify potential fault patterns; the fault warning and decision support unit issues fault warnings based on the results of fault pattern recognition and provides decision support for operation and maintenance personnel to ensure timely handling of equipment problems; S3. The system performs intelligent scheduling and optimization through the energy management and optimization module: the energy storage and power generation optimization scheduling unit optimizes the energy storage and power generation scheduling strategy based on real-time monitoring data and forecast analysis results; the load forecasting and energy allocation unit predicts the load demand in different time periods based on historical data and environmental forecasts, and intelligently allocates photovoltaic power generation and energy storage power resources according to load demand, thereby optimizing energy utilization efficiency; S4. Remote control and management module realizes remote monitoring and adjustment of equipment: remote fault diagnosis and recovery unit uses Internet of Things technology, the system can remotely monitor, diagnose photovoltaic system faults in real time, and even remotely recover or adjust. The system monitors the operating status of the equipment and automatically adjusts the equipment operating parameters according to real-time data to ensure that the system is always in the optimal operating state; S5. The system self-learning and optimization module continuously adjusts the optimization strategy based on historical data and real-time data: Through machine learning algorithms, the system can continuously optimize the equipment operation strategy based on the equipment's historical operation data and real-time operation data, and gradually improve the system efficiency; in a multi-device environment, the system can achieve collaborative work between devices, and improve the efficiency of the entire system through information sharing and collaborative optimization; S6. The system continuously optimizes the operation of the equipment through self-diagnosis and automatic adjustment functions: the system automatically optimizes the operation strategy through self-learning algorithms based on sensor data, equipment status, fault warning information, etc., thereby ensuring that photovoltaic, energy storage, inverter and other equipment can operate efficiently and stably under various environmental conditions.

Images