A control method, system and gear mold for powder metallurgy double helical gears

Abstract

The present application provides a control method, system and gear mold for powder metallurgy double helical gears, which determines the confidence distribution entropy of each frequency domain signal through each acoustic wave signal in the historical acoustic wave data of powder metallurgy forming manufacturing and process; determines the defect coupling characteristics when the target double helical gear is coupled with the acoustic wave signal, determines the positioning auxiliary signal of the target double helical gear when the metallurgical defect occurs according to each confidence distribution entropy and the defect coupling characteristics, determines the defect position of the metallurgical defect according to the positioning auxiliary signal and the structural parameters of the target double helical gear; and performs real-time compensation control on the powder metallurgy of the target double helical gear based on the defect. The present application can reduce the defect rate in the powder metallurgy double helical gear process, improve the powder metallurgy precision, realize mold precision control, and ensure that the gear mold demolding friction coefficient is smaller and the product precision is improved. It also ensures that the product is demolded smoothly, thereby improving the precision of the finished double helical gear.

Description

Technical Field

[0001] The present application relates to the technical field of powder metallurgy, and more specifically, to a control method, system and gear mold for powder metallurgy double helical gears. Background Art

[0002] Powder metallurgy is a manufacturing technology that manufactures parts by pressing metal powder into shape and sintering it at high temperature. This process can produce parts with complex shapes and high precision, and is used in the automotive, aerospace, electronics, machinery and other fields; double helical gears refer to a gear system consisting of two helical gears, which are characterized by parallel axes of the two helical gears and inclined tooth surfaces in opposite directions. It is often used in mechanical systems that need to transmit large torque and high-speed operation.

[0003] Powder metallurgy duplex helical gears are complex gear structures manufactured using powder metallurgy technology. Powder metallurgy technology has significant advantages in manufacturing complex shapes and high-precision parts, and is suitable for manufacturing duplex helical gears. The process of powder metallurgy forming duplex helical gears is often accompanied by complex physical and chemical changes, which can easily lead to defects. In addition, due to the difficulty of demolding the inclination of the helical gears and the low mold precision, the finished product precision is insufficient. In the existing technology, ultrasonic detection technology is usually used to detect the internal defects of duplex helical gears (such as pores, cracks and holes) online to provide real-time defect information. However, the detection of tiny cracks and pores requires High-frequency sound waves have a large attenuation in materials, making it difficult to achieve comprehensive inspection of the entire part while maintaining high resolution. The formation of defects in the metallurgical process will produce acoustic emission (i.e., the phenomenon that a local area in an object rapidly releases energy to produce transient elastic waves under the action of external factors). The source of acoustic emission (i.e., the defect) can be identified through signal processing, feature analysis and other means. Therefore, how to use acoustic emission to locate and correct the defects of duplex helical gears in real time, thereby reducing the defect rate in the powder metallurgy duplex helical gear process and improving the accuracy of the finished duplex helical gears has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a control method, system and gear mold for powder metallurgy double helical gears, which utilize acoustic emission to perform real-time positioning and correction of defects in double helical gears, thereby reducing the defect rate in the powder metallurgy double helical gear process and thereby improving the accuracy of the finished double helical gear products.

[0005] In a first aspect, the present application provides a control method for a powder metallurgy double helical gear, comprising:

[0006] Collect the acoustic wave signals of the target double helical gear during the powder metallurgy process, and then obtain historical acoustic wave data;

[0007] Performing frequency domain conversion on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, and determining the confidence distribution entropy of each frequency domain signal through signal coupling between the frequency domain signals;

[0008] Extracting defect coupling characteristics of the target double helical gear when acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data, and then determining the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when metallurgical defects occur according to each confidence distribution entropy and the defect coupling characteristics;

[0009] Acquire the reverse propagation path of the positioning auxiliary signal, and then determine the defect focus area of ​​the target double helical gear when metallurgical defects occur according to the reverse propagation path and the structural parameters of the target double helical gear;

[0010] By using the positioning auxiliary signal, sound source focusing positioning is performed in the defect focusing area to obtain the defect position of the metallurgical defect in the target duplex helical gear;

[0011] Based on the defect position, real-time compensation control is performed on the powder metallurgy of the target duplex helical gear.

[0012] In some embodiments, extracting the defect coupling characteristics of the target duplex helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data specifically includes:

[0013] Acquire the acoustic signal dataset of known metallurgical defects in the metallurgical process of duplex helical gears;

[0014] Extracting features from each acoustic wave signal in the acoustic wave signal data set to obtain a defect feature library of known metallurgical defects;

[0015] The defect coupling characteristics of the target duplex helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process are determined according to the historical acoustic wave data and the defect feature library.

[0016] In some embodiments, determining the confidence distribution entropy of each frequency domain signal through the signal coupling between each frequency domain signal specifically includes:

[0017] Determine the signal coupling between various frequency domain signals;

[0018] Selecting a frequency domain signal from all frequency domain signals as a selected frequency domain signal, and determining a frequency domain signal distribution entropy of the selected frequency domain signal;

[0019] Determining a coupling coefficient of a selected frequency domain signal by signal coupling between the selected frequency domain signal and other frequency domain signals;

[0020] Determining the confidence distribution entropy of the selected frequency domain signal according to the frequency domain signal distribution entropy and the coupling coefficient;

[0021] Continue to determine the confidence distribution entropy of the remaining frequency domain signal.

[0022] In some embodiments, determining the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs according to each confidence distribution entropy and the defect coupling feature specifically includes:

[0023] Determining a characteristic distribution entropy of the defect coupling characteristic;

[0024] Determining characteristic mutual information between a corresponding acoustic wave signal in the historical acoustic wave data and the defect coupling characteristic according to each confidence distribution entropy and the characteristic distribution entropy;

[0025] Screening out the time domain defect signal in the target duplex helical gear from the historical acoustic wave data according to all the feature mutual information;

[0026] A positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs is determined according to all the emission signal segments in the time domain defect signal.

[0027] In some embodiments, determining the defect focal area of ​​the target duplex helical gear when metallurgical defects are generated according to the reverse propagation path and the structural parameters of the target duplex helical gear specifically includes:

[0028] Obtaining structural parameters of the target double helical gear;

[0029] Determining the signal source position and signal propagation direction of the target duplex helical gear when a metallurgical defect occurs according to the reverse propagation path;

[0030] Transiently aggregate the metallurgical defects of the target duplex helical gear according to the structural parameters, the signal source position and the signal propagation direction, and obtain a sound pressure distribution diagram at the moment of maximum global instantaneous sound pressure inside the target duplex helical gear;

[0031] The defect focal area of ​​the target duplex helical gear when metallurgical defects occur is determined based on the sound pressure distribution diagram.

[0032] In some embodiments, performing sound source focusing positioning in the defect focus area by using the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear specifically includes:

[0033] Determine the focus center of the defect focus area according to the positioning auxiliary signal;

[0034] The sound source of the defect focus area is located according to the focus center to obtain the defect position of the metallurgical defect in the target double helical gear.

[0035] In some embodiments, the gear die used for the powder metallurgy duplex helical gear is a gear die with a friction plate added to the punch base.

[0036] In a second aspect, the present application provides a control system for a powder metallurgy double helical gear, comprising:

[0037] An acquisition module is used to collect the acoustic wave signals of the target double helical gear during the powder metallurgy process, and then obtain historical acoustic wave data;

[0038] A processing module, used for performing frequency domain conversion on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, and determining the confidence distribution entropy of each frequency domain signal through the signal coupling between the frequency domain signals;

[0039] The processing module is also used to extract the defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data, and then determine the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when the metallurgical defect occurs according to each confidence distribution entropy and the defect coupling characteristics;

[0040] The processing module is further used to obtain the reverse propagation path of the positioning auxiliary signal, and then determine the defect focus area of ​​the target double helical gear when the metallurgical defect occurs according to the reverse propagation path and the structural parameters of the target double helical gear;

[0041] The processing module is also used to perform sound source focusing positioning in the defect focus area through the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear;

[0042] An execution module is used to perform real-time compensation control on the powder metallurgy of the target duplex helical gear based on the defect position.

[0043] In some embodiments, the gear die used for the powder metallurgy duplex helical gear is a gear die with a friction plate added to the punch base.

[0044] In a third aspect, the present application provides a gear mold, which includes a control system of the above-mentioned powder metallurgy double helical gear.

[0045] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0046] In the control method, system and gear mold of powder metallurgy double helical gear provided by the present application, the acoustic wave signal of the target double helical gear in the powder metallurgy process is collected to obtain historical acoustic wave data; each acoustic wave signal in the historical acoustic wave data is converted into the frequency domain to obtain multiple frequency domain signals, and the confidence distribution entropy of each frequency domain signal is determined by the signal coupling between each frequency domain signal; the defect coupling characteristics when the acoustic wave signal coupling occurs in the powder metallurgy process of the target double helical gear are extracted from the historical acoustic wave data, and then the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when the metallurgical defect is generated is determined according to each confidence distribution entropy and the defect coupling characteristics; the reverse propagation path of the positioning auxiliary signal is obtained, and then the defect focusing domain of the target double helical gear when the metallurgical defect is generated is determined according to the reverse propagation path and the structural parameters of the target double helical gear, and the sound source is focused and positioned in the defect focusing domain by the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target double helical gear; the powder metallurgy of the target double helical gear is compensated and controlled in real time based on the defect position.

[0047] It can be seen that in the present application, real-time compensation control is performed on the powder metallurgy of the target double helical gear based on the defect position; firstly, the confidence distribution entropy is determined to obtain an indicator that measures the frequency domain signal complexity and randomness of the acoustic signal in the historical acoustic wave data, and key signal features can be extracted from a large amount of historical acoustic wave data, and then all key signal features can be used to more accurately screen out possible time domain defect signals, thereby improving the accuracy of the detection capability of defects in the target double helical gear during the powder metallurgy process; secondly, the defect focus domain is determined to obtain the possible location range of the metallurgical defects generated by the target double helical gear during the powder metallurgy process, which can help the system further narrow the defect search range, thereby more accurately locating metallurgical defects, and then The corresponding process adjustment and correction can be immediately made to the target duplex helical gear to reduce the generation and spread of defects; then, the sound source is focused and positioned in the defect focusing domain through the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear, and the powder metallurgy of the target duplex helical gear is compensated and controlled in real time based on the defect position; and a friction plate (i.e., a plane bearing) is added to the punch base of the gear mold used in the metallurgical process to ensure that the demolding of the gear mold is consistent with the rotation of the product, thereby smoothly demolding; in summary, based on the above scheme, real-time positioning and correction of the defects of the duplex helical gear can be achieved by using acoustic emission, which can reduce the defect rate in the powder metallurgy process of the duplex helical gear, thereby improving the accuracy of the finished duplex helical gear. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is an exemplary flow chart of a control method of a powder metallurgy double helical gear according to some embodiments of the present application;

[0049] Figure 2 is an exemplary flow chart of determining confidence distribution entropy according to some embodiments of the present application;

[0050] Figure 3 is an exemplary flow chart of determining a positioning auxiliary signal according to some embodiments of the present application;

[0051] Figure 4 is a schematic structural diagram of a control system of a powder metallurgy double helical gear according to some embodiments of the present application;

[0052] Figure 5 It is a structural schematic diagram of a computer device for implementing a control method for powder metallurgy double helical gears according to some embodiments of the present application. DETAILED DESCRIPTION

[0053] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a control method of a powder metallurgy double helical gear according to some embodiments of the present application. The control method 100 of a powder metallurgy double helical gear mainly includes the following steps:

[0054] In step 101, the acoustic wave signals of the target duplex helical gear during the powder metallurgy process are collected to obtain historical acoustic wave data.

[0055] It should be noted that, in the present application, the historical acoustic wave data is a data set consisting of all acoustic wave signals generated during the powder metallurgy process of the target duplex bevel gear; in specific implementation, the acoustic wave signals within a preset time period (half an hour by default) can be collected through a sensor array pre-arranged around the target duplex bevel gear, and the collection of all collected acoustic wave signals is used as the historical acoustic wave data, wherein the sensor array is a collection consisting of multiple (10 by default) acoustic wave sensors (such as piezoelectric sensors).

[0056] In step 102, each sound wave signal in the historical sound wave data is converted into a frequency domain to obtain a plurality of frequency domain signals, and the confidence distribution entropy of each frequency domain signal is determined by the signal coupling between the frequency domain signals.

[0057] In some embodiments, frequency domain conversion is performed on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, which can be achieved by using the following steps:

[0058] Selecting a sound wave signal from the historical sound wave data as a selected sound wave signal;

[0059] The selected sound wave signal is converted from the time domain to the frequency domain by a signal conversion algorithm to obtain a frequency domain signal of the selected sound wave signal;

[0060] Continue to determine the frequency domain signal of the remaining sound wave signal.

[0061] It should be noted that, in the present application, the frequency domain signal is a signal used to describe the amplitude and phase information of the sound wave signal at different frequencies; in specific implementation, first, a sound wave signal can be selected from the historical sound wave data as the selected sound wave signal, and the selected sound wave signal can be converted from the time domain to the frequency domain through the signal conversion algorithm in the prior art (such as Fourier transform), and the Fourier transform of the selected sound wave signal is used as the frequency domain signal of the selected sound wave signal, and then, the above steps are repeated to continue to obtain the frequency domain signals of the remaining sound wave signals in the historical sound wave data.

[0062] In some embodiments, reference Figure 2 , which is an exemplary flow chart of determining the confidence distribution entropy according to some embodiments of the present application. In the present application, the confidence distribution entropy of each frequency domain signal is determined by the signal coupling between each frequency domain signal, which can be implemented by the following steps:

[0063] In step 1021, the signal coupling between the frequency domain signals is determined;

[0064] In step 1022, a frequency domain signal is selected from all frequency domain signals as a selected frequency domain signal, and a frequency domain signal distribution entropy of the selected frequency domain signal is determined;

[0065] In step 1023, the coupling coefficient of the selected frequency domain signal is determined by the signal coupling between the selected frequency domain signal and other frequency domain signals;

[0066] In step 1024, the confidence distribution entropy of the selected frequency domain signal is determined according to the frequency domain signal distribution entropy and the coupling coefficient;

[0067] In step 1025 , the confidence distribution entropy of the remaining frequency domain signal continues to be determined.

[0068] It should be noted that, in the present application, confidence distribution entropy is an indicator for measuring the complexity and randomness of frequency domain signals; signal coupling indicates the degree of mutual coupling interference between acoustic signals when transmitted between the double helical gears and the sensor. The higher the signal coupling, the greater the mutual coupling interference between the two acoustic signals, and the lower the signal coupling, the smaller the mutual coupling interference between the two acoustic signals; frequency domain signal distribution entropy is a parameter that describes the degree of confusion of the amount of information in the acoustic signal in the frequency domain; the coupling coefficient is an indicator for measuring the degree of coupling interference of the acoustic signal by other acoustic signals when the acoustic signal is transmitted between the sensors of the double helical gears.

[0069] In specific implementation, first, the signal coupling between each frequency domain signal can be determined; secondly, a frequency domain signal is selected from all frequency domain signals, and the square of the amplitude of the frequency domain signal at each frequency component is divided by the total number of frequency components to obtain the probability density value of the frequency domain signal, and then each probability density value is multiplied by the logarithm of the probability density value with base ten to obtain the logarithmic product of the probability density value, and the inverse of the sum of all logarithmic products is used as the frequency domain signal distribution entropy of the frequency domain signal; then, the signal coupling between the frequency domain signal and all other frequency domain signals is added, and then divided by the total number of frequency domain signals, and the obtained value is used as the coupling coefficient of the frequency domain signal; finally, the product of the coupling coefficient of the frequency domain signal and the frequency domain signal distribution entropy is used as the confidence distribution entropy of the frequency domain signal, and the above steps are repeated to obtain the confidence distribution entropy of the remaining frequency domain signals.

[0070] In some embodiments, determining the signal coupling between the frequency domain signals may be achieved by using the following steps:

[0071] Selecting a frequency domain signal as a selected frequency domain signal;

[0072] determining the autopower spectral density of the selected frequency domain signal according to the amplitude of the selected frequency domain signal at each frequency component;

[0073] determining a cross power spectral density between a selected frequency domain signal and other frequency domain signals;

[0074] The signal coupling between the selected frequency domain signal and other frequency domain signals is determined according to the auto-power spectrum density and each cross-power spectrum density, and the signal coupling between the next selected frequency domain signal and other frequency domain signals is further determined, thereby obtaining the signal coupling between each frequency domain signal.

[0075] It should be noted that, in the present application, other frequency domain signals are the remaining frequency domain signals in all frequency domain signals except the selected frequency domain signal, the auto-power spectral density is a parameter that describes the energy distribution of the sound wave signal in the frequency domain, and can be used to analyze the frequency characteristics of the sound wave signal; the cross-power spectral density is a parameter that describes the power correlation between two sound wave signals in the frequency domain; in specific implementation, first, a frequency domain signal is selected as the selected frequency domain signal, and the existing discrete Fourier transform algorithm can be used to calculate the amplitude of the selected frequency domain signal at each frequency component, and the quotient of the sum of the squares of all amplitudes and the total number of frequency components is taken as the auto-power spectral density of the selected frequency domain signal; then, for each frequency domain signal in the other frequency domain signals, the selected frequency domain signal is The product of the amplitude of the frequency domain signal at each frequency component is added, the sum obtained is divided by the total number of frequency components, and the obtained value is used as the cross-power spectral density between the selected frequency domain signal and the frequency domain signal; finally, the selected frequency domain signal is multiplied by the auto-power spectral density of the frequency domain signal to obtain the density product, and the square of the cross-power spectral density between the selected frequency domain signal and the frequency domain signal is divided by the density product, and the quotient obtained is used as the signal coupling between the two frequency domain signals. The signal coupling between the selected frequency domain signal and each of the other frequency domain signals can be obtained in the above manner, and the signal coupling between the next selected frequency domain signal and other frequency domain signals can be determined, and then the signal coupling between each frequency domain signal can be obtained.

[0076] In step 103, the defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process are extracted from the historical acoustic wave data, and then the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when the metallurgical defect occurs is determined according to each confidence distribution entropy and the defect coupling characteristics.

[0077] In some embodiments, extracting the defect coupling characteristics of the target duplex helical gear when the acoustic wave signal coupling occurs during the powder metallurgy process from the historical acoustic wave data can be achieved by the following steps:

[0078] Acquire the acoustic signal dataset of known metallurgical defects in the metallurgical process of duplex helical gears;

[0079] Extracting features from each acoustic wave signal in the acoustic wave signal data set to obtain a defect feature library of known metallurgical defects;

[0080] The defect coupling characteristics of the target duplex helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process are determined according to the historical acoustic wave data and the defect feature library.

[0081] It should be noted that, in the present application, the defect coupling feature is the feature of the acoustic wave signals of multiple metallurgical defects of the target duplex helical gear during the powder metallurgy process after mutual coupling and interference; the acoustic wave signal data set is a data set of acoustic wave signals emitted by known metallurgical defects occurring in the metallurgical process of the duplex helical gear; and the defect feature library is a data set containing feature information of various known defects occurring in the powder metallurgy process of the duplex helical gear.

[0082] In specific implementation, first, known types of metallurgical defects (such as cracks and holes) can be introduced by operating on the double helical gears respectively, and the acoustic wave signals of each defect are collected by a sensor array pre-arranged around the double helical gears, and then the collected acoustic wave signals are labeled with the corresponding defect positions and types to generate a labeled data set, and the data set is used as the acoustic wave signal data set of known metallurgical defects; then, for each acoustic wave signal in the acoustic wave signal data set, a filter (such as mean filtering) is first used to remove the noise in the acoustic wave signal, and then a wavelet function suitable for analyzing the acoustic wave signal (such as Morlet wavelet) is used to perform a continuous wavelet transform on the acoustic wave signal to obtain a time-frequency curve of the acoustic wave signal. The time-frequency curve is a curve that describes the energy distribution of the acoustic wave signal at different times and frequencies, and the time-frequency curve is used as the feature of the acoustic wave signal. The feature of each acoustic wave signal in the acoustic wave signal data set can be obtained in the above manner, and the set consisting of the features of all the obtained acoustic wave signals is used as a defect feature library of known metallurgical defects.

[0083] In addition, in a specific implementation, the defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process can be determined according to the historical acoustic wave data and the defect feature library. This can be achieved in the following manner, namely: first, a filter (such as a mean filter) can be used to remove the noise in the historical acoustic wave data. Then, for each acoustic wave signal in the historical acoustic wave data, a wavelet function suitable for analyzing the acoustic wave signal (such as a Morlet wavelet) is used to perform a continuous wavelet transform on the acoustic wave signal to obtain a time-frequency curve of the acoustic wave signal. The continuous wavelet transform can decompose the acoustic wave signal into different frequency components and analyze their changes in time, which is convenient for subsequent analysis. The similarity between the acoustic wave signal and each acoustic wave signal in the defect feature library is analyzed, and the collection of time-frequency curves of all acoustic wave signals in the historical acoustic wave data is used as the feature of the historical acoustic wave data. Subsequently, the feature similarity between the feature of each acoustic wave signal in the defect feature library and the feature of the historical acoustic wave data is determined, and the features of all acoustic wave signals corresponding to feature similarities greater than a preset similarity threshold (the default value is 0.7) are synthesized into a new time-frequency curve through existing filtering synthesis methods (such as basic additive synthesis), and the time-frequency curve is used as the defect coupling feature of the target double helical gear when acoustic wave signal coupling occurs in the powder metallurgy process.

[0084] Preferably, in some embodiments, determining the feature similarity between the feature of each acoustic wave signal in the defect feature library and the feature of the historical acoustic wave data can be achieved in the following manner, namely: first, for the feature corresponding to each acoustic wave signal in the defect feature library, the existing discrete Fourier transform algorithm is used to calculate the amplitude spectrum of the feature, and the amplitude spectrum is flattened into a one-dimensional vector, and the one-dimensional vector is used as the feature vector of the acoustic wave signal. The feature vector of each acoustic wave signal in the defect feature library can be obtained by the above method; then, for each time-frequency curve in the feature of the historical acoustic wave data, the existing discrete Fourier transform algorithm is used to calculate the amplitude spectrum of the time-frequency curve, and the amplitude spectrum is flattened into a one-dimensional vector, and the one-dimensional vector is used as the amplitude vector of the time-frequency curve. The amplitude vector of each time-frequency curve in the feature of the historical acoustic wave data can be obtained by the above method, and the set of all amplitude vectors is used as the amplitude vector of the historical acoustic wave data. amplitude vector set; finally, selecting an acoustic wave signal in the defect feature library as the selected acoustic wave signal, obtaining the feature vector of the selected acoustic wave signal, for each amplitude vector in the amplitude vector set of the historical acoustic wave data, firstly calculating the dot product and the modulus of the feature vector and the amplitude vector respectively, then taking the product of the feature vector and the dot product of the amplitude vector as the dot product product, taking the product of the feature vector and the modulus of the amplitude vector as the modulus product, and taking the ratio between the dot product product and the modulus product as the cosine similarity between the feature vector and the amplitude vector. In the above manner, the cosine similarity between the feature vector of the selected acoustic wave signal and each amplitude vector in the amplitude vector set of the historical acoustic wave data can be obtained, and the average of all the cosine similarities obtained is taken as the feature similarity between the feature of the selected acoustic wave signal and the feature of the historical acoustic wave data, and then repeating the above steps to continue to obtain the feature similarity between the features of the remaining acoustic wave signals in the defect feature library and the features of the historical acoustic wave data.

[0085] In some embodiments, reference Figure 3 , which is an exemplary flow chart of determining a positioning auxiliary signal according to some embodiments of the present application. In the present application, the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs is determined according to each confidence distribution entropy and the defect coupling feature, which can be implemented by the following steps:

[0086] In step 1031, determining the characteristic distribution entropy of the defect coupling characteristic;

[0087] In step 1032, characteristic mutual information between the corresponding acoustic wave signal in the historical acoustic wave data and the defect coupling feature is determined according to each confidence distribution entropy and the characteristic distribution entropy;

[0088] In step 1033, a time domain defect signal in the target duplex helical gear is screened out from the historical acoustic wave data according to all feature mutual information;

[0089] In step 1034, a positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs is determined based on all the emission signal segments in the time domain defect signal.

[0090] It should be noted that, in the present application, the time domain defect signal is an acoustic wave signal that can reflect the defects of the target duplex helical gear during the powder metallurgy process; the characteristic distribution entropy is an indicator to measure the complexity and randomness of the defect coupling characteristics, reflecting the energy distribution of the defect coupling characteristics in the frequency domain; the characteristic mutual information is a parameter that describes the similarity between the acoustic wave signal in the historical acoustic wave data and the defect coupling characteristics of the target duplex helical gear. The larger the characteristic mutual information, the more similar the acoustic wave signal is to the defect coupling characteristics of the target duplex helical gear, and the greater the possibility that it is an acoustic wave signal emitted by the metallurgical defects on the target duplex helical gear. The smaller the characteristic mutual information, the more dissimilar the acoustic wave signal is to the defect coupling characteristics of the target duplex helical gear, and the smaller the possibility that it is an acoustic wave signal emitted by the metallurgical defects on the target duplex helical gear.

[0091] In specific implementation, first, the characteristic distribution entropy of the defect coupling feature can be determined; secondly, the frequency domain signal distribution entropy of the frequency domain signal corresponding to each acoustic wave signal in the historical acoustic wave data can be obtained, and the inverse of the difference between the distribution entropy of each frequency domain signal and the characteristic distribution entropy can be used as the characteristic mutual information between the corresponding acoustic wave signal and the defect coupling feature; then, the largest characteristic mutual information is selected from all the characteristic mutual information, and the acoustic wave signal corresponding to the largest characteristic mutual information in the historical acoustic wave data is used as the time domain defect signal in the target double helical gear; finally, the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when metallurgical defects are generated is determined according to all the transmitted signal segments in the time domain defect signal.

[0092] Preferably, in some embodiments, determining the characteristic distribution entropy of the defect coupling feature can be achieved in the following manner, namely: calculating the power at each time-frequency point in the defect coupling feature by short-time Fourier transform in the prior art, and using the obtained powers as the time-frequency energy value of the corresponding time-frequency point; then, for each time-frequency energy value, using the ratio of the time-frequency energy value to the sum of all time-frequency energy values ​​as the probability value of the time-frequency energy value, and using the inverse of the product of the probability value and the natural logarithm of the probability value as the entropy contribution of the time-frequency energy value, wherein the entropy contribution is the contribution of the time-frequency energy value to the characteristic distribution entropy, and the influence of the power of the acoustic wave signal at each time-frequency point on the characteristic distribution entropy can be quantified. The entropy contribution of each time-frequency energy value can be obtained in the above manner; finally, the sum obtained by adding up all entropy contributions is used as the characteristic distribution entropy of the defect coupling feature.

[0093] In addition, in some embodiments, determining the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs according to all the emission signal segments in the time domain defect signal can be implemented by the following steps:

[0094] Time-reversing all transmitted signal segments in the time-domain defect signal to obtain a time-reversed signal;

[0095] The positioning auxiliary signal of the metallurgical defect in the target double helical gear is determined by the timing information of the time reversal signal.

[0096] It should be noted that, in the present application, the positioning auxiliary signal is a signal that assists the positioning process of the target defect position; in specific implementation, first, the time axis of the time domain defect signal can be reversed, and the obtained new signal can be used as the time reversal signal. For example, the time domain defect signal is s(t)=[A,B,C,D,E], and after time reversal processing, the time reversal signal s(-t)=[E,D,C,B,A] is obtained; wherein the time reversal signal is a new signal obtained after time reversing the time domain defect signal; then, all the transmitted signal segments in the time reversal signal are filtered through an existing filter (such as a bandpass filter, the passband can be defaulted to 350KHz-450KHz), and the filtered transmitted signal segments are analyzed to obtain the earliest arrival time of the time reversal signal, the earliest arrival time is the arrival time of the first obvious energy peak in the time reversal signal, and a segment after the earliest arrival time (default is 180) is intercepted in the time reversal signal. ) time period signal is used as the positioning auxiliary signal.

[0097] In step 104, a reverse propagation path of the positioning auxiliary signal is obtained, and then a defect focal area of ​​the target double helical gear when a metallurgical defect occurs is determined based on the reverse propagation path and the structural parameters of the target double helical gear.

[0098] It should be noted that the reverse propagation path in the present application is the propagation path of the positioning auxiliary signal when it propagates in reverse inside the target double bevel gear; in specific implementation, the positioning auxiliary signal can be re-transmitted to the target double bevel gear through the sensor array of step 101, and the propagation path of the positioning auxiliary signal when it propagates in reverse inside the target double bevel gear is recorded, and the propagation path is used as the reverse propagation path of the positioning auxiliary signal.

[0099] In some embodiments, the defect focal area of ​​the target duplex helical gear when metallurgical defects are generated is determined according to the reverse propagation path and the structural parameters of the target duplex helical gear, which can be achieved by the following steps:

[0100] Obtaining structural parameters of the target double helical gear;

[0101] Determining the signal source position and signal propagation direction of the target duplex helical gear when a metallurgical defect occurs according to the reverse propagation path;

[0102] Transiently aggregate the metallurgical defects of the target duplex helical gear according to the structural parameters, the signal source position and the signal propagation direction, and obtain a sound pressure distribution diagram at the moment of maximum global instantaneous sound pressure inside the target duplex helical gear;

[0103] The defect focal area of ​​the target duplex helical gear when metallurgical defects occur is determined based on the sound pressure distribution diagram.

[0104] It should be noted that, in the present application, the defect focus area is the area where the positioning auxiliary signal of the metallurgical defect in the target double helical gear is focused inside the target double helical gear, indicating the position range where the defect may exist; the sound pressure distribution diagram is a graph used to visualize and analyze the sound pressure level distribution in the sound field, which can help intuitively understand the propagation characteristics of the sound wave in space;

[0105] In the specific implementation, first, the setting parameters (such as shape, size, tooth surface curvature, density and elastic modulus) input when the target double helical gear is subjected to powder metallurgy are obtained, and the obtained setting parameters are used as the structural parameters of the target double helical gear; secondly, a geometric model of the target double helical gear can be created in the COMSOL simulation software according to the structural parameters of the target double helical gear, and the geometric model is divided into finite element mesh units (the default finite element is a quadrilateral element), and the position and direction of the signal loading are set according to the emission position and emission direction of the positioning auxiliary signal in the reverse propagation path, and the position is used as the target The signal source position of the double helical gear when the metallurgical defect occurs is determined, and this direction is used as the signal propagation direction of the target double helical gear when the metallurgical defect occurs; then, the positioning auxiliary signal can be imported into the signal loading point in the COMSOL simulation software according to the signal source position and the signal propagation direction, and then the simulation software is run to perform transient analysis on the geometric model of the target double helical gear to obtain the sound pressure distribution diagram at the moment of the maximum global instantaneous sound pressure inside the target double helical gear; finally, the set of signal energy focusing areas in the sound pressure distribution diagram is used as the defect focusing area when the metallurgical defect occurs in the target double helical gear.

[0106] In step 105, the sound source is focused and positioned in the defect focus area by using the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear.

[0107] In some embodiments, the sound source focusing positioning is performed in the defect focus area by using the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear, which can be achieved by the following steps:

[0108] Determine the focus center of the defect focus area according to the positioning auxiliary signal;

[0109] The sound source of the defect focus area is located according to the focus center to obtain the defect position of the metallurgical defect in the target double helical gear.

[0110] It should be noted that, in the present application, the defect position is the position of the defect generated in the target duplex helical gear during the powder metallurgy process, and the shape and size of the defect generated on the target duplex helical gear can be further determined through the defect position, so as to correct the defect in real time; the focusing center is the set of coordinates of the center point of the energy focusing area in the defect focusing domain, indicating the position of the defect that may exist on the target duplex helical gear; in specific implementation, first, the coordinates of the global instantaneous sound pressure maximum value of the positioning auxiliary signal in each signal energy focusing area in the defect focusing domain can be identified, and the coordinates can be used as the candidate defect position of the target duplex helical gear, and then the set of all candidate defect positions can be used as the focusing center of the defect focusing domain; then, the candidate defect position with the largest peak value in the corresponding energy focusing area can be selected in the focusing center as the defect position of the metallurgical defect in the target duplex helical gear.

[0111] In step 106, real-time compensation control is performed on the powder metallurgy of the target duplex helical gear based on the defect position.

[0112] In some embodiments, the real-time compensation control of the powder metallurgy of the target duplex helical gear based on the defect position can be implemented by the following steps:

[0113] Determine the defect characteristics of the target duplex helical gear at the defect position;

[0114] According to the defect characteristics, the defects at the defect positions during the powder metallurgy process of the target duplex helical gear are corrected in real time.

[0115] It should be noted that, in the present application, the defect feature is the appearance feature of the defect that appears in the target duplex helical gear during the powder metallurgy process, which may include the shape and size of the defect; in specific implementation, first, a scanning electron microscope can be used to scan the surroundings of the defect position on the target duplex helical gear to obtain a defect image on the target duplex helical gear, and an image processing algorithm (such as edge detection and image segmentation algorithm) is used to determine the size and shape of the defect in the image, and then the complex number composed of the size and shape is used as the defect feature of the target duplex helical gear; subsequently, in the post-processing process of powder metallurgy, the defect at the defect position can be corrected according to the defect feature.

[0116] In addition, in another aspect of the present application, in some embodiments, the present application provides a control system for a powder metallurgy double helical gear, referring to Figure 4, which is a schematic diagram of the structure of a control system for a powder metallurgy double helical gear according to some embodiments of the present application. The control system 400 for the powder metallurgy double helical gear includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0117] The acquisition module 401 in the present application is mainly used to acquire the acoustic wave signal of the target double helical gear during the powder metallurgy process, and then obtain the historical acoustic wave data;

[0118] Processing module 402, in the present application, the processing module 402 is mainly used to perform frequency domain conversion on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, and determine the confidence distribution entropy of each frequency domain signal through the signal coupling between each frequency domain signal;

[0119] It should be noted that the processing module 402 in the present application is also used to extract the defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data, and then filter out the time domain defect signal in the target double helical gear from the historical acoustic wave data according to each confidence distribution entropy and the defect coupling characteristics;

[0120] In addition, it should be noted that the processing module 402 in the present application is also used to determine the positioning auxiliary signal of the metallurgical defect in the target double helical gear according to all the transmitted signal segments in the time domain defect signal, determine the defect focus area of ​​the target double helical gear when the metallurgical defect is generated according to the reverse propagation path and the structural parameters of the target double helical gear, perform sound source focusing positioning in the defect focus area through the positioning auxiliary signal, and obtain the defect position of the metallurgical defect in the target double helical gear;

[0121] Execution module 403, in the present application, the execution module 403 is mainly used to perform real-time compensation control on the powder metallurgy of the target double helical gear based on the defect position.

[0122] In other aspects of the present application, a gear mold is also provided, and the gear mold includes a control system of the above-mentioned powder metallurgy double helical gear.

[0123] It should be noted that the gear mold used for the powder metallurgy double helical gear in this application is a gear mold with a friction plate added to the punch base. The setting of the friction plate can ensure that the demoulding of the gear mold is consistent with the rotation of the product and demoulding is smooth. At the same time, acoustic emission is used to perform real-time positioning and correction of defects in the double helical gear, which can reduce the defect rate in the powder metallurgy double helical gear process and thus improve the accuracy of the finished double helical gear.

[0124] In some embodiments, reference Figure 5, which is a schematic diagram of the structure of a computer device for implementing a control method for a powder metallurgy double helical gear according to some embodiments of the present application. The control method for a powder metallurgy double helical gear in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0125] The processor 501 may be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0126] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0127] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0128] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The control method of the powder metallurgy double helical gear in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0129] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0130] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0131] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0132] In addition, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the control method of the powder metallurgy double helical gear is implemented.

[0133] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A control method for powder metallurgy double helical gears, characterized in that: The steps include: Collect the acoustic wave signals of the target double helical gear during the powder metallurgy process, and then obtain historical acoustic wave data; Performing frequency domain conversion on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, and determining the confidence distribution entropy of each frequency domain signal by the signal coupling between the frequency domain signals, wherein the confidence distribution entropy is an indicator for measuring the complexity and randomness of the frequency domain signal; Extracting defect coupling characteristics of the target double helical gear when acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data, and then determining the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when metallurgical defects occur according to the confidence distribution entropy of each frequency domain signal and the defect coupling characteristics; Acquire the reverse propagation path of the positioning auxiliary signal, and then determine the defect focus area of ​​the target double helical gear when metallurgical defects occur according to the reverse propagation path and the structural parameters of the target double helical gear; By using the positioning auxiliary signal, sound source focusing positioning is performed in the defect focusing area to obtain the defect position of the metallurgical defect in the target duplex helical gear; Based on the defect position, real-time compensation control is performed on the powder metallurgy of the target duplex helical gear; Among them, determining the confidence distribution entropy of each frequency domain signal through the signal coupling between each frequency domain signal specifically includes: Determine the signal coupling between various frequency domain signals; Selecting a frequency domain signal from all frequency domain signals as a selected frequency domain signal, and determining a frequency domain signal distribution entropy of the selected frequency domain signal; Determining a coupling coefficient of a selected frequency domain signal by signal coupling between the selected frequency domain signal and other frequency domain signals; Determining the confidence distribution entropy of the selected frequency domain signal according to the frequency domain signal distribution entropy and the coupling coefficient; Continue to determine the confidence distribution entropy of the remaining frequency domain signal.

2. The method according to claim 1, characterized in that The defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process are extracted from the historical acoustic wave data, specifically including: Acquire the acoustic signal dataset of known metallurgical defects in the metallurgical process of duplex helical gears; Extracting features from each acoustic wave signal in the acoustic wave signal data set to obtain a defect feature library of known metallurgical defects; The defect coupling characteristics of the target duplex helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process are determined according to the historical acoustic wave data and the defect feature library.

3. The method according to claim 1, characterized in that Determining the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs according to the confidence distribution entropy of each frequency domain signal and the defect coupling characteristics specifically includes: Determining a characteristic distribution entropy of the defect coupling characteristic; Determining the characteristic mutual information between the corresponding acoustic wave signal in the historical acoustic wave data and the defect coupling feature according to the confidence distribution entropy of each frequency domain signal and the characteristic distribution entropy; Screening out the time domain defect signal in the target duplex helical gear from the historical acoustic wave data according to all the feature mutual information; A positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when a metallurgical defect occurs is determined according to all the emission signal segments in the time domain defect signal.

4. The method according to claim 1, characterized in that Determining the defect focus area of ​​the target double helical gear when metallurgical defects are generated according to the reverse propagation path and the structural parameters of the target double helical gear specifically includes: Obtaining structural parameters of the target double helical gear; Determining the signal source position and signal propagation direction of the target duplex helical gear when a metallurgical defect occurs according to the reverse propagation path; Transiently aggregate the metallurgical defects of the target duplex helical gear according to the structural parameters, the signal source position and the signal propagation direction, and obtain a sound pressure distribution diagram at the moment of maximum global instantaneous sound pressure inside the target duplex helical gear; The defect focal area of ​​the target duplex helical gear when metallurgical defects occur is determined based on the sound pressure distribution diagram.

5. The method according to claim 1, characterized in that The method of performing sound source focusing positioning in the defect focus area by using the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear specifically includes: Determine the focus center of the defect focus area according to the positioning auxiliary signal; The sound source of the defect focus area is located according to the focus center to obtain the defect position of the metallurgical defect in the target double helical gear.

6. A control system for a powder metallurgy double helical gear, which uses the method described in any one of claims 1 to 5 to control the powder metallurgy double helical gear, characterized in that: The system includes: An acquisition module is used to collect the acoustic wave signals of the target double helical gear during the powder metallurgy process, and then obtain historical acoustic wave data; A processing module, used for performing frequency domain conversion on each sound wave signal in the historical sound wave data to obtain multiple frequency domain signals, and determining the confidence distribution entropy of each frequency domain signal through the signal coupling between the frequency domain signals; The processing module is also used to extract the defect coupling characteristics of the target double helical gear when the acoustic wave signal coupling occurs in the powder metallurgy process from the historical acoustic wave data, and then determine the positioning auxiliary signal of the target double helical gear in the historical acoustic wave data when the metallurgical defect occurs according to the confidence distribution entropy of each frequency domain signal and the defect coupling characteristics; The processing module is further used to obtain the reverse propagation path of the positioning auxiliary signal, and then determine the defect focus area of ​​the target double helical gear when the metallurgical defect occurs according to the reverse propagation path and the structural parameters of the target double helical gear; The processing module is also used to perform sound source focusing positioning in the defect focus area through the positioning auxiliary signal to obtain the defect position of the metallurgical defect in the target duplex helical gear; An execution module is used to perform real-time compensation control on the powder metallurgy of the target duplex helical gear based on the defect position.

7. A gear mold, characterized in that: A control system comprising the powder metallurgy double helical gears as described in claim 6.

8. The gear mold according to claim 7, characterized in that: The gear die is a gear die with a punch base having a flat bearing added thereto.

Images