Control Method and System for Intelligent Adjustment Food Processor

Abstract

This application relates to the field of food processor control technology, and discloses a control method and system for a food processor based on intelligent adjustment. The method or system includes: a data sensing unit that collects real-time data on the physical properties of ingredients and motor operating parameters; an ingredient characteristic identification unit that identifies the hardness, toughness, and processing stage of the ingredients; an adaptive control unit that intelligently calculates the optimal motor control command based on the identification results, motor status, and preset curves; a motor drive unit that executes the command; and a safety protection unit that monitors and triggers protection. By adopting the above technical solution, this application can avoid motor overload, food splashing, and uneven grinding, thereby improving processing efficiency, uniformity, and safety.

Description

Technical Field

[0001] This invention belongs to the field of food processor control technology, specifically relating to a control method and system for a food processor based on intelligent adjustment. Background Technology

[0002] Intelligent control technology plays an increasingly important role in modern industry and daily life. Its core lies in achieving autonomous optimization and efficient operation of equipment or systems through advanced sensing, computing, and execution mechanisms. In the field of smart homes, this technology is widely used in various household appliances, aiming to enhance user experience, improve energy efficiency, and expand device functionality. Among these, food preparation equipment, as a crucial component of kitchen appliances, sees significant progress in intelligent development, which is crucial for improving the cooking process, ensuring food safety, and meeting diverse user needs.

[0003] Among these, the control methods and systems of food processors, as a key component of smart kitchen equipment, aim to precisely adjust various parameters during the cooking process based on the characteristics of the ingredients, user preferences, or preset programs to achieve optimal processing results. Such systems typically involve real-time monitoring and adjustment of key parameters such as motor speed, power, and time to ensure that ingredients are processed evenly, efficiently, and safely, thereby improving the quality and convenience of cooking.

[0004] However, current technologies for controlling food processors still have many shortcomings. When processing ingredients of varying hardness and texture, existing food processors generally operate with fixed speeds or preset speeds. This one-size-fits-all control strategy is ill-suited to the complexity brought about by the diversity of ingredients. This not only easily leads to motor overload and accelerated equipment wear, but can also cause problems such as food splattering and uneven processing, seriously affecting the cooking results and user experience. More importantly, traditional control systems lack the ability to sense and intelligently respond to the real-time status of ingredients, failing to flexibly adjust according to the dynamic changes in the physical properties of ingredients during processing, resulting in energy waste and low operational efficiency. Furthermore, existing systems also have limitations in safety protection and fault warning, failing to effectively avoid risks caused by improper operation or equipment malfunctions, thus restricting the further development of intelligent and automated food processors. Summary of the Invention

[0005] The purpose of this invention is to provide a control method and system for a food processor based on intelligent adjustment, so as to solve the technical problem that existing food processors, when processing ingredients of different hardness, use a fixed speed or preset gear, which can easily lead to motor overload, food splashing, or uneven grinding.

[0006] To achieve the above objectives, the present invention provides a control system for a food processor based on intelligent adjustment, comprising: The data sensing unit is used to collect the physical property parameters of the ingredients in the food processor and the motor operating status parameters in real time; the physical property parameters of the ingredients include, but are not limited to, the resistance, viscosity and temperature of the ingredients; the motor operating status parameters include, but are not limited to, the motor speed, current, torque, power and vibration frequency. The food ingredient characteristic identification unit is electrically connected to the data sensing unit and is used to analyze and process the physical characteristic parameters of the food ingredients collected by the data sensing unit in order to identify the hardness, toughness and processing stage of the current food ingredients. An adaptive control unit, electrically connected to a food characteristic recognition unit and a data sensing unit, is used to intelligently calculate the current optimal motor control command based on the food characteristic information recognized by the food characteristic recognition unit, the motor operating status parameters collected by the data sensing unit, and a variety of preset food processing target curves, and then send the motor control command to the motor drive unit; the food processing target curves define the speed, torque, or power range required for specific foods at different processing stages; The motor drive unit is electrically connected to the adaptive control unit and is used to receive the motor control commands and drive the food processor motor to execute the commands. The safety protection unit is electrically connected to the data sensing unit and the motor drive unit, and is used to monitor the motor operating status parameters in real time. When the motor is detected to be overloaded, overheated or in other abnormal operating conditions, the safety protection unit automatically triggers the protection mechanism to adjust the motor operating status or stop the motor from running.

[0007] In one embodiment of the present invention, the data sensing unit includes: Force sensors are used to measure the resistance that food exerts on kitchen knives, in order to characterize the hardness and toughness of the food. A current sensor is used to measure the real-time operating current of the food processor motor to reflect the motor's load status. Temperature sensors are used to measure the operating temperature of food or motors to monitor heat changes during processing. A speed sensor is used to measure the real-time speed of the food processor motor; Furthermore, the data sensing unit also includes an acoustic sensor for collecting the noise spectrum generated during the operation of the food processor to help determine the degree of food pulverization and the working status of the motor; furthermore, the data sensing unit also includes an optical sensor for non-contact detection of the particle size distribution or color change of the food to assess the processing uniformity.

[0008] In one embodiment of the present invention, the food ingredient characteristic recognition unit specifically achieves the recognition of food ingredient characteristic information through the following steps: The physical property parameters of the ingredients collected by the data sensing unit are preprocessed, including noise filtering and data normalization. Extract multidimensional features from the preprocessed data, such as the peak value, average value, and variance of the force signal, and the rate of change of the current signal; The extracted features are input into a preset machine learning model to output the hardness level, toughness level, and processing stage of the food in a classification or regression manner; the machine learning model includes, but is not limited to, support vector machine, decision tree, or neural network model. Furthermore, the ingredient characteristic recognition unit also includes an ingredient feature database, which stores typical feature vectors of different types of ingredients at different processing stages and corresponding processing target curves. The machine learning model is trained and optimized based on the feature database.

[0009] In one embodiment of the present invention, the adaptive control unit intelligently calculates the current optimal motor control command through the following steps: Based on the food hardness, toughness, and processing stage output by the food characteristic recognition unit, an optimal curve matching the current food state and processing target is selected or dynamically generated from a variety of preset food processing target curves. Based on the optimal curve and the real-time motor operating status parameters fed back by the data sensing unit, the target speed, torque, or power of the motor is dynamically adjusted using a closed-loop control algorithm; the closed-loop control algorithm includes, but is not limited to, fuzzy PID control algorithm, model predictive control algorithm, or reinforcement learning control algorithm. The dynamically adjusted target parameters are then converted into specific motor drive commands, such as the duty cycle of a pulse width modulation signal or the output frequency of a frequency converter.

[0010] As one embodiment of the present invention, the security protection unit triggers the protection mechanism through the following steps: Continuously monitor the motor's current, temperature, and speed change rate; The monitored values ​​are compared in real time with a preset safety threshold, which is determined based on the characteristics of the food processor motor and experience in food processing. When the real-time current value of the motor exceeds the set overload current threshold, or the motor temperature exceeds the set overheat temperature threshold, or the motor speed drops sharply in a short period of time and exceeds the set stall threshold, the safety protection unit determines that the motor is in an abnormal working state. In response to abnormal operating conditions, the safety protection unit automatically sends instructions to the motor drive unit to perform deceleration, pause, or emergency stop operations, and issues warnings through the user interface.

[0011] This invention also provides a control method for a food processor based on intelligent adjustment, applied to the aforementioned control system, comprising the following steps: Step 100: Real-time acquisition of physical property parameters of ingredients in the food processor and motor operating status parameters. The physical property parameters of the ingredients include, but are not limited to, the resistance, viscosity and temperature of the ingredients. The motor operating status parameters include, but are not limited to, the motor speed, current, torque, power and vibration frequency. Step 200: Analyze and process the collected physical property parameters of the ingredients to identify the hardness, toughness, and processing stage of the current ingredients; Step 300: Based on the identified food characteristics information, the collected motor operating status parameters, and the preset multiple food processing target curves, the optimal motor control command is intelligently calculated. Step 400: Drive the food processor motor to execute the motor control instructions; Step 500: Monitor the motor operating status parameters in real time; when the motor is detected to be overloaded, overheated or in other abnormal operating conditions, automatically trigger the protection mechanism to adjust the motor operating status or stop the motor from running.

[0012] Furthermore, the specific methods for analyzing and processing the physical property parameters of the food ingredients in step 200 to identify the hardness, toughness, and processing stage of the current food ingredients include: The collected physical property parameters of the ingredients are subjected to noise filtering and data normalization preprocessing. Extract multidimensional features from the preprocessed data, including but not limited to the peak value, average value, and variance of the force signal and the rate of change of the current signal; The extracted features are input into a preset machine learning model to output the hardness level, toughness level, and processing stage of the food in a classification or regression manner.

[0013] Furthermore, the specific method for intelligently calculating the current optimal motor control command in step 300 includes: Based on the identified food hardness, toughness, and processing stage, an optimal curve matching the current food state and processing target is selected or dynamically generated from a variety of preset food processing target curves. Based on the optimal curve and the collected real-time motor operating status parameters, the target speed, torque, or power of the motor is dynamically adjusted using a closed-loop control algorithm. The dynamically adjusted target parameters are then converted into specific motor drive commands.

[0014] Furthermore, the specific method for automatically triggering the protection mechanism in step 500 includes: Continuously monitor the motor's real-time current, temperature, and speed change rate; The monitored values ​​are compared with preset safety thresholds in real time; When the real-time current value of the motor exceeds the set overload current threshold, or the motor temperature exceeds the set overheat temperature threshold, or the motor speed drops sharply in a short period of time and exceeds the set stall threshold, the motor is judged to be in an abnormal working state. In response to abnormal operating conditions, it automatically performs deceleration, pause, or emergency shutdown operations and provides alerts through the user interface.

[0015] Furthermore, the method of the present invention also includes: The user interaction steps are used to receive the cooking mode selected by the user or the instruction to manually adjust the parameters. The adaptive control unit adjusts or optimizes the target curve for food processing according to the user instruction.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are as follows: 1. This invention introduces a multi-dimensional data sensing unit to comprehensively and in real time acquire the physical property parameters of the ingredients and the operating status parameters of the motor, thereby achieving accurate perception of the internal processing environment and motor load of the food processor. This breaks through the limitations of traditional food processors that rely solely on fixed gears or experience presets, and provides a solid data foundation for subsequent intelligent decision-making. 2. This invention innovatively introduces a food characteristic recognition unit and uses advanced algorithms such as machine learning to perform in-depth analysis of the perceived data. It can accurately identify the hardness, toughness and processing stage of the food, so that the food processor no longer works blindly, but can understand the attributes of the food being processed. This ability is the key to achieving refined and personalized processing. 3. The core of this invention lies in the adaptive control unit. This unit combines the results of food characteristic identification, the real-time status of the motor, and the preset processing target curve to dynamically and intelligently calculate and output the optimal motor control commands. This means that the food processor can adjust its speed, torque, or power in real time during processing according to the actual condition of the food, thereby avoiding problems such as motor overload, food splashing, and uneven grinding, and improving processing efficiency, uniformity, and safety. 4. The safety protection unit equipped in this invention can monitor the motor's operating status in real time. Once an abnormal situation such as overload, overheating, or stall is detected, the protection mechanism is immediately activated to automatically adjust or stop the motor's operation. This not only effectively protects the lifespan of the motor and the food processor, but also fundamentally ensures the user's safety. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the overall technical architecture of the control system for the food processor based on intelligent adjustment proposed in this invention; Figure 2 This is a flowchart of the main stages of the control method for a food processor based on intelligent regulation proposed in this invention. Figure 3 This is a logical flow diagram of the food ingredient characteristic identification unit in this invention; Figure 4 This is a flowchart illustrating the logical flow of the adaptive control unit in this invention, which intelligently calculates the optimal motor control command. Detailed Implementation

[0018] Please refer to Figure 1-4 This invention provides a control system for a food processor based on intelligent adjustment. Its core objective is to solve the technical problems of existing food processors that, when processing ingredients of varying hardness, use fixed speeds or preset speeds, which easily lead to motor overload, food splattering, or uneven grinding. By introducing multi-dimensional data sensing, intelligent ingredient characteristic recognition, adaptive closed-loop control, and a comprehensive safety protection mechanism, the system achieves dynamic optimization and a high degree of intelligence in the food processor's processing. Please refer to the appendix. Figure 1 This invention provides a control system for a food processor based on intelligent adjustment, including a data sensing unit 101, a food characteristic recognition unit 102, an adaptive control unit 103, a motor drive unit 104, and a safety protection unit 105. The system is deployed in a modular manner, with each unit electrically connected via a standardized digital communication interface to ensure real-time data transmission, accuracy, and overall system robustness.

[0019] The overall operation process of the system is as follows: The data sensing unit 101 collects the physical characteristic parameters of the ingredients in the food processor and the motor operating status parameters in real time; the ingredient characteristic identification unit 102 performs in-depth analysis and processing on the collected physical characteristic parameters of the ingredients to identify the hardness, toughness and processing stage of the ingredients; the adaptive control unit 103 intelligently calculates the optimal motor control command based on the identified ingredient characteristic information, real-time motor operating status parameters and preset multiple ingredient processing target curves; the motor drive unit 104 receives and executes the motor control command to drive the food processor motor to perform operations; during this process, the safety protection unit 105 continuously monitors the motor operating status parameters, and when it detects overload, overheating or other abnormalities in the motor, it immediately triggers the protection mechanism to adjust or stop the motor operation.

[0020] Data sensing unit 101, please refer to the appendix. Figure 1The data sensing unit 101 is the foundational layer of this system, and its main function is to collect various key data from inside the food processor in real time, comprehensively, and accurately. This unit integrates multiple sensors to acquire the physical property parameters of the ingredients and the operating status parameters of the motor, providing rich and accurate data input for subsequent intelligent decision-making. The physical property parameters of the ingredients include, but are not limited to, the resistance, viscosity, and temperature of the ingredients. The motor operating status parameters include, but are not limited to, the motor's speed, current, torque, power, and vibration frequency. The data sensing unit 101 converts the collected raw analog signals into digital signals through an integrated analog-to-digital converter and performs preliminary preprocessing, such as signal filtering and amplification. Then, it sends the structured data stream to the ingredient characteristic recognition unit 102 and the safety protection unit 105 via an internal high-speed data bus.

[0021] Specifically, the data sensing unit 101 includes multiple sub-sensors: Force sensors, employing piezoelectric or strain gauge principles, are intricately mounted on the bottom of the spindle or motor bracket of a cutting tool to measure in real time the reaction force or torque experienced by the tool when processing food. This force signal directly characterizes the hardness and toughness of the food; for example, hard foods generate instantaneous high resistance peaks, while tough foods exhibit sustained high resistance. The force sensor is designed for high sensitivity and high response speed, capable of capturing subtle changes in resistance during the cutting, stirring, and grinding processes. Its output analog signal is converted into a digital signal by a high-precision 16-bit analog-to-digital converter and sampled at a frequency of 500 to 1000 times per second to ensure accurate capture of the dynamic characteristics of the food. The acquired data includes the instantaneous force value, peak value, average value, and force signal fluctuation amplitude; these parameters will be further used to identify the hardness and toughness of the food.

[0022] A current sensor, employing the Hall effect or a high-precision shunt resistor scheme, is connected in series in the main power circuit of the food processor motor to measure the instantaneous operating current of the motor in real time. The motor's current value directly reflects its load condition; high current usually indicates that the motor is under a heavy load, which may be related to the hardness of the food or the processing density. The current sensor has fast response capability and a wide measurement range, capable of capturing current fluctuations during motor startup, load changes, and potential stall. The acquisition frequency is synchronized with the force sensor to ensure data time consistency. By analyzing the effective value, peak value, average value, and harmonic components of the current signal, a more comprehensive assessment of the motor's operating status and the impact of food on the motor can be achieved.

[0023] Temperature sensors, employing thermistors or thermocouples, are strategically placed inside the food processor's motor windings, near the bearings, and on the inner walls of the food container. The motor winding temperature monitors for overheating, while the container wall temperature monitors whether the food experiences a significant temperature rise during processing due to friction or other factors, potentially affecting food quality or causing overcooking. The temperature sensors offer high accuracy and long-term stability, with a measurement range covering 0 to 150 degrees Celsius. Data is collected at a relatively low frequency, such as once per second, but is supplemented by temperature change rate monitoring to promptly detect abnormal temperature rises.

[0024] A speed sensor, employing a Hall effect sensor or optical encoder, is mounted on the food processor motor shaft to measure the motor's instantaneous speed in real time. The optical encoder uses an encoder disk and photoelectric pair to accurately measure the shaft's rotation angle and speed, providing a resolution of 256 to 1024 pulses per revolution. By calculating the number of pulses per unit time, the motor's speed per minute can be precisely determined. Real-time feedback of speed data is crucial for closed-loop control, reflecting not only the motor's current operating state but also indirectly the degree of resistance from food to the blades. Speed ​​data is acquired at a frequency of up to 1000 times per second to capture minute speed fluctuations and the risk of stalling.

[0025] For acoustic sensors, please refer to the appendix. Figure 1 This further enhances the data sensing capabilities. The sensor employs a high-sensitivity microelectromechanical system (MEMS) microphone array, strategically positioned inside the blender's casing or on top of the blending container, to collect the noise spectrum generated during blender operation. By performing real-time Fourier transforms on the collected sound signals, the energy distribution of different frequency components can be analyzed. For example, specific high-frequency noise is generated during food grinding, while mid-to-low-frequency noise may be generated due to motor bearing wear or gear malfunctions. By monitoring energy changes in these specific frequency bands, the degree and uniformity of food grinding, as well as potential mechanical faults in the motor, can be assessed. The acoustic sensor's data sampling rate is set between 44.1 kHz and 96 kHz to capture all sound characteristics within the range of sound audible to the human ear and partially within ultrasonic waves.

[0026] For optical sensors, please refer to the appendix. Figure 1As a non-contact detection method, this further expands the perception dimension of food characteristics. The unit includes a high-resolution miniature camera and a set of controllable spectral LED light sources. By setting a transparent observation window on the wall of the cooking container, it captures or scans images of the food in real time during the cooking process. The optical sensor uses image processing algorithms, such as edge detection, region segmentation, and morphological analysis, to evaluate the particle size distribution, shape changes, and mixing uniformity of the food. Simultaneously, by analyzing the color, brightness, and texture features of the images, it can non-contactly assess the processing maturity or color changes of the food, such as the uniform fermentation of bread dough or the uniform mixing of fruit and vegetable juices. The optical sensor can capture images at a frame rate of 30 to 60 frames per second, providing visual feedback for refined processing.

[0027] The data sensing unit 101 also includes a data fusion and synchronization module, responsible for timestamping, calibrating, and unifying the format of data from the various sensors mentioned above. This module uses a high-precision clock source to ensure the time consistency of all acquired data. For example, force signals, current signals, and speed signals are sampled synchronously at the same microsecond time point. The fused sensor data is output in a unified data packet format through the internal serial peripheral interface bus or controller area network bus, ensuring low latency and high reliability of data transmission. To address potential sensor anomalies, this module also implements sensor data validity verification, such as by comparing the logical consistency of different sensor data or monitoring the sensor's own fault flag bits.

[0028] Food ingredient characteristic recognition unit 102, please refer to the appendix. Figure 1 and attached Figure 3 Electrically connected to the data sensing unit 101, this unit is one of the core intelligent components of the system. Its main function is to perform in-depth analysis and processing of the physical property parameters of the ingredients, which have undergone preliminary pre-processing and are collected in real time by the data sensing unit 101, to accurately identify the hardness, toughness, and processing stage of the ingredients currently in the food processor. This unit uses advanced machine learning technology to transform the raw sensor data into high-level semantic information, providing crucial decision-making support for the adaptive control unit 103.

[0029] The ingredient characteristic recognition unit 102 specifically recognizes ingredient characteristic information through the following steps: Step 1: Preprocess the physical property parameters of the ingredients collected by the data sensing unit 101. This preprocessing stage aims to eliminate noise and outliers in the data and standardize the data to meet the input requirements of the machine learning model. Preprocessing includes: Noise Removal: Digital filters are used to process the raw sensor data. For example, Kalman filters or adaptive low-pass filters are applied to force, current, and rotational speed signals to smooth transient fluctuations and remove high-frequency random noise. For acoustic signals, bandpass filters may be used to remove ambient background noise and enhance characteristic signals in specific frequency bands. Filter parameters, such as cutoff frequency and order, are dynamically adjusted based on sensor characteristics and the expected noise type.

[0030] Data normalization: This involves unifying sensor data with different dimensions and numerical ranges to the same scale to prevent certain features from dominating machine learning models. Common normalization methods include min-max normalization (e.g., linearly scaling data to the range of 0 to 1) or Z-score normalization (e.g., converting data to a distribution with a mean of 0 and a standard deviation of 1). Normalization can improve the training efficiency and generalization ability of machine learning models.

[0031] Data windowing: For time-series data such as force, current, and rotational speed signals, a sliding window technique is used for segmented processing. Each window contains data of a fixed time step, such as 256 or 512 sampling points, and may set a certain window overlap rate, such as 50%, to ensure continuous capture of dynamic changes in the food.

[0032] Step 2: Extract multidimensional features from the preprocessed data. Feature extraction is crucial for the performance of machine learning models; it transforms raw data into more representative and discriminative numerical values. The features extracted in this step include: Force signal characteristics include, but are not limited to, the peak value, average value, RMS value, variance, skewness, kurtosis, and energy within a specific frequency range. By performing a Fast Fourier Transform on the force signal to extract its dominant frequency component and energy distribution, the hardness and viscosity of food can be distinguished more precisely. For example, a sudden high-intensity impact may indicate that the food is hard, while continuous fluctuations may indicate that the food is tough or has high viscosity.

[0033] Current signal characteristics include, but are not limited to, the average value, peak value, variance, root mean square value, and rate of change of the current signal. The rate of change of the current signal can reflect how fast the motor load changes, thereby indirectly inferring the speed at which food is broken. Furthermore, by analyzing the harmonic distortion rate of the current signal, it is possible to identify whether the motor is operating under abnormal load.

[0034] Temperature signal characteristics: including instantaneous temperature value and rate of temperature change.

[0035] Speed ​​signal characteristics: These include the average, variance, maximum, and minimum speed values, as well as the frequency and amplitude of speed fluctuations. A sharp drop or significant fluctuation in speed directly reflects increased motor load or difficulty in handling food.

[0036] Acoustic signal characteristics include sound pressure level, fundamental frequency, Mel-frequency cepstral coefficients (MFCC), and acoustic spectral entropy within a specific frequency range. These characteristics can effectively distinguish the stages of food grinding; for example, the frequency components of noise will change significantly from coarse to fine grinding.

[0037] Optical image features: These include the mean, variance, and shape factor of the food particle size distribution, as well as the mean and standard deviation of the R, G, and B components of color, extracted through image processing, and texture features such as the gray-level co-occurrence matrix (GLCM). These features directly reflect the processing uniformity and condition of the food.

[0038] All extracted features are integrated into a multidimensional feature vector, which is then used as input to the machine learning model.

[0039] Step 3: Input the extracted features into a preset machine learning model to output the hardness level, toughness level, and processing stage of the food in a classification or regression manner. The machine learning model includes, but is not limited to, Support Vector Machine (SVM), decision tree, or neural network model.

[0040] Machine learning model training: Before deployment, these models need to be trained and optimized using a large amount of labeled data. The training dataset covers sensor data and corresponding real food characteristic labels for various common ingredients such as potatoes, carrots, meat, grains, and fruits at different processing stages, such as coarse cutting, medium chopping, fine grinding, and stirring.

[0041] Support Vector Machines (SVMs) maximize the margin between different categories by finding the optimal hyperplane in a high-dimensional space, making them well-suited for classifying food hardness levels (e.g., soft, medium, hard) and toughness levels (e.g., low, medium, high). Using the Radial Basis Function (RBF) kernel function can handle non-linearly separable data.

[0042] Decision tree models branch through a series of feature-based decision rules to obtain classification or regression results. Ensemble learning methods such as random forests or gradient boosting trees can improve classification accuracy and robustness while providing good interpretability.

[0043] Neural network models, such as Multilayer Perceptron (MLP) or Convolutional Neural Network (CNN), can be used. For time-series features, one-dimensional convolutional neural networks can be used to extract local temporal patterns; for image features, two-dimensional convolutional neural networks can be used for feature learning. Neural network models can learn complex nonlinear relationships in data, possessing powerful feature learning capabilities and classification performance, making them particularly suitable for processing high-dimensional, nonlinear sensor data. The model's output can be a probability distribution indicating the likelihood of food belonging to various hardness / toughness levels and processing stages, or a continuous regression value.

[0044] Output Explanation: The model outputs, such as hardness scores between 0 and 10, toughness indices between 0 and 1, and labels for processing stages such as initial coarse cutting, medium stirring, and fine grinding, will be converted into food characteristic information that the adaptive control unit 103 can directly utilize.

[0045] For further details, please refer to the appendix. Figure 3 The ingredient characteristic identification unit 102 also includes an ingredient feature database. This database is used to store typical feature vectors of different types of ingredients at different processing stages and their corresponding processing target curves.

[0046] Database Structure: This database is designed as a relational database, containing tables such as an ingredient type table, a processing stage table, a feature vector table, and a target curve parameter table. The ingredient type table stores metadata such as ingredient name, basic hardness range, and viscosity range; the processing stage table stores descriptions of stages such as coarse crushing, medium crushing, fine grinding, and mixing; the feature vector table stores typical feature vectors of each ingredient after feature extraction at each stage; and the target curve parameter table stores suggested speed, torque, and power ranges corresponding to the feature vectors.

[0047] Model Training and Optimization: The machine learning model is trained and optimized based on this feature database. Training data is selected from the database and used to adjust the model's weights. By continuously adding new ingredient data and expert annotations to the database, the model's recognition accuracy and coverage can be continuously improved.

[0048] Real-time matching: During real-time operation, in addition to direct classification via machine learning models, the recognition unit 102 can also perform similarity matching between the currently extracted ingredient feature vectors and typical feature vectors stored in the database, such as through Euclidean distance or cosine similarity calculations. This helps to confirm the ingredient type and processing stage, further improving the accuracy and reliability of the recognition. When the confidence level of the model's recognition result is low, the entry with the highest similarity in the database can be referenced first.

[0049] Adaptive control unit 103, please refer to the appendix. Figure 1 and attached Figure 4 Electrically connected to the ingredient characteristic recognition unit 102 and the data sensing unit 101, this is the core intelligent decision-making unit of the system. Its function is to intelligently calculate the optimal motor control command based on the ingredient characteristic information identified by the ingredient characteristic recognition unit 102, the motor operating status parameters collected in real time by the data sensing unit 101, and various preset ingredient processing target curves, and then send the motor control command to the motor drive unit 104. The ingredient processing target curves define the required speed, torque, or power range for specific ingredients at different processing stages, and are key to achieving refined and personalized processing.

[0050] The adaptive control unit 103 intelligently calculates the optimal motor control command through the following steps: Step 1: Based on the food hardness, toughness and processing stage output by the food characteristic recognition unit 102, select or dynamically generate an optimal curve that matches the current food state and processing target from a variety of preset food processing target curves.

[0051] Preset Target Curves: The system internally stores a knowledge base containing hundreds, even thousands, of preset food processing target curves. These curves are meticulously designed based on extensive experimental data and the experience of culinary experts, targeting different food types such as vegetables, fruits, grains, and meats, and different processing goals such as coarse chopping, fine grinding, mixing, and pulverizing. Each curve defines the ideal trajectory of the motor's target speed, torque, or power as a function of time or processing progress during the cooking process. For example, a curve for hard grains might include a slow start-up phase followed by a high-torque grinding phase with gradually increasing speed; a curve for soft fruits might start with low-speed mixing and gradually transition to medium-high-speed pulverization.

[0052] Curve selection logic: When the ingredient characteristic recognition unit 102 outputs the current ingredient type (e.g., carrot), hardness level (e.g., medium-hard), toughness level (e.g., medium), and processing stage (e.g., initial coarse cutting), the adaptive control unit 103 searches for the most matching target curve in the knowledge base based on this information. The matching process may employ multi-dimensional matching algorithms, such as algorithms based on Euclidean distance or weighted similarity, to find the curve that is closest to the current ingredient state and the cooking mode selected by the user (e.g., making a puree).

[0053] Dynamic curve generation: For novel ingredient combinations that don't perfectly match or specific user-defined needs, the system can dynamically generate a new target curve using interpolation algorithms or parameterized model-based generation algorithms, such as Bézier curves or spline curve fitting. During generation, the system comprehensively considers the hardness, toughness, viscosity of the ingredients, and the desired final processing effect, ensuring the generated curve remains within the motor's capabilities and safety thresholds. For example, the slope, peak value, and plateau period of the curve can be adjusted to adapt to the crushing and grinding characteristics of different ingredients.

[0054] Step 2: Based on the optimal curve and the real-time motor operating status parameters fed back by the data sensing unit 101, the target speed, torque, or power of the motor is dynamically adjusted using a closed-loop control algorithm. This step is the core of achieving adaptive control.

[0055] Feedback mechanism: The real-time parameters such as motor speed, current, and torque continuously provided by the data sensing unit 101 serve as feedback signals for closed-loop control.

[0056] Error calculation: The adaptive control unit 103 compares the current real-time motor operating status parameters, such as the real-time speed, with the target speed at the current moment indicated by the optimal curve, and calculates the control error.

[0057] Closed-loop control algorithm: Fuzzy PID Control Algorithm: This system prioritizes the use of the fuzzy PID control algorithm to address the inherent nonlinearity, time-varying nature, and uncertainty of the food processor system. The fuzzy PID controller takes the error E and error rate of change EC of the traditional PID controller as inputs and dynamically adjusts the PID parameters through three steps: fuzzification, fuzzy inference, and defuzzification. , , .

[0058] Fuzzification: Convert precise E and EC values ​​into fuzzy linguistic variables, such as negative large, negative medium, zero, positive medium, positive large, etc., and define corresponding membership functions such as triangular and trapezoidal.

[0059] Fuzzy reasoning: Based on a pre-defined fuzzy rule base, for example, if E is positive and EC is zero, then... Should be increased Should be reduced The appropriate amount of variation should be obtained by reasoning, for example, using the minimax method, to determine the fuzzy variation of the PID parameters.

[0060] Defuzzification: Converting fuzzy inference results into precise PID parameter adjustments, for example, using the centroid method or weighted average method.

[0061] In this way, the fuzzy PID controller can optimize the PID parameters in real time according to the changes in the characteristics of the ingredients and the dynamic adjustment of the motor load, making the motor control smoother, the response faster, and effectively suppressing oscillations.

[0062] Model Predictive Control (MPC) Algorithm: As an optional enhanced control strategy, the MPC algorithm is suitable for scenarios that require consideration of future system dynamics and multivariate constraints. MPC establishes a predictive model of the interaction between the food processor motor and the ingredients, such as a physics-based model or a data-driven model. In each control cycle, it predicts the system's behavior over a future period and solves an optimization problem, such as minimizing speed error, energy consumption, and vibration, while satisfying constraints such as motor current, temperature, and speed limits, thus obtaining the current optimal sequence of control actions. Then, only the first control action in the sequence is executed, and the prediction and optimization are repeated in the next control cycle, forming a rolling optimization control method. MPC is particularly suitable for handling highly viscous or extremely unevenly hard ingredients, and can anticipate and avoid potential overload or stall risks.

[0063] Reinforcement learning control algorithms: As a cutting-edge adaptive control method, reinforcement learning algorithms can autonomously learn optimal control strategies through interaction with the environment. During the training phase, the agent, such as the adaptive control unit 103, executes different motor control actions (action space) under different food characteristics and motor states (e.g., state space) through a trial-and-error process. Based on reward and penalty signals from the system feedback (e.g., based on processing uniformity, time, energy consumption, and safety indicators), it adjusts its control strategy. After sufficient training, the reinforcement learning controller can autonomously discover and execute the optimal motor control strategy to adapt to various unknown or complex food processing scenarios without requiring a precise system model. This algorithm can handle highly nonlinear and uncertain systems.

[0064] Step 3: Convert the dynamically adjusted target parameters into specific motor drive commands, such as the duty cycle of the pulse width modulation (PWM) signal or the output frequency of the inverter.

[0065] PWM signal: For brushless DC motors or brushed DC motors driven by an H-bridge, the target speed or torque value is converted into a specific PWM signal duty cycle. A higher duty cycle means a higher average voltage is supplied to the motor, thereby increasing the speed or torque. The frequency of the PWM signal is typically set above 20 kHz to avoid audible noise.

[0066] Inverter output frequency: For AC induction motors or synchronous motors, the target speed or torque value is converted into the inverter's output frequency and voltage. By changing the frequency of the output voltage, the speed of the AC motor can be precisely controlled. Simultaneously, by adjusting the voltage-to-frequency ratio, constant flux control can be achieved, thereby precisely controlling the motor torque.

[0067] These specific motor drive commands are sent to the motor drive unit 104 via a high-speed digital communication interface, which directly drives the food processor motor.

[0068] The invention also includes a user interaction step for receiving a user-selected cooking mode or manual parameter adjustment command. The adaptive control unit 103 adjusts or optimizes the target curve for food processing according to the user command.

[0069] User Interface (UI): The system provides an intuitive user interface, such as a touch screen or physical buttons, allowing users to select preset cooking modes, such as juice, mincing meat, beating eggs, kneading dough, or customize processing parameters, such as finer grinding or slower stirring.

[0070] Command parsing: User-selected cooking modes or manually adjusted parameters, such as increasing grinding fineness by 20% or decreasing rotation speed by 10%, are parsed as correction factors for the current target curve. For example, if the user selects a finer grinding mode, the adaptive control unit 103 will select a curve with a higher final rotation speed and a longer grinding time, or, based on the current curve, increase the target rotation speed and extend the processing time for subsequent stages.

[0071] Prioritization and Integration: The system prioritizes and integrates user commands and suggestions from intelligent algorithms. Typically, user commands have higher priority, but the system intelligently verifies them while ensuring motor safety and food processing effectiveness. For example, if a user command might overload the motor, the system will issue a warning and suggest adjustments, or automatically make fine-tuning within safe limits. This human-machine collaboration model retains user control while leveraging the advantages of the intelligent system.

[0072] Motor drive unit 104, please refer to the appendix. Figure 1 Electrically connected to the adaptive control unit 103, the motor drive unit 104 is the system's actuator. Its main function is to receive motor control commands, such as PWM signals or inverter output frequencies, sent by the adaptive control unit 103, and drive the blender motor to execute these commands precisely. The motor drive unit 104 typically integrates a power drive circuit, such as an inverter bridge composed of MOSFETs or IGBTs, responsible for converting the electrical energy supplied by the power source into the specific voltage, current, and frequency required to drive the motor, thereby achieving precise control of the motor's speed, torque, and direction. The drive unit also includes current detection and protection circuitry to ensure the motor operates within a safe range and provides feedback signals such as current and voltage to the safety protection unit 105. The motor type can be a DC brushless motor, a DC brushed motor, or an AC induction motor, depending on the blender's design requirements and performance specifications.

[0073] Safety protection unit 105, please refer to the appendix. Figure 1 Electrically connected to the data sensing unit 101 and the motor drive unit 104, it is a key safety protection mechanism of this system. Its main function is to monitor the motor operating status parameters provided by the data sensing unit 101 in real time, and automatically trigger the protection mechanism when the motor is detected to be overloaded, overheated or in other abnormal operating conditions, so as to adjust the motor operating status or stop the motor, thereby protecting the safety of the motor, the food processor and the user.

[0074] The security protection unit 105 triggers the protection mechanism through the following steps: Step 1: Continuously monitor the motor's current, temperature, and speed change rate.

[0075] Real-time data stream: The safety protection unit 105 receives the instantaneous current value of the motor, the temperature value of the motor windings, and the rate of change of speed calculated by the speed sensor, such as angular acceleration, from the data sensing unit 101 in real time through an internal communication interface, such as a serial peripheral interface bus or a controller area network bus. The data receiving frequency is consistent with the sensor sampling frequency to ensure real-time monitoring.

[0076] Data preprocessing: Perform necessary filtering on the received raw data, such as moving average filtering, to eliminate instantaneous noise, prevent false triggering of protection mechanisms, and preserve rapidly changing trends.

[0077] Step 2: Compare the monitored values ​​with preset safety thresholds in real time. These safety thresholds are determined based on the characteristics of the food processor motor, experience in food processing, and international safety standards such as IEC 60335.

[0078] Threshold definition: Overload current threshold: Set a maximum allowable operating current value, such as 120% to 150% of the motor's rated current. When the real-time current exceeds this threshold and persists for a certain period of time, such as 500 milliseconds, it is considered an overload.

[0079] Overheating temperature threshold: Sets the maximum allowable temperature for a motor winding, for example, 90 to 120 degrees Celsius. When the real-time temperature exceeds this threshold, or the rate of temperature change is abnormally high, such as 5 degrees Celsius per second, it is considered overheating.

[0080] Stall threshold: Set a percentage or absolute value at which the speed drops sharply. For example, when the motor speed drops by more than 30% or falls below the set minimum safe speed, such as 1000 rpm, it is judged as stalling or stalling.

[0081] Dynamic thresholds: These thresholds can also be dynamic. For example, higher instantaneous current peaks are allowed during system startup; higher average currents are allowed when handling hard ingredients. Dynamic thresholds are determined by the current ingredient type and processing stage, and are derived from the system's internal safety configuration database.

[0082] Comparison logic: High-speed comparator circuits or microcontroller logic are used to perform real-time comparisons of the magnitudes of each monitored parameter.

[0083] Step 3: When the real-time current value of the motor exceeds the set overload current threshold, or the motor temperature exceeds the set overheat temperature threshold, or the motor speed drops sharply in a short period of time and exceeds the set stall threshold, the safety protection unit 105 determines that the motor is in an abnormal working state.

[0084] Anomaly detection: The detection logic can use combined conditions. For example, a combination of current exceeding a threshold and a sharp drop in speed can more accurately detect stall, rather than just a single parameter exceeding its limit. Simultaneously, a timer mechanism is introduced to prevent instantaneous peak values ​​from triggering protection, requiring the abnormal state to persist for a certain period.

[0085] Step 4: In response to abnormal operating conditions, the safety protection unit 105 automatically sends a command to the motor drive unit 104 to perform deceleration, pause or emergency stop operations, and issues a warning through the user interface.

[0086] Protective actions: Deceleration: If the abnormal state is minor or in its early stages, such as when the current is close to the threshold but not completely exceeded, the safety protection unit 105 will send a command to the motor drive unit 104 to gradually reduce the motor speed or power in order to reduce the motor load and attempt to restore normal operation.

[0087] Pause: If the abnormal state persists or is relatively serious, such as continuous overload, but has not yet reached a critical level, the system will send a pause command to temporarily stop the motor from running, waiting for user intervention or automatically attempting to restart after a short period of time, such as 10 seconds.

[0088] Emergency Stop: If a critical condition is detected, such as severe motor overload, rapid temperature rise, or complete stall, the safety protection unit 105 will immediately send an emergency stop command, such as directly cutting off the motor power supply, to prevent motor damage or danger.

[0089] Warning mechanism: Regardless of the type of protective action performed, the safety protection unit 105 will issue an audible and visual alarm via the user interface (e.g., a buzzer) and display specific fault information on the screen, such as "motor overload, please check the ingredients." Simultaneously, the fault information will be logged to the system log for subsequent diagnosis and maintenance.

[0090] Fault reset: After an emergency shutdown, the system usually requires manual reset by the user or automatic reset after the abnormal conditions are resolved, such as when the motor temperature drops to a safe range.

[0091] Please refer to the attached document. Figure 2 The present invention also provides a control method for a food processor based on intelligent adjustment, which is applied to the above-mentioned control system and includes the following main stage flowchart.

[0092] Step 100: Real-time collection of physical property parameters of the ingredients inside the food processor and motor operating status parameters.

[0093] This step is performed by the data sensing unit 101. For example, a force sensor continuously measures the blade resistance, a current sensor measures the motor current, a temperature sensor measures the motor and food temperature, a speed sensor measures the motor speed, an acoustic sensor collects the noise spectrum, and an optical sensor monitors the particle size and color of the food. All data is acquired at high frequency and synchronously, and transmitted via an internal data bus.

[0094] Step 200: Analyze and process the collected physical property parameters of the ingredients to identify the hardness, toughness, and processing stage of the ingredients.

[0095] This step is completed by the food ingredient characteristic recognition unit 102. The specific method includes noise filtering and data normalization preprocessing of the collected data. Subsequently, multidimensional features are extracted from the preprocessed data, such as the peak value, average value, and variance of the force signal, the rate of change of the current signal, and acoustic and optical features. These features are input into a pre-set machine learning model, such as a neural network model, to output the food ingredient's hardness level, toughness level, and processing stage in a classification or regression manner. The system also references an internal food ingredient feature database for comparison and verification to improve recognition accuracy.

[0096] Step 300: Based on the identified food characteristics information, the collected motor operating status parameters, and the preset target curves for processing various food ingredients, the optimal motor control command is intelligently calculated.

[0097] This step is completed by the adaptive control unit 103. First, based on the food hardness, toughness, and processing stage identified in step 200, and the cooking mode selected by the user, the most suitable food processing target curve is selected from a preset knowledge base or dynamically generated. Next, based on this optimal curve and the real-time motor operating status parameters fed back from step 100, the target speed, torque, or power of the motor is dynamically adjusted using a closed-loop control algorithm, such as a fuzzy PID control algorithm. Finally, the dynamically adjusted target parameters are converted into specific motor drive commands, such as the duty cycle of a pulse width modulation signal or the output frequency of the inverter.

[0098] Step 400: Drive the food processor motor to execute the motor control instructions.

[0099] This step is completed by the motor drive unit 104. The motor drive unit 104 receives motor control commands from the adaptive control unit 103 and precisely controls the food processor motor to adjust its speed and torque according to the commands, thereby achieving refined processing of the ingredients.

[0100] Step 500: Monitor the motor operating status parameters in real time; when the motor is detected to be overloaded, overheated or in other abnormal operating conditions, automatically trigger the protection mechanism to adjust the motor operating status or stop the motor from running.

[0101] This step is completed by the safety protection unit 105. The safety protection unit 105 continuously obtains the real-time current value, temperature value, and speed change rate of the motor from the data sensing unit 101, and compares them with the preset safety thresholds in real time. Once the current exceeds the overload threshold, the temperature exceeds the overheat threshold, or the speed drops sharply and exceeds the stall threshold, it is judged as an abnormal working state, and a command is immediately sent to the motor drive unit 104 to perform deceleration, pause, or emergency stop operations, and a warning is issued through the user interface.

[0102] The control system and method for a food processor based on intelligent adjustment provided by this invention, through the close collaboration of the above-mentioned units and the deep application of intelligent algorithms, achieves comprehensive perception, intelligent decision-making and precise control of the food processor's processing process. It effectively solves the core technical problems in the prior art, such as motor overload, food splashing and uneven grinding, and improves the performance, safety and user experience of the food processor.

[0103] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "include," "contain," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0104] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A control system for a food processor based on intelligent adjustment, characterized in that, include: The data sensing unit is used to collect the physical property parameters of the ingredients in the food processor and the motor operating status parameters in real time. The physical properties of the food include its resistance, viscosity, and temperature; the operating parameters of the motor include its speed, current, torque, power, and vibration frequency. The food ingredient characteristic identification unit is electrically connected to the data sensing unit and is used to analyze and process the physical characteristic parameters of the food ingredients collected by the data sensing unit in order to identify the hardness, toughness and processing stage of the current food ingredients. An adaptive control unit, electrically connected to the food characteristic recognition unit and the data sensing unit, is used to intelligently calculate the current optimal motor control command based on the food characteristic information identified by the food characteristic recognition unit, the motor operating status parameters collected by the data sensing unit, and a variety of preset food processing target curves, and send the motor control command to the motor drive unit; the food processing target curves define the speed, torque, or power range required for specific foods at different processing stages; The motor drive unit is electrically connected to the adaptive control unit and is used to receive the motor control command and drive the food processor motor to execute the command. The safety protection unit is electrically connected to the data sensing unit and the motor drive unit, and is used to monitor the motor operating status parameters in real time. When the motor is detected to be overloaded, overheated or in other abnormal operating conditions, the safety protection unit automatically triggers the protection mechanism to adjust the motor operating status or stop the motor from running.

2. The control system of the food processor based on intelligent adjustment according to claim 1, characterized in that, The data sensing unit includes: Force sensors are used to measure the resistance that food exerts on kitchen knives, in order to characterize the hardness and toughness of the food. A current sensor is used to measure the real-time operating current of the food processor motor to reflect the motor's load status. Temperature sensors are used to measure the operating temperature of food ingredients or motors to monitor heat changes during processing; and A speed sensor is used to measure the real-time speed of the food processor motor.

3. The control system of the food processor based on intelligent adjustment according to claim 2, characterized in that, The data sensing unit further includes: Acoustic sensors are used to collect the noise spectrum generated during the operation of the food processor to help determine the degree of food pulverization and the working status of the motor; and Optical sensors are used to detect particle size distribution or color changes in food ingredients in a non-contact manner to assess processing uniformity.

4. The control system of the food processor based on intelligent adjustment according to claim 1, characterized in that, The food ingredient characteristic recognition unit specifically identifies food ingredient characteristic information through the following steps: The physical property parameters of the ingredients collected by the data sensing unit are preprocessed, including noise filtering and data normalization. Extract multidimensional features from the preprocessed data, such as the peak value, average value, and variance of the force signal, and the rate of change of the current signal; The extracted features are input into a preset machine learning model to output the hardness level, toughness level, and processing stage of the food in a classification or regression manner.

5. The control system of the food processor based on intelligent adjustment according to claim 4, characterized in that, The machine learning model includes support vector machines, decision trees, or neural network models; The ingredient characteristic identification unit also includes an ingredient feature database, which stores typical feature vectors of different types of ingredients at different processing stages and corresponding processing target curves. The machine learning model is trained and optimized based on the ingredient feature database.

6. The control system of the food processor based on intelligent adjustment according to claim 1, characterized in that, The adaptive control unit intelligently calculates the optimal motor control command through the following steps: Based on the food hardness, toughness, and processing stage output by the food characteristic recognition unit, an optimal curve matching the current food state and processing target is selected or dynamically generated from a variety of preset food processing target curves. Based on the optimal curve and the real-time motor operating status parameters fed back by the data sensing unit, the target speed, torque or power of the motor is dynamically adjusted using a closed-loop control algorithm; The dynamically adjusted target parameters are then converted into specific motor drive commands, such as the duty cycle of a pulse width modulation signal or the output frequency of a frequency converter.

7. The control system of the food processor based on intelligent adjustment according to claim 6, characterized in that, The closed-loop control algorithm includes fuzzy PID control algorithm, model predictive control algorithm, or reinforcement learning control algorithm.

8. The control system of the food processor based on intelligent adjustment according to claim 1, characterized in that, The security protection unit triggers the protection mechanism through the following steps: Continuously monitor the motor's real-time current, temperature, and speed change rate; The monitored values ​​are compared with preset safety thresholds in real time; When the real-time current value of the motor exceeds the set overload current threshold, or the motor temperature exceeds the set overheat temperature threshold, or the motor speed drops sharply in a short period of time and exceeds the set stall threshold, the motor is judged to be in an abnormal working state. In response to abnormal operating conditions, commands are automatically sent to the motor drive unit to perform deceleration, pause, or emergency stop operations.

9. The control system of the food processor based on intelligent adjustment according to claim 1, characterized in that, The adaptive control unit is also used to receive the cooking mode selected by the user or the manual adjustment parameter instruction, and adjust or optimize the target curve of food processing according to the user instruction.

10. A control method for a food processor based on intelligent adjustment, applied to the control system described in claim 1, characterized in that, Includes the following steps: The physical properties of the ingredients inside the food processor and the operating parameters of the motor are collected in real time. The physical properties of the ingredients include resistance, viscosity and temperature. The operating parameters of the motor include the motor speed, current, torque, power and vibration frequency. The collected physical property parameters of the ingredients are analyzed and processed to identify the hardness, toughness, and processing stage of the ingredients. Based on the identified food characteristics, the collected motor operating status parameters, and the preset target curves for processing various foods, the optimal motor control command is intelligently calculated. The motor of the food processor is driven to execute the motor control instructions. The motor's operating status parameters are monitored in real time. When an overload, overheating, or other abnormal operating condition of the motor is detected, a protection mechanism is automatically triggered to adjust the motor's operating status or stop the motor from operating.

Images