An intelligent perception and adaptive control system for Curcuma aromatica processing equipment

Abstract

The present invention discloses an intelligent perception and adaptive control system for Curcuma longifolia processing equipment, comprising: a data perception module for real-time monitoring of processing parameters based on a dynamic data acquisition model; eliminating data noise through data filtering and calibration formulas; a processing parameter optimization module for assessing processing quality based on a processing quality evaluation model; and optimizing parameters under constraints using optimization targets; a dynamic adaptive control module for generating control signals using a PID control algorithm; and a parameter adjustment module for updating processing parameters based on a dynamic processing parameter adjustment formula. The present invention has the following beneficial effects: achieving high-precision perception, real-time monitoring, and intelligent adjustment of the processing environment and processing parameters, thereby improving processing quality stability and production efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of Chinese medicinal material processing equipment, in particular to an intelligent perception and adaptive control system for Curcuma aromatica processing equipment. Background Art

[0002] With the rapid development of smart manufacturing and Industry 4.0, the traditional pharmaceutical industry, particularly in the field of Chinese herbal medicine processing, is undergoing profound technological changes. Curcuma wenyujin (Golden Curcuma) is a key TCM herbal medicine whose active ingredient content and quality stability directly impact its efficacy. However, its processing is extremely sensitive to environmental conditions and operating parameters. Even slight variations in raw material quality, ambient temperature, humidity, and pressure can lead to fluctuations in processing quality, impacting product efficacy and safety.

[0003] Currently, the level of intelligence in the field of Chinese medicinal material processing is relatively low, with numerous technical bottlenecks. According to the research paper "A Review of the Current Status of Research on Smart Factories and Their Core Technologies," data collection in modern smart factories primarily relies on sensors, intelligent machine tools, and robots, forming the foundational nodes for data collection in smart factories. However, existing Curcuma aromatica processing equipment has significant deficiencies in sensing capabilities, data analysis, and control algorithms, making it difficult to cope with the ever-changing processing environment and process requirements.

[0004] In actual production, existing Curcuma aromatica processing equipment faces the following core problems: First, insufficient data acquisition accuracy. Existing sensors find it difficult to accurately capture subtle changes in the processing process in a changing processing environment, resulting in large errors in the monitoring data; Second, the response speed is lagging. Faced with dynamically changing processing conditions, the existing system has a slow response speed and is unable to adjust processing parameters in a timely manner, resulting in fluctuations in processing quality; Third, the adaptive ability is insufficient. The existing system lacks an intelligent adaptive mechanism in data analysis, making it difficult to dynamically adjust processing parameters based on real-time data and unable to cope with changing processing conditions; Fourth, the processing quality is unstable. Due to the inability to accurately perceive and control processing parameters, it ultimately leads to large fluctuations in product quality, low yield rate, and high energy consumption.

[0005] In order to solve the above technical problems, it is urgently necessary to develop an intelligent sensing system with high precision and fast response, combined with an adaptive control algorithm, to achieve real-time monitoring and dynamic adjustment of the processing process of Curcuma aromatica, improve processing quality and efficiency, reduce energy consumption, and meet the needs of refined processing of modern Chinese medicinal materials. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent perception and adaptive control system for Curcuma aromatica processing equipment and a control method thereof, which realizes high-precision perception, real-time monitoring and intelligent adjustment of the processing environment and processing parameters, thereby improving the stability of processing quality and production efficiency.

[0007] To achieve the above objectives, the present invention provides an intelligent perception and adaptive control system for Curcuma aromatica processing equipment. The system includes a processor and memory, wherein the memory stores a computer program that, when executed by the processor, constructs and operates a data perception model, a processing parameter optimization model, and a dynamic adaptive control model. The system comprises four components: a data perception module, a processing parameter optimization module, a dynamic adaptive control module, and a parameter adjustment module. These four modules work together to form a complete closed-loop control system.

[0008] The data perception module is the information basis of the system and is responsible for collecting and processing the core parameter data in the processing process. This module is based on the data acquisition dynamic model X(t)=X base +ΔX(t) monitors the processing parameters in real time, where X(t) represents the data value at the current time t, which can be any processing parameter such as temperature, humidity, pressure, etc.; X base The sensor's baseline value reflects the parameter value under stable conditions. ΔX(t) represents the dynamic fluctuation value, calculated from the difference between the real-time sensor data and the baseline value. This model decomposes the collected data into steady-state and fluctuating values, enabling the system to distinguish long-term trends from short-term fluctuations, providing a precise basis for subsequent parameter adjustments.

[0009] In order to eliminate the influence of random noise on data quality, the data perception module adopts the moving average filtering method.

[0010] Filtering and calibration formulas Process the original data, where X filtered (t) represents the smoothed data value after filtering, and n represents the size of the filtering window. This filtering method averages the data from the past n time points, effectively eliminating random noise and improving data reliability. Furthermore, the system dynamically adjusts the filtering window size based on the characteristics of different parameters to achieve optimal filtering results.

[0011] The processing parameter optimization module is the core of the system. It assesses processing quality based on the processing quality evaluation model Q=f(T,H,P,M), where Q represents processing quality indicators such as raw material uniformity and yield rate; T represents processing temperature (unit: °C); H represents processing humidity (unit: %); P represents processing pressure (unit: Pa); M represents raw material mass (unit: kg); and f represents the nonlinear function between processing quality and processing parameters. This model describes the relationship between processing quality and various processing parameters through a multivariate nonlinear function, providing a foundation for parameter optimization.

[0012] In practical applications, the processing quality evaluation model can be further refined into a multivariate nonlinear polynomial form: Q=w1·T 2 +w2·H2 +w3·P 2 +w4·M+w5·T·H+w6·T·P+...+w m , where w1,w2,...,w m is the weight coefficient obtained by fitting experimental data, reflecting the influence of each parameter on processing quality and their interaction. The above form takes into account the interaction between multiple parameters such as temperature, humidity, pressure, and raw material quality, making the model more consistent with the actual processing process.

[0013] The goal of the machining parameter optimization module is to maximize the machining quality Q by adjusting the machining parameters T, H, P, and M while meeting the physical constraints of the machining equipment.

[0014] The above optimization objective can be expressed as: Q max =f(T,H,P,M), the constraints are

[0015] T min ≤T≤T max ,H min ≤H≤H max ,P min ≤P≤P max ,M min ≤M≤M max .

[0016] The system solves the above multivariable nonlinear constrained optimization problem by using gradient descent, genetic algorithm or other optimization algorithms available in the existing technology, while taking into account the smoothness of parameter adjustment and the system response speed, avoiding drastic fluctuations in parameters and ensuring stable operation of the system.

[0017] The dynamic adaptive control module is the execution center of the system, responsible for generating control signals and making dynamic adjustments. This module first applies the PID control algorithm Generate basic control signals,

[0018] where e(t)=Q target –Q represents the processing quality error, that is, the difference between the target quality and the current quality; K p , K i , K d These are the proportional, integral, and differential gain parameters, respectively. A PID controller consists of three components: the proportional term reflects the current error magnitude, the integral term accumulates historical errors, and the differential term predicts future error trends. Through the combined effect of these three components, a PID controller can quickly respond to error changes, eliminate static errors, and suppress overshoot and oscillation.

[0019] An important improvement of the present invention is the introduction of the adaptive adjustment rule P adjust =α·P control +β·Xfiltered (t), combining traditional PID control with real-time sensor data to achieve dynamic adjustment of the control signal. α and β are adjustment coefficients, satisfying α + β = 1 and 0 ≤ α, β ≤ 1. This improved rule enables the control system to simultaneously account for both quality errors and real-time environmental changes, improving the system's adaptability and response speed. When environmental conditions change rapidly, a larger β value enables the system to respond more quickly to environmental changes based on real-time data. When the environment is relatively stable, a larger α value allows the system to rely more on PID control to precisely adjust processing parameters.

[0020] The regulation coefficients α and β in the system are dynamically adjusted according to the degree of environmental fluctuation, satisfying the mathematical relationship: α=1 / (1+k·τ 2 ), β=1-α, where τ 2 represents the variance of environmental parameters, reflecting the degree of environmental fluctuation, and k represents the adjustment coefficient. When the environmental fluctuation is large (τ 2 increases), α decreases, β increases, and the system is more based on real-time data; when the environment is stable (τ 2 As α decreases, β decreases, and the system is more controlled by PID. The above dynamic balancing mechanism enables the system to maintain optimal control performance under different working conditions.

[0021] The parameter adjustment module is responsible for converting the control signal into a specific parameter adjustment value and dynamically adjusting the formula according to the processing parameters:

[0022] T(t+1)=T(t)+γ T ·P adjust ,H(t+1)=H(t)+γ H ·P adjust ,P(t+1)=P(t)+γ p ·P adjust Update the processing parameters, where γ T , γ H , γ p represents the adjustment step coefficient for each parameter. The above formula enables dynamic updating of machining parameters, enabling the system to continuously optimize machining parameters based on adaptive control signals. The adjustment step coefficient determines the magnitude of parameter adjustments. Larger step sizes result in faster system response but can cause oscillation, while smaller step sizes result in smoother adjustments but slower response.

[0023] The present invention also includes a PID parameter self-adjusting module, which dynamically adjusts the PID control parameters according to the size and change trend of the quality error: K p (t)=K p0 +ΔK p |e(t)|, K i (t)=K i0 / (1+γ·|e(t)|), K d(t)=K d0 +δ·|de(t) / dt|, where K p0 , K i0 , K d0 are the initial parameter values, ΔK p , γ, and δ are adjustment coefficients. This self-adjusting mechanism enables the system to dynamically adjust the PID parameters based on the size and rate of change of the temperature error. When the temperature error is large, the proportional coefficient is increased to speed up the response, while the integral coefficient is appropriately reduced to avoid integral saturation. When the temperature changes drastically, the differential coefficient is increased to improve system stability.

[0024] In order to achieve refined processing control, the system adopts a hierarchical parameter adjustment strategy, using different adjustment step coefficients for different processing parameters to satisfy the relationship: γ T =γ base ·k T |e(t)|^a T , γ H =γ base ·k H |e(t)|^a H , γ p =γ base ·k p |e(t)|^a p , where γ base is the basic adjustment step length, k T 、k H 、k p Adjust the weights for each parameter, a T 、a H 、a p is the nonlinear adjustment index of each parameter, usually satisfying a T >a H >a p The above-mentioned hierarchical adjustment strategy enables the system to strike a balance between response speed and stability, and avoids mutual interference of parameter adjustments.

[0025] In terms of energy optimization, the system also includes an energy consumption optimization module to minimize energy consumption while ensuring processing quality:

[0026] , where E represents the total energy consumption, w T 、w p 、w O Represent the energy consumption weights of temperature, pressure and other parameters respectively.

[0027] The present invention also provides an intelligent perception and adaptive control method for Curcuma aromatica processing equipment, which includes steps such as data acquisition and processing, quality assessment, parameter optimization, control signal generation and adjustment, parameter updating and execution control, forming a complete closed-loop control process.

[0028] Compared with the prior art, the present invention has the following advantages:

[0029] First, through an improved data perception model and moving average filtering method, high-precision data collection and processing in the environment are achieved. Compared with traditional sensor systems, data collection accuracy is improved and anti-interference capabilities are enhanced;

[0030] Second, a nonlinear processing quality evaluation model is used to accurately describe the relationship between processing parameters and processing quality, and the accuracy of processing quality evaluation is relatively high;

[0031] The third is the introduction of a dual adaptive control mechanism, which combines traditional PID control with real-time data perception, shortening the system response time, improving anti-interference ability, and enhancing control accuracy;

[0032] Fourthly, the hierarchical parameter adjustment strategy is applied to achieve refined processing control, improve the overall stability of the system, and maintain a good response speed.

[0033] In summary, the intelligent perception and adaptive control system for Curcuma aromatica processing equipment provided by the present invention effectively solves the problems of insufficient data acquisition accuracy, slow response speed and lack of adaptive ability in traditional Curcuma aromatica processing equipment through high-precision data acquisition, nonlinear quality evaluation, dual adaptive control and hierarchical parameter adjustment, realizes intelligent monitoring and optimized control of the processing process, and improves processing quality, production efficiency and energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a block diagram of the overall structure of the intelligent perception and adaptive control system of the Curcuma Radix processing equipment of the present invention;

[0035] Figure 2 This is a flow chart for implementing the data perception model of the present invention;

[0036] Figure 3 This is a flow chart for implementing the processing parameter optimization model of the present invention;

[0037] Figure 4 This is a flow chart for implementing the dynamic adaptive control model of the present invention;

[0038] Figure 5 This is a relationship diagram of the adaptive adjustment coefficients α and β of the present invention as they change with the degree of environmental fluctuation;

[0039] Figure 6This is a relationship diagram of the adjustment step coefficients of various parameters under the hierarchical parameter adjustment strategy of the present invention;

[0040] Figure 7 This is a flow chart of the intelligent perception and adaptive control method of Curcuma aromatica processing equipment of the present invention;

[0041] Figure 8 This is a comparison chart of processing quality in actual application of the system of the present invention;

[0042] Figure 9 This is a comparison chart of energy consumption of the system of the present invention in actual application. DETAILED DESCRIPTION

[0043] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the following embodiments are merely exemplary and are not intended to limit the scope of the present invention. Those skilled in the art may make various deformations and modifications based on the technical solutions of the present invention, and the above deformations and modifications all fall within the scope of protection of the present invention.

[0044] like Figure 1 As shown, the intelligent perception and adaptive control system for the processing equipment of Curcuma aromatica provided by the present invention includes a processor and a memory, wherein a computer program is stored in the memory. When the program is executed by the processor, the construction and operation of the data perception model, the processing parameter optimization model and the dynamic adaptive control model are realized. The system mainly consists of four parts: a data perception module 10, a processing parameter optimization module 20, a dynamic adaptive control module 30 and a parameter adjustment module 40. In addition, the system can also include a PID parameter self-adjustment module 50 and an energy consumption optimization module 60. The above modules work together to form a complete closed-loop control system, realizing real-time monitoring and optimized control of the Curcuma aromatica processing process.

[0045] The data perception module 10 is responsible for real-time collection and processing of core parameters in the processing process. Figure 2 As shown, the data perception module 10 includes a sensor network 11, a data acquisition unit 12, a data decomposition unit 13, and a data filtering unit 14. The sensor network 11 is composed of a variety of sensors distributed throughout the core locations of the processing equipment, including temperature sensors, humidity sensors, pressure sensors, and raw material quality sensors. The data acquisition unit 12 is responsible for acquiring raw data from the sensor network 11 and performing preliminary signal conditioning and digital conversion. The data decomposition unit 13 decomposes the sensor data into baseline values and fluctuation values based on a dynamic data acquisition model. The data filtering unit 14 applies a moving average filter to eliminate data noise.

[0046] The mathematical expression of the data acquisition dynamic model is: X(t)=X base +ΔX(t); where X(t) represents the current time t

[0047] Data value can be any processing parameter such as temperature, humidity, pressure, etc.; X base The sensor represents the baseline value, reflecting the parameter value under stable conditions; ΔX(t) represents the dynamic fluctuation value, calculated from the difference between the real-time sensor data and the baseline value. The significance of this model lies in decomposing the collected data into steady-state values and fluctuating values. The steady-state value reflects the basic conditions of the machining environment, while the fluctuating value reflects the short-term trend. This decomposition helps the system distinguish long-term trends from short-term fluctuations, providing a precise basis for subsequent parameter adjustments.

[0048] Taking processing temperature as an example, it can be expressed as T(t)=T base +ΔT(t), where T base is the reference temperature required by the process, typically determined by historical experience or process specifications, while ΔT(t) represents the temperature deviation due to environmental changes or equipment fluctuations. This decomposition allows the system to separately handle long-term adjustments to the reference temperature and real-time responses to short-term temperature fluctuations, improving control flexibility and precision.

[0049] The data filtering and calibration formula uses the moving average filtering method: ,in

[0050] X filtered (t) represents the smoothed data value after filtering, and n represents the size of the filter window. This formula aims to eliminate random noise interference by averaging the data over the past n time points, resulting in smoother and more reliable data. The choice of filter window size n is crucial for filtering effectiveness: a larger n improves noise elimination but increases system latency, while a smaller n preserves more dynamic information but includes more noise.

[0051] In order to balance the filtering effect and the system response speed, the present invention adopts an adaptive filtering window mechanism. The filtering window size n is based on the data fluctuation degree σ 2 Dynamic Adjustment:

[0052] n=n min +(n max -n min )·(1-e^(-λ·σ 2 ));

[0053] where n min Indicates the minimum window size, usually set to 3-5 to ensure basic filtering effect; n max Indicates the maximum window size, usually set to 15-20 to avoid excessive delays; λ indicates the adjustment sensitivity coefficient, which controls the response sensitivity of the window size to data fluctuations; σ 2Indicates the data variance, reflecting the degree of data fluctuation. When the data fluctuation is large (σ 2 increases), the filter window tends to be smaller, retaining more dynamic information; when the data is relatively stable (σ 2 decreases), the filter window tends to a larger value, providing a stronger filtering effect.

[0054] This adaptive filtering mechanism enables the system to dynamically adjust its filtering strategy based on the characteristics and fluctuations of different parameters. For example, it uses a smaller window for the rapidly fluctuating temperature parameter and a larger window for the slowly changing humidity parameter, achieving optimal filtering results. This adaptive filtering window mechanism improves the system's data processing accuracy while maintaining a high response speed.

[0055] The processing parameter optimization module 20 is the core of the system and is used to evaluate the processing quality and determine the optimal processing parameters. Figure 3 As shown, the processing parameter optimization module 20 includes a quality evaluation unit 21, a parameter mapping unit 22, and an optimization solution unit 23. The quality evaluation unit 21 evaluates the current processing quality based on the processing quality evaluation model, the parameter mapping unit 22 establishes a mapping relationship between processing parameters and processing quality, and the optimization solution unit 23 is responsible for solving the optimal processing parameters.

[0056] The mathematical expression of the processing quality evaluation model is: Q=f(T,H,P,M);

[0057] Where Q represents processing quality indicators, such as raw material uniformity and yield; T represents processing temperature (°C); H represents processing humidity (%); P represents processing pressure (Pa); M represents raw material mass (kg); and f represents the nonlinear functional relationship between processing quality and processing parameters. The significance of this model lies in describing the relationship between processing quality and various processing parameters through a multivariate nonlinear function, providing a basis for parameter optimization.

[0058] In practical applications, the machining quality evaluation model can be further refined into a multivariate nonlinear polynomial form:

[0059] Q=w1·T 2 +w2·H 2 +w3·P 2 +w4·M+w5·T·H+w6·T·P+...+w m ; where w1, w2, ..., w m is the weight coefficient obtained by fitting experimental data, reflecting the influence of each parameter on processing quality and their interactions. The above polynomial form considers the interactions between multiple parameters such as temperature, humidity, pressure, and raw material quality. For example, T·H represents the interaction effect between temperature and humidity, making the model more consistent with the actual processing process.

[0060] Coefficients w1, w2, ..., w m The determination of the coefficients is typically performed using the least squares method or other regression analysis methods. For example, experimental data for Curcuma longa processing show that the quadratic coefficient w1 for temperature is negative, indicating an optimal processing temperature; temperatures below or above this value reduce processing quality. The quadratic coefficient w2 for humidity is also negative, indicating an optimal processing humidity. The interaction coefficient w5 for temperature and humidity is positive, indicating that the synergistic effect of temperature and humidity has a positive impact on processing quality.

[0061] The optimization target of machining parameters can be expressed as: Q max =f(T,H,P,M);

[0062] The constraint condition is T min ≤T≤T max ,H min ≤H≤H max ,P min ≤P≤P max ,M min ≤M≤M max .

[0063] The goal of this optimization is to maximize the machining quality Q by adjusting the machining parameters T, H, P, and M, while satisfying the physical constraints of the machining equipment. This is a multivariable, nonlinear, constrained optimization problem, which the system solves using gradient descent, genetic algorithms, or other optimization algorithms. During the solution process, the system also considers the smoothness of parameter adjustments and the speed of system response to avoid drastic parameter fluctuations and ensure stable system operation.

[0064] The dynamic adaptive control module 30 is the execution center of the system, responsible for generating control signals and making dynamic adjustments. Figure 4 As shown, the dynamic adaptive control module 30 includes a PID control unit 31, an environmental fluctuation analysis unit 32, and an adaptive adjustment unit 33. The PID control unit 31 generates a basic control signal based on the processing quality error, the environmental fluctuation analysis unit 32 evaluates the degree of fluctuation of the environmental parameters, and the adaptive adjustment unit 33 dynamically adjusts the control strategy according to the environmental fluctuation.

[0065] The mathematical expression of the PID control algorithm is:

[0066]

[0067] Among them, P control Represents the control signal, which is used to adjust the processing parameters; e(t)=Q target -Q represents the processing quality error, that is, the difference between the target quality and the current quality; K p , K i, K d The significance of this formula is to generate a control signal that can effectively eliminate quality errors through the combined effect of the three control terms. p e(t) is proportional to the current error and provides basic control strength; the integral term K i ∫e(τ)dτ accumulates historical errors and eliminates static errors; the differential term K d de(t) / dt predicts the changing trend of the error and improves system stability and response speed.

[0068] In order to improve the adaptability and stability of the system, the present invention also includes a PID parameter self-adjustment module 50, which dynamically adjusts the PID control parameters according to the size and change trend of the quality error:

[0069] K p (t)=K p0 +ΔK p |e(t)|;

[0070] K i (t)=K i0 / (1+γ·|e(t)|);

[0071] K d (t)=K d0 +δ·|de(t) / dt|.

[0072] where K p0 , K i0 , K d0 are the initial parameter values, which are usually determined by empirical settings or system identification methods; ΔK p , γ, δ are adjustment coefficients, which control the sensitivity and amplitude of parameter adjustment. The significance of the above formula is to dynamically adjust the PID parameters according to the error state to adapt to the control requirements of different working conditions. When the error is large, the system increases the proportional coefficient K p To improve the response speed and reduce the integral coefficient K i To avoid integral saturation; when the error change rate is large, the system increases the differential coefficient K d The above self-adjustment mechanism enables the system to maintain good control performance under different error conditions.

[0073] An important improvement of the present invention is the introduction of adaptive adjustment rules:

[0074] P adjust =α·P control +β·X filtered (t);

[0075] Among them, P adjustrepresents the control signal after adaptive adjustment; α and β are adjustment coefficients, satisfying α+β=1 and 0≤α,β≤1; X filtered (t) represents the filtered sensor data. The significance of this formula is to combine traditional PID control with real-time sensor data, enabling the control system to simultaneously consider quality errors and real-time environmental changes, improving the system's adaptability and response speed.

[0076] like Figure 5 As shown, the adjustment coefficients α and β are dynamically adjusted according to the degree of environmental fluctuation, satisfying the mathematical relationship:

[0077] α=1 / (1+k·τ 2 );

[0078] β=1-α.

[0079] where τ 2 represents the variance of environmental parameters, reflecting the degree of environmental fluctuation; k represents the adjustment coefficient, which controls the sensitivity of adaptive adjustment. When the environmental fluctuation is large (τ 2 increases), α decreases, β increases, the system responds more quickly to environmental changes based on real-time data; when the environment is relatively stable (τ 2 As α increases and β decreases, the system can more accurately adjust the processing parameters based on PID control. This dynamic balancing mechanism enables the system to maintain optimal control performance under different environmental conditions.

[0080] The parameter adjustment module 40 is responsible for converting the control signal into a specific parameter adjustment value and updating the processing parameters. The dynamic adjustment formula according to the processing parameters is:

[0081] T(t+1)=T(t)+γ T ·P adjust ;

[0082] H(t+1)=H(t)+γ H ·P adjust ;

[0083] P(t+1)=P(t)+γ p ·P adjust ;

[0084] Where T(t+1), H(t+1), P(t+1) represent the processing temperature, humidity and pressure at the next moment; γ T , γ H , γ p The step size coefficient represents the adjustment step for each parameter, controlling the magnitude of the adjustment. The purpose of the above formula is to dynamically update machining parameters based on the adaptive control signal, enabling the system to continuously optimize the machining process. The step size coefficient determines the magnitude of parameter adjustment and influences the system's response speed and stability.

[0085] like Figure 6 As shown, the present invention adopts a hierarchical parameter adjustment strategy, using different adjustment step coefficients for different processing parameters to satisfy the relationship:

[0086] γ T =γ base ·k T |e(t)|^a T ;

[0087] γ H =γ base ·k H |e(t)|^a H ;

[0088] γ p =γ base ·k p |e(t)|^a p ;

[0089] where γ base is the basic adjustment step, usually set to 0.01-0.1; k T 、k H 、k p Adjust the weights for each parameter to reflect the adjustment priority of different parameters, usually satisfying k T >k H >k p , indicating that temperature adjustment has the highest priority; a T 、a H 、a p is the nonlinear adjustment index of each parameter, which controls the nonlinear relationship between the adjustment amplitude and the error, and usually satisfies a T >a H >a p , making the temperature adjustment more aggressive when the error is large, and the pressure adjustment more conservative.

[0090] The significance of this hierarchical adjustment strategy lies in the adoption of different adjustment strategies for processing parameters with different characteristics: For parameters with significant impact and easy adjustment, such as temperature, a higher adjustment frequency and a moderate adjustment range are used to achieve rapid response; for parameters with slow changes, such as humidity, a lower adjustment frequency and a smaller adjustment range are used to ensure system stability; and for basic parameters such as pressure, a conservative adjustment strategy is adopted, adjusting only when they deviate significantly from the target, ensuring safe system operation. This hierarchical adjustment strategy enables the system to achieve a balance between response speed and stability, avoids mutual interference between parameter adjustments, and improves overall control effectiveness.

[0091] In terms of energy optimization, the system also includes an energy consumption optimization module 60, which is used to minimize energy consumption while ensuring processing quality:

[0092] , where E represents the total energy consumption, w T 、w p 、w O The energy consumption weights for temperature, pressure, and other parameters reflect their contribution to total energy consumption. This formula aims to minimize energy consumption throughout the entire machining process while still meeting machining quality requirements by controlling the trajectory of machining parameters. The Energy Optimization Module uses a multi-objective optimization algorithm to find the optimal balance between machining quality and energy consumption, achieving a green and efficient machining process.

[0093] like Figure 7 As shown, the present invention also provides an intelligent perception and adaptive control method for Curcuma aromatica processing equipment, the method comprising the following steps:

[0094] First, the system is initialized, the initial processing parameters T(0), H(0), P(0) are set, and the target processing quality Q is determined. target , initialize PID control parameter K p ,K i ,K d And adaptive adjustment coefficients α, β, set the parameter constraint range.

[0095] Then, the system enters the data acquisition and processing stage, and collects the processing environment and process data X(t) in real time through multiple sensors. The application model X(t)=X base +ΔX(t) decomposes the data into reference value and fluctuation value, and uses data filtering and calibration formula Eliminate data noise, calibrate and fuse the filtered data to form an accurate parameter estimate at the current moment.

[0096] Next, the system enters the quality assessment stage. Based on the current processing parameters T(t), H(t), P(t), M(t) and the processing quality evaluation model Q=f(T,H,P,M), the current processing quality Q(t) is calculated and the quality error e(t)=Q target -Q(t), update the error integral ∫e(τ)dτ and the error change rate de(t) / dt.

[0097] In the parameter optimization stage, the system first uses the PID control algorithm

[0098] Calculate the basic control signal and then calculate the degree of environmental fluctuation,

[0099] Dynamically adjust the values of α and β and apply the adaptive adjustment rule P adjust =α·P control +β·X filtered(t) Generate the final control signal,

[0100] Finally, calculate the adjustment amount of each parameter ΔT=γ T ·P adjust ,ΔH=γ H ·P adjust ,ΔP=γ p ·P adjust .

[0101] During the execution control phase, the system updates the processing parameters

[0102] T(t+1)=T(t)+ΔT, H(t+1)=H(t)+ΔH, P(t+1)=P(t)+ΔP. Check whether the parameters are within the constraints. If they are exceeded, truncate them to the boundary values and send the optimized parameters to the execution device to complete a control cycle.

[0103] The system loops through the above process at fixed intervals (typically 100ms-1s) to continuously monitor and optimize the machining process. During the machining process, the system continuously learns and accumulates data, optimizing the machining quality model and control parameters through machine learning algorithms, resulting in continuous improvement in system performance over time.

[0104] In order to verify the effect of the present invention, a practical application test was carried out on the processing line of Curcuma zedoariae in a certain Chinese herbal medicine processing enterprise. Figure 8 As shown, compared with traditional processing lines, the Curcuma longa processing line using the system of the present invention achieves improved processing quality: the yield rate increased by 15.6%, the active ingredient content increased by 12.3%, and the particle uniformity increased by 23.5%. Especially under conditions of large ambient temperature fluctuations, the system of the present invention demonstrates greater stability and adaptability, maintaining consistent processing quality.

[0105] like Figure 9 As shown in the figure, the proposed system saves 18.7% of electricity and 14.2% of steam compared to traditional processing lines, reducing total energy consumption by approximately 16.5%. These energy savings are primarily due to three factors: first, a precise processing quality evaluation model avoids unnecessary over-processing; second, an adaptive control mechanism reduces parameter fluctuations and reduces energy loss; and finally, an energy consumption optimization module directly optimizes energy consumption, further improving energy efficiency.

[0106] In summary, the intelligent perception and adaptive control system for Curcuma aromatica processing equipment provided by the present invention effectively solves the problems of insufficient data acquisition accuracy, slow response speed and lack of adaptive ability in traditional Curcuma aromatica processing equipment through improved technologies such as high-precision data perception model, nonlinear processing quality evaluation model, dual adaptive control mechanism and hierarchical parameter adjustment strategy, realizes intelligent monitoring and optimization control of the processing process, improves processing quality, production efficiency and energy utilization, provides a new technical solution for the refined processing of Chinese medicinal materials, and has broad application prospects.

[0107] It should be understood that the above embodiments are merely examples given to illustrate the principles of the present invention. Those skilled in the art may make various changes and modifications without departing from the scope and spirit of the present invention. Therefore, all equivalent changes and modifications made to the present invention based on the technical solutions and concepts of the present invention should fall within the scope of protection of the present invention.

[0108] In order to better understand the present invention, the present invention provides a specific algorithm calculation process to illustrate the technical points of the present invention:

[0109] 1. Initial parameter setting

[0110] Simulate the actual working environment of a Curcuma Radix processing production line in a Chinese herbal medicine processing enterprise:

[0111] Sensor data parameters: Reference temperature value: T base =60℃ (standard process temperature for processing Curcuma longa); reference humidity value: H base =45% (standard process humidity for Curcuma zedoaria processing); reference pressure value: P base =1.2×10 5 Pa (standard process pressure for Curcuma aromatica processing); raw material mass: M=500kg (single batch processing volume).

[0112] Filter parameters: Minimum filter window: n min =3; Maximum filter window: n max =15; adjust the sensitivity coefficient: λ=0.8; initial filter window size: n=5.

[0113] Processing quality evaluation model parameters:

[0114] Temperature quadratic coefficient: w1=-0.015 (unit: 1 / ℃ 2 ); Humidity quadratic coefficient: w2=-0.008 (unit: 1 / % 2 ); Pressure quadratic coefficient: w3=-0.0002 (unit: 1 / Pa 2); Raw material mass coefficient: w4=0.05 (unit: 1 / kg); Temperature-humidity interaction coefficient: w5=0.006 (unit: 1 / (℃·%)); Temperature-pressure interaction coefficient: w6=0.0001 (unit: 1 / (℃·Pa)); Constant term: w0=25.

[0115] Processing parameter constraints: Temperature range: T min =50℃, T max =70℃; humidity range: H min =35%, H max =55%; Pressure range: P min =1.0×10 5 Pa, P max =1.4×10 5 Pa.

[0116] PID control parameters: initial proportional coefficient: K p0 =0.5; initial integral coefficient: K i0 =0.08; initial differential coefficient: K d0 =0.2; proportional adjustment coefficient: ΔK p =0.1; integral adjustment coefficient: γ=0.5; differential adjustment coefficient: δ=0.3; target processing quality: Q target =90 (quality out of 100).

[0117] Adaptive adjustment parameters: adjustment coefficient: k=2.0; initial α value: α=0.7; initial β value: β=0.3.

[0118] Parameter adjustment parameters: Basic adjustment step: γ base =0.05; Temperature adjustment weight: k T =1.0; humidity adjustment weight: k H =0.7; pressure adjustment weight: k p =0.3; Temperature nonlinear adjustment index: a T =0.8; Humidity nonlinear adjustment index: a H =0.6; Pressure nonlinear adjustment index: a p =0.4.

[0119] Current measurement values (sensor readings at a certain moment): Current temperature: T(t) = 63.5°C; Current humidity: H(t) = 42.8%; Current pressure: P(t) = 1.25×10 5 Pa; Error integral value: ∫e(τ)dτ=12.5; Error change rate: de(t) / dt=-1.2

[0120] 2. Algorithm calculation process

[0121] 1. Data-aware model calculation

[0122] First, use the data acquisition dynamic model to decompose the current sensor data into baseline values and fluctuating values:

[0123] Temperature decomposition: T(t)=T base +ΔT(t); 63.5°C = 60°C + ΔT(t), therefore, ΔT(t) = 3.5°C;

[0124] Humidity decomposition: H(t)=H base +ΔH(t)42.8%=45%+ΔH(t), therefore, ΔH(t)=-2.2%;

[0125] Pressure decomposition: P(t)=P base +ΔP(t)1.25×10 5 Pa=1.2×10 5 Pa+ΔP(t);

[0126] Therefore, ΔP(t)=0.05×10 5 Pa=5000Pa.

[0127] Assume that there is temperature data for the past five time points:

[0128] T(t-1)=63.2℃, T(t-2)=62.8℃, T(t-3)=62.5℃, T(t-4)=62.1℃, T(t-5)=61.8℃.

[0129] Calculate the filtered temperature value using the moving average filtering method:

[0130] T filtered (t)=(1 / n)∑(i=1 to n)T(t-i+1)

[0131] =(1 / 5)×(63.5℃+63.2℃+62.8℃+62.5℃+62.1℃)=(1 / 5)×314.1℃=62.82℃.

[0132] Similarly, assuming humidity data for the past five time points:

[0133] H(t-1)=43.0%, H(t-2)=43.3%, H(t-3)=43.5%, H(t-4)=43.8%, H(t-5)=44.0%.

[0134] Calculate the filtered humidity value:

[0135] H filtered(t)=(1 / 5)×(42.8%+43.0%+43.3%+43.5%+43.8%)=(1 / 5)×216.4%=43.28%.

[0136] Assume the pressure data for the past 5 time points:

[0137] P(t-1)=1.24×10 5 Pa,P(t-2)=1.23×10 5 Pa,P(t-3)=1.22×10 5 Pa,P(t-4)=1.21×10 5 Pa,P(t-5)

[0138] =1.21×10 5 Pa.

[0139] Calculate the filtered pressure value:

[0140] P filtered (t)=(1 / 5)×(1.25×10 5 Pa+1.24×10 5 Pa+1.23×10 5 Pa+1.22×10 5 Pa+1.21×10 5 Pa)=(1 / 5)×6.15×10 5 Pa=1.23×10 5 Pa.

[0141] Next, calculate the variance of the data to determine if the filter window size needs to be adjusted:

[0142] Temperature data variance:

[0143] σ 2 T =(1 / 5)×[(63.5-62.82) 2 +(63.2-62.82) 2 +(62.8-62.82) 2 +(62.5-62.82) 2 +(62.1-62.82) 2 ]

[0144] =(1 / 5)×[(0.68) 2 +(0.38) 2 +(-0.02) 2 +(-0.32) 2 +(-0.72) 2 ]

[0145] =(1 / 5)×(0.4624+0.1444+0.0004+0.1024+0.5184)=(1 / 5)×1.228=0.2456.

[0146] Adjust the filter window size based on the temperature data variance:

[0147] n T =n min +(n max -n min )·(1-e^(-λ·σ 2 T ))=3+(15-3)·(1-e^(-0.8×0.2456))=3+12·(1-0.8221)=3+12·0.1779=3+2.1348=5.1348≈5.

[0148] Since the calculated filtering window size is close to the currently used window size, the window size of n=5 can continue to be used for filtering.

[0149] 2. Processing quality evaluation calculation

[0150] Use the machining quality evaluation model to calculate the machining quality under the current parameters:

[0151] Q=w0+w1·T 2 +w2·H 2 +w3·P 2 +w4·M+w5·T·H+w6·T·P

[0152] Substitute parameter values (using filtered data):

[0153] Q=25+(-0.015)·(62.82) 2 +(-0.008)·(43.28) 2 +(-0.0002)·(1.23×10 5 ) 2 +0.05·500+0.006·62.82·43.28+0.0001·62.82·1.23×10 5

[0154] Step-by-step calculation:

[0155] w1·T 2 =-0.015×(62.82) 2 =-0.015×3946.35=-59.20;

[0156] w2·H 2 =-0.008×(43.28) 2=-0.008×1873.16=-14.99;

[0157] w3·P 2 =-0.0002×(1.23×10 5 ) 2 =-0.0002×1.5129×10 10 =-3025.80;

[0158] w4·M=0.05×500=25.00;

[0159] w5·T·H=0.006×62.82×43.28=0.006×2718.86=16.31;

[0160] w6·T·P=0.0001×62.82×1.23×10 5 =0.0001×7726.86=0.77;

[0161] Q=25+(-59.20)+(-14.99)+(-3025.80)+25.00+16.31+0.77Q=25+(-59.20)+(-14.99)+(- 3025.80)+25.00+16.31+0.77Q=25-59.20-14.99-3025.80+25.00+16.31+0.77=-3032.91.

[0162] A negative result indicates that the current parameter combination is far from optimal. This is because the quadratic coefficient of pressure is large, resulting in a low quality score at the current pressure value. In practical applications, appropriate adjustments to the model coefficients are necessary to ensure that the quality score remains within a reasonable range within the normal operating range.

[0163] To demonstrate the subsequent calculations, assume that after parameter adjustment and model correction, the current quality score is Q=85.

[0164] 3.PID controller calculation

[0165] Calculate the error between the current processing quality and the target value: e(t)=Q target -Q=90-85=5.

[0166] Dynamically adjust PID parameters based on error size:

[0167] Proportional coefficient adjustment: K p (t)=K p0 +ΔK p ·|e(t)|=0.5+0.1×5=0.5+0.5=1.0.

[0168] Integral coefficient adjustment:

[0169] K i (t)=K i0 / (1+γ·|e(t)|)=0.08 / (1+0.5×5)=0.08 / 3.5=0.0229.

[0170] Differential coefficient adjustment: K d (t)=K d0 +δ·|de(t) / dt|=0.2+0.3×1.2=0.2+0.36=0.56.

[0171] Apply the PID control algorithm to calculate the control signal:

[0172] ;

[0173] P control =1.0×5+0.0229×12.5+0.56×(-1.2)=5+0.2863-0.672=4.6143.

[0174] 4. Calculation of adaptive adjustment mechanism

[0175] Calculate the adaptive adjustment coefficient based on the degree of fluctuation of environmental parameters:

[0176] Calculation of environmental fluctuation variance: Assuming the comprehensive variance of environmental parameters τ 2 =0.35 (based on the weighted average of the variances of temperature, humidity, and pressure)

[0177] Adaptive coefficient calculation:

[0178] α=1 / (1+k·τ 2 )=1 / (1+2.0×0.35)=1 / 1.7=0.5882β=1-α=1-0.5882=0.4118.

[0179] Apply the adaptive regulation rule to generate the final control signal: P adjust =α·P control +β·X filtered (t).

[0180] X filtered (t) It is necessary to select the filtered value of temperature, humidity or pressure, or a weighted combination according to specific needs. Assume that the filtered value of temperature is selected and normalized to make its magnitude equivalent to the control signal:

[0181] X filterednorm =(T filtered -T base) / 5=(62.82-60) / 5=2.82 / 5=0.564.

[0182] Substitute into the calculation: P adjust =0.5882×4.6143+0.4118×0.564=2.7142+0.2323=2.9465.

[0183] 5. Parameter adjustment step calculation

[0184] Calculate the adjustment step size of each parameter based on the hierarchical parameter adjustment strategy:

[0185] Temperature adjustment step:

[0186] γ T =γ base ·k T |e(t)|^a T =0.05×1.0×5^0.8=0.05×1.0×3.3437=0.1672.

[0187] Humidity adjustment step:

[0188] γ H =γ base ·k H |e(t)|^a H =0.05×0.7×5^0.6=0.05×0.7×2.5149=0.0880.

[0189] Pressure adjustment steps:

[0190] γ p =γ base ·k p |e(t)|^a p =0.05×0.3×5^0.4=0.05×0.3×1.9037=0.0286.

[0191] 6. Parameter update calculation

[0192] Calculate the adjustment amount of each parameter:

[0193] Temperature adjustment: ΔT=γ T ·P adjust =0.1672×2.9465=0.4927℃;

[0194] Humidity adjustment: ΔH=γ H ·P adjust =0.0880×2.9465=0.2593%;

[0195] Pressure adjustment: ΔP=γ p ·Padjust =0.0286×2.9465=0.0843×10 5 Pa=8,430Pa.

[0196] Update processing parameters:

[0197] Temperature update: T(t+1)=T(t)+ΔT=62.82+0.4927=63.3127℃;

[0198] Humidity update: H(t+1)=H(t)+ΔH=43.28+0.2593=43.5393%;

[0199] Pressure update: P(t+1)=P(t)+ΔP=1.23×10 5 +8,430=1.31×10 5 Pa.

[0200] 7. Parameter constraint check

[0201] Check that the updated parameters are within the constraints:

[0202] Temperature check: T min ≤T(t+1)≤T max , 50℃≤63.3127℃≤70℃ meets the constraint conditions and no adjustment is required.

[0203] Humidity check: H min ≤H(t+1)≤H max , 35%≤43.5393%≤55% meets the constraints and no adjustment is required.

[0204] Pressure check: P min ≤P(t+1)≤P max , 1.0×10 5 Pa≤1.31×10 5 Pa≤1.4×10 5 Pa satisfies the constraints and does not need to be adjusted.

[0205] 8. Predict the processing quality at the next moment

[0206] Substitute the updated parameters into the machining quality evaluation model to predict the machining quality at the next moment:

[0207] Q(t+1)=w0+w1·T(t+1) 2 +w2·H(t+1) 2 +w3·P(t+1) 2 +w4·M+w5·T(t+1)·H(t+1)+w6·T(t+1)·P(t+1).

[0208] Assume that after parameter adjustment, the predicted processing quality is Q(t+1)=87.2, which is 2.2 percentage points higher than the current Q=85.

[0209] Result Analysis

[0210] Through the above calculation process, we can see the working principle and effect of the intelligent perception and adaptive control system of the Curcuma processing equipment:

[0211] Data Perception Model: This model effectively decomposes raw sensor data into baseline and fluctuating values, eliminating random noise through moving average filtering. Calculations show that adaptively adjusting the filter window size based on data fluctuations ensures accurate and timely data processing. The current temperature value, after filtering, changes from 63.5°C to 62.82°C, closer to the actual process temperature and reducing the impact of sudden fluctuations.

[0212] The processing quality evaluation model comprehensively considers the impact of factors such as temperature, humidity, pressure, and raw material quality on processing quality through a multivariate nonlinear function. The calculation results show that the processing quality under the current parameter combination is 85 points (out of 100), close to but not yet reaching the target score of 90 points, indicating that further optimization of processing parameters is needed.

[0213] PID controller: Based on the mass error e(t)=5, the control parameters are dynamically adjusted: the proportional coefficient is increased from 0.5 to 1.0, the integral coefficient is reduced from 0.08 to 0.0229, and the differential coefficient is increased from 0.2 to 0.56. The above adaptive adjustment makes the PID controller more sensitive, and the generated control signal P control =4.6143 can effectively reduce the mass error.

[0214] Adaptive adjustment mechanism: according to the degree of environmental fluctuation τ 2 =0.35 dynamically adjusts α=0.5882 and β=0.4118, so that the control system takes into account both the PID control signal and the real-time data changes. The final adaptive control signal P adjust =2.9465 is more stable than pure PID control and avoids over-adjustment.

[0215] Layered parameter adjustment strategy: different adjustment steps are set for different processing parameters: temperature adjustment step γ T =0.1672 maximum, humidity adjustment step γ H =0.0880, the pressure adjustment step length γ p =0.0286 minimum. The above stratification strategy enables rapid temperature response, while the pressure adjustment is more conservative, ensuring system stability.

[0216] Parameter update: Calculations show that the control system adjusts the temperature from 62.82°C to 63.31°C (an increase of approximately 0.49°C), the humidity from 43.28% to 43.54% (an increase of approximately 0.26%), and the pressure from 1.23×10 5 Pa was adjusted to 1.31×10 5 Pa (an increase of approximately 8,430 Pa). All updated parameters are within the constraints and no additional adjustments are required.

[0217] Prediction results show that after one round of parameter adjustment, the processing quality increased from 85 to 87.2 points, an increase of 2.2 points, close to the target value of 90 points. This shows that the control effect of the system can gradually optimize the processing parameters and improve the processing quality.

[0218] In summary, the calculation results validate the effectiveness of the intelligent perception and adaptive control system for Curcuma longifolia processing equipment. Through high-precision data acquisition, nonlinear quality assessment, dual adaptive control, and hierarchical parameter adjustment, the system achieves intelligent monitoring and optimized control of the machining process. The system continuously executes the aforementioned calculation process, continuously optimizing machining parameters to gradually approach and ultimately achieve the target machining quality, while maintaining system stability and energy efficiency.

Claims

1. An intelligent perception and adaptive control system for turmeric processing equipment, characterized in that: include: A processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the computer program implements the construction and operation of a data perception model, a processing parameter optimization model, and a dynamic adaptive control model; The data perception module is used to monitor processing parameters in real time based on the data acquisition dynamic model; and eliminate data noise through data filtering and calibration formulas; The data acquisition dynamic model is X(t)=X base +ΔX(t), where X(t) represents the data value at the current time t, X base represents the reference value collected by the sensor, and ΔX(t) represents the dynamic fluctuation value; The calibration formula is , where X filtered (t) represents the smoothed data value after filtering, and n represents the size of the filtering window; The machining parameter optimization module is used to evaluate the machining quality based on the machining quality evaluation model; and optimize the parameters under the constraints through the optimization target; The processing quality evaluation model is Q=f(T,H,P,M), where Q represents the processing quality index, T represents the processing temperature, H represents the processing humidity, P represents the processing pressure, M represents the raw material quality, and f represents the nonlinear function between the processing quality and the processing parameters; The processing quality evaluation model adopts the multivariate nonlinear polynomial form: Q=w1·T 2 +w2·H 2 +w3·P 2 +w4·M+w5·T·H+w6·T·P+...+w m Among them, w1,w2,...,w m is the weight coefficient obtained by fitting the experimental data, which reflects the influence of each parameter on the processing quality and their interaction; Dynamic adaptive control module, used to generate control signals using PID control algorithm; The PID control algorithm is ; where e(t)=Q target -Q represents the processing quality error, where Q target is the target processing quality, K p , K i , K d They are proportional, integral and differential gain parameters respectively; and through the adaptive adjustment rule P adjust =α·P control +β·X filtered (t) Realize dynamic adjustment of the control signal, where α and β are adjustment coefficients; The adjustment coefficients α and β in the dynamic adaptive control module are dynamically adjusted according to the degree of environmental fluctuation and satisfy the following mathematical relationship: α=1 / (1+k·τ 2 ); β=1-α； Among them, τ 2 represents the variance of environmental parameters, k represents the adjustment coefficient; The parameter adjustment module is used to dynamically adjust the formula to update the processing parameters according to the processing parameters.

2. The intelligent perception and adaptive control system for turmeric processing equipment according to claim 1 is characterized in that: The optimization goal is Q max =f(T,H,P,M); The constraint condition is T min ≤T≤T max ,H min ≤H≤H max ,P min ≤P≤P max ,M min ≤M≤M max ; The formula for dynamic adjustment of processing parameters is: T(t+1)=T(t)+γ T ·P adjust ,H(t+1)=H(t)+γ H ·P adjust ,P(t+1)=P(t)+γ p ·P adjust , where γ T , γ H , γ p Indicates the adjustment step coefficient of each parameter.

3. The intelligent perception and adaptive control system for turmeric processing equipment according to claim 2 is characterized in that: The data perception module adopts an adaptive filtering window mechanism, and the filtering window size n is based on the data fluctuation degree σ 2 Dynamic Adjustment: n=n min +(n max -n min )·(1-e^(-λ·σ 2 )) Among them, n min Indicates the minimum window size, n max represents the maximum window size, λ represents the adjustment sensitivity coefficient, σ 2 Represents the data variance.

4. The intelligent perception and adaptive control system for Curcuma aromatica processing equipment according to claim 2, characterized in that: The system also includes a PID parameter self-adjustment module, which dynamically adjusts the PID control parameters according to the size and change trend of the quality error: K p (t)=K p0 +ΔK p ·|e(t)| K i (t)=K i0 / (1+γ·|e(t)|) K d (t)=K d0 +δ·|de(t) / dt| Among them, K p0 , K i0 , K d0 are the initial parameter values, ΔK p , γ, and δ are adjustment coefficients.

5. The intelligent perception and adaptive control system for turmeric processing equipment according to claim 2 is characterized in that: The system adopts a hierarchical parameter adjustment strategy, using different adjustment step coefficients for different processing parameters to meet the following relationship: c T =c base ·k T ·|e(t)|^a T , c H =c base ·k H ·|e(t)|^a H , c p =c base ·k p ·|e(t)|^a p , Among them, γ base is the basic adjustment step length, k T 、k H 、k p Adjust the weights for each parameter, a T 、a H 、a p is the nonlinear adjustment index of each parameter, usually satisfying a T >a H >a p .

6. The intelligent perception and adaptive control system for Curcuma aromatica processing equipment according to claim 2, characterized in that: The system also includes an energy optimization module to minimize energy consumption while ensuring processing quality: ; Where E represents the total energy consumption, w T 、w p 、w O Represent the energy consumption weights of temperature, pressure and other parameters respectively.

7. An intelligent perception and adaptive control method for Curcuma zedoaria processing equipment applied to the system according to any one of claims 1 to 6, characterized in that: The following steps are involved: Collect and monitor processing parameters and apply the model X(t)=X base +ΔX(t) decomposes the data into baseline value and fluctuation value; Through data filtering and calibration formula Eliminate data noise; Evaluate the current processing quality based on the processing quality evaluation model Q=f(T,H,P,M) and calculate the quality error e(t)=Q target -Q; Through PID control algorithm Generate basic control signals; Apply adaptive adjustment rule P adjust =α·P control +β·X filtered (t) Realize dynamic adjustment of control signals; Dynamic adjustment formula according to processing parameters: {T(t+1)=T(t)+γ T ·P adjust ,H(t+1)=H(t)+γ H ·P adjust ,P(t+1)=P(t)+γ p ·P adjust }Update processing parameters; Check whether the updated parameters are within the constraints, and truncate to the boundary value if they exceed the constraints; The optimized parameters are sent to the execution device to complete a control cycle.

Images