Rice mill control method and system based on voltage detection

Abstract

The invention discloses a rice husking machine control method and system based on voltage detection, relates to the technical field of grain processing, and discloses the rice husking machine control method and system based on voltage detection, by collecting voltage signals of a main motor to extract characteristic parameters, and combining with a pre-training model to dynamically adjust operation parameters of a rice husking machine, the rice husking machine control method and system based on voltage detection can improve the rice husking efficiency. The problems that a traditional method is low in monitoring precision and lagged in response are solved, the processing effect can be improved, and the method has the advantages that the rice milling efficiency is improved, the broken rice rate is reduced, and the self-adaptive capacity of equipment is enhanced.

Description

Technical Field

[0001] The present application relates to the field of grain processing technology, and in particular to a rice milling machine control method and system based on voltage detection. Background Art

[0002] In the grain processing industry, rice mills are crucial processing equipment, and their performance stability and efficiency directly impact the quality and yield of the final product. Traditional rice mill control methods rely heavily on manual experience or simple sensor feedback, making it difficult to achieve precise load control and intelligent regulation. This not only wastes energy and increases processing costs, but also compromises rice milling performance.

[0003] Existing technologies primarily monitor the load status of rice mills using mechanical pressure sensors or current detection devices. These methods suffer from issues such as delayed response and insufficient measurement accuracy. Particularly when processing rice with varying moisture contents, traditional methods are unable to accurately identify changes in material properties, leading to delayed adjustment of milling parameters, which can easily cause an increase in broken rice or uneven milling. Furthermore, when abnormal operating conditions occur, such as material blockage or equipment overload, existing control systems often lack effective early warning and automatic adjustment mechanisms, requiring manual intervention to restore normal operation, severely impacting production efficiency and equipment life.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the invention

[0005] The main purpose of this application is to provide a rice milling machine control method and system based on voltage detection, aiming to improve the processing effect of the rice milling machine.

[0006] To achieve the above objectives, the present application proposes a rice milling machine control method based on voltage detection, wherein the rice milling machine includes a grinding mechanism, the grinding mechanism includes a grinding roller and a main motor connected to the grinding roller, and the method includes:

[0007] collecting terminal voltage signals of the main motor to generate raw voltage data;

[0008] Preprocessing the raw voltage data to obtain corresponding preprocessed data;

[0009] Extracting the voltage mean, voltage fluctuation amplitude, and high-frequency energy ratio from the preprocessed data to generate corresponding voltage characteristic data;

[0010] Inputting the voltage characteristic data into a pre-trained load prediction model to output rice milling load state parameters;

[0011] Adjust the feeding speed of the rice milling machine and the gap of the milling roller according to the rice milling load state parameters.

[0012] In one embodiment, the step of collecting the terminal voltage signal of the main motor to generate the original voltage data includes:

[0013] Collect the three-phase terminal voltages of the main motor through a voltage sensor at a preset sampling frequency to generate original voltage waveform data;

[0014] Perform moving average noise reduction processing on the original voltage waveform data to obtain the noise-reduced voltage data;

[0015] Perform AD conversion on the noise-reduced voltage data to generate a digital voltage sequence as the original voltage data.

[0016] In one embodiment, the step of preprocessing the original voltage data to obtain corresponding preprocessed data includes:

[0017] Use a Butterworth low-pass filter to smooth the original voltage data, segment it according to a fixed-duration window, and extract the effective voltage range of each data segment;

[0018] Perform normalization processing on the segmented data to eliminate the dimensional difference caused by the voltage amplitude fluctuating with the power supply;

[0019] Compensate for the sensor sampling delay through a time series alignment algorithm to generate time-synchronized preprocessed data.

[0020] In one embodiment, the step of extracting the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio from the preprocessed data to generate corresponding voltage feature data includes:

[0021] Calculate the arithmetic mean value of the preprocessed data within a preset time window to generate the voltage mean value;

[0022] Calculate the difference between the maximum value and the minimum value of the preprocessed data within a preset time window to generate the voltage fluctuation amplitude;

[0023] Perform wavelet transform decomposition on the preprocessed data to extract the high-frequency components, calculate the energy value of the high-frequency components within a preset time window and the total energy value within the preset time window to determine the high-frequency energy ratio;

[0024] Combine the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio to form the voltage feature data.

[0025] In one embodiment, the rice milling load state parameters include the milling pressure demand level and the estimated value of the paddy moisture content, and the method further includes:

[0026] Collect a historical data set, where the historical data set includes voltage characteristic data, measured milling pressure levels, and paddy moisture content data, to form a training sample set;

[0027] Construct a dual-branch neural network model, including a first fully-connected network branch for outputting the required milling pressure level when inputting voltage mean data and fluctuation amplitude data, and a second convolutional network branch for outputting an estimated paddy moisture content value when inputting the proportion of high-frequency energy data;

[0028] Optimize the parameters of the dual-branch neural network model through the backpropagation algorithm until the error between the required milling pressure level and the estimated paddy moisture content value output by the dual-branch neural network model and the measured values in the training sample set reaches below a preset threshold;

[0029] Use the optimized dual-branch neural network model as the load prediction model.

[0030] In one embodiment, the rice mill further includes a feed motor; the step of adjusting the feed speed of the rice mill and the gap of the milling roller according to the rice milling load state parameters includes:

[0031] Query a preset pressure-speed mapping table according to the required milling pressure level of the rice milling load state parameters to generate a corresponding feed motor speed control signal to adjust the feed speed;

[0032] Determine the gap compensation amount of the milling roller according to the estimated paddy moisture content value in the rice milling load state parameters, and generate a corresponding milling roller displacement control signal to adjust the gap of the milling roller.

[0033] In one embodiment, the method further includes:

[0034] Determine the maximum allowable load current, and apply the milling pressure at equal interval pressure levels within the range from no load to full load of the rice mill, and record the steady-state load current of the feed motor under the corresponding required milling pressure level;

[0035] Calculate the speed ratio coefficient corresponding to each required milling pressure level according to the following formula:

[0036] ;

[0037] where, represents the required milling pressure level; represents at the speed ratio coefficient at the required milling pressure level of level; represents the maximum allowable load current; represents at the steady-state load current of the motor at the required milling pressure level of level;

[0038] Determine the rotational speed of the feed motor according to the rotational speed proportionality coefficient corresponding to the milling pressure demand level, which specifically includes:

[0039] Determine the rotational speed of the feed motor according to the following formula:

[0040] ;

[0041] Wherein, represents the rotational speed of the feed motor; represents the rotational speed proportionality coefficient; represents the rated rotational speed of the feed motor;

[0042] Establish the corresponding relationship between the milling pressure demand level and the rotational speed of the feed motor to construct the preset pressure-rotational speed mapping table.

[0043] In one embodiment, the method further includes:

[0044] When the measured load current is greater than the steady-state load current at a certain milling pressure demand level, correct the rotational speed according to the following formula:

[0045] ;

[0046] Wherein, represents the corrected rotational speed; represents the rotational speed of the feed motor; represents the measured load current, represents the maximum allowable load current; represents at the steady-state load current of the motor at the nth milling pressure demand level.

[0047] In one embodiment, the step of determining the gap compensation amount of the milling roller according to the estimated value of the paddy moisture content in the rice milling load state parameters includes:

[0048] When the estimated paddy moisture content is greater than the preset first threshold and less than the preset second threshold, determine that the gap compensation amount of the milling roller is 0;

[0049] When the estimated paddy moisture content is less than the preset first threshold, determine that the gap compensation amount of the milling roller is 0.1 mm;

[0050] When the estimated paddy moisture content is greater than the preset second threshold and less than the preset third threshold, determine that the gap compensation amount of the milling roller is 0.2 mm;

[0051] When the estimated moisture content of the paddy rice is greater than a preset third threshold, determine that the gap compensation amount of the milling roller is 0.3 mm; wherein, the preset first threshold is less than the preset second threshold, and the preset second threshold is less than the preset third threshold.

[0052] In one embodiment, the method further includes:

[0053] Calculate the voltage change rate based on the original voltage data;

[0054] Collect the current data of the main motor and calculate the current change rate;

[0055] When the current change rate is greater than the preset current change rate and the voltage change rate is less than the preset voltage change rate, control the feeding motor speed to decrease by a preset speed and control the roller gap to increase by a preset distance;

[0056] If after a continuous preset duration, the current change rate remains greater than the preset current change rate and the voltage change rate remains less than the preset voltage change rate, then control the milling roller to reverse.

[0057] In addition, to achieve the above object, the present application also proposes a rice milling machine control system based on voltage detection, the system includes: a memory, a processor, and a rice milling machine control program based on voltage detection stored on the memory and executable on the processor, the rice milling machine control program based on voltage detection is configured to implement the steps of the rice milling machine control method based on voltage detection.

[0058] A rice milling machine control method and system based on voltage detection provided by the present application extracts characteristic parameters by collecting the voltage signal of the main motor, and dynamically adjusts the operating parameters of the rice milling machine in combination with a pre-trained model, solving the problems of low monitoring accuracy and response lag in traditional methods, being able to provide processing effects, and having the advantages of improving rice milling efficiency, reducing the broken rice rate, and enhancing the equipment's adaptability. Description of the Drawings

[0059] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0060] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0061] Figure 1 It is a flowchart provided for an embodiment of the rice milling machine control method based on voltage detection of the present application;

[0062] Figure 2 For this application Figure 1 is a detailed process schematic diagram of step S100 in it;

[0063] Figure 3 For this application Figure 1 is a detailed process schematic diagram of step S200 in it;

[0064] Figure 4 For this application Figure 1 is a detailed process schematic diagram of step S300 in it;

[0065] Figure 5 is a process schematic diagram provided for another embodiment of the rice milling machine control method based on voltage detection in this application;

[0066] Figure 6 For this application Figure 1 is a detailed process schematic diagram of step S500 in it;

[0067] Figure 7 For this application Figure 6 is a detailed process schematic diagram of step S520 in it;

[0068] Figure 8 is a process schematic diagram provided for another embodiment of the rice milling machine control method based on voltage detection in this application;

[0069] Figure 9 is a structural schematic diagram provided for an embodiment of the rice milling machine control system based on voltage detection in this application.

[0070] Explanation of the reference numerals in the drawings:

[0071] 10. Memory; 20. Processor.

[0072] The realization of the purpose, functional characteristics and advantages of this application will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0073] Next, the technical solutions in this application will be clearly and completely described in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. The components of this application usually described and illustrated in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of this application to be protected, but only represents the selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative efforts belong to the scope of protection of this application.

[0074] It should be understood that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0075] In the prior art, the control of traditional rice milling machines mainly relies on the experience adjustment of operators or the feedback of single sensors, resulting in the problem of insufficient accuracy in perceiving the load state. When the material characteristics change or equipment wear occurs, manual adjustment has hysteresis, which easily leads to the imbalance between the milling pressure and the material supply, causing equipment overload or insufficient milling. In a certain grain processing workshop, due to the sudden change in the moisture content of paddy rice and the failure to adjust the roller gap in time, the rice milling machine continuously exceeded the broken rice rate standard and the motor overheated and stopped, resulting in a large amount of raw material waste.

[0076] To solve the above problems, the R & D personnel found that the terminal voltage signal of the main motor contains load state information. Through analysis, it is found that there is a correlation between the voltage mean value and the milling pressure, the voltage fluctuation amplitude reflects the stability of material flow, and the change in the energy of the high-frequency component can characterize the difference in paddy hardness. Thus, a technical idea is formed: to construct a multi-dimensional feature system of voltage signals, use a machine learning model to establish a mapping relationship between voltage features and load states, and achieve dynamic closed-loop control.

[0077] Therefore, the present application proposes a control method for a rice milling machine based on voltage detection. The rice milling machine includes a milling mechanism, and the milling mechanism includes a milling roller and a main motor drivingly connected to the milling roller. Refer to Figure 1 , the method includes steps S100 to S500, where:

[0078] Step S100, collect the terminal voltage signal of the main motor to generate original voltage data;

[0079] Step S200, preprocess the original voltage data to obtain corresponding preprocessed data;

[0080] Step S300, extract the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio from the preprocessed data to generate corresponding voltage feature data;

[0081] Step S400, input the voltage feature data into a pre-trained load prediction model to output rice milling load state parameters;

[0082] Step S500, adjust the feeding speed of the rice milling machine and the gap of the milling roller according to the rice milling load state parameters.

[0083] In this embodiment, the average voltage refers to the average level of the voltage signal within a preset time window, which can be calculated by a moving average algorithm and is used to reflect the overall load level of the milling pressure. The voltage fluctuation amplitude refers to the peak-to-valley difference of the voltage signal within the time window, which can be obtained by range calculation and is used to characterize the stability of material flow during the milling process. The high-frequency energy ratio refers to the energy ratio of the high-frequency component after wavelet decomposition of the voltage signal, which can be achieved by fast wavelet transform and is used to identify the transient impact characteristics caused by changes in paddy moisture content. The load prediction model refers to a dual-branch neural network trained with historical data, where the convolutional network branch processes the high-frequency energy characteristics, and the fully connected network processes the mean and fluctuation characteristics to achieve the joint prediction of milling pressure and moisture content.

[0084] Specifically, during the operation of the rice mill, the voltage sensor continuously collects the voltage signal at the main motor end with a fixed sampling frequency. After the original signal is filtered by a low-pass filter to eliminate high-frequency interference, the influence of grid voltage fluctuation is eliminated through normalization processing. The preprocessed data is segmented into time windows, and the average voltage, fluctuation amplitude, and high-frequency energy ratio within the windows are calculated synchronously. These three types of features are fused and analyzed through a neural network model to output the milling pressure demand level and the estimated value of paddy moisture content. The control system retrieves the preset speed mapping table according to the pressure level to control the feeding speed, and at the same time calculates the roller gap compensation amount based on the estimated moisture content value, and adjusts the milling pressure in real time through the servo mechanism.

[0085] Compared with the prior art, the traditional method relies on a single current sensor or vibration sensor to judge the load state and cannot distinguish the influence of changes in milling pressure and material characteristics. However, this solution can simultaneously capture the information of load intensity and material characteristic changes through multi-dimensional voltage feature extraction, and combines a dual-branch neural network to achieve accurate state recognition. In the prior art, the adjustment method based on threshold alarm has a response lag, and this solution realizes feedforward control through a prediction model, significantly improving the adjustment timeliness.

[0086] Through the above technical solution, this application effectively solves the problem of low load recognition accuracy of traditional control methods. The load prediction model based on multi-dimensional feature analysis of voltage signals can accurately distinguish the combined influence of changes in milling pressure and paddy moisture content, and realize the coordinated adjustment of feeding speed and roller gap. This solution avoids the uncertainty of manual experience adjustment, and through a data-driven closed-loop control mechanism, ensures that the rice mill maintains a stable working state under different material characteristics, improves the processing effect, and reduces energy waste and abnormal equipment loss.

[0087] In a feasible implementation, referring to Figure 2 , step S100 includes steps S110 to S130, where:

[0088] Step S110: Collect the three-phase terminal voltages of the main motor through a voltage sensor at a preset sampling frequency to generate original voltage waveform data;

[0089] Step S120: Perform moving average noise reduction processing on the original voltage waveform data to obtain the noise-reduced voltage data;

[0090] Step S130: Perform AD conversion on the noise-reduced voltage data to generate a digital voltage sequence as the original voltage data.

[0091] In this embodiment, the preset sampling frequency refers to the time interval parameter for data collection. Specifically, a sampling frequency of 1000 to 2000 times per second can be used to achieve this. This frequency range can cover the complete voltage fluctuation spectrum during the operation of the motor. The moving average noise reduction processing refers to an algorithm for calculating the local average value of time-series data with a dynamic window. Specifically, a moving window containing 50 to 200 sampling points can be used to achieve this, and the data quality is improved by suppressing high-frequency noise components. AD conversion refers to the quantization process of converting an analog voltage signal into a digital signal. Specifically, an analog-to-digital conversion chip with 12-bit or 16-bit precision can be used to achieve this, eliminating the distortion error during the transmission of the analog signal.

[0092] Specifically, the synchronous collection of the three-phase terminal voltages can completely capture the phase voltage differences during the operation of the motor, avoiding feature extraction errors caused by the missing of single-phase data. The moving average algorithm eliminates random interference, such as high-frequency spikes generated by brush contact noise or electromagnetic interference, while retaining the trend of the effective signal through a dynamically adjusted window length. The noise-reduced analog signal is converted into a digital sequence through a high-precision analog-to-digital converter. This process not only realizes the digital storage of the signal but also ensures the accuracy consistency in the subsequent data processing stage through the quantization resolution control.

[0093] Compared with the prior art, traditional methods usually adopt single-phase voltage collection and do not perform dynamic noise reduction processing, resulting in phase deviation and noise residue in the data. The mean filtering with a fixed window length in the prior art is prone to causing distortion of the effective signal, while the moving average algorithm adopted in this solution can adaptively adjust the window parameters according to the noise characteristics. In addition, the prior art often ignores the matching relationship between signal preprocessing and quantization accuracy in the AD conversion link, while this solution makes full use of the effective resolution of the AD converter through pre-noise reduction processing.

[0094] Through the above technical solution, this application solves the problem of waveform distortion caused by noise interference during the voltage signal acquisition process, eliminates the amplitude dimension difference caused by power supply fluctuations, and improves the quantization accuracy of the signal conversion link. The complete acquisition of three-phase voltage provides a data basis for subsequent feature extraction. The moving average algorithm effectively suppresses the contamination of the effective signal by high-frequency interference, and the high-precision AD conversion ensures the true restoration of the digital sequence, thus establishing a reliable data source for the accurate judgment of the load state of the rice mill.

[0095] In a feasible implementation manner, referring to Figure 3 , step S200 includes steps S210 to S230, where:

[0096] Step S210: Smooth the original voltage data using a Butterworth low-pass filter, segment it according to a fixed-duration window, and extract the effective voltage range of each data segment;

[0097] Step S220: Normalize the segmented data to eliminate the dimension difference caused by the voltage amplitude varying with the power supply fluctuation;

[0098] Step S230: Compensate for the sensor sampling delay through a time series alignment algorithm to generate time-synchronized preprocessed data.

[0099] In this embodiment, the Butterworth low-pass filter refers to a filter with the maximum flat amplitude characteristic in the passband. Specifically, it can be implemented by an eighth-order filter with a cut-off frequency of 50 Hz, which is used to filter out high-frequency interference noise and retain the effective low-frequency voltage signal. The fixed-duration window segmentation means dividing the continuous voltage data into independent analysis units according to a fixed time length. Specifically, it can be implemented by a non-overlapping window with a duration of 200 milliseconds, which is used to distinguish the data distribution characteristics of different milling stages. The normalization process refers to linearly mapping the voltage amplitude to a unified numerical interval. Specifically, it can be implemented by the maximum-minimum normalization method, which is used to eliminate the amplitude difference caused by the power grid voltage fluctuation. The time series alignment algorithm refers to synchronously correcting the timestamps of multi-source data. Specifically, it can use the cubic spline interpolation method to compensate for the sensor delay data, which is used to eliminate the data phase shift caused by the sampling time delay.

[0100] Specifically, in the preprocessing process, a Butterworth low-pass filter is first used to perform frequency-domain filtering on the noisy voltage data to suppress the contamination of the effective signal by high-frequency electromagnetic interference. Subsequently, the filtered data is segmented into multiple analysis units according to a fixed-duration window, and the effective working state is identified by calculating the difference in voltage extreme values within each window. Each data segment is normalized to eliminate the absolute value difference caused by the grid voltage fluctuation. Finally, an interpolation algorithm is used to compensate for the sensor sampling delay, so that the preprocessed data is synchronized in the time dimension. These three processing links sequentially eliminate signal noise, dimension difference, and timing deviation, forming a high-precision preprocessed data sequence.

[0101] Compared with the prior art, traditional methods usually only perform single filtering on voltage signals, without considering the dimension difference caused by power supply fluctuations and the problem of sensor sampling delay. When using moving average filtering in the prior art, it is easy to cause signal phase distortion, and the lack of a data segmentation mechanism results in limited feature extraction accuracy. This application realizes multi-dimensional data quality optimization through a combination of low-pass filtering, normalization processing, and time synchronization algorithm, effectively solving the signal distortion problem under complex working conditions.

[0102] Through the above technical solutions, this application can eliminate high-frequency noise interference in voltage signals, suppress the influence of power supply system fluctuations on data stability, and compensate for the timing error caused by sensor sampling delay, thereby obtaining high-precision preprocessed data. This provides a reliable data basis for accurately extracting voltage characteristic parameters subsequently, and ultimately improves the accuracy of predicting the rice milling load state.

[0103] In a feasible implementation manner, referring to Figure 4 , step S300 includes steps S310 to S340, where:

[0104] Step S310, calculate the arithmetic mean of the preprocessed data within a preset time window to generate a voltage mean value;

[0105] Step S320, calculate the difference between the maximum value and the minimum value of the preprocessed data within a preset time window to generate a voltage fluctuation amplitude;

[0106] Step S330, perform wavelet transform decomposition on the preprocessed data to extract high-frequency components, calculate the energy value of the high-frequency components within a preset time window and the total energy value within the preset time window to determine the high-frequency energy ratio;

[0107] Step S340, combine the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio to form the voltage characteristic data.

[0108] In this embodiment, the average voltage refers to the arithmetic mean of voltage data within a preset time window, which can be specifically implemented using a moving average algorithm or a weighted average algorithm, and is used to reflect the average load level during the operation of the motor. The voltage fluctuation amplitude refers to the difference between the maximum and minimum values of the voltage data, which can be specifically calculated through the range of a sliding window, and is used to characterize the dynamic disturbance characteristics of the voltage caused by load changes. The high-frequency energy ratio refers to the ratio of the energy of the high-frequency component after wavelet transform decomposition to the total energy, which can be specifically implemented by performing multi-scale decomposition using the Daubechies wavelet basis, and is used to capture the transient abnormal fluctuations related to the moisture content of paddy in the voltage waveform.

[0109] Specifically, the calculation of the average voltage eliminates random interference signals and establishes a quantitative index for the steady-state load level; the range calculation of the voltage fluctuation amplitude can effectively reflect the dynamic impact of the material density change on the motor during the rice milling process; the extraction of the high-frequency energy ratio identifies the voltage waveform distortion characteristics caused by the difference in paddy moisture content through time-frequency analysis technology. The three respectively construct a composite feature vector from the three dimensions of steady state, dynamic state, and transient state, enabling the subsequent model to simultaneously perceive the macroscopic trend and microscopic anomalies of the load change of the rice milling machine.

[0110] Compared with the prior art, the traditional method only uses a single average voltage or fluctuation amplitude as a feature and cannot distinguish different voltage change patterns caused by milling pressure and paddy moisture content. This solution can effectively distinguish the types of load changes and solve the prediction deviation problem caused by a single feature dimension by introducing the high-frequency energy ratio, a time-frequency domain feature, and combining multi-dimensional feature fusion.

[0111] Through the above technical solution, the present application realizes the extraction of multi-dimensional features of the voltage signal. In the prediction of the load state of the rice milling machine, it can simultaneously capture the steady-state load level, dynamic disturbance intensity, and transient abnormal fluctuations, providing input data with higher discrimination for the subsequent model, thereby improving the prediction accuracy of the milling pressure demand level and the estimated value of paddy moisture content.

[0112] In a feasible implementation manner, the rice milling load state parameters include the milling pressure demand level and the estimated value of paddy moisture content. Refer to Figure 5 , the method further includes steps S410 to S440, where:

[0113] Step S410, collect a historical data set, where the historical data set includes voltage feature data, measured milling pressure levels, and paddy moisture content data to form a training sample set;

[0114] Step S420: Construct a dual-branch neural network model, including a first fully-connected network branch for outputting the required grinding pressure level when input with the average voltage data and the fluctuation amplitude data, and a second convolutional network branch for outputting the estimated paddy moisture content when input with the high-frequency energy ratio data;

[0115] Step S430: Optimize the parameters of the dual-branch neural network model through the backpropagation algorithm until the error between the required grinding pressure level and the estimated paddy moisture content output by the dual-branch neural network model and the measured values in the training sample set reaches below a preset threshold;

[0116] Step S440: Use the optimized dual-branch neural network model as the load prediction model.

[0117] In this embodiment, the historical data set refers to an associated data set containing voltage characteristics and measured parameters, which can be specifically implemented by using a database storage method and is used to establish a mapping relationship between voltage characteristics and the grinding load state. The dual-branch neural network model refers to a composite model architecture containing independent feature processing paths, which can be specifically implemented by using a combined structure of a fully-connected layer and a convolutional layer. The fully-connected network captures the steady-state characteristics of the average voltage, and the convolutional network extracts the dynamic patterns of high-frequency energy. The backpropagation algorithm refers to a method of adjusting the network weights through gradient calculation, which can be specifically implemented by using the chain derivative rule to gradually converge the error between the model output and the measured values.

[0118] Specifically, the average voltage data reflects the average load level during the operation of the main motor and is directly mapped to the required grinding pressure level through the fully-connected network. The voltage fluctuation amplitude data characterizes the severity of load changes and is used by the fully-connected network to correct the tolerance range for pressure level determination. The high-frequency energy ratio data reflects the voltage high-frequency oscillation characteristics caused by material friction during the grinding process. The convolutional network extracts the associated patterns with the paddy moisture content through local perception. The dual-branch structure allows the pressure level and moisture content prediction tasks to share the underlying voltage characteristics but maintain independent parameter updates, avoiding feature interference caused by multi-task learning in a single network. The preset error threshold is set as the model training termination condition. For example, the iteration can be stopped when the mean square error is lower than 0.05 to ensure that the prediction accuracy meets the engineering control requirements.

[0119] Compared with the prior art, traditional methods usually use a single-output model to predict a single parameter such as grinding pressure or moisture content and cannot simultaneously reflect mechanical load and material characteristics. Conventional neural networks are prone to having high-frequency signal characteristics submerged by steady-state data when processing composite features, while this solution processes different frequency-domain features through a dual-branch structure and retains the recognition ability of high-frequency dynamic information. In the prior art, moisture content prediction mostly relies on humidity sensors, while this solution indirectly calculates the moisture content through voltage high-frequency characteristics, reducing the deployment requirements for dedicated sensors.

[0120] Through the above technical solution, the present application realizes the synchronous and accurate prediction of the milling pressure requirement and the moisture content of paddy rice, and solves the problem of load regulation lag caused by single-parameter prediction in traditional methods. The dual-path processing mechanism of voltage characteristics effectively distinguishes the steady-state load characteristics from the dynamic material characteristics, avoiding the feature confusion of a single model. The joint optimization of model parameters enables a synergistic effect between the pressure level and moisture content prediction. For example, the high-frequency voltage fluctuations caused by changes in moisture content can synchronously correct the pressure level determination result, improving the overall accuracy of load state recognition.

[0121] In a feasible implementation manner, the rice milling machine further includes a feed motor. Refer to Figure 6 , step S500 includes steps S510 to S520, where:

[0122] Step S510: According to the milling pressure requirement level of the rice milling load state parameter, query the preset pressure-speed mapping table to generate a corresponding feed motor speed control signal to adjust the feed speed.

[0123] Step S520: According to the estimated value of the paddy rice moisture content in the rice milling load state parameter, determine the gap compensation amount of the milling roller and generate a corresponding milling roller displacement control signal to adjust the gap of the milling roller.

[0124] In this embodiment, the pressure-speed mapping table refers to a reference table that pre-establishes the correspondence between the milling pressure level and the feed motor speed. Specifically, it can be constructed by recording the correspondence between the steady-state load current and speed of the motor at different pressure levels, and is used to achieve the standardized matching between the load state and the actions of the actuator. The estimated value of paddy rice moisture content refers to the predicted value of the material moisture content obtained by analyzing voltage characteristics data. Specifically, it can be estimated by using a neural network model trained with the high-frequency energy ratio and sample moisture content data, and is used to guide the dynamic adjustment of the milling gap. The gap compensation amount refers to the adjustment amount of the milling roller position set according to the difference in material moisture content. Specifically, it can be realized by setting different compensation amounts corresponding to preset moisture content threshold intervals. For example, the preset first threshold is set to 12%, the second threshold is set to 15%, and the third threshold is set to 18%.

[0125] Specifically, the adjustment process of the feed speed is automatically matched through the pressure-speed mapping table. When the milling pressure requirement level is detected, the system directly calls the corresponding speed parameter in the mapping table to generate a control signal, avoiding the response delay of manual experience adjustment. The adjustment of the milling roller gap is executed by comparing the estimated moisture content with the preset threshold interval. When low-moisture content material is detected, the gap compensation amount is automatically reduced to prevent insufficient milling, and when high-moisture content material is detected, the gap compensation amount is increased to avoid an increase in the broken rice rate. This dual-parameter collaborative control method enables the feed speed and milling intensity to form a dynamic balance according to the real-time load state.

[0126] Compared with the prior art, the traditional method relies on the operator to visually inspect the material state for mechanical adjustment, resulting in problems of adjustment lag and insufficient precision. In the prior art, only a single motor current parameter is used to adjust the feeding speed, and it is impossible to solve the problem of milling quality fluctuation caused by the change of moisture content. However, in this solution, a pressure-speed mapping relationship and a moisture content gap compensation mechanism are established to achieve the composite closed-loop control of the operating parameters of the rice milling machine.

[0127] Through the above technical solution, the present application realizes the automatic coordinated control of the feeding speed and the milling gap of the rice milling machine, effectively solving the problems of low adjustment precision and slow response speed caused by the dependence on manual experience in traditional equipment. The precise matching of the milling pressure and the feeding speed avoids the risk of motor overload, and the gap compensation mechanism based on the moisture content estimation reduces the broken rice rate during the milling process of high-moisture materials, improving the finished product quality while ensuring the milling efficiency.

[0128] In a feasible implementation manner, the method further includes determining the maximum allowable load current, applying the milling pressure at equal interval pressure levels within the range from no load to full load of the rice milling machine, and recording the steady-state load current of the feeding motor at each pressure level.

[0129] Calculate the speed ratio coefficient corresponding to each milling pressure demand level according to the following formula:

[0130] ;

[0131] wherein, represents the milling pressure demand level; represents at the speed ratio coefficient at the milling pressure demand level of represents the maximum allowable load current; represents at the steady-state load current of the motor at the milling pressure demand level of

[0132] Determine the speed of the feeding motor according to the speed ratio coefficient corresponding to the milling pressure demand level, which specifically includes:

[0133] Determine the speed of the feeding motor according to the following formula:

[0134] ;

[0135] wherein, represents the speed of the feeding motor; represents the speed ratio coefficient; represents the rated speed of the feeding motor;

[0136] Establish the correspondence between the grinding pressure demand level and the feed motor speed to construct the preset pressure-speed mapping table.

[0137] In this embodiment, the maximum allowable load current refers to the maximum current threshold of the rice milling machine drive motor under safe operating conditions, which can be specifically determined by the rated power parameter of the motor and the set value of the overload protection device, and is used to define the safety boundary of the system operation. The equal-interval pressure level means dividing the working pressure range of the rice milling machine into multiple evenly distributed test points, which can be specifically achieved by starting with the no-load pressure, ending with the full-load pressure, and increasing at a fixed step size, and is used to construct the reference data for different load states. The steady-state load current refers to the current value when the feed motor reaches a stable working state under a constant grinding pressure, which can be specifically obtained by continuously collecting current data and calculating its average value, and is used to reflect the load characteristics at a specific pressure level. The speed ratio coefficient refers to the ratio of the actual speed to the rated speed, which can be specifically calculated by a formula based on the difference between the steady-state load current and the maximum allowable current, and is used to achieve the non-linear adjustment of the speed with the change of the load.

[0138] Specifically, by pre-calibrating the steady-state current at different pressure levels, the correspondence between the load current and the grinding pressure is established. When the current pressure level is detected, the speed ratio coefficient is dynamically calculated according to the ratio of the steady-state current value recorded at this level to the maximum allowable current. For example, when the steady-state current of a certain pressure level reaches 80% of the maximum allowable current, the ratio coefficient will be adjusted to 0.8, and at this time the actual speed is 80% of the rated speed. This non-linear adjustment method based on the proportion of the load current can not only automatically reduce the feed speed to prevent overload at high loads, but also maintain a higher speed to improve the processing efficiency at low loads. The finally formed pressure-speed mapping table converts the abstract pressure level into an executable speed command, realizing the closed-loop control of the feed speed during the processing.

[0139] Compared with the prior art, the traditional method mostly adopts a fixed speed or a simple linear speed regulation strategy, and cannot adapt to the load fluctuations caused by the changes in the moisture content and hardness of paddy during the rice milling process. However, this method can automatically match the best feed speed according to the real-time load state by establishing a non-linear mapping relationship between the pressure level and the speed. For example, when encountering paddy with high hardness, the system automatically reduces the feed speed by detecting the increase in the load current, while the fixed speed scheme in the prior art will increase the risk of motor overload.

[0140] Through the above technical solutions, the present application realizes the dynamic adaptation of the feeding speed and milling pressure of the rice mill, effectively avoiding the phenomenon of motor overload caused by sudden load changes. At the same time, based on the non-linear speed regulation mechanism of the proportional coefficient, the energy utilization efficiency is optimized on the premise of ensuring processing safety. Through the preset pressure-speed mapping table, the parameter calculation process of the control system is simplified, and the real-time response speed is improved.

[0141] In a feasible implementation manner, the method further includes that when the measured load current is greater than the steady-state load current at a certain milling pressure requirement level, the speed is corrected according to the following formula:

[0142] ;

[0143] where, represents the corrected speed; represents the speed of the feeding motor; represents the measured load current, represents the maximum allowable load current; represents at the steady-state load current of the motor at the milling pressure requirement level of level.

[0144] In this embodiment, the measured load current refers to the working current of the feeding motor collected in real time by a current sensor during the operation of the rice mill, which can be specifically implemented by a Hall current sensor and is used to characterize the dynamic change of the current milling load. The steady-state load current refers to the average current value of the feeding motor in a stable working state at a specific milling pressure requirement level, which can be specifically obtained through a pressure level calibration experiment and is used to establish the reference current parameters under different working conditions. The maximum allowable load current refers to the limit current value that the main motor of the rice mill can withstand within the safe operating range, which is specifically set according to the rated parameters of the motor and is used to prevent equipment overload damage. The square root operation in the speed correction coefficient is used to balance the non-linear relationship between the current deviation amount and the speed adjustment amplitude, and its convergence is specifically verified through mathematical modeling to ensure that the corrected speed can quickly respond to abnormal currents and avoid the material flow disorder caused by sudden speed changes.

[0145] Specifically, when it is detected that the measured load current exceeds the steady-state current value corresponding to the current milling pressure requirement level, a rotational speed correction coefficient is generated by calculating the ratio of the difference between the maximum allowable load current and the measured current to the difference between the maximum allowable load current and the steady-state current. After multiplying this coefficient by the current rotational speed, the corrected rotational speed is obtained, such that the feeding speed dynamically decreases as the abnormality degree of the load current increases. For example, when the measured current approaches the maximum allowable current, the correction coefficient approaches zero, and the feeding speed significantly decreases to relieve the motor load pressure. This mechanism realizes the adaptive adjustment of the rotational speed through dynamic current feedback, taking into account both the normal load range differences under the current milling pressure level and avoiding misadjustment caused by instantaneous current fluctuations.

[0146] Compared with the prior art, traditional methods usually adopt fixed thresholds to trigger rotational speed adjustment or adjust the rotational speed through linear ratios, and cannot adapt to the dynamic change characteristics of the load current under different milling pressure levels. This solution introduces steady-state current parameters calibrated based on the pressure level, combines with the square root function to optimize the rotational speed correction ratio, while reducing the instantaneous load of the motor, maintaining the processing continuity of the rice mill under complex working conditions. For example, in the prior art, when the current exceeds the limit, the machine directly stops or reduces the speed step by step, which easily leads to material blockage or a sharp drop in processing efficiency. However, this solution maintains the stability of the processing flow while protecting the safety of the equipment through progressive rotational speed correction.

[0147] Through the above technical solution, this application realizes the dynamic rotational speed compensation of the rice mill when the load current abnormally increases, effectively avoiding the risk of motor overload caused by instantaneous material accumulation or sudden change in milling resistance. By combining the ratio of the difference between the steady-state current parameter and the maximum allowable current under the current pressure level, the adjustment amplitude of the rotational speed is precisely controlled, preventing both the decrease in processing efficiency caused by excessive speed reduction and ensuring a rapid response to abnormal current conditions. For example, when the milling resistance suddenly increases due to the fluctuation of the moisture content of paddy, this solution can automatically balance the milling load and the motor output power by real-time correcting the feeding speed, avoiding the impact of equipment protective shutdown on continuous production.

[0148] In a feasible implementation manner, referring to Figure 7 , step S520 includes steps S521 to S524, where:

[0149] Step S521, when the estimated value of the moisture content of the paddy is greater than a preset first threshold and less than a preset second threshold, determine that the gap compensation amount of the milling roller is 0;

[0150] Step S522, when the estimated value of the moisture content of the paddy is less than the preset first threshold, determine that the gap compensation amount of the milling roller is 0.1 mm;

[0151] Step S523, when the estimated paddy moisture content is greater than a preset second threshold and less than a preset third threshold, determine that the gap compensation amount of the milling roller is 0.2 mm;

[0152] Step S524, when the estimated paddy moisture content is greater than the preset third threshold, determine that the gap compensation amount of the milling roller is 0.3 mm; wherein, the preset first threshold is less than the preset second threshold, and the preset second threshold is less than the preset third threshold.

[0153] In this embodiment, the preset threshold refers to the critical value of paddy moisture content determined through experiments, and specifically can be set after measuring the milling effect of samples with different moisture contents by laboratory testing equipment. The gap compensation amount refers to the mechanical displacement amount of the milling roller relative to the reference position, and specifically can be realized by a servo motor driving an adjustment mechanism. The multi-level threshold division refers to mapping continuously changing moisture content data to discrete control intervals, and specifically can be realized by a conditional judgment logic module.

[0154] Specifically, when it is detected that the moisture content is in the intermediate threshold interval, it indicates that the paddy humidity is in the normal processing range. At this time, maintaining the reference gap can ensure the milling efficiency; when it is detected that the moisture content is lower than the lowest threshold, the system automatically increases the gap compensation amount to reduce the breakage rate of dried paddy; when the moisture content exceeds the intermediate threshold but does not reach the highest threshold, appropriately increasing the gap can prevent a sudden increase in pressure caused by material adhesion; when the moisture content breaks through the highest threshold, further increasing the gap can effectively avoid clogging of the milling chamber. This multi-level adjustment mechanism maintains a stable milling pressure by matching the moisture content change with the mechanical gap in real time.

[0155] In a specific embodiment, the first threshold can be set to 12%, the second threshold to 15%, and the third threshold to 18%. The actuator for the gap compensation amount can adopt a stepper motor combined with a ball screw structure, and the number of motor drive pulses corresponding to each 0.1 mm compensation amount is determined through a calibration test. The threshold parameters can be dynamically adjusted through a human-machine interface to adapt to the processing requirements of different paddy varieties.

[0156] Compared with the prior art, traditional methods mostly use fixed gaps or single-threshold adjustments, which are prone to causing an imbalance in milling pressure when dealing with large fluctuations in moisture content. The gap adjustment devices disclosed in the existing literature only perform feedback control based on the motor load current and cannot predict the impact of changes in material properties on the milling process. This solution combines feedforward control and feedback control by establishing a multi-level correspondence between the moisture content and the gap amount, significantly improving the system response speed and control accuracy.

[0157] Through the above technical solution, the present application can dynamically adjust the milling gap according to the moisture content of paddy rice, effectively avoid the increase in the broken rice rate caused by over-dry materials, prevent equipment overload failures caused by high-humidity materials, and at the same time reduce the frequency of manual adjustment. The multi-level threshold mechanism takes into account both control accuracy and system stability, and improves the continuous operation ability of the equipment on the premise of ensuring the milling quality.

[0158] In a feasible implementation manner, referring to Figure 8 , the method further includes steps S610 to S640, where:

[0159] Step S610, calculating the voltage change rate based on the original voltage data;

[0160] Step S620, collecting the current data of the main motor and calculating the current change rate;

[0161] Step S630, when the current change rate is greater than the preset current change rate and the voltage change rate is less than the preset voltage change rate, controlling the rotation speed of the feeding motor to decrease by a preset speed and controlling the roller gap to increase by a preset distance;

[0162] Step S640, if after a continuous preset duration, the current change rate remains greater than the preset current change rate and the voltage change rate remains less than the preset voltage change rate, controlling the milling roller to rotate in reverse.

[0163] In this embodiment, the voltage change rate refers to the change amount of voltage per unit time, which can be specifically realized by performing differential operation or sliding window difference calculation on the original voltage data, and is used to reflect the dynamic fluctuation of the power supply state of the main motor. The current change rate refers to the change amount of current per unit time, which can be specifically realized by collecting the current signal through a Hall sensor and then performing a first-order derivative calculation, and is used to characterize load mutation or mechanical resistance change. The preset speed can be set to 10%-30% of the current rotation speed of the feeding motor, and can be specifically realized by adjusting the output frequency of the frequency converter to quickly reduce the material supply amount. The preset distance can be set in the range of 0.05-0.15 mm, and is specifically executed by a servo motor driving the roller displacement mechanism to relieve the instantaneous mechanical pressure. The preset duration can be set to 3-5 seconds, and is specifically realized by a timer module to verify the effectiveness of the intervention measure.

[0164] Specifically, when the rice milling machine experiences a sudden load change due to abnormal moisture content in the material or the mixing of foreign matter, the current change rate of the main motor will quickly exceed the preset threshold, while the voltage change rate fails to rise synchronously due to the grid compensation mechanism. At this time, the first stage of protection is formed by reducing the amount of material accumulation by reducing the feed speed and increasing the roller gap to reduce the grinding resistance. If the abnormal state is not eliminated within the set time, it indicates that there is a risk of persistent blockage. At this time, the roller is controlled to rotate in the opposite direction by a specific angle, such as 30-60 degrees, to remove the stuck material from the grinding area. The entire process uses a multi-parameter collaborative judgment mechanism to implement a control strategy from early warning to active intervention in stages, while maintaining the continuous operation of the equipment.

[0165] Compared to existing technologies, traditional methods typically only monitor the absolute value of current or use fixed-time delays for shutdowns, failing to distinguish between transient fluctuations and persistent anomalies. Single-parameter threshold control in existing technologies can easily lead to malfunctions, such as triggering unnecessary shutdowns when grid voltage fluctuates. This solution, however, accurately identifies mechanical jamming characteristics through dynamic correlation analysis of the rate of change of voltage and current. It also employs a progressive control approach, avoiding efficiency losses caused by frequent shutdowns while proactively eliminating the source of the jam through reversal operations.

[0166] Through the above technical solution, this application can promptly eliminate abnormal loads without interrupting the processing flow, preventing excessive accumulation of material in the grinding area that could cause roller jamming. By implementing speed regulation, gap adjustment, and reversal operations in stages, this effectively solves the response lag or excessive intervention caused by a single threshold judgment in traditional control methods, maintaining the continuity of rice milling operations while ensuring equipment safety.

[0167] This application also provides a rice mill control system based on voltage detection, please refer to Figure 9 The system includes: a memory 10, a processor 20, and a rice milling machine control program based on voltage detection stored in the memory 10 and executable on the processor 20. The rice milling machine control program based on voltage detection is configured to implement the steps of the rice milling machine control method based on voltage detection.

[0168] The rice mill control system based on voltage detection provided by this application, which adopts the rice mill control method based on voltage detection in the above-mentioned embodiment, can improve the processing effect of the rice mill. Compared with the existing technology, the beneficial effects of the rice mill control system based on voltage detection provided by this application are the same as those of the rice mill control method based on voltage detection provided by the above-mentioned embodiment. The other technical features of the rice mill control system based on voltage detection are the same as those disclosed in the above-mentioned embodiment and are not further described here.

[0169] The above are only some embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or any direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A control method for a rice mill based on voltage detection, characterized in that, The rice milling machine includes a milling mechanism, and the milling mechanism includes a milling roller and a main motor that is drivingly connected to the milling roller. The method includes: Collect the terminal voltage signal of the main motor to generate original voltage data; Preprocess the original voltage data to obtain corresponding preprocessed data; Extract the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio from the preprocessed data to generate corresponding voltage characteristic data; Input the voltage characteristic data into a pre-trained load prediction model to output the rice milling load state parameters; Adjust the feeding speed of the rice milling machine and the gap of the milling roller according to the rice milling load state parameters.

2. The rice milling machine control method based on voltage detection according to claim 1, characterized in that, The step of preprocessing the original voltage data to obtain corresponding preprocessed data includes: Use a Butterworth low-pass filter to smooth the original voltage data, segment it according to a fixed-duration window, and extract the effective voltage range of each data segment; Normalize the segmented data to eliminate the dimensional difference caused by the voltage amplitude fluctuating with the power supply; Compensate for the sensor sampling delay through a time series alignment algorithm to generate time-synchronized preprocessed data.

3. The rice milling machine control method based on voltage detection according to claim 1, characterized in that, The step of extracting the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio from the preprocessed data to generate corresponding voltage characteristic data includes: Calculate the arithmetic mean value of the preprocessed data within a preset time window to generate the voltage mean value; Calculate the difference between the maximum value and the minimum value of the preprocessed data within a preset time window to generate the voltage fluctuation amplitude; Perform wavelet transform decomposition on the preprocessed data to extract high-frequency components, calculate the energy value of the high-frequency components within a preset time window and the total energy value within the preset time window to determine the high-frequency energy ratio; Combine the voltage mean value, voltage fluctuation amplitude, and high-frequency energy ratio to form the voltage characteristic data.

4. The rice milling machine control method based on voltage detection according to claim 1, characterized in that The rice milling load state parameters include the milling pressure demand level and the estimated value of the paddy moisture content. The method further includes: Collect a historical data set, where the historical data set includes voltage characteristic data, measured milling pressure levels, and paddy moisture content data to form a training sample set; Construct a dual-branch neural network model, including a first fully-connected network branch for outputting the milling pressure demand level when inputting voltage mean value data and fluctuation amplitude data, and a second convolutional network branch for outputting the estimated value of the paddy moisture content when inputting high-frequency energy ratio data; Optimize the parameters of the dual-branch neural network model through the backpropagation algorithm until the error between the milling pressure demand level and the estimated value of the paddy moisture content output by the dual-branch neural network model and the measured values in the training sample set reaches below a preset threshold; Use the optimized dual-branch neural network model as the load prediction model.

5. The rice milling machine control method based on voltage detection according to claim 4, characterized in that, The rice milling machine further includes a feeding motor. The step of adjusting the feeding speed of the rice milling machine and the gap of the milling roller according to the rice milling load state parameters includes: According to the milling pressure demand level of the rice milling load state parameters, query a preset pressure-speed mapping table to generate a corresponding feeding motor speed control signal to adjust the feeding speed; Based on the estimated value of the paddy moisture content in the rice milling load status parameters, determine the gap compensation amount of the milling roller, and generate a corresponding displacement control signal for the milling roller to adjust the gap of the milling roller.

6. The rice milling machine control method based on voltage detection according to claim 5, characterized in that The method further includes: Determine the maximum allowable load current, and apply the milling pressure at equal interval pressure levels within the range from no load to full load of the rice milling machine, and record the steady-state load current of the feeding motor at the corresponding milling pressure requirement level. Calculate the speed ratio coefficient corresponding to each milling pressure requirement level according to the following formula: ； Among them, represents the rice milling pressure demand level; represents the rotational speed ratio coefficient at the -level milling pressure demand level; represents the maximum allowable load current; represents the steady-state load current of the motor at the -level milling pressure demand level; Determine the speed of the feeding motor according to the speed ratio coefficient corresponding to the milling pressure requirement level, which specifically includes: Determine the speed of the feeding motor according to the following formula: ； Among them, represents the rotational speed of the feeding motor; represents the rotational speed proportionality coefficient; represents the rated rotational speed of the feeding motor; Establish the correspondence between the milling pressure requirement level and the speed of the feeding motor to construct the preset pressure-speed mapping table.

7. The rice milling machine control method based on voltage detection according to claim 6, characterized in that, The method further includes: When the measured load current is greater than the steady-state load current at a certain milling pressure requirement level, correct the speed according to the following formula: ； Among them, represents the corrected rotational speed; represents the rotational speed of the feed motor; represents the measured load current, represents the maximum allowable load current; represents at the steady-state load current of the motor at the milling pressure demand level of 8. The rice milling machine control method based on voltage detection according to claim 5, characterized in that, The step of determining the gap compensation amount of the milling roller based on the estimated value of the paddy moisture content in the rice milling load status parameters includes: When the estimated value of the paddy moisture content is greater than the preset first threshold and less than the preset second threshold, determine that the gap compensation amount of the milling roller is 0; When the estimated value of the paddy moisture content is less than the preset first threshold, determine that the gap compensation amount of the milling roller is 0.1 mm; When the estimated value of the paddy moisture content is greater than the preset second threshold and less than the preset third threshold, determine that the gap compensation amount of the milling roller is 0.2 mm; When the estimated value of the paddy moisture content is greater than the preset third threshold, determine that the gap compensation amount of the milling roller is 0.3 mm; wherein, the preset first threshold is less than the preset second threshold, and the preset second threshold is less than the preset third threshold.

9. The rice milling machine control method based on voltage detection according to claim 5, characterized in that, The method further includes: Calculate the voltage change rate based on the original voltage data; Collect the current data of the main motor and calculate the current change rate; When the current change rate is greater than the preset current change rate and the voltage change rate is less than the preset voltage change rate, control the speed of the feeding motor to decrease by a preset speed, and control the gap of the roller to increase by a preset distance; If after a preset duration, the current change rate remains greater than the preset current change rate and the voltage change rate remains less than the preset voltage change rate, control the milling roller to reverse.

10. A rice milling machine control system based on voltage detection, characterized in that, The system includes: a memory, a processor, and a rice milling machine control program based on voltage detection stored on the memory and executable on the processor, and the rice milling machine control program based on voltage detection is configured to implement the steps of the rice milling machine control method based on voltage detection as described in any one of claims 1 to 9.

Images