A method for monitoring abnormal operation of a turret-type plate-swinging machine

Abstract

The present invention relates to the field of vibration detection technology, and specifically to a method for monitoring the abnormal operation of a turret-type plate-swinging machine. The method combines the characteristics of low frequency and high power of impact-like vibration. Within a periodic working time period, the intra-cycle power contrast is obtained according to the difference between the power performance of the characteristic frequency of each power peak in the frequency spectrum of each local time period; the inter-cycle power contrast is obtained according to the difference between the power performance of the characteristic frequency in the frequency spectrum of each matching time period between the cycles; further, in combination with the characteristics of low frequency, the degree of vibration abnormality corresponding to each power peak that characterizes the possibility of impact-like vibration is obtained according to the intra-cycle power contrast and the inter-cycle power contrast as well as the size of the characteristic frequency; thereby more accurate monitoring of the abnormal operation vibration of the turret-type plate-swinging machine is performed according to the degree of vibration abnormality.

Description

Technical Field

[0001] The invention relates to the technical field of vibration detection, and in particular to a method for monitoring abnormal operation of a turret-type plate-stirring machine. Background Art

[0002] The turret plate-turning machine is a device used in automated production lines, usually in highly automated industrial production environments. In specific production environments, the turret plate-turning machine is usually used for workpiece transfer, temporary storage, process arrangement, automated assembly and quality inspection; in these scenarios, the turret plate-turning machine ensures the smooth and efficient operation of the production process through high-speed motion, precise positioning and complex automated control systems.

[0003] During the automated production process, the transmission components of the turret-type plate-switching machine will inevitably wear out, resulting in inaccurate positioning of the workpiece during transport, affecting working stability and efficiency; and the wear of the transmission components is often accompanied by abnormal vibration of the components. Therefore, it is necessary to monitor the vibration data of the transmission shaft or transmission components of the turret-type plate-switching machine for operational abnormalities and detect abnormal wear in a timely manner.

[0004] Considering that when the transmission parts are abnormally worn, the vibration amplitude of the abnormal vibration data generated is larger than the normal vibration amplitude, the prior art usually monitors the abnormal operation of the turret plate machine according to a pre-set vibration amplitude threshold. When the vibration amplitude of the vibration data is greater than the vibration amplitude threshold, it indicates that the transmission parts of the turret plate machine are abnormally worn, that is, the operation is abnormal. However, the method of monitoring the abnormal operation of the turret plate machine by the vibration amplitude threshold can only detect the abnormal operation of the turret plate machine when the wear of the transmission parts reaches a certain degree of wear; and the corresponding degree of wear of the transmission parts after the wear occurs is continuously increased with the operation, which leads to the method of the prior art being unable to detect the wear before the transmission parts reach a certain degree of wear, that is, the method of the prior art monitoring the abnormal operation of the turret plate machine by the pre-set vibration amplitude threshold has poor accuracy and real-time performance in the wear detection of the transmission parts of the turret plate machine, resulting in poor accuracy in the monitoring of the abnormal operation of the turret plate machine. Summary of the invention

[0005] The present application provides a method for monitoring the abnormal operation of a turret-type plate-swinging machine. The method, based on detecting the more prominent power peak in each local time period, obtains the degree of vibration abnormality of the power peak according to the contrast degree of the power peak within a working cycle and the contrast degree of the power peak between working cycles, and combined with the low-frequency and high-power characteristics of impact-like vibration. The turret-type plate-swinging machine is monitored for abnormal operation according to the degree of vibration abnormality, which solves the problem in the prior art that the wear of the transmission parts cannot be detected before the wear reaches a certain degree, improves the accuracy and real-time performance of the wear detection of the transmission parts of the turret-type plate-swinging machine, and makes the accuracy of the abnormal operation monitoring of the turret-type plate-swinging machine higher.

[0006] The first aspect of the present application provides a method for monitoring abnormal operation of a turret-type plate-swinging machine, comprising:

[0007] On the transmission shaft of the turret-type plate-stirring machine, all vibration amplitude data in each periodic working time period are collected by a vibration sensor; each periodic working time period is divided into at least two local time periods; wherein the division method of all periodic working time periods is the same;

[0008] Obtain each power peak in the corresponding frequency spectrum of each local time period and the characteristic frequency corresponding to the power peak; determine the power contrast within the period corresponding to each power peak according to the deviation distribution of all powers corresponding to the characteristic frequency in the frequency spectrum of all local time periods relative to the power peak;

[0009] Obtain a matching time period in which each local time period in each periodic working time period has the same periodic position in other periodic working time periods; in the local time period, determine the inter-cycle power contrast corresponding to each power peak value according to the distribution of deviations between all powers corresponding to each power peak value and the corresponding characteristic frequency in the frequency spectrum of all matching time periods;

[0010] The degree of vibration abnormality of each power peak is determined according to the characteristic frequency corresponding to each power peak, the power contrast within the cycle and the power contrast between the cycles; and the abnormal operation of the turret plate swing machine is monitored according to the degree of vibration abnormality.

[0011] In the above scheme, when the transmission parts have slight deformation or slight wear, impact-like vibration will occur, and the impact-like vibration will show the characteristics of low frequency and high amplitude; because the energy performance of impact-like vibration is more prominent, the power peak in the local time period is obtained for analysis to further determine whether the transmission parts have impact-like vibration, and thus further determine the degree of vibration abnormality. Further considering that the normal operation of the turret-type plate-swinging machine corresponds to periodic start-stop movement, the force on different positions of the transmission parts is uneven. Therefore, when abnormal wear occurs, the wear conditions at different positions of the transmission parts usually show different degrees of wear, that is, in the frequency spectrum corresponding to different local time periods, the power size deviation corresponding to the same frequency is large; therefore, the power deviation corresponding to different local time periods in the same periodic working time period for the frequency of the corresponding power peak that may represent the impact-like vibration is calculated, and the power contrast within the period obtained by calculation preliminarily represents the possibility that the power peak is an abnormal impact-like vibration. Further considering that the work of the turret-type plate-swinging machine is cyclical, when there is no wear on the transmission shaft, the frequency performance and power performance of different working cycles are similar; however, when wear occurs, the contact surfaces of the transmission mechanisms in different working cycles are different, resulting in different power performances of the frequencies corresponding to the wear in different working cycles. Specifically, the power corresponding to the same frequency at the same position in different cycles will deviate. Therefore, the power performance deviation of the frequency corresponding to the power peak in the matching time period corresponding to the same position in different working cycles is further calculated, and the possibility of the power peak being an impact-like vibration anomaly is further characterized by the calculated inter-cycle power contrast; finally, on the basis of the inter-cycle power contrast and the intra-cycle power contrast, combined with the characteristics of the low frequency of impact-like vibration, the degree of vibration anomaly corresponding to each power peak is obtained, which characterizes the possibility of impact-like vibration; thereby more accurate monitoring of the operation abnormality of the turret-type plate-swinging machine is performed according to the degree of vibration anomaly.

[0012] In an embodiment of the first aspect of the present application, the method for obtaining the power peak value includes:

[0013] According to all the vibration amplitude data in the local time period, all the frequency data points in the spectrum diagram corresponding to the local time period are obtained by using the time-frequency transformation method;

[0014] Performing cluster analysis on all frequency data points in the spectrum graph by using mean shift clustering to determine at least two frequency data point clusters;

[0015] The maximum power among all frequency data points corresponding to each frequency data point cluster is taken as the power peak value of each frequency data point cluster.

[0016] In the above scheme, frequencies with higher energy, that is, higher power, usually correspond to peaks or dense areas on the spectrum graph. Therefore, the mean shift algorithm based on density clustering is used for clustering analysis, which can make each cluster obtained concentrated at the power peak position of the spectrum graph, so that the power peak that may characterize the impact vibration located in each frequency data point cluster is more accurate.

[0017] In an embodiment of the first aspect of the present application, the method for obtaining the power contrast ratio within a period includes:

[0018] The other local time periods corresponding to each local time period are used as comparison data segments;

[0019] The characteristic frequency corresponding to each power peak in each local time period is used as the comparison frequency;

[0020] The numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of each comparison data segment and the power peak is used as the local comparison deviation of the power peak in each comparison data segment;

[0021] The local contrast deviations of the power peak values ​​in all contrast data segments are integrated to determine the intra-cycle power contrast ratio corresponding to each power peak value in each local time segment.

[0022] In the above scheme, based on the power deviation characteristics of the impact-like vibration, the local contrast deviation of the deviation between the corresponding power of the contrast frequency corresponding to the power peak in all contrast data segments and the power peak is calculated; further, based on the intra-periodic power contrast obtained by integrating all the local contrast deviations corresponding to the power peak, the possibility of impact-like vibration abnormality corresponding to the power peak is more accurately characterized.

[0023] In an embodiment of the first aspect of the present application, the method for obtaining the matching time period includes:

[0024] Arrange all local time periods corresponding to each periodic working time period in time order to obtain a local time period sequence corresponding to each periodic working time period;

[0025] Using the index value of each local time period in each periodic working time period in the local time period sequence as the matching index value of each local time period;

[0026] Each local time period in each periodic working time period is sequentially used as a target time period; other periodic working time periods outside the periodic working time period where the target time period is located are used as comparison working time periods;

[0027] In each comparison working time period, a local time period having the same matching index value as the target time period is used as a matching time period of the target time period.

[0028] In the above scheme, for each local time period, its corresponding matching time period is the local time period representing the same cycle position in different working cycles of the turret plate placing machine; and the division method of the local time periods of different cycle working time periods is the same. Therefore, in the local time period sequence of different cycle working time periods, matching time periods are matched with the same index value, so that each local time period can be more accurately obtained. The matching time period representing the same cycle position in different cycle working time periods; making subsequent matching more in line with objective facts.

[0029] In an embodiment of the first aspect of the present application, the method for obtaining the inter-cycle power contrast includes:

[0030] Using the characteristic frequency corresponding to each power peak value in the local time period as the comparison frequency;

[0031] The numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of the matching time period and the power peak is used as the matching comparison deviation of the power peak in each matching time period;

[0032] The matching contrast deviations of the power peak values ​​in all matching time periods are integrated to determine the inter-cycle power contrast corresponding to each power peak value in each local time period.

[0033] In the above scheme, according to the characteristic that the degree of wear of abnormal wear will gradually deepen as the work progresses, while the area without wear remains unchanged, the frequency size corresponding to the characteristic frequency is integrated with the power peak, that is, the deviation between the power and the power peak in each matching time period is integrated according to the comparison frequency, so that the inter-cycle power contrast can more accurately characterize the power change of the frequency corresponding to the power peak in different periodic working time periods, thereby more accurately characterizing the possibility of impact-like vibration abnormality corresponding to the power peak.

[0034] In an embodiment of the first aspect of the present application, the method for obtaining the degree of vibration abnormality includes:

[0035] After the characteristic frequency corresponding to each power peak, the intra-cycle power contrast and the inter-cycle power contrast are fused, the vibration abnormality degree of each power peak is determined by means of a normalization method.

[0036] In the above scheme, the characteristics of power deviation at different positions within the cycle of the abnormal frequency corresponding to the impact-like vibration, the characteristics of power change at the same position during the cycle, and the characteristics of low frequency and high power are combined through the normalization method, so that the characterization of the possibility of impact-like vibration abnormality corresponding to the power peak is more accurate.

[0037] In an embodiment of the first aspect of the present application, the method for monitoring the abnormal operation of the turret-type plate-swinging machine according to the abnormal vibration degree includes:

[0038] In each periodic working time period, the degree of operation abnormality of each local time period is determined according to the overall magnitude of the vibration abnormality of all power peaks corresponding to each local time period;

[0039] When there is a local time period in which the degree of operational abnormality is greater than a preset abnormality threshold, it is determined that the turret plate swinging machine is operating abnormally.

[0040] In the above scheme, the degree of operation abnormality is characterized by combining the overall magnitude of the vibration abnormality of all power peaks in a local time period, which can make the obtained degree of operation abnormality more credible and further make the monitoring of the operation abnormality of the turret-type plate swing machine more accurate.

[0041] In an embodiment of the first aspect of the present application, after the abnormal operation monitoring of the turret plate swing machine according to the abnormal vibration degree is performed, the process further includes:

[0042] When the turret plate-swinging machine operates abnormally, an abnormal warning signal is sent out through the alarm.

[0043] In an embodiment of the first aspect of the present application, the method for acquiring the local time period includes:

[0044] The periodic working time period is divided into a preset number of local time periods of the same length in chronological order.

[0045] Dividing the periodic working time period into local time periods of the same length can facilitate the matching of local time periods representing the same periodic position in different periodic working time periods, thereby improving the accuracy of the calculated vibration abnormality degree.

[0046] In an embodiment of the first aspect of the present application, the time-frequency transformation method adopts short-time Fourier transform.

[0047] The short-time Fourier transform has a relatively high computational efficiency for long-time signals, and the representation of the energy of different frequencies in the obtained spectrum, that is, the power distribution, is more intuitive, which facilitates the analysis of the degree of vibration abnormality.

[0048] In a second aspect, the present application provides a system for monitoring abnormal operation of a turret-type plate-swinging machine, the system comprising:

[0049] The data acquisition preprocessing module is used to collect all vibration amplitude data in each periodic working time period on the transmission shaft of the turret-type plate-stirring machine through a vibration sensor; each periodic working time period is divided into at least two local time periods; wherein the division method of all periodic working time periods is the same;

[0050] The first determination module is used to obtain each power peak in the corresponding frequency spectrum of each local time period and the characteristic frequency corresponding to the power peak; according to the deviation distribution of all powers corresponding to the characteristic frequency in the frequency spectrum of all local time periods relative to the power peak, determine the power contrast within the period corresponding to each power peak;

[0051] The second determination module is used to obtain a matching time period in which each local time period in each periodic working time period has the same periodic position in other periodic working time periods; in the local time period, the inter-cycle power contrast corresponding to each power peak is determined according to the deviation distribution between all powers corresponding to each power peak and the corresponding characteristic frequency in the frequency spectrum of all matching time periods;

[0052] The abnormality monitoring module is used to determine the degree of vibration abnormality of each power peak according to the characteristic frequency corresponding to each power peak, the power contrast within the cycle and the power contrast between the cycles; and perform abnormal operation monitoring of the turret plate swing machine according to the degree of vibration abnormality.

[0053] In a third aspect, the present application provides a computer device, comprising a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method of the first aspect of the present application or any embodiment of the first aspect.

[0054] In a fourth aspect, the present application provides a computer program product, comprising a computer program code, which, when executed, performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0055] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 A flow chart of a method for monitoring abnormal operation of a turret-type plate-stirring machine provided by one embodiment of the present invention;

[0058] Figure 2 A waveform diagram showing the vibration amplitude data of a transmission shaft of a turret-type plate-swinging machine provided by one embodiment of the present invention;

[0059] Figure 3 A flow chart of a method for obtaining a power peak value of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention;

[0060] Figure 4 A flow chart of a method for obtaining power contrast ratio within a cycle of a method for monitoring abnormal operation of a turret-type plate-stirring machine provided by one embodiment of the present invention;

[0061] Figure 5 A flow chart of a matching time period acquisition method of a method for monitoring abnormal operation of a turret-type plate-stirring machine provided by an embodiment of the present invention;

[0062] Figure 6 A flow chart of a method for obtaining power contrast ratio between cycles of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention;

[0063] Figure 7 A structural diagram of a turret-type plate-stirring machine operation abnormality monitoring system provided by one embodiment of the present invention;

[0064] Figure 8 A schematic diagram of the structure of a turret-type plate-stirring machine operation abnormality monitoring and alarm device provided by another embodiment of the present invention;

[0065] Fig. 9 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of a method for monitoring the abnormal operation of a turret-type plate-swinging machine proposed in accordance with the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment, and specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0067] Unless defined otherwise, 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 invention belongs.

[0068] The specific scheme of the method for monitoring abnormal operation of a turret-type plate-stirring machine provided by the present invention is described in detail below with reference to the accompanying drawings.

[0069] The present application embodiment provides a method for monitoring abnormal operation of a turret-type plate-swinging machine. Figure 1 , which shows a flow chart of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention, the method comprising:

[0070] Step S101: On the transmission shaft of the turret plate placing machine, all vibration amplitude data in each periodic working time period are collected by a vibration sensor; each periodic working time period is divided into at least two local time periods; wherein all periodic working time periods are divided in the same manner.

[0071] The wear of the transmission components of the turret-type plate-swinging machine is often accompanied by abnormal vibration of the components, so it is necessary to collect vibration amplitude data during the operation of the turret-type plate-swinging machine; and the embodiment of the present invention is aimed at the abnormal wear of the transmission structure caused by the daily operation of the turret-type plate-swinging machine, so a vibration sensor is installed on the rotating shaft of the turret-type plate-swinging machine; and the normal operation of the turret-type plate-swinging machine is a periodic start-stop movement, that is, corresponding to the moving state at startup and the stationary state at stop; and the required abnormal vibration amplitude data can only be collected during the startup working time period, so when the turret-type plate-swinging machine is in a moving state at startup, the vibration amplitude data at each sampling moment in each periodic working time period is collected by the vibration sensor.

[0072] Preferably, in some possible implementations of the embodiments of the present invention, the method for acquiring the local time period includes:

[0073] Dividing the periodic working time period into a preset number of local time periods of the same time length in time order; dividing the periodic working time period into local time periods of the same time length can facilitate the matching of local time periods representing the same period position in different periodic working time periods, thereby improving the accuracy of the calculated vibration abnormality degree. In one implementation of the embodiment of the present invention, the preset number is set to 100.

[0074] In one implementation of the embodiment of the present invention, the sampling frequency is set to 4kHz. In one implementation of the embodiment of the present invention, the total number of periodic working time periods collected is 50. It should be noted that the implementer can adjust the sampling frequency, the preset number and the total number of periodic working time periods collected according to the specific implementation environment, which will not be further described here. Please refer to Figure 2, which shows a vibration amplitude data waveform display diagram of a turret-type plate-swinging machine transmission shaft provided by an embodiment of the present invention. In the vibration amplitude data waveform display diagram, the horizontal axis represents time, and the vertical axis represents the vibration amplitude. The vibration amplitude change can be observed intuitively through the vibration amplitude data fluctuation display diagram, and it is convenient to perform subsequent time-frequency conversion to obtain the spectrum diagram required by the present invention.

[0075] Step S102: Obtain each power peak in the corresponding spectrum diagram of each local time period and the characteristic frequency corresponding to the power peak; determine the power contrast within the period corresponding to each power peak according to the deviation distribution of all powers corresponding to the characteristic frequency in the spectrum diagram of all local time periods relative to the power peak.

[0076] When a transmission component has a slight deformation or slight wear, a quasi-impact vibration will occur. The slight deformation or slight wear will increase the degree of wear as the work continues until the transmission component is damaged. Therefore, by detecting the quasi-impact vibration phenomenon of the transmission component in advance, the abnormality can be monitored in advance before the impact of the wear abnormality expands, and the corresponding monitoring is more real-time. Quasi-impact vibration data has the characteristics of low frequency and high energy, but not all low-frequency and high-energy characteristics are caused by quasi-impact vibration, so it is necessary to analyze the power peak that represents high energy.

[0077] The normal operation of the turret-type plate-swinging machine corresponds to periodic start-stop movements, and the forces at different positions of the transmission components are uneven. Therefore, when abnormal wear occurs, the wear conditions at different positions of the transmission components usually show different degrees of wear; therefore, if the power peak is caused by real impact-like vibration, then the characteristic frequency corresponding to the power peak will produce a large difference in power performance in the spectrum diagram of different local time periods of the same periodic working time period, and a larger intra-cycle power contrast will be obtained at this time. On the contrary, if the power peak is not caused by real impact-like vibration, that is, it is not abnormal, then the power peak is usually the inherent vibration generated in the periodic working time period, that is, the power performance of the characteristic frequency corresponding to the power peak in the spectrum diagram of different local time periods of the same periodic working time period is usually relatively stable, and this corresponds to a smaller intra-cycle power contrast. Therefore, the larger the intra-cycle power contrast, the more likely the corresponding power peak is caused by real impact-like vibration, that is, the more likely it is to correspond to abnormal vibration.

[0078] Step S103: Obtain the matching time period in each local time period in each periodic working time period that has the same periodic position in other periodic working time periods; in the local time period, determine the inter-cycle power contrast corresponding to each power peak according to the deviation distribution between all powers corresponding to each power peak and the corresponding characteristic frequency in the spectrum diagram of all matching time periods.

[0079] The operation of the turret plate-swinging machine is cyclical. When there is no wear on the transmission shaft, the frequency performance and power performance of different working cycles are similar; however, when wear occurs, the contact surface of the transmission mechanism in different working cycles is different, which leads to the frequency corresponding to the power peak of the real impact-like vibration wear anomaly. It is impossible to find similar or similar power performance in different working cycle time periods, that is, the corresponding power performance is quite different, resulting in the calculated power contrast ratio between cycles being usually large; on the contrary, when there is no wear, the appearance of the power peak should be the inherent vibration generated in the periodic working time period, which is usually related to the internal structure of the turret plate-swinging machine. Therefore, the characteristic frequency of the power peak will usually produce similar or similar power performance at the same period position in different periodic working time periods, and the calculated power contrast ratio between cycles is usually small. Therefore, the larger the power contrast ratio between cycles, the more likely the corresponding power peak is to be generated by real impact-like vibration, that is, the more likely it is to correspond to vibration anomalies.

[0080] Step S104: Determine the degree of vibration abnormality of each power peak value according to the characteristic frequency corresponding to each power peak value, the intra-cycle power contrast ratio and the inter-cycle power contrast ratio; and perform abnormal operation monitoring of the turret plate swinging machine according to the degree of vibration abnormality.

[0081] After processing from step S101 to step S103, the inter-cycle power contrast and intra-cycle contrast are obtained, both of which characterize the possibility that the power peak is a real impact-like vibration. In addition to the characteristics of high energy, impact-like vibration also has the characteristics of low frequency. Therefore, on the basis of the inter-cycle power contrast and intra-cycle contrast, the possibility of impact-like vibration anomalies is further analyzed in combination with the characteristic frequency corresponding to the power peak, so as to obtain a more accurate degree of vibration anomaly, that is, the possibility that the power peak is caused by impact-like vibration anomaly. Therefore, more accurate monitoring of the operation abnormality of the turret-type plate swing machine can be performed according to the degree of vibration anomaly.

[0082] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the power peak value in step S102 includes: Figure 3 , which shows a flow chart of a method for obtaining a power peak value of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention, the method comprising:

[0083] Step S301: Obtain all frequency data points in the frequency spectrum corresponding to the local time period by using a time-frequency transformation method based on all vibration amplitude data in the local time period.

[0084] The spectrum diagram can more intuitively display the frequency and power distribution of vibration data, thereby more accurately screening out the power peaks that may characterize impact-like vibrations based on the low frequency and high energy characteristics of impact-like vibrations.

[0085] In some possible implementations of the embodiments of the present invention, the time-frequency transformation method uses short-time Fourier transform. The computational efficiency of short-time Fourier transform for long-time signals is relatively high, and the characterization of the energy of different frequencies in the obtained spectrum diagram, that is, the power distribution, is more intuitive, which facilitates the analysis of the degree of vibration abnormality. It should be noted that in other implementations of the embodiments of the present invention, other time-frequency transformation methods, such as continuous wavelet transform, may also be used, which will not be further elaborated here.

[0086] Step S302: performing cluster analysis on all frequency data points in the frequency spectrum using mean shift clustering to determine at least two frequency data point clusters.

[0087] Mean shift clustering can make the frequency data points in the frequency data point clustering cluster concentrated in the dense area corresponding to the peak on the spectrum graph, and the peak corresponds to the impact-like vibration with higher energy performance or power performance. Therefore, with the help of the mean shift clustering algorithm, the required power peak that may characterize the impact-like vibration can be more accurately determined. In a specific implementation of an embodiment of the present invention, 30 seed points are evenly distributed in the spectrum graph, and the mean shift bandwidth is set to 20 for mean shift clustering. It should be noted that in other implementations of the embodiment of the present invention, the number of seed points and the size of the mean shift bandwidth can be adjusted according to the specific implementation environment, and mean shift clustering is a prior art well known to those skilled in the art, and will not be further limited or elaborated here.

[0088] Step S303: taking the maximum power among all frequency data points corresponding to each frequency data point cluster as the power peak value of each frequency data point cluster.

[0089] Shock-like vibrations have the characteristic of high power, so selecting the maximum power in the frequency data point cluster can make the power peak value that may characterize the shock-like vibration more accurate.

[0090] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the power contrast ratio within a period in step S102 includes: Figure 4 , which shows a flow chart of a method for obtaining power contrast ratio within a cycle of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention, the method comprising:

[0091] Step S401: taking other local time periods corresponding to each local time period as comparison data segments.

[0092] Obtaining the comparison data segment corresponding to each local time period can clearly distinguish the local data segment for analysis from the local data segment used for comparison, making the subsequent analysis process clearer or more intuitive.

[0093] Step S402: taking the characteristic frequency corresponding to each power peak in each local time period as the comparison frequency.

[0094] Since the power peak is caused by real impact-like vibration, the characteristic frequency corresponding to the power peak will produce different power performances in the spectrum diagram of different local time periods of the same cycle working time period. Therefore, it is necessary to analyze the power performance in the spectrum diagram of different local time periods according to the value of the characteristic frequency corresponding to the power peak; however, since there are characteristic frequencies corresponding to the power peak in different local time periods, in order to prevent confusion, the comparison frequency is defined as the value of the characteristic frequency to prevent confusion or unclear understanding; it should be noted that the characteristic frequency corresponding to the power peak is the frequency size corresponding to the power peak in the spectrum diagram of the corresponding local data segment. The purpose of using the characteristic frequency for expression here is to mark the frequency of the power peak to prevent confusion.

[0095] Step S403: taking the numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of each comparison data segment and the power peak as the local comparison deviation of the power peak in each comparison data segment.

[0096] In a specific implementation of an embodiment of the present invention, the absolute value of the difference between the power corresponding to the comparison frequency in the frequency diagram of the comparison data segment and the power peak is used as the local comparison deviation of the power peak in each comparison data segment; the larger the local comparison deviation, the larger the deviation of the power corresponding to the comparison frequency relative to the power peak in the spectrum diagram of the comparison data segment, and the more consistent with the situation where wear abnormality occurs, the wear conditions at different positions of the transmission parts usually have different degrees of wear, and therefore the corresponding power peak is more likely to correspond to impact-like vibration abnormality; for example, in the spectrum diagram of the local data segment, there is a power peak, and the frequency corresponding to the power peak is 1000, then 1000 is the characteristic frequency of the power peak, and the numerical value corresponding to 1000 is the comparison frequency; then in the spectrum diagram corresponding to each comparison data segment, the numerical deviation between the power with the corresponding frequency of 1000 and the power peak is used as the local comparison deviation.

[0097] Step S404: Integrate the local contrast deviations of the power peaks in all contrast data segments to determine the intra-cycle power contrast corresponding to each power peak in each local time segment.

[0098] Since the power peak corresponds to a local contrast deviation in each comparison data segment, all local contrast deviations corresponding to the power peak are further integrated so that the obtained intra-period power contrast can characterize the power deviation of the characteristic frequency corresponding to the power peak in all comparison data segments as a whole, so that the characterization of the possibility of quasi-impact vibration anomalies of the power peak based on the intra-period power contrast is more accurate. In a specific implementation of an embodiment of the present invention, the mean of the local contrast deviations of the power peak in all comparison data segments is used as the corresponding intra-period power contrast; in other implementations of an embodiment of the present invention, the accumulated value can be used instead of the mean for integration, and both are used to characterize the overall size of the power deviation, which will not be further elaborated here.

[0099] In a specific implementation of the embodiment of the present invention, the process of obtaining the power contrast ratio within a period is expressed by the formula: Among them, P t,h,k N is the intra-cycle power contrast ratio of the kth power peak corresponding to the hth local time period in the tth cycle working time period; t,h is the number of comparison data segments corresponding to the hth local time period in the tth periodic working time period; R t,h,k is the kth power peak value corresponding to the hth local time period in the tth period working time period; is the power of the comparison frequency of the kth power peak corresponding to the hth local time period in the tth periodic working time period in the frequency spectrum of the i-th comparison data segment; || is the absolute value symbol. In another specific implementation of the embodiment of the present invention, the square of the difference can also be used to replace the absolute value of the difference, and the square of the difference and the absolute value of the difference can both represent the numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of the comparison data segment and the power peak.

[0100] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the matching time period in step S103 includes: Figure 5 , which shows a flow chart of a matching time period acquisition method of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention, the method comprising:

[0101] Step S501: Arrange all local time periods corresponding to each periodic working time period in time order to obtain a local time period sequence corresponding to each periodic working time period.

[0102] In step S103, the matching time period is the time period with the same periodic position in other periodic working time periods corresponding to the corresponding local time period, and the lengths of different periodic working time periods are the same, and the corresponding local time periods are divided in the same way. Therefore, if the local time periods in each cycle are arranged in chronological order, the matching time period corresponding to each local time period can be obtained more intuitively and clearly.

[0103] Step S502: taking the index value of each local time period in each periodic working time period in the local time period sequence as the matching index value of each local time period.

[0104] The matching index value can quantify the period position of the local time period in the corresponding periodic working time period. Further matching of the period position in combination with the matching index value can make the obtained matching time period more accurate.

[0105] Step S503: taking each local time period in each periodic working time period as a target time period in turn; taking other periodic working time periods outside the periodic working time period where the target time period is located as comparison working time periods;

[0106] By comparing the working time periods, the periodic working time period to be analyzed and the periodic working time period used for matching or comparison are distinguished to prevent confusion, making subsequent analysis more intuitive and clear.

[0107] Step S504: In each comparison working time period, a local time period having the same matching index value as the target time period is used as a matching time period of the target time period.

[0108] The matching index value represents the period position of each local time period in the corresponding periodic working time period, so matching is performed by using the same matching index value to obtain a more accurate matching time period with the same period position corresponding to the target time period.

[0109] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for obtaining the cycle power contrast ratio in step S103 includes: Figure 6 , which shows a flow chart of a method for obtaining the power contrast ratio between cycles of a method for monitoring abnormal operation of a turret-type plate-swinging machine provided by an embodiment of the present invention, the method comprising:

[0110] Step S601: taking the characteristic frequency corresponding to each power peak in the local time period as the comparison frequency.

[0111] The meaning is the same as step S402, and the purpose is to prevent confusion or unclear understanding, so it will not be further elaborated here.

[0112] Step S602: taking the numerical deviation between the power corresponding to the comparison frequency in the spectrum diagram of the matching time period and the power peak as the matching comparison deviation of the power peak in each matching time period.

[0113] In a specific implementation of an embodiment of the present invention, the absolute value of the difference between the power corresponding to the comparison frequency in the spectrum diagram of the matching time period and the power peak is used as the matching comparison deviation of the power peak in each matching time period; the larger the corresponding matching comparison deviation, the larger the deviation of the power corresponding to the comparison frequency relative to the power peak in the spectrum diagram of the matching data segment, and the more consistent with the situation where the power performance corresponding to the same frequency at the same cycle position in different working cycle time periods is relatively different, that is, the corresponding power peak is more likely to correspond to an impact-like vibration anomaly.

[0114] Step S603: Integrate the matching contrast deviations of the power peaks in all matching time periods to determine the inter-cycle power contrast corresponding to each power peak in each local time period.

[0115] Since the power peak corresponds to a matching contrast deviation in each matching data segment, all matching contrast deviations corresponding to the power peak are further integrated so that the obtained inter-cycle power contrast ratio can characterize the power deviation of the characteristic frequency corresponding to the power peak in all matching data segments as a whole, so that the characterization of the possibility of quasi-impact vibration anomaly of the power peak according to the inter-cycle power contrast ratio is more accurate. In a specific implementation of an embodiment of the present invention, the mean of the matching contrast deviations of the power peak in all matching data segments is used as the corresponding inter-cycle power contrast ratio; in other implementations of an embodiment of the present invention, the accumulated value can be used instead of the mean value for integration, and both are used to characterize the overall size of the power deviation, which will not be further elaborated here.

[0116] In a specific implementation of the embodiment of the present invention, the process of obtaining the power contrast ratio between cycles is expressed by the formula: Among them, in each, Z t,h,k is the inter-cycle power contrast ratio of the kth power peak corresponding to the hth local time period in the tth periodic working time period; M t,h is the number of matching data segments corresponding to the hth local time period in the tth periodic working time period; R t,h,k is the kth power peak value corresponding to the hth local time period in the tth period working time period; is the power of the comparison frequency of the kth power peak corresponding to the hth local time period in the tth periodic working time period in the frequency spectrum of the mth matching data segment; || is the absolute value symbol. In another specific implementation of the embodiment of the present invention, the square of the difference can also be used to replace the absolute value of the difference, and the square of the difference and the absolute value of the difference can both represent the numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of the comparison data segment and the power peak.

[0117] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the degree of vibration abnormality includes:

[0118] After fusing the characteristic frequency, intra-cycle power contrast, and inter-cycle power contrast corresponding to each power peak, the vibration abnormality degree of each power peak is determined by means of a normalization method. In a specific implementation of an embodiment of the present invention, the normalized value of the product of the characteristic frequency, intra-cycle power contrast, and inter-cycle power contrast corresponding to each power peak is used as the vibration abnormality degree corresponding to each power peak. As the larger the intra-cycle power contrast and the inter-cycle power contrast, the more likely the corresponding power peak is to correspond to a shock-like vibration abnormality, that is, the more likely the power peak is to be generated by a shock-like vibration abnormality; therefore, both the intra-cycle power contrast and the inter-cycle power contrast are positively correlated with the vibration abnormality degree; further, combined with the low-frequency characteristics of shock-like vibrations, the smaller the value of the characteristic frequency corresponding to the power peak, the more likely the power peak is to be generated by a shock-like vibration abnormality; therefore, the characteristic frequency corresponding to the power peak is also positively correlated with the vibration abnormality degree. In a specific implementation of an embodiment of the present invention, the process of obtaining the vibration abnormality degree is expressed by the formula: E t,h,k =Norm(P t,h,k ×Z t,h,k ×f t,h,k ), where E t,h,k is the vibration abnormality degree of the kth power peak on the spectrum diagram of the hth local time period in the tth cycle working time period; P t,h,k is the intra-cycle power contrast ratio of the kth power peak corresponding to the hth local time period in the tth cycle working time period; Z t,h,k is the inter-cycle power contrast ratio of the kth power peak corresponding to the hth local time period in the tth periodic working time period; f t,h,kIt is the characteristic frequency corresponding to the kth power peak on the spectrum diagram of the hth local time period in the tth cycle working time period; Norm() is a normalization function. The normalization method in the embodiment of the present invention adopts linear normalization. In other implementations of the embodiment of the present invention, the normalization method can be adjusted according to the specific implementation environment, which will not be further elaborated here. In another specific implementation of the embodiment of the present invention, the average between the normalized value of the intra-cycle power contrast, the normalized power contrast between cycles and the normalized value of the corresponding characteristic frequency is used as the degree of vibration abnormality; that is, the characteristic frequency, the intra-cycle power contrast and the inter-cycle power contrast are all positively correlated with the degree of vibration abnormality, and the obtained degree of vibration abnormality is the normalized value. Normalization can keep the data range between 0 and 1, which is convenient for subsequent analysis and calculation.

[0119] Preferably, in some possible implementations of the embodiments of the present invention, the method for monitoring the abnormal operation of the turret-type plate-swinging machine according to the degree of abnormal vibration includes:

[0120] In each periodic working time period, the degree of operational abnormality of each local time period is determined according to the overall magnitude of the degree of vibration abnormality of all power peaks corresponding to each local time period; the degree of operational abnormality is characterized by combining the degree of vibration abnormality of all power peaks corresponding to each local time period, which can reduce the impact of random errors on abnormality monitoring and improve the robustness and accuracy of operational abnormality detection. In a specific implementation of an embodiment of the present invention, the average value of the degree of vibration abnormality of all power peaks corresponding to each local time period is used as the degree of operational abnormality of each local time period. In a specific implementation of an embodiment of the present invention, the process of obtaining the degree of operational abnormality is expressed by the formula: Among them, T t,h is the degree of abnormal operation in the hth local time period in the tth periodic working time period; U t,h is the number of power peaks corresponding to the hth local time period in the tth period working time period; E t,h,u is the vibration abnormality degree of the uth power peak corresponding to the hth local time period in the tth cycle working time period. When there is a local time period with an operation abnormality degree greater than the preset abnormal threshold, it is determined that the turret plate swing machine is operating abnormally; in the embodiment of the present invention, the preset abnormal threshold is set to 0.4, and the implementer can adjust it according to the specific implementation environment.

[0121] In other possible implementations of the embodiments of the present invention, the maximum value of the vibration abnormality of all power peaks corresponding to each local time period is used as the operation abnormality; and when there is a local time period in which the operation abnormality is greater than the preset reference abnormality threshold, the turret plate machine is determined to be operating abnormally; the preset reference abnormality threshold is set to 0.6, and the implementer can adjust it according to the specific implementation environment. Using the maximum vibration abnormality as the operation abnormality can avoid the occurrence of missed detection to the greatest extent.

[0122] Preferably, as another embodiment of the present invention, after the turret-type plate-swinging machine is monitored for abnormal operation according to the degree of abnormal vibration, an abnormal warning may be issued through an alarm, specifically including:

[0123] When the turret plate-swinging machine operates abnormally, an abnormal warning signal is issued through the alarm; and the staff is notified of abnormal wear through the abnormal warning signal; thus, the wear abnormality is detected in advance before the wear corresponding to the impact vibration is amplified, thereby ensuring the real-time nature of the wear abnormality monitoring.

[0124] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of a turret plate-stirring machine operation abnormality monitoring and alarm device according to another embodiment of the present invention. The device includes a vibration sensor 801, a computer device 802, and an alarm 803; wherein the sensor is used to collect vibration amplitude data on the transmission shaft of the turret plate-stirring machine and transmit it to the computer device, the computer device 802 is used to execute a turret plate-stirring machine operation abnormality monitoring method provided in an embodiment of the present application, and the alarm is used to issue an early warning when abnormal operation of the turret plate-stirring machine is detected.

[0125] In summary, a method for monitoring the operation abnormality of a turret-type plate-swinging machine combines the characteristics of low frequency and high power of impact-like vibration. During the periodic working time period, the intra-cycle power contrast is obtained according to the difference between the power performance of the characteristic frequency of each power peak in the spectrum diagram of each local time period; the inter-cycle power contrast is obtained according to the difference between the power performance of the characteristic frequency in the spectrum diagram of each matching time period between the cycles; further, combined with the characteristics of low frequency, the degree of vibration abnormality corresponding to each power peak that characterizes the possibility of impact-like vibration is obtained according to the intra-cycle power contrast, the inter-cycle power contrast and the size of the characteristic frequency; thereby more accurate monitoring of the operation abnormality of the turret-type plate-swinging machine is performed according to the degree of vibration abnormality.

[0126] This application also provides a turret-type plate-swinging machine operation abnormality monitoring system, please refer to Figure 7, which shows a structural diagram of a turret-type plate-stirring machine operation abnormality monitoring system provided by an embodiment of the present invention, the system comprising: a data acquisition preprocessing module 701, a first determination module 702, a second determination module 703 and an abnormality monitoring module 704.

[0127] The data acquisition preprocessing module 701 is used to collect all vibration amplitude data in each periodic working time period on the transmission shaft of the turret-type plate-stirring machine through a vibration sensor; each periodic working time period is divided into at least two local time periods; wherein the division method of all periodic working time periods is the same;

[0128] The first determination module 702 is used to obtain each power peak in the corresponding frequency spectrum of each local time period and the characteristic frequency corresponding to the power peak; according to the deviation distribution of all powers corresponding to the characteristic frequency in the frequency spectrum of all local time periods relative to the power peak, determine the power contrast within the period corresponding to each power peak;

[0129] The second determination module 703 is used to obtain a matching time period in each local time period of each periodic working time period that has the same periodic position in other periodic working time periods; in the local time period, according to the deviation distribution between all powers corresponding to each power peak and the corresponding characteristic frequency in the frequency spectrum of all matching time periods, determine the inter-cycle power contrast corresponding to each power peak;

[0130] The abnormality monitoring module 704 is used to determine the degree of vibration abnormality of each power peak according to the characteristic frequency corresponding to each power peak, the power contrast within a cycle and the power contrast between cycles; and to monitor the operation abnormality of the turret plate swing machine according to the degree of vibration abnormality.

[0131] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the above embodiment provides a turret-type plate-swinging machine operation abnormality monitoring system and a turret-type plate-swinging machine operation abnormality monitoring method embodiment, which belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0132] The present application also provides a computer device. Fig. 9, which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 901, a processor 902, and a computer program 903 stored in the memory 901 and running on the processor 902, wherein when the processor 902 executes the computer program 903, the computer device can execute any one of the above-mentioned methods for monitoring the abnormal operation of a turret-type plate placing machine.

[0133] The embodiment of the present application also provides a computer program product. When the computer program product is executed on a computer device, the computer device can execute any one of the above-mentioned methods for monitoring the abnormal operation of a turret-type plate placing machine.

[0134] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any one of the above-mentioned methods for monitoring the abnormal operation of a turret-type plate placing machine.

[0135] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0136] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for monitoring abnormal operation of a turret-type plate-swinging machine, characterized in that: The method comprises: On the transmission shaft of the turret-type plate-stirring machine, all vibration amplitude data in each periodic working time period are collected by a vibration sensor; each periodic working time period is divided into at least two local time periods; wherein all periodic working time periods are divided in the same manner; Obtain each power peak in the corresponding frequency spectrum of each local time period and the characteristic frequency corresponding to the power peak; determine the power contrast within the period corresponding to each power peak according to the deviation distribution of all powers corresponding to the characteristic frequency in the frequency spectrum of all local time periods relative to the power peak; The method for obtaining the power contrast ratio within the cycle includes: The other local time periods corresponding to each local time period are used as comparison data segments; The characteristic frequency corresponding to each power peak in each local time period is used as the comparison frequency; The numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of each comparison data segment and the power peak is used as the local comparison deviation of the power peak in each comparison data segment; Integrate the local contrast deviations of the power peak in all contrast data segments to determine the intra-cycle power contrast corresponding to each power peak in each local time segment; Obtain a matching time period in which each local time period in each periodic working time period has the same periodic position in other periodic working time periods; in the local time period, determine the inter-cycle power contrast corresponding to each power peak value according to the distribution of deviations between all powers corresponding to each power peak value and the corresponding characteristic frequency in the frequency spectrum of all matching time periods; The method for obtaining the inter-cycle power contrast ratio includes: Using the characteristic frequency corresponding to each power peak value in the local time period as the comparison frequency; The numerical deviation between the power corresponding to the comparison frequency in the frequency spectrum of the matching time period and the power peak is used as the matching comparison deviation of the power peak in each matching time period; Integrate the matching contrast deviations of the power peak in all matching time periods to determine the inter-cycle power contrast corresponding to each power peak in each local time period; The degree of vibration abnormality of each power peak is determined according to the characteristic frequency corresponding to each power peak, the power contrast within the cycle and the power contrast between the cycles; and the abnormal operation of the turret plate swing machine is monitored according to the degree of vibration abnormality.

2. The method for monitoring abnormal operation of a turret-type plate-swinging machine according to claim 1, characterized in that: The method for obtaining the power peak value includes: According to all the vibration amplitude data in the local time period, all the frequency data points in the spectrum diagram corresponding to the local time period are obtained by using the time-frequency transformation method; Performing cluster analysis on all frequency data points in the spectrum graph by using mean shift clustering to determine at least two frequency data point clusters; The maximum power among all frequency data points corresponding to each frequency data point cluster is taken as the power peak value of each frequency data point cluster.

3. The method for monitoring abnormal operation of a turret-type plate-swinging machine according to claim 1, characterized in that: The method for obtaining the matching time period includes: Arrange all local time periods corresponding to each periodic working time period in time order to obtain a local time period sequence corresponding to each periodic working time period; Using the index value of each local time period in each periodic working time period in the local time period sequence as the matching index value of each local time period; Each local time period in each periodic working time period is sequentially used as a target time period; other periodic working time periods outside the periodic working time period where the target time period is located are used as comparison working time periods; In each comparison working time period, a local time period having the same matching index value as the target time period is used as a matching time period of the target time period.

4. The method for monitoring abnormal operation of a turret-type plate-swinging machine according to claim 1, characterized in that: The method for obtaining the degree of vibration abnormality includes: After the characteristic frequency corresponding to each power peak, the intra-cycle power contrast and the inter-cycle power contrast are fused, the vibration abnormality degree of each power peak is determined by means of a normalization method.

5. The method for monitoring abnormal operation of a turret-type plate-swinging machine according to claim 1, characterized in that: The method for monitoring the abnormal operation of the turret-type plate-swinging machine according to the abnormal vibration degree comprises: In each periodic working time period, the degree of operation abnormality of each local time period is determined according to the overall magnitude of the vibration abnormality of all power peaks corresponding to each local time period; When there is a local time period in which the degree of operational abnormality is greater than a preset abnormality threshold, it is determined that the turret plate swinging machine is operating abnormally.

6. A method for monitoring abnormal operation of a turret-type plate-stirring machine according to claim 5, characterized in that: After the abnormal operation monitoring of the turret type plate swinging machine according to the abnormal vibration degree is performed, the following further comprises: When the turret plate-swinging machine operates abnormally, an abnormal warning signal is sent out through the alarm.

7. The method for monitoring abnormal operation of a turret-type plate-swinging machine according to claim 1, characterized in that: The method for obtaining the local time period includes: The periodic working time period is divided into a preset number of local time periods of the same length in chronological order.

8. The method for monitoring abnormal operation of a turret-type plate-stirring machine according to claim 2, characterized in that: The time-frequency transform method adopts short-time Fourier transform.

Images