Method and system for diagnosing abnormal state of power transmission cable of photovoltaic power station

Abstract

The invention relates to the technical field of power transmission cable monitoring, in particular to a photovoltaic power station power transmission cable abnormal state diagnosis method and system. Comprising the steps of establishing a plurality of equipment nodes according to transmission cable parameters; obtaining operation parameters of each equipment node, and generating an operation risk value of each equipment node according to a preset state diagnosis model; acquiring environment parameters of each equipment node, and generating an environment evaluation value of each equipment node according to the environment parameters; generating a state risk value of each equipment node according to the environment evaluation value and the operation risk value; the method comprises the following steps: establishing a plurality of equipment nodes according to equipment parameters of the power transmission cable, performing feature extraction on operation parameters according to a preset diagnosis model, and performing data correction according to an association relationship among feature indexes so as to eliminate abnormal data and obtain an operation risk value of each equipment node; therefore, the abnormal operation state of each equipment node is early warned in time, operation and maintenance personnel can make a maintenance decision conveniently, and stable operation of the power transmission cable is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission cable monitoring, and in particular to a method and system for diagnosing abnormal conditions of power transmission cables in photovoltaic power stations. Background Art

[0002] With the continuous development of science and technology, solar energy technology will become one of the green energy technologies in the future. Solar energy or photovoltaics is becoming more and more widespread. In addition to the rapid development of photovoltaic power plants supported by the government, private investors are also actively building plants. The most important issue that needs to be paid attention to in solar power supply technology is to ensure the normal transmission of photovoltaic cables during power transmission.

[0003] The operation of transmission cables is often affected by environmental damage, external damage, design defects, poor workmanship, operational errors, aging and other fault factors. Operational failures such as open circuit, short circuit, insulation damage and so on often occur, which bring great challenges to the stable operation of photovoltaic systems. Summary of the invention

[0004] The purpose of this application is: to solve the above technical problems, this application provides a method and system for diagnosing abnormal conditions of transmission cables in photovoltaic power stations, aiming to achieve timely early warning and maintenance of abnormal conditions of transmission cables and ensure stable operation of transmission cables.

[0005] In some embodiments of the present application, multiple device nodes are established according to the equipment parameters of the transmission cable, the operating parameters of the device nodes are periodically collected, and features of the operating parameters are extracted according to a preset diagnostic model. Data correction is performed according to the correlation between various characteristic indicators to eliminate abnormal data, and an operating risk value for each device node is generated according to the correction result, so as to timely issue an early warning of the abnormal operating status of each device node, facilitate operation and maintenance personnel to make maintenance decisions, and ensure the stable operation of the transmission cable.

[0006] In some embodiments of the present application, by collecting environmental parameters of each device node, multi-source data analysis is performed on each device node, the operating status of the transmission cable is corrected based on the real-time environmental evaluation value, and early warning of potential fault risks is issued, thereby improving the monitoring and early warning efficiency of the transmission cable and ensuring the safe operation of the transmission cable.

[0007] In some embodiments of the present application, a method for diagnosing abnormal status of a transmission cable in a photovoltaic power station is provided, comprising:

[0008] Establish multiple device nodes according to transmission cable parameters;

[0009] Obtaining the operating parameters of each device node, and generating the operating risk value of each device node according to the preset state diagnosis model;

[0010] Obtaining environmental parameters of each device node, and generating environmental evaluation values ​​of each device node according to the environmental parameters;

[0011] Generate the status risk value of each device node according to the environmental evaluation value and the operation risk value;

[0012] When creating multiple device nodes, include:

[0013] Generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node and n is the number of device nodes.

[0014] In some embodiments of the present application, obtaining the operating parameters of each device node includes:

[0015] Preset multiple feedback time nodes;

[0016] Setting the collection parameters of a single feedback time point, the collection parameters include: the number of data collection times and the total collection time;

[0017] Set a single collection cycle based on the total collection duration;

[0018] The single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times;

[0019] The operating parameters of each device node are obtained in turn according to the collection parameters.

[0020] In some embodiments of the present application, when generating the operation risk value of each device node, it includes:

[0021] According to the device node sequence A, set ai as the target device node in sequence;

[0022] Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes;

[0023] Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters;

[0024] Generate initial monitoring data for each characteristic indicator;

[0025] Correct the initial monitoring data of each characteristic index in turn according to the correction model;

[0026] Generate an operation risk value of the target device node according to the correction result and the status diagnosis model;

[0027] Generate the operation risk value of each device node in turn;

[0028] An operation risk value sequence F is established, where F = (f1, f2...fi...fn), wherein fi is the operation risk value of the i-th device node.

[0029] In some embodiments of the present application, when the initial monitoring data of each characteristic indicator is corrected in sequence, it includes:

[0030] According to the characteristic index sequence B, the i-th characteristic index is selected as the target characteristic index;

[0031] Generate the running value sequence D of the target characteristic index, D = (d1, d2...d i …d m ), where di is the running value of the target characteristic index collected at the rth moment in the collection cycle of the current feedback time node;

[0032] Establish a correction model based on the correlation between various characteristic indicators;

[0033] According to the calibration model and the running value series of the remaining characteristic indexes, it is judged in turn whether each running value in the running value series D is an abnormal value;

[0034] If di is an abnormal value, set d i =(d i+1 +d i－1 ) / 2;

[0035] Output the running value sequence D of the target characteristic index according to the correction result.

[0036] In some embodiments of the present application, when generating the operation risk value of the target device node, it includes:

[0037]

[0038] Where, f is the operation risk value of the target device node;

[0039] ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node;

[0040] e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

[0041] In some embodiments of the present application, when generating the state risk value of each device node, it includes:

[0042] Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters;

[0043]

[0044] Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators;

[0045] Generate the state risk value k of the target device node at the current feedback time node;

[0046] k = e3*f+e4*g;

[0047] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient;

[0048] Preset the first state risk value threshold K1;

[0049] If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node;

[0050] Determine in turn whether each device node generates a first-level warning instruction.

[0051] In some embodiments of the present application, a photovoltaic power station transmission cable abnormal state diagnosis system is provided, comprising:

[0052] The central control unit is used to establish multiple device nodes according to the transmission cable parameters;

[0053] A monitoring unit, comprising a plurality of monitoring modules, wherein the monitoring modules are arranged at the device nodes and are used to collect operating parameters and environmental parameters of each device node;

[0054] The central control unit comprises:

[0055] The first processing module is used to generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node; n is the number of device nodes;

[0056] The second processing module is used to obtain the operating parameters of each device node and generate the operating risk value of each device node according to the preset state diagnosis model;

[0057] The third processing module is used to obtain the environmental parameters of each device node and generate the environmental evaluation value of each device node according to the environmental parameters;

[0058] The third processing module is further used to generate a state risk value of each device node according to the environmental evaluation value and the operation risk value.

[0059] In some embodiments of the present application, the second processing module is further used to:

[0060] Preset multiple feedback time nodes;

[0061] Setting the collection parameters of a single feedback time point, the collection parameters include: the number of data collection times and the total collection time;

[0062] Set a single collection cycle based on the total collection duration;

[0063] The single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times;

[0064] The operating parameters of each device node are obtained in turn according to the collection parameters.

[0065] In some embodiments of the present application, the second processing module is further used to:

[0066] According to the device node sequence A, set ai as the target device node in sequence;

[0067] Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes;

[0068] Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters;

[0069] Generate initial monitoring data for each characteristic indicator;

[0070] Correct the initial monitoring data of each characteristic index in turn according to the correction model;

[0071] Generate an operation risk value of the target device node according to the correction result and the status diagnosis model;

[0072] Generate the operation risk value of each device node in turn;

[0073] Establish an operation risk value sequence F, F = (f1, f2...fi...fn), where fi is the operation risk value of the i-th device node;

[0074] Among them, when generating the operation risk value of the target device node, it includes:

[0075]

[0076] Where, f is the operation risk value of the target device node;

[0077] ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node;

[0078] e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

[0079] In some embodiments of the present application, the third processing module is further used to:

[0080] Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters;

[0081]

[0082] Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators;

[0083] Generate the state risk value k of the target device node at the current feedback time node;

[0084] k = e3*f+e4*g;

[0085] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient;

[0086] Preset the first state risk value threshold K1;

[0087] If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node;

[0088] Determine in turn whether each device node generates a first-level warning instruction.

[0089] Compared with the prior art, the method and system for diagnosing abnormal status of transmission cables in a photovoltaic power station according to the embodiment of the present application have the following beneficial effects:

[0090] Establish multiple equipment nodes according to the equipment parameters of the transmission cable, collect the operating parameters of the equipment nodes periodically, extract features of the operating parameters according to the preset diagnostic model, and perform data correction according to the correlation between various characteristic indicators to eliminate abnormal data. Generate the operating risk value of each equipment node according to the correction result, so as to timely warn of the abnormal operating status of each equipment node, facilitate operation and maintenance personnel to make maintenance decisions, and ensure the stable operation of the transmission cable.

[0091] By collecting the environmental parameters of each device node, performing multi-source data analysis on each device node, correcting the operating status of the transmission cable based on the real-time environmental evaluation value, and issuing early warnings for potential fault risks, the monitoring and early warning efficiency of the transmission cable is improved to ensure the safe operation of the transmission cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] Figure 1 It is a flow chart of a method for diagnosing abnormal status of a transmission cable in a photovoltaic power station in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0093] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0094] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0095] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0096] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0097] like Figure 1 As shown, a method for diagnosing abnormal status of a transmission cable in a photovoltaic power station according to a preferred embodiment of the present application includes:

[0098] S101: Establish multiple device nodes according to transmission cable parameters;

[0099] S102: Acquire the operating parameters of each device node, and generate the operating risk value of each device node according to a preset state diagnosis model;

[0100] S103: Acquire environmental parameters of each device node, and generate an environmental evaluation value of each device node according to the environmental parameters;

[0101] S104: Generate a state risk value for each device node according to the environmental evaluation value and the operation risk value;

[0102] When creating multiple device nodes, include:

[0103] Generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node and n is the number of device nodes.

[0104] Specifically, multiple device nodes are established according to the key nodes of the transmission cable (such as connectors, transformers, inverters, etc.), and monitoring modules are set up at each device node to collect the real-time operating parameters of each device node.

[0105] Specifically, when obtaining the operating parameters of each device node, it includes:

[0106] Preset multiple feedback time nodes;

[0107] Set the collection parameters for a single feedback time point, including: number of data collection times and total collection time;

[0108] Set a single collection cycle based on the total collection duration;

[0109] A single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times;

[0110] The operating parameters of each device node are obtained in turn according to the collection parameters.

[0111] Specifically, by setting multiple feedback time nodes, each device node is periodically monitored, and by setting the collection parameters of a single feedback time node, the operating parameters of each device node are collected multiple times to improve data collection accuracy, providing data support for subsequent status evaluation.

[0112] It can be understood that in the above embodiment, multiple device nodes are established according to the transmission cable equipment parameters, the operating parameters of the device nodes are periodically collected, and abnormal status of the device nodes are promptly warned according to the status diagnosis model, so as to facilitate the operation and maintenance personnel to make maintenance decisions and realize real-time monitoring of the transmission cables.

[0113] In a preferred embodiment of the present application, when generating the operation risk value of each device node, it includes:

[0114] According to the device node sequence A, set ai as the target device node in sequence;

[0115] Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes;

[0116] Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters;

[0117] Generate initial monitoring data for each characteristic indicator;

[0118] Correct the initial monitoring data of each characteristic index in turn according to the correction model;

[0119] Generate an operation risk value of the target device node according to the correction result and the status diagnosis model;

[0120] Generate the operation risk value of each device node in turn;

[0121] An operation risk value sequence F is established, where F = (f1, f2...fi...fn), wherein fi is the operation risk value of the i-th device node.

[0122] Specifically, the characteristic indicators include, but are not limited to, parameters such as current value, voltage value, conductor temperature, surface temperature and joint temperature of the device node.

[0123] Specifically, the initial monitoring data of each characteristic indicator is corrected in sequence, including:

[0124] According to the characteristic index sequence B, the i-th characteristic index is selected as the target characteristic index;

[0125] Generate the running value sequence D of the target characteristic index, D = (d1, d2...d i …d m ), where di is the running value of the target characteristic index collected at the rth moment in the collection cycle of the current feedback time node;

[0126] Establish a correction model based on the correlation between various characteristic indicators;

[0127] According to the calibration model and the running value series of the remaining characteristic indexes, it is judged in turn whether each running value in the running value series D is an abnormal value;

[0128] If di is an abnormal value, set d i =(d i+1 +d i－1 ) / 2;

[0129] Output the running value sequence D of the target characteristic index according to the correction result.

[0130] Specifically, according to the correlation between each characteristic indicator, a correction model is established, and by comparing the deviation of the operating values ​​of each characteristic indicator at the same time, it is determined whether there is an abnormality in the deviation of the current target characteristic indicator at each time. If there is an abnormality, the operating value collected at the corresponding time is marked as an abnormal value, and correction is performed using the difference method, thereby eliminating the abnormal values ​​in the data of each characteristic indicator and improving the evaluation accuracy of the state diagnosis model.

[0131] Specifically, when generating the operation risk value of the target device node, it includes:

[0132]

[0133] Where, f is the operation risk value of the target device node;

[0134] ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node;

[0135] e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

[0136] Specifically, the greater the operation risk value is, the greater the possibility that the cable of the current target device node has an operation abnormality.

[0137] It can be understood that in the above embodiment, the operating parameters are feature extracted according to the preset diagnostic model, and data correction is performed according to the correlation between various feature indicators to eliminate abnormal data, and the operating risk value of each device node is generated according to the correction result, so as to timely warn of the abnormal operating status of each device node, help operation and maintenance personnel make maintenance decisions, and ensure the stable operation of the transmission cable.

[0138] In a preferred embodiment of the present application, when generating the state risk value of each device node, it includes:

[0139] Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters;

[0140]

[0141] Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators;

[0142] Generate the state risk value k of the target device node at the current feedback time node;

[0143] k = e3*f+e4*g;

[0144] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient;

[0145] Preset the first state risk value threshold K1;

[0146] If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node;

[0147] Determine in turn whether each device node generates a first-level warning instruction.

[0148] Specifically, the environmental evaluation index includes multiple parameters such as environmental humidity and environmental temperature. The larger the environmental evaluation value, the greater the interference of the current environment on the device node.

[0149] Specifically, the state risk value of each device node is generated through the environmental evaluation value and the operation risk value, so as to warn the potential risks of the device nodes based on the environmental parameters, improve the monitoring and early warning efficiency of the transmission cables, and ensure the safe operation of the transmission cables.

[0150] Specifically, the first-level warning instruction means that the current device node is very likely to have a risk of failure and needs to be repaired in a timely manner.

[0151] Based on another preferred embodiment of a method for diagnosing abnormal state of a transmission cable in a photovoltaic power station in any of the above preferred embodiments, this preferred embodiment provides a system for diagnosing abnormal state of a transmission cable in a photovoltaic power station, comprising:

[0152] The central control unit is used to establish multiple device nodes according to the transmission cable parameters;

[0153] The monitoring unit includes a plurality of monitoring modules, which are arranged at the device nodes and used to collect the operation parameters and environmental parameters of each device node;

[0154] The central control unit includes:

[0155] The first processing module is used to generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node; n is the number of device nodes;

[0156] The second processing module is used to obtain the operating parameters of each device node and generate the operating risk value of each device node according to the preset state diagnosis model;

[0157] The third processing module is used to obtain the environmental parameters of each device node and generate the environmental evaluation value of each device node according to the environmental parameters;

[0158] The third processing module is also used to generate a state risk value for each device node according to the environmental evaluation value and the operation risk value.

[0159] In a preferred embodiment of the present application, the second processing module is also used for:

[0160] Preset multiple feedback time nodes;

[0161] Set the collection parameters for a single feedback time point, including: number of data collection times and total collection time;

[0162] Set a single collection cycle based on the total collection duration;

[0163] A single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times;

[0164] The operating parameters of each device node are obtained in turn according to the collection parameters.

[0165] Specifically, the second processing module is further used for:

[0166] According to the device node sequence A, set ai as the target device node in sequence;

[0167] Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes;

[0168] Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters;

[0169] Generate initial monitoring data for each characteristic indicator;

[0170] Correct the initial monitoring data of each characteristic index in turn according to the correction model;

[0171] Generate an operation risk value of the target device node according to the correction result and the status diagnosis model;

[0172] Generate the operation risk value of each device node in turn;

[0173] Establish an operation risk value sequence F, F = (f1, f2...fi...fn), where fi is the operation risk value of the i-th device node;

[0174] Among them, when generating the operation risk value of the target device node, it includes:

[0175]

[0176]

[0177] Where, f is the operation risk value of the target device node;

[0178] ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node;

[0179] e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

[0180] In a preferred embodiment of the present application, the third processing module is also used for:

[0181] Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters;

[0182]

[0183] Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators;

[0184] Generate the state risk value k of the target device node at the current feedback time node;

[0185] k = e3*f+e4*g;

[0186] Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient;

[0187] Preset the first state risk value threshold K1;

[0188] If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node;

[0189] Determine in turn whether each device node generates a first-level warning instruction.

[0190] According to the first concept of the present application, multiple device nodes are established according to the parameters of the transmission cable equipment, the operating parameters of the device nodes are periodically collected, and the features of the operating parameters are extracted according to the preset diagnostic model. The data is corrected according to the correlation between the various characteristic indicators, so as to eliminate abnormal data, and the operating risk value of each device node is generated according to the correction result, so as to timely warn of the abnormal operating status of each device node, facilitate the operation and maintenance personnel to make maintenance decisions, and ensure the stable operation of the transmission cable.

[0191] According to the second concept of the present application, by collecting the environmental parameters of each device node, multi-source data analysis is performed on each device node, the operating status of the transmission cable is corrected based on the real-time environmental evaluation value, and early warning of potential fault risks is issued, thereby improving the monitoring and early warning efficiency of the transmission cable and ensuring the safe operation of the transmission cable.

[0192] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for diagnosing abnormal status of transmission cables in photovoltaic power stations, characterized in that: include: Establish multiple device nodes according to transmission cable parameters; Obtaining the operating parameters of each device node, and generating the operating risk value of each device node according to the preset state diagnosis model; Obtaining environmental parameters of each device node, and generating environmental evaluation values ​​of each device node according to the environmental parameters; Generate the status risk value of each device node according to the environmental evaluation value and the operation risk value; When creating multiple device nodes, include: Generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node and n is the number of device nodes.

2. The method for diagnosing abnormal status of transmission cables in a photovoltaic power station according to claim 1, characterized in that: When obtaining the operating parameters of each device node, including: Preset multiple feedback time nodes; Setting the collection parameters of a single feedback time point, the collection parameters include: the number of data collection times and the total collection time; Set a single collection cycle based on the total collection duration; The single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times; The operating parameters of each device node are obtained in turn according to the collection parameters.

3. The method for diagnosing abnormal status of transmission cables in a photovoltaic power station according to claim 1, characterized in that: When generating the operation risk value of each device node, it includes: According to the device node sequence A, set ai as the target device node in sequence; Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes; Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters; Generate initial monitoring data for each characteristic indicator; Correct the initial monitoring data of each characteristic index in turn according to the correction model; Generate an operation risk value of the target device node according to the correction result and the status diagnosis model; Generate the operation risk value of each device node in turn; An operation risk value sequence F is established, where F = (f1, f2...fi...fn), wherein fi is the operation risk value of the i-th device node.

4. The method for diagnosing abnormal status of transmission cables in a photovoltaic power station according to claim 3, characterized in that: When correcting the initial monitoring data of each characteristic indicator in turn, it includes: According to the characteristic index sequence B, the i-th characteristic index is selected as the target characteristic index; Generate the running value sequence D of the target characteristic index, D = (d1, d2...d i …d m ), where di is the running value of the target characteristic index collected at the rth moment in the collection cycle of the current feedback time node; Establish a correction model based on the correlation between various characteristic indicators; According to the calibration model and the running value series of the remaining characteristic indexes, it is judged in turn whether each running value in the running value series D is an abnormal value; If di is an abnormal value, set d i =(d i+1 +d i－1 ) / 2; Output the running value sequence D of the target characteristic index according to the correction result.

5. The method for diagnosing abnormal status of transmission cables in a photovoltaic power station according to claim 4, characterized in that: When generating the operation risk value of the target device node, it includes: Where, f is the operation risk value of the target device node; ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node; e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

6. The method for diagnosing abnormal status of transmission cables in a photovoltaic power station according to claim 5, characterized in that: When generating the status risk value of each device node, it includes: Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters; Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators; Generate the state risk value k of the target device node at the current feedback time node; k = e3*f+e4*g; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Preset the first state risk value threshold K1; If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node; Determine in turn whether each device node generates a first-level warning instruction.

7. A photovoltaic power station transmission cable abnormal state diagnosis system, using the photovoltaic power station transmission cable abnormal state diagnosis method described in any one of claims 1 to 6, characterized in that: include: The central control unit is used to establish multiple device nodes according to the transmission cable parameters; A monitoring unit, comprising a plurality of monitoring modules, wherein the monitoring modules are arranged at the device nodes and are used to collect operating parameters and environmental parameters of each device node; The central control unit comprises: The first processing module is used to generate a device node sequence A, A = (a1, a2 ... ai ... an), where ai is the i-th device node; n is the number of device nodes; The second processing module is used to obtain the operating parameters of each device node and generate the operating risk value of each device node according to the preset state diagnosis model; The third processing module is used to obtain the environmental parameters of each device node and generate the environmental evaluation value of each device node according to the environmental parameters; The third processing module is further used to generate a state risk value of each device node according to the environmental evaluation value and the operation risk value.

8. The photovoltaic power station transmission cable abnormal state diagnosis system according to claim 7, characterized in that: The second processing module is also used for: Preset multiple feedback time nodes; Setting the collection parameters of a single feedback time point, the collection parameters include: the number of data collection times and the total collection time; Set a single collection cycle based on the total collection duration; The single monitoring cycle includes multiple moments, and a moment sequence T is established based on the time axis, T = (t1, t2...ti...tm), ti is the i-th moment in a single collection cycle; m is the number of data collection times; The operating parameters of each device node are obtained in turn according to the collection parameters.

9. The photovoltaic power station transmission cable abnormal state diagnosis system according to claim 7, characterized in that: The second processing module is also used for: According to the device node sequence A, set ai as the target device node in sequence; Generate multiple characteristic indicators according to the state diagnosis model, and establish a characteristic indicator sequence B, B = (b1, b2...b i …b n1 ), where b i is the i-th characteristic index; n1 is the number of characteristic indexes; Obtain the operating parameters of the target device node at the current feedback time node, and perform feature extraction on the operating parameters; Generate initial monitoring data for each characteristic indicator; Correct the initial monitoring data of each characteristic index in turn according to the correction model; Generate an operation risk value of the target device node according to the correction result and the status diagnosis model; Generate the operation risk value of each device node in turn; Establish an operation risk value sequence F, F = (f1, f2...fi...fn), where fi is the operation risk value of the i-th device node; Among them, when generating the operation risk value of the target device node, it includes: Where, f is the operation risk value of the target device node; ɑi is the influencing factor of the i-th characteristic indicator, Ci is the deviation evaluation value of the i-th characteristic indicator at the current feedback time node; e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; d ir is the running value of the i-th characteristic indicator collected at the r-th moment in the collection cycle of the current feedback time node; Δd i is the average running value of the i-th characteristic index collected at all times in the collection cycle of the current feedback time node; d' i is the standard operating value of the i-th characteristic indicator.

10. The photovoltaic power station transmission cable abnormal state diagnosis system according to claim 9, characterized in that: The third processing module is further used for: Obtaining the environmental parameters of the target device node, and generating an environmental evaluation value g of the target device node according to the environmental parameters; Among them, βi is the influencing factor of the i-th environmental monitoring indicator; hi is the real-time reference value of the i-th environmental monitoring indicator of the target device node at the current feedback time node; h'i is the standard reference value of the i-th environmental monitoring indicator of the target device node; η is the number of environmental monitoring indicators; Generate the state risk value k of the target device node at the current feedback time node; k = e3*f+e4*g; Wherein, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Preset the first state risk value threshold K1; If k>K1, a first-level warning instruction of the target device node is generated at the current feedback time node; Determine in turn whether each device node generates a first-level warning instruction.

Images