Steel wire rope magnetic flux leakage detection method based on multichannel filtering and support vector machine

Abstract

The invention belongs to the technical field of steel wire rope detection, and particularly discloses a steel wire rope magnetic flux leakage detection method based on multichannel filtering and a support vector machine, which comprises the following steps: acquiring a multichannel detection signal of a target steel wire rope detected by a magnetic flux leakage detection probe and displacement data of the magnetic flux leakage detection probe detected by a displacement sensor in real time; performing filtering and noise reduction processing on the multi-channel detection signal to obtain a noise-reduced multi-channel detection signal; determining the detection speed of the magnetic flux leakage detection probe based on the displacement data; and inputting the noise-reduced multi-channel detection signal and the detection speed into the trained soft interval support vector machine model, and obtaining a damage grade detection result of the target steel wire rope at a detection position corresponding to the multi-channel detection signal. According to the invention, high-precision accurate measurement and damage grade determination of the steel wire rope damage are realized.

Description

Technical Field

[0001] This application belongs to the technical field of wire rope detection, and more specifically, relates to a magnetic flux leakage detection method for wire ropes based on multi-channel filtering and support vector machines. Background Art

[0002] As an indispensable load-bearing and transmission component in many industrial fields (such as elevators, cranes, and mine hoisting equipment), the safety and reliability of wire ropes are directly related to the stable operation of the overall system and personnel safety. During long-term use, wire ropes may suffer damages such as wear, broken wires, etc. due to factors such as abrasion, fatigue, and corrosion. If not detected and processed in a timely manner, serious safety accidents may occur.

[0003] In related technologies, a variety of digital detection technologies have been adopted to design a variety of magnetic flux leakage detection schemes for wire ropes to improve the detection accuracy. For example, CN119191008A discloses a method for fault diagnosis and fatigue prediction of elevator wire ropes, which proposes a method for fault diagnosis of elevator wire ropes using a fault diagnosis model, aiming to obtain the single elevator fault diagnosis result. However, this method lacks the preprocessing of elevator operation data, which affects the final detection accuracy. Another example is that CN116359328A discloses a magnetic flux leakage detection method and detection system for wire ropes, which realizes damage detection through a combined method of magnetic flux leakage detection and image detection. However, in this method, the damage level is determined by a threshold, and the robustness of the wire rope damage level classification method is poor.

[0004] In summary, there are still deficiencies in the magnetic flux leakage detection methods for wire ropes in related technologies, and the accuracy of the magnetic flux leakage detection results of wire ropes needs to be improved. Summary of the Invention

[0005] In view of the above-mentioned defects existing in the prior art, this application provides a magnetic flux leakage detection method for wire ropes based on multi-channel filtering and support vector machines, aiming to solve the problem of the detection accuracy of magnetic flux leakage detection of wire ropes.

[0006] In a first aspect, this application provides a magnetic flux leakage detection method for wire ropes based on multi-channel filtering and support vector machines, including: Real-time acquisition of multi-channel detection signals of the target wire rope detected by a magnetic flux leakage detection probe and displacement data of the magnetic flux leakage detection probe detected by a displacement sensor; Performing filtering and noise reduction processing on the multi-channel detection signals to obtain the multi-channel detection signals after noise reduction; determining the detection speed of the magnetic flux leakage detection probe based on the displacement data; Inputting the multi-channel detection signals after noise reduction and the detection speed into a trained soft margin support vector machine model to obtain the damage level detection result of the target wire rope at the detection positions corresponding to the multi-channel detection signals.

[0007] In a second aspect, the present application further provides a signal processing terminal, including: An acquisition module, which acquires in real time multi-channel detection signals of a target wire rope detected by a magnetic flux leakage detection probe, and displacement data of the magnetic flux leakage detection probe detected by a displacement sensor; A multi-channel filtering module, which is used to perform filtering and noise reduction processing on the multi-channel detection signals to obtain the multi-channel detection signals after noise reduction; and determine the detection speed of the magnetic flux leakage detection probe based on the displacement data; A support vector machine classification module, which is used to input the multi-channel detection signals after noise reduction and the detection speed into a trained soft margin support vector machine model to obtain a damage level detection result of the target wire rope at the detection position corresponding to the multi-channel detection signals.

[0008] In a third aspect, the present application further provides a wire rope magnetic flux leakage detection system based on multi-channel filtering and support vector machines, including a magnetic flux leakage detection probe, a displacement sensor, and a signal processing terminal; The magnetic flux leakage detection probe includes a detection shoe and a multi-channel magnetosensitive sensor. The multi-channel magnetosensitive sensors are distributed in a circular array on the detection shoe and are used to detect multi-channel detection signals of the target wire rope; The displacement sensor is arranged on the side of the magnetic flux leakage detection probe and is used to detect the displacement data of the magnetic flux leakage detection probe in real time; The signal processing terminal is used to execute the method described in the first aspect or any one of the possible implementation manners of the first aspect.

[0009] In a fourth aspect, the present application further provides a signal processing terminal, including: at least one memory for storing a program; at least one processor for executing the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any one of the possible implementation manners of the first aspect.

[0010] In a fifth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program runs on a processor, the processor is caused to execute the method described in the first aspect or any one of the possible implementation manners of the first aspect.

[0011] In a sixth aspect, the present application further provides a computer program product. When the computer program product runs on a processor, the processor is caused to execute the method described in the first aspect or any one of the possible implementation manners of the first aspect.

[0012] Generally speaking, compared with the prior art, the above technical solutions conceived by the present application have the following beneficial effects: The magnetic flux leakage detection method for steel wire ropes based on multi-channel filtering and support vector machines provided by this application filters and reduces noise for the multi-channel detection signals of the target steel wire rope detected by the magnetic flux leakage detection probe, calculates the detection speed using the displacement data detected by the displacement sensor, and inputs the denoised multi-channel detection signals and the detection speed into the trained soft margin support vector machine model, thereby obtaining the damage level detection results corresponding to the detection positions of the multi-channel detection signals output by the soft margin support vector machine model, realizing the collaborative work of the magnetic flux leakage detection probe, displacement sensor and signal processing terminal, and achieving high-precision and accurate measurement of steel wire rope damage and determination of damage levels. Description of the Drawings

[0013] In order to more clearly illustrate the technical solutions in this application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0014] Figure 1 It is a schematic structural diagram of a magnetic flux leakage detection system for steel wire ropes based on multi-channel filtering and support vector machines provided by an embodiment of this application; Figure 2 It is a schematic structural diagram of the magnetic flux leakage detection probe provided by an embodiment of this application; Figure 3 It is one of the schematic structural diagrams of the signal processing terminal provided by an embodiment of this application; Figure 4 It is a schematic flow diagram of a magnetic flux leakage detection method for steel wire ropes based on multi-channel filtering and support vector machines provided by an embodiment of this application; Figure 5 It is another schematic structural diagram of the signal processing terminal provided by an embodiment of this application; In all the drawings, the same reference numerals are used to represent the same elements or structures, where: 1 - Magnetic flux leakage detection probe, 2 - Displacement sensor, 3 - Data line, 4 - Detection shoe, 5 - Multi-channel magnetic sensor, 6 - Signal processing terminal, 7 - Multi-channel filtering module, 8 - Support vector machine classification module. Detailed Embodiments

[0015] In order to make the purpose, technical solutions and advantages of this application clearer, the following further details this application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0016] Figure 1It is a schematic structural diagram of the magnetic flux leakage detection system for wire ropes based on multi-channel filtering and support vector machines provided by an embodiment of the present application. As Figure 1 shown, the system at least includes: a magnetic flux leakage detection probe 1, a displacement sensor 2, and a signal processing terminal ( Figure 1 not shown in the figure).

[0017] Through the coordinated work of the magnetic flux leakage detection probe 1, the displacement sensor 2, and the signal processing terminal, the system realizes the comprehensive detection of wire ropes under various working conditions, and has the characteristics of compact structure, high detection accuracy, and strong real-time performance. It is applicable to the magnetic flux leakage detection of wire ropes in industrial equipment and can effectively improve the safety and operation efficiency of the equipment.

[0018] Specifically, the magnetic flux leakage detection probe 1 is used to detect the magnetic flux leakage detection signal of the target wire rope. The displacement sensor 2 is installed on the side of the magnetic flux leakage detection probe 1 and is used to obtain the displacement data detected by the magnetic flux leakage detection probe 1 in real time. This displacement data provides dynamic information of the target wire rope at different detection positions for the system, ensuring the precise correspondence between the magnetic flux leakage detection signal and the spatial position.

[0019] Optionally, the magnetic flux leakage detection probe 1 is electrically connected to the signal processing terminal through a data line 3. Referring to Figure 1 , the data line 3 is installed at the tail of the magnetic flux leakage detection probe 1 to transmit the magnetic flux leakage detection signal detected by the magnetic flux leakage detection probe 1 and the displacement data detected by the displacement sensor 2 to the signal processing terminal in real time. The data transmission process maintains high efficiency and low latency, ensuring the integrity of the magnetic flux leakage detection signal.

[0020] Figure 2 It is a schematic structural diagram of the magnetic flux leakage detection probe provided by an embodiment of the present application. As Figure 2 shown, the magnetic flux leakage detection probe 1 includes a detection shoe 4 and a multi-channel magnetic sensor 5. The multi-channel magnetic sensor 5 is distributed in a circular array on the detection shoe 4. During the movement of the detection shoe 4 along the axis direction of the target wire rope, the multi-channel magnetic sensor 5 detects the spatial magnetic flux leakage field signal of the target wire rope, obtains multi-channel detection signals, and realizes high-precision and high-coverage signal acquisition. When there is damage to the target wire rope, the magnetic flux leakage field signal detected by the magnetic sensor closer to the damage position is significantly different from the normal signal, which is an important basis for the determination of wire rope damage and damage level.

[0021] Optionally, during the detection process, different types and specifications of magnetic flux leakage detection probes 1 and displacement sensors 2 can be selected for adaptive installation according to the actual needs of different application scenarios (such as the detection of wire ropes of indoor small equipment, the detection of wire ropes of outdoor large lifting equipment, etc.) to optimize the overall performance of the system. At the same time, for the selection of the data line 3, factors such as its transmission rate and anti-interference ability can be considered to ensure the high efficiency and stability of data transmission.

[0022] Optionally, to improve the reliability of the data, the multi-channel magnetic sensor 5 and the displacement sensor 2 can be periodically calibrated to ensure that the measurement accuracy of the sensors is always in the best state. In addition, according to the complexity of the detection site (such as the surrounding electromagnetic environment, the running state of the wire rope, etc.), the number and array mode of the multi-channel magnetic sensors 5 can be dynamically adjusted to ensure that the collected data can comprehensively reflect the state of the wire rope and effectively reduce unnecessary data redundancy.

[0023] Figure 3 is one of the structural schematic diagrams of the signal processing terminal provided by the embodiments of the present application. As Figure 3 shown, the signal processing terminal 6 is the core component for realizing the magnetic flux leakage detection of the wire rope, and is used to process the multi-channel detection signals detected by the magnetic flux leakage detection probe 1 and the displacement data detected by the displacement sensor 2 to realize the determination of the damage and damage level of the target wire rope. The signal processing terminal 6 at least includes a multi-channel filtering module 7 and a support vector machine classification module 8. The multi-channel filtering module 7 is used to eliminate noise and improve the signal quality; the support vector machine classification module 8 outputs the damage level detection result according to the processed signal to ensure the accuracy and reliability of the detection result. By integrating the multi-channel filtering module 7 and the support vector machine classification module 8 into the signal processing terminal 6, the system does not need to design a dedicated data processing device separately, reducing the design and implementation costs and realizing the portability and lightweight of the overall detection system.

[0024] Optionally, before the system is officially started for the magnetic flux leakage detection of the wire rope, the displacement sensor 2 has been pre-installed on the side of the magnetic flux leakage detection probe 1, and the connection between the two is stable and the position relationship is accurate; at the same time, the data line 3 is used to ensure the reliable connection between the magnetic flux leakage detection probe 1 and the signal processing terminal 6 to ensure the smoothness of the data transmission channel.

[0025] Optionally, before the system is officially started for the magnetic flux leakage detection of the wire rope, the system is pre-configured and debugged, and according to factors such as the material, specification, and detection environment of the target wire rope, fine parameter settings are made for the multi-channel filtering module 7 and the support vector machine classification module 8 in the signal processing terminal 6.

[0026] For example, according to the magnetic characteristics differences of wire ropes made of different materials, the filtering parameters of the multi-channel filtering module 7 are adjusted; according to the expected damage type and severity distribution, the classification parameters of the support vector machine classification module 8 are optimized. After the parameter settings are completed, a comprehensive system debugging is carried out to check whether the communication between modules is stable and whether the data interaction is accurate to ensure that the entire system can operate stably and accurately during real-time detection.

[0027] Optionally, the multi-channel filtering module 7 and the support vector machine classification module 8 are preliminarily tested and parameter-fine-tuned using simulated data. The simulated data can be generated according to various situations that may be encountered in actual detection, such as different degrees of noise interference, simulation of various types of damage, etc., so as to optimize the system parameters in advance and improve the adaptability and accuracy of the system.

[0028] Optionally, the filtering algorithm of the multi-channel filtering module 7 can be flexibly selected and optimized according to the noise characteristics encountered in actual detection. For example, the filtered signal can be monitored and analyzed in real time, and the filtering parameters can be adjusted according to signal quality indicators (such as signal-to-noise ratio, etc.) to achieve the best filtering effect.

[0029] Optionally, the model in the support vector machine classification module 8 can be updated and optimized regularly according to the actual detection situation. For example, when a new damage mode is detected or the wire rope material changes, relevant sample data is collected in a timely manner, and the model is retrained to continuously improve the classification ability and accuracy of the model for different damage situations.

[0030] The data processing process of the signal processing terminal 6 is introduced in detail below.

[0031] Figure 4 is a schematic flowchart of the wire rope magnetic flux leakage detection method based on multi-channel filtering and support vector machine provided by the embodiment of the present application. As Figure 4 shown, the execution subject of this method is the signal processing terminal 6, and this method at least includes the following steps (Step): S401. Real-time obtain the multi-channel detection signals of the target wire rope detected by the magnetic flux leakage detection probe 1, and the displacement data of the magnetic flux leakage detection probe 1 detected by the displacement sensor 2; S402. Perform filtering and noise reduction processing on the multi-channel detection signals to obtain the multi-channel detection signals after noise reduction; determine the detection speed of the magnetic flux leakage detection probe 1 based on the displacement data; S403. Input the multi-channel detection signals after noise reduction and the detection speed into the trained soft margin support vector machine model to obtain the damage level detection results of the target wire rope at the detection positions corresponding to the multi-channel detection signals.

[0032] In the embodiment of the present application, the multi-channel detection signals of the target wire rope detected by the magnetic flux leakage detection probe 1 are subjected to filtering and noise reduction processing, and the detection speed is calculated using the displacement data detected by the displacement sensor 2. The multi-channel detection signals after noise reduction and the detection speed are jointly input into the trained soft margin support vector machine model, so as to obtain the damage level detection results of the multi-channel detection signals corresponding to the detection positions output by the soft margin support vector machine model, realizing the collaborative work of the magnetic flux leakage detection probe, the displacement sensor and the signal processing terminal, and realizing the high-precision and accurate measurement of wire rope damage and the determination of damage levels.

[0033] For S401, the signal processing terminal 6 includes an acquisition module, which is configured to acquire in real time the multi-channel detection signals of the target wire rope detected by the magnetic flux leakage detection probe 1, and the displacement data of the magnetic flux leakage detection probe 1 detected by the displacement sensor 2.

[0034] Specifically, the operator operates the magnetic flux leakage detection probe 1 to scan along the target wire rope at a stable and appropriate speed. During the scanning process, the multi-channel magnetic sensors 5 distributed in an annular array on the detection shoe 4 acquire the multi-channel detection signals of the target wire rope in real time. At the same time, the displacement sensor 2 synchronously and accurately records the displacement data of the magnetic flux leakage detection probe 1. These data are transmitted to the signal processing terminal 6 in real time and stably through the data line 3, providing complete original data for subsequent analysis and processing.

[0035] For S402, the multi-channel filtering module 7 in the signal processing terminal 6 performs filtering and noise reduction processing on the multi-channel detection signals to obtain the multi-channel detection signals after noise reduction; and determines the detection speed of the magnetic flux leakage detection probe 1 based on the displacement data.

[0036] Specifically, the preprocessing of the data by the signal processing terminal 6 can be divided into two parts. One part is the preprocessing of the multi-channel detection signals detected by the magnetic flux leakage detection probe 1, specifically filtering and noise reduction processing. The other part is the preprocessing of the displacement data detected by the displacement sensor 2, specifically converting the displacement data into the detection speed. The execution order of the two parts is not limited in the embodiments of the present application.

[0037] In some embodiments, the filtering and noise reduction processing of the multi-channel detection signals in S402 specifically includes: Extracting the phase characteristics of the noise signals in different channels of the multi-channel detection signals in the time domain, and determining the phase difference between the noise signals in different channels based on the extracted phase characteristics; Performing a differential operation based on the phase difference to perform a first-stage filtering and noise reduction processing on the multi-channel detection signals.

[0038] Specifically, the differential operation subtracts two or more signals to extract the differences between the signals or eliminate the common-mode interference. In the noise cancellation of the multi-channel detection signals, the differential operation can accurately eliminate the phase difference between the noises, thereby greatly reducing the influence of the noise on the detection signals.

[0039] In order to eliminate noise by using differential operations, first, the phase characteristics of the noise signal in different channels of the multi-channel detection signal are extracted in the time domain, which can be achieved through phase measurement techniques. The multi-channel detection signals of the target wire rope detected by the multi-channel magnetic sensors 5 in the magnetic flux leakage detection probe 1 are aligned in time. Therefore, the phase characteristics of the noise signal in different channels of the multi-channel detection signal are extracted, and a direct differential operation is performed to perform the first-stage filtering and noise reduction processing on the multi-channel detection signal, specifically satisfying:

[0040] where, represents the sampling point value of the multi-channel detection signal at time t of, represents the multi-channel detection signal to be processed and the auxiliary channel signal in the phase difference in the time domain, represents the sampling point value corresponding to the auxiliary channel signal at time t after eliminating the phase difference, represents the noise reduction signal after the first-stage filtering and noise reduction processing.

[0041] Optionally, in order to further reduce the influence of noise, a filtering technique can be applied to the differential signal to remove high-frequency noise or other unwanted signal components.

[0042] In some embodiments, the filtering and noise reduction processing of the multi-channel detection signal in S102 further includes: Performing a second-stage filtering and noise reduction on the multi-channel detection signal after the first-stage filtering and noise reduction through wavelet filtering.

[0043] Specifically, wavelet filtering decomposes the signal into components of different frequencies and time scales by using wavelet transform and filters to achieve signal noise reduction. Wavelet filtering has the ability of multi-resolution analysis, can well handle non-stationary signals and abrupt signals, and is suitable for magnetic flux leakage detection of wire ropes.

[0044] The wavelet filtering process is generally completed by three steps: wavelet transform, non-linear processing of wavelet coefficients to filter out noise, and inverse wavelet transform. In the process of performing the second-stage filtering and noise reduction on the multi-channel detection signal after the first-stage filtering and noise reduction through wavelet filtering, first, the multi-channel detection signal after the first-stage filtering and noise reduction is subjected to wavelet transform to obtain wavelet coefficients of different scales; then, a threshold is selected for each decomposed scale of the wavelet coefficients for soft threshold quantization processing to achieve threshold quantization of the wavelet coefficients, so as to reduce or even completely eliminate the noise coefficients while retaining the signal coefficients to the greatest extent; finally, the processed wavelet coefficients are subjected to inverse transform for signal reconstruction.

[0045] Specifically, after eliminating the phase difference, the multi-channel detection signals after the first-stage filtering and noise reduction are subjected to a second-stage filtering and noise reduction through wavelet filtering. An appropriate wavelet basis function is selected, and after determining the appropriate threshold function and threshold rule, wavelet noise reduction is performed on the multi-channel signals to further filter out noise, specifically satisfying:

[0046] Among them, represents the noise-reduced signal after the second-stage filtering and noise reduction process. represents the wavelet coefficients after threshold processing, represents the selected mother wavelet, a represents the scale factor, and b represents the translation factor.

[0047] Through the double filtering and noise reduction process, finally, a multi-channel detection signal with a significantly improved signal-to-noise ratio is obtained, laying a foundation for the subsequent accurate damage identification of the target wire rope by the support vector machine classification module 8.

[0048] In some embodiments, determining the detection speed of the magnetic flux leakage detection probe 1 based on the displacement data in S402 specifically includes: Determining the detection speed based on the variation relationship of the displacement data over time.

[0049] Specifically, after obtaining the displacement data detected by the displacement sensor 2, a speed calculation algorithm is used to determine the detection speed of the magnetic flux leakage detection probe 1 in real time according to the variation relationship of the displacement data over time, and this detection speed will be used as important information for subsequent damage identification of the target wire rope.

[0050] When the displacement data detected by the displacement sensor 2 is obtained, the detection speed is obtained by dividing the displacement change amount in the current time period by the time change amount in the current time period, specifically satisfying:

[0051] Among them, represents the detection speed of the magnetic flux leakage detection probe 1, represents the displacement change amount, represents the time change amount.

[0052] For S403, the support vector machine classification module 8 in the signal processing terminal 6 inputs the noise-reduced multi-channel detection signal and the detection speed into the trained soft margin support vector machine model to obtain the damage level detection result of the target wire rope at the detection position corresponding to the multi-channel detection signal.

[0053] Specifically, the Soft Margin Support Vector Machine (SVM) is developed on the basis of the Hard Margin Support Vector Machine. Since data in practical applications often has noise and is not completely linearly separable, the Soft Margin SVM allows some samples not to satisfy the constraints, that is, it allows some sample points to fall on the wrong side of the hyperplane, but introduces a penalty term to control the number or degree of these samples that violate the margin.

[0054] Using the existing wire rope damage detection data (including multi-channel detection signals after double filtering and noise reduction, real-time detection speed, and damage levels) under set working conditions to create a wire rope damage data set, and training a Soft Margin Support Vector Machine model based on this data set, satisfying:

[0055] Among them, represents the normal vector of the hyperplane, represents the penalty factor, represents the slack variable of the i-th sample, and represent the coordinates of the i-th sample, represents the coordinates of the i-th sample after being mapped to a high-dimensional space through a non-linear mapping represents the bias, and n represents the number of samples.

[0056] Specifically, the first line in this expression solves for the optimal hyperplane of the Soft Margin Support Vector Machine model. Under this plane, after being corrected by the slack variable, the classification margin of different class samples is the largest, and the robustness of the classifier is the strongest. The second line in this expression is the constraint condition for the sample points, ensuring that each sample point i can be correctly classified after being corrected by the slack variable and is located outside the corresponding margin boundary under this Soft Margin Support Vector Machine model.

[0057] In the actual solution process, the variables that can be freely input in this expression are the penalty factor and the non-linear mapping . Controlling the tolerance of the model for misclassification will affect the coordinates of the samples mapped to the high-dimensional space through the kernel function method. For the same data set, each set of different input variables can obtain the relative optimal hyperplane under the current conditions by solving this expression.

[0058] ​Therefore, for the actual problem of wire rope damage level identification, after constructing the wire rope damage dataset, several relatively optimal hyperplanes are obtained through grid search in the two-dimensional independent variable space, and then the optimal hyperplane with the highest correct classification rate of the actual damage level among several relatively optimal hyperplanes is selected through actual testing as the optimal soft margin support vector machine model, and this optimal model is embedded into the system for practical application.

[0059] The soft margin support vector machine model extracts various features (such as peak values, etc.) of the multi-channel detection signals obtained after filtering and noise reduction processing by the multi-channel filtering module 7, and at the same time uses the real-time detection speed of the magnetic flux leakage detection probe 1 as an auxiliary feature to obtain the damage level detection result of the target wire rope at the detection position corresponding to the multi-channel detection signals.

[0060] It should be noted that in the embodiments of the present application, the input data of the soft margin support vector machine model includes not only the multi-channel detection signals after filtering and noise reduction processing, but also the real-time detection speed of the magnetic flux leakage detection probe 1. The detection speed has a certain influence on the signal form of the multi-channel detection signals, such as the amplitude width value, etc. Therefore, taking the detection speed as part of the feature quantities and inputting them into the soft margin support vector machine model can obtain more accurate damage detection results.

[0061] The soft margin support vector machine model accurately identifies the damage level corresponding to the detection signals by deeply analyzing and processing the input data, and clearly and intuitively displays the results on the display interface of the signal processing terminal 6, facilitating the operator to obtain the detection results in a timely manner and perform subsequent operations.

[0062] In some embodiments, the wire rope magnetic flux leakage detection method further includes: Fine-tuning and training the soft margin support vector machine model based on the damage level detection result output by the soft margin support vector machine model.

[0063] Specifically, the damage level detection result output by the soft margin support vector machine model during the actual detection process is added to the wire rope damage dataset of the soft margin support vector machine model, and the soft margin support vector machine model is fine-tuned and trained.

[0064] In some embodiments, the wire rope magnetic flux leakage detection method further includes: Generating and displaying a detection report for the target wire rope based on the damage level detection result. The detection report includes the detection position, detection time, and damage level where the target wire rope has damage.

[0065] Specifically, when the entire detection process is completed, the system automatically starts the detection report generation program. This program comprehensively summarizes all the key information in this detection process, including the detection time, detection location information, the degree of damage corresponding to each location, and the accurate damage level, etc., and generates a complete and standardized detection report for the target wire rope, providing a comprehensive and reliable data basis for subsequent detection data analysis, equipment maintenance decision-making, and other tasks.

[0066] Furthermore, evaluation indicators such as detection accuracy rate, false alarm rate, missed alarm rate, and detection time are used to evaluate the performance of the wire rope magnetic flux leakage detection system in actual detection tasks. The detection accuracy rate is calculated by precisely comparing with the actual known damage situation. The false alarm rate is the proportion of misjudged as damaged, and the missed alarm rate is the proportion of undetected actual damage. The detection time reflects the detection efficiency of the system. Through the comprehensive evaluation of these indicators, the reliability and accuracy of the system can be comprehensively understood.

[0067] Deploy the algorithms and model parameters with stable and satisfactory states of the above indicators to the actual wire rope detection equipment to achieve efficient and accurate detection tasks in various actual scenarios (such as elevators, mine hoisting equipment, port lifting equipment, etc.). In actual applications, further optimize the system parameters according to the characteristics and requirements of different scenarios to ensure the safe operation of the wire rope and effectively prevent safety accidents caused by wire rope damage.

[0068] Based on the method in the above embodiments, an embodiment of the present application provides a signal processing terminal. The signal processing terminal may include: at least one memory for storing programs and at least one processor for executing the programs stored in the memory. Wherein, when the program stored in the memory is executed, the processor is used to execute the method described in the above embodiments.

[0069] Figure 5 is the second structural schematic diagram of the signal processing terminal provided by the embodiment of the present application, as Figure 5 shown, the signal processing terminal may include: a processor (Processor) 501, a communication interface (Communications Interface) 502, a memory (Memory) 503, and a communication bus 504. Among them, the processor 501, the communication interface 502, and the memory 503 complete mutual communication through the communication bus 504. The processor 501 can call the software instructions in the memory 503 to execute the method described in the above embodiments.

[0070] In addition, when the logical instructions in the above-mentioned memory 503 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 such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of this application.

[0071] Based on the method in the above-mentioned embodiments, an embodiment of this application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program runs on a processor, it causes the processor to execute the method in the above-mentioned embodiments.

[0072] Based on the method in the above-mentioned embodiments, an embodiment of this application provides a computer program product. When the computer program product runs on a processor, it causes the processor to execute the method in the above-mentioned embodiments.

[0073] It can be understood that the processor in the embodiments of this application may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0074] The method steps in the embodiments of the present application can be implemented in a hardware manner or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory (RAM), flash memory, read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), register, hard disk, removable hard disk, CD-ROM, or any other form of storage medium well-known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0075] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0076] It can be understood that the various numerical numbers involved in the embodiments of the present application are only for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0077] It should be understood that expressions such as "including" and "may include" that can be used in this application indicate the existence of the disclosed functions, operations, or components, and do not limit one or more additional functions, operations, and components.

[0078] In the description of the embodiments of this application, it should be noted that unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a detachable connection or a non-detachable connection; it can be a direct connection or an indirect connection through an intermediate medium.

[0079] The directional terms mentioned in the embodiments of this application, such as "tail" and "side", are only with reference to the direction of the accompanying drawings. Therefore, the directional terms used are for better and clearer explanation and understanding of the embodiments of this application, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation on the embodiments of this application.

[0080] Those skilled in the art can easily understand that the above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, and improvements made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A wire rope magnetic flux leakage detection method based on multi-channel filtering and support vector machine, characterized in that: include: Acquire in real time the multi-channel detection signal of the target steel wire rope detected by the magnetic flux leakage detection probe, and the displacement data of the magnetic flux leakage detection probe detected by the displacement sensor; Performing filtering and noise reduction processing on the multi-channel detection signal to obtain a multi-channel detection signal after noise reduction; determining the detection speed of the magnetic flux leakage detection probe based on the displacement data; The denoised multi-channel detection signal and the detection speed are input into a trained soft margin support vector machine model to obtain a damage level detection result of the target steel wire rope at a detection position corresponding to the multi-channel detection signal.

2. The method for detecting magnetic flux leakage of a steel wire rope according to claim 1, characterized in that: The filtering and noise reduction process of the multi-channel detection signal comprises: Extracting phase features of noise signals in different channels in the multi-channel detection signal in the time domain, and determining phase differences of noise signals between different channels based on the extracted phase features; A differential operation is performed based on the phase difference, and a first filtering and noise reduction process is performed on the multi-channel detection signal.

3. The method for detecting magnetic flux leakage of a steel wire rope according to claim 2, characterized in that: The filtering and noise reduction processing of the multi-channel detection signal also includes: The multi-channel detection signal after the first filtering and denoising is subjected to a second filtering and denoising through wavelet filtering.

4. The method for detecting magnetic flux leakage of a steel wire rope according to claim 1, characterized in that: The soft margin support vector machine model satisfies: in, represents the normal vector of the hyperplane, represents the penalty factor, represents the slack variable of the i-th sample, and represents the coordinates of the i-th sample, Indicates that the coordinates of the i-th sample Through nonlinear mapping The coordinates after mapping to high-dimensional space, represents bias, and n represents the number of samples.

5. The method for detecting magnetic flux leakage of a steel wire rope according to claim 1, characterized in that: The step of determining the detection speed of the magnetic flux leakage detection probe based on the displacement data comprises: The detection speed is determined based on the relationship between the displacement data and time.

6. The method for detecting magnetic flux leakage of a steel wire rope according to claim 1, characterized in that: The method further comprises: The soft margin support vector machine model is fine-tuned and trained based on the damage level detection result output by the soft margin support vector machine model.

7. The method for detecting magnetic flux leakage of a steel wire rope according to any one of claims 1 to 6, characterized in that: The method further comprises: Based on the damage level detection result, a detection report of the target steel wire rope is generated and displayed, wherein the detection report includes a detection position, a detection time and a damage level of the target steel wire rope where damage exists.

8. A signal processing terminal, characterized in that: include: An acquisition module, which acquires in real time the multi-channel detection signal of the target steel wire rope detected by the magnetic flux leakage detection probe, and the displacement data of the magnetic flux leakage detection probe detected by the displacement sensor; A multi-channel filtering module, used for filtering and denoising the multi-channel detection signal to obtain the multi-channel detection signal after denoising; and determining the detection speed of the magnetic flux leakage detection probe based on the displacement data; The support vector machine classification module is used to input the denoised multi-channel detection signal and the detection speed into a trained soft-margin support vector machine model to obtain the damage level detection result of the target wire rope at the detection position corresponding to the multi-channel detection signal.

9. A wire rope magnetic flux leakage detection system based on multi-channel filtering and support vector machine, characterized in that: It includes a magnetic flux leakage detection probe, a displacement sensor and a signal processing terminal; The magnetic flux leakage detection probe comprises a detection probe shoe and a multi-channel magnetic sensor, wherein the multi-channel magnetic sensor is distributed in a ring array on the detection probe shoe and is used to detect a multi-channel detection signal of the target steel wire rope; The displacement sensor is arranged at the side of the magnetic flux leakage detection probe, and is used to detect the displacement data of the magnetic flux leakage detection probe in real time; The signal processing terminal is used to execute the wire rope magnetic flux leakage detection method based on multi-channel filtering and support vector machine as described in any one of claims 1 to 7.

10. The wire rope magnetic flux leakage detection system according to claim 9, characterized in that: The system further comprises a data line installed at the tail of the magnetic flux leakage detection probe, which is used to transmit the multi-channel detection signal detected by the magnetic flux leakage detection probe and the displacement data detected by the displacement sensor to the signal processing terminal.

Images