Distribution network fault detection system based on photovoltaic new energy

Abstract

The present invention belongs to the technical field of distribution network supervision, and specifically is a distribution network fault detection system based on photovoltaic new energy, comprising a distributed sensor network module, a fault detection output module, a distribution network decision control module and a background terminal; the present invention monitors various operating parameters of the corresponding distribution network in real time through the distributed sensor network module, the fault detection output module realizes distribution network fault identification based on a fault detection model, and the distribution network decision control module formulates a fault processing strategy according to the fault detection result, which is conducive to timely making corresponding regulation and improvement measures for the distribution network, and the distribution network safety assessment module detects and analyzes the safety of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period, and reminds management personnel to strengthen the supervision of the photovoltaic new energy distribution network in the future when a high-risk signal of the distribution network is generated, which significantly reduces the work difficulty of management personnel and effectively ensures the safe and stable operation of the distribution network.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network supervision, and in particular to a power distribution network fault detection system based on photovoltaic new energy. Background Art

[0002] With the advancement of global energy transformation, the proportion of photovoltaic new energy in the power system has gradually increased. The intermittent and unstable nature of photovoltaic equipment can easily lead to operational failures in the distribution network. Therefore, it is necessary to monitor the operation of the corresponding distribution network and conduct fault warning.

[0003] At present, when conducting fault detection on the distribution network of photovoltaic new energy, only fault identification and early warning can be performed, and the operation risk of the distribution network cannot be fully analyzed and comprehensively evaluated. When the operation risk of the distribution network is judged to be low, the performance status of the corresponding photovoltaic equipment and the control risk of the distribution network cannot be accurately evaluated, which increases the difficulty of the management personnel's work and is not conducive to ensuring the safe and stable operation of the distribution network;

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a distribution network fault detection system based on photovoltaic new energy, which solves the problem that the prior art cannot comprehensively analyze and comprehensively evaluate the operating risks of the distribution network, and cannot accurately evaluate the performance status of the corresponding photovoltaic equipment and the management and control risks of the distribution network when it is judged that the operating risk of the distribution network is low, which is not conducive to ensuring the safe and stable operation of the distribution network.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The distribution network fault detection system based on photovoltaic new energy includes a distributed sensor network module, a fault detection output module, a distribution network decision control module and a background terminal; the distributed sensor network module monitors the various operating parameters of the corresponding distribution network in real time by installing several types of sensors on the distribution network corresponding to the corresponding photovoltaic equipment, and sends all monitoring data to the fault detection output module;

[0008] The fault detection output module uses a deep learning algorithm to build a fault detection model and inputs all the received monitoring data into the fault detection model. When the corresponding monitoring data matches the features in the fault feature library, the fault warning mechanism is triggered and the fault type is automatically identified. The fault detection output module uses the distribution network topology information and combines the corresponding monitoring data to locate the fault location, and outputs the fault detection results to the distribution network decision control module and the background terminal; the distribution network decision control module formulates a fault handling strategy based on the fault detection results and sends it to the background terminal.

[0009] Furthermore, the background terminal is communicated with the distribution network safety assessment module. The distribution network safety assessment module is used to set a monitoring period, detect and analyze the safety of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period, and generate a high-risk signal for the distribution network or a low-risk signal for the distribution network through analysis. The distribution network safety assessment module sends the high-risk signal for the distribution network or the low-risk signal for the distribution network to the background terminal. When the background terminal receives the high-risk signal for the distribution network, it issues a corresponding warning.

[0010] Furthermore, the specific analysis process of the distribution network security assessment module is as follows:

[0011] Obtain all faults that occur in the corresponding distribution network during the monitoring period, count all types of faults, and mark the number of occurrences of the corresponding type of faults as a class inspection value; compare the class inspection value with the corresponding preset class inspection threshold value, and if the class inspection value exceeds the preset class inspection threshold value, mark the corresponding type of fault as a frequent fault; if there is a frequent fault, generate a high-risk signal for the distribution network;

[0012] If there are no common faults, a set of preset weight values ​​is set for each type of fault in advance, the class detection value of the corresponding type of fault is calculated by ratio with the corresponding preset class detection threshold to obtain the class condition value, and the product of the class condition value of the corresponding type of fault and the corresponding preset weight value is marked as the class risk value;

[0013] The class risk values ​​of all types of faults occurring in the corresponding distribution network during the monitoring period are obtained and summed up to obtain the distribution network safety warning value, and the distribution network safety warning value is numerically compared with the preset distribution network safety warning threshold. If the distribution network safety warning value exceeds the preset distribution network safety warning threshold, a high-risk signal for the distribution network is generated;

[0014] If the distribution network safety warning value does not exceed the preset distribution network safety warning threshold, the line table judgment symbol LP-1 or LP-2 of the corresponding distribution network is obtained. If the line table judgment symbol LP-1 is obtained, a high-risk signal for the distribution network is generated; if the line table judgment symbol LP-2 is obtained, a low-risk signal for the distribution network is generated.

[0015] Furthermore, the distribution network safety assessment module is communicatively connected to the line surface analysis module, and the line surface analysis module is used to collect the line surface image of the corresponding distribution network, and judge the line damage status based on the line surface image of the corresponding distribution network, and assign the line table judgment symbol LP-1 or LP-2 to the corresponding distribution network line, and the line surface analysis module sends the line table judgment symbol LP-1 or LP-2 to the distribution network safety assessment module.

[0016] Furthermore, the specific analysis process of the circuit surface analysis module is as follows:

[0017] A line surface image of the corresponding distribution network is obtained, and a line damaged part is identified based on the line surface image, and an area involved in the corresponding line damaged part is marked as a line damage face value, and a maximum damage depth and an average damage depth of the corresponding line damaged part are marked as a damage depth amplitude value and a damage depth surface value, respectively;

[0018] The damage hazard coefficient is obtained by numerically calculating the line loss face value, damage depth amplitude value and damage depth surface value, and the damage hazard coefficient is numerically compared with the preset damage hazard coefficient threshold. If the damage hazard coefficient exceeds the preset damage hazard coefficient threshold, the corresponding line damage is marked as a dangerous object; if there is a dangerous object, the line table judgment symbol LP-1 is assigned to the corresponding distribution network line.

[0019] Furthermore, if there is no dangerous object, the number of line damage points is marked as the line damage inspection value, and the damage hazard coefficients of all line damage points are averaged to obtain the damage hazard analysis value, and the damage hazard coefficient with the largest value is marked as the damage hazard amplitude value;

[0020] The line meter quality evaluation value is obtained by numerically calculating the line damage inspection value, damage risk analysis value and damage risk amplitude value, and the line meter quality evaluation value is numerically compared with the preset line meter quality evaluation threshold. If the line meter quality evaluation value exceeds the preset line meter quality evaluation threshold, the line meter judgment symbol LP-1 is assigned to the corresponding distribution network line; if the line meter quality evaluation value does not exceed the preset line meter quality evaluation threshold, the line meter judgment symbol LP-2 is assigned to the corresponding distribution network line.

[0021] Furthermore, the background terminal is communicated with the photovoltaic equipment impact analysis module, and the distribution network safety assessment module sends the distribution network low risk signal to the photovoltaic equipment impact analysis module. When the photovoltaic equipment impact analysis module receives the distribution network low risk signal, it detects the quality status of the photovoltaic equipment to determine the potential negative impact on the corresponding distribution network, and generates a photovoltaic equipment high impact signal or a photovoltaic equipment low impact signal accordingly. The photovoltaic equipment impact analysis module sends the photovoltaic equipment high impact signal or the photovoltaic equipment low impact signal to the background terminal, and the background terminal issues a corresponding warning when receiving the photovoltaic equipment high impact signal.

[0022] Furthermore, the specific analysis process of the photovoltaic equipment impact analysis module includes:

[0023] The production date of the corresponding photovoltaic equipment is collected, the interval between the current date and the production date is marked as the production detection value, and the various operating parameters of the corresponding photovoltaic equipment during operation are monitored. When the real-time monitoring data of the corresponding operating parameters do not meet the corresponding preset data requirements, the corresponding photovoltaic equipment is judged to be in a poor operating state, and the total time of the corresponding photovoltaic equipment in the poor operating state in the historical stage is obtained and marked as the operating abnormal time value;

[0024] The dust concentration, temperature deviation and humidity deviation of the environment in which the photovoltaic equipment is located are collected and marked as the environmental gray detection value, environmental temperature detection value and environmental humidity detection value respectively. If the environmental gray detection value, environmental temperature detection value or environmental humidity detection value exceeds the corresponding preset threshold, the photovoltaic equipment is judged to be in a bad storage loop state; the total time length of the corresponding photovoltaic equipment in the bad storage loop state in the historical stage is obtained and marked as the storage loop abnormal time value;

[0025] The photovoltaic equipment impact coefficient is obtained by numerically calculating the production detection value, the operation abnormal value and the storage loop abnormal value, and the photovoltaic equipment impact coefficient is numerically compared with the preset photovoltaic equipment impact coefficient threshold. If the photovoltaic equipment impact coefficient exceeds the preset photovoltaic equipment impact coefficient threshold, a photovoltaic equipment high impact signal is generated; if the photovoltaic equipment impact coefficient does not exceed the preset photovoltaic equipment impact coefficient threshold, a photovoltaic equipment low impact signal is generated.

[0026] Furthermore, the backend terminal communicates with the management and control risk analysis module, and the distribution network safety assessment module sends the distribution network low risk signal to the management and control risk analysis module. When the management and control risk analysis module receives the distribution network low risk signal, it analyzes the management and control risk of the corresponding distribution network during the monitoring period, and generates a high management and control risk signal or a low management and control risk signal through analysis. The management and control risk analysis module sends the high management and control risk signal or the low management and control risk signal to the backend terminal, and the backend terminal issues a corresponding warning when receiving the high management and control risk signal.

[0027] Furthermore, the specific analysis process of the management and control risk analysis module is as follows:

[0028] When it is determined that a fault occurs in the distribution network, the timing starts and the corresponding fault is resolved, thereby obtaining the fault response time; the fault response time is numerically compared with the corresponding preset fault response time threshold, and if the fault response time exceeds the corresponding fault response time threshold, the corresponding fault response time is marked as the fault response time;

[0029] The number of fault response durations during the monitoring period is obtained and the ratio is calculated with the total number of fault response durations to obtain a fault response detection value; the ratio of the fault response duration to the corresponding preset fault response duration threshold is marked as a fault response share value; the average of all fault response share values ​​is calculated to obtain a fault response condition value; the fault response detection value and the fault response condition value are numerically compared with the preset fault response detection threshold and the preset fault response condition threshold, respectively; if the fault response detection value or the fault response condition value exceeds the corresponding preset threshold, a high-risk control signal is generated; if both the fault response detection value and the fault response condition value do not exceed the corresponding preset threshold, a low-risk control signal is generated.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. In the present invention, various operating parameters of the corresponding distribution network are monitored in real time through a distributed sensor network module, the fault detection output module realizes distribution network fault identification based on the fault detection model, the distribution network decision control module formulates a fault handling strategy according to the fault detection result, and the distribution network safety assessment module detects and analyzes the safety of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period, strengthens the subsequent supervision of the photovoltaic new energy distribution network when a high-risk signal of the distribution network is generated, significantly reduces the work difficulty of managers, and effectively ensures the safe and stable operation of the distribution network;

[0032] 2. In the present invention, the low-risk signal of the distribution network is sent to the photovoltaic equipment impact analysis module and the management and control risk analysis module through the distribution network safety assessment module. The photovoltaic equipment impact analysis module detects the quality status of the photovoltaic equipment to determine the potential negative impact on the corresponding distribution network. The management and control risk analysis module analyzes the management and control risks of the corresponding distribution network during the monitoring period, and issues an early warning when a high-impact signal of the photovoltaic equipment or a high-risk signal of management and control is generated, thereby further ensuring the operational stability and safety of the distribution network, with a high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0034] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0035] Figure 2 This is a system block diagram of Embodiment 2 and Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] Embodiment 1: Figure 1 As shown, the distribution network fault detection system based on photovoltaic new energy proposed in the present invention includes a distributed sensor network module, a fault detection output module, a distribution network decision control module, a distribution network safety assessment module and a background terminal; the distributed sensor network module monitors various operating parameters of the corresponding distribution network (such as current, voltage, power factor and other parameters of the distribution network) in real time by installing several types of sensors on the distribution network corresponding to the corresponding photovoltaic equipment, and sends all monitoring data to the fault detection output module.

[0038] The fault detection output module uses a deep learning algorithm to build a fault detection model (the fault detection model uses the structure and capabilities of a deep neural network to learn the characteristics and patterns of faults from a large amount of data and can accurately identify faults in the distribution network). All received monitoring data is input into the fault detection model. When the corresponding monitoring data matches the features in the fault feature library, the fault warning mechanism is triggered and the fault type is automatically identified.

[0039] The fault detection output module uses the distribution network topology information and combines it with the corresponding monitoring data to locate the fault location, and outputs the fault detection results to the distribution network decision-making control module and the background terminal; the distribution network decision-making control module formulates a fault handling strategy based on the fault detection results and sends it to the background terminal, which is conducive to timely making corresponding control and improvement measures for the distribution network to ensure the safe and stable operation of the distribution network.

[0040] The distribution network security assessment module sets a monitoring period, preferably, the monitoring period is twenty days; the security of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period is detected and analyzed, and a high-risk signal or a low-risk signal of the distribution network is generated through analysis;

[0041] And the distribution network security assessment module sends the distribution network high risk signal or the distribution network low risk signal to the background terminal. When the background terminal receives the distribution network high risk signal, it issues a corresponding warning to remind the management personnel to strengthen the supervision of the photovoltaic new energy distribution network in the future, which is conducive to the reasonable planning of the distribution network management plan in the future and reduces the work difficulty of the management personnel. The specific analysis process of the distribution network security assessment module is as follows:

[0042] Obtain all faults that occur in the corresponding distribution network during the monitoring period, count all types of faults, and mark the number of occurrences of the corresponding type of faults as a class inspection value; compare the class inspection value with the corresponding preset class inspection threshold; if the class inspection value exceeds the preset class inspection threshold, it indicates that the corresponding type of fault occurs frequently in the distribution network during the monitoring period, and the corresponding type of fault is marked as a frequent fault; if there is a frequent fault, it indicates that the operation risk of the distribution network is relatively high, and a high-risk signal for the distribution network is generated;

[0043] If there are no common faults, a set of preset weight values ​​are set for each type of fault in advance, wherein the preset weight values ​​are all positive numbers, and the greater the damage caused by the corresponding type of fault to the distribution network, the greater the value of the preset weight value matching the corresponding type of fault; the class inspection value of the corresponding type of fault is calculated by ratio with the corresponding preset class inspection threshold to obtain the class condition value, and the product of the class condition value of the corresponding type of fault and the corresponding preset weight value is marked as the class risk value;

[0044] The class risk values ​​of all types of faults occurring in the corresponding distribution network during the monitoring period are obtained and summed up to obtain the distribution network safety warning value, wherein the larger the value of the distribution network safety warning value is, the greater the operation risk of the distribution network is; the distribution network safety warning value is numerically compared with the preset distribution network safety warning threshold, if the distribution network safety warning value exceeds the preset distribution network safety warning threshold, it indicates that the overall operation risk of the distribution network is relatively large, and a distribution network high-risk signal is generated;

[0045] If the distribution network safety warning value does not exceed the preset distribution network safety warning threshold, the line table judgment symbol LP-1 or LP-2 of the corresponding distribution network is obtained. If the line table judgment symbol LP-1 is obtained, it indicates that the line condition of the distribution network line is poor and the operation risk of the distribution network is relatively large, then a high-risk signal for the distribution network is generated; if the line table judgment symbol LP-2 is obtained, it indicates that the line condition of the distribution network line is good and the operation risk of the distribution network is relatively small, then a low-risk signal for the distribution network is generated.

[0046] Furthermore, the distribution network security assessment module is communicatively connected to the line surface analysis module, which is used to collect the line surface image of the corresponding distribution network, and judge the line damage status based on the line surface image of the corresponding distribution network, and assign the line table judgment symbol LP-1 or LP-2 to the corresponding distribution network line, and the line surface analysis module sends the line table judgment symbol LP-1 or LP-2 to the distribution network security assessment module, which can not only reasonably analyze and accurately feedback the line damage status of the distribution network line, but also provide data support for the analysis process of the distribution network security assessment module, so as to ensure the comprehensiveness of its analysis and the accuracy of the analysis results; the specific analysis process of the line surface analysis module is as follows:

[0047] A line surface image of the corresponding distribution network is obtained, and a line damaged part is identified based on the line surface image, and an area involved in the corresponding line damaged part is marked as a line damage face value, and a maximum damage depth and an average damage depth of the corresponding line damaged part are marked as a damage depth amplitude value and a damage depth surface value, respectively;

[0048] The damage hazard coefficient FN is obtained by numerically calculating the line loss face value FW, the damage depth amplitude value FK and the damage depth surface value FS through the formula FN=a1*FW+(a2*FK+a3*FS) / 2; wherein a1, a2, and a3 are preset proportional coefficients with values ​​greater than zero, and the larger the value of the damage hazard coefficient FN, the more serious the damage condition of the corresponding line damage part, and the greater the adverse impact on the safety of the distribution network line;

[0049] The damage hazard coefficient FN is numerically compared with the preset damage hazard coefficient threshold. If the damage hazard coefficient FN exceeds the preset damage hazard coefficient threshold, it indicates that the damage condition of the corresponding line damage is serious and has a great adverse impact on the safety of the distribution network line. The corresponding line damage is marked as a dangerous object. If there is a dangerous object, it indicates that the line condition of the distribution network line is poor, and the line table judgment symbol LP-1 is assigned to the corresponding distribution network line.

[0050] If there is no dangerous object, the number of line damage points is marked as the line damage inspection value, and the damage hazard coefficients of all line damage points are averaged to obtain the damage hazard analysis value, that is, the damage hazard analysis value represents the average value of the damage hazard coefficients of all line damage points. The larger the value of the damage hazard analysis value, the more serious the damage conditions of all line damage points are as a whole; and the damage hazard coefficient with the largest value is marked as the damage hazard amplitude value;

[0051] By formula The line damage inspection value ZS, the damage risk analysis value ZM and the damage risk amplitude value ZF are numerically calculated to obtain the line surface quality evaluation value ZP; wherein hu1, hu2, and hu3 are preset proportional coefficients, hu1>hu2>hu3>0; and the larger the value of the line surface quality evaluation value ZP, the worse the line condition of the distribution network line is in general;

[0052] The line meter quality evaluation value ZP is numerically compared with the preset line meter quality evaluation threshold. If the line meter quality evaluation value ZP exceeds the preset line meter quality evaluation threshold, indicating that the line condition of the distribution network line is generally poor, the corresponding distribution network line is assigned a line meter judgment symbol LP-1; if the line meter quality evaluation value ZP does not exceed the preset line meter quality evaluation threshold, indicating that the line condition of the distribution network line is generally good, the corresponding distribution network line is assigned a line meter judgment symbol LP-2.

[0053] Embodiment 2: Figure 2 As shown, the difference between this embodiment and the first embodiment is that the background terminal is connected to the photovoltaic equipment impact analysis module through communication. It should be noted that there is a certain correlation between the failure of the distribution network line and the corresponding photovoltaic equipment, and the abnormal performance quality of the photovoltaic equipment will threaten the stability and safety of the distribution network line;

[0054] The distribution network safety assessment module sends the distribution network low risk signal to the photovoltaic equipment impact analysis module. When the photovoltaic equipment impact analysis module receives the distribution network low risk signal, it detects the quality status of the photovoltaic equipment to determine the potential negative impact on the corresponding distribution network, and generates a photovoltaic equipment high impact signal or a photovoltaic equipment low impact signal accordingly;

[0055] The photovoltaic equipment impact analysis module sends the photovoltaic equipment high impact signal or the photovoltaic equipment low impact signal to the background terminal. When the background terminal receives the photovoltaic equipment high impact signal, it issues a corresponding warning to remind the management personnel to replace the corresponding photovoltaic equipment in time to ensure the performance and quality of the photovoltaic equipment, which is conducive to further improving the operation stability of the corresponding distribution network. The specific analysis process of the photovoltaic equipment impact analysis module is as follows:

[0056] The production date of the corresponding photovoltaic equipment is collected, the interval between the current date and the production date is marked as the production detection value, and the various operating parameters of the corresponding photovoltaic equipment during operation are monitored. When the real-time monitoring data of the corresponding operating parameters do not meet the corresponding preset data requirements, the corresponding photovoltaic equipment is judged to be in a poor operating state, and the total time of the corresponding photovoltaic equipment in the poor operating state in the historical stage is obtained and marked as the operating abnormal time value;

[0057] The dust concentration, temperature deviation amplitude and humidity deviation amplitude of the environment where the photovoltaic equipment is located are collected and marked as environmental gray detection value, environmental temperature detection value and environmental humidity detection value respectively. If the environmental gray detection value, environmental temperature detection value or environmental humidity detection value exceeds the corresponding preset threshold value, it is judged that the photovoltaic equipment is in a bad storage loop state; wherein, the bad storage loop state indicates that the real-time environmental conditions of the area where the photovoltaic equipment is located are not good, which is easy to cause damage to the service life of the photovoltaic equipment; the total duration of the corresponding photovoltaic equipment in the historical stage in the bad storage loop state is obtained and marked as the storage loop abnormal time value;

[0058] By formula The production detection value GY, the operation time difference value GS and the storage loop time difference value GP are numerically calculated to obtain the photovoltaic equipment influence coefficient GX; wherein, re1, re2 and re3 are preset proportional coefficients, and re2>re3>re1>0; and the larger the value of the photovoltaic equipment influence coefficient GX, the worse the equipment condition of the corresponding photovoltaic equipment is, and the greater the adverse impact on the corresponding distribution network;

[0059] The photovoltaic equipment impact coefficient GX is numerically compared with the preset photovoltaic equipment impact coefficient threshold. If the photovoltaic equipment impact coefficient GX exceeds the preset photovoltaic equipment impact coefficient threshold, it indicates that the equipment condition of the corresponding photovoltaic equipment is poor and the adverse impact on the corresponding distribution network is large, then a photovoltaic equipment high impact signal is generated; if the photovoltaic equipment impact coefficient GX does not exceed the preset photovoltaic equipment impact coefficient threshold, it indicates that the equipment condition of the corresponding photovoltaic equipment is good and the adverse impact on the corresponding distribution network is small, then a photovoltaic equipment low impact signal is generated.

[0060] Embodiment 3: Figure 2As shown, the difference between this embodiment and the first and second embodiments is that the background terminal is connected to the control risk analysis module through communication, and the distribution network safety assessment module sends the distribution network low risk signal to the control risk analysis module. When the control risk analysis module receives the distribution network low risk signal, it analyzes the control risk of the corresponding distribution network during the monitoring period, and generates a control high risk signal or a control low risk signal through analysis;

[0061] The control risk analysis module sends a high-risk control signal or a low-risk control signal to the back-end terminal. When the back-end terminal receives a high-risk control signal, it issues a corresponding warning to remind the back-end personnel to optimize the corresponding control measures, ensuring the timeliness of subsequent fault handling and operational safety for the distribution network, with a high degree of intelligence. The specific analysis process of the control risk analysis module is as follows:

[0062] When it is determined that a fault occurs in the distribution network, the timing starts and the corresponding fault is solved, thereby obtaining the fault response time; wherein, the larger the value of the fault response time is, the more delayed the corresponding fault is solved; the fault response time is numerically compared with the corresponding preset fault response time threshold, and if the fault response time exceeds the corresponding fault response time threshold, the corresponding fault response time is marked as the fault response time;

[0063] The number of fault response durations during the monitoring period is obtained and the ratio thereof to the total number of fault response durations is calculated to obtain a fault response detection value, and the ratio of the fault response duration to the corresponding preset fault response duration threshold is marked as a fault response value, and the average of all fault response values ​​is calculated to obtain a fault response value;

[0064] The fault abnormality detection value and the fault condition value are numerically compared with the preset fault abnormality detection threshold and the preset fault condition threshold respectively. If the fault abnormality detection value or the fault condition value exceeds the corresponding preset threshold, it indicates that the control risk of the distribution network during the monitoring period is high, and a high-risk control signal is generated; if the fault abnormality detection value and the fault condition value do not exceed the corresponding preset threshold, it indicates that the control risk of the distribution network during the monitoring period is low, and a low-risk control signal is generated.

[0065] The working principle of the present invention is as follows: when in use, the various operating parameters of the corresponding distribution network are monitored in real time through the distributed sensor network module, and all the monitoring data are sent to the fault detection output module. The fault detection output module inputs all the received monitoring data into the fault detection model. When the corresponding monitoring data matches the characteristics in the fault feature library, the fault warning mechanism is triggered and the fault type is automatically identified. The distribution network decision control module formulates a fault handling strategy according to the fault detection result and sends it to the background terminal, which is conducive to timely making corresponding control and improvement measures for the distribution network to ensure the safe and stable operation of the distribution network. The distribution network safety assessment module detects and analyzes the safety of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period. When a high-risk signal of the distribution network is generated, the management personnel are reminded to strengthen the supervision of the photovoltaic new energy distribution network in the future, which is conducive to the reasonable planning of the distribution network management plan in the future and significantly reduces the work difficulty of the management personnel.

[0066] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A distribution network fault detection system based on photovoltaic new energy, characterized in that: It includes a distributed sensor network module, a fault detection output module, a distribution network decision control module and a background terminal; the distributed sensor network module monitors the various operating parameters of the corresponding distribution network in real time by installing several types of sensors on the distribution network corresponding to the corresponding photovoltaic equipment, and sends all monitoring data to the fault detection output module; The fault detection output module uses a deep learning algorithm to build a fault detection model, and inputs all the received monitoring data into the fault detection model. When the corresponding monitoring data matches the features in the fault feature library, the fault warning mechanism is triggered and the fault type is automatically identified. The fault detection output module uses the distribution network topology information and combines the corresponding monitoring data to locate the fault location, and outputs the fault detection results to the distribution network decision control module and the background terminal; The distribution network decision control module formulates a fault handling strategy based on the fault detection results and sends it to the backend terminal; The backend terminal is connected to the distribution network security assessment module in communication. The distribution network security assessment module is used to set a monitoring period, detect and analyze the security of the distribution network corresponding to the corresponding photovoltaic equipment during the monitoring period, and generate a high-risk signal or a low-risk signal of the distribution network through analysis. The distribution network security assessment module sends the high-risk signal or the low-risk signal of the distribution network to the backend terminal; The specific analysis process of the distribution network security assessment module is as follows: Obtain all faults that occurred in the corresponding distribution network during the monitoring period, count all types of faults, and mark the number of occurrences of the corresponding type of faults as a class inspection value; If the class inspection value exceeds the corresponding preset class inspection threshold, the corresponding type of fault is marked as a frequent fault; if a frequent fault exists, a high-risk signal for the distribution network is generated; If there are no common faults, the class detection value of the corresponding type of fault is calculated by ratio with the corresponding preset class detection threshold to obtain the class condition value, and the product of the class condition value of the corresponding type of fault and the corresponding preset weight value is marked as the class risk value; The risk values ​​of all types of faults occurring in the corresponding distribution network during the monitoring period are obtained and summed up to obtain the distribution network safety warning value. If the distribution network safety warning value exceeds the preset distribution network safety warning threshold, a high-risk signal for the distribution network is generated; If the distribution network safety warning value does not exceed the preset distribution network safety warning threshold, the line table judgment symbol of the corresponding distribution network is obtained. If the line table judgment symbol LP-1 is obtained, a high-risk signal for the distribution network is generated; If the line table judgment symbol LP-2 is obtained, a low-risk signal for the distribution network is generated.

2. The photovoltaic new energy-based distribution network fault detection system according to claim 1 is characterized in that: The distribution network safety assessment module is communicatively connected to the line surface analysis module. The line surface analysis module is used to collect the line surface image of the corresponding distribution network, judge the line damage status based on the line surface image of the corresponding distribution network, and assign the line table judgment symbol LP-1 or LP-2 to the corresponding distribution network line accordingly. The line surface analysis module sends the line table judgment symbol LP-1 or LP-2 to the distribution network safety assessment module.

3. The distribution network fault detection system based on photovoltaic new energy according to claim 2 is characterized in that: The specific analysis process of the circuit surface analysis module is as follows: Based on the line surface image, the line damage is identified, the area involved in the corresponding line damage is marked as the line damage face value, and the maximum damage depth and the average damage depth of the corresponding line damage are marked as the damage depth amplitude value and the damage depth surface value respectively; The damage hazard coefficient is obtained by numerically calculating the line loss face value, damage depth amplitude value and damage depth surface value. If the damage hazard coefficient exceeds the preset damage hazard coefficient threshold, the corresponding line damage point is marked as a dangerous object; if a dangerous object exists, the line table judgment symbol LP-1 is assigned to the corresponding distribution network line.

4. The photovoltaic new energy-based distribution network fault detection system according to claim 3 is characterized in that: If there is no dangerous object, the number of line damage points is marked as the line damage inspection value, and the damage hazard coefficients of all line damage points are averaged to obtain the damage hazard analysis value, and the damage hazard coefficient with the largest value is marked as the damage hazard amplitude value; The line meter quality evaluation value is obtained by numerically calculating the line damage inspection value, damage risk analysis value and damage risk amplitude value. If the line meter quality evaluation value exceeds the preset line meter quality evaluation threshold, the line meter judgment symbol LP-1 is assigned to the corresponding distribution network line; If the line meter quality evaluation value does not exceed the preset line meter quality evaluation threshold, the line meter judgment symbol LP-2 is assigned to the corresponding distribution network line.

5. The photovoltaic new energy-based distribution network fault detection system according to claim 1, characterized in that: The background terminal is communicated with the photovoltaic equipment impact analysis module, and the distribution network safety assessment module sends the distribution network low risk signal to the photovoltaic equipment impact analysis module. When the photovoltaic equipment impact analysis module receives the distribution network low risk signal, it detects the quality status of the photovoltaic equipment to determine the potential negative impact on the corresponding distribution network, and generates a photovoltaic equipment high impact signal or a photovoltaic equipment low impact signal accordingly. The photovoltaic equipment impact analysis module sends the photovoltaic equipment high impact signal or the photovoltaic equipment low impact signal to the background terminal.

6. The photovoltaic new energy-based distribution network fault detection system according to claim 5 is characterized in that: The specific analysis process of the photovoltaic equipment impact analysis module includes: The production date of the corresponding photovoltaic equipment is collected, the interval between the current date and the production date is marked as the production detection value, and the various operating parameters of the corresponding photovoltaic equipment during operation are monitored. When the real-time monitoring data of the corresponding operating parameters do not meet the corresponding preset data requirements, the corresponding photovoltaic equipment is judged to be in a poor operating state, and the total time of the corresponding photovoltaic equipment in the poor operating state in the historical stage is obtained and marked as the operating abnormal time value; The dust concentration, temperature deviation and humidity deviation of the environment in which the photovoltaic equipment is located are collected and marked as the environmental gray detection value, environmental temperature detection value and environmental humidity detection value respectively. If the environmental gray detection value, environmental temperature detection value or environmental humidity detection value exceeds the corresponding preset threshold, the photovoltaic equipment is judged to be in a bad storage loop state; the total time length of the corresponding photovoltaic equipment in the bad storage loop state in the historical stage is obtained and marked as the storage loop abnormal time value; The photovoltaic equipment impact coefficient is obtained by numerically calculating the production detection value, the operation abnormal value and the storage loop abnormal value. If the photovoltaic equipment impact coefficient exceeds the preset photovoltaic equipment impact coefficient threshold, a photovoltaic equipment high impact signal is generated; if the photovoltaic equipment impact coefficient does not exceed the preset photovoltaic equipment impact coefficient threshold, a photovoltaic equipment low impact signal is generated.

7. The photovoltaic new energy-based distribution network fault detection system according to claim 5, characterized in that: The backend terminal communicates with the management and control risk analysis module. The distribution network safety assessment module sends the distribution network low risk signal to the management and control risk analysis module. When the management and control risk analysis module receives the distribution network low risk signal, it analyzes the management and control risk of the corresponding distribution network during the monitoring period, and generates a high management and control risk signal or a low management and control risk signal through analysis. The management and control risk analysis module sends the high management and control risk signal or the low management and control risk signal to the backend terminal.

8. The photovoltaic new energy-based distribution network fault detection system according to claim 7, characterized in that: The specific analysis process of the management and control risk analysis module is as follows: When it is determined that a fault occurs in the distribution network, the timing starts and the fault response time is calculated until the corresponding fault is resolved. If the fault response time exceeds the corresponding fault response time threshold, the corresponding fault response time is marked as the fault response time. The number of fault response durations during the monitoring period is obtained and the ratio thereof to the total number of fault response durations is calculated to obtain a fault response detection value. The ratio of the fault response duration to the corresponding preset fault response duration threshold is marked as a fault response value, and the average of all fault response values ​​is calculated to obtain a fault response value. If the fault response detection value or the fault response value exceeds the corresponding preset threshold, a high-risk control signal is generated. If the fault abnormality detection value and the fault condition value do not exceed the corresponding preset threshold, a low risk control signal is generated.

Images