MPC-based setting machine cropping moisture content control method and system

Abstract

The invention relates to the technical field of textile printing and dyeing, in particular to a setting machine cropping moisture content control method and system based on MPC. An MPC model is constructed, and the MPC model comprises the steps that actually-measured and preset water content and the first control parameter state vector serve as input, and predicted water content is obtained; minimizing the difference value between the predicted water content and the preset water content as a target; solving and optimizing the control increment by using the optimization matrix and sequential quadratic programming; and performing action regulation and control on an execution mechanism by utilizing the optimal control increment. The invention solves the problems of insufficient detection precision, hysteresis and poor interference resistance in the existing single temperature feedback control of the moisture content of the fabric.

Description

Technical Field

[0001] The present invention relates to the technical field of textile printing and dyeing, and in particular to a method and system for controlling the moisture content of falling cloth of a setting machine based on MPC. Background Art

[0002] During the fabric dyeing and finishing process, precise control of the moisture content of the finished fabric is crucial to ensure the fabric's feel, dimensional stability, color uniformity, and other physical properties during subsequent processing or use.

[0003] Existing drying and setting equipment controls the moisture content of fabrics through single temperature feedback, which has the following defects:

[0004] 1. Lag: The moisture content of the fabric is indirectly estimated by relying solely on the drying room temperature, which cannot respond to the actual moisture changes of the fabric in real time.

[0005] 2. Insufficient precision: The nonlinear relationship between temperature and moisture content is complex, and single temperature threshold control can easily lead to over-baking or under-baking;

[0006] 3. Poor anti-interference: Factors such as environmental humidity fluctuations, fabric types, and differences in organizational structure are not dynamically compensated. Summary of the Invention

[0007] In view of the shortcomings of the existing methods, the present invention uses the MPC model to fuse multi-sensor data and coordinates control with the actuator to achieve precise adjustment of the moisture content of the fabric.

[0008] The technical solution adopted by the present invention is: a method for controlling the moisture content of the cloth dropped by a setting machine based on MPC includes the following steps:

[0009] Step 1: Collect control parameters;

[0010] As a preferred embodiment of the present invention, the control parameters include: temperature value, humidity value, moisture content, air pressure difference value, vehicle speed value, exhaust volume, and ratio of heat source power to circulation fan flow rate.

[0011] Step 2: Construct an MPC model. The MPC model includes: taking the measured and preset water cuts and the first control parameter state vector as input to obtain the predicted water cut; minimizing the difference between the predicted water cut and the preset water cut; solving and optimizing the control increment using an optimization matrix and sequential quadratic programming; and controlling the actuator's motion using the optimal control increment;

[0012] As a preferred embodiment of the present invention, the first control parameters include: average humidity of the drying room, average temperature of the drying room, vehicle speed, and ratio of heat source power to circulation fan flow rate.

[0013] As a preferred embodiment of the present invention, step 2 specifically includes:

[0014] Preset prediction time domain N p , control time domain N c 、W H and W u ;

[0015] Construct the prediction equation:

[0016] Among them, H pred (k+1) is the moisture content prediction value at the k+1th moment; H(k) is the measured moisture content of the fabric at the drop point at the kth moment; α is the temperature influence coefficient; β is the humidity self-regulation coefficient; γ is the hot air ratio coefficient; ΔT is the difference in the average temperature of the drying room at adjacent moments; ε is the adjustable coefficient; v is the vehicle speed; Q / F is the ratio of heat source power to circulation fan flow;

[0017] Construct the minimization objective function:

[0018] Among them, W H is the weight of weighing error; W u Weigh the smoothness weight of the control increment; Δu is the control increment;

[0019] Construct the optimization matrix and use the SQP algorithm to solve Δu.

[0020] As a preferred embodiment of the present invention, the optimization matrix formula is:

[0021]

[0022] Where A is the first Jacobian matrix, b H 、b u is the error term and the control increment term vector, ΔX represents the increment of the state vector X(k).

[0023] As a preferred embodiment of the present invention, the optimization of the control increment adopts the model parameter online correction model, the formula is: θ(k'+1)=θ(k')+μ·J －1 (θ(k'))*(H(k')-H pred (k')), where μ is the adaptive learning rate, θ k’ is the control parameter coefficient vector at the k'th iteration, J-1 is the inverse of the second Jacobian matrix, H(k') is the measured value of the fabric moisture content at the drop point at the k'th iteration, H pred (k') The predicted value of moisture content at the k'+1th iteration.

[0024] As a preferred embodiment of the present invention, the control increment includes: the change in the speed of the vehicle motor, the change in the circulation fan flow at adjacent moments, the change in the heat source power at adjacent moments, and the change in the exhaust at adjacent moments.

[0025] As a preferred embodiment of the present invention, the control increment is constrained by utilizing the humidity gradient in adjacent drying rooms.

[0026] As a preferred embodiment of the present invention, the control increment is constrained by utilizing the air pressure difference between adjacent drying rooms.

[0027] As a preferred embodiment of the present invention, a system adopting a method for controlling moisture content of falling cloth of a setting machine based on MPC includes:

[0028] Actuator, controller, humidity sensor, temperature sensor, moisture content sensor; the actuator is electrically connected to the controller, and the humidity sensor, temperature sensor, moisture content sensor are electrically connected to the controller;

[0029] in,

[0030] The humidity sensor is used to collect the humidity value in each drying room;

[0031] The temperature sensor is used to collect the temperature value in each drying room;

[0032] The moisture content sensor is used to detect the moisture content of the fabric at the drop point;

[0033] The controller uses the collected humidity value, temperature value, moisture content and the trained MPC model to control the action of the actuator to adjust the moisture content.

[0034] Beneficial effects of the present invention:

[0035] 1. Build an MPC model and use it to collect indicators such as temperature, humidity, moisture content, and air pressure inside and outside the drying room. Use the MPC model to fine-tune the actuator's movements to achieve precise control of fabric moisture content. The moisture content control accuracy is ±0.5% to 2%, significantly better than the ±3% to 5% error of traditional single temperature feedback.

[0036] 2. Adaptive adjustment of the prediction time domain Np and the control time domain Nc, combined with the weighting matrix W H 、W u Dynamic optimization, real-time compensation for interference such as ambient humidity fluctuations, fabric types, and differences in weave structure, to ensure process stability;

[0037] 3. Construct an online correction model for model parameters, iteratively optimize the control parameter coefficients, and obtain the optimal control increment;

[0038] 4. Optimize humidity gradient constraints, adapt differentiated processes for cotton and chemical fibers, set gradient constraints to avoid uneven fiber expansion due to sudden changes in humidity, and reduce the risk of wrinkles and deformation; reduce energy waste in adjacent drying rooms through humidity gradient constraints, and dynamically match vehicle speed with heat source power; process 200g / m 2 When processing cotton fabrics, the average temperature of the drying room is reduced from 185℃ to 178℃ through humidity gradient constraint, and the energy consumption is reduced by 12%. When processing chemical fiber fabrics in the 5-section drying room setting machine, the humidity distribution is optimized from 60%→45%→30%→15%→5%RH to 55%→45%→35%→25%→15%RH through gradient constraint, combined with dynamic matching of vehicle speed (10-100m / min) and heat source power (20-100%), processing 200g / m 2 When processing cotton fabrics, the average drying room temperature is reduced from 185°C to 178°C through gradient constraint, which can reduce the frequency of fan and heat source power adjustment and reduce energy consumption by 12%.

[0039] 5. Pressure difference ΔP between adjacent drying rooms i,i+1 ≤50Pa, ensuring uniform airflow distribution and avoiding too fast or too slow airflow speed, which affects the uniformity of moisture evaporation on the fabric, resulting in insufficient or excessive drying of certain parts of the fabric, affecting the quality of the final product; for example, at a speed of 100m / min, pressure difference control can reduce the deviation of the fabric's lateral moisture content from ±2% to ±0.8%. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of the method for controlling the moisture content of the cloth dropped by the setting machine based on MPC of the present invention;

[0041] Figure 2 It is a schematic diagram of the moisture content control system of the cloth falling from the MPC setting machine of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore only shows the components related to the present invention.

[0043] like Figure 1 As shown, a method for controlling the moisture content of the cloth dropped from a setting machine based on MPC includes the following steps:

[0044] Step 1: Collect control parameters;

[0045] Control parameters include: temperature, humidity, moisture content, air pressure difference, vehicle speed, exhaust volume, ratio of heat source power to circulation fan flow;

[0046] It also includes: eliminating abnormal values of control parameters, and the 3σ criterion can be used.

[0047] The temperature value is collected by using several temperature sensors arranged along the fabric running direction of the drying room;

[0048] Temperature sensor T n , n is the number of temperature sensors, n>1;

[0049] The temperature sensor can be a distributed optical fiber temperature sensor, model IF-DTS, which is placed in the cavity of the drying room. The temperature sensor is firmly connected to the drying room and electrically connected to the controller.

[0050] The temperature sensor can also use an armored K-type thermocouple to measure the temperature of the space. It is inserted into the inner cavity of the drying room. The thermocouple is firmly connected to the drying room and electrically connected to the controller.

[0051] The humidity value is collected by using several humidity sensors arranged along the fabric running direction in the drying room;

[0052] Humidity sensorHair m , m is the number of humidity sensors, m>1;

[0053] The humidity sensor can be a high-temperature capacitive humidity sensor; it is placed on the inner wall of the drying room, with an accuracy of ±3% to 5% RH, and is firmly connected to the drying room and electrically connected to the controller;

[0054] The humidity sensor can also be an optical humidity sensor, placed in the drying room, with the optical window facing the mainstream wind direction, with an accuracy of ±1.5% to 3% RH, firmly connected to the drying room through a shock absorber and electrically connected to the control layer.

[0055] Among them, the moisture content is collected by using the fabric moisture content sensor at the drop of the setting machine;

[0056] The moisture content sensor MC can be an infrared absorption sensor / capacitive sensor, which is placed on the rack where the cloth is dropped by the setting machine outside the drying room. The measurement accuracy is: ±0.5%~2% / ±2%~5%. It is firmly connected to the drying room and electrically connected to the controller.

[0057] The moisture content sensor can also be a microwave moisture content sensor, which is placed on the rack where the fabric falls on the setting machine outside the drying room to measure the moisture content of the fabric with an accuracy of ±0.5%. It is firmly connected to the drying room and electrically connected to the controller.

[0058] The air pressure difference is collected by using the air pressure sensor installed between each drying room of the setting machine;

[0059] The air pressure difference ΔP is the pressure difference between adjacent drying rooms, ΔP i,i+1 =PA i-PA i+1 , accuracy ±0.5% FS;

[0060] Air pressure sensor PA w , w is the number of humidity sensors, w>1;

[0061] The air pressure sensor can be a high-temperature resistant ceramic capacitive / thermocouple differential pressure sensor, placed in the drying room with an accuracy of ±0.5% FS / ±1.0% FS, firmly connected to the drying room and electrically connected to the controller;

[0062] The air pressure sensor can also be a high-temperature piezoresistive sensor, placed outside the drying room, connected to the inner cavity of the drying room through a pressure-inducing pipe that has been insulated / heated, and firmly connected to the drying room, and electrically connected to the controller.

[0063] The vehicle speed value, circulation fan flow, heat source power, and exhaust volume are obtained using actuators, which include: vehicle speed motor, variable frequency circulation fan, heat source proportional valve, and electric exhaust valve;

[0064] The speed motor is mainly used to pull the fabric on the cloth clip / needle plate of the setting machine. Its speed value v usually ranges from 10 to 100 m / min to meet the setting requirements of different fabrics. The speed value v is proportional to the speed M of the speed motor.

[0065] The variable frequency circulating fan ensures uniform flow of hot air inside the setting machine. Its operating frequency range is between 30 and 60 Hz. By adjusting the fan speed with a frequency converter, the hot air flow in the fan drying room can be precisely controlled, thus ensuring that the temperature and humidity inside the setting machine are at an optimal state. The output circulating fan flow rate F is adjusted by changing the circulating fan speed v'.

[0066] The heat source proportional valve is used to control the heating system of the setting machine. The heat source proportional valve of the setting machine will be installed on the heat source transmission pipeline, such as the steam pipeline or gas pipeline. Its adjustment range is between 20% and 100%. By adjusting the opening of the proportional valve, the heat output of the heating system can be accurately controlled; the output heat source power value Q.

[0067] The electric exhaust valve is driven by a motor to open and close the valve, and its opening range is between 0 and 100%. It is used to control the air circulation between the drying room and the external environment, and adjust the air circulation volume inside the setting machine, so as to ensure that the temperature, humidity and pressure inside the drying room are in the optimal state, and output the exhaust volume E.

[0068] Also includes: setting fabric property parameters;

[0069] Fabric property parameters include: fabric weight (g / m 2 ), accuracy ±1g / m 2; Fabric width (m), accuracy ±0.01m; Fabric moisture content preset value (%), accuracy ±0.5%; Fabric types include: cotton or chemical fiber.

[0070] Step 2: Construct an MPC model. The MPC model includes: taking the measured and preset water cuts and the first control parameter state vector as input to obtain the predicted water cut; minimizing the difference between the predicted water cut and the preset water cut; solving and optimizing the control increment using an optimization matrix and sequential quadratic programming; and controlling the actuator's motion using the optimal control increment;

[0071] The first control parameters include: average humidity of the drying room Hair avg , average temperature of drying room T avg , vehicle speed v, ratio of heat source power to circulation fan flow Q / F;

[0072] Among them, Hair avg is the average value of m humidity sensors; T avg is the mean value of n temperature sensors;

[0073] The formula of the first control parameter state vector is:

[0074] X(k)=[Hair avg (k),T avg (k),v(k),Q / F(k)] T (1)

[0075] Wherein, k is the time; X(k) is updated periodically. In this embodiment, the timer Δt=5 seconds;

[0076] The first control parameter state vector is 4-dimensional, which is a mathematical abstraction of the thermodynamic state and equipment operating parameters in the drying room of the setting machine. Each dimension represents a key variable that affects the moisture content of the fabric at the outlet of the setting machine:

[0077] Hair avg (k) is the average air humidity (%RH) in the drying room at the kth moment, reflecting the water vapor content in the drying room;

[0078] T avg (k) is the average temperature in the drying room at the kth moment (°C), which determines the thermodynamic driving force for water evaporation;

[0079] v(k) is the vehicle speed at the kth moment (m / min), which is fed back in real time by the vehicle speed motor and affects the residence time of the fabric in the drying room;

[0080] Q / F(k) is the ratio of the heat source power Q to the circulation fan flow F at the kth moment (kW / Hz), reflecting the thermal intensity of the hot air;

[0081] These four variables constitute the core state parameters of the drying process in the drying room. Through linear or nonlinear combination, a state space model is established to characterize the dynamic changes of the system (such as drying room humidity, drying room temperature, vehicle speed, heat source power and circulation fan flow ratio) over time, providing basic input for the MPC prediction model.

[0082] The construction of the MPC model includes:

[0083] 1. Preset prediction time domain N p , control time domain N c , weight matrix W H and W u ;

[0084] In this embodiment, N p =10;N c =5;W H =diag(0.6,0.2,0.2), which are the weights of moisture content error, temperature error, and humidity error respectively; W u =diag(0.1,0.15,0.1,0.05), which are the smoothness weights of vehicle speed, circulation fan speed, heat source power and drying room exhaust opening respectively;

[0085] It also includes: setting control parameter constraints; wherein,

[0086] Humidity gradient constraints include:

[0087] Cotton fabric humidity gradient constraint: humidity gradient constraint threshold value in adjacent drying rooms | Hair i -Hair i+1 ∣≤15%;

[0088] Humidity gradient constraint for chemical fiber fabrics: Humidity gradient constraint threshold in adjacent drying rooms | Hair i -Hair i+1 ∣≤10%;

[0089] When constructing the optimization problem, the MPC model embeds the humidity gradient constraint as a hard constraint in the state-space model and in the objective function solution process. By limiting the humidity variable, the humidity gradient constraint directly influences the construction of the average humidity in the drying rooms in the state-space model. When the humidity difference between adjacent drying rooms approaches or exceeds the constraint threshold at a certain moment, the model adjusts its prediction of the future state. This is because abnormal humidity fluctuations can lead to deviations in fabric moisture content control, which in turn affects the operating status of the entire system.

[0090] The objective function of Equation 3 of the MPC model aims to make the actual moisture content of the fabric at the setting machine as close as possible to the moisture content set by the process, while satisfying a series of constraints. set, while reducing the frequent changes in the actuator output; the humidity gradient constraint is embedded in the solution process of this objective function as a hard constraint; during the optimization calculation, the algorithm will predict the fabric moisture content at multiple moments in the future based on the current system state and control input at each sampling moment; in this prediction process, the humidity gradient constraint will limit the range of change of the humidity variable to ensure that the predicted humidity state meets the constraint requirements; if the humidity gradient in the prediction result exceeds the constraint range, the controller adjusts the output of the actuator to meet the humidity gradient constraint and optimize the objective function.

[0091] For example, the MPC model executes cyclically to detect whether the humidity gradient constraint meets the threshold condition in real time. When the threshold is exceeded, W is adjusted. H The humidity error weight is quantified, which increases ΔE and decreases ΔM of the MPC model;

[0092] For example, a sudden increase in humidity for chemical fiber fabrics in the third drying room causes the humidity gradient constraint to be 12%, exceeding the limit by 2%. The MPC model will increase the exhaust valve opening ΔE (maximum within the limit) or increase ΔF, while slightly reducing ΔM (extending the residence time) to quickly restore the humidity gradient balance.

[0093] In addition, the humidity gradient constraint will also affect the average humidity of the drying room in X(k) avg When the humidity difference between adjacent drying rooms exceeds the threshold, the system determines that the current humidity distribution is abnormal and triggers formula 5. By comparing the measured moisture content H(k) with the predicted value H pred (k), the humidity self-regulation coefficient β of Formula 2 is modified (for example, β is increased from 0.12 to 0.14), and the influence weight of humidity on moisture content prediction is enhanced.

[0094] For example, in cotton fabric production, if the humidity in the second drying room is 60% and the humidity in the third drying room is 40% (humidity gradient 20% > 15%), the MPC model will forcibly adjust the opening E of the exhaust valve in the third drying room and increase the humidity self-regulation coefficient β in the prediction equation of Equation 2 to suppress the risk of subsequent gradient exceeding the standard.

[0095] Priority scheduling in dynamic optimization. When the humidity gradient constraint conflicts with other constraints (such as temperature safety margin and vehicle speed limit), the MPC model follows the process priority principle:

[0096] Low-priority scenario: When the temperature does not exceed the limit, priority is given to satisfying the humidity gradient constraint (for example, sacrificing some heat source power adjustment speed to ensure that the gradient is ≤15%).

[0097] High-risk scenarios: When the humidity gradient continues to exceed the standard and is accompanied by abnormal temperature, the "humidity gradient + temperature" dual constraints are triggered, and the exhaust valve E and heat source Q are adjusted synchronously to avoid fiber damage (for example, when the humidity gradient of chemical fiber fabrics exceeds the standard and the temperature is >150°C, the vehicle speed is automatically reduced and the exhaust is increased, providing double protection).

[0098] For fabrics made from different fiber materials, the humidity gradient constraints of adjacent drying rooms must be adjusted accordingly. For example, cotton fabrics are more sensitive to humidity changes and require smaller humidity gradient constraints; whereas chemical fiber fabrics are less sensitive to humidity changes and can tolerate larger humidity gradient constraints. This helps meet the processing requirements of different types of fabrics. The humidity gradient constraint in the drying room is a key innovation of this invention and has significant significance in dyeing and finishing processes. Specifically:

[0099] 1. Improve fabric quality: By controlling the humidity gradient between adjacent drying rooms, problems such as wrinkles and deformation caused by excessive humidity changes during the shaping process can be avoided. This helps to ensure the fabric's physical properties such as feel and dimensional stability in subsequent processing or use.

[0100] 2. Optimize energy consumption: Reasonable humidity gradient constraints can reduce humidity differences between drying rooms, thereby reducing energy consumption. For example, when the humidity gradient is large, it is necessary to increase the heat source power or extend the drying time to ensure that the fabric reaches the ideal moisture content. By controlling the humidity gradient, energy consumption can be reduced while ensuring fabric quality.

[0101] Also includes: the air pressure difference constraint threshold ΔP between adjacent drying rooms i,i+1 =PA i -PA i+1 ≤50Pa;

[0102] The change of the air pressure difference ΔP will change the airflow state in the drying room, thereby affecting the average humidity H in the drying room. avg and Q / F; when ΔP increases, it may cause abnormal air flow velocity in the drying room, change the moisture distribution, and affect H avg The change of airflow may also affect the heat transfer efficiency, and then affect the coordinated work of heat source power and circulation fan flow, resulting in changes in Q / F. These changes will eventually affect the actual state of the drying room reflected by the state vector. ΔP indirectly affects the calculation of the Q / F term in Equation 2, thereby changing the moisture content H of the fabric at the next moment. pred The predicted value enables the prediction model to more accurately reflect the actual situation; in the optimization solution process of formula 4, ΔP≤50Pa is used as a constraint condition; when the predicted H pred With H setWhen there is an error and ΔP approaches or exceeds the limit, it will constrain the adjustment of the control increment; if ΔP is too large, when solving Δu, the algorithm will give priority to adjusting the control variables related to air pressure, such as the exhaust valve opening ΔE and the circulation fan speed v'; to meet the air pressure difference constraint and balance the moisture content error at the same time, to ensure that the objective function reaches the optimal solution, realize the precise control of the fabric moisture content and the stable operation of the system.

[0103] Also includes: Maximum allowable temperature T max The constraints are: 180℃ for cotton and 150℃ for chemical fibers.

[0104] 2. Use the control parameters to construct the prediction equation, the formula is:

[0105]

[0106] Among them, H pred (k+1) is the moisture content prediction value at the k+1th moment; H(k) is the measured moisture content of the fabric at the drop point at the kth moment; α is the temperature influence coefficient; β is the humidity self-regulation coefficient; γ is the hot air ratio coefficient; ΔT is the difference in the average temperature of the drying room at adjacent moments, ΔT=T avg (k+1)-T avg (k); ε is the adjustable coefficient; v is the vehicle speed; Q / F is the ratio of heat source power to circulation fan flow rate;

[0107] In this embodiment, α=0.025-0.035, β=0.10-0.15, γ=0.005-0.015, and v=0.5; α is dynamically adjusted according to the fabric weight; β is adaptive according to the ambient humidity fluctuation; and γ is determined by historical data regression.

[0108] You can also set constraints; including: vehicle speed mutation limit, exhaust valve step limit.

[0109] Vehicle speed mutation constraint: |Δv|≤3m / min, dead zone ±0.5m / min;

[0110] Exhaust valve step constraint: |ΔE|≤8% / Δt (Δt=5s);

[0111] Temperature safety boundary constraint: T avg <T max , if it exceeds T max Trigger an alarm and reduce the heat source power Q;

[0112] ΔT reflects the dynamic changes in the drying room temperature and has an important impact on the evaporation of moisture from the fabric; v affects the residence time of the fabric in the drying room, thus affecting the drying effect;

[0113] Q / F reflects the thermal intensity of hot air, which affects the rate of moisture evaporation from fabrics;

[0114] α quantifies the influence of temperature change ΔT on the change of fabric moisture content. The value of α varies with different fabric types and drying room environments.

[0115] β is used to measure the relationship between H(k) and H set The impact of the differences between them on future moisture content changes;

[0116] γ reflects the influence of Q / F on the moisture content of fabric;

[0117] α·ΔT·v ﹣ε The larger the temperature change ΔT is, the faster the moisture in the fabric evaporates and the more the moisture content decreases. ΔT is positively correlated with the change in moisture content.

[0118] v ﹣ε This indicates that the faster the vehicle speed, the shorter the fabric stays in the drying room, and the chance of water evaporation per unit time is reduced, so the moisture content decreases relatively less; this item comprehensively considers the effects of temperature and vehicle speed on moisture content changes.

[0119] Hit when H(k)>H set hour, At this time, the term is negative, which means that the moisture content will decrease towards the target value; when H(k) <H set hour, This item is positive, indicating that the moisture content may increase to approach the target value. This item reflects that the system of the present invention has a mechanism for automatically adjusting the moisture content to approach the target value.

[0120] The larger the Q / F in γ·Q / F(k), the higher the thermal intensity of the hot air, the faster the moisture evaporates from the fabric, and the more obvious the decrease in moisture content, so this item is positively correlated with the change in moisture content.

[0121] 3. Optimize control input. The core of MPC is to solve an optimization problem, that is, to minimize the objective function. The formula for minimizing the objective function is:

[0122]

[0123] Among them, W H To weigh the error weights, such as moisture content error, temperature error, and humidity error; W u Weigh the smoothness of the control increment; Δu is the control increment, Δu = [ΔM, ΔF, ΔQ, ΔE] T , ΔM is the change in the speed of the vehicle motor, ΔF is the change in the circulation fan flow rate at adjacent moments, ΔQ is the change in the heat source power at adjacent moments, and ΔE is the change in the exhaust air at adjacent moments.

[0124] Formula 2 and Formula 3 are the core of the moisture content prediction model of the setting machine of the present invention. The system can predict H based on the current moment H(k), ΔT, v and Q / F information. pred (k+1); H pred (k+1) is used to optimize the solution of formula (3), H pred With H set Calculate the error to determine the optimal control input change Δu = [ΔM, ΔF, ΔQ, ΔE] T Therefore, it is necessary to explicitly predict the time domain N p and control time domain N c The value of N is calculated based on the state space model and the current state. p The predicted value H at the moment pred (k); prediction time domain N p Determines the range of the error term summation, that is The summation upper limit in the control time domain N c It is related to the summation range of the control input variation, that is, At the same time, some constraints can be set to limit the value of the control variable Δu in the optimization solution.

[0125] 4. Construct an optimization matrix and use the sequential quadratic programming (SQP) algorithm to solve Δu;

[0126] The formula for the optimization matrix is:

[0127]

[0128] Where A is the first Jacobian matrix, b H 、b u is the error term and the control increment term vector, ΔX represents the increment of the state vector X(k), which is the difference between the current state and the next state in MPC, that is,

[0129] Real-time computing equal partial derivatives; partial derivatives It represents the rate of change of fabric moisture content with vehicle speed, that is, the degree of influence of vehicle speed v on fabric moisture content. It is a key element of A and is used to quantify the dynamic influence of the control variable (vehicle speed) on the output variable (fabric moisture content).

[0130] Similarly, real-time computing Together they form the Jacobian matrix, which is used to quantify the relationship between the control variables and the output variables;

[0131] The velocity term “α·ΔT·v in Equation 2 -0.5 ", represents the contribution of vehicle speed v to the change of water content;

[0132] Partial derivatives It is the key element of A, which is used to describe the effects of control variables such as vehicle speed v, fan flow F, heat source power Q, exhaust opening E on fabric moisture content H. pred Dynamic effects; for example: when the vehicle speed v increases, The absolute value of v ﹣1.5 Decreasing function), indicating that the influence of vehicle speed on moisture content becomes weaker at high speeds, and the algorithm will automatically adjust the control strategy to avoid over-adjustment.

[0133] is the first-order partial derivative of the speed term in Equation 2 with respect to the vehicle speed v, that is: The two are the mathematical relationship between the original function and its derivative;

[0134] In formula 2, α·ΔT·v -0.5 It shows that the faster the speed v, the shorter the fabric stays in the drying room, the less water evaporation, and the smaller the decrease in moisture content. -0.5 Quantify the nonlinear effect of vehicle speed on moisture content: vehicle speed is negatively correlated with moisture content, but the degree of influence decreases with increasing vehicle speed;

[0135] The speed term describes the nonlinear effect of vehicle speed on the change in moisture content, and the partial derivative quantifies the instantaneous rate of this effect. The two together constitute the core of "model prediction" and "optimization solution" in the MPC model. This deep coupling of mathematics and physics enables the system to dynamically adapt to complex working conditions and realize the closed-loop control of "model prediction-optimization solution-execution adjustment". This is the key technical advantage of this invention that distinguishes it from traditional single-variable control (such as controlling only temperature).

[0136] SQP solving includes: setting the upper limit of the number of iterations to 100; or setting the convergence threshold to 1e-4 or 1e-5;

[0137] Output optimal control increment Δu=[ΔM,ΔF,ΔQ,ΔE] T ;

[0138] The optimized control increment is passed to the actuator to achieve real-time control; this is a direct application of the MPC algorithm output, directly corresponding to the optimization solution part of the MPC algorithm; according to H pred (k), W H and W u , construct the objective function of formula (3); and use nonlinear optimization algorithms (such as SQP, IPOPT, etc.) to solve the objective function and obtain the optimal control input change Δu so that the objective function reaches the minimum value.

[0139] During the solution process, W H and W uIt will affect the weights of the error term and the control input change term, thereby balancing the system's requirements for error control and control input change; the optimized control increment is transmitted to the actuator to achieve real-time control.

[0140] It also includes: building online correction of model parameters, iterating the control parameter coefficients of the prediction equation, and realizing closed-loop feedback;

[0141] θ(k'+1)=θ(k')+μ·J －1 (θ(k'))*(H(k')-H pred (k')) (5)

[0142] Wherein, μ is the adaptive learning rate, μ = 0.02 to 0.1. When the error increases suddenly, μ is increased (e.g., 0.1) to accelerate convergence, and when the error stabilizes, μ is reduced (e.g., 0.02) to avoid overshoot. J-1 is the inverse of the second Jacobian matrix, which is used to quantify the influence of each control parameter coefficient on the moisture content. For example, when the temperature increases by 1°C, the contribution of α accounts for 60%, guiding parameter adjustment to focus on key factors. k’ is the control parameter coefficient vector at the k'th iteration, and the control parameter coefficients include: α, β, and γ.

[0143] The A matrix in Equation 4 serves to optimize the control variables and describes the dynamic relationship of "control action → moisture content change". The dimension of A is 1x4. The input variables are vehicle speed, fan, heat source, and exhaust. The output is H. pred The partial derivatives of vehicle speed, fan, heat source, and exhaust variables are used to solve the rolling optimization of the MPC model, that is, to calculate the optimal control increment Δu.

[0144] In Equation 5, J is the Jacobian matrix of model parameter correction, with a dimension of 1x3. It represents the rate of influence of model parameters α, β, and γ on the output variable (i.e., the predicted moisture content). J focuses on the "influence of model parameters on the prediction results," A is used in the "optimization layer" of the MPC model, and J is used in the "correction layer" of the MPC model.

[0145] The present invention utilizes H(k) and H pred The error signal of (k) is combined with the dynamic control parameter coefficients μ and J to improve the prediction accuracy.

[0146] The present invention uses X(k) to predict the fabric moisture content H of formula 2 pred , H pred With H set Substitute into Equation 3 and use Equation 4 to solve. During the solution process, it is necessary to consider the vehicle speed mutation limit Δv, the exhaust valve step limit ΔE, and the temperature safety boundary T max The constraints are solved by the sequential quadratic programming (SQP) algorithm to obtain the optimal control increment Δu = [ΔM, ΔF, ΔQ, ΔE]T , the actuator is controlled by Δu; and the model parameters of Formula 5 are corrected online. The result of Formula 5 is given to Formula 2, and the α, β, and γ of the prediction model of Formula 2 are updated to make the model more suitable for the actual drying process and improve the prediction accuracy;

[0147] Then enter the next control cycle and repeat the above process.

[0148] Online correction of model parameters plays a vital role in the practical application of the MPC model. During the fabric shaping and dyeing and finishing process, the prediction accuracy of the model may be affected by factors such as environmental humidity fluctuations, fabric structure, and type differences. Therefore, the present invention constructs an online correction mechanism for model parameters to adjust the model parameters through real-time feedback to improve control accuracy and stability.

[0149] Also included: Coordinated adjustment of actuators, including incremental limiting output and interlocking protection mechanism;

[0150] Among them, the incremental limit output includes:

[0151] Vehicle speed increment ΔM: ±2m / min, dead zone ±0.5m / min;

[0152] Circulating fan flow increment ΔF: ±3Hz, dead zone ±1Hz;

[0153] Heat source power increment ΔQ: ±5%, dead zone ±2%;

[0154] Exhaust opening increment ΔE: ±6%, dead zone ±3%;

[0155] Interlock protection mechanism:

[0156] When the vehicle speed v is less than 5m / min, the heat source power Q automatically drops to a safe level (≤20%);

[0157] If ΔP i,i+1 >50Pa, give priority to adjusting the exhaust valve opening E and limiting the change rate of the circulating fan flow F.

[0158] This step is to apply the optimal control input change Δu obtained by solving Formula 4 to the actual actuator; in the MPC model of the present invention, usually only the first control input change Δu within the control time domain Nc is executed, and the subsequent control inputs will be recalculated in the next rolling optimization, that is, the control time domain Nc = 5, and the control increments Δu(k) (k = 0 to 4) for the next 5 moments are calculated each time, but only Δu(0) is executed; Δu is recalculated in the next sampling period (after 5 seconds) to achieve dynamic update.

[0159] At the same time, the operation of limiting and interlocking protection on the control input is to ensure the rationality of the control input and the safety of the system, which is also consistent with the constraint of the control input change in the minimum objective function. In response, avoid excessive changes in the control input; the optimal control input change is to minimize the value of the objective function.

[0160] Also included: temperature gradient anomaly detection;

[0161] Temperature gradient anomaly detection includes: monitoring of oven temperature gradient and fault diagnosis and response;

[0162] Monitoring the temperature gradient of the drying room includes: calculating the difference ΔT between adjacent temperature sensors i,i+1 =T i -T i+1 , if ΔT i,i+1 >10℃ for 10 seconds, triggering the air duct blockage warning.

[0163] Fault diagnosis and response include: After the warning, the system automatically performs the following operations:

[0164] 1. Increase the fan speed to 80% of the maximum allowable value;

[0165] 2. Gradually increase the opening of the exhaust valve by 10% each time;

[0166] 3. If it is not restored within 30 seconds, production will be suspended and a maintenance inspection will be prompted;

[0167] 4. Record fault logs to the cloud server.

[0168] Temperature gradient anomaly detection belongs to the feedback correction loop, that is, it detects whether the system has an abnormal situation. When an abnormality is detected, the control strategy will be adjusted, which is equivalent to feedback correction of the MPC prediction model, making subsequent predictions and optimization calculations more accurate, thereby ensuring that the system can continue to move towards the target H stably. set run.

[0169] Record fault logs to the cloud server to provide data support for subsequent system optimization and MPC model improvement; this is of great significance for the continuous optimization and upgrading of the MPC model.

[0170] like Figure 2 The system of the moisture content control method of the cloth falling from the setting machine based on MPC includes: an actuator, a controller, a humidity sensor, a temperature sensor, and a moisture content sensor; the actuator is electrically connected to the controller, and the humidity sensor, temperature sensor, and moisture content sensor are electrically connected to the controller;

[0171] in,

[0172] The humidity sensor is used to collect the humidity value in each drying room;

[0173] The temperature sensor is used to collect the temperature value in each drying room;

[0174] The moisture content sensor is used to detect the moisture content of the fabric at the drop point;

[0175] The controller uses the collected humidity value, temperature value, moisture content and the trained MPC model to control the action of the actuator to adjust the moisture content.

[0176] The controller can be a single chip microcomputer or an MCU controller; a new electric controller CTR can also be used. The electric controller CTR is electrically connected to the inherent setting machine electric control device. The CTR is an industrial control computer (IPC) or a direct digital controller (DDC).

[0177] It also includes: an air pressure sensor, which is electrically connected to the controller and is used to detect the air pressure value in the drying room;

[0178] Also included: a cloud server, which is used for online training of the MPC model;

[0179] Cloud server types include but are not limited to single servers, server clusters, cloud servers, and cloud server clusters. Server configurations must meet the following requirements:

[0180] CPU8 cores, memory 32GB, storage space 1TB;

[0181] High-speed Internet connection bandwidth 1Gbpsbps;

[0182] Security measures include firewall configuration, data encryption transmission, regular backup, etc.

[0183] It also supports basic cloud computing services such as network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDNs), as well as big data and artificial intelligence platforms.

[0184] The cloud server is responsible for data processing, storage and analysis, and also undertakes the deployment and optimization of the MPC model; it accesses the MPC control system in real time through the cloud server; it conducts deep learning and intelligent analysis of multi-source sensor data, and makes predictive maintenance, dynamic scheduling and adaptive control, thereby accurately adjusting parameters such as vehicle speed, fan speed, heat source power and exhaust opening, realizing intelligent control of fabric moisture content, and significantly improving control accuracy and production efficiency.

[0185] Experimental results:

[0186] Table 1: Product weight increase

[0187]

[0188] Table 2: Enhanced Enterprise Competitiveness

[0189] index Traditional methods Method of the present invention Economic benefits Equipment maintenance costs Annual maintenance cost is about RMB 80,000 (single unit) Annual maintenance cost is about 60,000 yuan 25% reduction Response speed Control cycle 100ms Control cycle ≤50ms 50% increase Production change time (cotton → chemical fiber) 8-10 minutes 3 minutes 62% increase High-end product development cycle 40-60 days 24-36 days 40% shorter Customer order fulfillment rate 85％ 95％ 12% increase

[0190] Table 3: Contribution of green production

[0191]

[0192]

[0193] Table 4: Comparison of key technical parameters

[0194]

[0195] A dyeing and finishing enterprise has achieved remarkable results in rapid production by adopting the method of the present invention;

[0196] Taking cotton fabrics as an example, data shows that after implementing this system, the variation in moisture content in the transverse direction of the fabric has been reduced from ±3% to within ±1%. Each batch of production, which previously took approximately eight hours, can now be completed in just six hours. This increase in production efficiency is attributed to the system's precise control of fabric moisture content and intelligent optimization of the production process. Furthermore, the improved product quality and shortened delivery times have earned the company increased customer trust and orders.

[0197] After implementing this system, precise control of fabric moisture content has been achieved, reducing downtime due to substandard moisture content and improving the continuity and stability of the production line. Data shows that the overall equipment effectiveness (OEE) has increased from 75% to over 85%, bringing significant economic benefits to the company.

[0198] The present invention significantly improves product quality. First, the physical properties are stable, and precise moisture content control ensures that the moisture regain of the fabric meets the process requirements (such as 8% to 10% for cotton and 4% to 6% for chemical fibers), avoiding fiber brittleness caused by over-drying or mildew caused by under-drying.

[0199] The synergistic effect of humidity gradient constraint and air pressure control improves the fabric width stability by 30% and controls the weight deviation within ±1.5g / m 2 within;

[0200] Multivariable model prediction and dynamic optimization create differentiated advantages, suitable for the production of high-end fabrics (such as functional home textiles and sportswear), meeting customers' stringent requirements for moisture content of ±0.5%;

[0201] Optimized appearance quality: Dynamically adjust vehicle speed and heat source power to reduce color fringing and color fastness degradation caused by temperature fluctuations. For example, in dyed polyester fabrics, the color difference value is reduced from 1.2 to below 0.8. The air duct blockage warning mechanism (ΔTi,i+1>10℃ for 10 seconds) can avoid local high-temperature damage and reduce the defective fabric rate by 0.5% to 1%.

[0202] This invention effectively improves production efficiency and controls production costs. It optimizes equipment operation, implements actuator output limiting (e.g., vehicle speed ΔM ± 2 m / min, fan ΔF ± 3 Hz), and implements interlock protection (heat source reduced to 20% at low speeds), extending equipment life by over 20% and reducing maintenance costs. The SQP algorithm solves within 50 ms, improving response speed by 50%, enabling rapid production changeovers (e.g., switching from cotton to chemical fiber takes only 3 minutes).

[0203] Improved energy efficiency: Coordinated regulation of heat sources and fans based on model predictions saves 15% to 25% energy compared to traditional PID control. For example, when processing 5,000 meters of fabric per day, the annual energy savings are approximately 120,000 kWh.

[0204] The present invention is highly intelligent and adaptable, self-adapting to process parameters, dynamically adjusting prediction model parameters (such as α = 0.025 ~ 0.035, β = 0.10 ~ 0.15), and automatically adapting to different gram weights (50 ~ 500g / m 2 ), fabrics with a width of 1.5 to 3.2 m, reducing manual intervention;

[0205] The cloud server supports deep learning of historical data, optimizes the process formula library, and shortens the new product development cycle by 40%.

[0206] Fault warning and diagnosis, abnormal temperature gradient detection and exhaust valve linkage adjustment can respond to air duct blockage within 30 seconds, avoiding downtime losses caused by equipment failure (for example, the downtime loss of a single device is about 2,000 yuan per hour).

[0207] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A method for controlling the moisture content of falling cloth in a setting machine based on MPC, characterized in that: The following steps are involved: Step 1: Collect control parameters; Step 2: Construct an MPC model. The MPC model includes: taking the measured and preset moisture content and the first control parameter state vector as input, and outputting the predicted moisture content; minimizing the difference between the predicted moisture content and the preset moisture content as the goal; solving and optimizing the control increment using the optimization matrix and sequential quadratic programming; and using the optimal control increment to regulate the action of the actuator.

2. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 1 is characterized in that: Step 2 specifically includes: Preset prediction time domain N p , control time domain N c 、W H and W u ; Construct the prediction equation: Among them, H pred (k+1) is the moisture content prediction value at the k+1th moment; H(k) is the measured moisture content of the fabric at the drop point at the kth moment; α is the temperature influence coefficient; β is the humidity self-regulation coefficient; γ is the hot air ratio coefficient; ΔT is the difference in the average temperature of the drying room at adjacent moments; ε is the adjustable coefficient; v is the vehicle speed; Q / F is the ratio of heat source power to circulation fan flow rate; Construct the minimization objective function: Among them, W H is the weight of weighing error; W u Weigh the smoothness weight of the control increment; Δu is the control increment; Construct the optimization matrix and use the SQP algorithm to solve Δu.

3. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 2 is characterized in that: The optimization matrix formula is: Where A is the first Jacobian matrix, b H 、b u is the error term and the control increment term vector, and ΔX represents the increment of the state vector X(k).

4. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 2 is characterized in that: The optimization of the control increment adopts the online correction of model parameters, and the formula is: θ(k'+1)=θ(k')+μ·J －1 (θ(k'))*(H(k')-H pred (k')); where μ is the adaptive learning rate, θ k’ is the control parameter coefficient vector at the k'th iteration, J-1 is the inverse of the second Jacobian matrix, H(k') is the measured value of the fabric moisture content at the drop point at the k'th iteration, H pred (k') The predicted value of moisture content at the k'+1th iteration.

5. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 2 or 3, characterized in that: The humidity gradient between adjacent drying rooms is used to constrain the control increment.

6. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 2 or 3, characterized in that: The control increment is constrained by the air pressure difference between adjacent drying rooms.

7. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 2, characterized in that: The control increments include: the change in the speed of the vehicle motor, the change in the flow rate of the circulating fan at adjacent moments, the change in the power of the heat source at adjacent moments, and the change in the exhaust at adjacent moments.

8. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 1 is characterized in that: The control parameters include: temperature, humidity, moisture content, air pressure difference, vehicle speed, exhaust volume, and ratio of heat source power to circulation fan flow.

9. The method for controlling the moisture content of the cloth dropped from the setting machine based on MPC according to claim 1, characterized in that: The first control parameters include: average humidity in the drying room, average temperature in the drying room, vehicle speed, and ratio of heat source power to circulation fan flow rate.

10. A system using the method for controlling moisture content of falling cloth of a setting machine based on MPC according to any one of claims 1 to 9, characterized in that: include: Actuators, controllers, humidity sensors, temperature sensors and moisture content sensors; in, The humidity sensor is used to collect the humidity value in each drying room; The temperature sensor is used to collect the temperature value in each drying room; The moisture content sensor is used to detect the moisture content of the fabric at the drop point; The controller uses the collected humidity value, temperature value, moisture content and the trained MPC model to control the action of the actuator to achieve moisture content regulation.

Images