Motor rotor magnetic sheet defect detection method based on intelligent sensing system

Abstract

The invention relates to the technical field of intelligent sensing, and particularly discloses a motor rotor magnetic sheet defect detection method based on an intelligent sensing system. According to the method, a plurality of ultrasonic array sensors are arranged around a motor rotor magnetic sheet, a self-adaptive signal processing technology is utilized, ultrasonic echo signals are subjected to filtering, feature extraction and beam imaging, and a neural network is combined, so that crack detection of the motor rotor magnetic sheet is realized. Compared with a traditional visual detection method and an X-ray detection method in the prior art, the technical problem that high-precision crack detection is difficult to realize due to environmental interference and equipment limitation in the traditional technology especially in a complex working condition and a high-load environment is solved. According to the intelligent sensing system and the self-adaptive signal processing method, high-precision detection of cracks of the motor rotor magnetic sheet is realized, the problems of misjudgment and missed judgment caused by a traditional method are avoided, and the accuracy and reliability of defect detection of the motor rotor magnetic sheet are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent sensing, and particularly relates to a method for detecting defects of motor rotor magnetic sheets based on an intelligent sensing system. Background Art

[0002] Currently, the methods for detecting defects of motor rotor magnetic sheets mainly rely on traditional visual inspection and X-ray inspection technologies. Although the visual inspection method can detect obvious surface cracks, it has poor detection ability for micro-cracks and hidden cracks, and the detection effect for cracks in complex surfaces or high-load operating environments is limited. Although X-ray inspection can provide relatively accurate internal defect images, it has high costs, complex operations, and cannot perform real-time monitoring, which limits its application in actual production. The existing technologies cannot fully meet the requirements for crack detection of motor rotor magnetic sheets in dynamic and high-load working environments, especially there are large gaps in real-time monitoring and high-precision detection. The problems faced by traditional technologies include low accuracy of crack detection, serious environmental interference, and poor adaptability to complex working conditions. Therefore, there is an urgent need for a method that can achieve high-precision real-time detection of micro-cracks in complex working environments, especially under high-load and dynamically changing conditions. By adopting intelligent sensing technology and advanced signal processing algorithms, the present invention provides an efficient and accurate solution for detecting defects of motor rotor magnetic sheets, thereby improving the reliability of crack detection and the operating safety of motor equipment. Summary of the Invention

[0003] Aiming at the above-mentioned existing technical deficiencies, the purpose of the present invention is to propose a method for detecting defects of motor rotor magnetic sheets based on an intelligent sensing system, aiming to solve the technical problems of traditional visual inspection methods and X-ray inspection methods in the prior art, especially in complex working conditions and high-load environments, where traditional technologies are affected by environmental interference and equipment limitations and it is difficult to achieve high-precision crack detection.

[0004] To solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a method for detecting defects of motor rotor magnetic sheets based on an intelligent sensing system,

[0005] The method for detecting defects of motor rotor magnetic sheets based on an intelligent sensing system includes:

[0006] Step S10: Arrange N ultrasonic array sensors around the motor rotor magnetic sheet, synchronously transmit ultrasonic pulse waves at time t, and receive the first ultrasonic echo signal; first perform adaptive Wiener filtering on the first ultrasonic echo signal to obtain the second ultrasonic echo signal, and then perform Hilbert transform on the second ultrasonic echo signal to obtain the filtered signal envelope curve;

[0007] Step S20: Extract the propagation feature differences of ultrasonic signals between different ultrasonic array sensors according to the filtered signal envelope curve, including: time difference, waveform amplitude attenuation difference, and phase difference; perform fast Fourier transform on the propagation feature differences to obtain crack-sensitive frequency domain features, and construct a multi-directional ultrasonic feature matrix based on the propagation feature differences and crack-sensitive frequency domain features;

[0008] Step S30: Use the beam imaging method based on the delay superposition algorithm to locate crack defects and output a crack imaging feature matrix;

[0009] Step S40: Construct a fusion matrix according to the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, input it into a preset crack detection model, and obtain a first crack detection result;

[0010] Step S50: Conduct error analysis on the first crack detection result and output a second crack detection result.

[0011] Preferably, in step S20, the time difference is calculated using a weighted cross-correlation function, and the expression is:

[0012]

[0013] where ΔT ij is the time difference between ultrasonic array sensor i and ultrasonic array sensor j, w(t) is the weighted window function, τ is the time difference displacement variable, y i (t), y j (t + τ) are the signals of ultrasonic array sensor i at time t and the signals of ultrasonic array sensor j at time t + τ respectively, and argmax is the weighted cross-correlation function; the waveform amplitude attenuation difference ΔA ij =|A i -A j |, where A i and A j are the waveform amplitudes of ultrasonic array sensors i and j respectively; the phase difference where are the waveform phases of ultrasonic array sensors i and j respectively.

[0014] Preferably, in step S30, the steps of using the beam imaging method based on the delay superposition algorithm to locate crack defects and output a crack imaging feature matrix specifically include:

[0015] Use the beam imaging method based on the delay superposition algorithm to calculate the ultrasonic imaging intensity at the two-dimensional spatial position (x, y) of the magnetic sheet of the motor rotor to be measured:

[0016]

[0017] Among them, I(x,y) is the ultrasonic imaging intensity at the two-dimensional spatial position (x,y) of the rotor magnet of the motor to be measured; y n is the second ultrasonic echo signal received by the nth ultrasonic array sensor; r n (x,y) is the geometric distance from the position (x,y) to be measured to the nth ultrasonic array sensor; v is the propagation speed of ultrasonic waves in the rotor magnet; A n is the weighting coefficient of the nth ultrasonic array sensor, determined according to the position of the ultrasonic array sensor;

[0018] Construct a crack imaging feature matrix based on the ultrasonic imaging intensity at the two-dimensional spatial position (x,y) of the rotor magnet of the motor to be measured.

[0019] Preferably, in step S40, the step of constructing a fusion matrix based on the crack imaging feature matrix and the multi-directional ultrasonic feature matrix and inputting it into a preset crack detection model to obtain the first crack detection result specifically includes:

[0020] Step S401: Construct a fusion matrix based on the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, and perform a two-dimensional convolution operation on the fusion matrix to obtain primary crack features;

[0021] Step S402: Introduce an attention mechanism network, input the primary crack features into the attention mechanism network, and calculate the attention weights between the primary crack features to enhance the recognition ability of crack-sensitive features, obtaining optimized crack features;

[0022] Step S403: Perform a max-pooling operation on the optimized crack features to obtain a crack-sensitive feature vector;

[0023] Step S404: Input the crack-sensitive feature vector into the fully connected layer of the crack detection model, and process it through the Softmax activation function to obtain the first crack detection result. The first crack detection result includes the crack category, crack position, and crack severity.

[0024] Preferably, in step S40, the attention mechanism network Attention adopts the formula:

[0025]

[0026] In the formula, Q, K, and V are the query matrix, key matrix, and value matrix of the attention mechanism network, constructed based on the primary crack features; d is the dimension of the feature matrix, used to normalize the scale of the feature vector; T is the matrix transpose symbol; softmax is the activation function.

[0027] Preferably, in step S50, the step of performing error analysis on the first crack detection result and outputting the second crack detection result specifically includes:

[0028] Step S501: Obtain the position coordinate information of the crack from the first crack detection result, and based on the position coordinate information of the crack, calculate the feedback propagation characteristic differences of the ultrasonic signals between different ultrasonic array sensors according to the crack position theoretical model, including: feedback time difference, feedback waveform amplitude attenuation difference, and feedback phase difference;

[0029] Step S502: Trace back to obtain the propagation characteristic differences in Step S20, and calculate the feedback error value according to the propagation characteristic differences and the feedback propagation characteristic differences;

[0030] Step S503: Set a first error threshold and a second error threshold, and divide the crack position credibility level according to the feedback error value:

[0031] If the feedback error value ≤ the first error threshold, define the crack position as high credibility;

[0032] If the first error threshold < the feedback error value ≤ the second error threshold, define it as medium credibility;

[0033] If the feedback error value > the second error threshold, define it as low credibility;

[0034] Step S504: Output the second crack detection result, the content of which includes: crack position coordinates, crack type and size, credibility level of the crack detection result, and feedback error value.

[0035] Preferably, in Step S50, when calculating the feedback error value according to the propagation characteristic differences and the feedback propagation characteristic differences, the formula is used:

[0036]

[0037] where, and are respectively the feedback time difference, feedback amplitude attenuation, and feedback phase difference of the nth ultrasonic array sensor; and are respectively the time difference, waveform amplitude attenuation difference, and phase difference obtained in Step S20.

[0038] The present invention also provides a motor rotor magnetic sheet defect detection system based on an intelligent sensing system, including:

[0039] An envelope curve generation module, configured to arrange N ultrasonic array sensors around the motor rotor magnetic sheet, synchronously transmit ultrasonic pulse waves at time t, and receive the first ultrasonic echo signal; first perform adaptive Wiener filtering on the first ultrasonic echo signal to obtain the second ultrasonic echo signal, and then perform Hilbert transform on the second ultrasonic echo signal to obtain the filtered signal envelope curve;

[0040] A multi-directional feature matrix construction module, which is used to extract the propagation feature differences of ultrasonic signals between different ultrasonic array sensors according to the envelope curve of the filtered signal, including: time difference, waveform amplitude attenuation difference, and phase difference; perform fast Fourier transform on the propagation feature differences to obtain crack-sensitive frequency domain features, and construct a multi-directional ultrasonic feature matrix according to the propagation feature differences and crack-sensitive frequency domain features;

[0041] A crack imaging feature matrix construction module, which is used to perform crack defect positioning by using the beam imaging method based on the delay superposition algorithm, and output a crack imaging feature matrix;

[0042] A first crack detection result output module, which is used to construct a fusion matrix according to the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, input a preset crack detection model, and obtain a first crack detection result;

[0043] A second crack detection result output module, which is used to perform error analysis on the first crack detection result and output a second crack detection result.

[0044] The present invention also provides a computer program product, including a motor rotor magnetic sheet defect detection program based on an intelligent sensing system. When the motor rotor magnetic sheet defect detection program based on the intelligent sensing system is executed by a processor, the motor rotor magnetic sheet defect detection method based on the intelligent sensing system described above is implemented.

[0045] The beneficial effects of the present invention are as follows: By introducing an intelligent sensing system and combining ultrasonic array sensors and adaptive signal processing technology, the present invention can detect crack defects in real time and with high precision during the operation of the motor rotor magnetic sheet. The intelligent sensor can automatically adjust the detection parameters to adapt to different working environments, thereby improving the flexibility and reliability of detection.

[0046] Through the precise monitoring of the propagation characteristics (time difference, amplitude attenuation difference, and phase difference) of ultrasonic signals, tiny cracks can be effectively identified and the specific positions of the cracks can be located, avoiding the problems of missed detection and false detection in traditional detection methods, thereby significantly improving the accuracy of crack detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a schematic flowchart of the first embodiment of a method for detecting defects in a motor rotor magnetic sheet based on an intelligent sensing system of the present invention.

[0049] Figure 2 This is a schematic diagram of the device for a method of detecting defects in the motor rotor magnetic sheet based on an intelligent sensing system according to the present invention. Specific embodiments

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] Embodiment 1: As Figure 1 shown, this is a schematic flowchart of the first embodiment of the method for detecting defects in the motor rotor magnetic sheet based on an intelligent sensing system according to the present invention, and the first embodiment of the method for detecting defects in the motor rotor magnetic sheet based on an intelligent sensing system according to the present invention is proposed.

[0052] In the first embodiment, the method for detecting defects in the motor rotor magnetic sheet based on an intelligent sensing system includes:

[0053] Step S10: Arrange N ultrasonic array sensors around the motor rotor magnetic sheet, synchronously emit ultrasonic pulse waves at time t, and receive the first ultrasonic echo signal; first perform adaptive Wiener filtering on the first ultrasonic echo signal to obtain a second ultrasonic echo signal, and then perform Hilbert transform on the second ultrasonic echo signal to obtain a filtered signal envelope curve;

[0054] It can be understood that the process of Wiener filtering adaptively denoises the ultrasonic echo signal by dynamically adjusting the filter parameters to adapt to different noise environments, greatly improving the signal quality. Subsequently, the Hilbert transform further extracts the envelope information of the echo signal, enabling the changes in the signal in the time domain to more clearly reflect the presence and characteristics of cracks.

[0055] It should be understood that through the combined processing of first performing Wiener filtering on the signal and then performing Hilbert transform, effective crack features can be extracted from a complex and noisy background, thereby avoiding misjudgment and missed judgment caused by noise interference and signal distortion in traditional methods. This method improves the signal-to-noise ratio of the signal, making it possible to detect tiny cracks.

[0056] For example, in an actual experiment, when using this method to detect the motor rotor, the signal-to-noise ratio of the ultrasonic echo signal obtained after Wiener filtering is increased by about 30%. The envelope signal extracted by Hilbert transform shows that the characteristics of the crack are more clearly separated and presented, and the detection accuracy is increased by about 20%. Through this improvement, the detection error caused by noise and interference can be significantly reduced, and the accuracy of micro-crack detection is significantly improved.

[0057] Step S20: Extract the propagation characteristic differences of ultrasonic signals between different ultrasonic array sensors according to the envelope curve of the filtered signal, including: time difference, waveform amplitude attenuation difference and phase difference; perform fast Fourier transform on the propagation characteristic differences to obtain crack-sensitive frequency domain characteristics, and construct a multi-directional ultrasonic characteristic matrix according to the propagation characteristic differences and crack-sensitive frequency domain characteristics;

[0058] It should be noted that in step S20, the time difference is calculated using the weighted cross-correlation function, and the expression is:

[0059]

[0060] where ΔT ij is the time difference between ultrasonic array sensor i and ultrasonic array sensor j, w(t) is the weighted window function, τ is the time difference displacement variable, y i (t), y j (t + τ) are the signals of ultrasonic array sensor i at time t and the signal of ultrasonic array sensor j at time t + τ respectively, and argmax is the weighted cross-correlation function; the waveform amplitude attenuation difference ΔA ij = |A i - A j |, where A i and A j are the waveform amplitudes of ultrasonic array sensors i and j respectively; the phase difference where are the waveform phases of ultrasonic array sensors i and j respectively.

[0061] It can be understood that in step S20, the time difference is used to calculate the propagation characteristic differences between different ultrasonic array sensors. Specifically, due to the presence of cracks during the propagation of ultrasonic signals, changes in propagation time, amplitude attenuation, and phase difference will occur. By calculating the time difference between the signals received by different ultrasonic array sensors, the location of the crack can be effectively identified. The time difference is determined by the propagation speed of the ultrasonic signal and the distance between the ultrasonic array sensors, so this difference is meaningful for crack location.

[0062] It should be understood that the time difference calculation uses the weighted cross - correlation function method. Taking the time displacement of the signal as a variable, the best matching position between signals is determined by maximizing the cross - correlation function, and then the time difference is obtained. This method can extract the propagation characteristics of cracks from noise and interference, enhance the signal distinguishability, and effectively reduce the influence of environmental noise on the detection results. The weighted window function in the time difference calculation formula makes the matching between signals more accurate, especially when the signal length is long or there are multiple reflections. By maximizing the correlation of signals, high - precision positioning of crack positions and characteristics can be achieved. This process can greatly improve the accuracy of crack detection through cross - calculation of multiple ultrasonic array sensors, especially in the dynamically changing environment of the motor rotor.

[0063] For example, three ultrasonic array sensors are arranged at different positions on the magnetic sheet of the motor rotor, and ultrasonic echo signals from the same crack are respectively recorded. By calculating the time difference between these three ultrasonic array sensors, the obtained propagation time difference has a strong correlation with the crack position. Experimental data show that through the combination of time difference calculation and the maximum cross - correlation function, the crack position can be accurately located, and the positioning accuracy is improved by about 20% compared with the traditional visual detection method.

[0064] Step S30: Use the beam imaging method based on the delay - superposition algorithm for crack defect positioning, and output the crack imaging feature matrix.

[0065] It should be noted that in step S30, the step of using the beam imaging method based on the delay - superposition algorithm for crack defect positioning and outputting the crack imaging feature matrix specifically includes:

[0066] Use the beam imaging method based on the delay - superposition algorithm to calculate the ultrasonic imaging intensity at the two - dimensional spatial position (x, y) of the magnetic sheet of the motor rotor to be measured:

[0067]

[0068] where I(x, y) is the ultrasonic imaging intensity at the two - dimensional spatial position (x, y) of the magnetic sheet of the motor rotor to be measured; y n is the second ultrasonic echo signal received by the nth ultrasonic array sensor; r n (x, y) is the geometric distance from the position to be measured (x, y) to the nth ultrasonic array sensor; v is the propagation speed of ultrasonic waves in the rotor magnet; A n is the weighting coefficient of the nth ultrasonic array sensor, which is determined according to the position of the ultrasonic array sensor;

[0069] Construct the crack imaging feature matrix according to the ultrasonic imaging intensity at the two - dimensional spatial position (x, y) of the magnetic sheet of the motor rotor to be measured.

[0070] It is understandable that step S30 uses a beam imaging method based on a delay superposition algorithm for crack defect localization. This is a time-domain delay superposition method that synchronously receives echo signals from multiple ultrasonic array sensors. By compensating for and superposing the propagation times of the signals from each ultrasonic array sensor, the echo signal of the crack can be effectively enhanced, and then a two-dimensional spatial position image of the crack on the rotor magnetic disc can be constructed through beam imaging. This method can greatly improve the accuracy and clarity of crack localization in dynamic and complex environments.

[0071] It should be understood that the beam imaging method is to compensate for the time differences of the signals from each ultrasonic array sensor to ensure that the echo signals are spatially aligned. This is a process based on the physical characteristics of ultrasonic signal propagation. By calculating the propagation times from each ultrasonic array sensor to the crack position and making appropriate delay corrections, the signals can be correctly superposed. The superposed signal can effectively reflect the accurate position and shape of the crack, not just its surface features. This technology avoids the errors and biases easily caused by traditional single-sensor methods, especially performing well in the complex environment of the motor rotor.

[0072] For example, in actual experiments, when using the beam imaging method to detect cracks in a motor rotor, by performing time-delay compensation and weighted superposition on the signals from multiple ultrasonic array sensors, the positioning accuracy of the crack position image is improved by about 30% compared with traditional methods. Five ultrasonic array sensors are arranged at different positions of the motor rotor. The signals after delay superposition clearly show the crack position, and the error is reduced by more than 20% compared with traditional detection methods. This experimental result shows that the beam imaging method based on the delay superposition algorithm can significantly improve the detection accuracy of crack defects.

[0073] Step S40: Construct a fusion matrix based on the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, input it into a preset crack detection model, and obtain a first crack detection result;

[0074] It should be noted that in step S40, the steps of constructing a fusion matrix based on the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, inputting it into a preset crack detection model, and obtaining a first crack detection result specifically include:

[0075] Step S401: Construct a fusion matrix based on the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, perform a two-dimensional convolution operation on the fusion matrix, and obtain primary crack features;

[0076] Step S402: Introduce an attention mechanism network, input the primary crack features into the attention mechanism network, calculate the attention weights between the primary crack features to enhance the recognition ability of crack-sensitive features, and obtain optimized crack features;

[0077] Step S403: Perform a max pooling operation on the optimized crack features to obtain a crack-sensitive feature vector;

[0078] Step S404: Input the crack-sensitive feature vector into the fully connected layer of the crack detection model, and obtain the first crack detection result through the processing of the Softmax activation function. The first crack detection result includes the crack category, crack location, and crack severity.

[0079] It can be understood that the key operation in Step S40 is to fuse the crack imaging feature matrix with the multi-directional ultrasonic feature matrix, combine the crack information provided by both, form a more comprehensive feature matrix, and feed it as input into the crack detection model. The goal of this step is to improve the accuracy and robustness of crack detection through efficient information fusion. The fusion of the crack imaging feature matrix and the multi-directional ultrasonic feature matrix can integrate information from different ultrasonic array sensors and different perspectives. Through two-dimensional convolution operations, richer and more accurate crack features can be extracted, reducing information loss or errors that may be caused by a single feature matrix. At the same time, the purpose of adding the attention mechanism network is to dynamically adjust the weights of the features, thereby automatically focusing on the parts that are crucial for crack localization and further improving the accuracy of crack detection.

[0080] It should be understood that with the introduction of the attention mechanism network, crack features can strengthen the more prominent features by calculating the correlation between features, thereby optimizing the crack recognition process. Through the max pooling operation, the system can select the most representative crack features from numerous features, thus avoiding the influence of redundant information on the subsequent classification process. Finally, through the processing of the fully connected layer and the Softmax activation function, the crack category, location, and severity information are extracted from the original features to obtain the first crack detection result. This series of operations ensures that the crack detection model can perform detection with higher accuracy and stronger adaptability.

[0081] For example, in actual experimental tests, when the crack imaging feature matrix is fused with the multi-directional ultrasonic feature matrix and primary features are extracted through two-dimensional convolution operations, after introducing the attention mechanism network, the detection accuracy of the system is improved by approximately 25% compared to the scheme without using this mechanism. In addition, when processing crack features, the stability and distinctiveness of the features are further improved through max-pooling operations, and finally, in the judgment of crack position, category, and severity, the error rate is reduced by 30%. These experimental data indicate that fusing different feature matrices and introducing the attention mechanism not only improves the detection accuracy but also enhances the system's adaptability to complex environments.

[0082] Step S50: Conduct error analysis on the first crack detection result and output the second crack detection result.

[0083] It should be noted that in step S50, the step of conducting error analysis on the first crack detection result and outputting the second crack detection result specifically includes:

[0084] Step S501: Obtain the position coordinate information of the crack from the first crack detection result, and based on the position coordinate information of the crack, calculate the feedback propagation feature differences of ultrasonic signals between different ultrasonic array sensors according to the crack position theoretical model, including: feedback time difference, feedback waveform amplitude attenuation difference, and feedback phase difference;

[0085] Step S502: Retrieve the propagation feature differences in step S20, and calculate the feedback error value based on the propagation feature differences and the feedback propagation feature differences;

[0086] Step S503: Set the first error threshold and the second error threshold, and divide the crack position credibility level according to the feedback error value:

[0087] If the feedback error value ≤ the first error threshold, define the crack position as high credibility;

[0088] If the first error threshold < the feedback error value ≤ the second error threshold, define it as medium credibility;

[0089] If the feedback error value > the second error threshold, define it as low credibility;

[0090] Step S504: Output the second crack detection result, the content of which includes: crack position coordinates, crack type and size, the credibility level of the crack detection result, and the feedback error value.

[0091] It is understandable that the calculation of the feedback propagation feature difference is based on the crack position coordinates obtained from the first crack detection result, and the propagation characteristics of the signal are deduced through a theoretical model. By calculating the time difference, amplitude attenuation difference, and phase difference of the ultrasonic signal, potential errors in the crack position can be identified. Based on the feedback differences of these features, we can more accurately evaluate the actual position of the crack and classify its credibility. Specifically, if the feedback error value is small, it indicates that the signal propagation characteristics are highly consistent with the theoretical model, and the credibility of the crack position is relatively high.

[0092] It should be understood that the calculation of the feedback error value is verified by combining theory and actual data through the method of backtracking to obtain the propagation feature difference. By setting the first error threshold and the second error threshold, the credibility level of the crack position can be divided according to the size of the feedback error value. If the error is small, the crack position has a high credibility; on the contrary, if the error is large, the credibility of the crack position is low. Ultimately, this process can not only improve the accuracy of the crack detection result but also provide valuable basis for subsequent maintenance decisions.

[0093] For example, in the experiment, by calculating the feedback error between the crack position in the first crack detection result and the actual crack position, we found that by setting the feedback error threshold, the credibility of the crack can be effectively distinguished. For example, when the feedback error value is less than the first error threshold, the positioning error of the crack is less than 1 mm, and the crack type and size are correctly identified; when the feedback error value is greater than the second error threshold, the error of the crack position is as high as 5 mm. At this time, the system automatically marks this result as low credibility and prompts that further confirmation is needed. Through this method, the crack positioning accuracy in the experiment has been improved by 20%, and false judgments can be effectively avoided.

[0094] Embodiment 2: In addition, a motor rotor magnetic sheet defect detection system based on an intelligent sensing system provided by the present invention adopts a motor rotor magnetic sheet defect detection method based on an intelligent sensing system in the above embodiment, which can solve the technical problem of motor rotor magnetic sheet defect detection based on an intelligent sensing system. Compared with the prior art, the beneficial effects of a motor rotor magnetic sheet defect detection system based on an intelligent sensing system provided by the present invention are the same as those of a motor rotor magnetic sheet defect detection method based on an intelligent sensing system provided in the above embodiment, and other technical features in the motor rotor magnetic sheet defect detection system based on an intelligent sensing system are the same as the features disclosed in the above embodiment method, and will not be elaborated here.

[0095] Embodiment 3: The present invention provides a motor rotor magnetic sheet defect detection device based on an intelligent sensing system. Please refer to Figure 2, A motor rotor magnetic sheet defect detection device based on an intelligent sensing system includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for detecting defects in a motor rotor magnetic sheet in Embodiment 1 above. A motor rotor magnetic sheet defect detection device in an embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable Media Player), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. A motor rotor magnetic sheet defect detection device based on an intelligent sensing system is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present invention. A motor rotor magnetic sheet defect detection device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for operating a motor rotor magnetic sheet defect detection device based on an intelligent sensing system are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow a motor rotor magnetic sheet defect detection device based on an intelligent sensing system to communicate with other devices wirelessly or wiredly to exchange data. Although a motor rotor magnetic sheet defect detection device with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the shown systems. Instead, more or fewer systems may be implemented or possessed.

[0096] Embodiment 4: The present invention also provides a computer program product, including a computer program which, when executed by a processor, implements the steps of a method for detecting defects of motor rotor magnetic tiles based on an intelligent sensing system as described above. The computer program product provided by the present invention can solve the technical problem of detecting defects of motor rotor magnetic tiles based on an intelligent sensing system. Compared with the prior art, the beneficial effects of the computer program product provided by the present invention are the same as those of the method for detecting defects of motor rotor magnetic tiles based on an intelligent sensing system provided in the above embodiment, and will not be elaborated here.

[0097] Particularly, according to the embodiments disclosed by the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed by the present invention include a computer program product which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, it executes the above-mentioned functions defined in the methods of the embodiments disclosed by the present invention.

[0098] It should be understood that each part disclosed by the present invention can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0099] Obviously, those skilled in the art can make various modifications 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 the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for detecting defects in the magnetic sheet of a motor rotor based on an intelligent sensing system, characterized in that, The method includes: Step S10: Arrange N ultrasonic array sensors around the motor rotor magnetic sheet, synchronously transmit ultrasonic pulse waves at time t, and receive the first ultrasonic echo signal; first perform adaptive Wiener filtering on the first ultrasonic echo signal to obtain the second ultrasonic echo signal, and then perform Hilbert transform on the second ultrasonic echo signal to obtain the filtered signal envelope curve; Step S20: Extract the propagation characteristic differences of ultrasonic signals between different ultrasonic array sensors according to the filtered signal envelope curve, including: time difference, wave amplitude attenuation difference, and phase difference; perform fast Fourier transform on the propagation characteristic differences to obtain crack-sensitive frequency domain characteristics, and construct a multi-directional ultrasonic characteristic matrix according to the propagation characteristic differences and crack-sensitive frequency domain characteristics; Step S30: Use the beam imaging method based on the delay and sum algorithm to locate crack defects and output a crack imaging characteristic matrix; Step S40: Construct a fusion matrix according to the crack imaging characteristic matrix and the multi-directional ultrasonic characteristic matrix, input it into a preset crack detection model, and obtain the first crack detection result; Step S50: Perform error analysis on the first crack detection result and output the second crack detection result.

2. The method for detecting defects of the motor rotor magnetic sheet based on the intelligent sensing system according to claim 1, characterized in that, In step S20, the time difference is calculated using a weighted cross-correlation function, and the expression is: where, ΔT ij is the time difference between the ultrasonic array sensor i and the ultrasonic array sensor j, w(t) is the weighted window function, τ is the time difference displacement variable, y i (t), y j (t + τ) are respectively the signals of the ultrasonic array sensor i at time t and the signals of the ultrasonic array sensor j at time t + τ, and argmax is the weighted cross-correlation function; the waveform amplitude attenuation difference ΔA ij = |A i - A j |, where, A i and A j are respectively the waveform amplitudes of the ultrasonic array sensors i and j; the phase difference where are respectively the waveform phases of the ultrasonic array sensors i and j.

3. A method for detecting defects of a motor rotor magnetic sheet based on an intelligent sensing system according to claim 1, characterized in that, In step S30, the steps of using the beam imaging method based on the delay and sum algorithm to locate crack defects and output a crack imaging characteristic matrix specifically include: Using the beam imaging method based on the delay and sum algorithm, calculate the ultrasonic imaging intensity at the two-dimensional spatial position (x, y) of the motor rotor magnetic sheet to be measured; Among them, I(x,y) is the ultrasonic imaging intensity at the two-dimensional spatial position (x,y) of the rotor magnet of the motor to be measured; y n is the second ultrasonic echo signal received by the nth ultrasonic array sensor; r n (x,y) is the geometric distance from the position (x,y) to be measured to the nth ultrasonic array sensor; v is the propagation speed of ultrasonic waves in the rotor magnet; A n is the weighting coefficient of the nth ultrasonic array sensor, which is determined according to the position of the ultrasonic array sensor; Construct a crack imaging characteristic matrix according to the ultrasonic imaging intensity at the two-dimensional spatial position (x, y) of the motor rotor magnetic sheet to be measured.

4. A method for detecting defects of a motor rotor magnetic sheet based on an intelligent sensing system according to claim 1, characterized in that, In step S40, the steps of constructing a fusion matrix according to the crack imaging characteristic matrix and the multi-directional ultrasonic characteristic matrix, inputting it into a preset crack detection model, and obtaining the first crack detection result specifically include: Step S401: Construct a fusion matrix according to the crack imaging characteristic matrix and the multi-directional ultrasonic characteristic matrix, perform two-dimensional convolution operation on the fusion matrix to obtain primary crack characteristics; Step S402: Introduce an attention mechanism network, input the primary crack characteristics into the attention mechanism network, calculate the attention weights between the primary crack characteristics to enhance the recognition ability of crack-sensitive characteristics, and obtain optimized crack characteristics; Step S403: Perform max pooling operation on the optimized crack characteristics to obtain a crack-sensitive feature vector; Step S404: Input the crack-sensitive feature vector into the fully connected layer of the crack detection model, and process it through the Softmax activation function to obtain the first crack detection result. The first crack detection result includes crack category, crack position, and crack severity.

5. The method for detecting defects of the motor rotor magnetic sheet based on the intelligent sensing system according to claim 4, characterized in that, In step S40, the attention mechanism network Attention adopts the formula: In the formula, Q, K, and V are the query matrix, key matrix, and value matrix of the attention mechanism network, constructed according to the primary crack characteristics; d is the dimension of the feature matrix, used to normalize the scale of the feature vector; T is the matrix transpose symbol; softmax is the activation function.

6. The method for detecting defects of the motor rotor magnetic sheet based on the intelligent sensing system according to claim 1, wherein In step S50, the step of performing error analysis on the first crack detection result and outputting the second crack detection result specifically includes: Step S501: Obtain the position coordinate information of the crack from the first crack detection result, and based on the position coordinate information of the crack, calculate the feedback propagation characteristic differences of ultrasonic signals between different ultrasonic array sensors according to the crack position theoretical model, including: feedback time difference, feedback waveform amplitude attenuation difference, and feedback phase difference; Step S502: Retrieve the propagation characteristic differences in step S20, and calculate the feedback error value based on the propagation characteristic differences and the feedback propagation characteristic differences; Step S503: Set a first error threshold and a second error threshold, and divide the crack position credibility levels according to the feedback error value: If the feedback error value ≤ the first error threshold, define the crack position as high credibility; If the first error threshold < feedback error value ≤ the second error threshold, define it as medium credibility; If the feedback error value > the second error threshold, define it as low credibility; Step S504: Output the second crack detection result, the content of which includes: crack position coordinates, crack type and size, the credibility level of the crack detection result, and the feedback error value.

7. The method for detecting defects of motor rotor magnetic sheets based on an intelligent sensing system according to claim 6, wherein In step S50, calculate the feedback error value according to the propagation characteristic differences and the feedback propagation characteristic differences, using the formula: Among them, and are respectively the feedback time difference, feedback amplitude attenuation, and feedback phase difference of the nth ultrasonic array sensor; and The time difference, waveform amplitude attenuation difference, and phase difference in the propagation characteristic difference of the nth ultrasonic array sensor.

8. A motor rotor magnetic sheet defect detection system based on an intelligent sensing system, which is applied to a motor rotor magnetic sheet defect detection method based on an intelligent sensing system according to any one of claims 1-7, characterized in that, The motor rotor magnetic sheet defect detection system based on the intelligent sensing system includes: An envelope curve generation module, which is used to arrange N ultrasonic array sensors around the motor rotor magnetic sheet, synchronously transmit ultrasonic pulse waves at time t, and receive the first ultrasonic echo signal; first perform adaptive Wiener filtering on the first ultrasonic echo signal to obtain the second ultrasonic echo signal, and then perform Hilbert transform on the second ultrasonic echo signal to obtain the filtered signal envelope curve; A multi-directional feature matrix construction module, which is used to extract the propagation characteristic differences of ultrasonic signals between different ultrasonic array sensors according to the filtered signal envelope curve, including: time difference, waveform amplitude attenuation difference, and phase difference; perform fast Fourier transform on the propagation characteristic differences to obtain crack-sensitive frequency domain features, and construct a multi-directional ultrasonic feature matrix according to the propagation characteristic differences and the crack-sensitive frequency domain features; A crack imaging feature matrix construction module, which is used to perform crack defect positioning using the beam imaging method based on the delay superposition algorithm, and output the crack imaging feature matrix; A first crack detection result output module, which is used to construct a fusion matrix according to the crack imaging feature matrix and the multi-directional ultrasonic feature matrix, input a preset crack detection model, and obtain the first crack detection result; A second crack detection result output module, which is used to perform error analysis on the first crack detection result and output the second crack detection result.

9. A motor rotor magnetic sheet defect detection device based on an intelligent sensing system, characterized in that, The motor rotor magnetic sheet defect detection device based on the intelligent sensing system includes: a memory, a processor, and a motor rotor magnetic sheet defect detection program based on the intelligent sensing system stored on the memory and operable on the processor. When the motor rotor magnetic sheet defect detection program based on the intelligent sensing system is executed by the processor, it implements the method for detecting defects in a motor rotor magnetic sheet based on an intelligent sensing system according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a motor rotor magnetic sheet defect detection program based on an intelligent sensing system. When the motor rotor magnetic sheet defect detection program based on the intelligent sensing system is executed by a processor, it implements a motor rotor magnetic sheet defect detection method according to any one of claims 1 to 7.

Images