Aluminum profile machining quality detection system and method based on multi-dimensional data analysis

Abstract

The application relates to the technical field of aluminum profile machining detection, and discloses an aluminum profile machining quality detection system and method based on multidimensional data analysis. The method comprises the following steps: S1, collecting cutting end face image data through an industrial camera, collecting cutting contour size data through a laser sensor, and collecting machining vibration signal data through a vibration sensor. Through the cooperative collection of the industrial camera, the laser sensor and the vibration sensor, the limitations of a single sensing dimension in surface quality, size precision and dynamic stability monitoring are overcome, the machining quality of a single aluminum profile is effectively comprehensively judged and analyzed, the scoring feature extraction in a sliding window and the multi-window trend analysis are utilized, the stability of the aluminum profile machining process is further judged and warned, the comprehensiveness and accuracy of the aluminum profile quality evaluation are improved, and process abnormalities can be identified before quality problems become dominant.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of aluminum profile processing detection, in particular to an aluminum profile processing quality detection system and method based on multi-dimensional data analysis. BACKGROUND

[0002] Aluminum profiles are widely used in the fields of building, automobile, aerospace, etc. due to their light weight, high strength, easy processing and other advantages. The processing quality of aluminum profiles, especially the cutting quality, directly affects the structural strength, assembly precision and aesthetic degree of the final product. Therefore, efficient and accurate quality detection and control of the aluminum profile processing process is a key link in the manufacturing industry.

[0003] In the prior art, aluminum profile processing quality detection mainly relies on single-dimensional technologies such as machine vision, size measurement or vibration analysis. These methods all have limitations: visual detection is easily disturbed by the environment and cannot perceive size deformation; size measurement is mostly sampling inspection, which is difficult to reflect the dynamic stability of the processing process; vibration analysis is difficult to directly correlate the workpiece surface and size quality. This single-dimensional quality detection mode leads to one-sided evaluation of aluminum profile processing quality and cannot effectively warn of quality problems before they occur. SUMMARY

[0004] In order to overcome the limitations of single detection technology and realize comprehensive evaluation and forward-looking early warning of aluminum profile processing quality, the application provides an aluminum profile processing quality detection system and method based on multi-dimensional data analysis.

[0005] In a first aspect, the application provides an aluminum profile processing quality detection method based on multi-dimensional data analysis, which adopts the following technical solution:

[0006] An aluminum profile processing quality detection system and method based on multi-dimensional data analysis, the method comprising:

[0007] S1, collecting cutting end face image data through an industrial camera, collecting cutting contour size data through a laser sensor, and collecting processing vibration signal data through a vibration sensor;

[0008] S2, comprehensively analyzing the collected multi-source data to obtain a comprehensive quality score of the current aluminum profile workpiece, and determining the quality of the aluminum profile workpiece according to the comprehensive quality score;

[0009] S3, presetting a sliding window in units of workpieces, extracting features of the comprehensive quality score sequence of all workpieces in the sliding window to obtain a score feature value of the preset sliding window;

[0010] S4, trend analysis is performed on the score feature value sequence of the preset number of continuous sliding windows, and when it is detected that the score feature value downward trend exceeds a preset threshold, a processing abnormality early warning is generated.

[0011] By adopting the technical solution, comprehensive quality detection based on multi-source data is realized, feature extraction and trend analysis are performed on the comprehensive quality score sequence through the preset sliding window, and when it is detected that the score feature value downward trend exceeds the threshold, a processing abnormality early warning is generated, thereby improving the comprehensiveness of the aluminum profile processing quality detection and the timeliness of the early warning.

[0012] Optionally, in step S2, the process of determining the quality of the aluminum profile processing piece according to the comprehensive quality score includes:

[0013]

[0014] The comprehensive quality score is obtained through formula analysis and calculation ;

[0015] wherein, is an aluminum profile surface defect score, is an aluminum profile size deviation score, is a vibration signal spectrum analysis score, , , is a first weight coefficient;

[0016] The comprehensive quality score is compared with a preset unqualified score threshold ;

[0017] If , it is determined that the aluminum profile is unqualified, the aluminum profile is marked and an unqualified signal is generated;

[0018] Otherwise, it is determined that the aluminum profile is qualified, the aluminum profile is marked and a qualified signal is generated.

[0019] By adopting the technical solution, the comprehensive quality score is obtained through formula calculation, and is automatically compared with the preset unqualified score threshold, thereby realizing objective and efficient quality determination of the aluminum profile processing piece and reducing subjective errors.

[0020] Optionally, the process of obtaining the aluminum profile surface defect score includes:

[0021]

[0022] The aluminum profile surface defect score is obtained through the above formula analysis and calculation ;

[0023] wherein, a constant value for full score in the scoring system, a total number of defects detected on the surface of the current aluminum profile, a type weight coefficient of the i th defect, a projected area of the i th defect, a total surface area of the aluminum profile.

[0024] By adopting the above technical scheme, the aluminum profile surface defect score is calculated by considering the defect type weight, the ratio of the defect projected area to the total surface area, so that the score more accurately reflects the severity of the surface defect, and the accuracy of the surface quality evaluation is improved.

[0025] Optionally, the process of obtaining the aluminum profile size deviation score includes:

[0026]

[0027] The aluminum profile size deviation score is obtained by analyzing and calculating the above formula ;

[0028] wherein, a total number of key size parameters to be measured, an actual measured value of the j th size parameter, a theoretical design value of the j th size parameter, a weight coefficient of the j th size parameter, a maximum allowed comprehensive relative deviation threshold value, a maximum value in the parentheses.

[0029] By adopting the above technical scheme, the size deviation score is obtained by calculating the relative deviation of multiple key size parameters, combined with the weight coefficient and the maximum allowed deviation threshold value, which realizes the comprehensive quantitative evaluation of the size quality of the aluminum profile, and improves the reliability of the size control.

[0030] Optionally, the process of obtaining the vibration signal spectrum analysis score includes:

[0031]

[0032] The vibration signal spectrum analysis score is obtained by analyzing and calculating the above formula ;

[0033] wherein, a number of characteristic frequency bands, an amplitude of the current vibration signal in the k th characteristic frequency band, a corresponding amplitude under the reference normal state, a weight coefficient of the k th frequency band, a maximum allowed amplitude deviation threshold value.

[0034] By adopting the technical scheme, the abnormal vibration in the processing process can be effectively recognized by comparing the amplitude deviation of the current vibration signal with the reference normal state in the characteristic frequency band, and calculating the vibration signal spectrum analysis score, so as to reflect the equipment state and the processing quality.

[0035] Optionally, in step S3, the process of obtaining the score characteristic value of the preset sliding window comprises:

[0036]

[0037]

[0038]

[0039]

[0040] The score characteristic value of the preset sliding window is obtained by simultaneous analysis and calculation of the above formulae ;

[0041] wherein, is the unqualified rate of the aluminum profile workpiece in the sliding window, is the average of the comprehensive quality score in the sliding window, is the fluctuation of the comprehensive quality score in the sliding window, , , is the second weight coefficient, is the number of unqualified aluminum profile workpieces in the sliding window, is the total number of aluminum profile workpieces in the sliding window, is the comprehensive quality score of the lth aluminum profile workpiece in the sliding window.

[0042] By adopting the technical scheme, the unqualified rate, the score average and the fluctuation and other characteristics in the sliding window are obtained by simultaneous formula calculation, the score characteristic value is obtained, the comprehensive characteristic extraction of the quality data in the window is realized, and the key index for trend analysis is provided.

[0043] Optionally, in step S4, the process of performing trend analysis on the score characteristic value sequence of the preset number of continuous sliding windows comprises:

[0044]

[0045] The trend slope of the score characteristic value of the preset number of continuous sliding windows with time is obtained by analysis and calculation of the above formulae ;

[0046] wherein, is the preset number of continuous sliding windows, a time sequence number of the sliding window sequence, a sliding window time identifier, a score feature value corresponding to the hth sliding window;

[0047] a score feature value of a preset number of continuous sliding windows a preset change threshold are compared;

[0048] when an aluminum profile quality abnormality downward trend occurs in the processing process, and a processing abnormality early warning is generated.

[0049] By adopting the above technical solution, by calculating the trend slope of the score feature value of the continuous sliding window and comparing it with the preset threshold, the quality abnormality downward trend can be detected in time, the processing abnormality early warning is generated, and predictive quality monitoring is realized.

[0050] Optionally, the method further comprises:

[0051] S5, analyzing the score feature values of a preset number of continuous sliding windows, and dynamically adjusting the size of the sliding window.

[0052] By adopting the above technical solution, by dynamically adjusting the size of the sliding window, the trend analysis can adapt to data changes, and the flexibility and adaptability of the quality detection system are improved.

[0053] Optionally, the process of dynamic adjustment comprises:

[0054]

[0055]

[0056] The size of the sliding window is obtained by simultaneous calculation and analysis of the above formula ;

[0057] wherein, is a standard deviation of score feature values of a preset n consecutive sliding windows, is an average value of score feature values of a preset n consecutive sliding windows, is a preset reference window size, is a floor function.

[0058] By adopting the above technical solution, based on the standard deviation and average value of the score feature values of the recent continuous sliding windows, the window size is dynamically calculated, the window adjustment is more in line with the data fluctuation characteristics, and the accuracy of the trend analysis is optimized.

[0059] In a second aspect, the application provides an aluminum profile machining quality detection system based on multi-dimensional data analysis, which adopts the following technical solution:

[0060] An aluminum profile machining quality detection system based on multi-dimensional data analysis, which is applied to the aluminum profile machining quality detection method based on multi-dimensional data analysis in any one of the above aspects, and comprises:

[0061] A data acquisition module for acquiring multi-source data in the machining process through an industrial camera, a laser sensor and a vibration sensor;

[0062] A comprehensive score calculation module for comprehensively analyzing the acquired multi-source data, obtaining a comprehensive quality score of the aluminum profile machining part and performing quality determination;

[0063] A sliding window feature extraction module for extracting features of the comprehensive quality score sequence based on a preset sliding window to obtain score feature values;

[0064] A trend analysis module for performing trend analysis on the score feature value sequence of the continuous sliding window and generating a machining abnormality early warning;

[0065] A dynamic window adjustment module for dynamically adjusting the size of the sliding window according to the score feature values;

[0066] An early warning module for executing a warning signal.

[0067] By adopting the above technical solution, a detection system for implementing the above method is provided, and the specific implementation and application of the aluminum profile machining quality detection method are ensured through modular design, thereby improving the practicality and automation level of the system.

[0068] In summary, the application has at least one of the following beneficial technical effects:

[0069] (1) The present application overcomes the limitations of single sensing dimension in surface quality, dimensional accuracy and dynamic stability monitoring through the cooperative collection of an industrial camera, a laser sensor and a vibration sensor, effectively performs comprehensive judgment and analysis on the quality of a single aluminum profile, and further judges and warns the stability of the aluminum profile machining process by using score feature extraction in the sliding window and multi-window trend analysis, thereby improving the comprehensiveness and accuracy of aluminum profile quality evaluation, identifying process abnormalities before quality problems become explicit, effectively addressing defects such as one-dimensional detection bias, sampling lag and inability to dynamically warn, and providing effective protection for continuous quality control of aluminum profile machining.

[0070] (2) The application realizes multi-dimensional and interpretable unified evaluation of the cutting quality of aluminum profiles by constructing quantitative scoring models of surface defects, size deviation and vibration stability respectively and fusing them into a comprehensive quality index, which can not only distinguish whether the aluminum profile is qualified in real time, but also provide data basis for process optimization through a structured scoring system, effectively overcoming the defects of single detection dimension in the background technology, which is one-sided and difficult to fully reflect the processing quality, and improving the systematicness and reliability of quality determination.

[0071] (3) The application realizes overall quantitative evaluation of batch processing quality by defining window characteristic values of unqualified rate, mean value and standard deviation, and realizes early identification of quality degradation trend by using the slope detection of continuous window characteristic values, which expands the quality monitoring perspective from a single workpiece to a process sequence, can find potential systemic degradation problems before the production line is significantly affected, effectively overcomes the defect of the traditional detection method in the background technology that can only make post-determination and cannot realize early warning, and provides effective support for predictive quality control of aluminum profile processing. BRIEF DESCRIPTION OF DRAWINGS

[0072] Figure 1 is a step flow chart of an aluminum profile processing quality detection method based on multi-dimensional data analysis disclosed by the application.

[0073] Figure 2 is a schematic block diagram of an aluminum profile processing quality detection system based on multi-dimensional data analysis disclosed by the application. DETAILED DESCRIPTION

[0074] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0075] In the description of the present specification, the description of the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the described embodiments or examples are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the described specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0076] The embodiments of the present application disclose an aluminum profile processing quality detection method based on multi-dimensional data analysis, referring to Figure 1 , the method comprises:

[0077] S1, collect cutting end face image data through an industrial camera for analyzing surface roughness, burr and texture uniformity, collect cutting contour size data through a laser sensor, size data including but not limited to length deviation, flatness and perpendicularity, collect vibration signals of a machining equipment main shaft or workbench through a vibration sensor to reflect machining dynamic stability;

[0078] S2, comprehensively analyze the collected multi-source data to obtain a comprehensive quality score of the current aluminum profile workpiece, and determine the aluminum profile workpiece quality according to the comprehensive quality score;

[0079] S3, preset a sliding window in the unit of a continuous number of workpieces, extract features of a comprehensive quality score sequence of all workpieces in the sliding window to obtain a score feature value of the preset sliding window, the extracted features including but not limited to score mean, standard deviation, descending slope, etc., for representing quality stability of the current window;

[0080] S4, perform trend analysis on score feature value sequences of a preset number of continuous sliding windows, generally using a linear regression algorithm to analyze the score feature value change trend, and generate a machining abnormality early warning when detecting that the score feature value descending trend exceeds a preset threshold.

[0081] Through the above technical solution, the embodiment provides an aluminum profile machining quality detection method based on multi-dimensional data analysis, which overcomes the limitations of single sensing dimension in surface quality, size accuracy and dynamic stability monitoring through the cooperative collection of industrial cameras, laser sensors and vibration sensors, effectively comprehensively judges and analyzes the quality of a single aluminum profile, and further judges and warns the stability of the aluminum profile machining process by using score feature extraction in a sliding window and multi-window trend analysis, which not only improves the comprehensiveness and accuracy of aluminum profile quality evaluation, but also identifies process abnormalities before quality problems become explicit, effectively addresses one-dimensional detection bias, sampling lag, and inability to dynamically warn, etc. defects, and provides effective protection for continuous quality control of aluminum profile machining.

[0082] In an embodiment, in step S2, the process of determining the aluminum profile workpiece quality according to the comprehensive quality score includes:

[0083]

[0084] The comprehensive quality score is obtained through formula analysis and calculation ;

[0085] wherein, is an aluminum profile surface defect score based on image analysis, is an aluminum profile size deviation score based on laser measurement, For vibration signal spectrum analysis scoring, 、 、 is the first weight coefficient, usually determined by production quality experts according to historical quality data or customer requirements, or fitted by machine learning method according to the importance of each dimension quality;

[0086] The comprehensive quality score is compared with the preset unqualified score threshold The preset unqualified score threshold can be set according to experience, generally set to 70-80 points, and can be dynamically adjusted according to product grade requirements and historical pass rate data;

[0087] If , it is judged that the aluminum profile is unqualified, the aluminum profile is marked and an unqualified signal is generated, triggering the rejection or rework process;

[0088] Otherwise, it is judged that the aluminum profile is qualified, the aluminum profile is marked and a qualified signal is generated, and the next process is entered.

[0089] The process of obtaining the aluminum profile surface defect score includes:

[0090]

[0091] The aluminum profile surface defect score is obtained by analyzing and calculating the above formula;

[0092] Wherein, is the full score constant value in the scoring system, usually set to 100, is the total number of defects detected on the current aluminum profile, which can be automatically identified and counted by image segmentation algorithm or deep learning target detection model, is the type weight coefficient of the i-th defect, which is assigned by process experts according to the influence of defect type (such as crack, scratch, pit) on product performance, and the crack type serious defect is usually taken as 1, and the slight scratch can be taken as 0.3, is the projection area of the i-th defect, in image processing, the number of pixels surrounded by the defect contour is calculated by pixel statistics, and the actual physical area is converted by combining the camera calibration parameters, is the total surface area of the aluminum profile, which is known from product drawings or calculated by three-dimensional scanning model.

[0093] The process of obtaining the aluminum profile size deviation score includes:

[0094]

[0095] The aluminum profile size deviation score is obtained by analyzing and calculating the above formula;

[0096] wherein, is the total number of critical dimension parameters to be measured, usually including 3-8 critical dimensions such as length, angle, flatness, etc., is the actual measured value of the jth dimension parameter, obtained by real-time acquisition through a laser sensor, is the theoretical design value of the jth dimension parameter, obtained according to CAD drawings or process specifications, is the weight coefficient of the jth dimension parameter, obtained according to the influence degree of the dimension on assembly accuracy and structural function, is the allowed maximum comprehensive relative deviation threshold, obtained according to experience, usually set to 0.05, and can be tightened to 0.02 in high-precision scenarios, is the maximum value in the brackets.

[0097] The process of obtaining the vibration signal spectrum analysis score includes:

[0098]

[0099] The vibration signal spectrum analysis score is obtained by analyzing and calculating the above formula ;

[0100] wherein, is the number of characteristic frequency bands, usually covering the main shaft rotation base frequency, tool engagement frequency and its harmonics, about 3-5 characteristic frequency bands, is the amplitude of the current vibration signal in the kth characteristic frequency band, after FFT transformation of the time domain signal collected by the vibration sensor, the amplitude value is obtained by integrating in the corresponding frequency band, is the reference amplitude under normal state, measured multiple times under the initial healthy state of the equipment and taking the statistical average value, is the weight coefficient of the kth frequency band, which can be obtained by setting according to experience, for example, high frequency bands (such as tool engagement bands) usually have higher weights (0.6-0.8) because they are more sensitive to tool wear and impact; is the allowed maximum amplitude deviation threshold, which is obtained based on historical normal operation data statistics, and is usually 3 times the standard deviation of normal amplitude fluctuation.

[0101] By the technical solution, the embodiment provides a kind of aluminum profile machining quality comprehensive score and judging method based on multi-source sensing data fusion, the method is by respectively constructing surface defect, size deviation and vibration stability quantitative scoring model, and fusion is comprehensive quality index, realizes the unified evaluation of multiple dimensions, interpretable of aluminum profile cutting quality, not only can distinguish whether aluminum profile is qualified in real time, more through structured scoring system provides data basis for process optimization, effectively overcome the defects of single detection dimension in background technology, difficult to fully reflect the processing quality, improve the systematicness and reliability of quality determination.

[0102] In an embodiment, in step S3, the process of obtaining the score feature value of the preset sliding window includes:

[0103]

[0104]

[0105]

[0106]

[0107] The score feature value of the preset sliding window is obtained by simultaneous analysis and calculation of the above formula ;

[0108] Wherein, is the unqualified rate of aluminum profile workpiece in sliding window, reflects the overall compliance level of processing quality in this window period, is the average value of all comprehensive quality scores in sliding window, represents the concentration trend of overall quality level, is the fluctuation of comprehensive quality score in sliding window, reflects the volatility and stability of quality output, , , is the second weight coefficient, for adjusting the contribution of each feature in overall evaluation, can be determined by historical data regression analysis or expert experience, is the number of unqualified aluminum profile workpieces in sliding window, directly obtained by step S2 determination result, is the total number of aluminum profile workpieces in sliding window, i.e. the preset window size, is the comprehensive quality score of the lth aluminum profile workpiece in sliding window, which can be obtained by calculating and analyzing according to step S2.

[0109] In step S4, the process of trend analysis on the score feature value sequence of a plurality of continuous sliding windows includes:

[0110]

[0111] The slope of the trend of the scoring feature value of a preset number of continuous sliding windows changing over time is obtained through the analysis and calculation using the above formula. ;

[0112] in, The preset number of consecutive sliding windows is typically set to 5-10. Too few windows can easily lead to false alarms, while too many will result in delayed warnings. Number the time sequence of the sliding window sequence. , For the sliding window time identifier, you can take the absolute timestamp at the end of the window, or directly use the window number sequence as the equally spaced time variable. The scoring feature value corresponding to the h-th sliding window can be obtained by calculation and analysis according to step S3;

[0113] The slope of the trend of the scoring feature values ​​of a preset number of continuous sliding windows over time. Compared with the preset change threshold The preset change threshold is compared. It can be determined by statistical analysis of the normal fluctuation range in historical data, and its value depends on the quality stability requirements;

[0114] when If an abnormal downward trend in the quality of aluminum profiles is detected during the processing, a processing anomaly warning will be generated.

[0115] Through the above technical solution, this embodiment provides a quality early warning method for aluminum profile processing based on sliding window and trend analysis. The method achieves overall quantitative evaluation of batch processing quality by defining window feature values ​​that integrate non-conforming rate, mean, and standard deviation. Furthermore, by utilizing the slope detection of continuous window feature values, it achieves early identification of quality degradation trends. This method extends the quality monitoring perspective from a single workpiece to a process sequence, enabling the detection of potential systemic degradation problems before they significantly impact the production line. It effectively overcomes the shortcomings of traditional detection methods proposed in the background art, which can only make post-event judgments and cannot achieve pre-event early warning, thus providing effective support for predictive quality control in aluminum profile processing.

[0116] In one embodiment, the method further includes:

[0117] S5. Analyze the scoring feature values ​​of a preset number of continuous sliding windows and dynamically adjust the size of the sliding windows.

[0118] The dynamic adjustment process includes:

[0119]

[0120]

[0121] The size of the sliding window is obtained by the simultaneous calculation and analysis of the above formula ;

[0122] wherein, is the standard deviation of the scoring characteristic values of the preset last n continuous sliding windows, and is calculated based on the characteristic values of the n continuous sliding windows before the current moment, is a key index for measuring the stability of the process quality, and the greater the value is, the more intense the recent process fluctuation is, and the worse the stability is, is the average value of the scoring characteristic values of the preset last n continuous sliding windows, and is calculated based on the characteristic values of the n continuous sliding windows before the current moment, and represents the central tendency of the recent quality level, and is used as a reference value for the stability in the formula, is the preset reference window size, and is an initial value set according to the specific production line beat and experience, for example, can be set as the yield of 1 hour or the fixed batch of 200 pieces, and is the reference line for the window size adjustment, is a floor function, and means taking the maximum integer not greater than the calculation result.

[0123] When the process is stable, the ratio is close to 1, and at this time is close to , the system adopts a larger sliding window, which is helpful for smoothing random fluctuations and avoiding false alarms caused by small noise, and improves the monitoring efficiency; when the process fluctuates, the ratio decreases, resulting in becomes smaller, the system automatically reduces the window size, so that the frequency of quality evaluation and trend analysis increases, so that the abnormal change of the process can be captured more quickly and more sensitively, and early warning is realized.

[0124] Through the above technical solution, the embodiment provides an aluminum profile machining quality monitoring method with adaptive ability, which realizes intelligent balance of monitoring sensitivity and robustness by introducing a dynamic window adjustment mechanism based on recent quality stability, overcomes the inherent defects that the fixed window size may be slow in response when the process is stable and may be too sensitive when the process fluctuates, so that the whole early warning system can automatically optimize its monitoring strategy according to the actual state of the production process, not only improves the timeliness and accuracy of early warning, but also further enhances the practicality and intelligent level of the system in dealing with complex working conditions, further solves the defects of the rigid single-point detection mode in the background technology, and realizes the change from static detection to dynamic intelligent monitoring.

[0125] The embodiment of the application also discloses an aluminum profile machining quality detection system based on multi-dimensional data analysis, which is referred to Figure 2The system is applied to the aluminum profile machining quality detection method based on multi-dimensional data analysis in any of the above, and the system comprises:

[0126] A data acquisition module is configured to acquire multi-source data in the machining process through an industrial camera, a laser sensor, and a vibration sensor.

[0127] A comprehensive score calculation module is configured to comprehensively analyze the acquired multi-source data, obtain a comprehensive quality score of the aluminum profile machining part, and perform quality determination.

[0128] A sliding window feature extraction module is configured to extract features of the comprehensive quality score sequence based on a preset sliding window, and obtain score feature values.

[0129] A trend analysis module is configured to perform trend analysis on the score feature value sequence of the continuous sliding window, and generate a machining abnormality early warning.

[0130] A dynamic window adjustment module is configured to dynamically adjust the size of the sliding window according to the score feature values.

[0131] An early warning module is configured to execute a warning signal.

[0132] Through the above technical solution, the embodiment provides an aluminum profile machining quality detection system based on multi-dimensional data analysis. The system cooperates the data acquisition, comprehensive score calculation, sliding window feature extraction, trend analysis, dynamic window adjustment, and early warning module to construct a multi-level quality monitoring system from real-time determination to process early warning. The system deeply integrates machine vision, precise measurement, and vibration analysis, introduces a dynamic trend monitoring and self-adaptive adjustment mechanism based on a sliding window, realizes comprehensive perception, accurate evaluation, and early warning of the aluminum profile machining quality, effectively solves the core defects of one-dimensional detection, sampling inspection lag, and inability to dynamically warn in the background technology, and significantly improves the intelligent level and foresight of quality control.

[0133] Although the embodiments of the application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the application. Those skilled in the art can make changes, modifications, replacements, and variations to the above embodiments within the scope of the application.

Claims

1. A method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis, characterized in that, The method includes: S1. Acquire image data of the cutting end face through an industrial camera, acquire cutting contour dimension data through a laser sensor, and acquire processing vibration signal data through a vibration sensor; S2. Perform comprehensive analysis on the collected multi-source data to obtain the comprehensive quality score of the current aluminum profile processed parts, and make quality judgment on the aluminum profile processed parts based on the comprehensive quality score. S3. Preset a sliding window with the number of workpieces as the unit, extract features from the comprehensive quality score sequence of all processed parts within the sliding window, and obtain the score feature value of the preset sliding window. S4. Perform trend analysis on the scoring feature value sequence of a preset number of continuous sliding windows. When the downward trend of the scoring feature value is detected to exceed the preset threshold, generate a processing anomaly warning. In step S2, the process of determining the quality of aluminum profile processed parts based on the comprehensive quality score includes: ； The overall quality score is obtained through formula analysis and calculation. ; in, Scoring of surface defects in aluminum profiles. Scoring for dimensional deviations of aluminum profiles. Scoring for vibration signal spectrum analysis. , , The first weighting coefficient; Comprehensive quality score Compared with the preset non-compliance scoring threshold Compare them.

2. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 1, characterized in that, The process of obtaining the surface defect score for the aluminum profile includes: ； The surface defect score of aluminum profiles is obtained through analysis and calculation using the above formula. ; in, This is the constant value for the maximum score in the scoring system. This represents the total number of defects currently detected on the surface of the aluminum profile. Let be the type weight coefficient for the i-th defect. Let be the projected area of ​​the i-th defect. This represents the total surface area of ​​the aluminum profile.

3. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 2, characterized in that, The process for obtaining the aluminum profile dimensional deviation score includes: ； The aluminum profile dimensional deviation score is obtained through analysis and calculation using the above formula. ; in, The total number of key dimensional parameters being measured. For the j-th dimensional parameter, Let j be the theoretical design value of the j-th dimensional parameter. The weighting coefficient for the j-th dimension parameter. The maximum permissible composite relative deviation threshold. To take the maximum value within the parentheses.

4. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 3, characterized in that, The process of obtaining the vibration signal spectrum analysis score includes: ； The vibration signal spectrum analysis score is obtained through the above formula analysis and calculation. ; in, The number of characteristic frequency bands, Let be the amplitude of the current vibration signal in the kth characteristic frequency band. To reference the corresponding amplitude under normal conditions, The weighting coefficients for the k-th frequency band are... This is the maximum allowable amplitude deviation threshold.

5. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 4, characterized in that, In step S3, the process of obtaining the scoring feature values ​​of the preset sliding window includes: ； ； ； ； The scoring characteristic value of the preset sliding window is obtained by combining the above formulas and performing simultaneous analysis. ; in, The defect rate of aluminum profile workpieces within the sliding window. This represents the average of all comprehensive quality scores within the sliding window. To account for the volatility of the overall quality score within the sliding window, , , This is the second weighting coefficient. This represents the number of defective aluminum profile workpieces within the sliding window. This represents the total number of aluminum profile workpieces within the sliding window. The overall quality score for the l-th aluminum profile workpiece within the sliding window.

6. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 5, characterized in that, In step S4, the process of performing trend analysis on the scoring feature value sequence of a preset number of continuous sliding windows includes: ； The slope of the trend of the scoring feature value of a preset number of continuous sliding windows over time was obtained by analyzing and calculating using the above formula. ; in, The preset number of consecutive sliding windows, Number the time sequence of the sliding window sequence. For the sliding window time indicator, The rating feature value corresponding to the h-th sliding window; The slope of the trend of the scoring feature values ​​of a preset number of continuous sliding windows over time. Compared with the preset change threshold Perform a comparison; when If an abnormal downward trend in the quality of aluminum profiles is detected during the processing, a processing anomaly warning will be generated.

7. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 6, characterized in that, The method further includes: S5. Analyze the scoring feature values ​​of a preset number of continuous sliding windows and dynamically adjust the size of the sliding windows.

8. The method for inspecting the processing quality of aluminum profiles based on multidimensional data analysis according to claim 7, characterized in that, The dynamic adjustment process includes: ； ； The size of the sliding window can be obtained by simultaneously calculating and analyzing the above formulas. ; in, To predetermine the standard deviation of the rating feature values ​​of the most recent n consecutive sliding windows, This is the average of the rating feature values ​​of the most recent n consecutive sliding windows. The preset baseline window size, This is the floor function.

9. A quality inspection system for aluminum profile processing based on multidimensional data analysis, characterized in that, The system is applied to the aluminum profile processing quality inspection method based on multidimensional data analysis as described in any one of claims 1-8, and the system comprises: The data acquisition module is used to collect multi-source data during the processing through industrial cameras, laser sensors, and vibration sensors; The comprehensive scoring calculation module is used to comprehensively analyze the collected multi-source data, obtain the comprehensive quality score of the aluminum profile processed parts, and make quality judgments. The sliding window feature extraction module is used to extract features from the comprehensive quality score sequence based on a preset sliding window to obtain score feature values; The trend analysis module is used to perform trend analysis on the scoring feature value sequence of a continuous sliding window and generate early warnings of processing anomalies. The dynamic window adjustment module is used to dynamically adjust the size of the sliding window based on the scoring feature value; The early warning module is used to execute early warning signals.

Images