A control optimization method for high-precision cutting of gypsum board

Abstract

The present invention discloses a control optimization method for high-precision cutting of gypsum board, comprising the following methods: step S1, setting multiple optimization targets for cutting control of the gypsum board, and establishing multiple optimization control models for the prediction generation of the cutter cutting control scheme based on each optimization target; step S2, quantifying the precision error between the predicted value of the cutting control scheme obtained by each optimization control model and the expected value of the cutting control scheme, and using the precision error to determine the model weight of each optimization control model; step S3, performing a weighted combination of the cutting control scheme output by each optimization control model and the model weight of each optimization model corresponding to each optimization model to obtain an optimal cutting control scheme, and using the optimal cutting control scheme to control the cutting operation of the cutter. The present invention focuses on multiple indicators for the control optimization of the entire cutting process, improves the comprehensiveness of the control optimization, ensures a higher control optimization effect, and achieves high-precision cutting of the gypsum board.

Description

Technical Field

[0001] The invention relates to the technical field of gypsum board cutting, and in particular to a control optimization method for high-precision cutting of paper-faced gypsum boards. Background Art

[0002] Through comprehensive data collection and in-depth analysis of production processes and control methods at the production site, we can identify the underlying causes of production bottlenecks and product defects, continuously improving production efficiency and gypsum board product quality. Comprehensive analysis based on field data collection improves gypsum board production control, reduces the number of on-site operators, reduces human intervention in production, and lowers operating costs, effectively conserving resources and energy, with far-reaching practical significance.

[0003] The cutter is a key piece of equipment in a gypsum board production line. Its function is to cut the continuously formed wet gypsum boards into groups. Cutting accuracy is closely related to subsequent production. Therefore, improving the cutting accuracy and stability of the cutter is crucial for ensuring continuous production and improving the input-output ratio. Existing technologies focus on optimizing the entire cutting process by focusing on a single indicator, resulting in a lack of comprehensiveness and ultimately impacting the optimization results. Summary of the Invention

[0004] The object of the present invention is to provide a control optimization method for high-precision cutting of paper-faced gypsum board, so as to solve the technical problem of low comprehensiveness of control optimization in the prior art.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A control optimization method for high-precision cutting of gypsum board, comprising the following methods:

[0007] Step S1: setting multiple optimization objectives for the gypsum board cutting control, and establishing multiple optimization control models for predicting and generating a cutter cutting control solution based on each optimization objective, wherein each optimization control model predicts and outputs a cutter cutting control solution to achieve the corresponding optimization objective;

[0008] Step S2: quantifying the accuracy error between the cut-off control scheme prediction value obtained by each optimization control model and the cut-off control scheme expected value, and using the accuracy error to determine the model weight of each optimization control model;

[0009] Step S3: The cutting control schemes output by each optimization control model are weightedly combined by the model weights corresponding to each optimization model to obtain the optimal cutting control scheme, and the optimal cutting control scheme is used to control the cutting operation of the cutter to achieve high-precision cutting of the paper-faced gypsum board.

[0010] As a preferred solution of the present invention, the setting of multiple optimization objectives for the gypsum board cutting control includes:

[0011] The stability of the dynamic adjustment of the cutter in the cutting control scheme is quantified as steady-state accuracy as the first optimization goal of the paper-faced gypsum board. The functional expression of the first optimization goal is:

[0012]

[0013] In the formula, taget1 represents the first optimization target, S t+1 、S t They are represented by the electrical signals for controlling the cutter cutting operation at the t+1th and tth cutting operation timings, respectively; N is represented by the total number of cutting operation timings; t is represented by the measurement constant; T is represented by the transposition operator; and min is represented by the minimization operator;

[0014] The dynamic adjustment accuracy of the cutter in the cutting control scheme is quantified as cutting accuracy as the second optimization goal of the paper-faced gypsum board. The function expression of the second optimization goal is:

[0015]

[0016] In the formula, taget2 represents the second optimization objective, V(S t ) is characterized by the cutting speed generated by the electrical signal controlling the cutting operation of the cutter at the t-th cutting operation timing, It is represented by the running distance of the control cutter cutting operation at the t+1th and tth cutting operation timing, It is represented by the total running distance of the cutter in the cutting control scheme, and L is represented by the cutting length of the paper-faced gypsum board;

[0017] The dynamic adjustment response degree of the cutter in the cutting control scheme is quantified as the response accuracy as the third optimization target of the paper-faced gypsum board. The function expression of the third optimization target is:

[0018]

[0019] Where taget3 represents the third optimization objective, M represents the total number of dynamic adjustments of the cutter in the cutting control scheme, and Δτ represents the response delay time of the dynamic adjustment of the cutter in the cutting control scheme;

[0020] The statistics of the total number of dynamic adjustments of the cutter in the cutting control scheme include:

[0021] when This indicates that the cutter produces dynamic adjustment at the t+1th and tth cutting operation timing in the cutting control scheme;

[0022] when This indicates that the cutter does not produce dynamic adjustment at the t+1th and tth cutting operation timings in the cutting control scheme;

[0023] Where θ represents the adjustment threshold of the stability.

[0024] As a preferred solution of the present invention, multiple optimization control models are established for prediction generation of the cutter cutting control scheme based on each optimization objective, including:

[0025] A first optimization control model is constructed for the first optimization objective, wherein the model expression of the first optimization control model is:

[0026] taget1[S t+1 ]=LSTM_1(taget1[S t ,…,S t-k ]);

[0027] In the formula, taget1[S t+1 ] represents the S obtained by solving the first optimization goal t+1 ,taget1[S t ,…,S1] represents the S obtained by solving the first optimization goal t ,…,S t-k , S t-k It represents the electrical signal of the control cutter cutting operation at the tkth cutting operation timing, LSTM_1 represents the LSTM network of the first optimization control model, and k represents the measurement constant;

[0028] A second optimization control model is constructed for the second optimization objective. The model expression of the second optimization control model is:

[0029] taget2[S t+1 ]=LSTM_2(taget2[S t ,…,S t-k ]);

[0030] In the formula, taget2[S t+1 ] represents the S obtained by solving the second optimization goal t+1 , taget2[S t ,…,S1] represents the S obtained by solving the second optimization goal t ,…,S t-k , LSTM_2 represents the LSTM network of the second optimization control model;

[0031] A third optimization control model is constructed for the third optimization objective. The model expression of the third optimization control model is:

[0032] taget3[St+1 ]=LSTM_3(taget3[S t ,…,S t-k ]);

[0033] In the formula, taget3[S t+1 ] represents the S obtained by solving the third optimization goal t+1 , taget3[S t ,…,S1] represents the S obtained by solving the third optimization goal t ,…,S t-k , LSTM_3 represents the LSTM network of the third optimization control model.

[0034] As a preferred solution of the present invention, the quantification of the accuracy error between the predicted value of the cut-off control scheme obtained by each optimization control model and the expected value of the cut-off control scheme includes:

[0035] The predicted value of the cut-off control scheme is obtained by predicting each optimization control model in turn [S N ,…,S1], and cut off the control scheme expected value [E N ,…,E1] and the predicted value of the cut-off control scheme [S N ,…,S1] similarity calculation is performed to obtain the accuracy error of each optimization control model. The calculation formula of the accuracy error is:

[0036]

[0037] Where p j Characterized as the accuracy error of the j-th optimization control model, taget j (S t ) is represented as the predicted value S obtained by the j-th optimization control model t , E t It is represented by the expected value of the electrical signal controlling the cutter cutting operation at the t-th cutting operation timing, j∈[1, 2, 3].

[0038] As a preferred solution of the present invention, the method of determining the model weights of each optimization control model by using the precision error includes:

[0039] Normalization processing is performed on the first optimization control model, the second optimization control model, and the third optimization control model to obtain the model weights of the first optimization control model, the second optimization control model, and the third optimization control model in sequence. The calculation formula of the model weights is:

[0040]

[0041] Where W j Characterized as the model weight of the j-th optimized control model.

[0042] As a preferred solution of the present invention, the cut-off control solutions output by each optimization control model are weightedly combined by the model weights corresponding to each optimization model to obtain the optimal cut-off control solution, including:

[0043] The model weights are used to sequentially weight the electrical signals of the control cutter cutting operation of each optimization control model at each cutting operation timing to obtain the optimal cutting control scheme. The function expression of the optimal cutting control scheme is:

[0044] Top_taget[S t ]=∑ j∈[一,二,三] W j *taget j [S t ];

[0045] In the formula, Top_taget[S t ] is represented by the electrical signal S of the control cutter cutting operation at the tth cutting operation timing in the optimal cutting control scheme t , taget j [S t ] is represented by the electrical signal S of the control cutter cutting operation at the t cutting operation timing predicted by the jth optimization control model. t .

[0046] As a preferred solution of the present invention, the electrical signal is normalized before calculation.

[0047] As a preferred embodiment of the present invention, the expected value [E N ,…,E1] and the predicted value [S N ,…,S1] is normalized before the accuracy error is calculated.

[0048] As a preferred solution of the present invention, the method of controlling the cutting operation of the cutter using the optimal cutting control solution to achieve high-precision cutting of the paper-faced gypsum board includes:

[0049] At the tth cutting operation timing, an electrical signal S is output to the servo motor driving the cutter. t , in order to control the cutting operation of the cutter at the tth cutting operation sequence to achieve high-precision cutting of the paper-faced gypsum board.

[0050] As a preferred solution of the present invention, after the cutting length of the gypsum board changes, the optimal cutting operation solution is re-optimized.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The present invention sets multiple optimization targets for cutting control, establishes multiple optimization control models, and performs weighted combination of the cutting control schemes output by each optimization control model corresponding to the model weights of each optimization model to obtain the optimal cutting control scheme. The control optimization of the entire cutting process focuses on multiple indicators, improves the comprehensiveness of the control optimization, ensures a higher control optimization effect, and achieves high-precision cutting of paper-faced gypsum board. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other implementation drawings based on the provided drawings without inventive effort.

[0054] Figure 1 This is a flow chart of a control optimization method for high-precision cutting of gypsum board provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0056] like Figure 1 As shown, the present invention provides a control optimization method for high-precision cutting of gypsum board, including the following methods:

[0057] Step S1: setting multiple optimization objectives for the gypsum board cutting control, and establishing multiple optimization control models for predicting and generating a cutter cutting control solution based on each optimization objective, wherein each optimization control model predicts and outputs a cutter cutting control solution to achieve the corresponding optimization objective;

[0058] Set multiple optimization goals for drywall cut-off control, including:

[0059] The dynamic adjustment stability of the cutter in the cutting control scheme is quantified as steady-state accuracy as the first optimization objective of the paper-faced gypsum board. The function expression of the first optimization objective is:

[0060]

[0061] In the formula, taget1 represents the first optimization target, S t+1 、S tThey are represented by the electrical signals for controlling the cutter cutting operation at the t+1th and tth cutting operation timings, respectively; N is represented by the total number of cutting operation timings; t is represented by the measurement constant; T is represented by the transposition operator; and min is represented by the minimization operator;

[0062] The dynamic adjustment accuracy of the cutter in the cutting control scheme is quantified as cutting accuracy as the second optimization objective of the paper-faced gypsum board. The function expression of the second optimization objective is:

[0063]

[0064] In the formula, taget2 represents the second optimization objective, V(S t ) is characterized by the cutting speed generated by the electrical signal controlling the cutting operation of the cutter at the t-th cutting operation timing, It is represented by the running distance of the control cutter cutting operation at the t+1th and tth cutting operation timing, It is represented by the total running distance of the cutter in the cutting control scheme, and L is represented by the cutting length of the paper-faced gypsum board;

[0065] The dynamic adjustment response degree of the cutter in the cutting control scheme is quantified as the response accuracy as the third optimization objective of the paper-faced gypsum board. The function expression of the third optimization objective is:

[0066]

[0067] Where taget3 represents the third optimization objective, M represents the total number of dynamic adjustments of the cutter in the cutting control scheme, and Δτ represents the response delay time of the dynamic adjustment of the cutter in the cutting control scheme;

[0068] Statistics on the total number of dynamic adjustments of the cutter in the cutting control scheme include:

[0069] when This indicates that the cutter produces dynamic adjustment at the t+1th and tth cutting operation timing in the cutting control scheme;

[0070] when This indicates that the cutter does not produce dynamic adjustment at the t+1th and tth cutting operation timings in the cutting control scheme;

[0071] Where θ represents the adjustment threshold of the stability.

[0072] The first optimization target, the second optimization target and the third optimization target are constructed, and the dynamic adjustment stability, dynamic adjustment accuracy and dynamic adjustment response during the cutting operation of the cutter are respectively used as optimization targets. That is, by optimizing the optimization targets, it is possible to simultaneously achieve high stability, high precision and high responsiveness of the cutting during the cutting process, thereby achieving the optimization of the three indicators. In actual use, additions, deletions and modifications can be made as needed to meet actual use.

[0073] Step S2: quantifying the accuracy error between the predicted value of the cut-off control scheme obtained by each optimization control model and the expected value of the cut-off control scheme, and using the accuracy error to determine the model weight of each optimization control model;

[0074] Based on each optimization objective, multiple optimization control models are established for the prediction and generation of the cutter cutting control scheme, including:

[0075] Construct the first optimization control model for the first optimization objective. The model expression of the first optimization control model is:

[0076] taget1[S t+1 ]=LSTM_1(taget1[S t ,…,S t-k ]);

[0077] In the formula, taget1[S t+1 ] represents the S obtained by solving the first optimization goal t+1 ,taget1[S t ,…,S1] represents the S obtained by solving the first optimization goal t ,…,S t-k , S t-k It represents the electrical signal of the control cutter cutting operation at the tkth cutting operation timing, LSTM_1 represents the LSTM network of the first optimization control model, and k represents the measurement constant;

[0078] Construct a second optimization control model for the second optimization objective. The model expression of the second optimization control model is:

[0079] taget2[S t+1 ]=LSTM_2(taget2[S t ,…,S t-k ]);

[0080] In the formula, taget2[S t+1 ] represents the S obtained by solving the second optimization goal t+1 , taget2[S t ,…,S1] represents the S obtained by solving the second optimization goal t ,…,St-k , LSTM_2 represents the LSTM network of the second optimization control model;

[0081] A third optimization control model is constructed for the third optimization objective. The model expression of the third optimization control model is:

[0082] taget3[S t+1 ]=LSTM_3(taget3[S t ,…,S t-k ]);

[0083] In the formula, taget3[S t+1 ] represents the S obtained by solving the third optimization goal t+1 , taget3[S t ,…,S1] represents the S obtained by solving the third optimization goal t ,…,S t-k , LSTM_3 represents the LSTM network of the third optimization control model.

[0084] The first optimization control model, the second optimization control model and the third optimization control model are constructed to respectively predict the cutter control schemes of the three optimization targets to be maintained during the cutter cutting operation. That is, by predicting the cutter control schemes that can respectively achieve high stability, high precision and high responsiveness of the cutter during the cutter cutting process, the three cutter cutting control schemes are realized to achieve the three optimization targets respectively. Like the optimization targets, corresponding additions, deletions and modifications can be made in actual use as needed to meet the actual use requirements.

[0085] Quantify the accuracy error between the predicted value of the cut-off control scheme obtained by each optimized control model and the expected value of the cut-off control scheme, including:

[0086] The predicted value of the cut-off control scheme is obtained by predicting each optimization control model in turn [S N ,…,S1], and cut off the control scheme expected value [E N ,…,E1] and the predicted value of the cut-off control scheme [S N ,…,S1] to calculate the similarity and obtain the accuracy error of each optimization control model. The calculation formula of the accuracy error is:

[0087]

[0088] Where p j Characterized as the accuracy error of the j-th optimization control model, taget j (S t ) is represented as the predicted value S obtained by the j-th optimization control model t , E tIt is represented by the expected value of the electrical signal controlling the cutter cutting operation at the t-th cutting operation timing, j∈[1, 2, 3].

[0089] The model weights of each optimization control model are determined using the precision error, including:

[0090] Normalization processing is performed on the first optimization control model, the second optimization control model, and the third optimization control model to obtain the model weights of the first optimization control model, the second optimization control model, and the third optimization control model in sequence. The calculation formula of the model weights is:

[0091]

[0092] Where W j Characterized as the model weight of the j-th optimized control model.

[0093] The accuracy error is used to measure the prediction accuracy of the three optimization control models, and a higher model weight is assigned to the model with higher prediction accuracy. The three optimization control models are weightedly combined using the model weights to determine the optimal cutting control scheme, thereby ensuring the correctness of the optimal cutting control scheme while being compatible with the optimization implementation of the three optimization objectives, thereby achieving high-precision cutting of paper-faced gypsum board.

[0094] Step S3: The cutting control schemes output by each optimization control model are weightedly combined by the model weights corresponding to each optimization model to obtain the optimal cutting control scheme, and the optimal cutting control scheme is used to control the cutting operation of the cutter to achieve high-precision cutting of the paper-faced gypsum board.

[0095] The cut-off control schemes output by the respective optimization control models are weightedly combined to obtain an optimal cut-off control scheme by corresponding model weights of the respective optimization models, including:

[0096] The model weights are used to sequentially weight the electrical signals of the control cutter cutting operation of each optimization control model at each cutting operation timing to obtain the optimal cutting control scheme. The function expression of the optimal cutting control scheme is:

[0097] Top_taget[S t ]=∑ j∈[一,二,三] W j *taget j [S t ];

[0098] In the formula, Top_taget[S t ] is represented by the electrical signal S of the control cutter cutting operation at the tth cutting operation timing in the optimal cutting control scheme t , taget j [St ] is represented by the electrical signal S of the control cutter cutting operation at the t cutting operation timing predicted by the jth optimization control model. t .

[0099] The electrical signals were normalized before calculation.

[0100] Expected value [E N ,…,E1] and the predicted value [S N ,…,S1] is normalized before the accuracy error is calculated.

[0101] Utilize the optimal cutting control scheme to control the cutter cutting operation to achieve high-precision cutting of paper-faced gypsum board, including:

[0102] At the tth cutting operation timing, an electrical signal S is output to the servo motor driving the cutter. t , in order to control the cutting operation of the cutter at the tth cutting operation sequence to achieve high-precision cutting of the paper-faced gypsum board.

[0103] After the cutting length of the gypsum board changes, the optimal cutting operation plan is re-optimized.

[0104] The present invention sets multiple optimization targets for cutting control, establishes multiple optimization control models, and performs weighted combination of the cutting control schemes output by each optimization control model corresponding to the model weights of each optimization model to obtain the optimal cutting control scheme. The control optimization of the entire cutting process focuses on multiple indicators, improves the comprehensiveness of the control optimization, ensures a higher control optimization effect, and achieves high-precision cutting of paper-faced gypsum board.

[0105] The above embodiments are merely exemplary embodiments of the present application and are not intended to limit the scope of the present application. The scope of protection 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 scope of protection of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the scope of protection of the present application.

Claims

1. A control optimization method for high-precision cutting of gypsum board, characterized in that: This includes the following methods: Step S1: setting multiple optimization objectives for the gypsum board cutting control, and establishing multiple optimization control models for predicting and generating a cutter cutting control solution based on each optimization objective, wherein each optimization control model predicts and outputs a cutter cutting control solution to achieve the corresponding optimization objective; Step S2: quantifying the accuracy error between the cut-off control scheme prediction value obtained by each optimization control model and the cut-off control scheme expected value, and using the accuracy error to determine the model weight of each optimization control model; Step S3: performing weighted combination of the cutting control schemes output by the respective optimization control models by the model weights corresponding to the respective optimization models to obtain an optimal cutting control scheme, and using the optimal cutting control scheme to control the cutting operation of the cutter to achieve high-precision cutting of the paper-faced gypsum board; Quantify the accuracy error between the predicted value of the cut-off control scheme obtained by each optimized control model and the expected value of the cut-off control scheme, including: The predicted value of the cut-off control scheme is obtained by predicting each optimization control model in turn [S N ,…,S1], and cut off the control scheme expected value [E N ,…,E1] and the predicted value of the cut-off control scheme [S N ,…,S1] similarity calculation is performed to obtain the accuracy error of each optimization control model. The calculation formula of the accuracy error is: Where p j Characterized as the accuracy error of the j-th optimization control model, taget j (S t ) is represented as the predicted value S obtained by the j-th optimization control model t , E t It is represented by the expected value of the electrical signal controlling the cutter cutting operation at the t-th cutting operation timing, j∈[1, 2, 3].

2. The control optimization method for high-precision cutting of gypsum board according to claim 1, characterized in that: The multiple optimization objectives of setting the gypsum board cutting control include: The stability of the dynamic adjustment of the cutter in the cutting control scheme is quantified as steady-state accuracy as the first optimization goal of the paper-faced gypsum board. The functional expression of the first optimization goal is: In the formula, taget1 represents the first optimization target, S t+1 、S t They are represented by the electrical signals for controlling the cutter cutting operation at the t+1th and tth cutting operation timings, respectively; N is represented by the total number of cutting operation timings; t is represented by the measurement constant; T is represented by the transposition operator; and min is represented by the minimization operator; The dynamic adjustment accuracy of the cutter in the cutting control scheme is quantified as cutting accuracy as the second optimization goal of the paper-faced gypsum board. The function expression of the second optimization goal is: In the formula, taget2 represents the second optimization objective, V(S t ) is characterized by the cutting speed generated by the electrical signal controlling the cutting operation of the cutter at the t-th cutting operation timing, It is represented by the running distance of the control cutter cutting operation at the t+1th and tth cutting operation timing, It is represented by the total running distance of the cutter in the cutting control scheme, and L is represented by the cutting length of the paper-faced gypsum board; The dynamic adjustment response degree of the cutter in the cutting control scheme is quantified as the response accuracy as the third optimization target of the paper-faced gypsum board. The function expression of the third optimization target is: Where taget3 represents the third optimization objective, M represents the total number of dynamic adjustments of the cutter in the cutting control scheme, and Δτ represents the response delay time of the dynamic adjustment of the cutter in the cutting control scheme; The statistics of the total number of dynamic adjustments of the cutter in the cutting control scheme include: when This indicates that the cutter produces dynamic adjustment at the t+1th and tth cutting operation timing in the cutting control scheme; when This indicates that the cutter does not produce dynamic adjustment at the t+1th and tth cutting operation timings in the cutting control scheme; Where θ represents the adjustment threshold of the stability.

3. The control optimization method for high-precision cutting of gypsum board according to claim 2, characterized in that: The above-mentioned multiple optimization control models are established for prediction generation of the cutter cutting control scheme based on each optimization objective, including: A first optimization control model is constructed for the first optimization objective, wherein the model expression of the first optimization control model is: taget1[S t+1 ]=LSTM_1(taget1[S t ,…,S t-k ]); In the formula, taget1[S t+1 ] represents the S obtained by solving the first optimization goal t+1 ,taget1[S t ,…,S1] represents the S obtained by solving the first optimization goal t ,…,S t-k , S t-k It represents the electrical signal of the control cutter cutting operation at the tkth cutting operation timing, LSTM_1 represents the LSTM network of the first optimization control model, and k represents the measurement constant; A second optimization control model is constructed for the second optimization objective. The model expression of the second optimization control model is: taget2[S t+1 ]=LSTM_2(taget2[S t ,…,S t-k ]); In the formula, taget2[S t+1 ] represents the S obtained by solving the second optimization goal t+1 , taget2[S t ,…,S1] represents the S obtained by solving the second optimization goal t ,…,S t-k , LSTM_2 represents the LSTM network of the second optimization control model; A third optimization control model is constructed for the third optimization objective. The model expression of the third optimization control model is: taget3[S t+1 ]=LSTM_3(taget3[S t ,…,S t-k ]); In the formula, taget3[S t+1 ] represents the S obtained by solving the third optimization goal t+1 , taget3[S t ,…,S1] represents the S obtained by solving the third optimization goal t ,…,S t-k , LSTM_3 represents the LSTM network of the third optimization control model.

4. The control optimization method for high-precision cutting of gypsum board according to claim 3, characterized in that: Determining the model weights of each optimization control model by using the precision error includes: Normalization processing is performed on the first optimization control model, the second optimization control model, and the third optimization control model to obtain the model weights of the first optimization control model, the second optimization control model, and the third optimization control model in sequence. The calculation formula of the model weights is: Where W j Characterized as the model weight of the j-th optimized control model.

5. The control optimization method for high-precision cutting of gypsum board according to claim 4, characterized in that: The cut-off control schemes output by the respective optimization control models are weightedly combined to obtain an optimal cut-off control scheme by corresponding model weights of the respective optimization models, including: The model weights are used to sequentially weight the electrical signals of the control cutter cutting operation of each optimization control model at each cutting operation timing to obtain the optimal cutting control scheme. The function expression of the optimal cutting control scheme is: Top_roof[S t ]=∑ j∈[一,二,三] W j *foggy j [S t ]; In the formula, Top_taget[S t ] is represented by the electrical signal S of the control cutter cutting operation at the tth cutting operation timing in the optimal cutting control scheme t , taget j [S t ] is represented by the electrical signal S of the control cutter cutting operation at the t cutting operation timing predicted by the jth optimization control model. t .

6. The control optimization method for high-precision cutting of gypsum board according to claim 5, characterized in that: The electrical signal is normalized before calculation.

7. The control optimization method for high-precision cutting of gypsum board according to claim 6, characterized in that: The expected value [E N ,…,E1] and the predicted value [S N ,…,S1] is normalized before the accuracy error is calculated.

8. The control optimization method for high-precision cutting of gypsum board according to claim 7, characterized in that: The method of controlling the cutting operation of the cutter using the optimal cutting control scheme to achieve high-precision cutting of the gypsum board includes: At the tth cutting operation timing, an electrical signal S is output to the servo motor driving the cutter. t , in order to control the cutting operation of the cutter at the tth cutting operation sequence to achieve high-precision cutting of the paper-faced gypsum board.

9. The control optimization method for high-precision cutting of gypsum board according to claim 8, characterized in that: After the cutting length of the gypsum board changes, the optimal cutting operation plan is re-optimized.

Images