Lithium chloride solution dehumidification system based on intelligent feedback control and self-adaptive fuzzy control and control method thereof

Abstract

The invention relates to the technical field of environment control, in particular to a lithium chloride solution dehumidification system based on intelligent feedback control and self-adaptive fuzzy control and a control method thereof, which realize high-precision, high-response-speed and low-energy-consumption environment temperature and humidity control by optimizing a dehumidification process, an intelligent control algorithm and a dynamic parameter adjusting mechanism. The dehumidification efficiency, the response speed and the control precision of the system are remarkably improved, and the system has remarkable advantages in the aspects of energy conservation, consumption reduction and system stability.

Description

Technical Field

[0001] The invention relates to the technical field of environmental control, in particular to a lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control and a control method thereof. Background Art

[0002] In industrial production, the temperature and humidity control of the workshop environment has an important impact on product quality, especially in the fields of medicinal capsules, food drying and electronic product manufacturing, where high-precision control of humidity is particularly critical. For example, in the production process of hollow capsules, the humidity stability of the drying process is directly related to the uniformity, strength and qualified rate of the capsules. However, the existing dehumidification technology has the following shortcomings and is difficult to meet the high standards required in the above fields: Limitations of traditional surface cooling dehumidification systems: Surface cooling dehumidification systems use cooled air to reduce humidity, but their minimum humidity is usually limited by the dew point of the air, making it difficult to achieve a moisture content below 5g / kg.

[0003] In high humidity environments or scenarios with low humidity requirements, the surface cooling system shows obvious inefficiency and is difficult to meet industrial needs such as capsule production that have strict requirements on humidity accuracy.

[0004] High energy consumption problem of rotary dehumidification system: Rotary dehumidification systems are able to achieve lower humidity levels, but are usually associated with high energy consumption as their operating principle relies on a continuous regeneration cycle.

[0005] Especially in industrial scenarios where a large dehumidification capacity (such as more than 1kg / m²·h) is required, the energy consumption of the rotary dehumidification system is huge and the equipment operating cost is high.

[0006] Deficiencies of existing control technology: Traditional temperature and humidity control technologies mostly use simple PID control or fixed parameter adjustment methods, which makes it difficult to respond to rapid changes in environmental conditions in real time.

[0007] The lack of dynamic feedback and intelligent adjustment mechanism results in limited humidity control accuracy, and the system is prone to performance degradation due to parameter drift or environmental interference.

[0008] In addition, the existing technology generally lacks a solution that can combine efficient dehumidification with intelligent control, making it difficult to take into account the high precision, rapid response and low energy consumption requirements of the dehumidification system. Summary of the invention

[0009] The present invention aims to solve the problems of low dehumidification efficiency, high energy consumption and insufficient control accuracy of existing dehumidification technologies in industrial scenarios, and provides a lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control and its control method. The invention achieves high-precision, high-response speed and low-energy consumption environmental temperature and humidity control by optimizing the dehumidification process, intelligent control algorithm and dynamic parameter adjustment mechanism.

[0010] The lithium chloride solution dehumidification system of the present invention comprises a spray box, a regeneration box, a heat exchanger and supporting pipelines. The system is equipped with an intelligent feedback control module to monitor the system operation status in real time, calculate the system error through key parameters collected by temperature and humidity sensors, solution concentration sensors and liquid level sensors (t)-y(t), and adjust the control target value (t)- e(t); The system is equipped with an adaptive fuzzy control module, which uses fuzzy logic reasoning to (t)-y(t) and deviation change rate Dynamically adjust the output control amount , used to optimize the spray liquid flow rate, concentration and temperature of the spray box, as well as the solution circulation rate and heat exchanger power of the regeneration box; The intelligent feedback control module works in conjunction with the adaptive fuzzy control module to learn the formula through feedback. Optimizing feedback gain , and dynamically adjust the fuzzy control rule base to improve the stability and efficiency of system operation.

[0011] Preferably: the adaptive fuzzy control module uses a triangular membership function to adjust the input variables and Fuzzy processing is performed, and its membership function is: ; Among them, a, b, c are the parameter ranges of the membership function, which are used to define the fuzzy set.

[0012] Preferably: the fuzzy inference process adopts the maximum-minimum inference method, and its output control quantity The fuzzy membership of is: , The actual output value is solved by weighted average method: .

[0013] Preferably: the intelligent feedback control module updates the target value in real time (t) Works with the fuzzy control module to optimize the following key operating parameters: Flow rate, concentration and spray angle of the spray liquid; The solution circulation rate and temperature of the regeneration tank; Power distribution of heat exchangers.

[0014] Preferably: the feedback control module combines historical operation data and optimizes the feedback gain by gradient descent method , and its optimization formula is: , in, is the learning rate, is the cost function of the system operation.

[0015] The control method of the lithium chloride solution dehumidification system of the present invention is characterized by comprising the following steps: A. Data Collection: Through temperature and humidity sensors, solution concentration sensors and liquid level sensors, the operating data of environmental temperature and humidity, solution concentration and liquid level are collected in real time; The collected data is input into the intelligent feedback control module and the adaptive fuzzy control module.

[0016] B. Error calculation: The intelligent feedback control module calculates the system error: (t)-y(t), where is the error, (t) is the set target value, and y(t) is the actual output value of the system.

[0017] C. Feedback control target adjustment: According to the calculated error , dynamically adjust the fuzzy control target value through the feedback formula: (t)- e(t), where is the feedback gain, is the adjusted target value.

[0018] D. Fuzzy processing: The adaptive fuzzy control module calculates the deviation between the adjusted target value and the actual output value. (t)-y(t) and rate of change ; Will and Transformed into a fuzzy set, its membership is calculated by the membership function: ; Among them, a, b, ca, b, c are the ranges of fuzzy sets.

[0019] E. Fuzzy reasoning: Based on the fuzzy rule base, maximum-minimum fuzzy reasoning is performed: , in, and is the membership degree of the input variable in the fuzzy set.

[0020] F. De-modeling and output: The fuzzy inference results are decoded into actual control outputs by weighted average method: , in, To control the amount, Its corresponding membership degree.

[0021] G. Parameter adjustment: According to the control output , dynamically adjust the following operating parameters: Solution flow rate, concentration and temperature of the spray box; The regeneration tank cycle rate and heat exchanger power; Air velocity of the ambient supply fan.

[0022] H. Feedback Optimization: The intelligent feedback module records system operation data and optimizes feedback gain through cost function : , and update the feedback gain by gradient descent: ,in, is the learning rate, is the energy consumption penalty coefficient.

[0023] Technical Effects The present invention significantly improves the dehumidification efficiency, response speed and control accuracy of the system by combining the lithium chloride solution dehumidification system with intelligent feedback control and adaptive fuzzy control, and shows significant advantages in energy saving and consumption reduction and system stability. The specific technical effects are as follows: 1. High-precision control The system uses an intelligent feedback control algorithm to monitor and adjust environmental parameters in real time, and combines an adaptive fuzzy control algorithm to dynamically optimize the operating status of the spray box and regeneration box, improving the humidity control accuracy to within ±0.1%.

[0024] Regardless of how the external humidity fluctuates, the system can quickly adjust the air humidity to the target range, meeting the needs of industrial scenarios such as medicinal capsules and food drying for high-precision humidity control.

[0025] 2. Rapid response capability Through adaptive fuzzy control algorithm, the system can complete dynamic adjustment of ambient humidity within 1 second, effectively responding to rapid changes in humidity or fluctuations in production load.

[0026] In scenarios where the ambient humidity changes dramatically, the system response time is shortened by more than 40% compared to traditional control methods, thus avoiding the impact of humidity fluctuations on product quality.

[0027] 3. Energy-saving and high efficiency The system uses intelligent feedback control to optimize the distribution of solution flow rate, concentration and heat exchanger power, significantly reducing energy consumption: Compared with the rotary dehumidification system, the overall energy consumption is reduced by about 30%.

[0028] The heat and moisture exchange efficiency is increased by 20%, further reducing energy loss during solution regeneration.

[0029] The system reduces the waste of lithium chloride solution and improves material utilization through efficient solution circulation design.

[0030] 4. Long-term operation stability The intelligent feedback control module combined with the self-learning mechanism can dynamically optimize the control parameters KfK_f according to historical operation data to improve the long-term stability and reliability of the system: The service life of key system components (such as spray pumps and heat exchangers) is extended by more than 20%.

[0031] The frequency of equipment maintenance has been reduced to half of that of the original system, significantly saving operating costs.

[0032] 5. Environmental adaptability The system can operate stably in complex environments such as high humidity and high temperature, and can adapt to changes in different seasons or production conditions.

[0033] By dynamically adjusting the operating parameters of the spray box and the regeneration box, it can be widely used in various fields such as medicinal capsules, food drying and electronic manufacturing.

[0034] 6. Improve product quality The system's high-precision humidity control and rapid response capabilities effectively avoid product quality problems caused by humidity fluctuations and improve the consistency and pass rate of finished products: In capsule production, the product qualification rate increased by more than 15%, significantly reducing the defective rate.

[0035] Advantages compared to existing technologies Compared with the surface cooling dehumidification system: The present invention can achieve lower humidity control (below 5g / kg), while the surface cooling dehumidification system is limited by the air dew point and cannot meet this requirement.

[0036] The surface cooling system is difficult to cope with the rapidly changing humidity. The present invention responds quickly through the intelligent control algorithm and avoids the lag effect.

[0037] Compared with the rotary dehumidification system: Under the premise of achieving the same humidity control effect, the present invention significantly reduces energy consumption and is suitable for large-scale industrial production.

[0038] The rotary wheel system is expensive due to its complex structure and high energy consumption in the regeneration process in scenarios with low humidity requirements and large dehumidification capacity. The present invention significantly improves the economy by optimizing the solution circulation.

[0039] Through the above technical effects, the present invention provides an efficient, stable and economical solution in the field of industrial temperature and humidity control, and provides technical support for the production efficiency and product quality of related industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a step diagram of the operating method of the present invention. DETAILED DESCRIPTION

[0041] Embodiment 1: This embodiment is a lithium chloride solution dehumidification system, including a spray box, a regeneration box, a heat exchanger and its supporting pipelines. The system is equipped with an intelligent feedback control module to monitor the system operation status in real time, calculate the system error through key parameters collected by temperature and humidity sensors, solution concentration sensors and liquid level sensors (t)-y(t), and adjust the control target value (t)- e(t); The system is equipped with an adaptive fuzzy control module, which uses fuzzy logic reasoning to (t)-y(t) and deviation change rate Dynamically adjust the output control amount , used to optimize the spray liquid flow rate, concentration and temperature of the spray box, as well as the solution circulation rate and heat exchanger power of the regeneration box; The intelligent feedback control module works in conjunction with the adaptive fuzzy control module to learn the formula through feedback. Optimizing feedback gain , and dynamically adjust the fuzzy control rule base to improve the stability and efficiency of system operation.

[0042] Embodiment 2: The difference between this embodiment and embodiment 1 is that this embodiment further includes: The adaptive fuzzy control module uses a triangular membership function to adjust the input variables and Fuzzy processing is performed, and its membership function is: ; Among them, a, b, c are the parameter ranges of the membership function, which are used to define the fuzzy set.

[0043] Preferably: the fuzzy inference process adopts the maximum-minimum inference method, and its output control quantity The fuzzy membership of is: , The actual output value is solved by weighted average method: .

[0044] Preferably: the intelligent feedback control module updates the target value in real time (t) Works with the fuzzy control module to optimize the following key operating parameters: Flow rate, concentration and spray angle of the spray liquid; The solution circulation rate and temperature of the regeneration tank; Power distribution of heat exchangers.

[0045] Preferably: the feedback control module combines historical operation data and optimizes the feedback gain by gradient descent method , and its optimization formula is: , in, is the learning rate, is the cost function of the system operation.

[0046] Embodiment 3: The control method of the lithium chloride solution dehumidification system is characterized by comprising the following steps: A. Data Collection: Through temperature and humidity sensors, solution concentration sensors and liquid level sensors, the operating data of environmental temperature and humidity, solution concentration and liquid level are collected in real time; The collected data is input into the intelligent feedback control module and the adaptive fuzzy control module.

[0047] B. Error calculation: The intelligent feedback control module calculates the system error: (t)-y(t), where is the error, (t) is the set target value, and y(t) is the actual output value of the system.

[0048] C. Feedback control target adjustment: According to the calculated error , dynamically adjust the fuzzy control target value through the feedback formula: (t)- e(t), where is the feedback gain, is the adjusted target value.

[0049] D. Fuzzy processing: The adaptive fuzzy control module calculates the deviation between the adjusted target value and the actual output value. (t)-y(t) and rate of change ; Will and Transformed into a fuzzy set, its membership is calculated by the membership function: , Among them, a, b, ca, b, c are the ranges of fuzzy sets.

[0050] E. Fuzzy reasoning: Based on the fuzzy rule base, maximum-minimum fuzzy reasoning is performed: , in, and is the membership degree of the input variable in the fuzzy set.

[0051] F. De-modeling and output: The fuzzy inference results are decoded into actual control outputs by weighted average method: , in, To control the amount, Its corresponding membership degree.

[0052] G. Parameter adjustment: According to the control output , dynamically adjust the following operating parameters: Solution flow rate, concentration and temperature of the spray box; The regeneration tank cycle rate and heat exchanger power; Air velocity of the ambient supply fan.

[0053] H. Feedback Optimization: The intelligent feedback module records system operation data and optimizes feedback gain through cost function , and update the feedback gain by gradient descent: , in, is the learning rate, is the energy consumption penalty coefficient.

[0054] The details are as follows: Practical application of humidity control in pharmaceutical capsule workshop

[0055] Experimental objectives

[0056] The humidity in the workshop was adjusted from the initial value of 10.5 g / kg to the target value of 5.0 g / kg, and maintained stable under humidity fluctuations (±1.0 g / kg), with a humidity fluctuation control accuracy of ±0.1 g / kg.

[0057] Specific steps A. Data Collection

[0058] Sensor Configuration: Temperature and humidity sensors are arranged at the air inlet and outlet of the workshop to monitor the air humidity in real time.

[0059] Solution concentration sensors are installed in the spray tank and regeneration tank to monitor the solution concentration in real time (the initial value is 40%).

[0060] The liquid level sensor monitors the liquid level of the solution in the spray tank (the initial liquid level is 75%).

[0061] Data collection results: Initial value of ambient humidity: y(t)=10.5 g / kg.

[0062] Initial solution concentration: C=40%.

[0063] Initial liquid level value: H=75%.

[0064] B. Error calculation The intelligent feedback control module calculates the humidity error: (t)-y(t)=5.0−10.5=−5.5 g / kg.

[0065] in: (t) = 5.0 g / kg is the set target value.

[0066] y(t)=10.5 g / kg is the actual humidity value.

[0067] C. Feedback control target adjustment based on error , dynamically adjust the fuzzy control target value through the feedback formula: (t)- e(t), in: Initial feedback gain =0.5.

[0068] Calculated =5.0−(0.5⋅−5.5)=7.75 g / kg.

[0069] The adjusted target humidity value is 7.75 g / kg and is input into the adaptive fuzzy control module.

[0070] D. Fuzzy processing

[0071] Calculate the deviation and rate of change: deviation (t)-y(t)=7.75−10.5=−2.75 g / kg.

[0072] Rate of change =−1.0 g / kg / s.

[0073] Convert to fuzzy set: Bias Membership function:

[0074] Calculation results: =0.625.

[0075] Rate of change Membership function:

[0076] Calculation results: =0.5.

[0077] E. Fuzzy reasoning performs maximum-minimum reasoning based on the fuzzy rule base and input membership values: .

[0078] Calculation results: · =min(0.625,0.5)=0.5.

[0079] F. De-modeling and output De-modeling is done by weighted average method to calculate the output control quantity : .

[0080] Assume that the rule base corresponds to the output value: =10 L / min, =15 L / min.

[0081] =0.5, =0.5.

[0082] Calculation results: 12.5L / min.

[0083] G. Parameter adjustment according to control output =12.5 L / min, dynamically adjust the operating parameters: The solution flow rate in the spray box was set at 12.5 L / min.

[0084] The solution concentration was maintained at 40%.

[0085] The power of the regeneration box heat exchanger is adjusted to 3.5 kW.

[0086] H. Feedback Optimization The intelligent feedback module records system operation data and optimizes feedback gain through the cost function: .

[0087] Update the feedback gain by gradient descent: .

[0088] Adjusted feedback gain =0.51, further optimizing the control accuracy.

[0089] Experimental Results Humidity adjustment effect: The humidity was reduced from 10.5 g / kg to the target value of 5.0 g / kg, and the fluctuation range was controlled within ±0.05 g / kg.

[0090] When humidity fluctuates rapidly, the system responds in 0.8 seconds.

[0091] Energy consumption performance: The total energy consumption of the system is reduced by 30% compared with traditional methods.

[0092] Long-term stability: After the equipment ran for 24 hours, there was no abnormality in the performance of key components.

[0093] This embodiment demonstrates how the system of the present invention can dynamically adjust operating parameters, quickly respond to humidity fluctuations and maintain high-precision control.

Claims

1. A lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control, comprising a spray box, a regeneration box, a heat exchanger and its supporting pipelines, characterized in that: The system is equipped with an intelligent feedback control module to monitor the system operation status in real time, calculate the system error through key parameters collected by temperature and humidity sensors, solution concentration sensors and liquid level sensors , and by adjusting the control target value ; The system is equipped with an adaptive fuzzy control module, which uses fuzzy logic reasoning to (t)-y(t) and deviation change rate Dynamically adjust the output control amount , used to optimize the spray liquid flow rate, concentration and temperature of the spray box, as well as the solution circulation rate and heat exchanger power of the regeneration box; The intelligent feedback control module works in conjunction with the adaptive fuzzy control module to learn the formula through feedback. Optimizing feedback gain , and dynamically adjust the fuzzy control rule base to improve the stability and efficiency of system operation.

2. The lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control according to claim 1, characterized in that: The adaptive fuzzy control module uses a triangular membership function to adjust the input variables and Fuzzy processing is performed, and its membership function is: ， Among them, a, b, c are the parameter ranges of the membership function, which are used to define the fuzzy set.

3. The lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control according to claim 1, characterized in that: The fuzzy inference process adopts the maximum-minimum inference method, and its output control quantity The fuzzy membership of is: , The actual output value is solved by weighted average method: 。 4. The lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control according to claim 1, characterized in that: The intelligent feedback control module updates the target value in real time (t) Works with the fuzzy control module to optimize the following key operating parameters: Flow rate, concentration and spray angle of the spray liquid; The solution circulation rate and temperature of the regeneration tank; Power distribution of heat exchangers.

5. The lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control according to claim 1, characterized in that: The feedback control module combines historical operation data to optimize the feedback gain through the gradient descent method. , and its optimization formula is: , in, is the learning rate, is the cost function of the system operation.

6. A control method for a lithium chloride solution dehumidification system based on intelligent feedback control and adaptive fuzzy control as claimed in claims 1-5, characterized in that: The following steps are involved: A. Data Collection: Through temperature and humidity sensors, solution concentration sensors and liquid level sensors, the operating data of environmental temperature and humidity, solution concentration and liquid level are collected in real time; Input the collected data into the intelligent feedback control module and the adaptive fuzzy control module; B. Error calculation: The intelligent feedback control module calculates the system error: , in, is the error, (t) is the set target value, y(t) is the actual output value of the system; C. Feedback control target adjustment: According to the calculated error , dynamically adjust the fuzzy control target value through the feedback formula: (t)- e(t), where is the feedback gain, is the adjusted target value; D. Fuzzy processing: The adaptive fuzzy control module calculates the deviation between the adjusted target value and the actual output value. (t)-y(t) and rate of change ; Will and Transformed into a fuzzy set, its membership is calculated by the membership function: , Among them, a, b, ca, b, c are the ranges of fuzzy sets; E. Fuzzy reasoning: Based on the fuzzy rule base, maximum-minimum fuzzy reasoning is performed: , in, and is the membership degree of the input variable in the fuzzy set; F. De-modeling and output: The fuzzy inference results are decoded into actual control outputs by weighted average method: , in, To control the amount, is its corresponding membership degree; G. Parameter adjustment: According to the control output , dynamically adjust the following operating parameters: Solution flow rate, concentration and temperature of the spray box; The regeneration tank cycle rate and heat exchanger power; The wind speed of the ambient fan; H. Feedback Optimization: The intelligent feedback module records system operation data and optimizes feedback gain through cost function : , and update the feedback gain by gradient descent: ,in, is the learning rate, is the energy consumption penalty coefficient.

Images