Intelligent monitoring method and system for hardware product automatic assembly production line

Abstract

The invention relates to an intelligent monitoring technology, and discloses an intelligent monitoring method and system for an automatic hardware product assembly production line, and the method comprises the steps: collecting the operation parameters and vibration parameters of production line equipment in real time, carrying out the resonance signal recognition of the vibration parameters of the equipment, completing the resonance denoising according to the resonance signal, and obtaining the denoised vibration parameters; and performing stability analysis by combining the de-noising vibration parameter and the equipment operation parameter to obtain a stability parameter, judging whether the stability parameter exceeds a preset stability threshold, and if the stability parameter is smaller than or equal to the stability threshold, triggering an equipment instability alarm. Otherwise, continuously collecting product images in the production line to generate a sequence, analyzing product consistency based on the sequence to obtain a consistency index, judging whether the consistency index exceeds a preset consistency threshold, if so, returning to continuously collect equipment parameters, and if not, triggering a product defect alarm. The monitoring efficiency of the hardware product automatic assembly production line can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring, and particularly to an intelligent monitoring method and system for an automated assembly production line of hardware products. Background Art

[0002] As a core link in modern manufacturing, the efficient and stable operation of the automated assembly production line of hardware products has a decisive impact on product quality and production efficiency. With the advancement of Industry 4.0 and intelligent manufacturing, the hardware industry is facing the following challenges.

[0003] In existing intelligent monitoring methods, vibration suppression algorithms (such as input shaping, PID control) are mostly aimed at single devices, without considering the coupling effect of vibrations in multiple production line links, resulting in a decrease in 3D modeling accuracy and an inability to process high-dimensional heterogeneous data, with time-consuming feature extraction. There are also methods that perform fault prediction based on fault prediction models of historical data (such as SVM, random forest), and this method has a high prediction error rate. Therefore, it is necessary to study a method to improve the efficiency and accuracy of monitoring the automated assembly production line of hardware products. Summary of the Invention

[0004] The present invention provides an intelligent monitoring method and system for an automated assembly production line of hardware products, and its main purpose is to solve the problems of low efficiency and low accuracy in existing monitoring methods for automated assembly production lines of hardware products.

[0005] To achieve the above object, an intelligent monitoring method for an automated assembly production line of hardware products provided by the present invention includes: Real-time collecting the device operation parameters and device vibration parameters in the assembly production line; Identifying resonance signals from the device vibration parameters, and performing resonance denoising processing on the device vibration parameters according to the resonance signals to obtain denoised vibration parameters; Performing device stability analysis based on the denoised vibration parameters and the device operation parameters to obtain stability parameters; Judging whether the stability parameter is greater than a preset stability threshold; If the stability parameter is less than or equal to the stability threshold, device instability warning is performed; If the stability parameter is greater than the stability threshold, continuously collect product images in the assembly production line to obtain a product image sequence; Performing product consistency analysis based on the product image sequence to obtain a consistency index; Judging whether the consistency index is greater than a preset consistency threshold; If the consistency index is greater than the consistency threshold, return the steps of acquiring the equipment operation parameters and equipment vibration parameters in the real-time acquisition assembly production line; If the consistency index is less than or equal to the consistency threshold, perform product defect warning.

[0006] Optionally, the resonance signal identification for the equipment vibration parameters includes: Perform smoothing denoising processing on each group of vibration parameters in the equipment vibration parameters to obtain denoised vibration parameters; Extract the spectral features of each group of denoised vibration parameters; Identify the peak positions of each spectral feature; Identify the peak correlation between all spectral features according to the peak positions to obtain a peak correlation identification result; According to the correlation identification res Confirm the resonance frequency and resonance amplitude according to the result to obtain a resonance signal.

[0007] Optionally, the identifying the peak correlation between all spectral features according to the peak positions to obtain a peak correlation identification result includes: Traverse the peak sets of any two groups of spectral features according to the peak positions, and calculate the frequency difference between each pair of peaks; Confirm that the peak pairs with a frequency difference less than the preset frequency difference threshold are relevant candidate peak pairs; Calculate the amplitude difference between each pair of peaks in the relevant candidate peak pairs; Confirm that the peak pairs with an amplitude difference less than the preset amplitude difference threshold are relevant peak pairs to obtain a correlation identification result.

[0008] Optionally, the resonance denoising processing of the equipment vibration parameters according to the resonance signal to obtain denoised vibration parameters includes: Perform wavelet decomposition on the equipment vibration parameters to obtain wavelet coefficients of different scales and frequency subbands; Perform energy distribution analysis on the wavelet coefficients according to the resonance signal, and confirm the subband where the resonance signal is located according to the analysis result to obtain a resonance subband; Perform threshold processing on the wavelet coefficients of the resonance subband to obtain processed wavelet coefficients; Perform wavelet reconstruction on the processed wavelet coefficients to obtain denoised vibration parameters.

[0009] Optionally, the equipment stability analysis according to the denoised vibration parameters and the equipment operation parameters to obtain stability parameters includes: Construct an equipment coupling effect matrix according to the denoised vibration parameters and the equipment operation parameters; Perform window partitioning on the operating parameters of the device to obtain device operating window data; Perform window partitioning on the denoised vibration parameters to obtain window vibration parameters; Calculate stability parameters according to the device coupling effect matrix, the device operating window data, and the window vibration parameters.

[0010] Optionally, the calculation formula for the device coupling effect matrix is as follows: Wherein, is the device coupling effect matrix, represents the vibration parameter of the th device in the denoised vibration parameters, represents the vibration parameter of the th device in the denoised vibration parameters, represents the cross-correlation coefficient of the vibration parameters of the th device and the th device in the denoised vibration parameters, represents the magnitude of the transfer function of the vibration parameters of the th device and the th device in the denoised vibration parameters at the preset reference vibration frequency , represents the variance of the vibration parameter of the th device in the denoised vibration parameters, represents the variance of the vibration parameter of the th device in the denoised vibration parameters.

[0011] Optionally, the calculation formula for the stability parameter is as follows: Wherein, is the stability parameter, is the preset weight parameter, is the sample number of the device operating window data, represents the standard deviation of the th window data in the device operating window data, represents the normalized mean of the th window data in the device operating window data, represents the vibration energy value of the th window data in the window vibration parameters at the preset reference vibration frequency , is the device coupling effect matrix, represents the maximum eigenvalue of the device coupling effect matrix.

[0012] Optionally, the product consistency analysis based on the product image sequence to obtain a consistency index includes: Identify the multi-dimensional dimensions of each product from the product image sequence to obtain a multi-dimensional dimension sequence; Calculate the dimension mean set and the dimension standard deviation set according to the multi-dimensional dimension sequence; Generate a sample covariance matrix according to the multi-dimensional dimension sequence; Calculate a consistency index according to the multi-dimensional dimension sequence, the dimension mean set, the dimension standard deviation set, and the sample covariance matrix.

[0013] Optionally, the calculation formula of the consistency index is as follows: Where, is the consistency index, is the number of dimensions of the multi-dimensional dimension sequence, is the multi-dimensional dimension sequence at the th dimension of the sample number, represents the multi-dimensional dimension sequence in the th dimension of the th sample size parameter, is the dimension mean of the th dimension in the dimension mean set, is the dimension standard deviation of the th dimension in the dimension standard deviation set, represents the multi-dimensional dimension parameter of the th sample in the multi-dimensional dimension sequence, is a pre-calculated mean vector, represents the transpose operation, represents the inverse matrix of the sample covariance matrix.

[0014] To solve the above problems, the present invention also provides an intelligent monitoring system for an automated assembly production line of hardware products, the system includes: A data acquisition module for real-time collecting equipment operation parameters and equipment vibration parameters in the assembly production line; A resonance denoising module for identifying resonance signals of the equipment vibration parameters, and performing resonance denoising processing on the equipment vibration parameters according to the resonance signals to obtain denoised vibration parameters; A stability analysis module for performing equipment stability analysis according to the denoised vibration parameters and the equipment operation parameters to obtain stability parameters; A stability judgment module is used to judge whether the stability parameter is greater than a preset stability threshold. If the stability parameter is less than or equal to the stability threshold, device instability alarm is carried out. If the stability parameter is greater than the stability threshold, product images in the assembly production line are continuously collected to obtain a product image sequence; A consistency analysis module is used to perform product consistency analysis according to the product image sequence to obtain a consistency index, and judge whether the consistency index is greater than a preset consistency threshold. If the consistency index is greater than the consistency threshold, return to the step of the data acquisition module 101 for collecting the device operation parameters and device vibration parameters in the real-time assembly production line. If the consistency index is less than or equal to the consistency threshold, product defect alarm is carried out.

[0015] In an embodiment of the present invention, the device operation parameters and device vibration parameters in the assembly production line are collected in real time, resonance signals in the device vibration parameters are identified, resonance denoising processing is performed on the device vibration parameters according to the resonance signals to obtain denoised vibration parameters, device stability analysis is performed according to the denoised vibration parameters and the device operation parameters to obtain a stability parameter, and judge whether the stability parameter is greater than a preset stability threshold. If the stability parameter is less than or equal to the stability threshold, device instability alarm is carried out. If the stability parameter is greater than the stability threshold, product images in the assembly production line are continuously collected to obtain a product image sequence, product consistency analysis is performed according to the product image sequence to obtain a consistency index, and judge whether the consistency index is greater than a preset consistency threshold. If the consistency index is greater than the consistency threshold, return to the step of collecting the device operation parameters and device vibration parameters in the real-time assembly production line. If the consistency index is less than or equal to the consistency threshold, product defect alarm is carried out. Therefore, the intelligent monitoring method and system for the automatic assembly production line of hardware products proposed by the present invention can solve the problems of low efficiency and low accuracy of the existing monitoring methods for the automatic assembly production line of hardware products. Description of the Drawings

[0016] Figure 1 It is a schematic flow chart of the intelligent monitoring method for the automatic assembly production line of hardware products provided by an embodiment of the present invention; Figure 2 It is a functional module diagram of the intelligent monitoring system for the automatic assembly production line of hardware products provided by an embodiment of the present invention.

[0017] The realization, functional features and advantages of the purpose of the present invention will be further described in conjunction with the embodiments with reference to the drawings. Detailed Embodiments

[0018] It should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0019] An embodiment of the present application provides an intelligent monitoring method for an automated assembly production line of hardware products. The execution subject of the intelligent monitoring method for the automated assembly production line of hardware products includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the intelligent monitoring method for the automated assembly production line of hardware products can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0020] Refer to Figure 1 As shown, it is a schematic flowchart of an intelligent monitoring method for an automated assembly production line of hardware products provided by an embodiment of the present invention. In this embodiment, the intelligent monitoring method for the automated assembly production line of hardware products includes: S1. Real-time collect the equipment operation parameters and equipment vibration parameters in the assembly production line.

[0021] In the embodiment of the present invention, the equipment operation parameters include the rotation speed, current parameter, voltage parameter, and temperature parameter of the equipment.

[0022] In the embodiment of the present invention, the equipment vibration parameter refers to the vibration parameters of multiple devices in the assembly production line.

[0023] Specifically, the equipment operation parameter refers to the equipment operation parameter within a preset time period, and the equipment vibration parameter also refers to the equipment vibration parameter within a preset time period.

[0024] In the embodiment of the present invention, by real-time collecting the equipment operation parameters and equipment vibration parameters in the assembly production line, the accuracy of subsequent resonance signal identification can be improved, and the accuracy of subsequent equipment stability analysis can be improved.

[0025] S2. Perform resonance signal identification on the equipment vibration parameter, and perform resonance denoising processing on the equipment vibration parameter according to the resonance signal to obtain denoised vibration parameters.

[0026] In the embodiment of the present invention, the performing resonance signal identification on the equipment vibration parameter includes: Perform smoothing denoising processing on each set of vibration parameters of the device to obtain denoised vibration parameters; Extract the spectral features of each set of denoised vibration parameters; Identify the peak positions of each spectral feature; Identify the peak correlation between all spectral features based on the peak positions to obtain the peak correlation identification result; According to the correlation identification result Confirm the resonance frequency and resonance amplitude to obtain the resonance signal.

[0027] Specifically, the smoothing denoising processing of each set of vibration parameters of the device may be to take the average value of a certain number of data points before and after each point in the vibration parameters as the new value of this point.

[0028] Specifically, the extraction of the spectral features of each set of denoised vibration parameters is to obtain the spectral features by performing Fourier transform on each set of denoised vibration parameters.

[0029] Specifically, the Fourier transform is a mathematical tool for converting a time-domain signal into a frequency-domain signal. By performing Fourier transform on the denoised vibration parameters, the signal can be converted from the time domain to the frequency domain, thereby obtaining the spectral features of the signal. The spectral features reflect the distribution of different frequency components in the signal.

[0030] Specifically, a peak refers to a point with a relatively large amplitude in the spectral feature. In the spectrogram, the peak usually corresponds to the main frequency component in the signal. A magnitude threshold can be set, and when the magnitude of a certain point in the spectrum exceeds this threshold, it is regarded as a peak.

[0031] Specifically, the identification of the peak correlation between all spectral features based on the peak positions means identifying whether the positions and amplitudes of the peaks between the spectral features are similar. If they are similar, it is confirmed that the peaks are correlated. A magnitude threshold is set, and when the magnitude of a certain point in the spectrum exceeds this threshold, it is regarded as a peak. The vibration signals of different devices may affect each other. By analyzing the peak correlation between spectral features, it can be judged whether there is a resonance phenomenon. If the peaks of different spectral features are close in frequency and the magnitude changes have a certain correlation, there may be resonance.

[0032] In the embodiment of the present invention, the identification of the peak correlation between all spectral features based on the peak positions to obtain the peak correlation identification result includes: Traverse the peak sets of any two sets of spectral features according to the peak positions and calculate the frequency difference between each pair of peaks; Identify the peak pairs with a frequency difference less than the preset frequency difference threshold as relevant candidate peak pairs; Calculate the amplitude difference between each pair of peaks in the relevant candidate peak pairs; Identify the peak pairs with an amplitude difference less than the preset amplitude difference threshold as relevant peak pairs, and obtain the correlation identification result.

[0033] In an embodiment of the present invention, the resonance denoising process of the device vibration parameters according to the resonance signal to obtain the denoised vibration parameters includes: Perform wavelet decomposition on the device vibration parameters to obtain wavelet coefficients in different scales and frequency subbands; Perform energy distribution analysis on the wavelet coefficients according to the resonance signal, and identify the subband where the resonance signal is located according to the analysis result to obtain the resonance subband; Perform threshold processing on the wavelet coefficients of the resonance subband to obtain processed wavelet coefficients; Perform wavelet reconstruction on the processed wavelet coefficients to obtain the denoised vibration parameters.

[0034] Specifically, wavelet decomposition is a multi-resolution analysis method that can decompose a signal into sub-signals of different scales and frequencies. Different from the traditional Fourier transform that can only provide the frequency domain information of the signal, wavelet transform can provide the local information of the signal in both the time domain and the frequency domain.

[0035] Specifically, performing wavelet decomposition on the device vibration parameters is to perform wavelet decomposition on the device vibration parameter signal by selecting appropriate wavelet basis functions (such as Daubechies wavelet, Haar wavelet, etc.) and the decomposition level (which can be from 3 to 7 layers). After decomposition, the signal is decomposed into a series of subbands of different scales and frequencies, and each subband corresponds to a set of wavelet coefficients. These wavelet coefficients reflect the characteristics of the signal at different scales and frequencies.

[0036] Specifically, the energy distribution analysis of the wavelet coefficients according to the resonance signal, and identifying the subband where the resonance signal is located according to the analysis result is to calculate the energy of the wavelet coefficients in each subband. The calculation method of energy is usually to sum the squares of all wavelet coefficients in the subband. By comparing the energy sizes of each subband, the energy distribution can be obtained, so as to judge in which subbands the resonance signal has larger energy.

[0037] Specifically, the threshold processing of the wavelet coefficients of the resonance subband is to set a threshold, set the wavelet coefficients less than the threshold to 0, and keep the wavelet coefficients greater than or equal to the threshold unchanged.

[0038] Specifically, the wavelet reconstruction of the processed wavelet coefficients is performed using the same wavelet basis function and decomposition level as in wavelet decomposition on the processed wavelet coefficients.

[0039] In the embodiment of the present invention, by identifying the resonance signal from the vibration parameters of the device, the efficiency of resonance denoising processing on the vibration parameters of the device can be improved. By performing resonance denoising processing on the vibration parameters of the device according to the resonance signal, the denoised vibration parameters can be obtained, and the accuracy of subsequent device stability analysis can be improved.

[0040] S3. Perform device stability analysis based on the denoised vibration parameters and the device operation parameters to obtain stability parameters.

[0041] In the embodiment of the present invention, the step of performing device stability analysis based on the denoised vibration parameters and the device operation parameters to obtain stability parameters is to obtain the stability parameters by analyzing the abnormality of the fluctuation relationship between the denoised vibration parameters and the device operation parameters.

[0042] Specifically, the stability parameter is a coefficient representing the stability of the device operation in the assembly production line.

[0043] In the embodiment of the present invention, the step of performing device stability analysis based on the denoised vibration parameters and the device operation parameters to obtain stability parameters includes: Construct a device coupling effect matrix based on the denoised vibration parameters and the device operation parameters; Perform window partitioning on the device operation parameters to obtain device operation window data; Perform window partitioning on the denoised vibration parameters to obtain window vibration parameters; Calculate the stability parameters based on the device coupling effect matrix, the device operation window data, and the window vibration parameters.

[0044] Specifically, the calculation formula of the device coupling effect matrix is as follows: Wherein, is the device coupling effect matrix, represents the vibration parameter of the th device in the denoised vibration parameters, represents the vibration parameter of the th device in the denoised vibration parameters, represents the cross-correlation coefficient between the vibration parameters of the th device and the th device in the denoised vibration parameters, represents the vibration parameter of the th device in the denoised vibration parameters and the The amplitude of the transfer function of the vibration parameter of a device at a preset reference vibration frequency wherein, represents the variance of the vibration parameter of the th device in the denoised vibration parameters, represents the variance of the vibration parameter of the th device in the denoised vibration parameters.

[0045] Specifically, the cross-correlation coefficient is calculated in advance according to the denoised vibration parameters, and is a statistic used to measure the similarity or correlation between two signals, and can be obtained by calculating the linear correlation of the change trends of the vibration parameters of two devices.

[0046] Specifically, the amplitude of the transfer function of the vibration parameter of the th device and the th device at a preset reference vibration frequency refers to the change of the signal amplitude when the vibration signal of the device is transmitted through the system to the device at the resonance frequency . It reflects the transfer efficiency and amplification or attenuation degree of the vibration energy between the devices and at a specific resonance frequency. It can usually be obtained through two methods: experimental measurement and data analysis.

[0047] In the embodiments of the present invention, the calculation formula of the stability parameter is as follows: wherein, is the stability parameter, is a preset weight parameter, is the number of samples of the device operation window data, represents the standard deviation of the th window data in the device operation window data, represents the normalized mean of the th window data in the device operation window data, represents the vibration energy value of the th window data in the window vibration parameters at a preset reference vibration frequency , is the device coupling effect matrix, represents the maximum eigenvalue of the device coupling effect matrix.

[0048] S4. Determine whether the stability parameter is greater than a preset stability threshold.

[0049] In an embodiment of the present invention, the stability threshold can be set after being calculated based on the historical operation parameters of the equipment in the assembly production line. For example, multiple equipment stability parameters can be calculated based on the historical operation parameters of the equipment in the assembly production line, and the maximum equipment stability parameter is selected as the stability threshold.

[0050] If the stability parameter is less than or equal to the stability threshold, then S5 is executed to give an alarm for equipment instability.

[0051] In an embodiment of the present invention, when the stability parameter is less than or equal to the stability threshold, it indicates that the operation stability of the equipment in the current assembly production line is low and there are potential safety hazards. Therefore, it is necessary to give an alarm for equipment instability to prompt relevant personnel to conduct inspections, ensuring production safety.

[0052] If the stability parameter is greater than the stability threshold, then S6 is executed to continuously collect product images in the assembly production line to obtain a product image sequence.

[0053] S7. Perform product consistency analysis based on the product image sequence to obtain a consistency index.

[0054] In an embodiment of the present invention, the performing product consistency analysis based on the product image sequence refers to analyzing the consistency of the size between products.

[0055] In an embodiment of the present invention, by performing product consistency analysis based on the product image sequence to obtain a consistency index, it can be used to judge the consistency of product sizes and ensure product quality.

[0056] In an embodiment of the present invention, the performing product consistency analysis based on the product image sequence to obtain a consistency index includes: Identifying the multi-dimensional sizes of each product based on the product image sequence to obtain a multi-dimensional size sequence; Calculating a size mean set and a size standard deviation set based on the multi-dimensional size sequence; Generating a sample covariance matrix based on the multi-dimensional size sequence; Calculating a consistency index based on the multi-dimensional size sequence, the size mean set, the size standard deviation set, and the sample covariance matrix.

[0057] Specifically, in the multi-dimensional sizes, it can refer to the sizes in several dimensions such as length, width, and height.

[0058] Specifically, the calculation formula of the consistency index is as follows: Wherein, is the consistency index, is the number of dimensions of the multi-dimensional size sequence, is the number of samples in the th dimension of the multi-dimensional size sequence, represents the th dimension of the multi-dimensional size sequence, and the th sample's size parameter, is the size mean of the th dimension in the size mean set, is the size standard deviation of the th dimension in the size standard deviation set, represents the multi-dimensional size parameter of the th sample in the multi-dimensional size sequence, is the pre-calculated mean vector, represents the transpose operation, represents the inverse matrix of the sample covariance matrix.

[0059] Specifically, the mean vector is a vector composed of the sample means of each dimension, which is used to describe the "central position" of the data in the multi-dimensional space. It is an extension of the univariate mean in the multi-dimensional scenario and is applicable to analyzing the data distribution with multiple features (such as length, width, aperture, etc.).

[0060] S8. Determine whether the consistency index is greater than a preset consistency threshold.

[0061] If the consistency index is greater than the consistency threshold, return to step S1 of real-time collecting the operation parameters and vibration parameters of the equipment in the assembly production line.

[0062] In the embodiment of the present invention, when the consistency index is greater than the consistency threshold, it indicates that the operation stability of the equipment in the current assembly production line meets the requirements, and the size consistency of the product meets the requirements. Therefore, it is necessary to return to the step of real-time collecting the operation parameters and vibration parameters of the equipment in the assembly production line to achieve a detection closed-loop.

[0063] If the consistency index is less than or equal to the consistency threshold, execute S9 to perform product defect warning.

[0064] In the embodiment of the present invention, when the consistency index is less than or equal to the consistency threshold, it indicates that the operation stability of the equipment in the current assembly production line meets the requirements, but the size consistency of the product does not meet the requirements. Therefore, it is necessary to perform product defect warning to notify relevant personnel to check the equipment in time to ensure production efficiency.

[0065] As Figure 2 shown, it is a functional module diagram of the intelligent monitoring system of the automatic assembly production line for hardware products provided by an embodiment of the present invention.

[0066] The intelligent monitoring system 100 of the automatic assembly production line of the hardware products described in the present invention can be installed in an electronic device. According to the functions achieved, the intelligent monitoring system 100 of the automatic assembly production line of the hardware products can include a data acquisition module 101, a resonance noise reduction module 102, a stability analysis module 103, a stability judgment module 104, and a consistency analysis module 105. The modules described in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0067] In this embodiment, the functions of each module / unit are as follows: The data acquisition module 101 is used to collect the equipment operation parameters and equipment vibration parameters in the assembly production line in real time; The resonance noise reduction module 102 is used to identify the resonance signal of the equipment vibration parameters, perform resonance noise reduction processing on the equipment vibration parameters according to the resonance signal, and obtain the denoised vibration parameters; The stability analysis module 103 performs equipment stability analysis according to the denoised vibration parameters and the equipment operation parameters to obtain stability parameters; The stability judgment module 104 is used to judge whether the stability parameter is greater than a preset stability threshold. If the stability parameter is less than or equal to the stability threshold, equipment instability alarm is performed. If the stability parameter is greater than the stability threshold, product images in the assembly production line are continuously collected to obtain a product image sequence; The consistency analysis module 105 is used to perform product consistency analysis according to the product image sequence to obtain a consistency index, and judge whether the consistency index is greater than a preset consistency threshold. If the consistency index is greater than the consistency threshold, the step of collecting the equipment operation parameters and equipment vibration parameters in the assembly production line in real time in the data acquisition module 101 is returned. If the consistency index is less than or equal to the consistency threshold, product defect alarm is performed.

[0068] Specifically, each module in the intelligent monitoring system 100 of the automatic assembly production line of the hardware products described in the embodiment of the present invention adopts the same technical means as those in the above Figure 1 intelligent monitoring method of the automatic assembly production line of the hardware products described, and can produce the same technical effects, which will not be elaborated here.

[0069] In the embodiments provided by the present invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation.

[0070] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, in each embodiment of the present invention, the functional modules can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a combination of hardware and software functional modules.

[0072] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0073] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0074] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0075] In addition, obviously, the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system claims can also be implemented by one unit or system through software or hardware. Words such as first and second are used to represent names and do not indicate any specific order.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent monitoring method for an automated assembly line of hardware products, characterized in that: The method comprises: Real-time collection of equipment operating parameters and equipment vibration parameters in the assembly production line; Resonance signal recognition is performed on the vibration parameters of the device, and resonance denoising is performed on the vibration parameters of the device according to the resonance signal to obtain denoised vibration parameters; Perform equipment stability analysis according to the denoised vibration parameters and the equipment operation parameters to obtain stability parameters; Determining whether the stability parameter is greater than a preset stability threshold; If the stability parameter is less than or equal to the stability threshold, an equipment instability alarm is issued; If the stability parameter is greater than the stability threshold, continuously collecting product images in the assembly production line to obtain a product image sequence; Perform product consistency analysis according to the product image sequence to obtain a consistency index; Determining whether the consistency index is greater than a preset consistency threshold; If the consistency index is greater than the consistency threshold, returning to the step of real-time acquisition of equipment operating parameters and equipment vibration parameters in the assembly production line; If the consistency index is less than or equal to the consistency threshold, a product defect alarm is issued.

2. The intelligent monitoring method for the automated assembly line of hardware products according to claim 1, characterized in that: The performing resonance signal identification on the vibration parameters of the device includes: Performing smoothing and denoising processing on each group of vibration parameters in the device vibration parameters to obtain denoised vibration parameters; Extracting the spectral features of each set of denoised vibration parameters; Identify the peak position of each spectral feature; Identify the peak correlations between all the spectrum features according to the peak positions to obtain a peak correlation identification result; Identify results based on correlation If the resonance frequency and resonance amplitude are confirmed, a resonance signal is obtained.

3. The intelligent monitoring method for the automated assembly line of hardware products according to claim 2, characterized in that: The step of identifying the peak correlations between all the spectrum features according to the peak positions to obtain the peak correlation identification results includes: Traversing the peak sets of any two groups of spectrum features according to the peak positions, and calculating the frequency difference of each pair of peaks; Confirming that a peak pair whose frequency difference is less than a preset frequency difference threshold is a relevant candidate peak pair; Calculating the amplitude difference of each pair of peaks in the related candidate peak pairs; It is confirmed that the peak pairs whose amplitude differences are less than the preset amplitude difference threshold are relevant peak pairs, and the correlation identification result is obtained.

4. The intelligent monitoring method for the automated assembly line of hardware products according to claim 1, characterized in that: The performing resonance denoising processing on the vibration parameters of the device according to the resonance signal to obtain the denoised vibration parameters comprises: Performing wavelet decomposition on the vibration parameters of the equipment to obtain wavelet coefficients of different scales and frequency sub-bands; Performing energy distribution analysis on the wavelet coefficients according to the resonance signal, confirming the subband where the resonance signal is located according to the analysis result, and obtaining the resonance subband; Performing threshold processing on the wavelet coefficients of the resonance subband to obtain processed wavelet coefficients; The processed wavelet coefficients are subjected to wavelet reconstruction to obtain denoised vibration parameters.

5. The intelligent monitoring method for the automated assembly line of hardware products according to claim 1, characterized in that: The performing of equipment stability analysis according to the denoising vibration parameters and the equipment operation parameters to obtain stability parameters includes: Constructing a device coupling effect matrix according to the denoising vibration parameters and the device operation parameters; Dividing the device operation parameters into windows to obtain device operation window data; Performing window division on the denoised vibration parameters to obtain window vibration parameters; The stability parameter is calculated according to the device coupling effect matrix, the device operation window data and the window vibration parameter.

6. The intelligent monitoring method for the automated assembly line of hardware products according to claim 5, characterized in that: The calculation formula of the device coupling effect matrix is ​​as follows: in, is the device coupling effect matrix, Indicates the denoising vibration parameter The vibration parameters of the equipment, Indicates the denoising vibration parameter The vibration parameters of the equipment, Indicates the denoising vibration parameter Device and The mutual correlation coefficients of the vibration parameters of the equipment, Indicates the denoising vibration parameter Device and The vibration parameters of each device are within the preset reference vibration frequency. The transfer function amplitude at Indicates the denoising vibration parameter The variance of the vibration parameters of each device, Indicates the denoising vibration parameter The variance of the vibration parameters of the equipment.

7. The intelligent monitoring method for the automated assembly line of hardware products according to claim 5, characterized in that: The calculation formula of the stability parameter is as follows: in, is the stability parameter, is the preset weight parameter, the number of samples of window data to run for the device in question, Indicates the device operation window data The standard deviation of the window data, Indicates the device operation window data The normalized mean of the window data, Indicates the window vibration parameter The window data is at the preset reference vibration frequency The vibration energy value at is the device coupling effect matrix, represents the maximum eigenvalue of the device coupling effect matrix.

8. The intelligent monitoring method for an automated assembly line of hardware products as claimed in claim 1, characterized in that: The performing product consistency analysis according to the product image sequence to obtain a consistency index includes: Identify the multi-dimensional size of each product according to the product image sequence to obtain a multi-dimensional size sequence; Calculate a size mean set and a size standard deviation set according to the multi-dimensional size sequence; Generate a sample covariance matrix according to the multi-dimensional size sequence; A consistency index is calculated according to the multi-dimensional size sequence, the size mean set, the size standard deviation set, and the sample covariance matrix.

9. The intelligent monitoring method for an automated assembly line of hardware products as claimed in claim 8, characterized in that: The calculation formula of the consistency index is as follows: in, is the consistency index, is the number of dimensions of the multi-dimensional size sequence, For the multi-dimensional size sequence in the first The number of samples in the dimension, Indicates the first Size dimension The size parameter of the samples, is the size mean value set The mean size of the dimension, is the size standard deviation set The standard deviation of the size dimension, Indicates the first The multi-dimensional size parameter of samples, is the pre-computed mean vector, represents the transpose operation, represents the inverse matrix of the sample covariance matrix.

10. An intelligent monitoring system for an automated assembly line of hardware products, characterized in that: The system comprises: Data acquisition module, used to collect equipment operation parameters and equipment vibration parameters in the assembly production line in real time; A resonance denoising module, used for performing resonance signal recognition on the vibration parameters of the device, and performing resonance denoising on the vibration parameters of the device according to the resonance signal to obtain denoised vibration parameters; A stability analysis module, performing equipment stability analysis according to the denoised vibration parameters and the equipment operation parameters to obtain stability parameters; A stability judgment module, used to judge whether the stability parameter is greater than a preset stability threshold, and if the stability parameter is less than or equal to the stability threshold, an equipment instability alarm is issued; if the stability parameter is greater than the stability threshold, product images in the assembly line are continuously collected to obtain a product image sequence; The consistency analysis module is used to perform product consistency analysis based on the product image sequence to obtain a consistency index, and determine whether the consistency index is greater than a preset consistency threshold. If the consistency index is greater than the consistency threshold, the module returns to the step of real-time acquisition of equipment operating parameters and equipment vibration parameters in the assembly production line in the data acquisition module 101. If the consistency index is less than or equal to the consistency threshold, a product defect alarm is issued.

Images