An adaptive control method and system for operation of a rice huller

Abstract

This invention discloses an adaptive control method and system for the operation of a rice hulling machine, relating to the field of agricultural product processing control technology. It addresses the problem of how to adaptively regulate the difference in linear speed between the rubber rollers of a rice hulling machine to suppress load fluctuations and stabilize the hulling rate. The method includes: acquiring monitoring data of the rice hulling machine within a preset time window; determining probability parameters based on the main motor power supply voltage, the difference in linear speed between the rubber rollers, and the rice hulling rate; determining the adjustment capability parameters of the rice hulling machine based on the difference between the rice inflow and outflow speeds, the probability parameters, and the control response time; determining environmental and state disturbance parameters based on environmental and equipment state parameters, and determining adaptive control weights based on the adjustment capability parameters and the environmental and state disturbance parameters; and adjusting the proportional gain value of the linear speeds of the two rubber rollers according to the adaptive control weights.

Description

Technical Field

[0001] This invention relates to the field of agricultural product processing control technology, specifically to an adaptive control method and system for the operation of a rice hulling and milling machine. Background Technology

[0002] The rice hulling machine is the core equipment for processing paddy into rice, and its hulling effect directly affects the rice yield and the integrity of the rice grains. In this equipment, the linear speed difference between the two rollers is a key process parameter determining the hulling efficiency and quality of the paddy. Currently, the setting and adjustment of this parameter mainly rely on the operator's experience or preset values ​​for a fixed variety, lacking online adaptive adjustment capabilities. Because environmental conditions, material characteristics, and mechanical wear are constantly changing and interdependent during processing, this static or experience-based control method struggles to respond in real-time to complex operating disturbances, leading to fluctuations in equipment load, poor stability of the hulling process, and difficulty in maintaining optimal overall processing efficiency and quality. Summary of the Invention

[0003] To address the current technical problem of how to adaptively control the linear speed difference of the rubber rollers in rice hulling machines to suppress load fluctuations and stabilize the hulling rate, the present invention aims to provide an adaptive control method and system for the operation of a rice hulling machine. The specific technical solution adopted is as follows: In a first aspect, the present invention provides an adaptive control method for the operation of a rice hulling machine, comprising: acquiring monitoring data of the rice hulling machine within a preset time window; wherein the monitoring data includes the main motor power supply voltage, the linear speed difference between the rubber rollers, the rice hulling rate, the rice inflow velocity, the rice outflow velocity, and environmental and equipment status parameters; determining probability parameters based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate; wherein the probability parameters are used to characterize the probability that the load fluctuation of the rice hulling machine is caused by the linear speed difference between the rubber rollers; and determining the probability parameters based on the rice inflow velocity and the rice outflow velocity. The adjustment capability parameters of the rice huller are determined by considering the difference in output speed, probability parameters, and control response time. The control response time is the time from sensing a load disturbance to triggering a control command. Environmental and equipment state parameters are determined, and adaptive control weights are determined based on the adjustment capability parameters and environmental and state disturbance parameters. The environmental and state disturbance parameters characterize the degree of interference caused by environmental factors and equipment state on system regulation. The proportional gain value of the linear speed of the two rubber rollers is adjusted according to the adaptive control weights.

[0004] Secondly, the present invention provides an adaptive control system for the operation of a rice hulling machine, comprising: a data acquisition module, a probability calculation module, an adjustment capability assessment module, an adaptive weight calculation module, and a proportional gain control module; the data acquisition module is used to acquire monitoring data of the rice hulling machine within a preset time window; wherein, the monitoring data includes the main motor power supply voltage, the linear speed difference between the rubber rollers, the rice hulling rate, the rice inflow velocity, the rice outflow velocity, and environmental and equipment status parameters; the probability calculation module is used to determine probability parameters based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate; wherein, the probability parameters are used to characterize the probability that the load fluctuation of the rice hulling machine is caused by the linear speed difference between the rubber rollers. The system comprises the following modules: a regulation capability assessment module, used to determine the regulation capability parameters of the rice huller based on the difference between the rice inflow and outflow velocities, probability parameters, and regulation response time; wherein, the regulation response time is the time from when the rice huller senses a load disturbance to when it triggers a regulation command; an adaptive weight calculation module, used to determine environmental and state disturbance parameters based on environmental and equipment state parameters, and to determine adaptive regulation weights based on the regulation capability parameters and environmental and state disturbance parameters; wherein, the environmental and state disturbance parameters characterize the degree of interference caused by environmental factors and equipment state on system regulation; and a proportional gain control module, used to control the proportional gain value of the linear speed of the two rubber rollers based on the adaptive control weights.

[0005] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer-executable instructions, and when the electronic device is running, the processor executes the computer-executable instructions stored in the memory to cause the electronic device to perform an adaptive control method for operating a rice huller as described in the first aspect and any possible implementation thereof.

[0006] This invention has the following beneficial effects: by constructing a complete technical chain from multi-dimensional data perception, load fluctuation attribution analysis, system regulation performance evaluation, to environmental interference quantitative compensation, and finally to adaptive adjustment of control parameters, the rice hulling mill can automatically respond to changes in the operating environment, material characteristics, and equipment status, and optimize the key process parameter of roller linear speed difference in real time. This effectively suppresses irregular and drastic fluctuations in load, stabilizes the equipment operation in the high-efficiency range, and ultimately achieves stability and improvement in rice hulling rate. Attached Figure Description

[0007] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 This is a schematic diagram of the architecture of an adaptive control system for the operation of a rice hulling and milling machine, provided in one embodiment of the present invention. Figure 2 This is a flowchart illustrating an adaptive control method for operating a rice hulling machine, as provided in one embodiment of the present invention. Detailed Implementation

[0009] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0010] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0011] In all division and logarithmic operations involved in this invention, a smoothing mechanism is employed to prevent computer program crashes or invalid values ​​from being generated due to a zero denominator or zero input. Specifically, a correction factor ε, which is a very small positive number, is superimposed on the denominator term of the division operation or the argument term of the logarithmic function, for example, a value of 10 to the power of negative 5, thereby ensuring the robustness and feasibility of the algorithm under extreme conditions.

[0012] Unless otherwise specified, the normalization function Norm() mentioned in this invention uses maximum and minimum value normalization. The maximum and minimum values ​​are preset empirical extreme values ​​derived from a large amount of historical experimental data. If the calculation result exceeds the [0, 1] interval, it is restricted to the [0, 1] range by a truncation function (i.e., if the result is less than 0, it is taken as 0; if it is greater than 1, it is taken as 1) to eliminate the influence of outliers on the evaluation index.

[0013] The following description, in conjunction with the accompanying drawings, details the specific scheme of the adaptive control method and system for the operation of a rice hulling machine provided by the present invention.

[0014] For example, such as Figure 1The diagram shown is an architectural schematic of an adaptive control system (hereinafter referred to as the adaptive control system) for the operation of a rice hulling and milling machine according to an embodiment of the present invention. The adaptive control system 10 includes: a data acquisition module 11, a probability calculation module 12, a regulation capability evaluation module 13, an adaptive weight calculation module 14, and a proportional gain control module 15. The modules are described in detail below: (1) Data acquisition module 11.

[0015] The data acquisition module 11 is responsible for collecting various real-time and historical data related to the operating status of the rice hulling and milling machine, providing a unified and synchronous data source for subsequent analysis and control.

[0016] Optionally, the data acquisition module 11 is used to acquire monitoring data of the rice hulling and milling machine within a preset time window.

[0017] Specifically, the data acquisition module 11 utilizes various sensors and data interfaces integrated into the equipment. First, an embedded intelligent acquisition unit installed at the lower end of the contactor or circuit breaker in the motor drive cabinet acquires the main motor power supply voltage at fixed sampling intervals and outputs digital signals. Then, an encoder or speed sensor synchronously acquires the rotational speeds of the two rubber rollers and calculates the linear velocity difference between them. Simultaneously, tachometers installed at the inlet and outlet of the rubber rollers acquire the rice inflow and outflow velocities. The data acquisition module 11 also acquires ambient temperature and humidity and the equipment's mechanical vibration frequency from environmental sensors installed at key locations within the equipment. Furthermore, the rice hulling rate can be obtained through machine vision system image analysis of the outflowing material, and the rubber roller radius information can be obtained through a preset wear detection model or periodic manual input interfaces.

[0018] The data acquisition module 11 synchronizes and extracts features from the above multi-source data according to the voltage sampling time base to form a structured monitoring data set, and then transmits it to the probability calculation module 12.

[0019] (2) Probability calculation module 12.

[0020] The probability calculation module 12 is responsible for receiving the monitoring data provided by the data acquisition module 11, analyzing the correlation between load fluctuation and the speed difference of the rubber roller, calculating the probability parameters of load fluctuation caused by the speed difference, and providing a basis for subsequent judgment and control direction.

[0021] Optionally, the probability calculation module 12 is used to determine probability parameters based on the main motor power supply voltage, the difference in linear speed between the rubber rollers, and the rice hulling rate. These probability parameters characterize the probability that load fluctuations in the rice hulling machine are caused by the difference in linear speed between the rubber rollers.

[0022] For example, the probability calculation module 12 can be divided into a load fluctuation analysis submodule 121 and a coupling analysis submodule 122, which respectively complete the load fluctuation degree assessment and the speed difference-shelling rate correlation analysis, and will be described below: (2.1) Load fluctuation analysis submodule 121.

[0023] Optionally, the load fluctuation analysis submodule 121 is used to determine load fluctuation parameters based on the changes in the main motor power supply voltage within a preset time window. The load fluctuation parameters are used to characterize the severity of the load on the rice hulling machine.

[0024] Specifically, the load fluctuation analysis submodule 121 first extracts the power supply voltage sequence within a preset time window from the monitoring data. Then, for each pair of adjacent sampled values ​​in the sequence, its instantaneous slope is calculated. Next, based on the differences between all instantaneous slopes, a first characteristic index characterizing the voltage fluctuation amplitude is calculated. Simultaneously, based on the time intervals between all adjacent sampled points, a second characteristic index characterizing the voltage fluctuation rate is calculated. Finally, based on the combined calculation of the first and second characteristic indices, the load fluctuation parameters are determined.

[0025] (2.2) Coupling analysis submodule 122.

[0026] Optionally, the coupling analysis submodule 122 is used to determine coupling parameters based on the difference in linear speed between the rubber rollers and the rice hulling rate. The coupling parameters characterize the degree to which changes in the difference in linear speed between the rubber rollers affect changes in the rice hulling rate.

[0027] Specifically, the coupling analysis submodule 122 first acquires the sequence of linear velocity differences between rubber rollers and the corresponding rice hulling rate sequence at multiple consecutive sampling times within a preset time window. Then, it analyzes the two sequences separately to obtain a first slope sequence of the linear velocity difference changing with time, and a second slope sequence of the hulling rate changing with time. Finally, based on the overall difference between the first and second slope sequences, the coupling relationship parameters are determined.

[0028] After obtaining the load fluctuation parameters and coupling relationship parameters, the probability calculation module 12 calculates the probability parameters based on the proportional relationship between the two and outputs the parameters to the regulation capability assessment module 13.

[0029] (3) Adjustment capacity assessment module 13.

[0030] The adjustment capability assessment module 13 is responsible for evaluating the adjustment performance and efficiency of the rice hulling and milling machine system to load disturbances. This module uses probability parameters, material flow rate changes and system response time for calculation.

[0031] Optionally, the regulation capability assessment module 13 is used to determine the regulation capability parameters of the rice huller based on the difference between the rice inflow rate and the rice outflow rate, probability parameters, and regulation response time. The regulation response time is the time from when the rice huller senses a load disturbance to when it triggers a regulation command.

[0032] For example, the regulation capability assessment module 13 may include a disturbance intensity calculation submodule 131 and a regulation evaluation submodule 132, which will be described below: (3.1) Disturbance intensity calculation submodule 131.

[0033] Optionally, the disturbance intensity calculation submodule 131 is used to determine the load disturbance intensity at each control trigger moment within a preset time window, based on the difference between the rice inflow velocity and the outflow velocity and the probability parameter.

[0034] Specifically, the disturbance intensity calculation submodule 131 first obtains the current rice inflow and outflow velocities from the data acquisition module 11. Then, it calculates the absolute value of the difference between the two. Finally, it multiplies this velocity difference by the probability parameter transmitted from the probability calculation module 12 to obtain the quantified current load disturbance intensity.

[0035] (3.2) Adjustment evaluation submodule 132.

[0036] Optionally, the adjustment evaluation submodule 132 is used to determine the adjustment degree evaluation value at the control trigger time based on the load disturbance intensity change at two adjacent control trigger times and the time interval between the two controls, and to obtain the adjustment capability parameter by integrating all evaluation values.

[0037] Specifically, the regulation evaluation submodule 132 first receives the load disturbance intensity calculated by the disturbance intensity calculation submodule 131 for two adjacent regulation cycles (e.g., the b-th and b-1-th cycles). Then, it calculates the percentage change in the load disturbance intensity between the two cycles and, combined with the time interval between the two regulation cycles (i.e., the regulation delay), calculates the regulation degree evaluation value for a single regulation cycle. Finally, it averages or comprehensively calculates the regulation degree evaluation values ​​for all regulation trigger times within a preset time window and outputs the regulation capability parameter, characterizing the overall regulation performance of the system, to the adaptive weight calculation module 14.

[0038] (4) Adaptive weight calculation module 14.

[0039] The adaptive weight calculation module 14 is responsible for comprehensively evaluating the interference of the environment and equipment status on the adjustment process, and calculating the adaptive control weights for the final control adjustment in combination with the system's own adjustment capabilities.

[0040] Optionally, the adaptive weight calculation module 14 is used to determine the environmental and state disturbance parameters based on the environmental and equipment state parameters, and to determine the adaptive control weight based on the adjustment capability parameters and the environmental and state disturbance parameters.

[0041] The adaptive weight calculation module 14 first determines the interference parameters based on environmental and equipment state parameters. Specifically, at each control trigger moment, the adaptive weight calculation module 14 calls the normal temperature and humidity baseline values ​​and the standard radius of the rubber roller from the historical database, compares them with the current average temperature and humidity and the current average radius of the rubber roller in the monitoring data, and calculates the factors reflecting environmental influences and the state difference values ​​reflecting equipment wear and vibration. Then, it averages the state difference values ​​of all control trigger moments within the preset time window to obtain the environmental and state interference parameters.

[0042] After obtaining the regulation capability parameters and environmental and state disturbance parameters, the adaptive weight calculation module 14 multiplies the two to obtain an initial regulation difference value. Finally, the adaptive weight calculation module 14 also obtains the deviation between the current rice transport flow rate and the historical normal flow rate, and uses this deviation to correct the initial regulation difference value. When the flow deviation is too large, the adaptive weight calculation module 14 reduces the final output adaptive regulation weight to eliminate interference caused by non-velocity difference factors such as material blockage. The calculated adaptive regulation weight is then sent to the proportional gain control module 15.

[0043] (5) Proportional gain control module 15.

[0044] The proportional gain control module 15 is the final execution unit of the system. It is responsible for dynamically adjusting the proportional gain value of the PID controller that controls the linear speed of the two rubber rollers according to the calculated adaptive control weight, so as to achieve precise and adaptive control of the speed difference of the rubber rollers.

[0045] Optionally, the proportional gain control module 15 is used to control the proportional gain value of the linear speed of the two rubber rollers according to the adaptive control weight.

[0046] Specifically, the proportional gain control module 15 first reads the current proportional gain value and the preset maximum adjustable range of the proportional gain value from the system controller. Simultaneously, it obtains the difference between the current operating power and the rated power of the rice hulling machine through a power sensor. Then, based on the sign of the power difference (indicating whether the load is too heavy or too light), the adaptive control weight from the adaptive weight calculation module 14, and the maximum adjustable range, the proportional gain control module 15 calculates the adjustment amount for the current proportional gain value. Finally, the proportional gain control module 15 generates a corrected new proportional gain value and sends it to the motor controller driving the two rubber rollers, completing the adjustment for one control cycle. The system runs periodically, and the corrected proportional gain value will be used as the initial value for the next control cycle.

[0047] The adaptive control system 10 and its included modules have been described above.

[0048] For example, such as Figure 2 The diagram shown is a flowchart illustrating an adaptive control method for operating a rice hulling machine according to an embodiment of the present invention, comprising the following steps: S201. Acquire monitoring data of the rice hulling and milling machine within a preset time window. The monitoring data includes the main motor power supply voltage, the difference in linear speed between the rubber rollers, the rice hulling rate, the rice inflow velocity, the rice outflow velocity, and environmental and equipment status parameters.

[0049] For example, this step can be performed by the data acquisition module 11 in the adaptive control system 10 described above.

[0050] Specifically, the data acquisition module 11 achieves synchronous acquisition of multi-source data through sensors and data interfaces integrated into the device. First, the data acquisition module 11 acquires the real-time value of the main motor's power supply voltage at fixed sampling intervals using an embedded intelligent acquisition unit connected to the output of the contactor or circuit breaker in the motor drive cabinet. Then, the data acquisition module 11 uses encoders installed at the ends of the two rubber roller shafts to synchronously acquire their rotational speeds and calculates the difference in linear velocity between the rollers based on their radii. Simultaneously, the data acquisition module 11 acquires the rice inflow and outflow velocities using speed sensors deployed at the inlet and outlet of the rubber rollers, respectively.

[0051] The collection of environmental and equipment status parameters includes: obtaining real-time temperature and humidity of the environment in which the equipment is located through temperature and humidity sensors; obtaining the mechanical vibration frequency of key parts of the equipment through vibration sensors; the radius information of the rubber roller can be calculated through a preset wear detection model or obtained by periodic input from the operation interface; the rice hulling rate is obtained by image analysis of the outgoing material through a machine vision system, specifically: collecting real-time images of the outgoing material, and based on the differences in color, texture, or shape between rice grains and rice, distinguishing between unhulled rice and hulled rice grains through image recognition algorithms, counting the total number of particles in the material, and then calculating the hulling rate based on the number of hulled rice grains and the total number of particles.

[0052] The data acquisition module 11 aligns and packages all the above data according to a unified voltage sampling time benchmark, forming a structured monitoring data set. Thus, by integrating hardware sensors and data interfaces, the data acquisition module 11 provides a synchronous, multi-dimensional, and high-precision profile of the system's operational status for subsequent analysis.

[0053] S202. Determine the probability parameters based on the main motor power supply voltage, the difference in linear speed between the rubber rollers, and the rice hulling rate. The probability parameters characterize the probability that the load fluctuation of the rice hulling machine is caused by the difference in linear speed between the rubber rollers.

[0054] For example, this step can be performed by the probability calculation module 12 in the adaptive control system 10 described above. Specifically, the probability calculation module 12 first calculates a load fluctuation parameter to quantify the severity of load fluctuation based on the fluctuation characteristics of the power supply voltage sequence within the time window. Then, the probability calculation module 12 analyzes the correlation between the changing trends of the linear speed difference sequence between the rubber rollers and the rice hulling rate sequence within the same time period, and calculates a coupling relationship parameter to characterize the degree of coupling between the two. Finally, the probability calculation module 12 calculates the final probability parameter based on the proportional relationship between the load fluctuation parameter and the coupling relationship parameter. It should be noted that the specific process of the aforementioned sub-steps can be found in S301-S303 below, and will not be repeated here.

[0055] In another possible implementation, when determining the probability parameters, the probability calculation module 12 can also directly calculate the pairwise correlation coefficients between the power supply voltage fluctuation variance, the linear velocity difference variance, and the shell removal rate variance within a preset time window, and integrate these correlation coefficients into a probability parameter that characterizes the correlation between load fluctuation and velocity difference through a preset weighted fusion rule.

[0056] Therefore, the probability calculation module 12 transforms the causal relationship between the complex load fluctuation phenomenon and the key process control variable (linear velocity difference) into a quantifiable probability value by integrating load fluctuation characterization and process parameter coupling analysis, providing a key basis for subsequent decision-making.

[0057] S203. Based on the difference between the inflow and outflow velocities of paddy rice, probability parameters, and control response time, determine the adjustment capability parameters of the rice hulling machine. The control response time is the time from when the rice hulling machine senses a load disturbance to when it triggers a control command.

[0058] For example, this step can be performed by the adjustment capability evaluation module 13 in the adaptive control system 10 described above. Specifically, the adjustment capability evaluation module 13 first calculates the load disturbance intensity at each system control trigger moment within a preset time window using the absolute difference between the inflow and outflow velocities of rice, combined with probability parameters. Then, the adjustment capability evaluation module 13 analyzes the change in load disturbance intensity between two adjacent control trigger moments, and, combined with the actual time interval between the two control commands, evaluates the adjustment effect and timeliness of a single control action, obtaining a single adjustment degree evaluation value. Finally, the adjustment capability evaluation module 13 synthesizes (e.g., takes the average) all single adjustment degree evaluation values ​​within the time window, outputting an adjustment capability parameter characterizing the overall system adjustment performance. It should be noted that the specific process of the aforementioned sub-steps can be found in S401-S403 below, and will not be repeated here.

[0059] In another possible implementation, when determining the regulation capability parameters of the rice huller, the regulation capability assessment module 13 can also, when calculating the evaluation value of a single regulation degree, not only consider the change in load disturbance intensity and response time, but also introduce an ideal disturbance intensity decay curve derived from historical data or theoretical models. By calculating the fitting degree between the actual disturbance intensity change and the ideal curve, the quality of each regulation action can be evaluated more precisely, thereby obtaining more accurate system regulation capability parameters.

[0060] Therefore, the regulation capability assessment module 13 objectively evaluates the dynamic performance of the control system's closed-loop regulation by quantitatively analyzing the system's actual suppression effect and response speed to load disturbances, providing important input for determining whether and how to adjust control parameters.

[0061] S204. Based on the environmental and equipment state parameters, determine the environmental and state disturbance parameters, and determine the adaptive control weights based on the regulation capability parameters and the environmental and state disturbance parameters. The environmental and state disturbance parameters characterize the degree of interference caused by environmental factors and equipment state on system regulation.

[0062] For example, this step can be executed by the adaptive weight calculation module 14 in the adaptive control system 10 described above. Specifically, it includes: First, at each control trigger moment, the adaptive weight calculation module 14 compares the current average temperature and humidity with the historical normal temperature and humidity benchmark to calculate the environmental impact factor; simultaneously, it calculates the state difference value at that moment by combining the deviation between the current average radius of the rubber roller and the standard radius, as well as the current mechanical vibration frequency. Then, it averages the state difference values ​​at all control trigger moments within the time window to obtain environmental and state disturbance parameters. Next, the adaptive weight calculation module 14 multiplies the adjustment capability parameter with the environmental and state disturbance parameters to obtain the original control difference value. Finally, the adaptive weight calculation module 14 obtains the deviation between the current rice conveying flow rate and the historical normal flow rate, and uses this deviation to correct the original control difference value. When the flow rate deviation is too large, the correction output value is reduced, thereby obtaining the final adaptive control weight. It should be noted that the specific process of the aforementioned sub-steps can be found in S501-S505 below, and will not be repeated here.

[0063] In another possible implementation, when determining the environmental and state disturbance parameters, the adaptive weight calculation module 14 can also preset different influence coefficients for temperature deviation, humidity deviation, rubber roller radius wear, and vibration frequency, respectively. It can directly calculate the state difference value at each moment by weighted summation, and then integrate all values ​​in the window to more flexibly reflect the differences in importance of different disturbance factors.

[0064] In another possible implementation, when determining the adaptive control weight, the adaptive weight calculation module 14 can also multiply the original control difference value by a decay factor that is negatively correlated with the continuous running time of the equipment (the longer the running time, the smaller the factor value) after correcting the original control difference value according to the flow deviation. This allows for conservative adjustment of control parameters under long-term operating conditions, avoiding over-control due to sensor drift or model accumulation errors.

[0065] Therefore, the adaptive weight calculation module 14 accurately quantifies and corrects the control strength required by the system by comprehensively evaluating external environmental interference, changes in the equipment's own state, and abnormal material conveying, and generates the core weight value that ultimately guides the adjustment of parameters.

[0066] S205. Adjust the proportional gain value of the linear speed of the two rubber rollers according to the adaptive adjustment weight.

[0067] For example, this step can be performed by the proportional gain control module 15 in the adaptive control system 10 described above, and specifically includes the following steps: (1) Obtain the maximum adjustable range of the proportional gain value and the difference between the current operating power and the rated power of the rice huller.

[0068] In this step, the proportional gain control module 15 reads the current proportional gain value and its maximum adjustable limit (i.e., the maximum adjustable range) from the configuration parameters of the system PID controller. Simultaneously, the proportional gain control module 15 obtains the real-time operating power of the main motor through the power measurement unit and compares it with the rated power on the equipment nameplate to calculate the power difference.

[0069] (2) Adjust the current proportional gain value according to the adaptive adjustment weight, the maximum adjustable range and the difference to obtain the corrected proportional gain value.

[0070] Furthermore, the proportional gain control module 15 first determines the sign of the power difference: if the current operating power is greater than the rated power (the difference is positive), it indicates that the current load is too heavy, and the control direction should be to reduce the proportional gain value to adjust it smoothly; otherwise, it indicates that the load is too light, and the proportional gain value should be increased to strengthen the adjustment.

[0071] Subsequently, the proportional gain control module 15 combines the adaptive control weight, the maximum adjustable range, and the direction of the power difference to calculate the specific adjustment amount. The absolute value of the adjustment amount is determined by both the adaptive control weight and the maximum adjustable range (the larger the weight, the closer the adjustment is to the maximum range), and the sign of the adjustment amount is determined by the direction of the power difference.

[0072] Finally, the proportional gain control module 15 adds the adjustment amount to the current proportional gain value to obtain a corrected new proportional gain value, and writes it into the PID controller, thereby changing the control output signal strength of the motors driving the two rubber rollers.

[0073] Thus, the proportional gain control module 15 transforms the abstract adaptive control weight into a specific and targeted adjustment of the core control parameter (proportional gain value), ultimately achieving closed-loop, adaptive, and precise control of the difference in linear speed of the rubber roller.

[0074] Based on the above technical solutions, this invention constructs a complete technical chain from multi-dimensional data perception, load fluctuation attribution analysis, system regulation performance evaluation, to environmental interference quantitative compensation, and finally achieves adaptive adjustment of control parameters. This enables the rice hulling mill to automatically respond to changes in the operating environment, material characteristics, and equipment status, and optimize the key process parameter of roller linear speed difference in real time. This effectively suppresses irregular and drastic fluctuations in load, stabilizes the equipment operation in the high-efficiency range, and ultimately achieves stability and improvement in rice hulling rate.

[0075] For example, in another adaptive control method for operating a rice hulling machine provided in one embodiment of the present invention, the probability parameter is determined based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate. Specifically, the method includes the following steps: S301. Determine the load fluctuation parameters of the rice hulling machine based on the changes in the main motor power supply voltage within a preset time window. The load fluctuation parameters characterize the severity of the load on the rice hulling machine.

[0076] Optionally, this step is performed by the load fluctuation analysis submodule 121 in the probability calculation module 12, and specifically includes the following steps: (1) Determine the first characteristic index based on the instantaneous slope of each pair of adjacent sampled values ​​of the main motor power supply voltage within a preset time window. The first characteristic index is used to characterize the fluctuation range of the main motor power supply voltage.

[0077] Specifically, the load fluctuation analysis submodule 121 first extracts a sequence of continuous sampled values ​​of the main motor supply voltage within a preset time window (e.g., one load fluctuation cycle, which can be 5 minutes) from the monitoring data. For each pair of adjacent sampled values ​​in this sequence, its instantaneous slope k is calculated, which is the ratio of the voltage change to the corresponding time interval. Assuming there are x+1 sampled values ​​in the window, x instantaneous slope values ​​can be obtained.

[0078] Next, the load fluctuation analysis submodule 121 calculates the absolute value of the difference between all adjacent instantaneous slopes, and averages these absolute values ​​to obtain the first characteristic index. B An example calculation formula is as follows: in, , These represent the instantaneous slopes between the i-th and (i+1)-th adjacent sampling points on the voltage curve, respectively. ε represents the absolute value of the slope difference between adjacent slopes in the c-th group; x represents the total number of slope difference groups; ε is a preset non-zero constant used to prevent the calculation from being unstable due to a zero difference. Its value range is, for example, between 0 and 0.1, and an empirical value of 0.01 can be taken.

[0079] Understandably, the above formula quantifies the fluctuation amplitude of the voltage curve by calculating the average absolute value of adjacent slope changes. The larger and more frequent the slope changes, the larger the B value, indicating a more significant voltage fluctuation amplitude.

[0080] (2) Determine the second characteristic index based on the time interval between all adjacent sampled values. The second characteristic index is used to characterize the fluctuation rate of the main motor power supply voltage.

[0081] Specifically, the load fluctuation analysis submodule 121 calculates the time interval between all adjacent sampling point pairs on the voltage curve. At a fixed sampling interval, the time interval between all adjacent sampled values ​​is equal, i.e. = This fixed sampling interval The load fluctuation analysis submodule 121 will average the sampling time interval, which determines the system's time resolution for sampling voltage fluctuations. Determined as = And as a second characteristic indicator. Second characteristic indicator Used to benchmark and characterize fluctuation rates. The smaller the value, the higher the system's time resolution, and the better it can capture and reflect rapid voltage fluctuations; conversely, The larger the value, the weaker the system's ability to capture rapid fluctuations. Therefore, in subsequent calculations, It will participate in the quantification of fluctuation rate through its reciprocal form.

[0082] (3) Determine the load fluctuation parameters based on the first characteristic index and the second characteristic index.

[0083] Furthermore, the load fluctuation analysis submodule 121 analyzes the load fluctuation based on the first characteristic index B and the second characteristic index B. Calculate the load fluctuation parameters Load fluctuation parameter A combines the amplitude (B) and rate (via) of voltage fluctuations. reflect, (The smaller the value, the larger this item is). The larger the A value, the more drastic and rapid the voltage fluctuations occurred within a unit of time, thus directly and comprehensively quantifying the degree of drastic load fluctuations of the rice hulling machine within that time window.

[0084] S302. Determine the coupling relationship parameters based on the difference in linear speed between the rubber rollers and the rice hulling rate. The coupling relationship parameters characterize the degree to which changes in the difference in linear speed between the rubber rollers affect the change in the rice hulling rate.

[0085] Optionally, this step is performed by the coupling analysis submodule 122 in the probability calculation module 12, and specifically includes the following steps: (1) Obtain the difference in linear velocity between rubber rollers and the corresponding rice hulling rate at multiple consecutive sampling times within a preset time window.

[0086] Specifically, the coupling analysis submodule 122 extracts the linear velocity difference sequence between rubber rollers and the rice hulling rate sequence, arranged chronologically within the same preset time window, from the synchronous monitoring data provided by the data acquisition module 11. These two sequences are strictly aligned in time, with each sampling moment having a corresponding set of linear velocity differences (denoted as...). , which is the difference between the linear speed of the fast roller and the linear speed of the slow roller) and the shelling rate (denoted as ). ).

[0087] (2) Determine the first slope sequence of the linear speed difference between the rubber rollers as a function of time, and the second slope sequence of the rice hulling rate as a function of time.

[0088] Furthermore, the coupling analysis submodule 122 analyzes the linear velocity difference sequence and the uncoating rate sequence respectively. For each sequence, the slope of the numerical change between two adjacent sampling points is calculated. For example, for the linear velocity difference sequence, the j-th slope... For the shelling rate sequence, the j-th slope Furthermore, the first slope sequence is obtained respectively. Second slope sequence , where n is the number of slopes.

[0089] (3) Determine the coupling parameters based on the first slope sequence and the second slope sequence.

[0090] For example, the coupling analysis submodule 122 determines the coupling parameter Z using the following formula: in, This represents the j-th slope of the peeling rate curve; Indicates the difference in linear velocity on the curve and The j-th slope within the same time interval; n represents the total number of slope pairs. It should be noted that the above formula calculates the absolute value of the difference between the slope of the change in the shelling rate and the slope of the change in the linear velocity difference at each moment, and then takes the average of these differences. This average value reflects the overall degree of deviation between the changing trends of the two parameters. The smaller the average value, the more synchronized and consistent the changing trends of the two parameters are, i.e., the better the coupling. Finally, the reciprocal of this average value is taken as the coupling relationship parameter Z. Therefore, the larger the Z value, the higher the degree of coupling between the change in the linear velocity difference and the change in the shelling rate, i.e., the more direct and significant the influence of the linear velocity difference on the shelling rate.

[0091] S303. Determine the probability parameters based on the load fluctuation parameters and coupling relationship parameters.

[0092] In this step, the probability calculation module 12 receives the load fluctuation parameter A and the coupling relationship parameter Z calculated by its internal sub-modules (load fluctuation analysis sub-module 121 and coupling analysis sub-module 122). Then, the probability calculation module 12 divides the load fluctuation parameter A by the coupling relationship parameter Z to calculate the probability parameter U=A / Z.

[0093] Understandably, the probability parameter U reflects the proportional relationship between the currently observed severe load fluctuation (A) and the ability (Z) of the core process parameter (linear velocity difference) to affect the shelling effect. If the load fluctuation is severe (large A), but at the same time the coupling between the linear velocity difference and the shelling rate is strong (large Z, meaning the shelling rate is sensitive to changes in the velocity difference), then the probability that the current load fluctuation is caused by an unreasonable linear velocity difference is relatively low (small U value). Conversely, if the load fluctuation is severe (large A) but the coupling is weak (small Z, meaning the shelling rate is not sensitive to changes in the velocity difference, and other factors may have a greater impact), then the probability that the load fluctuation is caused by the velocity difference is relatively high (large U value). Therefore, the U value is used as a probability parameter to characterize the load fluctuation caused by the linear velocity difference between the rubber rollers.

[0094] Based on the above technical solution, this invention, through step-by-step calculation of load fluctuation parameters and coupling relationship parameters, and finally synthesizing them into probability parameters, achieves quantitative analysis and probabilistic assessment of the causes of load fluctuations in rice hullers (whether they are caused by the difference in linear velocity, a core process parameter). This method transforms the causal relationship between complex equipment phenomena (load fluctuations) and key control variables (linear velocity difference) into calculable values, providing an objective and quantitative basis for subsequent adaptive control decisions. This allows for more accurate identification of the objects requiring regulation, avoiding blind adjustments.

[0095] For example, in another adaptive control method for operating a rice hulling machine provided in one embodiment of the present invention, the adjustment capability parameters of the rice hulling machine are determined based on the difference between the rice inflow velocity and the rice outflow velocity, the probability parameter, and the adjustment response time. Specifically, this includes the following steps: S401. At each control trigger moment within the preset time window, the load disturbance intensity at the current control trigger moment is determined based on the difference between the rice inflow rate and the outflow rate, as well as probability parameters.

[0096] It should be noted that the current control trigger moment specifically refers to the specific time point within the r-th preset time window when the system determines that the load is abnormal based on real-time monitoring data (such as load fluctuation parameter A, probability parameter U, etc.), and thus decides to adjust the control parameters and issue a control command.

[0097] Optionally, this step is performed by the disturbance intensity calculation submodule 131 in the adjustment capability assessment module 13.

[0098] Specifically, when the system detects an abnormal load and triggers a control command (referred to as the b-th control trigger time), the disturbance intensity calculation submodule 131 first obtains the average rice inflow velocity within a preset time window corresponding to the control trigger time from the synchronous monitoring data of the data acquisition module 11. and average velocity of rice outflow Then, the disturbance intensity calculation submodule 131 calculates the absolute value of the difference between the two and multiplies it by the probability parameter U from the probability calculation module 12 to obtain the load disturbance intensity at the current control trigger moment. The calculation formula is as follows: in, This represents the average speed at which the rice grains enter the space between the two rubber rollers during the analysis period corresponding to the bth control trigger time. This represents the average speed at which rice grains flow out of the two rubber rollers after being hulled within the same time period. ε represents the absolute value of the difference between the inflow and outflow velocities; U is a probability parameter characterizing the load fluctuation caused by the difference in linear velocity between the rubber rollers; ε is a preset non-zero constant used to prevent the difference from being zero, which would lead to calculation instability. Its value range is, for example, between 0 and 0.1, and an empirical value of 0.01 can be taken.

[0099] It should be noted that the difference between the inflow and outflow velocities of rice in the above formula directly reflects the influence of the working resistance between the rubber rollers on the material flow rate. The larger the difference, the greater the resistance, and the stronger the load disturbance directly caused by the working state of the rubber rollers. Simultaneously, this physical disturbance intensity is multiplied by the probability parameter U of the causal relationship, and the disturbance intensity is weighted by attribution. That is, when the probability parameter U is large (load fluctuations are very likely caused by velocity differences), the calculated load disturbance intensity... A change in the target control variable (linear velocity difference) is amplified, thus giving it greater importance in subsequent regulation; conversely, a decrease in its importance is diminished. This ensures that the assessment of subsequent regulatory capacity focuses on the main disturbances caused by the target control variable (linear velocity difference).

[0100] S402. Based on the load disturbance intensity at two adjacent control trigger times and the time interval between the two control actions, determine the adjustment degree evaluation value at the current control trigger time.

[0101] Optionally, this step is performed by the regulation evaluation submodule 132 in the regulation capacity assessment module 13.

[0102] Specifically, the adjustment evaluation submodule 132 first obtains the load disturbance intensity at two adjacent control trigger times, calculated by the disturbance intensity calculation submodule 131, that is, the disturbance intensity after the b-th control. and the intensity of the disturbance after the (b-1)th regulation Simultaneously, the time interval between the system's detection of the need for the b-th adjustment and the actual triggering of the b-th adjustment command is recorded as the adjustment response time. Subsequently, the regulation evaluation submodule 132 calculates the regulation degree evaluation value for the b-th regulation using a comprehensive evaluation function. For example, the degree of adjustment rating can be calculated using the following formula: in, , These represent the load disturbance intensity at the b-th and b-1-th control trigger times, respectively; This indicates the response time of the b-th adjustment; This represents the normalization function, which will... Map to the interval [0, 1].

[0103] It is understandable that in the above formula The "timeliness" and "effectiveness" of a single intervention were comprehensively considered. (Quantity) This reflects the system response delay; a larger normalized value indicates a longer relative delay and less timely intervention. (Component) This reflects the effectiveness of the control. A value closer to 1 indicates a smaller change in the disturbance intensity and a less significant control effect; a value less than 1 indicates a weakened disturbance and effective control; a value greater than 1 indicates an enhanced disturbance and the possibility of counterproductive control. Multiplying the two values ​​yields... The larger the value, the longer the delay in the adjustment and the poorer the effect (the disturbance is not significantly reduced or even enhanced), that is, the degree of single adjustment is poor.

[0104] It should be noted that for the initial control trigger moment (i.e., b=1), since there is no previous load disturbance intensity... Therefore, the degree of adjustment evaluation value is not calculated. .

[0105] S403. Determine the regulation capability parameters based on the regulation degree evaluation values ​​of all regulation trigger times within the preset time window.

[0106] Furthermore, the adjustment evaluation submodule 132 calculates the adjustment degree evaluation value at each adjustment trigger time within a preset time window (e.g., the r-th window). After (b=1, 2, ..., m; m is the total number of adjustments within the window), a comprehensive calculation is performed on all evaluation values ​​to characterize the overall adjustment capability of the system within that time window. For example, the average of all evaluation values ​​is calculated as the adjustment capability parameter D, using the following formula: Where m represents the total number of times the system triggers control commands within the preset time window. In particular, if the total number of control triggers m=1 within the window, the control level evaluation value cannot be calculated. In this case, the control capability parameter D can be set to the preset default value (e.g., 1.0), indicating that the system control capability cannot be evaluated within the current window and is handled according to the worst-case scenario.

[0107] It should be noted that the regulation capability parameter D is the average performance of all effective single-action regulation within the window. If multiple regulation... A generally large D value (meaning long adjustment delay and poor effect) indicates a large average value D, suggesting poor overall adaptive adjustment capability of the system within the entire time window, and low efficiency in self-correction and load stabilization. Conversely, a small D value indicates a rapid and effective system adjustment response and strong overall adjustment capability.

[0108] Based on the above technical solution, this invention achieves an objective evaluation of the dynamic adjustment performance of the rice hulling machine control system by quantifying the response delay and effect changes of a single adjustment and statistically analyzing the average performance within a window. This method not only focuses on whether the adjustment is executed but also more precisely evaluates the timeliness and effectiveness of the adjustment. The resulting adjustment capability parameters truly reflect the robustness and agility of the system's closed-loop control, providing crucial performance data for subsequently determining whether and how to adjust the controller's core parameters (proportional gain).

[0109] For example, in another adaptive control method for operating a rice hulling machine provided in one embodiment of the present invention, the environmental and equipment state parameters include: ambient temperature and humidity, the mechanical vibration frequency of the rice hulling machine, and the radii of the two rubber rollers. Furthermore, based on the environmental and equipment state parameters, environmental and state disturbance parameters are determined, specifically including the following steps: S501. At each control trigger moment within the preset time window, determine the environmental impact factor based on the first deviation between the current average temperature and the historical normal temperature, and the second deviation between the current average humidity and the historical normal humidity.

[0110] It should be noted that the current control trigger time is consistent with the meaning defined in step S401. Specifically, it refers to the specific time point within the r-th preset time window when the system judges the load abnormality based on real-time monitoring data (such as load fluctuation parameter A, probability parameter U, etc.), thereby deciding to adjust the control parameters and issue a control command.

[0111] In this step, the adaptive weight calculation module 14 first acquires all temperature sampling values ​​of the device within the r-th preset time window, from the time after the (b-1)th adjustment to the time before the b-th adjustment is triggered, and calculates the arithmetic mean of these temperature sampling values ​​to obtain the average temperature value for this time period. Simultaneously, all humidity samples within the same time period are acquired, and the arithmetic mean of these humidity samples is calculated to obtain the average humidity value for that time period. Furthermore, the adaptive weight calculation module 14 retrieves the arithmetic mean of all temperature samples recorded by the device under normal and stable operating conditions from the system's historical operation database as the baseline average temperature value. The average humidity value, as a benchmark, is the arithmetic mean of all humidity samples. Next, the absolute deviation between the current value and the benchmark value is calculated, and the two deviation values ​​are multiplied to obtain the environmental impact factor at the time of triggering this regulation. The calculation formula is as follows: in, , These represent the average temperature of the equipment and the average humidity of the environment during the current time period, respectively. , These represent the average temperature and average humidity values ​​under normal operating conditions in historical records, respectively; ε is a preset non-zero constant used to prevent the difference from being zero, which would lead to calculation instability. Its value range is, for example, between 0 and 0.1, and an empirical value of 0.01 can be taken. This represents the normalization function.

[0112] Understandably, the above formulas quantify the degree of deviation of temperature and humidity from ideal conditions, respectively. The absolute value of the temperature deviation... (That is, the first deviation) reflects the potential impact of equipment heating or ambient temperature on the performance of sensors and electrical components; the absolute value of humidity deviation (This is also known as the second bias) reflects the potential impact of environmental humidity on the physical properties of rice. The result is obtained by normalizing the two and then multiplying them. The value comprehensively characterizes the intensity of interference generated by the combined effects of temperature and humidity on the system's sensing and regulation processes. The larger the value, the further the environmental conditions deviate from the normal value, and the stronger the interference to the system.

[0113] S502. Based on the environmental impact factor, the third deviation between the average radius of the rubber roller and the standard radius, and the mechanical vibration frequency, determine the state difference value at the current control trigger moment.

[0114] Specifically, after calculating the environmental impact factor, the adaptive weight calculation module 14 obtains the average radius of the two rubber rollers within the same time period. and the mechanical vibration frequency of the rice hulling machine. At the same time, the average standard radius of the two rubber rollers was obtained from the equipment's factory specifications. For example, the adaptive weight calculation module 14 calculates the state difference value at the current control trigger moment according to the following formula: in, This represents the state difference value at the current time of the control trigger; This represents the environmental impact factor calculated in step S501; This represents the average standard radius of the rubber roller at the time of manufacture. This represents the average radius of the two rubber rollers within the current time period; This represents the absolute value of the radius change caused by roller wear (i.e., the third deviation). This represents the mechanical vibration frequency of the equipment during the current time period; ε is a preset non-zero constant used to prevent the difference from being zero, which would lead to unstable calculations. Its value range is, for example, between 0 and 0.1, and an empirical value of 0.01 can be taken.

[0115] It should be noted that the state difference value in the above formula It consists of three multiplied parts, used to comprehensively quantify the interference of the equipment's own state on the regulation performance. Part One This represents the basis of environmental interference. Part Two. This represents the degree of wear on the rubber roller. Greater wear (smaller radius) results in a lower linear speed at the same rotational speed, directly impacting the descrambling process and representing irreversible equipment degradation. Part Three This represents the intensity of mechanical vibration; severe vibration can interfere with sensor readings and control stability. Multiplying these three factors means that the state difference value only increases under abnormal environmental conditions, when the rubber rollers are worn, and the equipment vibrates strongly. This will significantly increase, which accurately reflects the comprehensive interference caused by the coupling effect of multiple unfavorable equipment states on the system's adaptive adjustment.

[0116] S503. Determine the environmental and state interference parameters based on the state difference values ​​of all control trigger times within the preset time window.

[0117] Furthermore, the adaptive weight calculation module 14 obtains the state difference value at each adjustment trigger moment within the r-th preset time window. After (b=1, 2, ..., m), these values ​​are averaged to obtain the environmental and state disturbance parameters for this window. , that is , where m represents the total number of times the system triggers control commands within the preset time window.

[0118] Understandably, the environmental and state disturbance parameter Q represents the average level of disturbances experienced at all control moments within the window. By averaging, the occasional fluctuations of a single measurement can be smoothed out, resulting in a stable average level of disturbance to the system's control function caused by the combined effects of environmental factors and the equipment's own condition (wear, vibration) throughout the entire time window. A larger Q value indicates that the system is operating under relatively harsh comprehensive conditions during that time period, and its adaptive control baseline performance is under greater challenge.

[0119] S504. Determine the original control difference value based on the regulation capability parameter, environmental and state disturbance parameters.

[0120] For example, the adaptive weight calculation module 14 obtains the regulation capability parameter D, which characterizes the system's own regulation performance, from the regulation capability assessment module 13, and multiplies it with the environmental and state disturbance parameter Q calculated by this module to obtain the original regulation difference value R, i.e., R=Q×D.

[0121] It should be noted that the initial control difference value R integrates both "internal factors" and "external factors." The regulation capability parameter D is the "internal factor," reflecting the inherent inadequacy of the control system's closed-loop performance. The environmental and state disturbance parameter Q is the "external factor," reflecting the limitations imposed by objective conditions on control performance. Multiplying the two means that when the system's inherent regulation capability is poor (large D) and it is under strong disturbance conditions (large Q), the overall misalignment exhibited by the system will be significantly amplified (large R). The initial control difference value R preliminarily quantifies the degree to which the system currently deviates from the ideal adaptive state and forms the basis for calculating the final control weights.

[0122] S505. Obtain the fourth deviation between the current rice transport flow rate and the historical normal flow rate, and correct the original control difference value based on the fourth deviation to obtain the adaptive control weight.

[0123] Finally, the adaptive weight calculation module 14 obtains the average flow rate of rice delivered by the system within the r-th preset time window. And the average rice transport flow rate under normal operating conditions retrieved from historical databases. Next, the absolute deviation between the current flow and the normal flow (i.e., the fourth deviation) is calculated, and the original control difference value R is corrected based on this deviation to obtain the final adaptive control weight. For example, The calculation formula is as follows: Where R represents the original regulation difference value; I This represents the average transport flow rate of rice within the current time window; This represents the average conveying flow rate under historical normal operating conditions. Represents the absolute value of the flow deviation; This represents a normalization function that maps the values ​​of the parameters within the parentheses to the interval [0, 1].

[0124] It should be noted that the core correction factor in the above formula is In deviation When the value is 0, the value of the fraction is 1, at which point the weights are adaptively adjusted. The flow rate is entirely determined by the original control difference value R, meaning no additional correction is made when the flow rate is normal; at the current transport flow rate I Significantly deviating from normal values When the flow rate is too high, causing blockage between rollers, the absolute value of the deviation will be very large, resulting in a very small correction factor, which in turn significantly reduces the final calculated weight. This is because the load fluctuations caused by abnormal flow are not fundamentally due to an unreasonable difference in the linear speed of the rubber rollers, but rather to a problem with the material input. Such problems should be resolved by adjusting the feed rate, not by over-adjusting the speed difference control parameters. Through this correction, the system can identify and eliminate interference caused by non-target reasons (abnormal material flow), ensuring the final adaptive control weights. This primarily reflects the control requirements driven by the target cause (unreasonable roller speed difference and its influence by environmental / equipment conditions). Weighting The larger the value, the greater the urgency and intensity of the system's adjustment of the proportional gain value.

[0125] Based on the above technical solution, this invention quantifies various factors such as environmental interference, equipment condition deterioration, and abnormal material flow in a hierarchical manner, and then integrates and corrects them to ultimately generate a precise adaptive control weight. This method not only identifies internal and external factors affecting regulation performance, but more importantly, through flow correction logic, it distinguishes load fluctuations from different sources, ensuring that the control system's adjustment actions always focus on resolving issues related to its core control variable (the difference in rubber roller linear speed). This significantly improves the targeting and effectiveness of adaptive control, avoiding misadjustment and overadjustment.

[0126] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. An adaptive control method for the operation of a rice hulling and milling machine, characterized in that, The method includes: Acquire monitoring data of the rice hulling and milling machine within a preset time window; wherein, the monitoring data includes the main motor power supply voltage, the difference in linear speed between the rubber rollers, the rice hulling rate, the rice inflow speed, the rice outflow speed, and environmental and equipment status parameters; The probability parameter is determined based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate; wherein, the probability parameter is used to characterize the probability that the load fluctuation of the rice hulling machine is caused by the linear speed difference between the rubber rollers; The adjustment capability parameters of the rice hulling machine are determined based on the difference between the rice inflow velocity and the rice outflow velocity, the probability parameter, and the control response time; wherein, the control response time is the time from when the rice hulling machine senses a load disturbance to when it triggers a control command. Based on the environmental and equipment state parameters, environmental and state disturbance parameters are determined, and adaptive control weights are determined based on the adjustment capability parameters and the environmental and state disturbance parameters; wherein, the environmental and state disturbance parameters are used to characterize the degree of interference caused by environmental factors and equipment state to the system adjustment; The proportional gain value of the linear speed of the two rubber rollers is adjusted according to the adaptive adjustment weight.

2. The adaptive control method for the operation of a rice hulling and milling machine according to claim 1, characterized in that, The probability parameters are determined based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate, specifically including: The load fluctuation parameters of the rice hulling machine are determined based on the change of the main motor power supply voltage within the preset time window; wherein, the load fluctuation parameters are used to characterize the severity of the load on the rice hulling machine. Based on the linear velocity difference between the rubber rollers and the rice dehulling rate, a coupling relationship parameter is determined; wherein, the coupling relationship parameter is used to characterize the degree of influence of the change in the linear velocity difference between the rubber rollers on the change in the rice dehulling rate; The probability parameter is determined based on the load fluctuation parameter and the coupling relationship parameter.

3. The adaptive control method for the operation of a rice hulling and milling machine according to claim 2, characterized in that, Based on the variation of the main motor power supply voltage within the preset time window, the load fluctuation parameters of the rice hulling and milling machine are determined, specifically including: A first characteristic index is determined based on the instantaneous slope of each pair of adjacent sampled values ​​of the main motor power supply voltage within the preset time window; wherein, the first characteristic index is used to characterize the fluctuation amplitude of the main motor power supply voltage. A second characteristic index is determined based on the time interval between all adjacent sampled values; wherein the second characteristic index is used to characterize the fluctuation rate of the main motor power supply voltage; The load fluctuation parameters are determined based on the first characteristic index and the second characteristic index.

4. The adaptive control method for the operation of a rice hulling and milling machine according to claim 2, characterized in that, Based on the linear velocity difference between the rubber rollers and the rice hulling rate, the coupling relationship parameters are determined, specifically including: Obtain the linear velocity difference between the rubber rollers and the corresponding rice dehulling rate at multiple consecutive sampling moments within the preset time window; The first slope sequence of the linear velocity difference between the rubber rollers as a function of time, and the second slope sequence of the rice hulling rate as a function of time, are determined respectively. The coupling relationship parameters are determined based on the first slope sequence and the second slope sequence.

5. The adaptive control method for operating a rice hulling and milling machine according to claim 1, characterized in that, Based on the difference between the rice inflow velocity and the rice outflow velocity, the probability parameter, and the control response time, the adjustment capability parameters of the rice hulling machine are determined, specifically including: At each control trigger moment within the preset time window, the load disturbance intensity at the current control trigger moment is determined based on the difference between the rice inflow rate and the outflow rate and the probability parameter. The adjustment level evaluation value at the current adjustment trigger moment is determined based on the load disturbance intensity at two adjacent adjustment trigger moments and the time interval between the two adjustments. The adjustment capability parameter is determined based on the adjustment degree evaluation value of all adjustment trigger times within the preset time window.

6. The adaptive control method for operating a rice hulling and milling machine according to claim 1, characterized in that, The environmental and equipment status parameters include: ambient temperature and humidity, mechanical vibration frequency of the rice hulling machine, and the radius of the two rubber rollers; based on the environmental and equipment status parameters, environmental and status interference parameters are determined, specifically including: At each adjustment trigger time within the preset time window, environmental impact factors are determined based on the first deviation between the current average temperature and the historical normal temperature, and the second deviation between the current average humidity and the historical normal humidity. Based on the environmental impact factor, the third deviation between the average radius of the rubber roller and the standard radius, and the mechanical vibration frequency, determine the state difference value at the current control trigger moment; The environmental and state interference parameters are determined based on the state difference values ​​of all control trigger times within the preset time window.

7. The adaptive control method for the operation of a rice hulling and milling machine according to claim 1, characterized in that, The adaptive control weights are determined based on the regulation capability parameters and the environmental and state disturbance parameters, specifically including: The original regulation difference value is determined based on the regulation capability parameter and the environmental and state disturbance parameters; The fourth deviation between the current rice transport flow rate and the historical normal flow rate is obtained, and the original control difference value is corrected according to the fourth deviation to obtain the adaptive control weight.

8. The adaptive control method for operating a rice hulling and milling machine according to claim 1, characterized in that, Based on the aforementioned adaptive control weights, the proportional gain value of the linear speeds of the two rubber rollers is adjusted, specifically including: Obtain the maximum adjustable range of the proportional gain value and the difference between the current operating power and the rated power of the rice hulling machine; Based on the adaptive adjustment weight, the maximum adjustable range, and the difference, the current proportional gain value is adjusted to obtain the corrected proportional gain value.

9. The adaptive control method for operating a rice hulling and milling machine according to any one of claims 1-8, characterized in that, The method further includes: During the operation of the rice hulling and milling machine, the corrected proportional gain value calculated based on the monitoring data of the current preset time window is used as the initial proportional gain value for adjustment in the next preset time window.

10. An adaptive control system for the operation of a rice hulling and milling machine, characterized in that, The system includes: a data acquisition module, a probability calculation module, a regulation capability assessment module, an adaptive weight calculation module, and a proportional gain control module; The data acquisition module is used to acquire monitoring data of the rice hulling and milling machine within a preset time window; wherein, the monitoring data includes the main motor power supply voltage, the difference in linear speed between the rubber rollers, the rice hulling rate, the rice inflow speed, the rice outflow speed, and environmental and equipment status parameters. The probability calculation module is used to determine the probability parameter based on the main motor power supply voltage, the linear speed difference between the rubber rollers, and the rice hulling rate; wherein, the probability parameter is used to characterize the probability that the load fluctuation of the rice hulling machine is caused by the linear speed difference between the rubber rollers; The regulation capability assessment module is used to determine the regulation capability parameters of the rice hulling machine based on the difference between the rice inflow rate and the rice outflow rate, the probability parameter, and the regulation response time; wherein, the regulation response time is the time from when the rice hulling machine senses a load disturbance to when it triggers a regulation command. The adaptive weight calculation module is used to determine environmental and state interference parameters based on the environmental and equipment state parameters, and to determine adaptive control weights based on the adjustment capability parameters and the environmental and state interference parameters; wherein, the environmental and state interference parameters are used to characterize the degree of interference caused by environmental factors and equipment state to the system adjustment; The proportional gain control module is used to control the proportional gain value of the linear speed of the two rubber rollers according to the adaptive control weight.

Images