WO2024060443A1 - Cutting length regulation and control method for high-precision cutting of gypsum plaster board - Google Patents

Abstract

Disclosed in the present invention is a cutting length regulation and control method for high-precision cutting of a gypsum plaster board, comprising the following steps: step S1, dividing, into three operation stages, cutting operation tracks of cutters for cutting gypsum plaster boards, and quantifying driving energy consumption of the cutters of different sizes corresponding to the gypsum plaster boards having different cutting lengths; step S2, obtaining a model training sample on the basis of minimum driving energy consumption and cam curves of the cutters; and step S3, performing training on the basis of the model training sample by using a BP neural network so as to obtain a cam curve regulation and control model representing a mapping relationship between the cutting lengths and the cam curves. According to the present invention, a data sample of a construction model is obtained by using a driving energy consumption minimization optimization method, a cam curve regulation and control model is trained on the basis of the data sample, and the cam curve regulation and control model is directly applied to regulation and control of the cutting lengths of gypsum plaster boards, so that the complex calculation amount in the regulation and control process is avoided, the manpower workload is reduced, and the regulation and control precision and efficiency are improved.

Description

A cutting length control method for high-precision cutting of gypsum board Technical field

The invention relates to the technical field of gypsum board cutting, and in particular to a cutting length control method for high-precision cutting of a paper-faced gypsum board.

Background technique

Conducting research on unmanned automation technology for the intelligent production process of gypsum board is in line with the specific requirements of the Industry 4.0 strategy and the Made in China 2025 action plan. Through comprehensive collection and in-depth analysis of the production process and control methods at the production site, we can discover the underlying causes of production bottlenecks and product defects, and continuously improve production efficiency and product quality of gypsum boards. Comprehensive analysis based on on-site data collection can improve the production control level of gypsum boards, reduce on-site operators, reduce personnel intervention in production, reduce corporate operating costs, and effectively save resources and energy, which has far-reaching practical significance.

The cutting machine is a key equipment of the gypsum board production line. Its function is to cut and group the continuously formed wet gypsum board boards. The cutting accuracy is closely related to the subsequent production. Therefore, improving the cutting accuracy and stability of the cutting machine is an important factor for the continuous production of the gypsum board production line. Guarantee is also the most critical factor in improving production input-output rate. In the existing technology, the entire cutting process adopts a unified operating layout and a single cutting speed setting. As a result, the cutting process can only be adapted to a single size type of gypsum board. The adaptability is poor and the cutting process needs to be stopped and then carried out. Hardware adjustments, such as changing the size of the cutter, are quite troublesome, not conducive to stable production, and are not suitable for the production needs of large-scale gypsum board production lines.

Contents of the invention

The object of the present invention is to provide a cutting length control method for high-precision cutting of gypsum board, so as to solve the technical problem of poor adaptability of cutting length control in the prior art.

In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

A cutting length control method for high-precision cutting of gypsum board, including the following steps:

Step S1: Divide the cutting operation trajectory of the cutter for cutting gypsum board into three operating stages, and operate the cutters of different sizes in the three operating stages of the cutting operation trajectory corresponding to the gypsum board with different cutting lengths. Quantify drive energy consumption;

Step S2: Obtain a set of operating parameter expected values of the cutter in three operating stages based on minimizing drive energy consumption and the cam curve of the cutter, and use a set of expected operating values, cutting length, and cutter size as model training samples;

Step S3: Use the BP neural network to train based on the model training samples to obtain a cam curve control model that represents the mapping relationship between the cutting length and the cam curve, so as to achieve high-precision control of the cutter cam curve according to the cutting length of the gypsum board.

As a preferred embodiment of the present invention, the cutting operation trajectory of the cutter for cutting gypsum board is divided into three operation stages, including:

The cutting circle of the cutter is used as the cutting operation track of the cutter, and the stop point, shearing point, start synchronization point and end synchronization point are set on the cutting operation track, where,

The stop point and the shearing point are located at both ends of the same circumferential diameter axis of the trajectory profile, and the start synchronization point and the end synchronization point are symmetrically located on both sides of the shearing point;

The trajectory profile between the stopping point and the starting synchronization point is set as an acceleration segment, the trajectory profile between the starting synchronization point and the ending synchronization point is set as a synchronization segment, and the trajectory profile between the ending synchronization point and the stopping point is set as a deceleration segment. , in order to control the cutting length of the gypsum board through the acceleration section, synchronization section and deceleration section.

As a preferred solution of the present invention, the driving energy consumption of cutters of different sizes operating in three operating stages of cutting operation trajectories corresponding to different cutting lengths of gypsum boards is quantified, including:

Calculate the cutting time for each cut length of gypsum board. The calculation formula for the cutting time is:

In the formula, t _c,i is the cutting time for the i-th cutting length, L _c,i is the i-th cutting length, and V _c is the production line conveying speed of the gypsum board;

The cutting time spent for each cutting length is used as the trajectory duration of the cutting operation trajectory of each size cutter, and the trajectory duration of each size cutter is divided into equal parts to obtain a set of trajectory timings {T _{k,i ,j} |j∈[1,n],k∈[1,m]}, n is the total number of trajectory timings, m is the total number of cutter sizes, T _k,i,j is the kth size cutter The jth trajectory timing of i trajectory duration;

Set the expected running speed value {V _k,i,j |i∈[1,n]} and the expected position value {y _k,i,j |i∈[1,n] for each trajectory timing of each size cutter ]} and acceleration expectation value {a _k,i,j |i∈[1,n]}, using the similarity of the velocity expectation value and acceleration expectation value in the trajectory timing sequence to measure the three operations of the cutting operation trajectory of each size cutter The energy consumption of the drive running in the stage. The quantitative formula of the drive energy consumption is:

In the formula, p _k,i is the driving energy consumption of the i-th trajectory in the k-th size cutter, V _k,i,j+1 and V _k,i,j are respectively the k-th size cutter. The running speed at the j+1th trajectory timing of the i trajectory duration, the running speed at the jth trajectory timing, a _k,i,j+1 and a _k,i,j are the kth size cutter respectively The running speed at the j+1th trajectory timing of the i-th trajectory duration and the running speed at the _j- th trajectory timing in The running position at j+1 trajectory time series, i, j, k are all metrology constants.

As a preferred solution of the present invention, a set of operating parameter expectations of the cutter in three operating stages is obtained based on minimizing the driving energy consumption and the cam curve of the cutter, including:

The integral summation of the expected operating speed value at each trajectory timing of each size cutter is equal to the length of the cutting operation trajectory of each size cutter as the first constraint for minimizing drive energy consumption. The first constraint is The function expression of is:

In the formula, L _q,k is the shearing circle circumference of the k-th size cutter, and the length of the cutting operation trajectory is equal to the shearing circle circumference;

The cam curve of each cutting operation trajectory of each size cutter is constructed as the second constraint condition for minimizing the drive energy consumption. The function expression of the second constraint condition is:

y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

In the formula,

A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

Based on the first constraint and the second constraint, the minimum driving energy consumption is solved to obtain the expected running speed value, expected position value and expected acceleration value of each size cutter at each trajectory timing.

As a preferred solution of the present invention, the method of using a set of expected operation values, cutting length, and cutter size as model training samples includes:

The trajectory timing, shearing circle circumference, and cutting length of each size cutter are used as sample feature data, and the expected running speed value, position expectation value, and acceleration expectation value at the trajectory timing sequence of each size cutter are used as sample label data;

The sample feature data and sample label data are combined as model training samples.

As a preferred solution of the present invention, the BP neural network is used for training based on model training samples to obtain a cam curve control model that represents the mapping relationship between cutting length and cam curve, including:

Use the sample feature data in the model training samples as the input data of the BP neural network, use the sample label data in the model training samples as the output data of the BP neural network, and use the BP neural network to perform convolution training on the input data and output data. The cam curve control model is obtained, and the model expression of the cam curve control model is:

[y,V,a]=BP(L _q ,L _c ,T);

In the formula, y, V, a are the expression identifiers of the expected running speed value, the expected position value and the expected acceleration value respectively. L _q , L _c and T are the expression identifiers of the shearing circle circumference, cutting length and trajectory timing respectively.

As a preferred solution of the present invention, the construction of the cam curve for each cutting operation trajectory of each size cutter includes:

Divide the acceleration section of the cutting operation trajectory of each size cutter into three curve stages, divide the synchronization section into two curve stages, and use a fifth-order polynomial to obtain the cam curve of each size cutter. The functional expression of the cutter’s cam curve is:

y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

In the formula,

A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

The cam curve of each size cutter is used to obtain the speed function and acceleration function in turn. The functional expression of the speed function is:

V _k,i,j =A ₁ +2A ₂ x _k,i,j +3A ₃ x _k,i,j ² +4A ₄ x _k,i,j ³ +5A ₅ x _k,i,j ⁴ ;

The functional expression of the acceleration function is:

a _k,i,j ＝2A ₂ +6A ₃ x _k,i,j +12A ₄ x _k,i,j ² +20A ₅ x _k,i,j ³ ;

The cam curve of each size cutter is normalized to obtain the boundary conditions, and A ₀ , A ₁ , A ₂ , A ₃ , A ₄ , and A ₅ are solved by boundary adjustment to determine the function expression of the cam curve of each size cutter.

As a preferred solution of the present invention, the running speed of the cutter in the synchronized section is the same as the conveying speed of the gypsum board production line.

As a preferred solution of the present invention, the cutting length and the shearing circle circumference are normalized before operation to eliminate dimensional errors.

As a preferred solution of the present invention, the high-precision control of the cutter cam curve according to the cutting length of the gypsum board includes:

Calculate the cutting time of the gypsum board with the cutting length to be controlled as the trajectory duration of the cutter, and divide the trajectory duration into equal parts to obtain a set of trajectory timings;

Input the cutting length to be controlled, the shearing circumference of the cutter and the trajectory timing into the cam curve control model to obtain the expected running speed value, expected position value and expected acceleration value at each trajectory timing;

The operation of the cutter is controlled according to the expected running speed value, expected position value and expected acceleration value at each trajectory sequence, and the cutting length of the gypsum board is adjusted to the cutting length to be controlled.

Compared with the prior art, the present invention has the following beneficial effects:

The present invention uses the driving energy consumption minimization and optimization method to obtain data samples for building the model, and trains a cam curve control model based on the data samples. The cam curve control model is directly applied to the control of the cutting length of the gypsum board, which avoids The complex calculation amount in the control process is reduced, and the human workload is reduced. The use of models for calculations improves the accuracy and efficiency of control.

Description of the drawings

In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the drawings required for the implementation methods or the description of the prior art are briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

Figure 1 is a flow chart of a cutting length control method for high-precision cutting of gypsum boards provided by an embodiment of the present invention;

Figure 2 is a segmented schematic diagram of a cam curve provided by an embodiment of the present invention;

Figure 3 is a normalized schematic diagram of a cam curve provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

As shown in FIG1 , the present invention provides a method for controlling the cutting length for high-precision cutting of a gypsum board, comprising the following steps:

Step S1: Divide the cutting operation trajectory of the cutter for cutting gypsum board into three operating stages, and operate the cutters of different sizes in the three operating stages of the cutting operation trajectory corresponding to the gypsum board with different cutting lengths. Quantify drive energy consumption;

The cutting operation path of the gypsum board cutting knife is divided into three operating stages, including:

The cutting circle of the cutter is used as the cutting running track of the cutter, and the stop point, cutting point, start synchronization point and end synchronization point are set on the cutting running track, wherein,

The stop point and the shear point are located at the two ends of the same circumferential diameter axis of the trajectory profile, and the start synchronization point and the end synchronization point are symmetrically located on both sides of the shear point;

The trajectory profile between the stop point and the start synchronization point is set as the acceleration segment, the trajectory profile between the start synchronization point and the end synchronization point is set as the synchronization segment, and the trajectory profile between the end synchronization point and the stop point is set as the deceleration segment. The cutting length of the gypsum board can be controlled through the acceleration section, synchronization section and deceleration section.

Quantify the driving energy consumption of cutters of different sizes operating in three operating stages of cutting operation trajectories corresponding to different cutting lengths of gypsum boards, including:

Calculate the cutting time for each cut length of gypsum board. The calculation formula for the cutting time is:

In the formula, t _c,i is the cutting time for the i-th cutting length, L _c,i is the i-th cutting length, and V _c is the production line conveying speed of the gypsum board;

The cutting time spent for each cutting length is used as the trajectory duration of the cutting operation trajectory of each size cutter, and the trajectory duration of each size cutter is divided into equal parts to obtain a set of trajectory timings {T _{k,i ,j} |j∈[1,n],k∈[1,m]}, n is the total number of trajectory timings, m is the total number of cutter sizes, T _k,i,j is the kth size cutter The jth trajectory timing of i trajectory duration;

Set the expected running speed value {V _k,i,j |i∈[1,n]} and the expected position value {y _k,i,j |i∈[1,n] for each trajectory timing of each size cutter ]} and acceleration expectation value {a _k,i,j |i∈[1,n]}, using the similarity of the velocity expectation value and acceleration expectation value in the trajectory timing sequence to measure the three operations of the cutting operation trajectory of each size cutter The energy consumption of the drive running in the stage, the quantitative formula of the drive energy consumption is:

Wherein, pk _,i is the driving energy consumption of the i-th trajectory duration in the k-th size cutter, Vk _,i,j+1 and Vk _,i,j are the running speed at the j+1th trajectory timing and the running speed at the j-th trajectory timing of the i-th trajectory duration in the k-th size cutter, respectively _{, ak,i,j+1} and ak _,i,j are the running speed at the j+1th trajectory timing and the running speed at the j-th trajectory timing of the i-th trajectory duration in the k-th size cutter, respectively, yk _,i,j is the running position at the j+1th trajectory timing of the i-th trajectory duration in the k-th size cutter, and i, j, k are all measurement constants.

Calculate the sum of the similarities of the running speed and acceleration between adjacent time series in turn. The similarity is measured by the Euclidean distance. Among them, the smaller the Euclidean distance between the running speed and acceleration between adjacent time series, the smaller the Euclidean distance between the running speed and acceleration between adjacent time series. The higher the similarity, the lower the adjustment of operating speed and acceleration between adjacent time series, that is, the lower the drive energy consumption caused by the adjustment of operating speed and acceleration. Therefore, minimizing drive energy consumption is the key to ensuring operation between adjacent time series. The sum of the similarities of speed and acceleration is the highest, and the sum of the adjustment amounts is the lowest, ensuring the highest smoothness of speed and acceleration adjustment between adjacent time series, and there will be no violent vibration of the blade, causing cutting vibration to reduce the smoothness of the cut surface of the gypsum board. properties, ultimately affecting the cutting accuracy. Therefore, this embodiment uses minimizing driving energy consumption to obtain data samples, which can ensure that the cam curve output by the cam curve control model subsequently trained based on the data samples has low driving energy consumption and adjacent timing. It has the advantage of high smoothness in speed and acceleration adjustment.

Step S2: Obtain a set of operating parameter expected values of the cutter in three operating stages based on minimizing drive energy consumption and the cam curve of the cutter, and use a set of expected operating values, cutting length, and cutter size as model training samples;

Based on the cam curve that minimizes the drive energy consumption and the cutter, a set of expected operating parameter values of the cutter in three operating stages are obtained, including:

The integral summation of the expected running speed value at each trajectory timing of each size cutter is equal to the length of the cutting running trajectory of each size cutter as the first constraint for minimizing drive energy consumption, and the function of the first constraint The expression is:

In the formula, L _q,k is the shearing circle circumference of the k-th size cutter, and the cutting operation trajectory length is equal to the shearing circle circumference;

The cam curve of each cutting operation trajectory of each size cutter is constructed as the second constraint to minimize the driving energy consumption. The functional expression of the second constraint is:

y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

In the formula,

A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

Based on the first constraint and the second constraint, the minimum driving energy consumption is solved to obtain the expected running speed value, expected position value and expected acceleration value of each size cutter at each trajectory timing.

A set of operating expected values, cutting length, and cutter size are used as model training samples, including:

The trajectory timing, cutting circle circumference, and cutting length of each size cutter are used as sample feature data, and the expected running speed value, position expectation value, and acceleration expectation value at the trajectory timing sequence of each size cutter are used as sample label data;

The sample feature data and sample label data are combined as model training samples.

Construct the cam curve for each cutting operation trajectory of each size cutter, including:

The acceleration section in the cutting operation trajectory of each size cutter is divided into three curve stages, the synchronization section is divided into two curve stages, and the cam curve of each size cutter is obtained by using a quintic polynomial. The function expression of the cam curve of each size cutter is:

y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

In the formula,

A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

The speed function and acceleration function are obtained in turn using the cam curve of each size cutter. The function expression of the speed function is:

V _k,i,j =A ₁ +2A ₂ x _k,i,j +3A ₃ x _k,i,j ² +4A ₄ x _k,i,j ³ +5A ₅ x _k,i,j ⁴ ;

The functional expression of the acceleration function is:

a _k,i,j ＝2A ₂ +6A ₃ x _k,i,j +12A ₄ x _k,i,j ² +20A ₅ x _k,i,j ³ ;

Normalize the cam curve of each size cutter to obtain the boundary conditions, and use boundary adjustment to solve A ₀ , A ₁ , A ₂ , A ₃ , A ₄ , and A ₅ to determine the cam of each size cutter. Functional expression of the curve.

As shown in FIG. 2 and FIG. 3 , this embodiment provides a solution example for obtaining the cam curve of each size cutter using a fifth-order polynomial, assuming that the function expression of the cam curve is:

y＝f(x)＝A ₀ +A ₁ x +A ₂ x ² +A ₃ x ³ +A ₄ x ⁴ +A ₅ x ⁵ ;

These 6 coefficients require 6 equations to solve. In order to determine these six equations, we need to express the cam curve in segments, and we normalize the acceleration segment with a nominal value of 1 to simplify the coefficient solution equation system. As shown in Figure 3.

According to the previous formula, we can get:

(a) Position: y=f(x)=A ₀ +A ₁ x +A ₂ x ² +A ₃ x ³ +A ₄ x ⁴ +A ₅ x ⁵ ;

(b) Speed: y′=f′(x)=A ₁ +2A ₂ x+3A ₃ x ² +4A ₄ x ³ +5A ₅ x ⁴ ;

(c) Acceleration: y″=f″(x)=2A ₂ x+6A ₃ x+12A ₄ x ² +20A ₅ x ³ ;

Substituting the six boundary conditions listed in Figure 3 into the three equations (a), (b), and (c) respectively, we can get:

According to this system of equations, these six coefficients can be solved.

The cam curve obtained by using the fifth degree polynomial is used as a constraint to ensure the continuity of the blade running position, running speed and acceleration. The data sample obtained through this constraint can also ensure the output of the cam curve control model trained based on the data sample in the future. The cam curve has the advantage of ensuring high continuity of speed and acceleration adjustment between adjacent time sequences, further supplementing the smoothness of the control.

Step S3: Use the BP neural network to train based on the model training samples to obtain a cam curve control model that represents the mapping relationship between the cutting length and the cam curve, so as to achieve high-precision control of the cutter cam curve according to the cutting length of the gypsum board.

The BP neural network is used to train based on model training samples to obtain a cam curve control model that represents the mapping relationship between cutting length and cam curve, including:

The sample feature data in the model training samples is used as the input data of the BP neural network, the sample label data in the model training samples is used as the output data of the BP neural network, and the BP neural network is used to perform convolution training on the input data and the output data to obtain the cam Curve control model, the model expression of the cam curve control model is:

[y,V,a]=BP(L _q ,L _c ,T);

In the formula, y, V, a are the expression identifiers of the expected running speed value, the expected position value and the expected acceleration value respectively. L _q , L _c and T are the expression identifiers of the shearing circle circumference, cutting length and trajectory timing respectively.

Using BP neural network to conduct model training based on data samples can effectively ensure the degree of fitting. In the existing technology, the quintic polynomial is solved to obtain the cam curve and the definite expression of the cam curve is determined. However, although the quintic polynomial can be fitted to a certain extent The cam curve is obtained, but there is a certain degree of fitting error in order to facilitate the solution. This embodiment uses BP neural network for fitting, which can effectively fit higher power accuracy. For example, the fifth-order polynomial can only be fitted to The fifth power, but the fitting of BP neural network can fit the mapping relationship after the fifth power, so the obtained cam curve control model is more accurate. Combined with the above, the cam curve control model also has the ability to ensure low driving energy consumption. , the advantages of high smoothness and high continuity of speed and acceleration adjustment between adjacent time series.

The running speed of the cutter in the synchronized section is the same as the conveying speed of the gypsum board production line.

The cutting length and shearing circle circumference are normalized before operation to eliminate dimensional errors.

High-precision control of the cutter cam curve according to the cut length of the gypsum board, including:

Calculate the cutting time of the gypsum board with the cutting length to be controlled as the trajectory duration of the cutter, and divide the trajectory duration into equal parts to obtain a set of trajectory timings;

Input the cutting length to be controlled, the shearing circumference of the cutter and the trajectory timing into the cam curve control model, and obtain the expected running speed value, expected position value and expected acceleration value at each trajectory timing;

The operation of the cutter is controlled according to the expected running speed value, expected position value and expected acceleration value at each trajectory sequence, and the cutting length of the gypsum board is adjusted to the cutting length to be controlled.

The present invention uses the driving energy consumption minimization and optimization method to obtain data samples for building the model, and trains a cam curve control model based on the data samples. The cam curve control model is directly applied to the control of the cutting length of the gypsum board, which avoids The complex calculation amount in the control process is reduced, and the human workload is reduced. The use of models for calculations improves the accuracy and efficiency of control.

The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims (10)

1. A cutting length control method for high-precision cutting of gypsum board, which is characterized by including the following steps:

   Step S1: Divide the cutting operation trajectory of the cutter for cutting gypsum board into three operating stages, and operate the cutters of different sizes in the three operating stages of the cutting operation trajectory corresponding to the gypsum board with different cutting lengths. Quantify drive energy consumption;

   Step S2, obtaining a set of expected values of operation parameters of the cutter in three operation stages based on the cam curve that minimizes the driving energy consumption and the cutter, and taking the set of expected values, the cutting length, and the cutter size as model training samples;

   Step S3: Use the BP neural network to train based on the model training samples to obtain a cam curve control model that represents the mapping relationship between the cutting length and the cam curve, so as to achieve high-precision control of the cutter cam curve according to the cutting length of the gypsum board.
2. A cutting length control method for high-precision cutting of gypsum board according to claim 1, characterized in that: the cutting operation trajectory of the cutter for cutting gypsum board is divided into three operating stages, including:

   The cutting circle of the cutter is used as the cutting operation track of the cutter, and the stop point, shearing point, start synchronization point and end synchronization point are set on the cutting operation track, where,

   The stop point and the shearing point are located at both ends of the same circumferential diameter axis of the trajectory profile, and the start synchronization point and the end synchronization point are symmetrically located on both sides of the shearing point;

   The trajectory profile between the stopping point and the starting synchronization point is set as an acceleration segment, the trajectory profile between the starting synchronization point and the ending synchronization point is set as a synchronization segment, and the trajectory profile between the ending synchronization point and the stopping point is set as a deceleration segment. , in order to control the cutting length of the gypsum board through the acceleration section, synchronization section and deceleration section.
3. The method for controlling the cutting length for high-precision cutting of gypsum boards according to claim 2 is characterized in that: the driving energy consumption of the cutters of different sizes in the three operating stages of the cutting operation trajectory corresponding to the gypsum boards of different cutting lengths is quantified, including:

   Calculate the cutting time for each cut length of gypsum board. The calculation formula for the cutting time is:

   

   In the formula, t _c,i is the cutting time for the i-th cutting length, L _c,i is the i-th cutting length, and V _c is the production line conveying speed of the gypsum board;

   The cutting time spent for each cutting length is used as the trajectory duration of the cutting operation trajectory of each size cutter, and the trajectory duration of each size cutter is divided into equal parts to obtain a set of trajectory timings {T _{k,i ,j} |j∈[1,n],k∈[1,m]}, n is the total number of trajectory timings, m is the total number of cutter sizes, T _k,i,j is the kth size cutter The jth trajectory timing of i trajectory duration;

   Set the expected running speed value {V _k,i,j |i∈[1,n]} and the expected position value {y _k,i,j |i∈[1,n] for each trajectory timing of each size cutter ]} and acceleration expectation value {a _k,i,j |i∈[1,n]}, using the similarity of the velocity expectation value and acceleration expectation value in the trajectory timing sequence to measure the three operations of the cutting operation trajectory of each size cutter The energy consumption of the drive running in the stage. The quantitative formula of the drive energy consumption is:

   

   In the formula, p _k,i is the driving energy consumption of the i-th trajectory in the k-th size cutter, and V _k,i,j+1 and V _k,i,j are respectively the k-th size cutter. The running speed at the j+1th trajectory timing of the i trajectory duration, the running speed at the jth trajectory timing, a _k,i,j+1 , a _k,i,j are the kth size cutter respectively The running speed at the j+1th trajectory timing of the i-th trajectory duration and the running speed at the _j- th trajectory timing in The running position at j+1 trajectory time series, i, j, k are all metrology constants.
4. A cutting length control method for high-precision cutting of gypsum board according to claim 3, characterized in that: the cam curve of the cutter is based on minimizing the driving energy consumption and the cutter to obtain the cutting length of the cutter in three operating stages. A set of expected operating parameter values, including:

   The integral summation of the expected operating speed value at each trajectory timing of each size cutter is equal to the length of the cutting operation trajectory of each size cutter as the first constraint for minimizing drive energy consumption. The first constraint is The function expression of is:

   

   In the formula, L _q,k is the shearing circle circumference of the k-th size cutter, and the length of the cutting operation trajectory is equal to the shearing circle circumference;

   The cam curve of each cutting operation trajectory of each size cutter is constructed as the second constraint to minimize the driving energy consumption. The functional expression of the second constraint is:

   y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

   In the formula,

   

   A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

   Based on the first constraint and the second constraint, the minimum driving energy consumption is solved to obtain the expected value of the running speed, the expected value of the position and the expected value of the acceleration at each trajectory timing of each size cutter.
5. A cutting length control method for high-precision cutting of gypsum board according to claim 4, characterized in that: a set of operating expected values, cutting length, and cutter size are used as model training samples, including:

   The trajectory timing, shearing circle circumference, and cutting length of each size cutter are used as sample feature data, and the expected running speed value, position expectation value, and acceleration expectation value at the trajectory timing sequence of each size cutter are used as sample label data;

   The sample feature data and sample label data are combined as model training samples.
6. A cutting length control method for high-precision cutting of gypsum board according to claim 5, characterized in that: the BP neural network is used for training based on model training samples to obtain a cam curve representing the mapping relationship between the cutting length and the cam curve. Regulatory models, including:

   Use the sample feature data in the model training samples as the input data of the BP neural network, use the sample label data in the model training samples as the output data of the BP neural network, and use the BP neural network to perform convolution training on the input data and output data. The cam curve control model is obtained, and the model expression of the cam curve control model is:

   [y,V,a]=BP(L _q ,L _c ,T);

   Where y, V, a are expression identifiers for the expected value of running speed, expected value of position and expected value of acceleration respectively; L _q , L _c , T are expression identifiers for the shear circle circumference, cutting length and trajectory timing respectively.
7. A cutting length control method for high-precision cutting of gypsum board according to claim 6, characterized in that the cam curve for constructing each cutting operation trajectory of each size cutter includes:

   The acceleration section in the cutting operation trajectory of each size cutter is divided into three curve stages, the synchronization section is divided into two curve stages, and the cam curve of each size cutter is obtained by using a fifth-order polynomial. The function expression of the cam curve of each size cutter is:

   y _k,i,j =A ₀ +A ₁ x _k,i,j +A ₂ x _k,i,j ² +A ₃ x _k,i,j ³ +A ₄ x _k,i,j ⁴ +A ₅ x _k,i,j ⁵ ;

   In the formula,

   

   A ₀ , A ₁ , A ₂ , A ₃ , A ₄ and A ₅ are the fitting coefficients of the cam curve respectively, and x _k,i,j and x _k,i,j-1 are the kth size cutter. The j and j-1th trajectory timing positions of the i trajectory duration correspond to the running position of the transmission axis of the production line, and T _k,i,j-1 is the j-1th trajectory duration of the kth size cutter. trajectory timing;

   The cam curve of each size cutter is used to obtain the speed function and acceleration function in turn. The functional expression of the speed function is:

   V _k,i,j =A ₁ +2A ₂ x _k,i,j +3A ₃ x _k,i,j ² +4A ₄ x _k,i,j ³ +5A ₅ x _k,i,j ⁴ ;

   The functional expression of the acceleration function is:

   a _k,i,j ＝2A ₂ +6A ₃ x _k,i,j +12A ₄ x _k,i,j ² +20A ₅ x _k,i,j ³ ;

   Normalize the cam curve of each size cutter to obtain the boundary conditions, and use boundary adjustment to solve A ₀ , A ₁ , A ₂ , A ₃ , A ₄ , and A ₅ to determine the cam of each size cutter. Functional expression of the curve.
8. A cutting length control method for high-precision cutting of gypsum board according to claim 7, characterized in that the running speed of the cutter in the synchronization section is the same as the production line transmission speed of the gypsum board.
9. A cutting length control method for high-precision cutting of gypsum board according to claim 8, characterized in that the cutting length and the shearing circle circumference are normalized before operation to eliminate dimensional errors.
10. A cutting length control method for high-precision cutting of gypsum board according to claim 9, characterized in that the high-precision control of the cutter cam curve according to the cutting length of the gypsum board includes:

    Calculate the cutting time of the gypsum board with the cutting length to be controlled as the trajectory duration of the cutter, and divide the trajectory duration into equal parts to obtain a set of trajectory timings;

    Input the cutting length to be controlled, the shearing circumference of the cutter and the trajectory timing into the cam curve control model, and obtain the expected running speed value, expected position value and expected acceleration value at each trajectory timing;

    The operation of the cutter is controlled according to the expected value of the running speed, the expected value of the position and the expected value of the acceleration at each trajectory timing, and the cutting length of the paper-faced gypsum board is adjusted to the cutting length to be adjusted.

Images