Magnetic ring detection device and detection method

Abstract

The invention relates to the technical field of magnetic ring detection, in particular to a magnetic ring detection device and method, and the method comprises the following steps: S1, positioning a magnetic ring and configuring initial parameters; s2, magnetic field data are collected and preprocessed, and weighted fusion magnetic field data are obtained; s3, correcting the weighted fused magnetic field data based on the environment temperature; s4, analyzing the magnetic field data based on a machine learning model to identify the defect type of the magnetic ring; and S5, generating a detection report, and if the magnetic ring has defects, performing early warning. The system has the beneficial effects that the magnetic field intensity distribution on the surface of the magnetic ring can be measured through the magnetic field scanning module, the magnetic field intensity is subjected to weighted fusion and temperature correction processing, the magnetic field data is analyzed through the data analysis module, the defect type and position of the magnetic ring are identified, and the accuracy of magnetic ring detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of magnetic ring detection, and particularly relates to a magnetic ring detection device and a detection method. Background Art

[0002] Magnetic rings are commonly used in filters and transformers, and their performance directly affects the anti-interference ability of equipment. Qualified magnetic rings can reduce the risk of equipment failure. The size and magnetic properties of magnetic rings are crucial for their stable operation under complex working conditions.

[0003] In the prior art, the detection of magnetic rings usually relies on manual detection. Manual detection uses methods such as vernier calipers and visual inspection, which are inefficient and subjective, and are prone to introducing secondary damages such as scratches. Contact measurement cannot meet the high-precision requirements, especially it is difficult to ensure consistency in precision equipment. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present application proposes a magnetic ring detection device and a detection method, which can measure the magnetic field intensity distribution on the surface of the magnetic ring through a magnetic field scanning module, perform weighted fusion and temperature correction processing on the magnetic field intensity, analyze the magnetic field data through a data analysis module, identify the types and positions of magnetic ring defects, and improve the accuracy of magnetic ring detection.

[0005] The following is the technical solution of the present invention. A magnetic ring detection method includes the following steps:

[0006] S1. Locate the magnetic ring and configure initial parameters;

[0007] S2. Collect magnetic field data and perform preprocessing to obtain weighted fusion magnetic field data;

[0008] S3. Correct the weighted fusion magnetic field data based on the ambient temperature;

[0009] S4. Analyze the magnetic field data based on a machine learning model to identify the types of magnetic ring defects;

[0010] S5. Generate a detection report. If there are defects in the magnetic ring, give an early warning.

[0011] As a preferred solution of the present invention, S1 includes the following steps:

[0012] S11. A vision sensor collects an image of the magnetic ring and extracts the edge contour;

[0013] S12. Calculate the center coordinates and radius of the magnetic ring through Hough transformation;

[0014] S13. Dynamically adjust the spacing of the Hall sensor array according to the size of the magnetic ring.

[0015] As a preferred embodiment of the present invention, in S13, the optimal number of sensors is calculated according to the radius of the magnetic ring, and the expression is as follows:

[0016]

[0017] In the above formula, n is the number of sensors, r is the radius of the magnetic ring, and Δd is the minimum resolution.

[0018] As a preferred embodiment of the present invention, in S13, the distance between sensors in the sensor array is calculated according to the number of sensors and the diameter of the magnetic ring, and the expression is as follows:

[0019]

[0020] In the above formula, d is the distance between the sensor arrays, D is the diameter of the magnetic ring, and n is the number of sensors.

[0021] As a preferred embodiment of the present invention, in S2, the weighted fusion magnetic field data is calculated, and the expression is as follows:

[0022]

[0023]

[0024] In the above formula, w i is the weight of the i-th sensor, σ i is the noise variance of the i-th sensor, B fused is the magnetic field strength after fusion, B i is the magnetic field strength of the i-th sensor, and n is the number of sensors.

[0025] As a preferred embodiment of the present invention, in S3, the weighted fusion magnetic field data is corrected based on the ambient temperature, and the expression is as follows:

[0026] B corr = B fused ·[1 + α(T - T0)]

[0027] In the above formula, B corr is the corrected magnetic field strength, B fused is the magnetic field strength after fusion, T is the ambient temperature, T0 is the standard ambient temperature, and α is the temperature coefficient.

[0028] As a preferred embodiment of the present invention, in S5, the detection report includes a magnetic field distribution heat map, a contour map, a defect type, a defect location, and a confidence level.

[0029] A magnetic ring detection device includes:

[0030] A magnetic ring positioning module for precise positioning and clamping of the magnetic ring, connected to the control module;

[0031] A magnetic field scanning module, which is used to measure the magnetic field strength distribution on the surface of the magnetic ring and is connected to the signal processing module and the control module;

[0032] A signal processing module, which is used to filter, amplify and denoise the original magnetic field signal;

[0033] A data analysis module, which analyzes the magnetic field data based on a machine learning model to identify the types of magnetic ring defects and is connected to the signal processing module;

[0034] A control module, which is used to coordinate the operation of each module and dynamically adjust the detection parameters.

[0035] As a preferred solution of the present invention, the magnetic ring positioning module includes a vision sensor and a robotic arm. The signal output by the vision sensor is transmitted to the control module, and the control module drives the robotic arm to adjust the position.

[0036] As a preferred solution of the present invention, the magnetic field scanning module is provided with a sensor array, and the sensor array and the signal processing module are connected through an SPI bus.

[0037] The beneficial effects of the present invention are as follows:

[0038] 1. In the present invention, the magnetic ring is accurately positioned and clamped through the magnetic ring positioning module, improving the detection accuracy;

[0039] 2. In the present invention, the magnetic field strength distribution on the surface of the magnetic ring is measured through the magnetic field scanning module, and weighted fusion and temperature correction processing are performed on the magnetic field strength, improving the accuracy of magnetic field strength detection;

[0040] 3. By analyzing the magnetic field data through the data analysis module, the types and positions of magnetic ring defects are identified, improving the accuracy of magnetic ring detection. Description of the Drawings

[0041] Figure 1 Schematic diagram of the detection device of the present invention Figure 1 ;

[0042] Figure 2 Schematic diagram of the detection device of the present invention Figure 2 ;

[0043] Figure 3 Flowchart of the detection method of the present invention;

[0044] Figure 4 Flowchart of the detection device of the present invention;

[0045] In the figure: 1. Magnetic ring positioning module; 101. Vision sensor; 102. Robotic arm; 2. Magnetic field scanning module; 201. Sensor array; 3. Signal processing module; 4. Data analysis module; 5. Control module. Detailed Embodiments

[0046] To make the technical problems solved by the present invention, the technical solutions adopted, and the achieved technical effects clearer, the following will further describe in detail the technical solutions of the embodiments of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0047] Embodiment 1:

[0048] As Figure 1 and Figure 2 shown, a magnetic ring detection device includes:

[0049] A magnetic ring positioning module 1 for precise positioning and clamping of the magnetic ring, connected to the control module 5;

[0050] A magnetic field scanning module 2 for measuring the magnetic field strength distribution on the surface of the magnetic ring, connected to the signal processing module 3 and the control module 5;

[0051] A signal processing module 3 for filtering, amplifying, and noise-reducing the original magnetic field signal, connected to the magnetic field scanning module 2;

[0052] A data analysis module 4 for analyzing magnetic field data based on a machine learning model to identify the types of magnetic ring defects, connected to the signal processing module 3;

[0053] A control module 5 for coordinating the operation of each module and dynamically adjusting the detection parameters.

[0054] In this embodiment, the magnetic ring positioning module 1 works in cooperation with a vision sensor 101 (CCD camera) and a robotic arm 102 to achieve precise positioning and clamping of the magnetic ring, and accurately place the magnetic ring on the detection platform. The signal output by the vision sensor 101 is transmitted to the control module 5, and the control module 5 drives the robotic arm 102 to adjust the position.

[0055] In this embodiment, the magnetic field scanning module 2 uses a high-precision Hall sensor array 201 to measure the magnetic field strength distribution on the surface of the magnetic ring. The sensor array 201 is connected to the signal processing module 3 through an SPI bus to transmit magnetic field data in real time. The sampling frequency f of the sensor s ≥10 kHz.

[0056] In this embodiment, the signal processing module 3 filters, amplifies, and noise-reduces the original magnetic field signal.

[0057] In this embodiment, the data analysis module 4 analyzes magnetic field data based on a machine learning model to identify the types of magnetic ring defects. The machine learning model is a support vector machine SVM.

[0058] In this embodiment, the control module 5 coordinates the operation of each module and dynamically adjusts the detection parameters. The control module 5 uses a PID controller to adjust the movement speed of the robotic arm 102, and the expression is as follows:

[0059]

[0060] In the above formula, v(t) is the movement speed of the robotic arm 102, e(t) is the position error, and K p , k i and K d are control coefficients.

[0061] Embodiment 2:

[0062] As shown in Figure 3 and Figure 4 , a method for detecting magnetic rings includes the following steps:

[0063] S1. Locate the magnetic ring and configure initial parameters;

[0064] S2. Collect magnetic field data and perform preprocessing to obtain weighted fusion magnetic field data;

[0065] S3. Correct the weighted fusion magnetic field data based on the ambient temperature;

[0066] S4. Analyze the magnetic field data based on a machine learning model to identify the types of magnetic ring defects;

[0067] S5. Generate a detection report, and if there are defects in the magnetic ring, give an early warning.

[0068] In step S1, locate the magnetic ring and configure initial parameters. Specifically, the magnetic ring positioning includes the following steps:

[0069] S11. The vision sensor 101 collects the magnetic ring image and extracts the edge contour;

[0070] S12. Calculate the magnetic ring center coordinates (x c , y c ) and the radius r through Hough transform;

[0071] S13. Dynamically adjust the spacing d of the Hall sensor array 201 according to the magnetic ring size.

[0072] In step S12, calculate the magnetic ring center coordinates (x c , y c ) and the radius r through Hough transform. Specifically, the magnetic ring positioning module 1 uses a circle detection algorithm based on Hough transform to locate the magnetic ring center coordinates, and the expression is as follows:

[0073] (x - x c ) 2 +(y - yc ) 2 = r 2

[0074] In the above formula, x c and y c are the abscissa and ordinate of the center of the magnetic ring, and r is the radius of the magnetic ring, which is obtained by fitting after extracting the contour through edge detection.

[0075] In step S13, the spacing of the Hall sensor array 201 is dynamically adjusted according to the size of the magnetic ring. Specifically, the optimal number of sensors n is calculated according to the radius r of the magnetic ring, and the expression is as follows:

[0076]

[0077] In the above formula, n is the number of sensors, r is the radius of the magnetic ring, and Δd is the minimum resolution.

[0078] The sensor spacing within the sensor array 201 is calculated according to the number of sensors n and the size of the magnetic ring, and the expression is as follows:

[0079]

[0080] In the above formula, d is the spacing of the sensor array 201, D is the diameter of the magnetic ring, and n is the number of sensors.

[0081] The sensor array 201 is driven by a stepper motor to adjust the sensor array to a uniformly distributed ring.

[0082] In step S2, magnetic field data is collected and preprocessed. Specifically, the magnetic field scanning module 2 samples the magnetic field intensity at a frequency of f s = 10 kHz, and wavelet denoising is used to reduce high-frequency interference.

[0083] The expression of the wavelet threshold denoising algorithm is as follows:

[0084]

[0085] In the above formula, λ is the threshold coefficient, ψ j ,k is the wavelet basis function.

[0086] Weighted fusion is performed on each sensor data, and the weight expression is as follows:

[0087]

[0088] In the above formula, w i is the weight of the i-th sensor, and σ i is the noise variance of the i-th sensor.

[0089] The expression of the fused magnetic field intensity is as follows:

[0090]

[0091] In the above formula, B fused is the magnetic field strength after fusion, B i is the magnetic field strength of the i-th sensor, w i is the weight of the i-th sensor, and n is the number of sensors.

[0092] In step S3, the magnetic field data of weighted fusion is corrected based on the ambient temperature. Specifically, the ambient temperature T is monitored in real time, and the expression of the corrected magnetic field strength is as follows:

[0093] B corr = B fused ·[1 + α(T - T0)]

[0094] In the above formula, B corr is the corrected magnetic field strength, B fused is the magnetic field strength after fusion, T is the ambient temperature, T0 is the standard ambient temperature, and α is the temperature coefficient.

[0095] In step S4, the magnetic field data is analyzed based on a machine learning model to identify the type of magnetic ring defect. Specifically, defect features are extracted. The feature vector of the machine learning model includes the magnetic field gradient and the standard deviation σ B , and classification is performed. A convolutional neural network is trained. The magnetic field distribution matrix is input, and the softmax function is used in the output layer to calculate the defect probability, and the defect position and confidence are output.

[0096] In step S5, a detection report is generated. If there is a defect in the magnetic ring, a warning is given. The detection report includes a heat map of the magnetic field distribution, a contour map, the type of defect, the defect position, and the confidence, etc. It is judged whether there is a defect in the performance of the magnetic ring through the heat map of the magnetic field distribution and the defect position, and it is judged whether there is a defect in the size of the magnetic ring through the heat map of the magnetic field distribution and the contour map. If there is a performance or size defect in the magnetic ring, a warning is given through voice broadcast to remind the tester.

[0097] In the present invention, the magnetic ring positioning module 1 accurately positions and clamps the magnetic ring, improving the detection accuracy; the magnetic field scanning module 2 measures the magnetic field strength distribution on the surface of the magnetic ring, performs weighted fusion and temperature correction processing on the magnetic field strength, improving the accuracy of magnetic field strength detection; the data analysis module 4 analyzes the magnetic field data, identifies the type and position of the magnetic ring defect, improving the accuracy of magnetic ring detection.

[0098] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic inventive concept. Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of equivalent technology of the present invention, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting magnetic rings, characterized in that, It includes the following steps: S1. Locate the magnetic ring and configure initial parameters; S2. Collect magnetic field data and perform preprocessing to obtain weighted fusion magnetic field data; S3. Correct the weighted fusion magnetic field data based on the ambient temperature; S4. Analyze the magnetic field data based on a machine learning model to identify the types of magnetic ring defects; S5. Generate a detection report. If there are defects in the magnetic ring, give an early warning.

2. The magnetic ring detection method according to claim 1, wherein S1 includes the following steps: S11. The vision sensor collects magnetic ring images and extracts edge contours; S12. Calculate the center coordinates and radius of the magnetic ring through Hough transform; S13. Dynamically adjust the spacing of the Hall sensor array according to the magnetic ring size.

3. The magnetic ring detection method according to claim 2, characterized in that In S13, calculate the optimal number of sensors according to the magnetic ring radius. The expression is as follows: In the above formula, n is the number of sensors, r is the magnetic ring radius, and Δd is the minimum resolution.

4. A method for detecting a magnetic ring according to claim 2, wherein In S13, calculate the sensor spacing within the sensor array according to the number of sensors and the magnetic ring diameter. The expression is as follows: In the above formula, d is the sensor array spacing, D is the magnetic ring diameter, and n is the number of sensors.

5. A method for detecting magnetic rings according to claim 1, characterized in that, In S2, calculate the weighted fusion magnetic field data. The expression is as follows: In the above formula, w i is the weight of the i-th sensor, and σ i is the noise variance of the i-th sensor. B fused is the magnetic field strength after fusion, B i is the magnetic field strength of the i-th sensor, and n is the number of sensors.

6. A method for detecting a magnetic ring according to claim 5, wherein, In S3, correct the weighted fusion magnetic field data based on the ambient temperature. The expression is as follows: B corr = B fused ·[1 + α(T - T0)] In the above formula, B corr is the corrected magnetic field strength, B fused is the fused magnetic field strength, T is the ambient temperature, T0 is the standard ambient temperature, and α is the temperature coefficient.

7. A method for detecting magnetic rings according to claim 1, characterized in that In S5, the detection report includes a magnetic field distribution heat map, a contour map, defect types, defect positions, and confidence levels.

8. A magnetic ring detection device, applicable to a magnetic ring detection method according to any one of claims 1-7, characterized in that, It includes: A magnetic ring positioning module for the precise positioning and clamping of the magnetic ring, connected to the control module; A magnetic field scanning module for measuring the magnetic field intensity distribution on the surface of the magnetic ring, connected to the signal processing module and the control module; A signal processing module for filtering, amplifying, and noise-reducing the original magnetic field signal; A data analysis module for analyzing the magnetic field data based on a machine learning model to identify the types of magnetic ring defects, connected to the signal processing module; A control module for coordinating the operation of each module and dynamically adjusting detection parameters.

9. A magnetic ring detection device according to claim 8, characterized in that, The magnetic ring positioning module includes a vision sensor and a robotic arm. The output signal of the vision sensor is transmitted to the control module, and the control module drives the robotic arm to adjust the position.

10. A magnetic ring detection device according to claim 8, characterized in that, The magnetic field scanning module is provided with a sensor array, and the sensor array and the signal processing module are connected through the SPI bus.

Images