Glass fiber cloth warp tension control system

Abstract

The invention provides a glass fiber cloth warp tension control system. The glass fiber cloth warp tension control system comprises a double-sensor measuring unit, a signal processing unit, a control unit and an execution unit which are electrically connected. The double-sensor measuring unit comprises a front-end strain type tension sensor and a rear-end strain type tension sensor; the front-end strain type tension sensor is arranged between a let-off roller and a dropper of the weaving machine and is used for acquiring tension data of an upstream position of warp yarns; the rear-end strain type tension sensor is arranged between a reed and a cloth roller of the weaving machine and is used for acquiring tension data of the whole fabric; the signal processing unit comprises a first signal conditioning module, a second signal conditioning module and a data fusion module; the control unit comprises a basic PID (Proportion Integration Differentiation) module, a tension prediction module for operating a tension prediction algorithm based on an LSTM (Long Short Term Memory) neural network, a compensation calculation module and a control fusion module; the execution unit comprises a let-off motor. The present invention improves the control accuracy of warp tension control of a loom.

Description

Technical Field

[0001] The invention relates to a warp tension control system, in particular to a glass fiber cloth warp tension control system, and belongs to the technical field of textile machinery control. Background Art

[0002] Glass fiber cloth is an important industrial cloth with excellent high temperature resistance, corrosion resistance, insulation and other properties. It is widely used in composite material reinforcement, electronic circuit boards, insulation materials and other fields. Due to the characteristics of glass fiber yarn, it is easy to have problems such as broken yarn and hairy yarn during the weaving process. These problems are closely related to the control of warp tension. Therefore, the control of warp tension has an important influence on the quality of glass fiber cloth fabric.

[0003] At present, the commonly used warp tension control system mainly adopts a single sensor measurement combined with PID control. The tension sensor is installed between the warp let-off roller and the warp stopper, and can only measure the tension change in the warp area. This single-point measurement method cannot fully reflect the law of tension change during the weaving process, ignores the cumulative effect of warp tension, and cannot accurately reflect the influence of the weaving process on the warp tension, thereby restricting the control accuracy of the warp tension during the weaving process of glass fiber cloth. In addition, the control parameters of PID control are relatively fixed, which makes it difficult to adapt to the dynamic changes of weaving conditions. The control response has a lag and cannot effectively respond to sudden tension fluctuations.

[0004] Therefore, there is an urgent need for a novel glass fiber cloth warp tension control system in the art. Summary of the invention

[0005] Based on the above background, the purpose of the present invention is to provide a glass fiber cloth warp tension control system, which improves the control accuracy of the warp tension control of the loom through dual sensor collaborative measurement, combined with tension prediction and dual-level control.

[0006] In order to achieve the above-mentioned object of the invention, the present invention provides the following technical solutions:

[0007] A glass fiber cloth warp tension control system is used to control the warp tension of a loom, and the glass fiber cloth warp tension control system includes an electrically connected dual sensor measurement unit, a signal processing unit, a control unit and an execution unit;

[0008] The dual sensor measurement unit includes a front strain type tension sensor and a rear strain type tension sensor; the front strain type tension sensor is installed between the warp let-off roller and the warp dropper of the loom, and is used to collect tension data at the upstream position of the warp yarn; the rear strain type tension sensor is installed between the reed and the cloth winding roller of the loom, and is used to collect tension data of the entire fabric;

[0009] The signal processing unit includes a first signal conditioning module for processing the sampled data of the front-end strain type tension sensor, a second signal conditioning module for processing the sampled data of the rear-end strain type tension sensor, and a data fusion module for running an adaptive weighting algorithm;

[0010] The control unit includes a basic PID module, a tension prediction module for running a tension prediction algorithm based on the LSTM neural network, a compensation calculation module, and a control fusion module;

[0011] The execution unit includes a let-off motor.

[0012] Preferably, the adaptive weighting algorithm calculates the fused measured tension value F using the following formula

[0013] F = w1·Fs + w2·Fp;

[0014] In the formula, Fs is the tension data output by the first signal conditioning module, Fp is the tension data output by the second signal conditioning module, and w1 and w2 are weight coefficients;

[0015] Among them, the values of w1 and w2 follow the following formula:

[0016] When v ≤ 100 m / min, w1 = 0.7, w2 = 0.3;

[0017] When 100 m / min < v ≤ 200 m / min, w1 = 0.5, w2 = 0.5;

[0018] When v > 200 m / min, w1 = 0.3, w2 = 0.7;

[0019] In the formula, v is the loom speed.

[0020] Preferably, the basic PID module is used to calculate the basic torque adjustment amount ΔM b (t) of the let-off motor according to the deviation and the deviation change rate between the set tension value and the fused measured tension value

[0021] ΔM b (t) = K p ×e(t) + K i ×∫e(t)dt + K d ×de(t) / dt;

[0022] In the formula, K p is the proportionality coefficient, K i is the integral coefficient, K d is the differential coefficient, e(t) is the deviation between the set tension value and the fused measured tension value, ∫ is the integral symbol, and d is the differential symbol.

[0023] Preferably, the input of the tension prediction algorithm is an input vector consisting of a fused measured tension value sequence of a set number of historical sampling periods, a loom speed sequence, a temperature parameter sequence and a humidity parameter sequence, and the output of the tension prediction algorithm is a predicted tension value sequence of a set number of future sampling periods; the tension prediction algorithm is constructed based on an LSTM neural network, comprising an input layer, three LSTM layers, two fully connected layers and an output layer arranged in sequence, wherein the first LSTM layer includes 128 neurons, the second LSTM layer includes 64 neurons, the third LSTM layer includes 32 neurons, the first fully connected layer includes 64 neurons, the second fully connected layer includes 32 neurons, both fully connected layers use ReLU activation function, and the output layer uses a linear activation function.

[0024] Preferably, the set number of the historical sampling periods is greater than the set number of the future sampling periods.

[0025] Preferably, the compensation calculation module is used to calculate the predicted tension deviation sequence of a set number of future sampling periods according to the predicted tension value sequence of a set number of future sampling periods output by the tension prediction module, calculate the comprehensive prediction deviation by using the weighted time series method through the predicted tension deviation sequence, and calculate the compensation torque adjustment amount ΔM of the warp let-off motor by the following formula: f (t),

[0026] ΔM f (t) = K pf ×e p (t)+K if ×∫e p (t)dt+K df × p (t) / dt;

[0027] In the formula, K pf is the compensation proportional coefficient, K if is the compensation integral coefficient, K df is the compensation differential coefficient, e p (t) is the comprehensive prediction deviation, ∫ is the integral symbol, and d is the differential symbol.

[0028] Preferably, the comprehensive prediction deviation is calculated by the following formula:

[0029] e p (t) = Σ(ui × e'(t+i));

[0030] Wherein, ui is the weight coefficient of the ith deviation value in the predicted tension deviation sequence, e'(t+i) is the ith deviation value in the predicted tension deviation sequence, i=1~M, and M is the set number of future sampling cycles.

[0031] Preferably, the control fusion module is used to calculate the final torque adjustment amount ΔM(t) of the warp let-off motor according to the basic torque adjustment amount of the warp let-off motor output by the basic PID module and the compensation torque adjustment amount of the warp let-off motor output by the compensation calculation module by the following formula:

[0032] ΔM(t)=αΔM b (t)+βΔM f (t);

[0033] Where, ΔM b (t) is the basic torque adjustment, ΔM f (t) is the compensation torque adjustment amount, α and β are the variable weight coefficients, when the prediction accuracy index PA ≥ 0.95, α = 0.7, β = 0.3, when 0.9 ≤ PA < 0.95, α = 0.5, β = 0.5, when PA < 0.9, α = 0.3, β = 0.7.

[0034] Preferably, the prediction accuracy index is calculated by the following formula:

[0035] PA = 1 - |T'(t) - T(t)| / T(t);

[0036] Wherein, T'(t) is the predicted tension value of sampling period t in the predicted tension value sequence output by the tension prediction module in sampling period t-1, and T(t) is the fused measured tension value output by the data fusion module in sampling period t.

[0037] Compared with the prior art, the present invention has the following advantages:

[0038] The system uses dual sensors for collaborative measurement. The front strain type tension sensor is installed in the warp yarn area to timely sense the tension fluctuations caused by the warp let-off system. The rear strain type tension sensor is installed in the cloth forming area to detect the tension changes caused by the weaving process. The measurement data of the dual sensors are adaptively weighted and fused to simultaneously reflect the instantaneous changes and cumulative effects of the warp yarn tension, effectively improving the control accuracy.

[0039] Taking the basic PID module as the control basis, the LSTM neural network is used to realize tension prediction, and the compensation calculation and control fusion are combined for double-level control, ultimately achieving precise control with feedforward compensation for the torque adjustment amount of the warp feeding motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 It is a schematic diagram of a glass fiber cloth warp tension control system of the present invention;

[0042] In the figure: 1. front-end strain type tension sensor; 2. rear-end strain type tension sensor; 3. warp let-off roller; 4. warp dropper; 5. reed; 6. cloth winding roller; 7. heald frame; 8. warp yarn; 9. fabric; 10. first signal conditioning module; 11. second signal conditioning module; 12. data fusion module; 13. basic PID module; 14. tension prediction module; 15. compensation calculation module; 16. control fusion module; 17. warp let-off motor. DETAILED DESCRIPTION

[0043] The technical solution of the present invention is further described in detail below through specific embodiments and in conjunction with the accompanying drawings. It should be understood that the implementation of the present invention is not limited to the following embodiments, and any form of modification and / or change made to the present invention will fall within the protection scope of the present invention.

[0044] In the present invention, unless otherwise specified, all parts and percentages are weight units, and the equipment and raw materials used can be purchased from the market or are commonly used in the art. The methods in the following embodiments, unless otherwise specified, are conventional methods in the art. The components or equipment in the following embodiments, unless otherwise specified, are universal standard parts or components known to those skilled in the art, and their structures and principles are known to those skilled in the art through technical manuals or conventional experimental methods.

[0045] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present invention. However, one or more embodiments may also be implemented by those skilled in the art without these specific details.

[0046] An embodiment of the present invention discloses a glass fiber cloth warp yarn tension control system for controlling the warp yarn tension of a loom. The glass fiber cloth warp yarn tension control system includes an electrically connected dual sensor measurement unit, a signal processing unit, a control unit and an execution unit.

[0047] The dual sensor measurement unit includes a front strain type tension sensor 1 and a rear strain type tension sensor 2. The front strain type tension sensor 1 is installed between the warp let-off roller 3 and the warp dropper 4 of the loom to collect tension data at the upstream position of the warp yarn 8. The rear strain type tension sensor 2 is installed between the reed 5 and the cloth winding roller 6 of the loom to collect tension data of the entire fabric 9.

[0048] The signal processing unit includes a first signal conditioning module 10 for processing the sampling data of the front-end strain type tension sensor 1, a second signal conditioning module 11 for processing the sampling data of the rear-end strain type tension sensor 2, and a data fusion module 12 for running an adaptive weighting algorithm.

[0049] The control unit includes a basic PID module 13 , a tension prediction module 14 for running a tension prediction algorithm based on an LSTM neural network, a compensation calculation module 15 and a control fusion module 16 .

[0050] The execution unit comprises a warp let-off motor 17 .

[0051] The front-end strain-type tension sensor 1 is installed between the warp feed roller 3 and the warp dropper 4 of the loom, at a distance of 450-80mm from the warp dropper. The rear-end strain-type tension sensor 2 is installed between the reed 5 and the cloth winding roller 6 of the loom, at a distance of 5100-120mm from the reed. The two sensors are respectively mounted on adjustable mounting seats through independent vibration-damping brackets, and the adjustment ranges of the height and horizontal position of the mounting seats are ±20mm and ±15mm, respectively. The strain-type tension sensor is a prior art, and the specific structure is not described in detail. The sampling frequency of the front-end strain-type tension sensor 1 is 1000-1200Hz, and the sampling frequency of the rear-end strain-type tension sensor 2 is 500-600Hz. The reason for this setting is that the tension fluctuation frequency in the warp yarn 8 area is relatively high, and a higher sampling frequency is required to accurately capture it, while the tension change in the fabric 9 area is relatively gentle, and a lower sampling frequency can meet the measurement requirements.

[0052] The first signal conditioning module 10 and the second signal conditioning module 11 adopt the same structure, both including a first-stage amplifier circuit, a second-order Butterworth low-pass filter circuit and a second-stage amplifier circuit. The difference is that the cutoff frequency of the low-pass filter circuit of the first signal conditioning module 10 is 200Hz, and the cutoff frequency of the low-pass filter circuit of the second signal conditioning module 11 is 100Hz, so different filtering parameters are used to match the tension characteristics of different positions.

[0053] The adaptive weighted algorithm run by the data fusion module 12 uses the following formula to calculate the measured tension value F after fusion:

[0054] F=w1·Fs+w2·Fp;

[0055] In the formula, Fs is the tension data output by the first signal conditioning module 10, Fp is the tension data output by the second signal conditioning module 11, and w1 and w2 are weight coefficients;

[0056] Among them, the values of w1 and w2 follow the following formula:

[0057] When v ≤ 100 m / min, w1 = 0.7 and w2 = 0.3;

[0058] When 100 m / min < v ≤ 200 m / min, w1 = 0.5 and w2 = 0.5;

[0059] When v > 200 m / min, w1 = 0.3 and w2 = 0.7;

[0060] In the formula, v is the loom speed.

[0061] In the warp yarn 8 area, the front-end strain type tension sensor 1 can timely sense the tension fluctuation generated by the warp feeding system. In the cloth-forming area, the rear-end strain type tension sensor 2 can detect the tension change caused by the weaving process. After the measurement data of the two sensors are adaptively weighted and fused, it can simultaneously reflect the instantaneous change and cumulative effect of the tension of the warp yarn 8, effectively improving the control accuracy.

[0062] The basic PID module 13 is used to calculate the basic torque adjustment amount ΔM b (t) of the warp feeding motor 17 according to the deviation between the set tension value and the fused measured tension value and the deviation change rate through the following formula

[0063] ΔM b (t) = K p × e(t) + K i × ∫e(t)dt + K d × de(t) / dt;

[0064] In the formula, K p is the proportionality coefficient, K i is the integral coefficient, K d is the differential coefficient, e(t) is the deviation between the set tension value and the fused measured tension value, ∫ is the integral symbol, and d is the differential symbol.

[0065] The tension prediction algorithm operated by the tension prediction module 14, its input is an input vector composed of the fused measured tension value sequence, loom speed sequence, temperature parameter sequence, and humidity parameter sequence of a set number of historical sampling periods, and the output of the tension prediction algorithm is the predicted tension value sequence of a set number of future sampling periods.

[0066] The tension prediction algorithm is built on the basis of LSTM neural network, which is suitable for processing time series data. The tension prediction algorithm includes an input layer, three LSTM layers, two fully connected layers and an output layer, which are arranged in sequence. The first LSTM layer includes 128 neurons, the second LSTM layer includes 64 neurons, the third LSTM layer includes 32 neurons, the first fully connected layer includes 64 neurons, the second fully connected layer includes 32 neurons, both fully connected layers use ReLU activation function, and the output layer uses linear activation function. The three-layer LSTM structure is used to extract short-term, medium-term and long-term features, and the fully connected layer is used to realize the deep fusion of features.

[0067] Among them, the set number of historical sampling periods is greater than the set number of future sampling periods.

[0068] The compensation calculation module 15 is used to calculate the predicted tension deviation sequence of a set number of future sampling periods according to the predicted tension value sequence of a set number of future sampling periods output by the tension prediction module 14, calculate the comprehensive prediction deviation by using the weighted time series method through the predicted tension deviation sequence, and calculate the compensation torque adjustment amount ΔM of the warp let-off motor 17 by the following formula: f (t),

[0069] ΔM f (t) = K pf ×e p (t)+K if ×∫e p (t)dt+K df × p (t) / dt;

[0070] In the formula, K pf is the compensation proportional coefficient, K if is the compensation integral coefficient, K df is the compensation differential coefficient, e p (t) is the comprehensive prediction deviation, ∫ is the integral symbol, and d is the differential symbol.

[0071] It is difficult to cope with complex dynamic changes by relying solely on basic PID control. Predictive compensation is used to cope with tension changes in advance, and compensation control uses the same PID structure as basic PID control to maintain coordination with basic PID control.

[0072] Among them, the comprehensive prediction deviation is calculated by the following formula,

[0073] e p (t) = Σ(ui × e'(t+i));

[0074] Wherein, ui is the weight coefficient of the ith deviation value in the predicted tension deviation sequence, e'(t+i) is the ith deviation value in the predicted tension deviation sequence, i=1~M, and M is the set number of future sampling cycles.

[0075] The control fusion module 16 is used to calculate the final torque adjustment amount ΔM(t) of the warp let-off motor 17 according to the basic torque adjustment amount of the warp let-off motor 17 output by the basic PID module 13 and the compensation torque adjustment amount of the warp let-off motor 17 output by the compensation calculation module 15 by the following formula:

[0076] ΔM(t)=αΔM b (t)+βΔM f (t);

[0077] Where, ΔM b (t) is the basic torque adjustment, ΔM f (t) is the compensation torque adjustment amount, α and β are the variable weight coefficients, when the prediction accuracy index PA ≥ 0.95, α = 0.7, β = 0.3, when 0.9 ≤ PA < 0.95, α = 0.5, β = 0.5, when PA < 0.9, α = 0.3, β = 0.7.

[0078] Basic control and predictive compensation are dynamically balanced according to the predictive reliability. When the predictive reliability is accurate, the compensation effect is increased, and when the predictive reliability is inaccurate, basic control is mainly used to achieve the optimal balance between control stability and foresight.

[0079] Among them, the prediction accuracy index is calculated by the following formula:

[0080] PA = 1 - |T'(t) - T(t)| / T(t);

[0081] Wherein, T'(t) is the predicted tension value of sampling period t in the predicted tension value sequence output by the tension prediction module 14 in sampling period t-1, and T(t) is the fused measured tension value output by the data fusion module 12 in sampling period t.

[0082] The glass fiber cloth warp tension control system adopts dual sensors for collaborative measurement. The front-end strain type tension sensor 1 is installed in the warp yarn 8 area to timely sense the tension fluctuations caused by the warp feeding system. The rear-end strain type tension sensor 2 is installed in the cloth forming area to detect the tension changes caused by the weaving process. After the measurement data of the dual sensors are adaptively weighted and fused, they can simultaneously reflect the instantaneous changes and cumulative effects of the tension of the warp yarn 8, effectively improving the control accuracy.

[0083] The glass fiber cloth warp tension control system uses the basic PID module 13 as the control basis, uses the LSTM neural network to realize tension prediction, and performs double-level control in conjunction with compensation calculation and control fusion, ultimately achieving precise control of the torque adjustment amount of the warp let-off motor 17 with feedforward compensation.

[0084] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core ideas of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

Claims

1. A glass fiber cloth warp tension control system, used to control the warp tension of a loom, characterized in that: The warp tension control system of the fiberglass cloth includes a dual-sensor measurement unit, a signal processing unit, an intelligent control unit, a control unit, and an execution unit; The dual-sensor measurement unit includes a front-end strain-type tension sensor (1) and a rear-end strain-type tension sensor (2); the front-end strain-type tension sensor (1) is installed between the warp beam roller (3) and the heddle frame (4) of the loom for collecting tension data at the upstream position of the warp yarn (8); The rear-end strain-type tension sensor (2) is installed between the reed (5) and the cloth roller (6) of the loom for collecting tension data of the overall fabric (9); The signal processing unit includes a first signal conditioning module (10) for processing the sampling data of the front-end strain-type tension sensor (1), a second signal conditioning module (11) for processing the sampling data of the rear-end strain-type tension sensor (2), and a data fusion module (12) for running an adaptive weighted algorithm; The control unit includes a basic PID module (13), a tension prediction module (14) for running a tension prediction algorithm based on the LSTM neural network, a compensation calculation module (15), and a control fusion module (16); The execution unit includes a warp beam motor (17).

2. A glass fiber cloth warp tension control system according to claim 1, characterized in that: The adaptive weighted algorithm calculates the fused measured tension value F using the following formula F = w1·Fs + w2·Fp; In the formula, Fs is the tension data output by the first signal conditioning module (10), Fp is the tension data output by the second signal conditioning module (11), and w1 and w2 are weight coefficients; Among them, the values of w1 and w2 follow the following formula: When v ≤ 100 m / min, w1 = 0.7, w2 = 0.3; When 100 m / min < v ≤ 200 m / min, w1 = 0.5, w2 = 0.5; When v > 200 m / min, w1 = 0.3, w2 = 0.7; In the formula, v is the speed of the loom.

3. A glass fiber cloth warp tension control system according to claim 2, characterized in that: The basic PID module (13) is used to calculate the basic torque adjustment amount ΔM of the warp let-off motor (17) according to the deviation between the set tension value and the fused measured tension value and the deviation change rate through the following formula: b (t), ΔM b (t)=K p ×e(t)+K i ×∫e(t)dt+K d ×de(t) / dt; In the formula, K p is the proportionality coefficient, K i is the integration coefficient, K d is the differential coefficient, e(t) is the deviation between the set tension value and the measured tension value after fusion, ∫ is the integral sign, and d is the differential sign.

4. A glass fiber cloth warp tension control system according to claim 1, characterized in that: The input of the tension prediction algorithm is an input vector composed of a sequence of fused measured tension values, a sequence of loom speeds, a sequence of temperature parameters, and a sequence of humidity parameters for a set number of historical sampling periods. The output of the tension prediction algorithm is a sequence of predicted tension values for a set number of future sampling periods; the tension prediction algorithm is constructed based on the LSTM neural network and includes an input layer, three LSTM layers, two fully connected layers, and an output layer arranged in sequence. Among them, the first LSTM layer includes 128 neurons, the second LSTM layer includes 64 neurons, the third LSTM layer includes 32 neurons, the first fully connected layer includes 64 neurons, the second fully connected layer includes 32 neurons. Both fully connected layers use the ReLU activation function, and the output layer uses the linear activation function.

5. A glass fiber cloth warp tension control system according to claim 4, characterized in that: The set number of the historical sampling periods is greater than the set number of the future sampling periods.

6. A glass fiber cloth warp tension control system according to claim 4, characterized in that: The compensation calculation module (15) is used to calculate a predicted tension deviation sequence of a set number of future sampling periods according to a predicted tension value sequence of a set number of future sampling periods output by the tension prediction module (14), calculate a comprehensive predicted deviation by using a weighted time series method through the predicted tension deviation sequence, and calculate a compensation torque adjustment amount ΔM of the warp let-off motor (17) by the following formula: f (t), ΔM f (t)=K pf ×e p (t)+K if ×∫e p (t)dt+K df ×de p (t) / dt; In the formula, K pf is the compensation proportional coefficient, K if is the compensation integral coefficient, K df is the compensation differential coefficient, e p (t) is the comprehensive prediction deviation, ∫ is the integral symbol, and d is the differential symbol.

7. A glass fiber cloth warp tension control system according to claim 6, characterized in that: The comprehensive prediction deviation is calculated by the following formula e p (t)=Σ(ui×e'(t+i)); In the formula, ui is the weight coefficient of the i-th deviation value in the predicted tension deviation sequence, e'(t + i) is the i-th deviation value in the predicted tension deviation sequence, i = 1 ~ M, and M is the set number of future sampling periods.

8. A glass fiber cloth warp tension control system according to claim 1, characterized in that: The control fusion module (16) is used to calculate the final torque adjustment amount ΔM(t) of the warp let-off motor (17) according to the basic torque adjustment amount of the warp let-off motor (17) output by the basic PID module (13) and the compensation torque adjustment amount of the warp let-off motor (17) output by the compensation calculation module (15) by the following formula: ΔM(t)=αΔM b (t)+βΔM f (t); In the formula, ΔM b (t) is the basic torque adjustment, ΔM f (t) is the compensation torque adjustment amount, α and β are the variable weight coefficients, when the prediction accuracy index PA ≥ 0.95, α = 0.7, β = 0.3, when 0.9 ≤ PA < 0.95, α = 0.5, β = 0.5, when PA < 0.9, α = 0.3, β = 0.

7.

9. A glass fiber cloth warp tension control system according to claim 8, characterized in that: The prediction accuracy index is calculated by the following formula: PA = 1 - |T'(t) - T(t)| / T(t); In the formula, T'(t) is the predicted tension value of the t sampling period in the predicted tension value sequence output by the tension prediction module (14) in the t-1 sampling period, and T(t) is the fused measured tension value output by the data fusion module (12) in the t sampling period.

Images