A method, device, equipment and medium for intelligent fault detection

Abstract

The present disclosure relates to the field of fault detection technology, and provides a fault intelligent detection method, device, equipment and medium, the method comprising: respectively obtaining a positive data set, a negative data set and an observation data set of a weak current device; aligning and arranging the data sets in order to obtain a data matrix; calculating the data difference value of each column in the data matrix, and taking the column with the largest data difference value as the benchmark feature column; arranging the other remaining columns in descending order according to the correlation coefficient, and filling them to both sides of the benchmark feature column in sequence, thereby constructing a feature significance matrix; using a first sliding window and a second sliding window to scan the data set of the feature significance matrix and calculate the window difference; after completing the whole row scan, accumulating the difference according to the weight, and triggering a fault warning when the accumulated difference exceeds a threshold value. By adopting the above scheme, for weak current devices that are sensitive to signal changes, the fault type of the weak current device can be detected in real time and accurately.

Description

Technical Field

[0001] The present disclosure relates to the technical field of fault detection, and in particular to a method, apparatus, device and medium for intelligent fault detection. Background Art

[0002] The weak current equipment in steel mills operates at low voltages and has small signal amplitudes, making it difficult for traditional detection methods to effectively capture weak fault signatures. Furthermore, weak current equipment is susceptible to electromagnetic interference, environmental noise, and other factors, resulting in a low signal-to-noise ratio. These characteristics make fault detection in weak current equipment even more difficult.

[0003] Existing technologies have a high false alarm rate in weak current equipment fault detection and are unable to effectively identify tiny signal changes, making it easy to miss or misreport faults. Simple statistical analysis methods struggle to capture fault characteristics, resulting in insufficient real-time and accuracy in fault detection. In addition, traditional fault detection methods often lack the ability to comprehensively analyze multiple fault types, making it difficult to accurately classify and locate fault types.

[0004] Therefore, there is an urgent need to develop an intelligent detection method for weak current equipment faults to solve the problems of low detection sensitivity, high false alarm rate, and fuzzy fault classification in the existing technology, and to achieve accurate capture of minor fault characteristics and real-time identification of fault types. Summary of the Invention

[0005] The present disclosure provides a method, apparatus, device and medium for intelligent fault detection, which are used to realize real-time and accurate detection of fault types of weak current equipment.

[0006] In a first aspect, the present disclosure provides a method for intelligent fault detection, comprising:

[0007] Obtain N positive data sets and N negative data sets of weak current equipment respectively; obtain the latest observation data set of weak current equipment; each data set includes M data, where M is an odd number;

[0008] Align the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix;

[0009] Calculate the data difference value of each column in the data matrix, take the column with the largest data difference value as the benchmark feature column, and move the benchmark feature column to the middle column position of the data matrix; calculate the correlation coefficient between the remaining columns and the benchmark feature column, arrange the remaining columns in descending order of the correlation coefficient, and fill them in on both sides of the benchmark feature column in sequence, thereby constructing a feature significance matrix;

[0010] A first sliding window is used to scan the observed data set in the N+1th row of the feature significance matrix; a second sliding window is used to synchronously scan the positive data set in the Kth row of the feature significance matrix, where the Kth row is the middle row of the positive data set; the two sliding windows are synchronously moved, the difference between the two sliding windows is calculated in real time, and a first weight is set according to the real-time distance between the center position of the sliding window and the reference feature column; after completing the entire row scan, the difference is accumulated according to the first weight, and when the accumulated difference exceeds a threshold, a fault warning is triggered.

[0011] According to the intelligent fault detection method provided by the present disclosure, obtaining N positive data sets and N negative data sets of weak current equipment respectively includes:

[0012] The N positive data sets are data of weak current equipment in normal operation;

[0013] N negative data sets are data of weak current equipment in N typical fault critical states; N negative data sets respectively represent N typical faults, and the N typical faults include at least one of short circuit, open circuit, poor contact, signal attenuation, electromagnetic interference, component aging and environmental interference;

[0014] The data set is row data, and one data set is a row of data including M data.

[0015] According to the intelligent fault detection method provided by the present disclosure, triggering a fault warning also includes:

[0016] N third sliding windows are used to synchronously scan the negative data set from the N+1th row to the 2N+1th row of the feature significance matrix, and each window is responsible for scanning data of a typical fault mode;

[0017] Synchronously moving the first sliding window and the N third sliding windows, calculating in real time the feature similarities between the first sliding window and the N third sliding windows respectively; and setting a second weight according to the real-time distance between the center position of the sliding window and the reference feature column;

[0018] After completing the entire row scan, the similarity of each row is accumulated according to the second weight, the row with the largest accumulated similarity is selected, and the fault type is determined according to the negative data set corresponding to the row with the largest similarity.

[0019] According to the intelligent fault detection method provided by the present disclosure, the data difference value of each column in the data matrix is calculated, and the column with the largest data difference value is used as the reference feature column, including:

[0020] Performing wavelet transform on each column of the data matrix to extract wavelet coefficients of each column of data;

[0021] Calculate the energy distribution of the wavelet coefficients of each column of data;

[0022] Calculate the entropy value of the energy distribution of each column of data;

[0023] The column with the largest entropy value is determined as the benchmark feature column.

[0024] According to the intelligent fault detection method provided by the present disclosure, calculating the correlation coefficient between the remaining columns and the reference feature column includes:

[0025] Obtaining the time domain correlation coefficient X between the remaining columns and the benchmark feature column;

[0026] Obtaining the frequency domain correlation coefficient Y between the remaining columns and the reference feature column;

[0027] Obtaining waveform correlation coefficients Z between the remaining columns and the reference feature column;

[0028] Perform weighted calculation on X, Y, and Z to obtain the correlation coefficient.

[0029] According to the intelligent fault detection method provided by the present disclosure, the remaining columns are arranged in descending order according to the correlation coefficients and sequentially filled on both sides of the reference feature column, including:

[0030] Sort the remaining columns by their correlation coefficients with the benchmark feature column from large to small;

[0031] Moving the reference feature column to the middle column position of the data matrix;

[0032] Adopting the left-right alternating filling rule, the first remaining column after sorting is filled to the position immediately to the left of the benchmark feature column, the second remaining column is filled to the position immediately to the right of the benchmark feature column, and the subsequent remaining columns are filled to the left vacancies according to the parity of the serial numbers, with odd numbers filling the vacancies on the left and even numbers filling the vacancies on the right, thereby constructing a feature significance matrix with the benchmark feature column as the center and the correlation of columns gradually weakening on both sides.

[0033] According to the intelligent fault detection method provided by the present disclosure, synchronously moving two sliding windows and calculating the difference between the two sliding windows in real time include:

[0034] The two sliding windows are moved synchronously to keep the starting positions of the two windows aligned synchronously on their respective rows; the size of the sliding windows is optimized according to the signal characteristics of the weak current equipment and the fault detection requirements.

[0035] In a second aspect, the present disclosure further provides an intelligent fault detection device, comprising:

[0036] The data acquisition module obtains N positive data sets and N negative data sets of the weak current equipment respectively; obtains the latest observation data set of the weak current equipment; each data set includes M data, where M is an odd number;

[0037] A data matrix module aligns the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix;

[0038] A feature significance matrix is constructed by calculating the data difference value of each column in the data matrix, taking the column with the largest data difference value as the benchmark feature column, and moving the benchmark feature column to the middle column position of the data matrix; calculating the correlation coefficient between the remaining columns and the benchmark feature column, arranging the remaining columns in descending order of the correlation coefficient, and sequentially filling them on both sides of the benchmark feature column, thereby constructing a feature significance matrix;

[0039] The early warning module uses a first sliding window to scan the observation data set in the N+1th row of the feature significance matrix; uses a second sliding window to synchronously scan the positive data set in the Kth row of the feature significance matrix, and the Kth row is the middle row of the positive data set; the two sliding windows are synchronously moved, the difference between the two sliding windows is calculated in real time, and a first weight is set according to the real-time distance between the center position of the sliding window and the reference feature column; after completing the entire row scan, the difference is accumulated according to the first weight, and when the accumulated difference exceeds a threshold, a fault early warning is triggered.

[0040] Compared with the prior art, the present disclosure relates to a fault intelligent detection method, which includes: obtaining a positive data set, a negative data set and an observation data set of a weak current device respectively; aligning the data sets in order to obtain a data matrix; calculating the data difference value of each column in the data matrix, and taking the column with the largest data difference value as the benchmark feature column; arranging the other remaining columns in descending order according to the correlation coefficient, and filling them to both sides of the benchmark feature column in sequence, thereby constructing a feature significance matrix; using a first sliding window and a second sliding window to scan the data set of the feature significance matrix and calculate the difference; after completing the entire row scan, accumulating the difference according to the weight, and triggering a fault warning when the accumulated difference exceeds a threshold. By adopting the above scheme, for weak current devices that are sensitive to signal changes, the sensitivity and accuracy of weak current device fault detection can be significantly improved, weak fault signals can be effectively captured, the false alarm rate can be reduced, and early warning and precise positioning of faults can be achieved, providing effective protection for the stable operation of weak current devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present disclosure, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0042] Figure 1A flow chart of a fault intelligent detection method provided by the present disclosure;

[0043] Figure 2 The feature significance matrix provided by the present disclosure constructs a diagram;

[0044] Figure 3 A schematic diagram of an intelligent fault detection device provided by the present disclosure;

[0045] Figure 4 A schematic diagram of the electronic device provided in the present disclosure. DETAILED DESCRIPTION

[0046] To make the objectives, technical solutions, and advantages of this disclosure more clear, the technical solutions of this disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this disclosure, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of this disclosure without creative effort shall fall within the scope of protection of this disclosure.

[0047] In modern steel mills, weak current equipment is a critical component of the production process, including but not limited to automated control systems, sensor networks, communications equipment, monitoring systems, and various intelligent instruments. These devices typically operate in low-voltage, low-current environments and are susceptible to interference from strong electromagnetic sources such as arc furnaces, inverters, and motor clusters within the steel mill. Their proper operation is crucial to the mill's production efficiency and safety.

[0048] Figure 1 This is a flow chart of a fault intelligent detection method provided by the present disclosure. Figure 1 As shown, the method includes:

[0049] Step 1: Obtain N positive data sets and N negative data sets of weak current equipment respectively; obtain the latest observation data set of weak current equipment; each data set includes M data, where M is an odd number;

[0050] Furthermore, N positive data sets D i,j + It contains N rows of data, where i is the row number, representing an integer from 1 to N, and j is the column number, representing an integer from 1 to M.

[0051] Specifically, the first row of positive data sets includes M data, marked as D 1,M + ={D 1,1 + ,D 1,2 + ,…,D 1,M +}, which represents historical data of weak current equipment during normal operation. Each row of data corresponds to one normal operation cycle. For example, M parameters (ripple factor, voltage fluctuation, temperature, etc.) of the power module of a PLC controller in a steel plant during normal operation.

[0052] Similarly, N negative data sets D i,j - It contains N rows of data, where i is the row number, representing an integer from 1 to N, and j is the column number, representing an integer from 1 to M.

[0053] Specifically, the first row of negative data sets includes M data, marked as D 1,M - ={D 1,1 - ,D 1,2 - ,…,D 1,M -}, which is the data of the weak current equipment in the critical state of typical fault, reflecting the typical characteristics of typical faults.

[0054] Furthermore, the data format of the latest observation data set of weak current equipment is D j ={D1,D2,…,D M}, which is the real-time data of the current operation cycle of the weak current equipment. It has the same number of columns M as the positive and negative data sets and is acquired in real time through a high-speed acquisition module (sampling rate ≥ 10kHz) to ensure data timeliness.

[0055] Step 2: Align the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix;

[0056] Furthermore, the above-arranged positive data set, observation data set, and negative data set are merged in order to form a data matrix of size (2N+1)×M;

[0057] The first N rows correspond to the positive data set {D i,j +}, representing the normal operating status of weak current equipment; the N+1th row corresponds to the observation data set D j , is the current real-time operation data of the device; the next N rows correspond to the negative data set {D i,j −}, record typical fault critical state data;

[0058] The data matrix form of (2N+1)×M is:

[0059]

[0060] Step 3: Calculate the data difference value of each column in the data matrix, take the column with the largest data difference value as the benchmark feature column, and move the benchmark feature column to the middle column position of the data matrix; calculate the correlation coefficient between the remaining columns and the benchmark feature column, arrange the remaining columns in descending order of the correlation coefficient, and fill them in on both sides of the benchmark feature column in turn, thereby constructing a feature significance matrix;

[0061] Furthermore, for each column in the data matrix, the data difference value of the column is calculated, and the data difference value reflects the degree of change of the data in the column between different rows;

[0062] After calculating the data difference value of each column, the column with the largest difference value is selected as the baseline feature column. The baseline feature column reflects the most significant changes in the data matrix and is most relevant to the changes in the operating status of the weak current equipment.

[0063] The benchmark feature column is moved to the middle column position of the data matrix, that is, the (M+1) / 2th column. This process ensures the core position of the benchmark feature column in subsequent analysis, facilitating subsequent feature analysis and fault detection.

[0064] Step 4: Use the first sliding window to scan the observed data set in the N+1th row of the feature significance matrix; use the second sliding window to synchronously scan the positive data set in the Kth row of the feature significance matrix, and the Kth row is the middle row of the positive data set; move the two sliding windows synchronously, calculate the difference between the two sliding windows in real time, and set the first weight according to the real-time distance between the center position of the sliding window and the reference feature column; after completing the entire row scan, accumulate the difference according to the first weight, and when the accumulated difference exceeds the threshold, trigger a fault warning.

[0065] Furthermore, the positive dataset contains N rows of data, representing various operating conditions of weak current equipment under normal operation. Row K, the middle row of the positive dataset, represents the typical normal data characteristics and serves as a benchmark. Selecting the middle row for scanning allows us to obtain the most representative normal operating characteristic patterns based on a comprehensive consideration of the various normal state data in the positive dataset. Here, K = [(N+1) / 2], where [(N+1) / 2] is the rounding function.

[0066] Furthermore, the first weight is optimized according to the position of the sliding window in the feature significance matrix, and the sliding window farther away from the benchmark feature column is assigned a lower weight to reflect the characteristic that the importance of data decreases with increasing distance, thereby improving the reliability of fault detection.

[0067] Compared with the prior art, the fault intelligent detection method disclosed in the present invention obtains positive data sets, negative data sets and observation data sets of weak current equipment respectively; aligns the data sets in order to obtain a data matrix; calculates the data difference value of each column in the data matrix, and uses the column with the largest data difference value as the benchmark feature column; arranges the other remaining columns in descending order according to the correlation coefficient, and fills them to both sides of the benchmark feature column in turn, thereby constructing a feature significance matrix; uses a first sliding window and a second sliding window to scan the data set of the feature significance matrix and calculate the difference; after completing the entire row scan, the difference is accumulated according to the weight, and when the accumulated difference exceeds a threshold, a fault warning is triggered. By adopting the above scheme, for weak current equipment that is sensitive to signal changes, the sensitivity and accuracy of weak current equipment fault detection can be significantly improved, weak fault signals can be effectively captured, the false alarm rate can be reduced, and early warning and precise positioning of faults can be achieved, providing effective protection for the stable operation of weak current equipment.

[0068] In one embodiment, obtaining N positive data sets and N negative data sets of weak current devices in step S1 includes:

[0069] The N positive data sets are data of weak current equipment in normal operation;

[0070] N negative data sets contain data of weak current equipment in N typical fault critical states, reflecting the operating characteristics of the equipment under different fault conditions and used for fault detection and classification. The N negative data sets represent N typical faults, including but not limited to short circuit, open circuit, poor contact, signal attenuation, electromagnetic interference, component aging, and environmental interference.

[0071] The data set is row data, and one data set is a row of data including M data.

[0072] Through the above steps, N positive data sets and N negative data sets of weak current equipment are successfully obtained. These data sets provide high-quality basic data for subsequent fault detection and classification.

[0073] In one embodiment, after the fault warning is triggered in step 4, the method further includes:

[0074] N third sliding windows are used to synchronously scan the negative data set from the N+1th row to the 2N+1th row of the feature significance matrix, and each window is responsible for scanning data of a typical fault mode;

[0075] Synchronously moving the first sliding window and the N third sliding windows, calculating in real time the feature similarities between the first sliding window and the N third sliding windows respectively; and setting a second weight according to the real-time distance between the center position of the sliding window and the reference feature column;

[0076] After scanning the entire row, the similarity of each row is accumulated based on the second weight. The row with the highest accumulated similarity is selected. The negative dataset corresponding to the row with the highest similarity is the current fault type. The fault type is then determined based on the negative dataset corresponding to the row with the highest similarity. For example, if the accumulated similarity corresponding to the third sliding window is the highest, and this window scans the negative dataset representing a "poor contact" fault, the current fault type is determined to be poor contact.

[0077] In one embodiment, calculating the data difference value of each column in the data matrix and taking the column with the largest data difference value as the reference feature column includes:

[0078] Performing wavelet transform on each column of the data matrix to extract wavelet coefficients of each column of data;

[0079] Calculate the energy distribution of the wavelet coefficients of each column of data;

[0080] Calculate the entropy value of the energy distribution of each column of data;

[0081] The column with the largest entropy value is determined as the benchmark feature column.

[0082] In one embodiment, calculating the correlation coefficients between the remaining columns and the reference feature column includes:

[0083] Obtaining the time domain correlation coefficient X between the remaining columns and the benchmark feature column;

[0084] Obtaining the frequency domain correlation coefficient Y between the remaining columns and the reference feature column;

[0085] Obtaining waveform correlation coefficients Z between the remaining columns and the reference feature column;

[0086] Perform weighted calculation on X, Y, and Z to obtain the correlation coefficient.

[0087] In one embodiment, arranging the remaining columns in descending order of correlation coefficients and sequentially filling both sides of the reference feature column includes:

[0088] Sort the remaining columns by their correlation coefficients with the benchmark feature column from large to small;

[0089] Moving the reference feature column to the middle column position of the data matrix;

[0090] Adopting the left-right alternating filling rule, the first remaining column after sorting is filled to the position immediately to the left of the benchmark feature column, the second remaining column is filled to the position immediately to the right of the benchmark feature column, and the subsequent remaining columns are filled to the left vacancies according to the parity of the serial numbers, with odd numbers filling the vacancies on the left and even numbers filling the vacancies on the right, thereby constructing a feature significance matrix with the benchmark feature column as the center and the correlation of columns gradually weakening on both sides.

[0091] Specifically, such as Figure 2 As shown, assuming M=5, N=3, the data matrix is as follows Figure 2 Shown on the left;

[0092] Calculate the difference value of the data in each column. Assume that the difference values are: column 1 = 0.5, column 2 = 0.6, column 3 = 0.7, column 4 = 0.8, column 5 = 0.9;

[0093] Select column 5 with the largest difference value as the benchmark feature column; move column 5 to the middle position, that is, column 3;

[0094] Calculate the correlation coefficients of the other columns with the benchmark feature column (column 5). Assume that the correlation coefficients are: column 1 = 0.8, column 2 = 0.9, column 3 = 0.7, column 4 = 0.6; sort them in descending order of correlation coefficient: column 2, column 1, column 3, column 4;

[0095] Construct the feature significance matrix according to the left-right alternating filling rule:

[0096] Column 2 (highest correlation) is filled to the immediate left of the baseline feature column;

[0097] Column 1 (second highest correlation) is filled to the right of the reference feature column;

[0098] Column 3 (the third most relevant) is filled to the second position to the left of the baseline feature column;

[0099] Column 4 (fourth most relevant) is filled to the second position to the right of the baseline feature column;

[0100] The final feature saliency matrix is as follows Figure 2 Shown on the right.

[0101] In one embodiment, synchronously moving the two sliding windows and calculating the difference between the two sliding windows in real time includes:

[0102] The two sliding windows are moved synchronously to keep the starting positions of the two windows aligned synchronously on their respective rows; the size of the sliding windows is optimized according to the signal characteristics of the weak current equipment and the fault detection requirements.

[0103] Specifically, the first sliding window starts from column 1, and the second sliding window also starts from column 1. At each time step, both windows move to the right by one data point simultaneously until all columns are covered.

[0104] During actual operation, the sliding window size is dynamically adjusted based on the characteristics of the real-time data. For example, when a change in the frequency component of a signal is detected, the sliding window size is automatically adjusted to adapt to the new signal characteristics.

[0105] An intelligent fault detection device provided by the present disclosure is described below. The detection system described below and the detection method described above can be referenced to each other.

[0106] like Figure 3 As shown, an intelligent fault detection device includes:

[0107] The data acquisition module obtains N positive data sets and N negative data sets of the weak current equipment respectively; obtains the latest observation data set of the weak current equipment; each data set includes M data, where M is an odd number;

[0108] A data matrix module aligns the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix;

[0109] A feature significance matrix is constructed by calculating the data difference value of each column in the data matrix, taking the column with the largest data difference value as the benchmark feature column, and moving the benchmark feature column to the middle column position of the data matrix; calculating the correlation coefficient between the remaining columns and the benchmark feature column, arranging the remaining columns in descending order of the correlation coefficient, and sequentially filling them on both sides of the benchmark feature column, thereby constructing a feature significance matrix;

[0110] The early warning module uses a first sliding window to scan the observation data set in the N+1th row of the feature significance matrix; uses a second sliding window to synchronously scan the positive data set in the Kth row of the feature significance matrix, and the Kth row is the middle row of the positive data set; the two sliding windows are synchronously moved, the difference between the two sliding windows is calculated in real time, and a first weight is set according to the real-time distance between the center position of the sliding window and the reference feature column; after completing the entire row scan, the difference is accumulated according to the first weight, and when the accumulated difference exceeds a threshold, a fault early warning is triggered.

[0111] An electronic device provided in an embodiment of the present application is Figure 4 As shown, the electronic device includes a processor 401 and a memory 403, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method provided in the above embodiment are implemented.

[0112] See also Figure 4 The electronic device further includes: a bus 404 and a communication interface 402, a processor 401, a communication interface 402 and a memory 403 connected via the bus 404; the processor 401 is used to execute executable modules stored in the memory 403, such as computer programs.

[0113] Memory 403 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive. Communication between the system network element and at least one other network element is achieved via at least one communication interface 402 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0114] The bus 404 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0115] Among them, the memory 403 is used to store programs, and the processor 401 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 401 or implemented by the processor 401.

[0116] The processor 401 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 401 or by instructions in the form of software. The above-mentioned processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 403, and processor 401 reads the information in memory 403 and performs the steps of the above method in conjunction with its hardware.

[0117] Corresponding to the above-mentioned intelligent fault detection method, an embodiment of the present application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer-readable storage medium stores computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned intelligent fault detection method.

[0118] The intelligent fault detection device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application, its implementation principle and the technical effect produced are the same as those in the aforementioned method embodiment. For the sake of brief description, where the device embodiment is not mentioned, reference can be made to the corresponding content in the aforementioned method embodiment. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0119] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0120] For another example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0122] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0123] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the intelligent fault detection method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0124] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0125] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. However, these modifications, changes, or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A fault intelligent detection method, characterized in that: The following steps are involved: Obtain N positive data sets and N negative data sets of weak current equipment respectively; obtain the latest observation data set of weak current equipment; each data set includes M data, where M is an odd number; Align the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix; Calculate the data difference value of each column in the data matrix, take the column with the largest data difference value as the benchmark feature column, and move the benchmark feature column to the middle column position of the data matrix; calculate the correlation coefficient between the remaining columns and the benchmark feature column, arrange the remaining columns in descending order of the correlation coefficient, and fill them in on both sides of the benchmark feature column in sequence, thereby constructing a feature significance matrix; A first sliding window is used to scan the observed data set in the N+1th row of the feature significance matrix; a second sliding window is used to synchronously scan the positive data set in the Kth row of the feature significance matrix, where the Kth row is the middle row of the positive data set; the two sliding windows are synchronously moved, the difference between the two sliding windows is calculated in real time, and a first weight is set according to the real-time distance between the center position of the sliding window and the reference feature column; After completing the entire row scan, the difference is accumulated according to the first weight, and when the accumulated difference exceeds a threshold, a fault warning is triggered.

2. The intelligent fault detection method according to claim 1, characterized in that: The step of respectively obtaining N positive data sets and N negative data sets of weak current equipment includes: The N positive data sets are data of weak current equipment in normal operating state; N negative data sets are data of weak current equipment in N typical fault critical states; N negative data sets respectively represent N typical faults, and the N typical faults include at least one of short circuit, open circuit, poor contact, signal attenuation, electromagnetic interference, component aging and environmental interference; The data set is row data, and one data set is a row of data including M data.

3. The intelligent fault detection method according to claim 2, characterized in that: The triggering of the fault warning further includes: N third sliding windows are used to synchronously scan the negative data set from the N+1th row to the 2N+1th row of the feature significance matrix, and each window is responsible for scanning data of a typical fault mode; Synchronously moving the first sliding window and the N third sliding windows, calculating in real time the feature similarities between the first sliding window and the N third sliding windows respectively; and setting a second weight according to the real-time distance between the center position of the sliding window and the reference feature column; After completing the entire row scan, the similarity of each row is accumulated according to the second weight, the row with the largest accumulated similarity is selected, and the fault type is determined according to the negative data set corresponding to the row with the largest similarity.

4. The intelligent fault detection method according to claim 1, characterized in that: Calculating the data difference value of each column in the data matrix and taking the column with the largest data difference value as the reference feature column includes: Performing wavelet transform on each column of the data matrix to extract wavelet coefficients of each column of data; Calculate the energy distribution of the wavelet coefficients of each column of data; Calculate the entropy value of the energy distribution of each column of data; The column with the largest entropy value is determined as the benchmark feature column.

5. The intelligent fault detection method according to claim 1, characterized in that: Calculating the correlation coefficients between the remaining columns and the benchmark feature column includes: Obtaining the time domain correlation coefficient X between the remaining columns and the benchmark feature column; Obtaining the frequency domain correlation coefficient Y between the remaining columns and the reference feature column; Obtaining waveform correlation coefficients Z between the remaining columns and the reference feature column; Perform weighted calculation on X, Y, and Z to obtain the correlation coefficient.

6. The intelligent fault detection method according to claim 5, characterized in that: The step of arranging the remaining columns in descending order of correlation coefficients and sequentially filling the two sides of the reference feature column includes: Sort the remaining columns by their correlation coefficients with the benchmark feature column from large to small; Moving the reference feature column to the middle column position of the data matrix; Adopting the left-right alternating filling rule, the first remaining column after sorting is filled to the position immediately to the left of the benchmark feature column, the second remaining column is filled to the position immediately to the right of the benchmark feature column, and the subsequent remaining columns are filled to the left vacancies according to the parity of the serial numbers, with odd numbers filling the vacancies on the left and even numbers filling the vacancies on the right, thereby constructing a feature significance matrix with the benchmark feature column as the center and the correlation of columns gradually weakening on both sides.

7. The intelligent fault detection method according to claim 1, characterized in that: The synchronously moving the two sliding windows and calculating the difference between the two sliding windows in real time includes: The two sliding windows are moved synchronously to keep the starting positions of the two windows aligned synchronously on their respective rows; the size of the sliding windows is optimized according to the signal characteristics of the weak current equipment and the fault detection requirements.

8. An intelligent fault detection device, characterized in that: include: The data acquisition module acquires N positive data sets and N negative data sets of weak current equipment respectively; Get the latest observation data set of weak current equipment; each data set includes M data, where M is an odd number; A data matrix module aligns the N positive data sets, 1 observation data set, and N negative data sets in order to obtain a (2N+1)×M data matrix; A feature significance matrix is constructed by calculating the data difference value of each column in the data matrix, taking the column with the largest data difference value as the benchmark feature column, and moving the benchmark feature column to the middle column position of the data matrix; calculating the correlation coefficient between the remaining columns and the benchmark feature column, arranging the remaining columns in descending order of the correlation coefficient, and sequentially filling them on both sides of the benchmark feature column, thereby constructing a feature significance matrix; The early warning module uses a first sliding window to scan the observed data set in the N+1th row of the feature significance matrix; uses a second sliding window to synchronously scan the positive data set in the Kth row of the feature significance matrix, where the Kth row is the middle row of the positive data set; synchronously moves the two sliding windows, calculates the difference between the two sliding windows in real time, and sets a first weight based on the real-time distance between the center position of the sliding window and the reference feature column; After completing the entire row scan, the difference is accumulated according to the first weight, and when the accumulated difference exceeds a threshold, a fault warning is triggered.

9. An electronic device comprising: processor; A memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer-readable storage medium stores instructions or a computer program, and when the instructions or the computer program are executed on a device, the device is caused to execute the method according to any one of claims 1 to 7.

Images