Cross-type test method and system for power protection device

Abstract

The invention relates to the technical field of electric power system protection device testing, in particular to a cross-type testing method and system for an electric power protection device, and the method comprises the steps: carrying out the adaptive configuration of a hardware interface of a testing system; constructing feature vectors based on the interface features, the parameter features and the action logic features; performing similarity matching on the feature vector and a reference feature vector in a cross-type feature library to determine the type of the protection device; adapting an interface parameter, a signal parameter and a criterion parameter of the test system according to the type of the protection device; generating a test case according to the type of the protection device and the current running state of the protection device to be tested; and executing the test case on the to-be-tested protection device. By means of the mode, the problem that an existing testing system cannot guarantee the high efficiency and accuracy of testing of multiple types of protection devices is solved, the cross-type compatibility of the testing system is improved, and self-adaptive testing of the multiple types of protection devices is supported.

Description

Technical Field

[0001] This invention relates to the field of power system protection device testing technology, and in particular to a cross-type testing method and system for power protection devices. Background Technology

[0002] With the increasing demands for safe operation of power systems, the reliability and testing efficiency of protection devices have become critical challenges. Power systems employ a variety of protection devices, such as line protection for line fault isolation, transformer protection for transformer differential or gas protection, and busbar protection for busbar branch fault isolation. These devices differ significantly in interface specifications (e.g., 3-channel or 6-channel analog current), core parameters (e.g., impedance settings or differential current settings), and operating logic (e.g., distance protection or differential protection). Existing testing systems are typically designed for single-type devices, resulting in poor hardware compatibility, limited adaptability, and fragmented testing processes. This leads to low testing efficiency and insufficient accuracy, failing to meet the needs of batch testing of multiple types of devices.

[0003] While some existing technologies attempt to achieve adaptive testing of protection devices, none have solved the core challenge of cross-type adaptation. For example, existing technology (authorization announcement number CN111458585B) discloses a method and device for automatic detection of localized line protection devices based on automatic test case construction. This method automatically generates test cases by parsing the configuration file of the entire station system, thus achieving automated testing of line protection devices. However, this solution focuses only on the specific type of localized line protection, relies on the static mapping test logic of the preset configuration file, and lacks cross-type feature recognition and dynamic parameter adaptation mechanisms. When facing other types of devices such as transformer protection and bus protection, it is impossible to dynamically switch hardware interfaces or optimize test algorithms through software instructions. It still requires manual replacement of hardware modules or recompilation of test code, with adaptation taking up to several hours. At the same time, this solution does not consider the unique state parameters of different types of devices (such as transformer oil temperature or bus branch current difference). The test process is limited to a single device type and cannot achieve a unified closed loop of "type recognition - parameter adaptation - test case generation - result optimization". This results in an efficiency reduction of more than 50% and a test deviation of more than 15% when testing multiple types of devices in batches. Therefore, existing testing systems struggle to achieve breakthroughs in hardware compatibility, cross-type algorithm adaptation, and process uniformity. In particular, they lack software-controllable hardware configurations, online iteration of cross-type feature libraries, and type-independent testing frameworks, which fails to guarantee the efficiency and accuracy of testing multiple types of protection devices. Summary of the Invention

[0004] To address the aforementioned shortcomings or drawbacks, this invention provides a cross-type testing method and system for power protection devices, which can solve the problem that existing testing systems cannot guarantee the efficiency and accuracy of testing multiple types of protection devices.

[0005] This invention provides a cross-type testing method for power protection devices, comprising: Perform adaptive configuration on the hardware interface of the test system.

[0006] Feature vectors are constructed by extracting interface features, parameter features, and action logic features from the protection device under test.

[0007] The feature vector is matched with a reference feature vector in a pre-stored cross-type feature library, and the type of protection device is determined based on the similarity matching result.

[0008] Based on the type of protection device, a parameter mapping algorithm is used to adapt the interface parameters, signal parameters, and criterion parameters of the test system.

[0009] Test cases are generated based on the type of protection device and the current operating status of the protection device under test.

[0010] The test cases are executed on the protection device under test, and the parameter mapping algorithm and test case generation process are updated based on the deviation between the action response signal obtained from the test and the expected value.

[0011] According to a second aspect, the present invention provides a cross-type testing system for power protection devices, comprising: The interface adaptive configuration module is used to perform adaptive configuration on the hardware interfaces of the test system.

[0012] The feature vector construction module is used to construct feature vectors based on the interface features, parameter features, and action logic features extracted from the protection device under test.

[0013] The protection device type identification module is used to perform similarity matching between the feature vector and the reference feature vector in the pre-stored cross-type feature library, and determine the protection device type based on the similarity matching result.

[0014] The test system interface adaptation module is used to adapt the interface parameters, signal parameters, and criterion parameters of the test system based on the type of protection device and using a parameter mapping algorithm.

[0015] The test case generation module is used to generate test cases based on the type of protection device and the current operating status of the protection device under test.

[0016] The test case execution module is used to execute test cases on the protection device under test, and update the parameter mapping algorithm and test case generation process based on the deviation between the action response signal obtained from the test and the expected value.

[0017] According to a third aspect, the present invention provides an electronic device comprising: At least one processor; and The memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform a cross-type test method for any power protection device in the embodiments of the present invention.

[0018] According to another aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute a cross-type test method for any power protection device in the embodiments of the present invention.

[0019] The technical solution of this invention identifies the interface pin type, signal path number, and communication protocol of the protection device under test (DUT) by performing adaptive configuration of the hardware interface of the test system; constructs a feature vector based on the interface features, parameter features, and action logic features extracted from the DUT; performs similarity matching between the feature vector and reference feature vectors in a pre-stored cross-type feature library, and determines the protection device type based on the similarity matching result; adapts the interface parameters, signal parameters, and criterion parameters of the test system using a parameter mapping algorithm based on the protection device type; generates test cases according to the protection device type and the current operating state of the DUT; executes the test cases on the DUT, and updates the parameter mapping algorithm and the test case generation process based on the deviation between the obtained action response signal and the expected value.

[0020] In this technical solution, the present invention addresses the problem of fixed hardware interfaces and lack of adaptive expansion capabilities in existing testing systems, as described in the background section. Through adaptive hardware interface configuration, it dynamically identifies interface pin types, signal paths, and communication protocols, enabling adaptation to multiple types of protection devices without manual hardware module replacement. This solves the problems of poor compatibility and high maintenance costs caused by the hardware specialization of traditional systems. Regarding the issue of limited adaptive capabilities and lack of cross-type adaptation logic, cross-type device identification is achieved through feature vector construction and similarity matching, overcoming the limitation of existing systems that only support fine-tuning of single-type parameters. Addressing the problem of fragmented testing processes and lack of a unified adaptive closed loop, a parameter mapping algorithm adapts interface parameters, signal parameters, and criterion parameters, and generates test cases based on the current operating state, forming a unified closed-loop process of "type identification - parameter adaptation - test case generation - test execution - result optimization," eliminating the inefficiency of switching between multiple software programs and manually formulating solutions. Therefore, the technical solution of this invention solves the problem that existing testing systems cannot guarantee the efficiency and accuracy of testing multiple types of protection devices, improves the cross-type compatibility of the testing system, and supports adaptive testing of multiple protection device types. Attached Figure Description

[0021] Figure 1 This is a structural block diagram of a cross-type adaptive testing system for power protection devices according to an embodiment of the present invention; Figure 2 This is a flowchart of a cross-type testing method for a power protection device according to an embodiment of the present invention; Figure 3 This is a block diagram of the main control unit structure according to an embodiment of the present invention; Figure 4 This is a structural block diagram of a configurable interface unit according to an embodiment of the present invention; Figure 5 This is a structural block diagram of a status acquisition unit according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a test signal generation module according to an embodiment of the present invention; Figure 7 This is a system hardware structure block diagram according to an embodiment of the present invention; Figure 8 This is a flowchart of an adaptive testing method according to an embodiment of the present invention; Figure 9 This is a structural block diagram of a cross-type testing system for a power protection device according to an embodiment of the present invention; Figure 10 This is a block diagram of an electronic device used to implement embodiments of the present invention. Detailed Implementation

[0022] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0023] This invention provides a cross-type testing method for power protection devices based on a first aspect. This method can be applied to a cross-type adaptive testing system for power protection devices (hereinafter referred to as the "system"). The system operates locally or remotely via cloud collaboration within a substation automation system and across multiple types of protection devices and their nodes to complete adaptive testing and batch verification tasks for various types of protection devices. The deployed physical equipment includes, but is not limited to, a main control unit, a configurable interface unit, a status acquisition unit, a test signal generation module, a power supply unit, and a human-machine interface unit. These physical devices must possess adaptive hardware configuration, multi-dimensional data acquisition, fault simulation signal generation, and real-time communication capabilities to support cross-type feature recognition, dynamic parameter adaptation, and closed-loop test execution. This ensures the system can efficiently accommodate more than 15 device types, such as line protection, transformer protection, and busbar protection, achieving fully automated unattended operation and maintenance with a test accuracy deviation not exceeding 3%.

[0024] In some embodiments, such as Figure 1 The diagram shows the structural block of a cross-type adaptive testing system for power protection devices. This system achieves adaptive testing through the collaborative work of its various units. The specific implementation process is as follows: The user selects the test mode and initiates the process via the human-machine interface unit. The main control unit then sends a 3D detection command to the configurable interface module. When a transformer protection device (i.e., the device under test) is connected, the configurable interface module automatically identifies the transformer protection device's six current interfaces and matches them to the IEC 61850 protocol. It then adjusts the analog output channels to six and the range to 5 amps. The status acquisition unit can collect the device's operating current and lifespan loss rate in real time at a 1000 Hz sampling rate. The main control unit constructs a feature vector based on this data and matches it with a feature library using a weighted cosine similarity algorithm to identify the transformer protection type. The system then calls the differential protection test case. The test signal generation module outputs a 2.4 amp differential current signal, and the status acquisition unit records the action time as 0.019 seconds, with a deviation of 5% within the tolerance. The test data is synchronously stored on a local industrial storage card and a cloud platform, forming a closed-loop optimization.

[0025] like Figure 2 As shown, cross-type testing methods for power protection devices may include: Step S110: Perform adaptive configuration on the hardware interface of the test system.

[0026] Among them, the interface pin type can refer to the pin definition of the physical interface of the protection device (such as analog input pins and digital output pins), the number of signal channels can refer to the number of analog or digital channels (such as the number of current signal channels can be 3 or 6), and the communication protocol can refer to the data protocol for interaction between the device and the test system (such as IEC 61850 or Modbus).

[0027] Specifically, the system can perform adaptive configuration by sending three-dimensional detection commands from the main control unit, including: pin type detection (scanning pin levels to identify analog or digital signal types), signal path detection (sending single-channel current enable commands to count the number of response channels), and communication protocol detection (sending multi-protocol test frames to match frame header characteristics). For example, when a line protection device is connected, the system identifies it as a 3-channel current + 3-channel voltage analog interface through pin detection, determines that 3 current channels need to be enabled through path detection, and matches the IEC 61850 protocol through protocol detection. Subsequently, it automatically adjusts the range (e.g., 5 amps) and terminal mapping relationship. Generally, the adaptive configuration time does not exceed 30 seconds, ensuring rapid adaptation to multiple types of devices.

[0028] In some embodiments, such as Figure 3 The diagram shown is a block diagram of the main control unit. The core of this unit consists of a quad-core Cortex-A9 ARM (Advanced RISC Machines, i.e., an advanced reduced instruction set processor, such as...) Figure 3 Processing system units (represented by PS in Chinese) and programmable logic units (such as...) Figure 3 The system (represented by PL) is constructed collaboratively via shared memory. When the system initiates a transformer protection device test, the PS unit first calls the weighted feature matching algorithm of the cross-type adaptive algorithm module from the shared memory to calculate the similarity between the feature vector and the reference vector (e.g., a result of 0.94). Simultaneously, the PL unit sends pin type detection commands (e.g., scanning pin levels to identify 6 current interfaces) to the configurable interface module through the hardware control unit. The PS unit writes the algorithm result (device type: transformer protection) into the shared memory, and the PL unit reads it in real time and controls the test signal generation module to output a 2.4 ampere differential current signal, recording the action time with 1 microsecond accuracy through the status acquisition unit. Throughout the process, the shared memory enables data interaction between the PS and PL (e.g., type identifier, signal parameters), ensuring that algorithm decisions and hardware control are completed synchronously.

[0029] In some embodiments, such as Figure 4The diagram shows the structural block of the configurable interface unit, which employs a layered architecture to achieve adaptive configuration of the hardware interfaces. When the system connects to the protection device under test, the main control unit sends a three-dimensional detection command to this unit: the terminal mapping unit (hardware support) first scans the pin levels through the level detection unit (hardware support) to identify 6 current interfaces and 3 voltage interfaces; the analog configurable module then activates the 9U+9I range switching function, automatically adjusting the current range to 5 amps, and remaps the terminal connection relationship through the relay array (hardware support); simultaneously, the protocol detection engine (algorithm support) of the communication configurable module sends the corresponding test frames in parallel. After matching the device response to the IEC 61850 protocol, the protocol adaptive matching unit automatically loads the 4000 Hz sampling rate parameter. For example, when testing a line protection device, this unit can complete the entire process from identifying 3 current interfaces to range switching (e.g., 3 amps) and communication protocol matching (e.g., Modbus) within 30 seconds, without requiring manual replacement of hardware modules, thus improving cross-type adaptation efficiency.

[0030] Step S120: Construct a feature vector based on the interface features, parameter features, and action logic features extracted from the protection device under test.

[0031] The interface features include the number of analog input / output channels and the communication protocol type, such as 6 current channels and 3 voltage channels; the parameter features include current setting or impedance setting, such as differential current setting of 2 amperes; and the action logic features include distance protection or differential protection type, such as differential logic for transformer protection.

[0032] Specifically, the system can collect device data in real time through the status acquisition unit and combine the three types of feature data into a feature vector: ; in, For interface features, For parameter features, This refers to the action logic characteristics.

[0033] For example, for a transformer protection device, the eigenvector can be represented as: Differential protection; "6I+3U" indicates 6 current channels and 3 voltage channels.

[0034] Step S130: Perform similarity matching between the feature vector and the reference feature vector in the pre-stored cross-type feature library, and determine the type of protection device based on the similarity matching result.

[0035] Among them, the cross-type feature library pre-stores reference feature vectors for types such as line protection and transformer protection, and similarity matching is calculated by weighted cosine similarity algorithm.

[0036] Specifically, the system calculates the feature vector. With reference vector similarity value When the similarity value is not less than the preset threshold (e.g., 0.9), it is determined to be the corresponding type. For example, if the similarity value of the transformer protection reference vector is 0.94, the system automatically identifies it as a transformer protection type; otherwise, the manual assisted identification process is started.

[0037] Step S140: Based on the type of protection device, use a parameter mapping algorithm to adapt the interface parameters, signal parameters, and criterion parameters of the test system.

[0038] Among them, the parameter mapping algorithm can refer to the mapping algorithm using a fuzzy neural network; the interface parameters include the number and range of analog signals, the signal parameters include the amplitude of the fault signal, and the criterion parameters include the action time limit.

[0039] Specifically, the system uses this parameter mapping algorithm to take the device type (such as line protection) and parameter type as input, and maps them to specific parameter values ​​through fuzzy rules (such as "high / medium / low" sets). For example, the impedance signal amplitude of line protection is adapted to 1.5 times the impedance setting, i.e. Alternatively, for line protection with an impedance setting of 10 ohms, the system automatically generates an impedance fault signal with an amplitude of 15 ohms.

[0040] In some embodiments, the training process of the fuzzy neural network of the parameter mapping algorithm may include the following steps: First, historical test data is collected to construct the training input set. This dataset contains interface parameters, signal parameters, and corresponding correct judgment parameters of various typical protection devices (such as line protection and transformer protection) under different test scenarios, serving as sample labels. Subsequently, the data undergoes preprocessing operations such as normalization. Network training employs a supervised backpropagation algorithm. Specifically, in the forward computation, the input samples are processed by the network's fuzzy rule layer and linear combination coefficients to obtain the predicted output of the parameter mapping. Then, the mean squared error between the predicted output and the sample labels is calculated as the loss function. During backpropagation, based on the error gradient descent principle, the connection weights and linear combination coefficients in the network are adjusted layer by layer (i.e., in the formula...). and To minimize the loss function, this iterative optimization process continues until the network converges or reaches the preset number of iterations, thereby ensuring that the trained network can accurately achieve intelligent mapping from device features to test parameters.

[0041] Step S150: Generate test cases based on the type of protection device and the current operating status of the protection device under test.

[0042] The current operating status includes the operating current and life loss rate, for example, the operating current is 400 amps and the life loss rate is 30%; the test cases include distance protection test, differential protection test and other types.

[0043] Specifically, the system can calculate use case priority scores based on the correlation matrix, prioritizing high-scoring use cases. If the device is in an aging state (life loss rate exceeding 60%), high-risk use cases (such as long-term overload tests) are filtered out. For example, when the transformer protection reaches an oil temperature of 40 degrees Celsius, the system generates a differential instantaneous trip test as a priority use case.

[0044] Step S160: Execute test cases for the protection device under test, and update the parameter mapping algorithm and test case generation process based on the deviation between the action response signal obtained from the test and the expected value.

[0045] The action response signal includes the tripping time or the action current value. The expected value is calculated based on the device setting. The system can calculate the deviation between the response signal and the expected value using the following formula (1): |Test value − Theoretical value| / Theoretical value (1); Specifically, the system can control the test signal generation module to output a fault simulation signal (such as a differential current of 2.4 amperes), record the action time through the status acquisition unit, and if the deviation exceeds a preset tolerance (such as 5%), adjust the rule coefficients of the parameter mapping algorithm (such as the coefficients of the fuzzy neural network). The system then updates the test case association matrix. For example, when the action time deviation is 6%, the system automatically lowers the priority of the impedance test cases and stores the data in the cloud for iterative optimization.

[0046] Therefore, according to the above implementation method, the system can identify the interface pin type, signal path number, and communication protocol of the protection device under test by performing hardware interface adaptive configuration of the test system; construct a feature vector based on the interface features, parameter features, and action logic features extracted from the protection device under test; perform similarity matching between the feature vector and the reference feature vector in the pre-stored cross-type feature library, and determine the protection device type according to the similarity matching result; adapt the interface parameters, signal parameters, and criterion parameters of the test system using a parameter mapping algorithm based on the protection device type; generate test cases according to the protection device type and the current operating state of the protection device under test; execute the test cases on the protection device under test, and update the parameter mapping algorithm and the test case generation process according to the deviation between the action response signal obtained from the test and the expected value.

[0047] In this technical solution, this embodiment addresses the problem of fixed hardware interfaces and lack of adaptive expansion capabilities in existing test systems, as described in the background section. Through adaptive hardware interface configuration, it dynamically identifies interface pin types, signal paths, and communication protocols, enabling adaptation to multiple types of protection devices without manual hardware module replacement. This solves the problems of poor compatibility and high maintenance costs caused by the hardware specialization of traditional systems. Regarding the issue of limited adaptive capabilities and lack of cross-type adaptation logic, cross-type device identification is achieved through feature vector construction and similarity matching, overcoming the limitation of existing systems that only support fine-tuning of single-type parameters. Addressing the problem of fragmented test processes and lack of a unified adaptive closed loop, a parameter mapping algorithm adapts interface parameters, signal parameters, and criterion parameters, and generates test cases based on the current operating state, forming a unified closed-loop process of "type identification - parameter adaptation - test case generation - test execution - result optimization," eliminating the inefficiency of switching between multiple software programs and manually developing solutions. Therefore, the technical solution of this embodiment solves the problem that existing test systems cannot guarantee the efficiency and accuracy of testing multiple types of protection devices, improves the cross-type compatibility of the test system, and supports adaptive testing of multiple protection device types.

[0048] In some embodiments, adaptive configuration is performed on the hardware interface of the test system, including: Send probe commands to the hardware interface of the test system. The probe commands include pin type detection, signal path detection, and communication protocol detection.

[0049] Specifically, when performing pin type detection, the system can identify the physical type of the pin by scanning the level or signal response characteristics of the interface pin (e.g., high level indicates analog input, low level indicates digital output); when performing signal channel detection, the system can determine the number of analog or digital input channels by sending a single enable signal (e.g., a single current output command) and counting the number of response channels of the device; when performing communication protocol detection, the system sends test frames of multiple communication protocols in parallel (e.g., IEC 61850), Modbus, or CDT (Cyclic Data Transmission), analyzes the frame header or function code characteristics of the response frames to match the protocol types supported by the device.

[0050] For example, the system sends pin detection signals to the device under test: if a pin responds to an analog voltage signal (amplitude range 0~10V), it is identified as an analog input pin; simultaneously, through signal path detection, after enabling single-channel current output, if the device responds to 6 current inputs, then the number of analog input channels is determined to be 6; in communication protocol detection, after sending an IEC 61850 SV (sampled value) test frame, if the device returns valid data, then it matches the IEC 61850 protocol. Generally, the detection command is issued by the main control unit through an industrial bus (such as a CAN bus), taking no more than 2 seconds to ensure rapid identification.

[0051] Based on the results of pin type detection, the interface pin type of the protection device under test is identified.

[0052] The interface pin types include analog pins (for current or voltage signal input / output), digital pins (for status signals such as tripping or alarms), and digital communication pins (for protocol data transmission). For example, if the pin detection results show that pins 1-3 respond to current signals (amplitude 0-5 amperes) and pins 4-6 respond to voltage signals (amplitude 0-100 volts), the system identifies them as analog pins; if pins 7-8 respond to digital levels (high / low), the system identifies them as digital pins; and if pins 9-10 support data frame interaction, they are identified as communication pins.

[0053] Based on the results of signal path detection, the number of analog input paths of the protection device under test is determined.

[0054] The number of analog input channels refers to the number of analog signal channels accepted by the device, such as the number of current input channels or the number of voltage input channels. For example, through signal channel detection, if the system sends a single-channel current enable command and the device returns a 6-channel current response, then the number of analog input channels is determined to be 6 current channels; at the same time, the voltage channel detection displays 3 voltage input channels, thus fully describing the device interface specifications.

[0055] Based on the results of the communication protocol detection, the communication protocol of the protection device under test is matched.

[0056] Communication protocol matching refers to determining the communication protocol used by the device based on response characteristics (such as frame format and baud rate). For example, if the device returns correct sampled data to an IEC 61850 test frame but does not respond to a Modbus test frame, then it is matched to the IEC 61850 protocol; the system automatically loads protocol parameters, such as a sampling rate of 4000 Hz or dataset configuration.

[0057] Adjust the number of analog output channels, range configuration, and terminal mapping of the test system according to the interface pin type.

[0058] The range configuration refers to the setting of the range of analog signal output or input (e.g., a current range of 5 amps or 1 amp); the terminal mapping relationship refers to the physical connection correspondence between the test system terminals and the device pins. For example, for a device identified as transformer protection (requiring 6 current inputs), the system automatically adjusts the number of analog output channels to 6 and sets the range to 5 amps; simultaneously, it maps the test system terminals... to High-voltage side of the corresponding device to and low-pressure side to Pins ensure correct signal transmission.

[0059] Load the parameters corresponding to the communication protocol to complete the adaptive configuration of the hardware interface.

[0060] The communication protocol parameters include protocol-specific settings, such as the LD (Logical Device) name in IEC 61850 or the station address in Modbus. For example, after matching the IEC 61850 protocol, the system automatically loads the SV (Sampled Values) publication period of 250 microseconds and the GOOSE (Generic Object Oriented Substation Events) parameters to complete the configuration; the entire adaptive configuration process takes no more than 30 seconds and requires no manual intervention.

[0061] Therefore, according to the above implementation method, the system can dynamically adapt to various types of protection devices, eliminate the bottleneck of manually replacing hardware modules in traditional testing, and improve testing efficiency and compatibility.

[0062] In some embodiments, the test system is configured with a status acquisition unit; based on the interface features, parameter features, and action logic features extracted from the protection device under test, a feature vector is constructed, including: The status acquisition unit collects interface characteristic data, parameter characteristic data, and action logic characteristic data from the protection device under test. The interface characteristic data includes the number of analog input / output channels and the communication protocol type. The parameter characteristic data includes current setting or impedance setting. The action logic characteristic data includes distance protection or differential protection type.

[0063] Among them, the status acquisition unit refers to the hardware module in the test system responsible for real-time acquisition of the status data of the protection device. Its core components include an AD (Analog-to-Digital) conversion unit, a general parameter acquisition module (acquiring load current, bus voltage, etc. through current or voltage sensors) and a dedicated parameter acquisition module (acquiring dedicated parameters through oil temperature, gas or branch current sensors), realizing full-dimensional perception of "general parameters and dedicated parameters".

[0064] Interface characteristic data includes the number of analog input / output channels (e.g., 3 or 6 current channels) and communication protocol type (e.g., IEC 61850 or Modbus), used to describe the physical specifications of the device's hardware interface; parameter characteristic data includes current settings (e.g., differential current settings, in amperes) or impedance settings (e.g., distance protection impedance settings, in ohms), reflecting the device's protection parameter settings; and action logic characteristic data includes distance protection or differential protection types (e.g., distance protection logic for line protection or differential protection logic for transformer protection), characterizing the device's action behavior rules. Specifically, the system collects data in real time through the sensor array of the status acquisition unit (e.g., current sensors with an accuracy of 0.5 class and voltage sensors with a range of 0-100 volts), and performs AD conversion at a sampling rate of 1000 times per second to ensure data accuracy. For example, for a transformer protection device, the acquired interface characteristic data is "6 current channels and 3 voltage channels" analog quantities, with the communication protocol being IEC 61850; the parameter characteristic data is the differential current setting of 2 amperes; and the action logic characteristic data is the differential protection logic, forming the raw dataset.

[0065] In some embodiments, Figure 5 The diagram shows the structural block diagram of the status acquisition unit. The status acquisition unit adopts a hierarchical acquisition architecture to achieve comprehensive monitoring of the operating status of the power protection device. In specific implementation, when the system tests the transformer protection device, the general parameter acquisition module acquires the bus voltage (110 kV) and load current (400 amps) in real time at a sampling rate of 1000 times per second using voltage / current data acquisition hardware (accuracy class 0.5). Simultaneously, the dedicated parameter acquisition module acquires the transformer oil temperature (65 degrees Celsius), gas concentration (0.1% LEL), and high-voltage side branch current (280 amps) respectively using an oil temperature sensor (range 0-150 degrees Celsius), a gas concentration sensor (range 0-100% LEL, lower explosive limit), and a branch current sensor (accuracy class 0.2). All analog signals are digitized by an AD conversion unit (using a 24-bit Σ-Δ analog-to-digital converter), converting the oil temperature signal into the digital quantity "065.0 degrees Celsius" and the gas signal into "00.1% LEL", and combining them with the voltage and current data to form a status feature vector. Through this structure, the system completes full-dimensional data acquisition within 10 milliseconds, effectively identifying transformer overload (excessive current) and insulation hazards (abnormal oil temperature), providing accurate data support for the generation of subsequent test cases, and directly solving the problem of one-sided state perception in the background technology.

[0066] The interface feature data, parameter feature data, and action logic feature data are combined into a feature vector.

[0067] A feature vector is a mathematical vector formed by combining multi-dimensional feature data in a predetermined order, used to quantitatively represent device type characteristics. Specifically, the interface feature data is used as the first dimension (denoted as...). ), parameter feature data as the second dimension (denoted as Action logic feature data is used as the third dimension (denoted as...). ), construct feature vectors For example, for a transformer protection device, the eigenvector can be represented as... The “6I+3U” indicates 6 current channels and 3 voltage channels.

[0068] Therefore, according to the above implementation method, the system can efficiently and automatically construct feature vectors representing the type of protection device, providing standardized input for subsequent cross-type similarity matching, directly solving the problem of one-sided state perception (such as ignoring specific parameters) mentioned in the background technology, realizing full-dimensional feature extraction, and improving the accuracy of type recognition and the adaptive capability of the testing system.

[0069] In some embodiments, the protection device types include line protection, transformer protection, busbar protection, capacitor protection, and generator protection. A cross-type feature library is configured with interface feature data, parameter feature data, and action logic feature data. Similarity matching is performed between the feature vectors and reference feature vectors in the pre-stored cross-type feature library, and the protection device type is determined based on the similarity matching result, including: The similarity value between the feature vector and the reference feature vector is calculated by a weighted feature matching algorithm, and the similarity value is compared with a preset threshold.

[0070] Among them, the weighted feature matching algorithm refers to a method based on the calculation of weighted cosine similarity, used to quantify feature vectors. (in For interface features, For parameter features, (for action logic features) and reference feature vectors The similarity between them is considered. The algorithm weights are preset to 0.4 for interface features, 0.35 for parameter features, and 0.25 for action logic features, ensuring that key features for type recognition are matched first. Generally, the cross-type feature library is initialized based on standard device type data, and the update mechanism includes manually added new feature vectors.

[0071] Specifically, the system can calculate the similarity value between the feature vector and the reference feature vector using the following formula (2): (2); Wherein, the assumed weights (Interface features are the most critical for type identification) (Parameter features are secondary) (With action logic feature assistance), the result is a dimensionless value between 0 and 1. The preset threshold is set to 0.9, which is based on the test calibration of 100 different types of devices, and the recognition accuracy is not less than 99%.

[0072] For example, for transformer protection devices, the eigenvector With reference vector The similarity value of (transformer protection type) is calculated to be 0.94, and the system automatically compares it with the threshold of 0.9.

[0073] If the similarity value is not less than the preset threshold, the protection device type is determined to be the type corresponding to the reference feature vector.

[0074] Specifically, when the similarity value is not less than 0.9, the system directly determines that the device type is consistent with the reference vector without manual intervention. For example, if the similarity value of the above transformer protection is 0.94 ≥ 0.9, the system outputs the "transformer protection" type and automatically loads the corresponding test parameters.

[0075] If the similarity value is less than the preset threshold, the manual assisted recognition process will be initiated and the feature data in the cross-type feature library will be updated.

[0076] Generally, the manual-assisted identification process refers to the process where, when automatic identification fails, the user inputs device type information through a human-machine interface. The system records the new feature data and updates the feature library to optimize subsequent matching accuracy. For example, if the similarity value of the new type of reactor protection is 0.85 (<0.9), the system prompts the user to confirm the type and adds the new feature vector to the feature library to ensure future identification accuracy.

[0077] Therefore, according to the above implementation method, the system can achieve efficient and accurate automatic identification of protection device types, solve the problem of limited adaptive capability in the background technology, improve the type identification accuracy to over 99% through weighted algorithm and dynamic update mechanism, and support batch testing of multiple types of devices, reducing manual configuration time by more than 50%.

[0078] In some embodiments, test cases are generated based on the type of protection device and the current operating status of the protection device under test, including: Collect the current operating status data of the protection device under test, including operating current and life loss rate.

[0079] Among them, the current operating status data refers to the device operating parameters acquired in real time through the status acquisition unit, which are used to reflect the immediate working status of the device; the operating current represents the load current value of the circuit where the protection device is located, in amperes; the life loss rate represents the degree of performance degradation of the device due to long-term use, measured as a percentage, and calculated based on historical operating time, number of interruptions, etc.

[0080] Specifically, the system can acquire data at a sampling rate of 1000 times per second through the current sensor (accuracy class 0.5) and life monitoring module of the status acquisition unit to ensure real-time performance. For example, for a transformer protection device, if the operating current is 400 amperes and the life loss rate is 30%, a status dataset can be formed.

[0081] Based on the type of protection device and the current operating status data, the priority score of the test cases is calculated.

[0082] Among them, priority scoring refers to the algorithmic quantification of the execution priority of test cases, which is calculated based on device type, status parameters and historical test coverage.

[0083] For example, the system can use the correlation matrix algorithm to calculate the priority score using the following formula (3): (3); in, The priority weights are the corresponding values ​​in the type-state-use case association matrix. This represents the historical test coverage for the use case (a value closer to 1 indicates more comprehensive coverage). For example, for a line protection device (of the distance protection type), considering an operating current of 300 amps and a lifespan loss rate of 25%, calculate the priority of distance segment I testing. The score is 0.88 (out of 1.0), and the score for the overcurrent stage II test is 0.82.

[0084] Based on priority scoring, the target test case with the highest priority is selected from the pre-defined test case configuration as the test case.

[0085] Among them, the pre-set test case configuration refers to the set of test scenarios pre-stored in the system, such as distance protection test, overcurrent protection test, etc.; the target test case refers to the optimal test scenario selected based on the score.

[0086] Specifically, the system sorts the test cases in descending order of their scores and selects the top N test cases (e.g., the top three) as the execution targets. For example, if the priority scores for transformer protection are ranked as differential instantaneous trip test (0.86), oil temperature over-limit test (0.76), and gas protection test (0.72), then the system automatically selects the differential instantaneous trip test as the primary test case.

[0087] If the current operating status data indicates that the protection device under test is in an aging state, then remove the abnormal high-risk test cases from the test case configuration.

[0088] Among them, aging state refers to a life loss rate exceeding a preset threshold (e.g., 60%), indicating that the device is in a high wear stage; high-risk test cases refer to test scenarios that may exacerbate device damage or cause test deviations, such as long-term overload tests (fault duration exceeding 1 second). For example, if the life loss rate is 70% (exceeding the 60% threshold), the system automatically filters out long-term overload tests, retaining only safety test cases (e.g., differential instantaneous trip tests) to prevent device overload damage.

[0089] Therefore, according to the above implementation method, the system can dynamically generate test cases that adapt to the device type and status, thereby improving testing efficiency and security.

[0090] In some embodiments, the test system is further configured with a test signal generation module; test cases include distance protection test, overcurrent protection test, differential protection test, and gas protection test; the test cases are executed on the protection device under test, including: The control test signal generation module outputs a fault simulation signal to the protection device under test.

[0091] The test signal generation module is the hardware module in the test system responsible for generating simulated power system fault signals. Its core components include a fault simulation signal library (pre-stores over 100 fault waveform logics), a 24-bit DAC (Digital-to-Analog Converter) module (generates basic analog signals), a gain-adjustable amplifier (adjusts signal amplitude), and a signal amplitude limiter (prevents output over-limits). The fault simulation signal refers to the current or voltage waveform that simulates a real power fault, used to test the operating performance of protection devices, such as differential current signals or impedance fault signals. Specifically, the system sends output commands to the test signal generation module through the main control unit, for example, sending a "high-voltage side" command to the transformer protection device. Ampere, low-pressure side The "Ampere's differential current signal" is generated based on a 24-bit DAC that produces a basic waveform at a sampling rate of 1000 times per second. The waveform is then amplified to the target amplitude and output to the device via a configurable interface unit.

[0092] In some embodiments, Figure 6The diagram shows the structural block diagram of the test signal generation module. This module employs a layered signal generation architecture to achieve high-precision output of fault simulation signals. The module consists of four core units working collaboratively: a fault simulation signal library (algorithm support) pre-stores over 100 types of fault waveform logic (such as differential current waveforms and impedance fault waveforms); a 24-bit DAC module (digital-to-analog converter, hardware support) converts digital instructions into analog voltage signals with a resolution of 16,777,216 levels; a signal amplitude limiter (hardware support) clamps the output amplitude through hardware circuitry to prevent overshoot (e.g., current limit ±10 amps); and a gain-adjustable amplifier (hardware support) dynamically adjusts the gain coefficient according to the target range (e.g., adjustable from 0.1 to 10 times). In practical implementation, when the system performs differential protection testing on the transformer protection device, the fault simulation signal library calls up the differential current waveform digital sequence (e.g., 5 amps on the high-voltage side / 3 amps on the low-voltage side). The 24-bit DAC module converts this sequence into a reference voltage signal (e.g., 0~5 volts). The signal amplitude limiter ensures that the voltage does not exceed the limit (clamped to ±5 volts). The gain-adjustable amplifier amplifies the voltage to the corresponding current signal (gain coefficient 2.0) according to the target range (5 amps), and finally outputs a 2.4 amp differential current test signal. The entire process is completed within 10 milliseconds, with an output accuracy error ≤0.1%, supporting the test system to efficiently generate fault simulation signals adapted to multiple types of devices.

[0093] The status acquisition unit collects the action response signals of the protection device under test in real time.

[0094] Among them, the action response signal refers to the output signal generated by the protection device after receiving a fault simulation signal, such as a trip signal (indicating circuit breaker tripping) or an alarm signal (indicating an abnormal state). Specifically, the status acquisition unit can acquire signals in real time at a sampling rate of 1000 times per second through an AD conversion unit and a sensor array (such as current sensors and voltage sensors) to ensure data synchronization and accuracy. For example, in differential protection testing, the rise time of the trip signal acquired by the acquisition device is measured, such as... Figure 5 The state acquisition unit structure shown supports this process.

[0095] Record the action time and action value of the action response signal.

[0096] Among them, the action time refers to the time interval from the start of the fault simulation signal output to the triggering of the device action signal, and the unit is seconds; the action value refers to the measured value of relevant parameters when the device acts, such as the action current value or the action voltage value, and the unit is ampere or volt.

[0097] Specifically, the system can record the action time using a high-precision timer (1 microsecond resolution) and record the action value using the AD conversion result. For example, when testing transformer protection, the differential current action time is recorded as 0.019 seconds and the action current value as 2.05 amperes; the data is stored in real time to a local storage card or the cloud for subsequent deviation analysis.

[0098] Therefore, according to the above implementation method, the system can automatically and accurately execute test cases, and achieve high efficiency and reliability in the testing process through closed-loop control.

[0099] In some embodiments, the rule coefficients of the parameter mapping algorithm include linear combination coefficients in fuzzy rules, and the association matrix used in the test case generation process includes device type dimension, device state dimension, and test case type dimension; the steps of updating the parameter mapping algorithm and the test case generation process according to the deviation between the action response signal obtained from the test and the expected value include: Calculate the deviation between the action response signal and the expected value, and compare the deviation with a preset tolerance.

[0100] Among them, the action response signal refers to the actual output signal generated by the protection device after executing the test case, such as the action time (in seconds) or action current value (in amperes) of the trip signal; the expected value refers to the theoretical standard value calculated based on the protection device setting parameters (such as current setting or impedance setting), such as the theoretical action time of 0.02 seconds corresponding to the differential current setting of 2 amperes; the deviation refers to the relative difference between the actual value and the theoretical value, which is calculated by the above formula (1) and the result is a percentage value; the preset tolerance refers to the maximum deviation threshold allowed by the system, such as 5%, which is used to judge whether the test result is qualified.

[0101] If the deviation exceeds the preset tolerance, the linear combination coefficients are adjusted and the correlation matrix is ​​updated.

[0102] Linear combination coefficients refer to the regular coefficients in parameter mapping algorithms (fuzzy neural networks). and , used to calculate adaptation parameters; For example, the system can calculate the current signal amplitude using the following formula (4): ;(4); in, This represents the final current signal amplitude calculated by the parameter mapping algorithm, in amperes, and serves as the output target value of the test signal generation unit. The value represents the membership weight of the i-th fuzzy rule, ranging from 0 to 1, reflecting the degree of contribution of the rule to the output result, and is calculated through the fuzzification layer. This represents the proportional adjustment coefficient in the i-th fuzzy rule, used to dynamically adjust the amplitude ratio of the set current, and is one of the core rule parameters of the parameter mapping algorithm. This represents the DC offset in the i-th fuzzy rule, used to compensate for deviations caused by system errors or environmental factors, and is related to... Together they form a linear mapping relationship. This represents the reference current amplitude determined based on the protection device settings (such as differential current settings), in amperes, and serves as the basic input parameter for the algorithm. `n` represents the total number of rules in the fuzzy rule base, determining the computational complexity of the algorithm; it is usually preset to a fixed value (e.g., n=5) based on the device type. These coefficients are obtained through training on historical test data; adjustment coefficients refer to fine-tuning the coefficient values ​​based on the deviation magnitude. For example, if the deviation is 6%, then the gradient descent method (learning rate 0.01) will be used to adjust the coefficient values. The value decreased from 1.5 to 1.45. The association matrix refers to the three-dimensional matrix of "type-state-use case". The device type dimension (m) includes types such as line protection and transformer protection; the device status dimension (n) includes parameters such as operating current and life loss rate; and the use case type dimension (p) includes scenarios such as distance protection testing and differential protection testing. Updating the correlation matrix refers to adjusting the priority weights of use cases in the matrix based on the test results. For example, if the test deviation of a certain use case is greater than 5% for two consecutive tests, its priority weight will be adjusted. Reduce by 0.1. For example, for line protection devices, if the impedance test deviation is 6.7%, the system automatically adjusts the rule coefficients of the fuzzy neural network. And update the priority of the "impedance test" test cases in the correlation matrix to ensure that subsequent tests prioritize high-reliability test cases.

[0103] Test data is stored in the data layer, which is configured on local storage devices and cloud storage platforms.

[0104] The data layer refers to the module in the testing system used to store historical data, including local storage devices (such as industrial-grade memory cards with a capacity of no less than 100,000 records) and cloud storage platforms (such as remote servers, supporting data storage for no less than 5 years). Stored data includes key information such as device type, test time, test cases, action results, and deviation values. For example, after the test is completed, the system synchronously stores the transformer protection test data (device type, action time 0.019 seconds, deviation value 5%) to both the local memory card and the cloud platform, and uses timestamp indexing to support subsequent algorithm iterations and maintenance traceability.

[0105] Therefore, according to the above implementation method, the system can dynamically improve the test accuracy and adaptability through a closed-loop optimization mechanism.

[0106] In other embodiments of the invention, the system is based on, for example... Figure 7 The system hardware block diagram shown can perform tasks such as... Figure 8 The adaptive testing method flowchart shown enables efficient cross-type testing of power protection devices. Specifically, the core control module (CPU) in the hardware structure diagram serves as the system's main control unit, cooperating with various functional units via the ESP (Enhanced Serial Peripheral) bus: current amplifiers, voltage amplifiers, and DAC modules (digital-to-analog converters) are used to generate fault simulation signals; ADC (Analog-to-Digital Converter) modules and detection bridges are used for status acquisition; digital input / output units are used for interface pin detection and signal path identification; and the human-machine interface unit supports parameter setting and result display. When the system starts testing, the hardware units proceed according to... Figure 8 The process is automated: For example, when testing a transformer protection device, the core control module first sends a pin type detection command through the switch output unit to identify the device as a 6-channel current interface; then, the ADC module collects the operating current (420 amps) and life loss rate (35%) to construct a feature vector; the feature vector is compared with the feature library through a weighted similarity matching algorithm (weight: interface feature 0.4, parameter feature 0.35, action logic feature 0.25), and the similarity value of 0.94 exceeds the threshold of 0.9, thus determining it to be a transformer protection type; in the parameter self-adaptation stage, the fuzzy neural network (FNN) algorithm is called, and the differential current signal (2.4 amps) is output through the DAC module; after the test template is generated, the status acquisition unit records the action time of 0.019 seconds (expected value 0.02 seconds), with a deviation of 5% within the tolerance; finally, the test result self-optimization module updates the algorithm parameters and stores the data in the EEPROM (Electrically Erasable Programmable Read-Only Memory) of the human-machine interaction unit and the remote platform. The entire process is completed within 30 seconds without manual intervention, improving testing accuracy (deviation ≤3%) and efficiency, and solving the problems of poor hardware compatibility and fragmented processes in the background technology.

[0107] Figure 9 This is a structural block diagram of a cross-type testing system for a power protection device according to an embodiment of the present invention.

[0108] like Figure 9 As shown, the cross-type test system for this power protection device includes: The interface adaptive configuration module 210 is used to perform adaptive configuration on the hardware interface of the test system.

[0109] The feature vector construction module 220 is used to construct feature vectors based on the interface features, parameter features and action logic features extracted from the protection device under test.

[0110] The protection device type identification module 230 is used to perform similarity matching between the feature vector and the reference feature vector in the pre-stored cross-type feature library, and determine the protection device type based on the similarity matching result.

[0111] The test system interface adaptation module 240 is used to adapt the interface parameters, signal parameters, and criterion parameters of the test system based on the type of protection device using a parameter mapping algorithm.

[0112] The test case generation module 250 is used to generate test cases based on the type of protection device and the current operating status of the protection device under test.

[0113] The test case execution module 260 is used to execute test cases for the protection device under test, and update the parameter mapping algorithm and the test case generation process based on the deviation between the action response signal obtained from the test and the expected value.

[0114] In some embodiments, the test system is configured with a status acquisition unit; the feature vector construction module is further used to acquire interface feature data, parameter feature data and action logic feature data from the protection device under test through the status acquisition unit. The interface feature data includes the number of analog input / output channels and the communication protocol type, the parameter feature data includes current setting or impedance setting, and the action logic feature data includes distance protection or differential protection type; and the interface feature data, parameter feature data and action logic feature data are combined into a feature vector.

[0115] In some embodiments, the protection device types include line protection, transformer protection, busbar protection, capacitor protection, and generator protection. The cross-type feature library is configured with interface feature data, parameter feature data, and action logic feature data. The protection device type identification module is also used to calculate the similarity value between the feature vector and the reference feature vector through a weighted feature matching algorithm, and compare the similarity value with a preset threshold. If the similarity value is not less than the preset threshold, the protection device type is determined to be the type corresponding to the reference feature vector. If the similarity value is less than the preset threshold, the manual assisted identification process is initiated and the feature data in the cross-type feature library is updated.

[0116] The specific functions and examples of each module and submodule of the device in this embodiment of the invention can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0117] According to embodiments of the present invention, the above-described method of the present invention can be applied to an electronic device and a readable storage medium.

[0118] Figure 10 A schematic block diagram of an electronic device 600 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0119] like Figure 10 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0120] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0121] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a cross-type testing method for a power protection device. For example, in some embodiments, a cross-type testing method for a power protection device may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the cross-type testing method for a power protection device described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured by any other suitable means (e.g., by means of firmware) to perform a cross-type test method for a power protection device.

[0122] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0126] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0127] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0128] 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 this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this invention should be included within the scope of protection of this invention.

Claims

1. A cross-type testing method for power protection devices, characterized in that, include: Perform adaptive configuration on the hardware interface of the test system; A feature vector is constructed based on the interface features, parameter features, and action logic features extracted from the protection device under test. The feature vector is matched with a reference feature vector in a pre-stored cross-type feature library, and the type of protection device is determined based on the similarity matching result. Based on the type of protection device, the interface parameters, signal parameters, and criterion parameters of the test system are adapted using a parameter mapping algorithm. Test cases are generated based on the type of protection device and the current operating status of the protection device under test; The test cases are executed on the protection device under test, and the parameter mapping algorithm and the test case generation process are updated according to the deviation between the action response signal obtained from the test and the expected value.

2. The method according to claim 1, characterized in that, The adaptive configuration of the hardware interface of the test system includes: Send probe commands to the hardware interface of the test system. The probe commands include pin type detection, signal path detection, and communication protocol detection. Based on the results of the pin type detection, the interface pin type of the protection device under test is identified; Based on the results of the signal number detection, the number of analog input channels of the protection device under test is determined; Based on the detection results of the communication protocol, the communication protocol of the protection device under test is matched; Adjust the number of analog output channels, range configuration, and terminal mapping relationship of the test system according to the interface pin type; Load the parameters corresponding to the communication protocol to complete the adaptive configuration of the hardware interface.

3. The method according to claim 2, characterized in that, The test system is equipped with a status acquisition unit; the feature vector is constructed based on the interface features, parameter features, and action logic features extracted from the protection device under test, including: The status acquisition unit acquires interface characteristic data, parameter characteristic data, and action logic characteristic data from the protection device under test. The interface characteristic data includes the number of analog input / output channels and the communication protocol type. The parameter characteristic data includes current setting or impedance setting. The action logic characteristic data includes distance protection or differential protection type. The interface feature data, the parameter feature data, and the action logic feature data are combined into the feature vector.

4. The method according to claim 3, characterized in that, The protection device types include line protection, transformer protection, busbar protection, capacitor protection, and generator protection. The cross-type feature library is configured with interface feature data, parameter feature data, and action logic feature data. The step of performing similarity matching between the feature vectors and reference feature vectors in the pre-stored cross-type feature library, and determining the protection device type based on the similarity matching result, includes: The similarity value between the feature vector and the reference feature vector is calculated by a weighted feature matching algorithm, and the similarity value is compared with a preset threshold. If the similarity value is not less than the preset threshold, then the type of the protection device is determined to be the type corresponding to the reference feature vector; If the similarity value is less than the preset threshold, then the manual assisted recognition process is initiated and the feature data in the cross-type feature library is updated.

5. The method according to claim 4, characterized in that, The step of generating test cases based on the type of protection device and the current operating status of the protection device under test includes: Collect the current operating status data of the protection device under test, including operating current and life loss rate; Based on the type of protection device and the current operating status data, calculate the priority score of the test cases; Based on the priority score, the target test case with the highest priority is selected from the pre-set test case configuration as the test case; If the current operating status data indicates that the protection device under test is in an aging state, then the abnormal high-risk test cases are removed from the test case configuration.

6. The method according to claim 5, characterized in that, The testing system is also equipped with a test signal generation module; the test cases include distance protection testing, overcurrent protection testing, differential protection testing, and gas protection testing; executing the test cases on the protection device under test includes: The test signal generation module is controlled to output a fault simulation signal to the protection device under test; The status acquisition unit collects the action response signal of the protection device under test in real time. Record the action time and action value of the action response signal.

7. The method according to claim 6, characterized in that, The rule coefficients of the parameter mapping algorithm include linear combination coefficients in fuzzy rules, and the association matrix used in the test case generation process includes device type dimension, device state dimension and test case type dimension; The step of updating the parameter mapping algorithm and the test case generation process based on the deviation between the action response signal obtained from the test and the expected value includes: Calculate the deviation between the action response signal and the expected value, and compare the deviation with a preset tolerance; If the deviation exceeds the preset tolerance, the linear combination coefficients are adjusted and the correlation matrix is ​​updated. Test data is stored in a data layer, which is configured on local storage devices and cloud storage platforms.

8. A cross-type testing system for power protection devices, characterized in that, include: The interface adaptive configuration module is used to perform adaptive configuration on the hardware interfaces of the test system; The feature vector construction module is used to construct feature vectors based on the interface features, parameter features, and action logic features extracted from the protection device under test. The protection device type identification module is used to perform similarity matching between the feature vector and the reference feature vector in the pre-stored cross-type feature library, and determine the protection device type based on the similarity matching result; The test system interface adaptation module is used to adapt the interface parameters, signal parameters, and criterion parameters of the test system based on the type of the protection device using a parameter mapping algorithm. The test case generation module is used to generate test cases based on the type of protection device and the current operating status of the protection device under test. The test case execution module is used to execute the test cases on the protection device under test, and update the parameter mapping algorithm and the test case generation process according to the deviation between the action response signal obtained from the test and the expected value.

9. The cross-type testing system for power protection devices according to claim 8, characterized in that, The test system is equipped with a status acquisition unit; the feature vector construction module is also used to acquire interface feature data, parameter feature data and action logic feature data from the protection device under test through the status acquisition unit. The interface feature data includes the number of analog input / output channels and the communication protocol type. The parameter feature data includes current setting or impedance setting. The action logic feature data includes distance protection or differential protection type. The interface feature data, the parameter feature data and the action logic feature data are combined into the feature vector.

10. The cross-type testing system for power protection devices according to claim 9, characterized in that, The protection device types include line protection, transformer protection, busbar protection, capacitor protection, and generator protection. The cross-type feature library is configured with interface feature data, parameter feature data, and action logic feature data. The protection device type identification module is further used to calculate the similarity value between the feature vector and the reference feature vector using a weighted feature matching algorithm, and compare the similarity value with a preset threshold. If the similarity value is not less than the preset threshold, the protection device type is determined to be the type corresponding to the reference feature vector. If the similarity value is less than the preset threshold, a manual assisted identification process is initiated and the feature data in the cross-type feature library is updated.

Images