An automatic quality inspection method, equipment and system for a steel-wood door production line

Abstract

The application relates to the technical field of ultrasonic detection, in particular to an automatic quality inspection method, a quality inspection equipment and a system for a steel-wood door production line, which comprises the following steps: collecting echo signals of ultrasonic waves reflected by each steel-wood door in the steel-wood door production line, fitting the echo signals, obtaining interface reflection peak values of the echo signals, further obtaining reflection amplitude characteristic values of the echo signals, combining the differences between the interface reflection peak values of each position and adjacent positions, obtaining reflection amplitude fluctuation abnormal values of the echo signals and local wave peak change significant values of the echo signals, further obtaining fluctuation abnormal coefficients of the echo signals and structure defect abnormal values of the echo signals, and performing automatic quality inspection on the steel-wood door production line through quality inspection abnormal values of each steel-wood door. The application can improve the precision of automatic quality inspection on the steel-wood door production line.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of ultrasonic detection, in particular to an automatic quality inspection method, a quality inspection device and a system for a steel-wood door production line. BACKGROUND

[0002] The steel-wood door is a composite door widely used indoors, and the core structure thereof is the combination of an outer steel plate, an inner wood frame and a filler. The steel plate needs to be formed by stamping, edge welding, polishing and surface treatment, and then assembled with a density board which has undergone engraving and plastic coating processes. In order to ensure the stable quality and efficient output of the steel-wood door in the production process, automatic quality inspection has become an indispensable link.

[0003] The gluing assembly of the steel plate and the density board is a key step in the production of the steel-wood door. However, the stamping forming process easily causes the steel plate to be excessively twisted, and the roughness of the surface of the density board also affects the close fitting of the steel plate and the density board, thereby causing defects such as bubbling or warping, which affects the overall quality of the steel-wood door. The ultrasonic method is often used for quality inspection to detect the possible gluing state and internal abnormalities of the steel-wood door. Due to the differences between different materials of the steel-wood door, the speed and attenuation of the ultrasonic wave are different when the ultrasonic wave propagates in different directions, thereby affecting the accuracy and reliability of the detection results. The existing method does not fully consider the influence of material differences on the propagation of ultrasonic signals in the quality inspection process, and there is a problem of insufficient accuracy of automatic quality inspection. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide an automatic quality inspection method, a quality inspection device and a system for a steel-wood door production line, and the technical solutions adopted are as follows:

[0005] In a first aspect, the embodiments of the present application provide an automatic quality inspection method for a steel-wood door production line, comprising the following steps:

[0006] Collecting each position echo signal of ultrasonic wave reflection of each steel-wood door in the steel-wood door production line;

[0007] According to the differences of the internal interfaces of the steel-wood door, the position echo signals are divided into three interfaces, each position echo signal is fitted, the maximum peak value of each interface echo signal after fitting is taken as the interface reflection peak value of each position echo signal, and then the reflection amplitude characteristic value of each position echo signal is obtained, and the reflection amplitude fluctuation abnormal value of each position echo signal is obtained in combination with the difference between the interface reflection peak values of each position and its adjacent position.

[0008] The local peak change significant value of each position echo signal is obtained by the difference between the maximum peak value in the signal between the first interface and the second interface of each position echo signal and all other peak values, combined with the fluctuation degree of all adjacent peak values in the signal between the first interface and the second interface of each position echo signal, and the fluctuation abnormality coefficient of each position echo signal is obtained combined with the reflection amplitude fluctuation abnormal value of each position echo signal, and the frequency domain transformation is performed on each position echo signal, and the structure defect abnormal value of each position echo signal is obtained according to the deviation degree of the frequency amplitude in the frequency domain;

[0009] The average level of the structure defect abnormal value of each position echo signal in each steel-wood door is counted, and the average level and the dispersion degree of the fluctuation abnormality coefficient of all position echo signals of each steel-wood door are combined to obtain the quality inspection abnormal value of each steel-wood door, and then the steel-wood door production line is automatically quality inspected.

[0010] Preferably, the three interfaces of the each position echo signal further comprise:

[0011] The each position echo signal of the ultrasonic wave reflection is processed, the reflection wave generated by the interface between the probe contacting the first layer of steel plate and the density plate is taken as the first interface reflection wave, the reflection wave generated by the interface between the density plate and the second layer of steel plate is taken as the second interface reflection wave, and the interface between the second layer of steel plate and the air is taken as the third interface reflection wave.

[0012] Preferably, the calculation method of the reflection amplitude characteristic value of each position echo signal is:

[0013] ;

[0014] In the formula, is the reflection amplitude characteristic value of each position echo signal; is the first interface reflection wave peak value of each position echo signal; is the second interface reflection wave peak value of each position echo signal; is the third interface reflection wave peak value of each position echo signal; is a preset constant to avoid the denominator being 0.

[0015] Preferably, the calculation formula of the reflection amplitude fluctuation abnormal value of each position echo signal is:

[0016] ;

[0017] C is an abnormal value of fluctuation of reflection amplitude of the echo signal of each position; B is a mean value of Euclidean distance between reflection peak value sequences of each position and its left and right adjacent positions, wherein the reflection peak value sequence is a sequence arranged in time sequence of reflection peak values of each interface of each position and its left and right adjacent positions; A is an eigenvalue of reflection amplitude of the echo signal of each position.

[0018] Preferably, the calculation formula of the local peak variation significant value of the echo signal of each position is:

[0019] ;

[0020] H is a local peak variation significant value of the echo signal of each position; D is a sum value of differences between the maximum peak value and all other peak values in the clutter region of the echo signal of each position; E is a standard deviation of slope between all adjacent peak values in the clutter region of the echo signal of each position, wherein the echo signal between the right end point position of the peak of the first interface reflection wave and the left end point position of the peak of the second interface reflection wave in the echo signal of each position is taken as the clutter region of the echo signal of each position.

[0021] Preferably, the calculation formula of the fluctuation abnormal coefficient of the echo signal of each position is:

[0022] ;

[0023] L is a fluctuation abnormal coefficient of the echo signal of each position; C is an abnormal value of fluctuation of reflection amplitude of the echo signal of each position; H is a local peak variation significant value of the echo signal of each position; is a preset first weight coefficient; is a preset second weight coefficient; wherein, .

[0024] Preferably, the calculation formula of the structural defect abnormal value of the echo signal of each position is:

[0025] ;

[0026] T is a structural defect abnormal value of the echo signal of each position; L is a fluctuation abnormal coefficient of the echo signal of each position; S is a main frequency shift coefficient of the echo signal of each position; R is a high frequency attenuation coefficient of the echo signal of each position;

[0027] Wherein, the echo signal of each position is subjected to frequency domain conversion to obtain the spectrum diagram of the echo signal of each position, and the frequency with the largest amplitude in the spectrum diagram of the echo signal of each position is counted as the main frequency of the spectrum diagram of the echo signal of each position, the component greater than the main frequency is taken as the high frequency region, the sum of the difference values of the main frequencies in the corresponding spectrum diagrams between each position and other positions is counted as the main frequency offset coefficient of the echo signal of each position, and the ratio between the sum of the amplitudes of all frequencies in the high frequency region of the echo signal of each position and the sum of the amplitudes of all frequencies in the spectrum diagram of the echo signal of each position is taken as the high frequency attenuation coefficient of the echo signal of each position.

[0028] Preferably, the calculation formula of the quality inspection abnormal value of each steel-wood door is as follows:

[0029] ;

[0030] In the formula, Q is the quality inspection abnormal value of each steel-wood door; is the mean value of the fluctuation abnormality coefficients of all position echo signals in each steel-wood door; is the standard deviation of the fluctuation abnormality coefficients of all position echo signals in each steel-wood door; and P is a statistical quantity of the trend inspection of the mean value of the structural defect abnormality values of the position echo signals in each steel-wood door and the preceding preset number of steel-wood doors according to the trend inspection algorithm. is an exponential function with e as the base.

[0031] In a second aspect, the embodiments of the present application further provide an automatic quality inspection system of a steel-wood door production line, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the automatic quality inspection method of the steel-wood door production line according to any one of the above embodiments when executing the computer program.

[0032] In a third aspect, the embodiments of the present application further provide an automatic quality inspection device of a steel-wood door production line, which stores a computer program, and the computer program is executed by a processor to implement the automatic quality inspection method of the steel-wood door production line according to any one of the above embodiments.

[0033] As can be seen from the above, the automatic quality inspection method, device and system of the steel-wood door production line provided by the present application have at least the following beneficial effects:

[0034] The present application does not fully consider the influence of material difference on ultrasonic signal propagation in the quality inspection process of the existing method. Through in-depth analysis of the steel-wood door detection process, the amplitude abnormal change and difference characteristics of the reflection wave of each interface in the echo signal of each position, and the local sharp peak and irregular distribution characteristics of the reflection wave in the clutter area of the echo signal of each position, and further combining the abnormal change trend of the quality of the steel-wood door produced on the steel-wood door production line, the quality inspection abnormal value of each steel-wood door is calculated, which can reduce the influence of material difference of the steel-wood door on ultrasonic signal propagation, obtain more accurate steel-wood door quality abnormal characteristics, and perform quality evaluation based on the obtained quality inspection abnormal value, so as to improve the precision of automatic quality inspection of the steel-wood door production line. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0036] Figure 1 A step flow chart of an automatic quality inspection method of a steel-wood door production line provided by the present application;

[0037] Figure 2 A step flow chart of a reflection wave amplitude fluctuation abnormal value acquisition method provided by the present application. DETAILED DESCRIPTION

[0038] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the specific embodiments, structures, characteristics and effects of a steel-wood door production line automatic quality inspection method, quality inspection equipment and system according to the present application are described in detail as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0039] Unless otherwise specified and limited, terms such as “comprising,” “including,” or any other variations thereof are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes said element. Furthermore, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items. All technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0040] The following description, in conjunction with the accompanying drawings, details the specific scheme of the automated quality inspection method, equipment, and system for a steel-wood door production line provided in this application.

[0041] Please see Figure 1 The document illustrates a flowchart of an automated quality inspection method for a steel-wood door production line according to an embodiment of this application, including the following steps:

[0042] Step 1: Collect echo signals from various locations of ultrasonic wave reflections from each steel-wood door in the steel-wood door production line.

[0043] Ultrasonic testing does not damage the material and structure of the steel-wood door, enabling efficient and rapid testing while ensuring product integrity. This significantly shortens quality inspection time and improves overall production efficiency, making it suitable for automated quality inspection processes on production lines. After the steel-wood door completes its processing and assembly, this embodiment uses an ultrasonic thickness gauge to inspect the internal condition of the door. Specifically, the ultrasonic probe is placed on the glued area of ​​the steel-wood door and moved at a constant speed along its surface. A preset time interval is set for data acquisition, allowing continuous acquisition of echo signals corresponding to ultrasonic reflections at different locations on the steel-wood door. Preferably, in this embodiment, the preset time is 0.5 seconds.

[0044] Step 2: Based on the different internal interfaces of the steel-wood door, the echo signals at each position are divided into three interfaces. The echo signals at each position are fitted separately. The maximum peak value of the echo signal at each interface after fitting is taken as the peak value of the reflected wave at each interface of the echo signal at each position. Then, the characteristic value of the reflected wave amplitude of the echo signal at each position is obtained. Combined with the difference between the peak values ​​of the reflected waves at each position and the interfaces at the adjacent positions, the abnormal value of the reflected wave amplitude fluctuation of the echo signal at each position is obtained.

[0045] The steel-wood door is a composite door spliced by an outer steel plate and an inner wood plate. Due to the difference in density between the steel plate and the wood plate, the ultrasonic waves are reflected at the interface between the two. Therefore, by analyzing the waveform change of the ultrasonic signal, macroscopic defects such as debonding in the interior of the steel-wood door can be detected. However, the presence of air bubbles in the glue layer and the difference in ultrasonic wave propagation in different directions can easily cause distortion of the waveform of the ultrasonic signal, such as abnormality in the amplitude, position and shape of the signal, which will interfere with the accurate judgment of the internal state of the steel-wood door.

[0046] Further, when the ultrasonic wave propagates in the steel-wood door, it will be reflected at multiple interfaces such as the interface between the steel plate and the wood, the interior of the steel plate and the interior of the wood. Due to the large difference in acoustic characteristics between the steel plate and the wood, the reflection of the ultrasonic wave at the interface between the two is obvious, and the signal amplitude is large. In this embodiment, the wood in the steel-wood door is taken as an example of a density board. When the steel-wood door is well glued, the ultrasonic wave can propagate smoothly in the material, and the instrument will receive multiple bottom reflection waves. The waveform is relatively regular as a whole, and the interval time and amplitude of the ultrasonic signal reflected at different positions are relatively stable. However, when the steel plate and the density board are not tightly attached and there is a large gap, due to the large difference in acoustic impedance between air and the steel plate and the density board, a large part of the ultrasonic wave energy will be reflected back, and a small part of the ultrasonic wave can pass through the gap to reach the bottom. Therefore, a strong reflection signal will be generated at the gap, and the amplitude of the reflection signal is higher than that of the reflection wave generated at the interface when the steel-wood door is well glued. The gap will also change the propagation path of the ultrasonic wave, causing distortion of the waveform.

[0047] Specifically, the echo signals at different positions of the ultrasonic reflection are processed. In this embodiment, the echo signal collected at a certain position is taken as an example. There are usually three interface reflection waves with large amplitudes in the echo signal. The first interface reflection wave corresponds to the reflection wave generated at the interface between the first layer of steel plate and the density board, the second interface reflection wave corresponds to the reflection wave generated at the interface between the density board and the second layer of steel plate, and the amplitude of the last interface reflection wave is the largest, corresponding to the interface between the second layer of steel plate and the air. When the steel-wood door is well glued, the amplitudes of the first two wave peaks are close to each other and smaller than the amplitude of the last wave peak. If there is a large gap, the first or second wave peak will be significantly larger. In addition, the stratification, non-uniformity in the density board and air bubbles in the glue layer will all affect the reflection of the ultrasonic wave. The amplitudes of these wave peaks are smaller than the amplitudes of the reflection waves generated at the interfaces, and are random.

[0048] Therefore, the least square fitting technique is used to obtain the fitting curve of each position echo signal, and all the maximum values of the fitting curve are calculated as the interface echo signal peak values of each position echo signal. The interface echo signal peak values contain reflection time and amplitude data, and then the peak value with the maximum amplitude in the interface echo signal peak values is taken as the interface reflection peak value of each position echo signal, and the interface reflection peak values are sequentially recorded as , , . Preferably, in the embodiment, the least square fitting technique is a known technique, and the specific process will not be described again.

[0049] Through the above analysis, according to the difference between the interface reflection peak values in each position echo signal, the reflection amplitude characteristic value of each position echo signal is calculated, and in the embodiment, the specific calculation formula is:

[0050] ;

[0051] In the formula, is the reflection amplitude characteristic value of each position echo signal; is the first interface reflection peak value of each position echo signal; is the second interface reflection peak value of each position echo signal; is the third interface reflection peak value of each position echo signal; is a preset constant to avoid a denominator of 0.

[0052] Wherein, the value range of A is (0, 0.1), and in the embodiment A is 0.1; the smaller A is, the more likely it is that the steel plate and the density plate have a large gap, resulting in abnormal fluctuation of the interface reflection amplitude in the echo signal.

[0053] Further, in order to judge the abnormal situation of the interface reflection amplitude fluctuation in the echo signal caused by a large gap, when the steel plate and the density plate have a large gap, the actual propagation path length of the ultrasonic wave at different positions will also change, thereby causing a certain difference in the position of the interface reflection peak value in the echo signal corresponding to different positions. Therefore, the interface reflection peak values of each position and its left and right adjacent positions are arranged in time sequence to obtain the reflection peak value sequence of each position, and the average of the Euclidean distance of the reflection peak value sequence between each position and its left and right adjacent positions is calculated.

[0054] Through the above analysis, according to the difference between the interface reflection peak values in each position echo signal, the reflection amplitude characteristic value of each position echo signal is calculated, and in the embodiment, the specific calculation formula is:

[0055] ;

[0056] In the formula, C is the reflection amplitude fluctuation abnormal value of the echo signal at each position; B is the mean value of the Euclidean distance between the reflection peak value sequence of each position and its left and right adjacent positions, wherein the reflection peak value sequence is the sequence arranged in time sequence of the reflection peak value of each interface of each position and its left and right adjacent positions; and A is the reflection amplitude characteristic value of the echo signal at each position.

[0057] Wherein, C reflects the fluctuation of the interface reflection amplitude value in the echo signal, and the abnormal characteristics of the interface reflection amplitude value between different echo signals, and B reflects the difference characteristics of the interface reflection amplitude value and position caused by the influence of the larger gap between different echo signals. The step flow chart of the method for obtaining the reflection amplitude fluctuation abnormal value provided in the embodiment is shown in Figure 2

[0058] Step three: obtain the local wave peak change significant value of the echo signal at each position by the difference between the maximum peak value and all other peak values in the signal between the first interface and the second interface of the echo signal at each position, and the fluctuation degree of all adjacent peak values in the signal between the first interface and the second interface of the echo signal at each position, and obtain the fluctuation abnormal coefficient of the echo signal at each position by combining the reflection amplitude fluctuation abnormal value of the echo signal at each position, and perform frequency domain transformation on the echo signal at each position, and obtain the structure defect abnormal value of the echo signal at each position according to the deviation degree of the frequency amplitude in the frequency domain.

[0059] In addition, due to the rough surface of the density board and the shape distortion of the steel plate caused by stamping, although the spliced steel-wood door does not have obvious large gaps, the fit degree of the glued position may still be poor, for example, there are glue bubbles and unevenness inside the density board, which will affect the overall quality of the steel-wood door, resulting in some abnormal small wave peaks or clutter in the echo signal, and most of these small wave peaks or clutter are distributed between the first interface reflection wave and the second interface reflection wave. Therefore, the peak width of the first interface reflection wave and the second interface reflection wave of the echo signal at each position is obtained, and the echo signal between the right end point position of the wave peak of the first interface reflection wave and the left end point position of the wave peak of the second interface reflection wave is taken as the clutter region of the echo signal at each position according to the two end point positions in the wave peak width range of the first interface reflection wave and the second interface reflection wave.

[0060] ​Since adjacent peaks with extremely close distances can exist in the clutter region of each position echo signal, in order to more accurately extract the reflected waves existing in the clutter region of each position echo signal, in the embodiment, an AMPD peak detection algorithm is used to obtain all peaks in the clutter region of each position echo signal. If there is a significant local sharp peak in the clutter region of each position echo signal, and the distribution of each peak position and amplitude is more irregular, it means that there is more likely to be a problem of glue bubbles or internal unevenness of the density plate, which further affects the quality of the steel-wood door. Preferably, in the embodiment, the AMPD peak detection algorithm is a known technology, and the specific process is not described again. Further, the difference between the maximum peak and all other peaks in the clutter region of each position echo signal is counted, all the differences are summed, and the slope between all adjacent peaks in the clutter region of each position echo signal is calculated to obtain the standard deviation of all slopes.

[0061] Through the above analysis, according to the difference between the maximum peak and all other peaks in the clutter region of each position echo signal, and combining the fluctuation degree of all adjacent peaks in the clutter region of each position echo signal, the local peak change significant value of each position echo signal is calculated, and in the embodiment, the specific calculation formula is:

[0062] ;

[0063] In the formula, H is the local peak change significant value of each position echo signal; D is the sum of the difference between the maximum peak and all other peaks in the clutter region of each position echo signal; E is the standard deviation of the slope between all adjacent peaks in the clutter region of each position echo signal, wherein the echo signal between the right end point position of the peak of the first interface reflected wave and the left end point position of the peak of the second interface reflected wave in each position echo signal is the clutter region of each position echo signal.

[0064] Wherein, the larger H is, the more obvious the irregular characteristics of the local sharp peak, the peak position and the amplitude distribution in the clutter region of each position echo signal are, and the more likely the steel-wood door has glue bubbles or internal unevenness of the density plate; the larger D is, the more obvious the local sharp peak characteristics in the clutter region of each position echo signal are; the larger E is, the more irregular the peak distribution in the clutter region of each position echo signal is.

[0065] Further, since the reflected wave amplitude fluctuation abnormal value C of each position echo signal reflects the echo signal abnormality caused by the existence of a large gap between the steel plate and the density plate, and the local peak change significant value H of each position echo signal reflects the echo signal abnormality caused by the existence of glue bubbles or internal unevenness of the density plate when there is no obvious large gap, further analysis is made on the possible multiple quality problems of the steel-wood door, and the abnormal conditions of the existence of a large gap or internal unevenness between the steel plate and the density plate are comprehensively considered.

[0066] Through the above analysis, according to the reflection amplitude fluctuation abnormal value of each position echo signal, and combining the local peak change significant value of each position echo signal, the fluctuation abnormal coefficient of each position echo signal is calculated, and in the embodiment, the specific calculation formula is:

[0067] ;

[0068] In the formula, L is the fluctuation abnormal coefficient of each position echo signal; C is the reflection amplitude fluctuation abnormal value of each position echo signal; H is the local peak change significant value of each position echo signal; is a preset first weight coefficient; is a preset second weight coefficient; wherein, ; L reflects the abnormal characteristics of the existence of a large gap between the steel plate and the density plate and internal unevenness. Preferably, in the embodiment, 0.4 is taken, 0.6 is taken.

[0069] Not only the material structure of the steel-wood door at different positions is different, but also the material itself may have certain defects, for example, the internal structure of the density plate at some positions is relatively loose, and there are cracks in the steel plate. Under the comprehensive influence of these internal structure defects of the material, the loose internal structure and the cracks will cause more scattering and reflection of ultrasonic waves in the propagation process, and the ultrasonic wave energy of high frequency components is more easily absorbed by these defects, thereby making the collected echo signal exhibit the characteristics of main frequency shift and high frequency component weakening in the frequency domain. Therefore, in the embodiment, the discrete Fourier transform is used to obtain the frequency spectrum of each position echo signal, and taking the frequency spectrum corresponding to a position as an example, the frequency with the largest amplitude is taken as the main frequency of the frequency spectrum, but the obtained main frequency is usually low, and then the components greater than the main frequency are taken as the high frequency region. Preferably, in the embodiment, the discrete Fourier transform is a known technology, and the specific process will not be repeated.

[0070] Further, the sum of the amplitudes of all frequencies in the high frequency region of each position echo signal and the sum of the amplitudes of all frequencies in the frequency spectrum of each position echo signal are calculated, and the ratio of the two sum values is taken as the high frequency weakening coefficient of each position echo signal caused by the material structure defect, and then the sum of the differences of the main frequencies in the corresponding frequency spectrum between each position and other positions is taken as the main frequency shift coefficient of each position echo signal.

[0071] Through the above content, the sum of the amplitudes of all frequencies in the high frequency region of each position echo signal and the sum of the amplitudes of all frequencies in the frequency spectrum of each position echo signal are calculated, the difference of the main frequencies in the corresponding frequency spectrum between each position and other positions is calculated, and the structure defect abnormal value of each position echo signal is calculated by combining the fluctuation abnormal coefficient of each position echo signal, and in the embodiment, the specific calculation formula is:

[0072] ;

[0073] In the formula, T is the structural defect abnormal value of the echo signal at each position; L is the fluctuation abnormal coefficient of the echo signal at each position; S is the main frequency offset coefficient of the echo signal at each position; and R is the high frequency attenuation coefficient of the echo signal at each position. The frequency spectrum of the echo signal at each position is obtained by frequency domain conversion, and the frequency with the largest amplitude in the frequency spectrum of the echo signal at each position is counted as the main frequency of the frequency spectrum of the echo signal at each position. The components greater than the main frequency are taken as the high frequency region, the sum of the differences between the main frequencies in the corresponding frequency spectra between each position and other positions is counted as the main frequency offset coefficient of the echo signal at each position, and the ratio between the sum of the amplitudes of all frequencies in the high frequency region of the echo signal at each position and the sum of the amplitudes of all frequencies in the frequency spectrum of the echo signal at each position is taken as the high frequency attenuation coefficient of the echo signal at each position.

[0074] In the formula, T reflects the abnormal characteristics of the gluing effect and the material defect state; R reflects the attenuation characteristics of the high frequency components of the echo signal at each position; and S reflects the offset degree of the main frequencies of the echo signals between each position and other positions.

[0075] In addition, there may be problems such as improper use of glue and insufficient pressure during assembly on the production line of the steel-wood door, which makes it difficult to maintain the stability of the quality of the steel-wood door in batch production. The worse the overall quality of the produced steel-wood door is, the more obvious the trend that the fluctuation abnormal coefficient of the echo signal at each position obtained by real-time detection gradually increases. Therefore, the mean value of the structural defect abnormal value of the echo signal at each position in each steel-wood door is calculated, and the Mann-Kendall test algorithm is used to calculate the trend test statistic of each steel-wood door and the mean values of the previous preset number of steel-wood doors, wherein the value of the preset number ranges from 8 to 10. Preferably, in the present embodiment, the preset number is 9; the Mann-Kendall test algorithm is a known technology, and the specific process is not described again.

[0076] Step four: The average level of the structural defect abnormal value of the echo signal at each position in each steel-wood door is counted, and the average level and the dispersion degree of the fluctuation abnormal coefficient of the echo signal at all positions of each steel-wood door are combined to obtain the quality inspection abnormal value of each steel-wood door, and then the automatic quality inspection of the steel-wood door production line is carried out.

[0077] Through the above analysis, the average level of the structural defect abnormal value of the echo signal at each position in each steel-wood door is calculated, the average level of each steel-wood door and the previous preset number of steel-wood doors is tested and counted, and the average level and the dispersion degree of the fluctuation abnormal coefficient of the echo signal at all positions of each steel-wood door are combined to calculate the quality inspection abnormal value of each steel-wood door. In the present embodiment, the specific calculation formula is:

[0078] ;

[0079] Q is the quality inspection abnormal value of each steel-wooden door; is the mean value of the fluctuation abnormal coefficient of the echo signal at all positions in each steel-wooden door; is the standard deviation of the fluctuation abnormal coefficient of the echo signal at all positions in each steel-wooden door; P is a statistical quantity for trend inspection of the mean value of the structural defect abnormal value of the echo signal at each position in each steel-wooden door and a preset number of steel-wooden doors in front of the steel-wooden door according to a trend inspection algorithm; is an exponential function with e as the base.

[0080] wherein, , respectively reflect the overall quality state and consistency characteristics of each steel-wooden door; Q reflects the overall state and the change trend characteristics of the quality abnormality of the steel-wooden door on the production line; the greater P is, the worse the overall quality of the steel-wooden door produced on the production line is.

[0081] Preferably, in the embodiment, the steel-wooden door detection process is analyzed in depth, the abnormal change and difference characteristics of the interface reflection wave in the echo signal at each position, and the local sharp peak and irregular distribution characteristics of the reflection wave in the clutter region of the echo signal at each position are analyzed, and then the quality inspection abnormal value of each steel-wooden door is calculated in combination with the change trend of the quality abnormality of the steel-wooden door produced on the production line. The embodiment is based on the quality inspection abnormal value for automatic quality inspection. The quality inspection abnormal value is normalized by using the tanh function, and the steel-wooden door quality evaluation interval is set as follows: [0, 0.5] for good quality, (0.5, 0.7) for general quality, and [0.7, 1] for poor quality. The quality inspection is performed according to the quality inspection abnormal value detected in real time on the steel-wooden door production line, so as to improve the accuracy of the automatic quality inspection of the steel-wooden door production line. Preferably, in the embodiment, the tanh function is a known technology, and the specific process is not described again.

[0082] Based on the same inventive concept as the above method, the embodiment of the present application also provides an automatic quality inspection system for a steel-wooden door production line, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the methods in the above automatic quality inspection method for a steel-wooden door production line.

[0083] Meanwhile, the embodiment of the present application also provides an automatic quality inspection device for a steel-wooden door production line, which stores a computer program, and the computer program is executed by the processor to implement the above automatic quality inspection method for a steel-wooden door production line.

[0084] It can be understood that the above-mentioned embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments. And the above describes specific embodiments of the specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0085] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0086] The above is only an embodiment of the application, and is not used to limit the scope of the application. Any equivalent structure or equivalent process transformation using the content of the specification and the drawings, or direct or indirect application in other related technical fields, is also included in the protection scope of the application.

Claims

1. An automatic quality inspection method for a steel-wood door production line, characterized in that, The method comprises the following steps: Collecting echo signals of each position of the steel-wood door in the production line; According to the different internal interfaces of the steel-wood door, the echo signals of each position are divided into three interfaces, and each position echo signal is fitted, the maximum peak value of each interface echo signal after fitting is taken as the reflection peak value of each interface of each position echo signal, and then the reflection amplitude characteristic value of each position echo signal is obtained, and the difference between the reflection peak value of each position and its adjacent position is obtained to obtain the reflection amplitude fluctuation abnormal value of each position echo signal; The difference between the maximum peak value and all other peak values in the signal between the first interface and the second interface of each position echo signal is obtained, the fluctuation degree of all adjacent peak values in the signal between the first interface and the second interface of each position echo signal is obtained, the local peak change significant value of each position echo signal is obtained, the fluctuation abnormal coefficient of each position echo signal is obtained by combining the reflection amplitude fluctuation abnormal value of each position echo signal, and the frequency domain transformation of each position echo signal is carried out, the structural defect abnormal value of each position echo signal is obtained according to the deviation degree of the frequency amplitude in the frequency domain; The average level of the structural defect abnormal value of each position echo signal in each steel-wood door is counted, the average level and the dispersion degree of the fluctuation abnormal coefficient of all position echo signals of each steel-wood door are combined to obtain the quality inspection abnormal value of each steel-wood door, and then the automatic quality inspection of the steel-wood door production line is carried out; The echo signals of each position divided into three interfaces further comprise: The echo signals of each position reflected by the ultrasonic wave are processed, the reflection wave generated between the interface of the first layer of steel plate and the density plate contacted by the probe is taken as the first interface reflection wave, the reflection wave generated between the interface of the density plate and the second layer of steel plate is taken as the second interface reflection wave, and the interface of the second layer of steel plate contacted with air is taken as the third interface reflection wave; The calculation method of the reflection amplitude characteristic value of each position echo signal is: ； wherein, is a reflection amplitude eigenvalue of the echo signal of each position; is a first interface reflection peak value of the echo signal of each position; is a second interface reflection peak value of the echo signal of each position; is a third interface reflection peak value of the echo signal of each position; is a preset constant to avoid the denominator being 0; The calculation formula of the reflection amplitude fluctuation abnormal value of each position echo signal is: ； In the formula, C is the reflection amplitude fluctuation abnormal value of each position echo signal, B is the average value of the Euclidean distance of the reflection peak value sequence between each position and its left and right adjacent positions, wherein the reflection peak value sequence is the sequence arranged in time sequence according to the reflection peak value of each position and its left and right adjacent positions, and A is the reflection amplitude characteristic value of each position echo signal; The calculation formula of the local peak change significant value of each position echo signal is: ； In the formula, H is the local peak change significant value of each position echo signal, D is the sum of the differences between the maximum peak value and all other peak values in the clutter area of each position echo signal, and E is the standard deviation of the slope between all adjacent peak values in the clutter area of each position echo signal, wherein the echo signal between the right end point position of the wave peak of the first interface reflection wave and the left end point position of the wave peak of the second interface reflection wave in each position echo signal is taken as the clutter area of each position echo signal; The calculation formula of the fluctuation abnormal coefficient of each position echo signal is: ； In the formula, L is the fluctuation abnormal coefficient of the echo signal at each position; C is the reflection amplitude fluctuation abnormal value of the echo signal at each position; H is the local peak change significant value of the echo signal at each position; is a preset first weight coefficient; is a preset second weight coefficient; wherein, ; The calculation formula of the structural defect abnormal value of each position echo signal is: ； In the formula, T is a structural defect abnormal value of each position echo signal; L is a fluctuation abnormal coefficient of each position echo signal; S is a main frequency offset coefficient of each position echo signal; and R is a high frequency attenuation coefficient of each position echo signal. In the formula, T is a structural defect abnormal value of each position echo signal; L is a fluctuation abnormal coefficient of each position echo signal; S is a main frequency offset coefficient of each position echo signal; and R is a high frequency attenuation coefficient of each position echo signal. The calculation formula of the quality inspection abnormal value of each steel-wood door is as follows: ； In the formula, Q is the abnormal value of quality inspection of each steel-wooden door; is the mean value of the fluctuation abnormal coefficient of the echo signal at all positions in each steel-wooden door; is the standard deviation of the fluctuation abnormal coefficient of the echo signal at all positions in each steel-wooden door; P is a statistic quantity for trend inspection of the mean value of the structural defect abnormal value of the echo signal at each position in each steel-wooden door and the preset number of steel-wooden doors in front of the steel-wooden door according to the trend inspection algorithm; is the exponential function with base e.

2. An automatic quality inspection system for a steel-wood door production line, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor executes the computer program to realize the steps of the automatic quality inspection method of the steel-wood door production line.

3. An automatic quality inspection equipment for a steel-wood door production line, wherein a computer program is stored in the equipment, characterized in that, The computer program is executed by the processor to realize the automatic quality inspection method of the steel-wood door production line.

Images