Photovoltaic inverter power distribution monitoring method and system based on multiple modes

Abstract

The invention relates to the field of photovoltaic power generation system monitoring, in particular to a photovoltaic inverter power distribution monitoring method and system based on multiple modalities, and the method comprises the steps: determining a photovoltaic inverter based on a power distribution monitoring instruction, determining an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environment monitoring mechanism, carrying out the electromagnetic analysis of the photovoltaic inverter through the electromagnetic monitoring mechanism, and carrying out the temperature analysis of the photovoltaic inverter through the temperature analysis mechanism; the temperature analysis mechanism is used for carrying out temperature image analysis on the semiconductor module to obtain a temperature anomaly index, and the environment monitoring mechanism is used for monitoring the device shell to obtain an operation stability index; and inputting the electromagnetic anomaly weight, the electromagnetic anomaly index, the temperature anomaly weight, the temperature anomaly index, the current environment weight and the operation stability index into a pre-constructed multi-mode monitoring model to obtain a power distribution anomaly degree, and completing power distribution monitoring of the photovoltaic inverter based on a danger monitoring end or a safety monitoring end. According to the invention, the accuracy and the automation degree of monitoring the photovoltaic inverter can be improved.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic power generation system monitoring, and in particular to a photovoltaic inverter power distribution monitoring method and system based on multi-modality. Background Art

[0002] As global demand for renewable energy continues to grow, photovoltaic power generation systems are increasingly being used in various buildings, industrial facilities, and grid-connected scenarios. As the core device connecting photovoltaic panels to the grid, the photovoltaic inverter's operational stability and power distribution safety have a decisive impact on the power generation efficiency and service life of the entire photovoltaic system.

[0003] Currently, most monitoring methods for photovoltaic inverters are single-mode or single-threshold data analysis methods, which issue an alarm when parameters such as temperature or current exceed a certain threshold.

[0004] Although existing methods can monitor the power distribution of photovoltaic inverters, single-modal data analysis methods can only evaluate the local characteristics of photovoltaic inverters and cannot perform correlation analysis on multiple interference factors such as electromagnetic disturbances, temperature rise risks and environmental factors, which can easily lead to delayed fault warning or misjudgment. Therefore, there is an urgent need for a monitoring method that can integrate multi-modal information. By integrating multi-modal data such as electromagnetic, temperature and environmental data, a comprehensive assessment and intelligent judgment of the power distribution status of photovoltaic inverters can be achieved, thereby improving monitoring accuracy and enhancing fault response efficiency. Summary of the Invention

[0005] The present invention provides a photovoltaic inverter power distribution monitoring method based on multi-modality and a computer-readable storage medium, the main purpose of which is to improve the accuracy and automation of monitoring photovoltaic inverters.

[0006] To achieve the above objectives, the present invention provides a multi-modal photovoltaic inverter power distribution monitoring method, comprising:

[0007] receiving a power distribution monitoring instruction, and identifying a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a heat sink;

[0008] Identify the electromagnetic monitoring mechanism, temperature analysis mechanism, and environmental monitoring mechanism. The electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The temperature analysis mechanism includes: a high-definition camera and an infrared camera. The environmental monitoring mechanism includes: a sound sensor and a vibration sensor. The EMI monitor includes: a test antenna. The light sensor, humidity sensor, sound sensor, and vibration sensor are all installed on the surface of the device housing.

[0009] Using the pre-built environmental database and electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, the electromagnetic monitoring mechanism is used to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index;

[0010] Use the temperature analysis mechanism to evaluate the status of the radiator and obtain the temperature anomaly weight. Use the temperature analysis mechanism to analyze the temperature image of the semiconductor module and obtain the temperature anomaly index.

[0011] Determine the current environmental weight, use the environmental monitoring agency to monitor the device shell, and obtain the operation stability index;

[0012] The electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight, and operation stability index are input into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree;

[0013] Compare the power distribution abnormality with a preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, send a pre-built danger signal to a pre-built inverter monitoring terminal to obtain a danger monitoring terminal. Otherwise, send a pre-built safety signal to the inverter monitoring terminal to obtain a safety monitoring terminal.

[0014] Complete power distribution monitoring of photovoltaic inverters based on the danger monitoring terminal or the safety monitoring terminal.

[0015] Optionally, the obtaining of electromagnetic anomaly weights using a pre-built environmental database and an electromagnetic monitoring mechanism includes:

[0016] Determine the current time and the current time range based on the current time and the preset reference duration;

[0017] Extracting multiple historical moment data from the environmental database based on the current time range, wherein the historical moment data includes: historical light intensity and historical humidity;

[0018] Extracting multiple historical light intensities and multiple historical humidity data from multiple historical moments, and calculating a current reference light intensity based on the multiple historical light intensities, wherein the current reference light intensity is an average value of the multiple historical light intensities;

[0019] Calculate current reference humidity based on multiple historical humidity levels;

[0020] Acquire multiple current light intensities and multiple current humidity levels based on a preset monitoring interval, a preset monitoring time, a light sensor, and a humidity sensor;

[0021] The electromagnetic anomaly weight is calculated based on multiple current light intensities, multiple current humidity levels, current reference light intensities, and current reference humidity.

[0022] Optionally, the electromagnetic analysis of the photovoltaic inverter using an electromagnetic monitoring mechanism to obtain an electromagnetic anomaly index includes:

[0023] Lift and align the test antenna of the EMI monitor in the electromagnetic monitoring mechanism to prepare the monitor;

[0024] Based on the preset monitoring frequency band and the prepared monitor, the photovoltaic inverter is monitored for electromagnetic interference to obtain an electromagnetic spectrum curve, wherein the horizontal axis of the electromagnetic spectrum curve is the frequency and the vertical axis of the electromagnetic spectrum curve is the amplitude;

[0025] Performing a uniform division operation on the monitoring frequency band based on a preset frequency band interval to obtain multiple frequency ranges;

[0026] For each of the multiple frequency ranges, perform the following operations:

[0027] Identify a target spectrum curve in the electromagnetic spectrum curve based on the frequency range, and confirm the maximum interference amplitude of the target spectrum curve;

[0028] Summarizing the maximum interference amplitudes to obtain multiple maximum interference amplitudes, and calculating an average interference amplitude based on the multiple maximum interference amplitudes, wherein the average interference amplitude is an average value of the multiple maximum interference amplitudes;

[0029] The photovoltaic input cable in the photovoltaic inverter is monitored based on the monitoring interval, the monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple input current values;

[0030] Based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism, the distribution output cable in the photovoltaic inverter is monitored to obtain multiple output current values;

[0031] Calculating an input current mean and an input current variance based on a plurality of input current values, and obtaining an output current mean and an output current variance based on a plurality of output current values;

[0032] Use a resistance monitor to detect the grounding device in the photovoltaic inverter to obtain the grounding resistance;

[0033] The electromagnetic anomaly index is calculated based on the average interference amplitude, input current mean, input current variance, output current mean, output current variance and ground resistance.

[0034] Optionally, the calculation formula of the electromagnetic anomaly index is as follows:

[0035]

[0036] Among them, ψ B is the electromagnetic anomaly index, is the average interference amplitude, and are the mean input current and the mean output current, and are the preset reference input current value and the preset reference output current value respectively. and are the input current variance and output current variance, R L is the grounding resistance, and e is a natural constant.

[0037] Optionally, the step of using a temperature analysis mechanism to perform a status assessment on the radiator to obtain a temperature anomaly weight includes:

[0038] The radiator is photographed using a high-definition camera in the temperature analysis mechanism to obtain an image of the radiator surface;

[0039] Inputting the pre-constructed initial radiator image and the radiator surface image into the pre-constructed image comparison model to obtain image similarity;

[0040] The temperature anomaly weight is calculated using image similarity.

[0041] Optionally, the step of performing temperature image analysis on the semiconductor module using a temperature analysis mechanism to obtain a temperature anomaly index includes:

[0042] The semiconductor module is photographed by an infrared camera in the temperature analysis mechanism based on the monitoring interval, the monitoring time, and to obtain a plurality of infrared temperature images, wherein the infrared temperature images include: a plurality of infrared pixels, and the infrared pixels include: infrared temperature values;

[0043] The following operations are performed on each of the multiple infrared temperature images:

[0044] Calculate the temperature average value according to multiple infrared pixel points in the infrared temperature image;

[0045] The following operations are performed on each of the multiple infrared pixels in the infrared temperature image:

[0046] Compare the infrared temperature value corresponding to the infrared pixel point with the preset temperature threshold;

[0047] If the infrared temperature value corresponding to the infrared pixel point is greater than the temperature threshold, the infrared pixel point is recorded as an over-temperature pixel point;

[0048] Summarizing the over-temperature pixels to obtain a plurality of over-temperature pixels, and determining the number of over-temperature pixels in the plurality of over-temperature pixels, wherein the number of over-temperature pixels is the number of over-temperature pixels in the plurality of over-temperature pixels;

[0049] Calculate the over-temperature ratio based on the over-temperature quantity;

[0050] The temperature mean and over-temperature ratio corresponding to the infrared temperature image are combined to obtain an infrared data set;

[0051] Aggregating the infrared data groups to obtain multiple infrared data groups;

[0052] A temperature anomaly index is calculated based on the plurality of infrared data sets.

[0053] Optionally, determining the current environment weight includes:

[0054] Confirm the current wind speed and rainfall;

[0055] The current weather wind speed and current weather rainfall are used to calculate the current environmental weight.

[0056] Optionally, the monitoring of the device housing by an environmental monitoring mechanism to obtain an operation stability index includes:

[0057] The sound sensor and vibration sensor in the environmental monitoring mechanism are used to monitor the device shell to obtain the internal noise intensity and shell vibration amplitude;

[0058] The operation stability index is calculated based on the internal noise intensity and the shell vibration amplitude.

[0059] Optionally, the multimodal monitoring model is as follows:

[0060]

[0061] Among them, Z G is the power distribution abnormality, ρ B is the electromagnetic anomaly weight, ρ T is the temperature anomaly weight, ρ E is the current environment weight, ψ T is the temperature anomaly index, ψ X is the running stability index, and tanh is the hyperbolic tangent function.

[0062] To achieve the above objectives, the present invention further provides a multi-modal photovoltaic inverter power distribution monitoring system, comprising:

[0063] a power distribution mechanism confirmation module, configured to receive a power distribution monitoring instruction, and identify a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a radiator; and to identify an electromagnetic monitoring mechanism, a temperature analysis mechanism, and an environmental monitoring mechanism, wherein the electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor; the temperature analysis mechanism includes: a high-definition camera and an infrared camera; the environmental monitoring mechanism includes: a sound sensor and a vibration sensor; the EMI monitor includes: a test antenna; wherein the light sensor, humidity sensor, sound sensor, and vibration sensor are all mounted on the surface of the device housing;

[0064] The modal data analysis module is used to obtain electromagnetic anomaly weights using a pre-built environmental database and an electromagnetic monitoring mechanism, perform electromagnetic analysis on the photovoltaic inverter using the electromagnetic monitoring mechanism to obtain an electromagnetic anomaly index, perform status assessment on the radiator using a temperature analysis mechanism to obtain a temperature anomaly weight, perform temperature image analysis on the semiconductor module using the temperature analysis mechanism to obtain a temperature anomaly index, confirm the current environmental weight, and monitor the device housing using the environmental monitoring mechanism to obtain an operation stability index;

[0065] The power distribution status assessment module is used to input the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight and operation stability index into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree;

[0066] The monitoring signal reminder module is used to compare the power distribution abnormality with the preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, the pre-built danger signal is sent to the pre-built inverter monitoring end to obtain the danger monitoring end. Otherwise, the pre-built safety signal is sent to the inverter monitoring end to obtain the safety monitoring end. The power distribution monitoring of the photovoltaic inverter is completed based on the danger monitoring end or the safety monitoring end.

[0067] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0068] a memory storing at least one instruction;

[0069] The processor executes the instructions stored in the memory to implement the above-mentioned photovoltaic inverter power distribution monitoring method based on multi-mode.

[0070] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned multi-modal photovoltaic inverter power distribution monitoring method.

[0071] The present invention is to solve the problems described in the background technology. The present invention receives a power distribution monitoring instruction and identifies a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device shell, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device and a radiator, and identifies an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environmental monitoring mechanism, wherein the electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor and a resistance monitor, the temperature analysis mechanism includes: a high-definition camera and an infrared camera, the environmental monitoring mechanism includes: a sound sensor and a vibration sensor, the EMI monitor includes: a test antenna, wherein the light sensor, the humidity sensor, the sound sensor and the vibration sensor are all installed on the surface of the device shell. It can be seen that the embodiment of the present invention provides a systematic and automated monitoring environment for the monitoring of photovoltaic inverters by pre-building an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environmental monitoring mechanism, and then uses the pre-built environmental database and the electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, and uses the electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index. It can be seen that the embodiment of the present invention combines the environmental database and the monitoring results of the current electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter, accurately confirm the abnormality degree of the photovoltaic inverter in terms of electrical performance, and improve the accuracy of monitoring the photovoltaic inverter. The temperature analysis mechanism is used to evaluate the state of the radiator to obtain the temperature anomaly weight, and the temperature analysis mechanism is used to evaluate the semiconductor module. The temperature image is analyzed to obtain the temperature anomaly index. It can be seen that the embodiment of the present invention simultaneously performs image analysis on the radiator and the semiconductor module through the temperature analysis mechanism, and takes into account the heat dissipation state and heat generation state of the photovoltaic inverter, thereby improving the accuracy of monitoring the photovoltaic inverter, confirming the current environmental weight, and using the environmental monitoring mechanism to monitor the device shell to obtain the operation stability index. It can be seen that the embodiment of the present invention accurately evaluates the operation stability of the components in the photovoltaic inverter by fusing sound and vibration data and combining the current environmental status, thereby improving the accuracy of monitoring the photovoltaic inverter, and inputs the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environmental weight and operation stability index into the pre-built multimodal monitoring model. In the embodiment of the present invention, the power distribution abnormality is obtained. It can be seen that the embodiment of the present invention uses a multimodal monitoring model to perform correlation analysis on the electrical performance, temperature rise risk and operation stability of the photovoltaic inverter, thereby improving the accuracy of monitoring the photovoltaic inverter, and comparing the power distribution abnormality with the preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, the pre-constructed danger signal is sent to the pre-constructed inverter monitoring end to obtain a danger monitoring end. Otherwise, the pre-constructed safety signal is sent to the inverter monitoring end to obtain a safety monitoring end. The power distribution monitoring of the photovoltaic inverter is completed based on the danger monitoring end or the safety monitoring end. It can be seen that the embodiment of the present invention automatically sends a danger signal or a safety signal to the inverter monitoring end through the power distribution abnormality, thereby improving the fault response efficiency and the degree of automation of monitoring.Therefore, the application can improve the accuracy and automation degree of monitoring the photovoltaic inverter. BRIEF DESCRIPTION OF DRAWINGS

[0072] Figure 1 A flowchart of a photovoltaic inverter power distribution monitoring method based on multi-modal provided by an embodiment of the application is shown in the figure.

[0073] Figure 2 A functional module diagram of a photovoltaic inverter power distribution monitoring system based on multi-modal provided by an embodiment of the application is shown in the figure.

[0074] Figure 3 A structural diagram of an electronic device for implementing the photovoltaic inverter power distribution monitoring method based on multi-modal provided by an embodiment of the application is shown in the figure.

[0075] REFERENCE SIGNS:

[0076] 1, electronic device; 10, processor; 11, memory; 12, bus.

[0077] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0078] It should be understood that the specific embodiments described herein are only used to explain the application and do not limit the application.

[0079] The embodiment of the application provides a photovoltaic inverter power distribution monitoring method based on multi-modal. The execution subject of the photovoltaic inverter power distribution monitoring method based on multi-modal includes but is not limited to at least one of the electronic devices such as a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the photovoltaic inverter power distribution monitoring method based on multi-modal can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster and the like.

[0080] REFERENCE Figure 1 A flowchart of a photovoltaic inverter power distribution monitoring method based on multi-modal provided by an embodiment of the application is shown in the figure. In this embodiment, the photovoltaic inverter power distribution monitoring method based on multi-modal includes:

[0081] S1, receiving a power distribution monitoring instruction, and confirming a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes a device shell, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device and a radiator.

[0082] It should be explained that the power distribution monitoring instruction is generally initiated by the monitor of the inverter monitoring center. For example, Xiao Zhang is a monitor of a certain inverter monitoring center. He now needs to monitor a certain photovoltaic inverter, so he initiates the power distribution monitoring instruction. Since each photovoltaic inverter has a corresponding number or code in the inverter monitoring terminal of the inverter monitoring center, the number or code of the photovoltaic inverter can be specified when initiating the power distribution monitoring instruction, thereby issuing a power distribution monitoring instruction only for a specific photovoltaic inverter. Then, the inverter monitoring center can confirm the corresponding photovoltaic inverter according to the number or code of the photovoltaic inverter corresponding to the power distribution monitoring instruction. The inverter monitoring center is a department in a photovoltaic power station used to monitor photovoltaic inverters.

[0083] It is understood that a photovoltaic inverter consists of: a device housing, photovoltaic input cables, distribution output cables, semiconductor modules, a grounding device, and a heat sink. The device housing is the structural shell that encloses, supports, and protects the components within the photovoltaic inverter. It is typically made of metal or high-strength composite materials to ensure the safety of the components in outdoor environments. The photovoltaic input cables are the conductors that transmit the direct current generated by photovoltaic devices (such as solar panels) to the photovoltaic inverter. The distribution output cables are the conductors that output the converted alternating current from the photovoltaic inverter to the grid or load. Semiconductor modules refer to the IGBT modules (insulated gate bipolar transistors) in the photovoltaic inverter. The grounding device refers to the grounding conductor in the photovoltaic inverter. Its main function is to provide a low-impedance current discharge path in the event of insulation failure, leakage, or lightning strike, ensuring the safety of the photovoltaic inverter. The heat sink is a device used to dissipate heat from the internal components of the photovoltaic inverter and includes metal heat sinks, heat pipes, and air cooling system blocks.

[0084] S2. Identify the electromagnetic monitoring mechanism, temperature analysis mechanism, and environmental monitoring mechanism. The electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The temperature analysis mechanism includes: a high-definition camera and an infrared camera. The environmental monitoring mechanism includes: a sound sensor and a vibration sensor. The EMI monitor includes: a test antenna. The light sensor, humidity sensor, sound sensor, and vibration sensor are all installed on the surface of the device housing.

[0085] It should be explained that the electromagnetic monitoring mechanism is a device that integrates a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The light sensor and humidity sensor are installed on the surface of the PV inverter housing to monitor the relative humidity and light intensity of the environment outside the PV inverter housing. The EMI monitor is an EMI test receiver that includes a test antenna, a biconical antenna, for monitoring low-frequency (30 MHz to 300 MHz) electromagnetic interference signals generated by the PV inverter during operation. The EMI monitor is installed at a preset electromagnetic position, where the distance between the electromagnetic position and the center of gravity of the PV inverter is within 3 to 10 meters. The specific electromagnetic position is manually set by the staff of the inverter monitoring center. The current sensor is a clamp-on ammeter fixed to the PV input cable and distribution output cable of the PV inverter to monitor the current in the PV input cable and the current in the distribution output cable. The resistance monitor is a clamp-on ground resistance meter installed on the grounding device of the PV inverter to detect the resistance of the grounding device. The temperature analysis mechanism is a device that integrates a high-definition camera and an infrared camera. The high-definition camera is a high-definition video camera, and the infrared camera is an infrared imager. The environmental monitoring mechanism is a device that integrates a sound sensor and a vibration sensor. Both the sound sensor and the vibration sensor are mounted on the surface of the device housing and are used to monitor the vibration amplitude of the device housing and the sound intensity of the noise inside the device housing, respectively.

[0086] S3. Use the pre-built environmental database and electromagnetic monitoring agency to obtain the electromagnetic anomaly weight, use the electromagnetic monitoring agency to perform electromagnetic analysis on the photovoltaic inverter, and obtain the electromagnetic anomaly index.

[0087] In detail, the method of obtaining electromagnetic anomaly weights using a pre-built environmental database and an electromagnetic monitoring mechanism includes:

[0088] Determine the current time and the current time range based on the current time and the preset reference duration;

[0089] Extracting multiple historical moment data from the environmental database based on the current time range, wherein the historical moment data includes: historical light intensity and historical humidity;

[0090] Extracting multiple historical light intensities and multiple historical humidity data from multiple historical moments, and calculating a current reference light intensity based on the multiple historical light intensities, wherein the current reference light intensity is an average value of the multiple historical light intensities;

[0091] Calculate current reference humidity based on multiple historical humidity levels;

[0092] Acquire multiple current light intensities and multiple current humidity levels based on a preset monitoring interval, a preset monitoring time, a light sensor, and a humidity sensor;

[0093] The electromagnetic anomaly weight is calculated based on multiple current light intensities, multiple current humidity levels, current reference light intensity, and current reference humidity. The calculation formula is as follows:

[0094]

[0095] Among them, ρ B is the electromagnetic anomaly weight, LX i is the i-th current light intensity among multiple current light intensities, S i is the i-th current humidity among multiple current humidity, and are the current reference light intensity and the current reference humidity respectively, and n is the number of current light intensities in multiple current light intensities.

[0096] It should be explained that the current moment refers to the time at this moment. The minimum value of the current time range is the moment obtained by subtracting the reference duration from the current moment, and the maximum value of the current time range is the moment obtained by adding the reference duration to the current moment. The environmental database is a database that stores multiple environmental data monitored by light sensors and humidity sensors over a recent period of time. The environmental data consists of light intensity and relative humidity. The recent period is optionally 30 days, and the environmental database is pre-built by staff at the inverter monitoring center.

[0097] For example, if the time at this moment is 10:00:00, the current time is 10:00:00. If the reference time is half an hour, the current time range is [09:30:00, 10:30:00]. Then, multiple environmental data within 30 days and located in the time period of [09:30:00, 10:30:00] are extracted from the environmental database, and the multiple environmental data are used as multiple historical moment data, and the historical moment data include: historical light intensity and historical humidity. The historical light intensity is the light intensity in the environmental data, and the historical humidity is the relative humidity in the environmental data.

[0098] It is understandable that the method for calculating the current reference humidity based on multiple historical humidity values ​​is the same as the method for calculating the current reference light intensity based on multiple historical light intensities, and will not be described in detail here.

[0099] For example, if the monitoring interval is 1 second and the monitoring time is 10 seconds, the light sensor and humidity sensor are used to obtain the light intensity and relative humidity in the current environment once every 1 second, and finally 10 current light intensities and 10 current humidity are obtained. The current light intensity is the light intensity at the deployment location of the light sensor, and the current humidity is the relative humidity of the air at the deployment location of the humidity sensor. The monitoring interval and monitoring time are both manually set by the staff of the inverter monitoring center.

[0100] It should be understood that when the current light intensity is too high, the output current generated by the photovoltaic modules under the light will increase accordingly, resulting in an increase in the load borne by the input end of the photovoltaic inverter. When the current humidity is too high, the insulation performance inside the photovoltaic inverter or at the terminal is more likely to degrade, resulting in an increased probability of electrical faults such as short circuit or leakage. The electromagnetic anomaly weight reflects the risk level of electrical performance failure of the photovoltaic inverter. The greater the electromagnetic anomaly weight, the higher the risk of electrical performance failure of the photovoltaic inverter.

[0101] In detail, the use of the electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index includes:

[0102] Lift and align the test antenna of the EMI monitor in the electromagnetic monitoring mechanism to prepare the monitor;

[0103] Based on the preset monitoring frequency band and the prepared monitor, the photovoltaic inverter is monitored for electromagnetic interference to obtain an electromagnetic spectrum curve, wherein the horizontal axis of the electromagnetic spectrum curve is the frequency and the vertical axis of the electromagnetic spectrum curve is the amplitude;

[0104] Performing a uniform division operation on the monitoring frequency band based on a preset frequency band interval to obtain multiple frequency ranges;

[0105] For each of the multiple frequency ranges, perform the following operations:

[0106] Identify a target spectrum curve in the electromagnetic spectrum curve based on the frequency range, and confirm the maximum interference amplitude of the target spectrum curve;

[0107] Summarizing the maximum interference amplitudes to obtain multiple maximum interference amplitudes, and calculating an average interference amplitude based on the multiple maximum interference amplitudes, wherein the average interference amplitude is an average value of the multiple maximum interference amplitudes;

[0108] The photovoltaic input cable in the photovoltaic inverter is monitored based on the monitoring interval, the monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple input current values;

[0109] Based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism, the distribution output cable in the photovoltaic inverter is monitored to obtain multiple output current values;

[0110] Calculating an input current mean and an input current variance based on a plurality of input current values, and obtaining an output current mean and an output current variance based on a plurality of output current values;

[0111] Use a resistance monitor to detect the grounding device in the photovoltaic inverter to obtain the grounding resistance;

[0112] The electromagnetic anomaly index is calculated based on the average interference amplitude, input current mean, input current variance, output current mean, output current variance and ground resistance.

[0113] It should be explained that the lifting and aligning of the test antenna of the EMI monitor in the electromagnetic monitoring mechanism means: lifting the test antenna of the EMI monitor to a preset monitoring height, and aligning the receiving direction of the test antenna with the center of gravity of the photovoltaic inverter, wherein the monitoring height is based on the ground, and the monitoring height is manually set by the staff of the inverter monitoring center. Preferably, the monitoring height is 3 meters.

[0114] It can be understood that the monitoring frequency band is 30MHz to 300MHz. The electromagnetic interference monitoring of the photovoltaic inverter based on the preset monitoring frequency band and the preparation monitor to obtain the electromagnetic spectrum curve means: using the preparation monitor to monitor the electromagnetic interference signal generated by the photovoltaic inverter within the monitoring frequency band, and generating a frequency-amplitude relationship curve in the preparation monitor based on the frequency distribution of the electromagnetic interference signal and the amplitude corresponding to each frequency. The curve is the electromagnetic spectrum curve, and the technology of using the preparation monitor to monitor the electromagnetic interference signal generated by the photovoltaic inverter within the monitoring frequency band, and generating a frequency-amplitude relationship curve in the preparation monitor based on the frequency distribution of the electromagnetic interference signal and the amplitude corresponding to each frequency is an existing technology and will not be repeated here.

[0115] For example, if the frequency band interval is 10 MHz, the range of [30 MHz, 300 MHz] is evenly divided to obtain multiple frequency ranges: {[30 MHz, 40 MHz], [40 MHz, 50 MHz] . . . [290 MHz, 300 MHz]}.

[0116] It should be understood that identifying the target spectrum curve in the electromagnetic spectrum curve based on the frequency range means extracting a curve segment within the frequency range from the electromagnetic spectrum curve to obtain the target spectrum curve. The maximum interference amplitude is the largest amplitude among all amplitudes corresponding to the target spectrum curve.

[0117] For example, if the monitoring interval is 1 second and the monitoring time is 10 seconds, the current value in the photovoltaic input cable is monitored once every 1 second using the current sensor, and finally 10 current values ​​are obtained, which are the input current values.

[0118] It can be understood that the method of monitoring the distribution output cable in the photovoltaic inverter based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple output current values ​​is the same as the method of monitoring the photovoltaic input cable in the photovoltaic inverter based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple input current values, and will not be repeated here.

[0119] It should be explained that the grounding resistance is the size of the resistance of the grounding device, and the technology of using a resistance monitor to detect the grounding device in the photovoltaic inverter to obtain the grounding resistance and the technology of monitoring the photovoltaic input cable in the photovoltaic inverter based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple input current values ​​are all existing technologies and will not be repeated here.

[0120] In detail, the calculation formula of the electromagnetic anomaly index is as follows:

[0121]

[0122] Among them, ψ B is the electromagnetic anomaly index, is the average interference amplitude, and are the mean input current and the mean output current, and are the preset reference input current value and the preset reference output current value respectively. and are the input current variance and output current variance, R L is the grounding resistance, and e is a natural constant.

[0123] It should be understood that the greater the deviation of the input current mean from the reference input current value and the greater the deviation of the output current mean from the reference output current value, the electrical components in the photovoltaic inverter may have faults such as short circuit or aging. When the input current variance and the output current variance are larger, the fluctuation degree of multiple input current values ​​and multiple output current values ​​is greater. When the average interference amplitude is larger, that is, the radiated electromagnetic interference generated by the photovoltaic inverter is greater, it means that the electrical components in the photovoltaic inverter may have structural damage, resulting in high-frequency energy that could have been absorbed or converted being directly discharged in the form of radiation. When the grounding resistance is too large, external interference current (such as lightning strikes) and fault current in the photovoltaic inverter cannot be effectively introduced into the earth. Therefore, the electromagnetic anomaly index reflects the degree of abnormality in the electrical performance of the photovoltaic inverter. The larger the electromagnetic anomaly index, the greater the degree of abnormality in the electrical performance of the photovoltaic inverter.

[0124] S4. Using a temperature analysis mechanism to evaluate the state of the radiator to obtain a temperature anomaly weight, and using the temperature analysis mechanism to analyze a temperature image of the semiconductor module to obtain a temperature anomaly index.

[0125] Specifically, the method of using the temperature analysis mechanism to evaluate the status of the radiator and obtain the temperature anomaly weight includes:

[0126] The radiator is photographed using a high-definition camera in the temperature analysis mechanism to obtain an image of the radiator surface;

[0127] Inputting the pre-constructed initial radiator image and the radiator surface image into the pre-constructed image comparison model to obtain image similarity;

[0128] The temperature anomaly weight is calculated using image similarity. The calculation formula is as follows:

[0129] ρ T =1-γ s

[0130] Among them, ρ T is the temperature anomaly weight, γ s is the image similarity.

[0131] It should be explained that the initial radiator image refers to an image of the radiator captured by a high-definition camera when the PV inverter is first put into operation. The radiator surface image refers to an image of the radiator surface captured by the high-definition camera.

[0132] It can be understood that the image comparison model is constructed based on a convolutional neural network, and the main operating principle of the image comparison model is: first, the convolutional neural network in the image comparison model is used to perform multi-layer convolution, pooling and activation function processing on the initial radiator image and the radiator surface image to obtain two feature vectors, and then the cosine similarity of the two feature vectors is calculated. The cosine similarity is the image similarity, and the above process is a disclosed technical solution, and the embodiments of the present invention will not be repeated here.

[0133] It should be understood that the smaller the image similarity, the greater the difference between the current radiator surface state and the radiator surface state when the photovoltaic inverter was first put into use, indicating that the degree of dust accumulation, foreign matter attachment or surface aging on the radiator surface is more serious, which in turn leads to a decrease in its heat dissipation performance. Therefore, the temperature anomaly weight reflects the risk level of temperature anomalies in the photovoltaic inverter. The larger the temperature anomaly weight, the higher the risk of temperature anomalies in the photovoltaic inverter.

[0134] Specifically, the method of analyzing the temperature image of the semiconductor module using the temperature analysis mechanism to obtain the temperature anomaly index includes:

[0135] The semiconductor module is photographed by an infrared camera in the temperature analysis mechanism based on the monitoring interval, the monitoring time, and to obtain a plurality of infrared temperature images, wherein the infrared temperature images include: a plurality of infrared pixels, and the infrared pixels include: infrared temperature values;

[0136] The following operations are performed on each of the multiple infrared temperature images:

[0137] The temperature mean is calculated based on multiple infrared pixels in the infrared temperature image. The calculation formula is as follows:

[0138]

[0139] in, is the mean temperature, T i is the infrared temperature value of the i-th infrared pixel in the plurality of infrared pixels, and m is the number of infrared pixels in the plurality of infrared pixels;

[0140] The following operations are performed on each of the multiple infrared pixels in the infrared temperature image:

[0141] Compare the infrared temperature value corresponding to the infrared pixel point with the preset temperature threshold;

[0142] If the infrared temperature value corresponding to the infrared pixel point is greater than the temperature threshold, the infrared pixel point is recorded as an over-temperature pixel point;

[0143] Summarizing the over-temperature pixels to obtain a plurality of over-temperature pixels, and determining the number of over-temperature pixels in the plurality of over-temperature pixels, wherein the number of over-temperature pixels is the number of over-temperature pixels in the plurality of over-temperature pixels;

[0144] The overtemperature ratio is calculated based on the number of overtemperatures. The calculation formula is as follows:

[0145]

[0146] Among them, K T is the overtemperature ratio, N T is the number of overtemperatures;

[0147] The temperature mean and over-temperature ratio corresponding to the infrared temperature image are combined to obtain an infrared data set;

[0148] Aggregating the infrared data groups to obtain multiple infrared data groups;

[0149] The temperature anomaly index is calculated based on multiple infrared data sets. The calculation formula is as follows:

[0150]

[0151] Among them, ψ T is the temperature anomaly index, is the temperature average of the i-th infrared data set among multiple infrared data sets, K i is the overtemperature ratio of the i-th infrared data group in multiple infrared data groups, T y is the temperature threshold, and L is the number of infrared data groups in the multiple infrared data groups.

[0152] For example, if the monitoring interval is 1 second and the monitoring time is 10 seconds, the infrared camera takes a picture of the semiconductor module every 1 second, and finally obtains 10 infrared images, which are infrared temperature images. Infrared pixels are pixels in the infrared temperature image.

[0153] It should be understood that since the infrared camera receives the infrared radiation energy emitted by each point on the semiconductor module through the internal infrared detector array, converts it into an electrical signal and then restores it to a temperature value, thereby generating an infrared temperature image, each infrared pixel in the infrared temperature image corresponds to an infrared temperature value, which reflects the temperature of the point corresponding to the corresponding infrared pixel in reality.

[0154] It should be explained that the temperature threshold is manually set by the staff of the inverter monitoring center. Optionally, the temperature threshold is 90 degrees Celsius.

[0155] For example, if the average temperature is 70° C. and the overtemperature ratio is 0.02, the infrared data set is: [70° C., 0.02].

[0156] It is understandable that the temperature anomaly index reflects the degree of abnormality of the surface temperature of the semiconductor module in the photovoltaic inverter. The larger the temperature anomaly index, the greater the degree of abnormality of the surface temperature of the semiconductor module in the photovoltaic inverter.

[0157] S5. Determine the current environmental weight, use an environmental monitoring mechanism to monitor the device housing, and obtain an operation stability index.

[0158] Specifically, determining the current environment weight includes:

[0159] Confirm the current wind speed and rainfall;

[0160] The current environmental weight is calculated using the current wind speed and current rainfall. The calculation formula is as follows:

[0161]

[0162] Among them, ρ E is the current environment weight, f d is the current weather wind speed, P d The rainfall in the current weather.

[0163] It should be explained that the current position refers to the actual position of the PV inverter.

[0164] For example, at 12:00 on a certain day in history, the precipitation and wind speed at the location of the photovoltaic inverter were obtained from the website of the China Meteorological Administration as 10 mm and 2.5 m / s, respectively. That is, the current wind speed is 2.5 m / s and the current rainfall is 10 mm.

[0165] It is understandable that wind and rainfall in the environment will cause mechanical vibration and acoustic interference to the device housing of the photovoltaic inverter, thereby affecting the stability of the measurement of the environmental monitoring mechanism installed thereon. Therefore, the current environmental weight reflects the degree of interference of external environmental factors on the environmental monitoring mechanism. The greater the current environmental weight, the less interference the external environmental factors have on the environmental monitoring mechanism.

[0166] In detail, the use of the environmental monitoring mechanism to monitor the device housing to obtain the operation stability index includes:

[0167] The sound sensor and vibration sensor in the environmental monitoring mechanism are used to monitor the device housing to obtain the internal noise intensity and housing vibration amplitude;

[0168] The operation stability index is calculated based on the internal noise intensity and the housing vibration amplitude. The calculation formula is as follows:

[0169]

[0170] Among them, ψ X is the operation stability index, Su x is the internal noise intensity, F k is the vibration amplitude of the shell, and ln is the natural logarithm.

[0171] It should be explained that the internal noise intensity refers to the intensity of the noise inside the device shell, and the shell vibration amplitude refers to the amplitude of the vibration of the device shell caused by the operation of mechanical parts or external disturbances.

[0172] It is understandable that the operation stability index reflects the operation smoothness of the internal components of the photovoltaic inverter. The larger the operation stability index, the greater the operation smoothness of the internal components of the photovoltaic inverter.

[0173] S6. Input the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight, and operation stability index into a pre-built multimodal monitoring model to obtain the power distribution anomaly degree.

[0174] In detail, the multimodal monitoring model is as follows:

[0175]

[0176] wherein, Z G is the power distribution abnormality degree, p B is the electromagnetic abnormality weight, p T is the temperature abnormality weight, p E is the current environment weight, p T is the temperature abnormality index, p X is the operation stability index, and tanh is the hyperbolic tangent function.

[0177] It should be understood that the power distribution abnormality degree reflects the abnormality degree of the overall operation state of the photovoltaic inverter, and the greater the power distribution abnormality degree, the greater the abnormality degree of the overall operation state of the photovoltaic inverter.

[0178] S7, comparing the power distribution abnormality degree with a preset abnormality threshold value, if the power distribution abnormality degree is greater than or equal to the abnormality threshold value, a pre-constructed danger signal is sent to a pre-constructed inverter monitoring terminal to obtain a danger monitoring terminal, otherwise a pre-constructed safety signal is sent to the inverter monitoring terminal to obtain a safety monitoring terminal.

[0179] It should be explained that the inverter monitoring terminal is a software pre-programmed in the computer of the inverter monitoring center through python or C++, which can parse the information contained in the danger signal or the safety signal and display on the page of the computer of the inverter monitoring center.

[0180] It can be understood that the danger signal is a data packet containing danger information, and the danger information is a piece of text for reminding the monitor of the inverter monitoring center that the photovoltaic inverter is abnormal. Optionally, the piece of text for reminding the monitor of the inverter monitoring center that the photovoltaic inverter is abnormal is: “photovoltaic inverter appears abnormal risk, please check or repair in time!”. The danger monitoring terminal is the inverter monitoring terminal after receiving the danger signal. The safety signal is a data packet containing safety information, and the safety information is a piece of text for informing the monitor of the photovoltaic inverter that the photovoltaic inverter is running normally. Optionally, the piece of text for informing the monitor of the photovoltaic inverter that the photovoltaic inverter is running normally is: “photovoltaic inverter is running normally”. The safety monitoring terminal is the inverter monitoring terminal after receiving the safety signal. The abnormality threshold value is a value artificially set by the monitor of the inverter monitoring center according to historical data. Optionally, the average value of a plurality of power distribution abnormality degrees corresponding to a plurality of times of photovoltaic inverter failures in history is taken as the abnormality threshold value.

[0181] S8, completing the power distribution monitoring of the photovoltaic inverter based on the danger monitoring terminal or the safety monitoring terminal.

[0182] For example, when the monitor of the inverter monitoring center sees the text "The photovoltaic inverter has abnormal risks, please inspect or repair it in time" displayed on the page of the danger monitoring end, he can promptly notify the maintenance personnel to repair the photovoltaic inverter in time. When the monitor of the inverter monitoring center sees the text "The photovoltaic inverter is in normal operation" displayed on the page of the safety monitoring end, he can confirm that the current operation status of the photovoltaic inverter is normal and wait for the next time monitoring is needed to initiate the distribution monitoring instruction again.

[0183] The present invention is to solve the problems described in the background technology. The present invention receives a power distribution monitoring instruction and identifies a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device shell, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device and a radiator, and identifies an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environmental monitoring mechanism, wherein the electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor and a resistance monitor, the temperature analysis mechanism includes: a high-definition camera and an infrared camera, the environmental monitoring mechanism includes: a sound sensor and a vibration sensor, the EMI monitor includes: a test antenna, wherein the light sensor, the humidity sensor, the sound sensor and the vibration sensor are all installed on the surface of the device shell. It can be seen that the embodiment of the present invention provides a systematic and automated monitoring environment for the monitoring of photovoltaic inverters by pre-building an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environmental monitoring mechanism, and then uses the pre-built environmental database and the electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, and uses the electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index. It can be seen that the embodiment of the present invention combines the environmental database and the monitoring results of the current electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter, accurately confirm the abnormality degree of the photovoltaic inverter in terms of electrical performance, and improve the accuracy of monitoring the photovoltaic inverter. The temperature analysis mechanism is used to evaluate the state of the radiator to obtain the temperature anomaly weight, and the temperature analysis mechanism is used to evaluate the semiconductor module. The temperature image is analyzed to obtain the temperature anomaly index. It can be seen that the embodiment of the present invention simultaneously performs image analysis on the radiator and the semiconductor module through the temperature analysis mechanism, and takes into account the heat dissipation state and heat generation state of the photovoltaic inverter, thereby improving the accuracy of monitoring the photovoltaic inverter, confirming the current environmental weight, and using the environmental monitoring mechanism to monitor the device shell to obtain the operation stability index. It can be seen that the embodiment of the present invention accurately evaluates the operation stability of the components in the photovoltaic inverter by fusing sound and vibration data and combining the current environmental status, thereby improving the accuracy of monitoring the photovoltaic inverter, and inputs the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environmental weight and operation stability index into the pre-built multimodal monitoring model. In the embodiment of the present invention, the power distribution abnormality is obtained. It can be seen that the embodiment of the present invention uses a multimodal monitoring model to perform correlation analysis on the electrical performance, temperature rise risk and operation stability of the photovoltaic inverter, thereby improving the accuracy of monitoring the photovoltaic inverter, and comparing the power distribution abnormality with the preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, the pre-constructed danger signal is sent to the pre-constructed inverter monitoring end to obtain a danger monitoring end. Otherwise, the pre-constructed safety signal is sent to the inverter monitoring end to obtain a safety monitoring end. The power distribution monitoring of the photovoltaic inverter is completed based on the danger monitoring end or the safety monitoring end. It can be seen that the embodiment of the present invention automatically sends a danger signal or a safety signal to the inverter monitoring end through the power distribution abnormality, thereby improving the fault response efficiency and the degree of automation of monitoring.Therefore, the present invention can improve the accuracy and automation level of monitoring photovoltaic inverters.

[0184] like Figure 2 , which is a functional module diagram of a multi-modal photovoltaic inverter power distribution monitoring system provided by an embodiment of the present invention.

[0185] The multimodal photovoltaic inverter power distribution monitoring system 100 described in the present invention can be installed in an electronic device 1. Depending on the functionality to be implemented, the multimodal photovoltaic inverter power distribution monitoring system 100 can include a power distribution mechanism confirmation module 101, a modal data analysis module 102, a power distribution status assessment module 103, and a monitoring signal reminder module 104. A module, also referred to as a unit, refers to a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0186] The power distribution mechanism confirmation module 101 is used to receive a power distribution monitoring instruction, and confirm a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device and a radiator, and confirm an electromagnetic monitoring mechanism, a temperature analysis mechanism and an environmental monitoring mechanism, wherein the electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor and a resistance monitor, the temperature analysis mechanism includes: a high-definition camera and an infrared camera, the environmental monitoring mechanism includes: a sound sensor and a vibration sensor, and the EMI monitor includes: a test antenna, wherein the light sensor, humidity sensor, sound sensor and vibration sensor are all installed on the surface of the device housing;

[0187] The modal data analysis module 102 is configured to utilize a pre-built environmental database and an electromagnetic monitoring mechanism to obtain an electromagnetic anomaly weight, utilize the electromagnetic monitoring mechanism to perform electromagnetic analysis on the photovoltaic inverter to obtain an electromagnetic anomaly index, utilize a temperature analysis mechanism to perform a status assessment on the radiator to obtain a temperature anomaly weight, utilize the temperature analysis mechanism to perform temperature image analysis on the semiconductor module to obtain a temperature anomaly index, determine the current environmental weight, and utilize the environmental monitoring mechanism to monitor the device housing to obtain an operation stability index;

[0188] The power distribution status evaluation module 103 is used to input the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight and operation stability index into a pre-built multi-modal monitoring model to obtain the power distribution anomaly degree;

[0189] The monitoring signal reminder module 104 is used to compare the power distribution abnormality with a preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, a pre-constructed danger signal is sent to a pre-constructed inverter monitoring terminal to obtain a danger monitoring terminal. Otherwise, a pre-constructed safety signal is sent to the inverter monitoring terminal to obtain a safety monitoring terminal. The power distribution monitoring of the photovoltaic inverter is completed based on the danger monitoring terminal or the safety monitoring terminal.

[0190] In detail, the modules in the multi-modal photovoltaic inverter power distribution monitoring system 100 according to the embodiment of the present invention are used in the same manner as above. Figure 1 The same technical means as the multi-modal photovoltaic inverter distribution monitoring method described in the previous section can produce the same technical effects, so they will not be repeated here.

[0191] like Figure 3 , which is a structural diagram of an electronic device 1 for implementing a photovoltaic inverter power distribution monitoring method based on multi-mode according to an embodiment of the present invention.

[0192] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a multi-modal photovoltaic inverter power distribution monitoring method program.

[0193] The memory 11 includes at least one type of readable storage medium, including a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Furthermore, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the multi-modal photovoltaic inverter power distribution monitoring method program, but can also be used to temporarily store data that has been output or is to be output.

[0194] In some embodiments, the processor 10 may be comprised of an integrated circuit, such as a single packaged integrated circuit or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or runs programs or modules stored in the memory 11 (e.g., a multi-modal photovoltaic inverter power distribution monitoring method program) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0195] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0196] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0197] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering the various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management device, thereby implementing functions such as charging management, discharging management, and power consumption management through the power management device. The power source may further include any components such as one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0198] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0199] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0200] The multi-modal photovoltaic inverter power distribution monitoring method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve the following:

[0201] receiving a power distribution monitoring instruction, and identifying a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a heat sink;

[0202] Identify the electromagnetic monitoring mechanism, temperature analysis mechanism, and environmental monitoring mechanism. The electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The temperature analysis mechanism includes: a high-definition camera and an infrared camera. The environmental monitoring mechanism includes: a sound sensor and a vibration sensor. The EMI monitor includes: a test antenna. The light sensor, humidity sensor, sound sensor, and vibration sensor are all installed on the surface of the device housing.

[0203] Using the pre-built environmental database and electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, the electromagnetic monitoring mechanism is used to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index;

[0204] Use the temperature analysis mechanism to evaluate the status of the radiator and obtain the temperature anomaly weight. Use the temperature analysis mechanism to analyze the temperature image of the semiconductor module and obtain the temperature anomaly index.

[0205] Determine the current environmental weight, use the environmental monitoring agency to monitor the device shell, and obtain the operation stability index;

[0206] The electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight, and operation stability index are input into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree;

[0207] Compare the power distribution abnormality with a preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, send a pre-built danger signal to a pre-built inverter monitoring terminal to obtain a danger monitoring terminal. Otherwise, send a pre-built safety signal to the inverter monitoring terminal to obtain a safety monitoring terminal.

[0208] Complete power distribution monitoring of photovoltaic inverters based on the danger monitoring terminal or the safety monitoring terminal.

[0209] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0210] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0211] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0212] receiving a power distribution monitoring instruction, and identifying a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a heat sink;

[0213] Identify the electromagnetic monitoring mechanism, temperature analysis mechanism, and environmental monitoring mechanism. The electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The temperature analysis mechanism includes: a high-definition camera and an infrared camera. The environmental monitoring mechanism includes: a sound sensor and a vibration sensor. The EMI monitor includes: a test antenna. The light sensor, humidity sensor, sound sensor, and vibration sensor are all installed on the surface of the device housing.

[0214] Using the pre-built environmental database and electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, the electromagnetic monitoring mechanism is used to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index;

[0215] Use the temperature analysis mechanism to evaluate the status of the radiator and obtain the temperature anomaly weight. Use the temperature analysis mechanism to analyze the temperature image of the semiconductor module and obtain the temperature anomaly index.

[0216] Determine the current environmental weight, use the environmental monitoring agency to monitor the device shell, and obtain the operation stability index;

[0217] The electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight, and operation stability index are input into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree;

[0218] Compare the power distribution abnormality with a preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, send a pre-built danger signal to a pre-built inverter monitoring terminal to obtain a danger monitoring terminal. Otherwise, send a pre-built safety signal to the inverter monitoring terminal to obtain a safety monitoring terminal.

[0219] Complete power distribution monitoring of photovoltaic inverters based on the danger monitoring terminal or the safety monitoring terminal.

[0220] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0221] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0222] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0223] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0224] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. 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.

Claims

1. A photovoltaic inverter power distribution monitoring method based on multi-modality, characterized in that: The method comprises: receiving a power distribution monitoring instruction, and identifying a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a heat sink; Identify the electromagnetic monitoring mechanism, temperature analysis mechanism, and environmental monitoring mechanism. The electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor. The temperature analysis mechanism includes: a high-definition camera and an infrared camera. The environmental monitoring mechanism includes: a sound sensor and a vibration sensor. The EMI monitor includes: a test antenna. The light sensor, humidity sensor, sound sensor, and vibration sensor are all installed on the surface of the device housing. Using the pre-built environmental database and electromagnetic monitoring mechanism to obtain the electromagnetic anomaly weight, the electromagnetic monitoring mechanism is used to perform electromagnetic analysis on the photovoltaic inverter to obtain the electromagnetic anomaly index; Use the temperature analysis mechanism to evaluate the status of the radiator and obtain the temperature anomaly weight. Use the temperature analysis mechanism to analyze the temperature image of the semiconductor module and obtain the temperature anomaly index. Determine the current environmental weight, use the environmental monitoring agency to monitor the device shell, and obtain the operation stability index; The electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight, and operation stability index are input into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree; Compare the power distribution abnormality with a preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, send a pre-built danger signal to a pre-built inverter monitoring terminal to obtain a danger monitoring terminal. Otherwise, send a pre-built safety signal to the inverter monitoring terminal to obtain a safety monitoring terminal. Complete power distribution monitoring of photovoltaic inverters based on the danger monitoring terminal or the safety monitoring terminal.

2. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 1, characterized in that: The method of obtaining electromagnetic anomaly weights by using a pre-built environmental database and an electromagnetic monitoring mechanism includes: Determine the current time and the current time range based on the current time and the preset reference duration; Extracting multiple historical moment data from the environmental database based on the current time range, wherein the historical moment data includes: historical light intensity and historical humidity; Extracting multiple historical light intensities and multiple historical humidity data from multiple historical moments, and calculating a current reference light intensity based on the multiple historical light intensities, wherein the current reference light intensity is an average value of the multiple historical light intensities; Calculate current reference humidity based on multiple historical humidity levels; Acquire multiple current light intensities and multiple current humidity levels based on a preset monitoring interval, a preset monitoring time, a light sensor, and a humidity sensor; The electromagnetic anomaly weight is calculated based on multiple current light intensities, multiple current humidity levels, current reference light intensities, and current reference humidity.

3. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 2, characterized in that: The electromagnetic analysis of the photovoltaic inverter using the electromagnetic monitoring mechanism to obtain the electromagnetic anomaly index includes: Lift and align the test antenna of the EMI monitor in the electromagnetic monitoring mechanism to prepare the monitor; Based on the preset monitoring frequency band and the prepared monitor, the photovoltaic inverter is monitored for electromagnetic interference to obtain an electromagnetic spectrum curve, wherein the horizontal axis of the electromagnetic spectrum curve is the frequency and the vertical axis of the electromagnetic spectrum curve is the amplitude; Performing a uniform division operation on the monitoring frequency band based on a preset frequency band interval to obtain multiple frequency ranges; For each of the multiple frequency ranges, perform the following operations: Identify a target spectrum curve in the electromagnetic spectrum curve based on the frequency range, and confirm the maximum interference amplitude of the target spectrum curve; Summarizing the maximum interference amplitudes to obtain multiple maximum interference amplitudes, and calculating an average interference amplitude based on the multiple maximum interference amplitudes, wherein the average interference amplitude is an average value of the multiple maximum interference amplitudes; The photovoltaic input cable in the photovoltaic inverter is monitored based on the monitoring interval, the monitoring time and the current sensor in the electromagnetic monitoring mechanism to obtain multiple input current values; Based on the monitoring interval, monitoring time and the current sensor in the electromagnetic monitoring mechanism, the distribution output cable in the photovoltaic inverter is monitored to obtain multiple output current values; Calculating an input current mean and an input current variance based on a plurality of input current values, and obtaining an output current mean and an output current variance based on a plurality of output current values; Use a resistance monitor to detect the grounding device in the photovoltaic inverter to obtain the grounding resistance; The electromagnetic anomaly index is calculated based on the average interference amplitude, input current mean, input current variance, output current mean, output current variance and grounding resistance.

4. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 3, characterized in that: The calculation formula of the electromagnetic anomaly index is as follows: Among them, ψ B is the electromagnetic anomaly index, is the average interference amplitude, and are the mean input current and the mean output current, and are the preset reference input current value and the preset reference output current value respectively. and are the input current variance and output current variance, R L is the grounding resistance, and e is a natural constant.

5. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 4, characterized in that: The method of using the temperature analysis mechanism to evaluate the state of the radiator and obtain the temperature anomaly weight includes: The radiator is photographed using a high-definition camera in the temperature analysis mechanism to obtain an image of the radiator surface; Inputting the pre-constructed initial radiator image and the radiator surface image into the pre-constructed image comparison model to obtain image similarity; The temperature anomaly weight is calculated using image similarity.

6. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 5, characterized in that: The method of performing temperature image analysis on the semiconductor module using the temperature analysis mechanism to obtain the temperature anomaly index includes: The semiconductor module is photographed by an infrared camera in the temperature analysis mechanism based on the monitoring interval, the monitoring time, and to obtain a plurality of infrared temperature images, wherein the infrared temperature images include: a plurality of infrared pixels, and the infrared pixels include: infrared temperature values; The following operations are performed on each of the multiple infrared temperature images: Calculate the temperature average value according to multiple infrared pixel points in the infrared temperature image; The following operations are performed on each of the multiple infrared pixels in the infrared temperature image: Compare the infrared temperature value corresponding to the infrared pixel point with the preset temperature threshold; If the infrared temperature value corresponding to the infrared pixel point is greater than the temperature threshold, the infrared pixel point is recorded as an over-temperature pixel point; Summarizing the over-temperature pixels to obtain a plurality of over-temperature pixels, and determining the number of over-temperature pixels in the plurality of over-temperature pixels, wherein the number of over-temperature pixels is the number of over-temperature pixels in the plurality of over-temperature pixels; Calculate the over-temperature ratio based on the over-temperature quantity; The temperature mean and over-temperature ratio corresponding to the infrared temperature image are combined to obtain an infrared data set; Aggregating the infrared data groups to obtain multiple infrared data groups; A temperature anomaly index is calculated based on the plurality of infrared data sets.

7. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 6, characterized in that: Determining the current environment weight includes: Confirm the current wind speed and rainfall; The current environmental weight is calculated using the current wind speed and current rainfall.

8. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 7, characterized in that: The environmental monitoring mechanism is used to monitor the device housing to obtain an operation stability index, including: The sound sensor and vibration sensor in the environmental monitoring mechanism are used to monitor the device housing to obtain the internal noise intensity and housing vibration amplitude; The operation stability index is calculated based on the internal noise intensity and the shell vibration amplitude.

9. The photovoltaic inverter power distribution monitoring method based on multi-mode according to claim 8, characterized in that: The multimodal monitoring model is as follows: Among them, Z G is the power distribution abnormality, ρ B is the electromagnetic anomaly weight, ρ T is the temperature anomaly weight, ρ E is the current environment weight, ψ T is the temperature anomaly index, ψ X is the running stability index, and tanh is the hyperbolic tangent function.

10. A photovoltaic inverter power distribution monitoring system based on multi-mode, characterized in that: The system comprises: a power distribution mechanism confirmation module, configured to receive a power distribution monitoring instruction, and identify a photovoltaic inverter based on the power distribution monitoring instruction, wherein the photovoltaic inverter includes: a device housing, a photovoltaic input cable, a power distribution output cable, a semiconductor module, a grounding device, and a radiator; and to identify an electromagnetic monitoring mechanism, a temperature analysis mechanism, and an environmental monitoring mechanism, wherein the electromagnetic monitoring mechanism includes: a light sensor, a humidity sensor, an EMI monitor, a current sensor, and a resistance monitor; the temperature analysis mechanism includes: a high-definition camera and an infrared camera; the environmental monitoring mechanism includes: a sound sensor and a vibration sensor; the EMI monitor includes: a test antenna; wherein the light sensor, humidity sensor, sound sensor, and vibration sensor are all mounted on the surface of the device housing; The modal data analysis module is used to obtain electromagnetic anomaly weights using a pre-built environmental database and an electromagnetic monitoring mechanism, perform electromagnetic analysis on the photovoltaic inverter using the electromagnetic monitoring mechanism to obtain an electromagnetic anomaly index, perform status assessment on the radiator using a temperature analysis mechanism to obtain a temperature anomaly weight, perform temperature image analysis on the semiconductor module using the temperature analysis mechanism to obtain a temperature anomaly index, confirm the current environmental weight, and monitor the device housing using the environmental monitoring mechanism to obtain an operation stability index; The power distribution status assessment module is used to input the electromagnetic anomaly weight, electromagnetic anomaly index, temperature anomaly weight, temperature anomaly index, current environment weight and operation stability index into the pre-built multimodal monitoring model to obtain the power distribution anomaly degree; The monitoring signal reminder module is used to compare the power distribution abnormality with the preset abnormality threshold. If the power distribution abnormality is greater than or equal to the abnormality threshold, the pre-built danger signal is sent to the pre-built inverter monitoring end to obtain the danger monitoring end. Otherwise, the pre-built safety signal is sent to the inverter monitoring end to obtain the safety monitoring end. The power distribution monitoring of the photovoltaic inverter is completed based on the danger monitoring end or the safety monitoring end.

Images