A smart CNC cutting system for furniture production

Abstract

The application relates to the technical field of cutting adjustment control systems, in particular to a plate intelligent numerical control cutting system for furniture production. The system comprises a data monitoring module, which monitors cutting force and vibration intensity in a plate cutting process; a wear analysis module, which obtains vibration wear abnormality degrees at each collection moment in the cutting process and calculates cooperative wear degrees at each collection moment in the cutting process; an expected adjustment module, which is used for obtaining cutting interference degrees in the cutting process, calculating process control coefficients and obtaining expected cutting speeds at each collection moment in the plate cutting process; and a process control module, which adjusts the rotating speed of a motor by using a PID controller according to actual cutting speed and expected cutting speed in the plate cutting process, so as to control the cutting speed in the cutting process. The application improves the plate intelligent numerical control cutting machining precision.

Description

Technical Field

[0001] This application relates to the field of cutting and adjustment control system technology, specifically to an intelligent CNC cutting system for furniture production boards. Background Technology

[0002] Furniture manufacturing often requires a large amount of wood panels, which are then processed using cutting equipment for rapid cutting. By introducing intelligent numerical control technology, precise control of the cutting process can be achieved, thus enabling high-efficiency and high-precision furniture manufacturing.

[0003] Most existing technologies use CNC panel saws for high-speed cutting of furniture boards. They analyze the wear of the panel saw by monitoring cutting parameters in real time and then control the cutting speed accordingly to prevent further wear. However, the effects of panel saw wear during board cutting are complex, and existing technologies do not adequately consider the impact of wear on cutting accuracy. This results in inaccurate control of the cutting speed, ultimately affecting the precision of furniture board cutting. Summary of the Invention

[0004] To address the aforementioned technical problems, the purpose of this application is to provide an intelligent CNC cutting system for furniture production boards, the specific technical solution of which is as follows:

[0005] This application proposes an intelligent CNC cutting system for furniture production boards, the system comprising:

[0006] Data monitoring module: used to monitor cutting force and vibration intensity during the sheet metal cutting process;

[0007] Wear Analysis Module: Performs frequency domain analysis on the vibration intensity within a preset time period before each acquisition moment. By analyzing the changes and differences in frequency domain amplitude, it obtains the vibration wear anomaly degree at each acquisition moment during the cutting process. It performs time-series decomposition on the cutting force within a preset time period before each acquisition moment. By analyzing the differences between cutting forces in the trend sequence after time-series decomposition, combined with the vibration wear anomaly degree, it obtains the collaborative wear degree at each acquisition moment during the cutting process.

[0008] Expected adjustment module: Performs detrending analysis on cutting force, vibration intensity and co-wear degree. Utilizes the correlation between co-wear degree and cutting force and vibration intensity after detrending analysis, as well as the randomness of the changes in cutting force and vibration intensity after detrending analysis, to obtain the cutting interference degree at each acquisition moment during the cutting process. Then, based on the change characteristics of the cutting interference degree, obtains the process control coefficient at each acquisition moment. Finally, combined with the actual cutting speed, obtains the expected cutting speed at each acquisition moment during the board cutting process.

[0009] Process control module: Based on the actual cutting speed and the desired cutting speed during the board cutting process, the PID controller is used to adjust the motor speed to control the cutting speed during the cutting process.

[0010] Preferably, the data of all vibration intensity and cutting force within a preset time period before each acquisition time are normalized and arranged in chronological order to obtain the vibration intensity sequence and cutting force sequence for each acquisition time.

[0011] Preferably, the calculation process for the vibration wear anomaly degree at each sampling moment during the cutting process is as follows:

[0012]

[0013] In the formula, G t Let PE be the vibration wear anomaly at the t-th acquisition time. t Let f be the permutation entropy of the frequency domain amplitude sequence corresponding to the t-th acquisition time, M be the number of elements in the frequency domain amplitude sequence corresponding to the t-th acquisition time, and f t,i and f t,i-1 These are the i-th and (i-1)-th elements in the frequency domain amplitude sequence corresponding to the t-th acquisition time, respectively.

[0014] Preferably, the vibration intensity sequence at each acquisition time is transformed in the frequency domain, and the amplitudes of all frequencies after the frequency domain transformation are arranged in ascending order of frequency to form the frequency domain amplitude sequence at each acquisition time.

[0015] Preferably, the calculation process for the collaborative wear degree at each acquisition moment during the cutting process is as follows:

[0016]

[0017] In the formula, R t Let be the collaborative wear degree at the t-th acquisition time, N be the number of elements in the trend sequence at the t-th acquisition time, exp() be the exponential function with the natural constant as the base, and d t,j and d t,j-1 These are the j-th and (j-1)-th elements in the trend sequence at the t-th acquisition time, respectively. The cutting force sequence at each acquisition time is decomposed into a time series to obtain the trend sequence at each acquisition time.

[0018] Preferably, the calculation process for the cutting interference degree at each acquisition time during the cutting process is as follows:

[0019] H t =Rs t ×σz t +Rv t ×σc t In the formula, H t Let Rs be the cutting interference at the t-th acquisition time. t and Rv t The first and second correlations at the t-th acquisition time are respectively obtained by detrending analysis of the correlation between wear degree and cutting force and vibration intensity, yielding the first and second correlations, σz. t Let σc be the information entropy of the first-order difference sequence of the cutting force fluctuation sequence at the t-th acquisition time. t Let be the information entropy of the first-order difference sequence of the vibration intensity fluctuation sequence at the t-th acquisition time, where the cutting force sequence and vibration intensity sequence at each acquisition time are obtained by performing detrending analysis respectively.

[0020] Preferably, the process of obtaining the first correlation and the second correlation further includes:

[0021] All co-wear values ​​within a preset time period prior to each acquisition time are arranged in chronological order to form a co-wear value sequence for each acquisition time. The absolute values ​​of the correlation between the co-wear fluctuation sequence and the cutting force fluctuation sequence and the vibration intensity fluctuation sequence are calculated respectively, and used as the first correlation and the second correlation for each acquisition time.

[0022] Preferably, the calculation process of the process control coefficients at each acquisition time is as follows:

[0023] In the formula, W is the process control coefficient at the current acquisition time, α is the proportional adjustment factor, arctan() is the arctangent function, m is the number of elements in the cut interference sequence at the current acquisition time, and H s and H s-1 These are the s-th and s-1-th elements in the cut interference sequence at the current acquisition time, respectively.

[0024] Preferably, all cutting interference degrees within a preset time period before each acquisition time are arranged in chronological order to obtain the cutting interference degree sequence for each acquisition time.

[0025] Preferably, the calculation process for the desired cutting speed at each acquisition moment during the sheet metal cutting process is as follows:

[0026] EV = (1 + W) × V; where EV is the desired cutting speed at the current acquisition time, V is the actual cutting speed at the current acquisition time, and W is the process control coefficient at the current acquisition time.

[0027] This application has the following beneficial effects:

[0028] This application addresses the issue that existing technologies, when controlling cutting speed, do not adequately analyze the impact of panel saw wear on cutting accuracy, leading to inaccurate control of the cutting speed and consequently affecting the precision of furniture board cutting. Therefore, this application employs frequency domain analysis to measure the abnormal characteristics of vibration wear on the panel saw during board cutting, and combines this with the trend changes in cutting force on the panel saw to measure the synergistic wear characteristics among different influencing factors during board cutting. This more clearly reveals the wear characteristics of the panel saw during board cutting, facilitating more accurate control of the cutting speed in subsequent processes.

[0029] Furthermore, this application analyzes the interference effect of collaborative wear characteristics on the cutting accuracy of the board saw, and uses correlation analysis to accurately measure the degree of interference of collaborative wear characteristics during board cutting. This is used to control and adjust the cutting speed during the subsequent cutting process, so as to avoid further aggravating the wear of the board saw and reduce the impact of the wear of the board saw on the cutting accuracy.

[0030] Meanwhile, this application fully considers the impact of panel saw wear on cutting accuracy. Based on the changing characteristics of wear interference during panel cutting, the desired cutting speed during panel cutting is calculated in real time, and a PID controller is used to accurately control the cutting speed during the cutting process, thereby improving the accuracy of cutting furniture panels. Attached Figure Description

[0031] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This application provides a block diagram of an intelligent CNC cutting system for furniture production, as one embodiment of the present application.

[0033] Figure 2 This is a schematic diagram of the cutting speed control process during the sheet metal cutting process provided in one embodiment of this application. Detailed Implementation

[0034] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent CNC cutting system for furniture production based on this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0035] Unless otherwise defined, 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.

[0036] The following description, in conjunction with the accompanying drawings, details a specific solution for an intelligent CNC cutting system for furniture production provided in this application.

[0037] Please see Figure 1 The diagram illustrates a block diagram of an intelligent CNC cutting system for furniture production, provided in one embodiment of this application. The system includes:

[0038] Data monitoring module: used to monitor cutting force and vibration intensity during the board cutting process.

[0039] In the process of cutting furniture boards using CNC panel saws, in order to achieve precise control of the board cutting process, it is necessary to monitor the processing parameters in real time through sensor technology and promptly identify potential problems with the cutting speed, thereby enabling more accurate process control of the cutting speed.

[0040] The data monitoring module of the CNC cutting system collects processing parameters in real time during the cutting process. The sensors of the data monitoring module include force sensors and vibration sensors. The force sensor is installed at the connection between the panel saw and the spindle, and the vibration sensor is installed on the spindle of the panel saw. The sensors are fixed with bolts to collect the cutting force and vibration intensity in real time during the cutting process. In this embodiment, the acquisition frequency of cutting force and vibration intensity is 100Hz. The implementer can adaptively select the acquisition frequency according to the actual situation.

[0041] To improve the accuracy of subsequent process control for sheet metal cutting, it is necessary to eliminate the dimensions between different processing parameters. All cutting forces and vibration intensities collected within a preset time period before each acquisition moment are normalized by range, and the normalized data are then arranged in chronological order to obtain the cutting force sequence and vibration intensity sequence for each acquisition moment. In this embodiment, the preset time period is 1 second; in actual application scenarios, the implementer can set it themselves.

[0042] Wear Analysis Module: Performs frequency domain analysis on the vibration intensity within a preset time period before each acquisition moment. By analyzing the changes and differences in frequency domain amplitude, it obtains the vibration wear anomaly degree at each acquisition moment during the cutting process. It performs time-series decomposition on the cutting force within a preset time period before each acquisition moment. By analyzing the differences between cutting forces in the trend sequence after time-series decomposition, combined with the vibration wear anomaly degree, it obtains the collaborative wear degree at each acquisition moment during the cutting process.

[0043] The factors influencing panel saw wear during sheet metal cutting are generally complex. Tool wear not only affects the precision of sheet metal cutting but can even lead to panel saw breakage in severe cases. Therefore, it is necessary to analyze the complex impact of panel saw wear on cutting accuracy and to implement accurate process control for sheet metal cutting to ensure that the quality of sheet metal cutting is not affected.

[0044] To analyze the vibration state of the panel saw during the board cutting process, the vibration intensity sequence at each acquisition moment is used as the input of the Fourier transform. The Fourier transform can be either the Fast Fourier Transform or the Discrete Fourier Transform. In this embodiment, the Discrete Fourier Transform is used to obtain the amplitude of all frequencies in the vibration intensity sequence. The Discrete Fourier Transform is a well-known technique and will not be elaborated further.

[0045] Furthermore, the amplitude of all frequencies within the vibration intensity sequence at each acquisition time is arranged in ascending order of frequency and denoted as the frequency domain amplitude sequence at each acquisition time. This sequence reflects the variation characteristics of the panel saw's vibration amplitude with frequency during the board cutting process. The greater the difference between adjacent amplitudes within the frequency domain amplitude sequence and the higher the degree of disorder in the amplitude variation within the frequency domain amplitude sequence, the more significant the abnormal variation of the panel saw's vibration amplitude with frequency. This indicates that the panel saw will exhibit abnormal vibration wear characteristics, and more accurate process control of the board cutting speed is required to avoid adverse effects on the cutting accuracy.

[0046] Based on the above analysis, the vibration wear anomaly degree at each sampling moment during the sheet cutting process was calculated:

[0047]

[0048] In the formula, G t Let PE be the vibration wear anomaly at the t-th acquisition time. t Let f be the permutation entropy of the frequency domain amplitude sequence corresponding to the t-th acquisition time, M be the number of elements in the frequency domain amplitude sequence corresponding to the t-th acquisition time, and f t,i and f t,i-1 These are the i-th and (i-1)-th elements in the frequency domain amplitude sequence corresponding to the t-th acquisition time, respectively.

[0049] It should be noted that the calculation of permutation entropy is a well-known technique and will not be elaborated upon further.

[0050] It is understandable that the vibration wear anomaly reflects the magnitude of the wear characteristics on the panel saw caused by abnormal spindle vibration during the CNC cutting process control. The greater the vibration wear characteristics on the panel saw, the more unstable the contact state between the panel saw and the board is, and the more accurate the process control of the cutting speed of the board is required to improve the precision of cutting furniture boards.

[0051] Generally, the higher the abnormal vibration and wear characteristics exhibited by the panel saw, and the stronger the upward trend of the cutting force, the more it reflects the synergistic wear characteristics between different influencing factors on the panel saw. In this case, more accurate process control of the panel cutting is required.

[0052] Therefore, in order to more accurately measure the synergistic wear characteristics among different influencing factors, the cutting force sequence at each acquisition time is used as the input for STL time series decomposition. The trend sequence at each acquisition time is obtained by using STL time series decomposition. STL time series decomposition is a well-known technique and will not be elaborated further.

[0053] Based on the above analysis, the collaborative wear degree at each data collection moment during the sheet cutting process is calculated:

[0054]

[0055] In the formula, R t Let be the collaborative wear degree at the t-th acquisition time, N be the number of elements in the trend sequence at the t-th acquisition time, exp() be the exponential function with the natural constant as the base, and d t,j and d t,j-1 These are the j-th and (j-1)-th elements in the trend sequence at the t-th acquisition time, respectively.

[0056] Among them, the synergistic wear degree reflects the synergistic wear characteristics among different influencing factors on the panel saw. If the synergistic wear characteristics are more significant, then it is more likely to interfere with the cutting accuracy of furniture boards. At this time, it is necessary to control and adjust the cutting speed in time during the cutting process to avoid affecting the cutting accuracy of furniture boards.

[0057] The desired adjustment module performs detrending analysis on cutting force, vibration intensity, and synergistic wear degree. By utilizing the correlation between synergistic wear degree and cutting force and vibration intensity after detrending analysis, as well as the randomness of the changes in cutting force and vibration intensity after detrending analysis, the cutting interference degree at each acquisition moment during the cutting process is obtained. Then, based on the change characteristics of cutting interference degree, the process control coefficient at each acquisition moment is obtained. Finally, combined with the actual cutting speed, the desired cutting speed at each acquisition moment during the board cutting process is obtained.

[0058] In the process control of sheet metal cutting, the stronger the synergistic effect among different factors affecting panel saw wear, the more easily the stability of the CNC panel saw is affected, thus impacting the quality of sheet metal cutting. Therefore, it is necessary to fully consider the complex impact of panel saw wear on cutting accuracy and improve the accuracy of cutting speed control during the cutting process to ensure the quality of sheet metal cutting.

[0059] Furthermore, the collaborative wear degree of all acquisition moments within one second before each acquisition moment is arranged in chronological order to obtain the collaborative wear degree sequence of each acquisition moment, which reflects the change of collaborative wear characteristics over time, and facilitates subsequent analysis of the complex impact on the cutting accuracy of the plate.

[0060] To accurately analyze the interference effect of collaborative wear characteristics on cutting accuracy, the collaborative wear degree sequence, cutting force sequence, and vibration intensity sequence at each acquisition time are used as inputs to the DFA detrended fluctuation analysis algorithm. The DFA detrended fluctuation analysis algorithm is used to obtain the corresponding sequences after detrended analysis of the collaborative wear degree sequence, cutting force sequence, and vibration intensity sequence. In this embodiment, for ease of understanding and description, they are referred to as collaborative wear fluctuation sequence, cutting force fluctuation sequence, and vibration intensity fluctuation sequence, respectively. The DFA detrended fluctuation analysis algorithm is a well-known technology and will not be described in detail.

[0061] Furthermore, the absolute values ​​of the correlation between the co-wear fluctuation sequence and the cutting force fluctuation sequence and the vibration intensity fluctuation sequence are calculated respectively, and are denoted as the first correlation and the second correlation at each acquisition time. The correlation can be measured by Pearson correlation coefficient, mutual information or covariance. In this embodiment, covariance is used to measure the correlation.

[0062] The greater the first and second correlations, the greater the impact of the synergistic wear characteristics on the stability of the CNC panel saw. This results in non-stationary and irregular changes in the cutting force and vibration intensity within the CNC panel saw, highlighting the interference of synergistic wear characteristics on the cutting accuracy of the board during the cutting process.

[0063] Based on the above analysis, the cutting interference degree at each acquisition moment during the board cutting process is calculated. In this embodiment, the specific calculation formula is as follows:

[0064] H t =Rs t ×σz t +Rv t ×σc t ;

[0065] In the formula, H t Let Rs be the cutting interference at the t-th acquisition time. t and Rv t The first and second correlations at the t-th acquisition time are respectively, σz t Let σc be the information entropy of the first-order difference sequence of the cutting force fluctuation sequence at the t-th acquisition time. t Let be the information entropy of the first-order difference sequence of the vibration intensity fluctuation sequence at the t-th acquisition time. The calculation of information entropy is a well-known technique and will not be elaborated further.

[0066] Cutting interference reflects the degree of interference from the collaborative wear characteristics on the panel saw when cutting the board. The higher the degree of interference from the collaborative wear characteristics when cutting the board, the greater the impact of the panel saw wear on the cutting accuracy. In this case, the cutting speed of the CNC panel saw should be reduced to avoid further aggravating the wear of the panel saw and to reduce the impact of the wear on the cutting accuracy.

[0067] Generally, the more significant the upward trend of the cutting interference characteristics on the panel saw in the short time before the current data collection time, the more continuously the cutting of the board will be affected by the collaborative wear characteristics. In this case, the cutting speed of the CNC panel saw should be appropriately reduced to decrease the interference of the collaborative wear characteristics on the panel saw on the board cutting. Conversely, if the downward trend of the cutting interference characteristics on the panel saw in the short time before the current data collection time is smaller, it indicates that the cutting of the board is less affected by the collaborative wear characteristics. In this case, the cutting speed of the CNC panel saw should be appropriately increased to improve the efficiency of cutting furniture boards.

[0068] Therefore, in this embodiment, the cutting interference degrees of all acquisition times within one second prior to the current acquisition time are arranged in chronological order to obtain the cutting interference degree sequence of the current acquisition time. This sequence reflects the changes in the cutting interference characteristics on the panel saw in the short period prior to the current acquisition time. Based on the differences in the changes of elements within the cutting interference degree, the process control coefficients for each acquisition time during the cutting process are calculated. Preferably, in this embodiment, the calculation formula is as follows:

[0069]

[0070] In the formula, W is the process control coefficient at the current acquisition time, α is the proportional adjustment factor used to control the range of the process control coefficient to avoid adjusting the cutting speed too high or too low in the future. In this embodiment, the value is 0.2, arctan() is the arctangent function, m is the number of elements in the cutting interference sequence at the current acquisition time, and H... s and H s-1 These are the s-th and s-1-th elements in the cut interference sequence at the current acquisition time, respectively.

[0071] Furthermore, based on the process control coefficient and the actual cutting speed at the current acquisition moment, the desired cutting speed at the current acquisition moment is obtained. The specific calculation method in this embodiment is as follows:

[0072] EV = (1 + W) × V; where EV is the desired cutting speed at the current acquisition time, V is the actual cutting speed at the current acquisition time, and W is the process control coefficient at the current acquisition time.

[0073] Understandably, by analyzing the changes in cutting interference characteristics on the panel saw shortly before the current data collection time, a process control coefficient for panel cutting can be set. This coefficient can then be used to adjust the actual cutting speed, thereby preventing the cutting speed from being too high or too low and improving the quality and efficiency of cutting furniture panels.

[0074] Process control module: Based on the actual cutting speed and the desired cutting speed during the board cutting process, the PID controller is used to adjust the motor speed to control the cutting speed during the cutting process.

[0075] Furthermore, a PID controller is used to accurately control the cutting speed during the cutting process. By monitoring and calculating the actual cutting speed and the desired adjustment speed during the board cutting process in real time, the actual cutting speed and the desired adjustment speed at the current acquisition moment are input into the PID controller. The PID controller outputs a control signal based on the error between the actual cutting speed and the desired adjustment speed. The control signal acts on the frequency converter in the CNC panel saw equipment. The frequency converter adjusts the motor speed through the output signal of the controller, thereby changing the cutting speed of the panel saw. This achieves accurate process control of the cutting speed during the cutting process, thereby avoiding increased wear on the panel saw during the board cutting process and reducing the impact of panel saw wear on cutting accuracy.

[0076] Specifically, in this embodiment, a flowchart illustrating the cutting speed control during the board cutting process in furniture production is shown below. Figure 2 As shown.

[0077] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0079] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A plate intelligent numerical control cutting system for furniture production, characterized in that, The system comprises: a data monitoring module for monitoring cutting force and vibration intensity during plate cutting processing; a wear analysis module for performing frequency domain analysis on vibration intensity within a preset time length before each collection time, obtaining vibration wear abnormality at each collection time during cutting processing through changes and differences in frequency domain amplitude, performing time series decomposition on cutting force within the preset time length before each collection time, obtaining collaborative wear degree at each collection time during cutting processing through differences between cutting forces in the trend sequence after time series decomposition and in combination with vibration wear abnormality; an expected adjustment module for performing detrend analysis on cutting force, vibration intensity and collaborative wear degree, obtaining cutting interference degree at each collection time during cutting processing through correlation between collaborative wear degree after detrend analysis and cutting force and vibration intensity and variation randomness of cutting force and vibration intensity after detrend analysis, and further obtaining process control coefficient at each collection time according to variation characteristics of cutting interference degree, and then obtaining expected cutting speed at each collection time during plate cutting processing in combination with actual cutting speed; a process control module for adjusting speed of a motor by using a PID controller according to actual cutting speed and expected cutting speed during plate cutting processing to control cutting speed during cutting processing; all vibration intensities and cutting forces within a preset time length before each collection time are arranged in time sequence after normalization to obtain vibration intensity sequence and cutting force sequence at each collection time; the calculation process of vibration wear abnormality at each collection time during cutting processing is as follows: ； In the formula, is the vibration wear abnormality degree of the tth collection moment, is the permutation entropy of the frequency domain amplitude sequence corresponding to the tth collection moment, is the number of elements in the frequency domain amplitude sequence corresponding to the tth collection moment, and are the i th and i-1 th elements in the frequency domain amplitude sequence corresponding to the tth collection moment, respectively.

2. The plate intelligent numerical control cutting system for furniture production according to claim 1, characterized in that, the vibration intensity sequence at each collection time is subjected to frequency domain transformation, and amplitudes of all frequencies after frequency domain transformation of the vibration intensity sequence are arranged in descending order of frequency to form frequency domain amplitude sequence at each collection time.

3. The plate intelligent numerical control cutting system for furniture production according to claim 1, characterized in that, the calculation process of collaborative wear degree at each collection time during cutting processing is as follows: ； wherein is the collaborative wear degree of the tth collection time, is the number of elements in the trend sequence of the tth collection time, is an exponential function with a natural constant as the base number, and are the jth and j-1th elements in the trend sequence of the tth collection time, respectively, wherein the cutting force sequence of each collection time is time series decomposed to obtain the trend sequence of each collection time.

4. The plate intelligent numerical control cutting system for furniture production of claim 1, wherein, the calculation process of cutting interference degree at each collection time during cutting processing is as follows: ; wherein, is the cutting interference degree of the tth acquisition moment, and are the first correlation and the second correlation of the tth acquisition moment, respectively, the first correlation and the second correlation are obtained by analyzing the correlation between the cooperative wear degree and the cutting force, the vibration intensity after detrending, respectively, is the information entropy of the first-order difference sequence of the cutting force fluctuation sequence of the tth acquisition moment, is the information entropy of the first-order difference sequence of the vibration intensity fluctuation sequence of the tth acquisition moment, wherein the cutting force fluctuation sequence and the vibration intensity fluctuation sequence are obtained by respectively performing detrending analysis on the cutting force sequence and the vibration intensity sequence of each acquisition moment.

5. The board intelligent numerical control cutting system for furniture production of claim 4, wherein, the process further comprises: all collaborative wear degrees within a preset time length before each collection time are arranged in time sequence to form collaborative wear degree sequence at each collection time, and absolute values of correlation degrees between collaborative wear fluctuation sequence and cutting force fluctuation sequence and vibration intensity fluctuation sequence are calculated as first correlation and second correlation at each collection time.

6. The board intelligent numerical control cutting system for furniture production of claim 1, wherein, the calculation process of process control coefficient at each collection time is as follows: ; where is the process control coefficient at the current sampling instant, is the proportional regulation factor, is the arc tangent function, is the number of elements in the cutting interference degree sequence at the current sampling instant, and are the s-th and s-1-th elements in the cutting interference degree sequence at the current sampling instant, respectively.

7. The board intelligent numerical control cutting system for furniture production of claim 6, wherein, all cutting interference degrees within a preset time length before each collection time are arranged in time sequence to obtain cutting interference degree sequence at each collection time.

8. The plate intelligent numerical control cutting system for furniture production of claim 1, wherein, the calculation process of expected cutting speed at each collection time during plate cutting processing is as follows: ; wherein is the desired cutting speed at the current acquisition time point, is the actual cutting speed at the current acquisition time point, is the process control coefficient at the current acquisition time point.

Images