Chef machine intelligent control method and system based on multi-dimensional analysis and storage medium

Abstract

The invention discloses a chef machine intelligent control method and system based on multi-dimensional analysis and a storage medium, and particularly relates to the technical field of chef machine control. Multi-dimensional state features in the operation process of the chef machine are obtained in real time, operation feature vectors are generated, feature clustering and time sequence mode analysis are utilized, self-adaptive dynamic mapping of the load change rate is combined, the physical change trend of the dough state is accurately evaluated, and load reference grades suitable for different types of dough are generated; the chef machine can dynamically adjust the stirring force, the rotating speed curve and the working time window, optimizes the processing process of different types of dough, and prevents the situation that the gluten development of high-moisture dough is affected due to misjudgment of load reduction or non-uniform stirring of gluten-free dough is caused by load fluctuation, the adaptability and accuracy of the intelligent chef machine can be improved, and the intelligent chef machine is suitable for popularization and application. The dough processing quality is optimized, the baking stability and success rate are improved, and the intelligent stirring requirements of different dough types are met.

Description

Technical Field

[0001] The present invention relates to the technical field of chef machine control, and particularly relates to an intelligent control method, system and storage medium for a chef machine based on multi-dimensional analysis. Background Art

[0002] In modern kitchens, as a multi-functional cooking aid, a chef machine can complete various tasks such as stirring, kneading, and cutting, greatly improving cooking efficiency. Current intelligent chef machines usually rely on preset programs or simple sensor feedback for control. For example, the stirring speed is set according to time, or a single load sensor is used to judge the state of the dough.

[0003] In existing intelligent chef machines, a common intelligent control method is to judge the stirring progress of the dough by the change of the motor load and adjust the stirring speed according to the set logic. However, in actual use, certain special types of dough (such as high-moisture European bread dough or gluten-free dough) will undergo complex physical changes during stirring. For example, high-moisture dough is viscous in the initial stage and gradually forms gluten as it is stirred, while gluten-free dough has large fluctuations in its stirring state due to the lack of a gluten structure. The load sensors of existing intelligent chef machines usually judge the dough state based on the change of motor torque. In this case, the structural change of the dough will cause non-linear fluctuations in the torque signal, making the control system misjudge that the dough is not fully kneaded or has been kneaded, and then wrongly adjust the stirring speed.

[0004] Specifically, in the initial stage of high-moisture dough stirring, the motor load is low. Subsequently, as the dough gradually forms gluten, the load will increase. However, in some stages, due to the enhanced resilience of the dough, the load may briefly decrease. If the system misjudges at this time, the stirring force may be reduced, resulting in the dough not fully developing gluten and affecting the final baking quality. In addition, when stirring gluten-free dough, due to the lack of a gluten network, its stirring resistance fluctuates continuously, and the existing system cannot stably adjust the stirring rhythm, resulting in reduced stirring efficiency or uneven stirring. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control method, system and storage medium for a chef machine based on multi-dimensional analysis to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: An intelligent control method for a chef machine based on multi-dimensional analysis, comprising:

[0007] Based on a multi-sensor array combined with vibration signal analysis and power spectrum segmentation technology, obtain multi-dimensional state characteristics during the operation of the chef machine, and generate an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature change, and humidity level;

[0008] Based on the operating characteristic vector, through feature clustering and time-series pattern analysis, combined with the adaptive dynamic mapping of the load change rate, evaluate the changing trend of the dough state, and generate the load benchmark levels adapted to different dough types;

[0009] Combined with the load benchmark levels and the changing trend of the dough state, dynamically adjust the stirring force, rotation speed curve and working time window of the mixer to optimize the processing effects of different types of dough.

[0010] Preferably, the multi-sensor array includes: a motor torque sensor for detecting the torque change of the motor; a vibration sensor for monitoring the vibration characteristics of the mixer; a microphone for collecting the sound signal during the operation of the mixer; a temperature sensor for measuring the temperature inside the stirring chamber or the motor; and a humidity sensor for monitoring the humidity level inside the chamber.

[0011] Preferably, adopt the feature clustering method to classify the feature patterns of different dough types to identify different categories such as high-moisture dough, low-gluten dough and gluten-free dough.

[0012] Preferably, generate an outlier of the torque change rate by analyzing the change rate of the motor torque over time to evaluate the viscoelastic change of the dough. The method for obtaining the outlier of the torque change rate is as follows:

[0013] First, calculate the motor torque change rate, and the expression is: where: ΔT t is the torque change rate, representing the change rate of the torque over time, T t is the motor torque at the current time t, T t-1 is the motor torque at time t - 1, and Δt is the sampling interval time. Sort the calculated torque change rates, calculate the first quartile Q1, representing the lower quartile, at the 25% position; calculate the third quartile Q3, representing the upper quartile, at the 75% position. The interquartile range IQR represents the middle 50% distribution range of the data, and the calculation formula is: IQR = Q3 - Q1; according to the IQR rule, define the upper and lower boundaries: lower limit = Q1 - 1.5×IQR; upper limit = Q3 + 1.5×IQR; calculate the mean value of the torque change rates exceeding the upper and lower boundaries as the outlier of the torque change rate, marked as SZ.

[0014] Preferably, adopt a sliding window to calculate the changing trend of the vibration and sound energy to identify the moment of dough state transition, and the expression is: where: ΔE t is the vibration-sound combined energy trend, and N is the window length.

[0015] Preferably, calculate the comprehensive change factor through weighted summation for mapping the load benchmark levels F of different dough types t; and dynamically adjust the load reference level, and use the Sigmoid function to smoothly map the load reference levels of different dough states: Where: L t is the current load reference level, L min , L max are the minimum and maximum load thresholds respectively, α is the adjustment coefficient to control the response speed, and F threshold is the trigger threshold for load change.

[0016] Preferably, combining the load reference level with the change trend of the dough state, dynamically adjusting the stirring force, rotation speed curve and working time window of the mixer specifically includes: taking the obtained current load reference level and the dough state change factor as the input items of fuzzy logic, and taking the stirring force, rotation speed curve and working time window of the mixer as the output items of fuzzy logic; calculating the current optimal stirring force, rotation speed curve and working time window according to the inference rules; adjusting the operating parameters of the mixer, and performing fuzzy inference in a loop until the dough reaches the optimal state or the mixing end condition is detected.

[0017] The present invention also provides a smart control system for a mixer based on multi-dimensional analysis, including a feature vector construction module, a feature analysis module and a dynamic adjustment module;

[0018] Feature vector construction module: Based on a multi-sensor array combined with vibration signal analysis and power spectrum segmentation technology, obtain multi-dimensional state features during the operation of the mixer, and generate an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature change and humidity level;

[0019] Feature analysis module: Based on the operation feature vector, through feature clustering and time series pattern analysis, combined with the adaptive dynamic mapping of the load change rate, evaluate the change trend of the dough state, and generate a load reference level suitable for different dough types;

[0020] Dynamic adjustment module: Combine the load reference level with the change trend of the dough state, and dynamically adjust the stirring force, rotation speed curve and working time window of the mixer to optimize the processing effect of different types of dough.

[0021] The present invention also provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the above-mentioned smart control method for a mixer based on multi-dimensional analysis.

[0022] In the above technical solution, the technical effects and advantages provided by the present invention:

[0023] 1. The present invention accurately obtains the physical change characteristics of dough through multi-sensor fusion (torque, vibration, sound, temperature and humidity), combined with vibration signal analysis and power spectrum segmentation technology. Through feature clustering, time series pattern analysis and adaptive dynamic mapping, the present invention can evaluate the state change trend of dough in real time and generate load benchmark levels adapted to different dough types. Compared with existing intelligent cookers that only rely on motor load signals to control stirring, the present invention improves the recognition accuracy of special doughs such as high-moisture dough, low-gluten dough, and gluten-free dough through methods such as IQR anomaly detection, sliding window analysis, and dynamic time warping (DTW), avoiding problems of insufficient or over-stirring caused by misjudgment.

[0024] 2. The present invention adopts fuzzy logic control to dynamically adjust the stirring force, rotation speed curve and working time window, realizing intelligent adaptive control of the cooker. This method not only improves the uniformity and stability of dough processing, ensures that the dough is kneaded in the best state, but also has functions such as real-time optimization, anomaly detection, and safety protection (such as automatic adjustment when the temperature is too high), which can significantly improve the automation level, adaptability and baking success rate of intelligent cookers, meeting the needs of home and professional baking. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0026] Figure 1 It is a flowchart of the method of the present invention.

[0027] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] Example 1, please refer to Figure 1 As shown, the intelligent control method of a cooker based on multi-dimensional analysis in this embodiment includes:

[0030] Based on the multi-sensor array combined with vibration signal analysis and power spectrum segmentation technology, multi-dimensional state characteristics during the operation of the mixer are obtained, and an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature change, and humidity level is generated;

[0031] Based on the operation feature vector, through feature clustering and time series pattern analysis, combined with the adaptive dynamic mapping of the load change rate, the change trend of the dough state is evaluated, and a load benchmark level suitable for different dough types is generated;

[0032] Combined with the load benchmark level and the change trend of the dough state, the stirring force, rotation speed curve, and working time window of the mixer are dynamically adjusted to optimize the processing effect of different types of dough.

[0033] A variety of sensors are arranged inside and outside the mixer to collect key physical parameters during the operation of the mixer in real time: Motor torque sensor: Detects the torque change of the motor, reflecting the resistance of the ingredients, such as the change in dough viscosity and stirring resistance. Vibration sensor (accelerometer): Monitors the vibration characteristics of the mixer to identify changes in the dough state (such as the viscoelastic change before and after forming). Microphone (sound sensor): Captures the sound change during the operation of the mixer to analyze the motor load and the dough kneading state (such as whether abnormal noise is generated due to over-stirring). Temperature sensor: Measures the temperature inside the mixing chamber or the motor to prevent overheating and optimize the dough fermentation conditions. Humidity sensor: Monitors the humidity inside the chamber to help determine whether the dough needs additional water or whether it is close to the optimal state. The data sampling frequency is set to 1kHz - 5kHz to ensure the accurate capture of high-speed vibration, sound, and torque changes.

[0034] Since the data collected by the sensors may contain noise and external interference, preprocessing is required to improve the quality and accuracy of the signals: Data filtering: A band-pass filter is used to remove environmental noise (such as kitchen background noise) and retain the effective signals within the frequency range. For vibration signals, wavelet denoising method is used to eliminate irrelevant high-frequency interference. Signal synchronization: Since multiple sensors collect data simultaneously, time synchronization is required. Hardware timestamps or software interpolation can be used to align the data of each sensor. Data normalization: Since the data magnitudes of different sensors are different, Min-Max normalization or Z-score standardization is adopted to ensure that the data is processed on the same scale.

[0035] Based on the filtered data, key features reflecting the operating state of the mixer are extracted to form an operating feature vector. Motor torque feature: Calculate the instantaneous torque value, average torque, and torque change rate to analyze the change in dough resistance. Use Fourier transform (FFT) to analyze the spectral distribution of the torque signal and identify abnormal peaks (which may be motor overload signals). Vibration frequency feature (power spectrum analysis): Calculate the vibration energy in the time domain to evaluate the change in dough viscoelasticity. Use short-time Fourier transform (STFT) to extract the power spectrum of the vibration signal and analyze the energy change in different frequency bands during the stirring process. Identify the changes in spectral peaks and bandwidths to determine whether dough agglomeration or separation occurs. Sound feature: Use Mel-frequency cepstral coefficients (MFCC) to extract sound features and analyze the operating state of the mixer (such as overload, no-load). Calculate the average value, peak value, and coefficient of variation of sound energy to judge the mixing uniformity of ingredients and the dough forming situation. Temperature change feature: Monitor the motor temperature curve and calculate the temperature change rate to prevent performance degradation caused by motor overheating. Combine with the dough temperature change to evaluate whether the appropriate stirring temperature is reached. Humidity level feature: Calculate the humidity change rate to judge whether the dough needs additional water or is within the optimal humidity range. Combine temperature-humidity joint analysis to optimize the control strategy of the mixer during the dough mixing and fermentation stages.

[0036] Combine the above features to construct a time-series multi-dimensional operating feature vector of the mixer: V t =[T t ,Q t ,A t ,S t ,W t ,H t ; where: V t is the operating feature vector representing the operating state of the mixer at time t, T t is the motor torque in N·m, reflecting the change in dough resistance, Q t is the root mean square (RMS) value of vibration, representing the vibration amplitude of stirring, A t is the vibration frequency in Hz, analyzing the flow characteristics of the dough during the stirring process, S t is the sound energy in dB, representing the friction between the dough and the mixing paddle, W t is the dough temperature in °C, reflecting the temperature change caused by stirring. H t is the humidity change rate, analyzing the water evaporation situation.

[0037] Store the calculated feature vector in the local cache and use a ring buffer to store historical data for subsequent trend analysis and anomaly detection. Optionally, upload the data to the cloud through a wireless communication module (Wi-Fi / BLE) to achieve remote monitoring and intelligent optimization.

[0038] Based on the operating feature vector, through feature clustering and time-series pattern analysis, combined with the adaptive dynamic mapping of the load change rate, evaluate the changing trend of the dough state, and generate load benchmark levels suitable for different dough types, specifically including:

[0039] Since the dimensions of different features are different, normalization processing is required: Where: X t is the standardized feature vector, and μ(V) and σ(V) are the mean and standard deviation of the feature respectively.

[0040] Use the K-means or DBSCAN algorithm to cluster the dough state and identify the operating feature patterns corresponding to different dough types: C = Cluster(X t ); where: C is the clustering category of the current dough (such as high-moisture dough, low-gluten dough, etc.).

[0041] Generate an outlier of the torque change rate by analyzing the change rate of the motor torque over time, and evaluate the viscoelastic change of the dough. The method for obtaining the outlier of the torque change rate is:

[0042] First, calculate the motor torque change rate, and the expression is: Where: ΔT t is the torque change rate, indicating the change rate of the torque over time, T t is the motor torque at the current time t, T t-1 is the motor torque at time t - 1, and Δt is the sampling interval time. Sort the calculated torque change rates, calculate the first quartile Q1, representing the lower quartile, at the 25% position: calculate the third quartile Q3, representing the upper quartile, at the 75% position. The interquartile range IQR represents the middle 50% distribution range of the data, and the calculation formula is: IQR = Q3 - Q1; according to the IQR rule, define the upper and lower boundaries (outlier thresholds): lower limit = Q1 - 1.5 × IQR; upper limit = Q3 + 1.5 × IQR; calculate the mean of the torque change rates exceeding the upper and lower boundaries as the outlier of the torque change rate, denoted as SZ.

[0043] Use a sliding window to calculate the changing trend of vibration and sound energy to identify the moment of dough state transition, and the expression is: Where: ΔE t is the vibration-sound combined energy trend, and N is the window length (such as 10 time steps).

[0044] Use the dynamic time warping (DTW) algorithm to match the current feature sequence (X t ) with the feature patterns of known dough types to determine what development stage the current dough is in (such as initial mixing, gluten formation, overmixing, etc.).

[0045] The comprehensive variation factor is calculated by weighted summation to map the load base levels for different dough types: F t =w1·SZ+w2·ΔE t +w3·H t ; Among them: F t is the dough state change factor. The higher the value, the more drastic the change in the dough state. w1, w2, and w3 are feature weights, which can be optimized through experimental data.

[0046] Dynamically adjust the load benchmark level, and use the Sigmoid function to smoothly map the load benchmark level of different dough states: Where: L t is the current load reference level, L min , L max are the minimum and maximum load thresholds respectively, α is the adjustment coefficient, controlling the response speed, F threshold is the trigger threshold of load change. According to the dough clustering category and load benchmark level, the final adaptive mixing strategy is determined, such as adjusting the mixing intensity and speed curve.

[0047] Combined with the load benchmark level and the change trend of the dough state, the stirring force, speed curve and working time window of the chef machine are dynamically adjusted to optimize the processing effect of different types of dough, specifically including: using the current load benchmark level and dough state change factor obtained as the input items of fuzzy logic, and using the stirring force, speed curve and working time window of the chef machine as the output items of fuzzy logic;

[0048] During the operation of the food processor, two types of input data need to be obtained as input items of the fuzzy logic control system:

[0049] The load base level is based on multi-sensor data analysis and is used to indicate the current load of the dough on the chef machine. The load base level can be divided into four levels: low, medium, high, and very high, which represent the resistance of the dough to the motor. The higher the load, the more viscoelastic the dough has become and may have entered the gluten formation stage or the over-mixing stage.

[0050] The dough state change factor is calculated from parameters such as torque change rate, vibration energy, sound energy, and humidity change, and is used to determine the change trend of the physical properties of the dough. The change factor can be divided into four levels: stable, slowly changing, quickly changing, and drastically changing, indicating whether the dough state is stable or undergoing drastic changes. For example, when the dough begins to form gluten, the torque may rise rapidly, while when it is over-mixed, the torque may fluctuate abnormally.

[0051] In the fuzzy logic system, three key parameters for controlling the kitchen machine are used as output items:

[0052] The stirring intensity reflects the actual power output of the mixer and can be divided into four levels: low, medium, high, and extremely high. For example, during the initial mixing stage of the dough, the stirring intensity should be low, while during the gluten formation stage, the intensity should be appropriately increased to enhance the uniformity of the dough.

[0053] The rotation speed curve reflects the changing trend of the stirring speed of the mixer and can select four modes: constant low speed, gradual acceleration, pulse variable speed, and constant high speed. For example, during the initial mixing stage of high-moisture dough, the gradual acceleration mode should be adopted, while during the processing of gluten-free dough, the pulse variable speed mode can be used to prevent over-stirring.

[0054] The working time window determines the total stirring duration, avoiding over-stirring or under-stirring, and can be divided into four levels: short, medium, long, and extremely long. For example, high-gluten dough may require a longer stirring time, while the stirring time of cake batter should be shorter to prevent damage to the bubble structure.

[0055] Analyze the dough characteristics to determine the appropriate stirring intensity:

[0056] If the load reference level is low and the dough state change factor is stable, it indicates that the dough is still in the initial mixing stage, and the stirring intensity should be set to low or medium.

[0057] If the load reference level is high and the change factor changes rapidly, it indicates that the dough has entered the gluten formation stage, and a high stirring intensity is required to enhance the elasticity of the dough.

[0058] If the load reference level is extremely high and the change factor changes violently, it indicates that over-stirring may occur, and the stirring intensity should be reduced or the stirring should be stopped.

[0059] Adjust the rotation speed curve according to the dough development trend:

[0060] When the load reference level is low and the change factor is stable, it is suitable to use the constant low speed mode for initial mixing.

[0061] When the load level is medium and the change factor changes slowly, the gradual acceleration mode can be adopted to ensure uniform stirring.

[0062] If the load level is high and the change factor changes rapidly, the pulse variable speed mode should be adopted to simulate the effect of manual folding and kneading to avoid damage to the gluten.

[0063] If the load level is extremely high and the change factor changes violently, it is necessary to switch to the constant high speed mode, but execute it for a short time to prevent the dough from overheating or being over-stretched.

[0064] Dynamically adjust the working time window:

[0065] If the dough state is stable, use a medium stirring time to ensure that the basic mixing is completed.

[0066] If the dough state changes rapidly (such as rapid growth of gluten), extend the working time window to ensure full development of the dough.

[0067] If it is detected that the dough enters the over - mixing state, shorten the time window or automatically stop the machine at an appropriate moment.

[0068] Execute fuzzy control adjustment in real - time, collect data at intervals of one second or shorter, update the load reference level and the dough state change factor. Input into the fuzzy logic system, calculate the current optimal stirring force, rotation speed curve and working time window according to the inference rules. Adjust the operating parameters of the mixer and continue to monitor the dough state to ensure the accuracy of the adjustment. Execute fuzzy inference in a loop until the dough reaches the optimal state or the mixing end condition is detected.

[0069] To prevent abnormal situations, the mixer should have safety mechanisms and intelligent optimization functions: Temperature protection: If it is detected that the motor temperature is too high, reduce the stirring force or pause the stirring to prevent motor damage. Humidity compensation: If the dough humidity drops too fast, which may cause the dough to be too dry, prompt the user to add water or automatically adjust the humidity. Intelligent learning: Record the historical data of different dough types, optimize the fuzzy rules, and make the mixer more intelligent to adapt to the processing requirements of different ingredients.

[0070] Example 2, please refer to Figure 2 As shown, an intelligent control system for a mixer based on multi - dimensional analysis in this embodiment includes a feature vector construction module, a feature analysis module, and a dynamic adjustment module;

[0071] Feature vector construction module: Based on a multi - sensor array combined with vibration signal analysis and power spectrum segmentation technology, obtain multi - dimensional state features during the operation of the mixer, and generate an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature change, and humidity level;

[0072] Feature analysis module: Based on the operation feature vector, through feature clustering and time - series pattern analysis, combined with the adaptive dynamic mapping of the load change rate, evaluate the change trend of the dough state, and generate a load reference level adapted to different dough types;

[0073] Dynamic adjustment module: Combine the load reference level and the change trend of the dough state, and dynamically adjust the stirring force, rotation speed curve, and working time window of the mixer to optimize the processing effect of different types of dough.

[0074] Embodiment 3. A computer-readable storage medium stores a computer program. When the program is executed by a processor, the steps of an intelligent control method for a chef machine based on multi-dimensional analysis in Embodiment 1 are implemented. More specifically, the readable storage medium may include, but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0075] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other arbitrary combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center to another website, a computer, a server, or a data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0077] It should be understood that the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context before and after.

[0078] It should be understood that in various embodiments of the present application, the sequence numbers of the above processes do not imply the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0079] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0080] As mentioned above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered within the protection scope of the present application.

Claims

1. An intelligent control method for a chef machine based on multi-dimensional analysis, characterized in that: include; Based on a multi-sensor array combined with vibration signal analysis and power spectrum segmentation technology, the multi-dimensional state characteristics of the kitchen machine during operation are obtained, and an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature changes and humidity levels is generated; Based on the running feature vector, through feature clustering and time series pattern analysis, combined with adaptive dynamic mapping of load change rate, the change trend of dough state is evaluated to generate load benchmark levels suitable for different dough types; Based on the load benchmark level and the changing trend of the dough state, the stirring force, speed curve and working time window of the food processor are dynamically adjusted to optimize the processing effect of different types of dough.

2. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 1, characterized in that: The multi-sensor array includes: a motor torque sensor for detecting torque changes of the motor; a vibration sensor for monitoring the vibration characteristics of the food processor; a microphone for collecting sound signals when the food processor is running; a temperature sensor for measuring the temperature inside the mixing chamber or the motor; and a humidity sensor for monitoring the humidity level in the chamber.

3. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 2, characterized in that: The feature clustering method was used to classify the feature patterns of different dough types to identify different categories of high-moisture dough, low-gluten dough and gluten-free dough.

4. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 1, characterized in that: By analyzing the rate of change of the motor torque over time, the torque change rate abnormal value is generated to evaluate the viscoelastic changes of the dough. The method for obtaining the torque change rate abnormal value is as follows: First, calculate the motor torque change rate, the expression is: Where: ΔT t is the torque change rate, which indicates the rate of change of torque over time, T t is the motor torque at the current time t, T t-1 is the motor torque at time t-1, Δt is the sampling interval, the calculated torque change rate is sorted, and the first quartile Q1 is calculated, which represents the lower quartile, 25% position: the third quartile Q3 is calculated, which represents the upper quartile, 75% position, and the interquartile range IQR represents the middle 50% distribution range of the data. The calculation formula is: IQR = Q3-Q1; according to the IQR rule, the upper and lower boundaries are defined: lower limit = Q1-1.5×IQR; upper limit = Q3+1.5×IQR; the mean of the torque change rate exceeding the upper and lower boundaries is calculated as the torque change rate abnormal value, marked as SZ.

5. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 4, characterized in that: The sliding window is used to calculate the changing trend of vibration and sound energy to identify the moment of dough state transition. The expression is: Where: ΔE t is the vibration-sound joint energy trend, and N is the window length.

6. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 5, characterized in that: The comprehensive variation factor is calculated by weighted summation to map the load base level F for different dough types t ; And dynamically adjust the load benchmark level, using the Sigmoid function to smoothly map the load benchmark level of different dough states: Where: L t is the current load reference level, L min , L max are the minimum and maximum load thresholds respectively, α is the adjustment coefficient, controlling the response speed, F threshold is the trigger threshold for load change.

7. The method for intelligent control of a chef machine based on multi-dimensional analysis according to claim 6, characterized in that: In combination with the load reference level and the changing trend of the dough state, the specific steps of dynamically adjusting the stirring force, speed curve and working time window of the food processor include: using the current load reference level and the dough state change factor obtained as the input items of the fuzzy logic, and using the stirring force, speed curve and working time window of the food processor as the output items of the fuzzy logic; calculating the current optimal stirring force, speed curve and working time window according to the inference rules; adjusting the operating parameters of the food processor, and executing fuzzy reasoning in a loop until the dough reaches the optimal state or the stirring end condition is detected.

8. An intelligent control system for a chef machine based on multi-dimensional analysis, used to implement an intelligent control method for a chef machine based on multi-dimensional analysis according to any one of claims 1 to 7, characterized in that: It includes a feature vector construction module, a feature analysis module and a dynamic adjustment module; Feature vector construction module: Based on a multi-sensor array combined with vibration signal analysis and power spectrum segmentation technology, it obtains the multi-dimensional state characteristics of the chef machine during operation and generates an operation feature vector including motor torque, vibration frequency, sound characteristics, temperature changes and humidity levels; Feature analysis module: Based on the running feature vector, through feature clustering and time series pattern analysis, combined with adaptive dynamic mapping of load change rate, it evaluates the change trend of dough state and generates load benchmark levels suitable for different dough types; Dynamic Adjustment Module: Based on the load benchmark level and the changing trend of the dough state, the stirring force, speed curve and working time window of the chef machine are dynamically adjusted to optimize the processing effect of different types of dough.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by the processor, it implements the intelligent control method of the chef machine based on multi-dimensional analysis as described in any one of claims 1-8.

Images