Risk detection method and equipment for converter station, and storage medium

Abstract

The invention discloses a risk detection method and device for a converter station, and a storage medium. The method comprises the following steps: determining various types of electrical devices in the converter station; for the same type, generating a total state value according to the operation state of the electrical equipment; for the same type, generating a total alarm value according to the alarm signal of the electrical equipment; acquiring site information related to the operation state and the alarm signal of the converter station; determining an extreme learning machine; and inputting the total state value and the total alarm value of the same type and the station information into an extreme learning machine to detect the risk level of the converter station. According to the embodiment of the invention, overall state and alarm analysis is carried out on different types of electrical equipment of the converter station, and more comprehensive information is provided in combination with overall information of the converter station, so that the risk of the converter station is evaluated globally, the risk detection precision of the converter station is improved, and the risk detection efficiency of the converter station is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power, and in particular to a risk detection method, device and storage medium for a converter station. Background Art

[0002] In the power grid, DC transmission technology is widely used in power systems due to its unique advantages in long-distance transmission, such as high efficiency, low loss, and flexible regulation. The converter station is one of the core facilities of the DC transmission system. The converter station is the link between the AC line and the DC line. Its main function is to efficiently convert AC and DC to achieve stable operation of the power system.

[0003] Due to the diversity of equipment and complex operating conditions in converter stations, the failure of any device may cause the entire system to collapse, or even trigger a chain reaction, affecting power supply in a wide range of areas.

[0004] Currently, single equipment or single events in converter stations are usually analyzed, and the efficiency of detecting the overall risk of converter stations is low. Summary of the invention

[0005] In view of this, the present invention provides a converter station risk detection method, device and storage medium, so as to improve the efficiency of detecting the overall risk of the converter station.

[0006] A first aspect of the present invention provides a risk detection method for a converter station, comprising:

[0007] Identify various types of electrical equipment in converter stations;

[0008] For the same type, a total status value is generated according to the operating status of the electrical equipment;

[0009] For the same type, generating a total alarm value according to the alarm signal of the electrical equipment;

[0010] collecting station information related to the operating status and alarm signals of the converter station;

[0011] Determine the extreme learning machine;

[0012] The total state value and the total alarm value of the same type, as well as the site information, are input into the extreme learning machine to detect the risk level of the converter station.

[0013] A second aspect of the present invention provides a risk detection device for a converter station, comprising:

[0014] An equipment determination module is used to determine various types of electrical equipment in a converter station;

[0015] A total status value generating module, used for generating a total status value according to the operating status of the electrical equipment of the same type;

[0016] A total alarm value generating module, used for generating a total alarm value according to the alarm signal of the electrical equipment of the same type;

[0017] A site information collection module, used for collecting site information related to the operating status and alarm signals of the converter station;

[0018] An extreme learning machine determination module, used for determining an extreme learning machine;

[0019] The risk level detection module is used to input the total state value and the total alarm value of the same type, as well as the site information, into the extreme learning machine to detect the risk level of the converter station.

[0020] A third aspect of the present invention provides an electronic device, the electronic device comprising:

[0021] at least one processor; and

[0022] a memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk detection method for the converter station as described in the first aspect above.

[0024] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the risk detection method for a converter station as described in the first aspect above.

[0025] A fifth aspect of the present invention provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the risk detection method for a converter station as described in the first aspect above is implemented.

[0026] In this embodiment, various types of electrical equipment are determined in the converter station; for the same type, a total state value is generated according to the operating state of the electrical equipment; for the same type, a total alarm value is generated according to the alarm signal of the electrical equipment; the site information related to the operating state and the alarm signal of the converter station is collected; an extreme learning machine is determined; the total state value and the total alarm value of the same type, as well as the site information are input into the extreme learning machine to detect the risk level of the converter station. This embodiment performs an overall state and alarm analysis on different types of electrical equipment in the converter station, and provides more comprehensive information in combination with the overall information of the converter station, thereby evaluating the risk of the converter station from a global perspective, improving the accuracy of detecting the risk of the converter station, and effectively improving the efficiency of detecting the risk of the converter station.

[0027] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 This is a flow chart of a risk detection method for a converter station provided in Embodiment 1 of the present invention.

[0030] Figure 2 It is a structural schematic diagram of an extreme learning machine provided in Example 1 of the present invention.

[0031] Figure 3 It is a structural schematic diagram of a risk detection device for a converter station provided in Embodiment 2 of the present invention.

[0032] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can cover sequential implementations other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Embodiment 1

[0036] See also Figure 1 , shows a flow chart of a risk detection method for a converter station provided by Embodiment 1 of the present invention, the method can be executed by a risk detection device for a converter station, the risk detection device for a converter station can be implemented in the form of hardware and / or software, and the risk detection device for a converter station can be configured in an electronic device. Figure 1 As shown, the method includes:

[0037] Step 101: Determine various types of electrical equipment in a converter station.

[0038] In this embodiment, the electrical equipment in the converter station can be divided into multiple types according to their functions.

[0039] Exemplarily, the types of electrical equipment in the converter station include converter valves (such as thyristor converter valves, IGBT converter valves, etc.), converter transformers (such as single-phase two-winding converter transformers, three-phase three-winding converter transformers, etc.), smoothing reactors (such as dry-type smoothing reactors, oil-immersed smoothing reactors, etc.), AC filters (such as passive AC filters, active AC filters, etc.), DC filters (such as smoothing DC filters, active DC filters, etc.), reactive compensation equipment (such as static VAR compensators (SVCs), static VAR generators (SVGs), etc.), and control and protection equipment (such as converter station control systems, relay protection equipment, etc.).

[0040] Step 102: For the same type of electrical equipment, generate a total status value according to the operating status of the electrical equipment.

[0041] In this embodiment, various types of electrical equipment in the converter station can be traversed, and for the electrical equipment of the same type, the overall total status value of the electrical equipment of the same type is generated based on the operating status of these electrical equipment, thereby quantifying the overall operating status of the electrical equipment of the same type.

[0042] In a specific implementation, for each electrical device of the same type, a sub-state value representing the operating state is collected.

[0043] Generally, the sub-status value can be calculated based on the performance parameters (such as load, etc.) of the electrical equipment during self-inspection and uploaded to the cloud.

[0044] The operating status of each electrical device conforms to the normal distribution. At this time, the average value and standard deviation of each sub-state value can be calculated.

[0045] The average value is expressed as follows:

[0046]

[0047] Among them, n i The number of electrical equipment of type i, p ij is the sub-state value of the jth electrical equipment in the i-th type, is the average value of the i-th type.

[0048] The standard deviation is expressed as follows:

[0049]

[0050] Among them, n i The number of electrical equipment of type i, p ij is the sub-state value of the jth electrical equipment in the i-th type, is the average value of the ith type, σ i is the standard deviation of the ith type.

[0051] Use linear or nonlinear methods to generate the total state value from the sub-state values, mean and standard deviation.

[0052] Exemplarily, the total state value is expressed as:

[0053]

[0054] Among them, C i is the total state value of the i-th type, n i The number of electrical equipment of type i, p ij is the sub-state value of the jth electrical equipment in the ith type, k is the importance weight of the electrical equipment, is the average value of the ith type, σ i is the standard deviation of the ith type, r i is the correction coefficient of the ith type.

[0055] Further, k is the exponential parameter of the power mean, which is used to control the influence of the sub-state value of the electronic device on the total state value of this type of electrical device. When k > 1, the influence of the sub-state value of the electronic device on the total state value of this type of electrical device is more significant; when 0 < k < 1, the influence of the sub-state value of the electronic device on the total state value of this type of electrical device is less significant; the recommended value of k is 2, and in practical applications, k can be assigned and modified according to the importance of this electrical device.

[0056] r i used to adjust the influence of the total state value of the i-th type of electrical device on the overall risk assessment of the converter station, r i The recommended value of is 1, and in practical applications, r can be assigned and modified according to the importance of this type of electrical device. i for assignment modification.

[0057] Step 103: For the same type, generate the total alarm value according to the alarm signals of the electrical devices.

[0058] In this embodiment, the electrical devices of each type in the converter station can be traversed. For the electrical devices of the same type, the alarm signals sent when these electrical devices detect abnormalities during self-inspection can be collected, and the total alarm value of the electrical devices of the same type as a whole can be generated according to these alarm signals, so as to quantify the abnormalities of the electrical devices of the same type as a whole.

[0059] In specific implementation, for the same type, alarm signals of various levels are collected from each electrical device within a preset time range, and the urgency of the alarm signals at different levels is different.

[0060] For each level, the number of alarm signals within the same level can be separately counted, so as to generate the total alarm value in a linear or non-linear manner according to the number of alarm signals within each level.

[0061] Exemplarily, the levels include the emergency category, the alarm category, and the minor category; among them, the urgency of the emergency category is higher than that of the alarm category, and the urgency of the alarm category is higher than that of the minor category.

[0062] In this example, the total alarm value is expressed as:

[0063]

[0064] where, T i is the total alarm value of the i-th type, X i is the number of alarm signals of the emergency category within the i-th type, Y i is the number of alarm signals of the alarm category within the i-th type, Z iis the number of minor alarm signals in the i-th type, γ is the attenuation factor, β is the impact weight, a is the weight of the emergency alarm signal, b is the weight of the alarm signal, and c is the weight of the minor alarm signal.

[0065] When γ increases, the total alarm value is more sensitive to changes in the number of alarm signals of each level, causing the total alarm value to drop faster; when γ decreases, the tolerance of the total alarm value to changes in the number of alarm signals of each level increases, slowing down the rate at which the total alarm value drops; the recommended value of γ is 0.02. In actual applications, γ can be assigned and modified according to the urgency of the alarm signal of the electrical equipment of this type.

[0066] β is the linear influence weight of the total number of alarm signals, which is used to control the influence of the total number of alarm signals on the total alarm value. When β increases, the penalty of the total number of alarm signals on the total alarm value is increased, making the decrease of the total alarm value more obvious; when β decreases, the influence of the total number of alarm signals on the total alarm value is reduced, and the total alarm value is more tolerant to the change of the total number of alarm signals; the recommended value of β is 0.05. In practical applications, β can be assigned and modified according to the specific requirements of the total number of alarm signals of electrical equipment of this type.

[0067] a is used to reflect the severity of the emergency alarm signal of the electrical equipment under this type. The recommended value of a is 0.1. In actual applications, a can be modified according to the urgency of the emergency alarm signal of the electrical equipment under this type. b is used to reflect the severity of the alarm signal of the alarm type of the electrical equipment under this type. The recommended value of b is 0.05. In actual applications, b can be modified according to the urgency of the alarm signal of the alarm type of the electrical equipment under this type. c is used to reflect the severity of the minor alarm signal of the electrical equipment under this type. The recommended value of c is 0.02. In actual applications, c can be modified according to the urgency of the minor alarm signal of the electrical equipment under this type.

[0068] Step 104: Collect station information related to the operating status and alarm signals of the converter station.

[0069] In this embodiment, the station information related to the operating status and alarm signals can be collected from the converter station, so as to enhance the total status value and the total alarm value.

[0070] In one case, when the protection device is triggered to perform a protection action, the protection action of the protection device in the converter station is collected within a preset time range (such as 1 day).

[0071] The number of times the protection actions are correctly executed is counted, recorded as the number of correct actions, and the number of all protection actions is counted, recorded as the total number of actions.

[0072] The ratio between the number of correct actions and the total number of actions is set as the protection action correctness rate, which serves as the site information related to the alarm signal.

[0073] At this time, the protection action accuracy can be expressed as:

[0074] In another case, within a preset time range (such as 1 day), the actual operating load of the converter station is collected, and the ratio between the actual operating load and the preset rated maximum load is set as the average load rate as the site information related to the operating status.

[0075] At this time, the average load rate can be expressed as:

[0076] Step 105: Determine the extreme learning machine.

[0077] In this embodiment, an extreme learning machine (ELM) may be pre-trained to detect risks of the converter station.

[0078] Furthermore, the extreme learning machine is a single hidden layer feedforward neural network that has the characteristics of randomly generating the weights of the input layer and the bias of the hidden layer, and quickly completes the training by minimizing the weights of the output layer. ELM has high computational efficiency and is suitable for processing large-scale data. It also shows strong generalization ability in classification and regression tasks.

[0079] In practical applications, the output effect of ELM is not stable due to the random generation of input layer weights and hidden layer biases. To overcome this shortcoming, the human learning optimization algorithm (Human Learning-based Optimization, HLO) can be introduced in this embodiment to help ELM find the optimal input layer weights and hidden layer biases.

[0080] Among them, HLO is an optimization algorithm that simulates human learning behavior. It achieves global optimization by imitating the process of human acquisition of knowledge, reflection on mistakes, and continuous improvement. HLO combines experience accumulation and environmental adaptability, has a strong balance between exploration and development, and is suitable for complex optimization problems.

[0081] By using the extreme learning machine (ELM), an efficient neural network algorithm, combined with the human learning optimization algorithm (HLO), it is possible to fully utilize the massive data generated during the operation of the converter station, automatically learn and identify potential risk patterns, and thus achieve more accurate risk assessment. This data-driven approach can adjust network parameters through optimization algorithms, quickly adapt to changes in the operating status of the power grid, provide real-time risk assessment and early warning, and thus provide more scientific and reliable decision support for power system managers.

[0082] During the training process, training sets can be collected for converter stations in units of a preset time range (such as day); each piece of data in the training set includes the total status value and total alarm value of the same type of converter station in history, site information and risk level.

[0083] Among them, the risk level is a manually marked label.

[0084] Randomly set the weights of the input layer and the biases of the hidden layer in the extreme learning machine.

[0085] The weights of the input layer and the bias of the hidden layer in the extreme learning machine are iteratively updated according to the training set. In each round of iteration, the training set is input into the extreme learning machine to detect the risk level of the converter station, and the fitness of the weights of the input layer and the bias of the hidden layer in the extreme learning machine is calculated according to the difference between the detected risk level and the risk level as the label. The weights of the input layer and the bias of the hidden layer in the extreme learning machine are updated according to the fitness by using selection operations, exchange operations and mutation operations.

[0086] Among them, the higher the fitness value, the better the ELM performance under the weight of the input layer and the bias of the hidden layer.

[0087] When completing the iterative update, the extreme learning machine selects the weight of the input layer and the bias of the hidden layer when the fitness is the highest.

[0088] In practical applications, the training set of ELM can be expanded by collecting more data sets, thereby achieving continuous self-learning and continuous optimization of ELM.

[0089] Step 106: Input the total state value and total alarm value of the same type and the site information into an extreme learning machine to detect the risk level of the converter station.

[0090] In this embodiment, if Figure 2 As shown, the total state value and total alarm value of the same type, as well as site information (such as protection action accuracy, average load rate, etc.) can be input into the extreme learning machine.

[0091] In the extreme learning machine, the risk level is output at the output layer after being processed by the weight of the input layer and the bias of the hidden layer. The risk level refers to the impact and degree of harm of the risk, which is divided into levels.

[0092] Exemplarily, the risk level is divided into four levels: Level I, Level II, Level III, and Level IV, where Level I is the highest risk level and Level IV is the lowest risk level.

[0093] Generally speaking, the significance of risk assessment in converter stations can be reflected in the following two aspects:

[0094] 1) Through in-depth risk assessment, the power system can carry out targeted equipment maintenance, prioritize limited resources in high-risk areas, and optimize maintenance plans. This precise resource allocation can not only reduce operation and maintenance costs, but also greatly improve the reliability and efficiency of equipment operation.

[0095] 2) Through reliable risk assessment, potential operational hazards can be identified in advance. By continuously monitoring and evaluating the operating status of the converter station, possible abnormal conditions in the operation of the equipment or system can be discovered, and preventive measures can be taken in time to avoid failures from the source.

[0096] In this embodiment, various types of electrical equipment are determined in the converter station; for the same type, a total state value is generated according to the operating state of the electrical equipment; for the same type, a total alarm value is generated according to the alarm signal of the electrical equipment; the site information related to the operating state and the alarm signal of the converter station is collected; an extreme learning machine is determined; the total state value and the total alarm value of the same type, as well as the site information are input into the extreme learning machine to detect the risk level of the converter station. This embodiment performs an overall state and alarm analysis on different types of electrical equipment in the converter station, and provides more comprehensive information in combination with the overall information of the converter station, thereby evaluating the risk of the converter station from a global perspective, improving the accuracy of detecting the risk of the converter station, and effectively improving the efficiency of detecting the risk of the converter station.

[0097] Embodiment 2

[0098] See also Figure 3 , shows a schematic diagram of the structure of a risk detection device for a converter station provided by Embodiment 2 of the present invention. Figure 3 As shown, the device comprises:

[0099] The equipment determination module 301 is used to determine various types of electrical equipment in the converter station;

[0100] A total status value generating module 302 is used to generate a total status value according to the operating status of the electrical equipment of the same type;

[0101] A total alarm value generating module 303, for generating a total alarm value according to the alarm signal of the electrical equipment of the same type;

[0102] The site information collection module 304 is used to collect site information related to the operation status and alarm signals of the converter station;

[0103] An extreme learning machine determination module 305, used to determine an extreme learning machine;

[0104] The risk level detection module 306 is used to input the total state value and the total alarm value of the same type, as well as the site information, into the extreme learning machine to detect the risk level of the converter station.

[0105] In one embodiment of the present invention, the total state value generating module 302 is further used for:

[0106] For the same type, collecting sub-state values ​​representing the operating state of each of the electrical devices;

[0107] Calculating the average value and standard deviation for each of the sub-state values;

[0108] The sub-state values, the average value and the standard deviation are combined to generate a total state value.

[0109] In one embodiment of the present invention, the total state value is expressed as:

[0110]

[0111] Among them, C i is the total state value of the i-th type, n i The number of electrical equipment of type i, p ij is the sub-state value of the j-th electrical device in the i-th type, k is the importance weight of the electrical device, is the average value of the i-th type, σ i is the standard deviation of the ith type, r i is the correction coefficient of the ith type.

[0112] In one embodiment of the present invention, the total alarm value generating module 303 is further used to:

[0113] For the same type, alarm signals of various levels are collected from each of the electrical devices within a preset time range;

[0114] Count the number of warning signals of the same level;

[0115] A total alarm value is generated according to the number of the alarm signals in various levels.

[0116] In one embodiment of the present invention, the levels include emergency, alarm and minor; the urgency of the emergency is higher than that of the alarm, and the urgency of the alarm is higher than that of the minor;

[0117] The total alarm value is expressed as:

[0118]

[0119] Among them, Ti is the total alarm value of the i-th type, X i is the number of emergency alarm signals in the i-th type, Y i is the number of the alarm signals of the alarm class in the i-th type, Z i is the number of the alarm signals of the minor class within the ith type, γ is the attenuation factor, B is the impact weight, a is the weight of the alarm signal of the emergency class, b is the weight of the alarm signal of the alarm class, and c is the weight of the alarm signal of the minor class.

[0120] In one embodiment of the present invention, the site information collection module 304 is further used to:

[0121] Collecting protection actions of the protection device in the converter station within a preset time range;

[0122] Counting the number of correct actions of correctly executing the protection actions and the total number of actions of all the protection actions;

[0123] The ratio between the number of correct actions and the total number of actions is set as a protection action correctness rate as site information related to the alarm signal;

[0124] Collecting actual operating load of the converter station within a preset time range;

[0125] The ratio between the actual operating load and the preset rated maximum load is set as the average load rate as the site information related to the operating status.

[0126] In one embodiment of the present invention, the extreme learning machine determination module 305 is further used to:

[0127] Collect training sets; the training sets include total status values ​​and total alarm values ​​of the same type of converter stations in history, and station information;

[0128] Randomly set the weights of the input layer and the bias of the hidden layer in the extreme learning machine;

[0129] Iteratively updating the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the training set; in each round of iteration, inputting the training set into the extreme learning machine to detect the risk level of the converter station, calculating the fitness of the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the risk level, and updating the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the fitness;

[0130] When the iterative update is completed, the weight of the input layer and the bias of the hidden layer when the fitness is the highest are selected for the extreme learning machine.

[0131] The risk detection device for a converter station provided in an embodiment of the present invention can execute the risk detection method for a converter station provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to executing the risk detection method for a converter station.

[0132] Embodiment 3

[0133] See also Figure 4 , showing a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0134] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0135] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0136] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the risk detection method of the converter station.

[0137] In some embodiments, the risk detection method for the converter station may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the risk detection method for the converter station described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the risk detection method for the converter station in any other appropriate manner (e.g., by means of firmware).

[0138] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0139] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0140] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0141] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0142] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0143] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0144] Embodiment 4

[0145] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the risk detection method for a converter station provided in any embodiment of the present invention is implemented.

[0146] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0147] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0148] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A risk detection method for a converter station, characterized in that: include: Identify various types of electrical equipment in converter stations; For the same type, a total status value is generated according to the operating status of the electrical equipment; For the same type, generating a total alarm value according to the alarm signal of the electrical equipment; collecting station information related to the operating status and alarm signals of the converter station; Determine the extreme learning machine; The total state value and the total alarm value of the same type, as well as the site information, are input into the extreme learning machine to detect the risk level of the converter station.

2. The method according to claim 1, characterized in that For the same type, generating a total status value according to the operating status of the electrical equipment includes: For the same type, collecting sub-state values ​​representing the operating state of each of the electrical devices; Calculating the average value and standard deviation for each of the sub-state values; The sub-state values, the average value and the standard deviation are combined to generate a total state value.

3. The method according to claim 2, characterized in that The total state value is expressed as: Among them, C i is the total state value of the i-th type, n i The number of electrical equipment of type i, p ij is the sub-state value of the j-th electrical device in the i-th type, k is the importance weight of the electrical device, is the average value of the i-th type, σ i is the standard deviation of the i-th type, r i is the correction coefficient of the ith type.

4. The method according to claim 1, characterized in that: For the same type, generating a total alarm value according to the alarm signal of the electrical equipment includes: For the same type, alarm signals of various levels are collected from each of the electrical devices within a preset time range; Count the number of warning signals of the same level; A total alarm value is generated according to the number of the alarm signals in various levels.

5. The method according to claim 4, characterized in that The levels include emergency, alarm and minor; the emergency level is higher than the alarm level, and the alarm level is higher than the minor level; The total alarm value is expressed as: Among them, T i is the total alarm value of the i-th type, X i is the number of emergency alarm signals in the i-th type, Y i is the number of the alarm signals of the alarm class in the i-th type, Z i is the number of the alarm signals of the minor class within the i-th type, γ is the attenuation factor, β is the impact weight, a is the weight of the alarm signal of the emergency class, b is the weight of the alarm signal of the alarm class, and c is the weight of the alarm signal of the minor class.

6. The method according to claim 1, characterized in that The collecting of station information related to the operation status and alarm signal of the converter station includes: Collecting protection actions of the protection device in the converter station within a preset time range; Counting the number of correct actions of correctly executing the protection actions and the total number of actions of all the protection actions; The ratio between the number of correct actions and the total number of actions is set as a protection action correctness rate as site information related to the alarm signal; Collecting actual operating load of the converter station within a preset time range; The ratio between the actual operating load and the preset rated maximum load is set as the average load rate as the site information related to the operating status.

7. The method according to any one of claims 1 to 6, characterized in that The step of determining an extreme learning machine comprises: Collect training sets; the training sets include total status values ​​and total alarm values ​​of the same type of converter stations in history, and station information; Randomly set the weights of the input layer and the bias of the hidden layer in the extreme learning machine; Iteratively updating the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the training set; in each round of iteration, inputting the training set into the extreme learning machine to detect the risk level of the converter station, calculating the fitness of the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the risk level, and updating the weight of the input layer and the bias of the hidden layer in the extreme learning machine according to the fitness; When the iterative update is completed, the weight of the input layer and the bias of the hidden layer when the fitness is the highest are selected for the extreme learning machine.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the risk detection method for a converter station according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the risk detection method for a converter station according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the risk detection method for a converter station according to any one of claims 1 to 7 is implemented.

Images