Intelligent power control method and system for cooking stick

Abstract

The present invention belongs to the field of adaptive control technology, and discloses an intelligent power control method and system for a food stick, comprising collecting comprehensive operating data of the food stick; preprocessing the collected comprehensive operating data of the food stick to obtain a comprehensive operating feature data set; training an operating power prediction model based on the comprehensive operating feature data set, and predicting the operating power of the food stick through the operating power prediction model; comparing the predicted operating power of the food stick with the preset operating power of the food stick to determine whether there is an abnormality in the operating power of the food stick; if the operating power of the food stick is abnormal, automatically generating early warning information to an intelligent power control terminal; and automatically adjusting the motor power through an improved adaptive algorithm to keep the food stick within an optimal power range under different working conditions; through the prediction of the operating power, potential problems can be discovered in a timely manner to ensure that the equipment always operates in a safe and efficient state.

Description

Technical Field

[0001] The present invention relates to the field of adaptive control technology, and more specifically, to an intelligent power control method and system for a food processor. Background Art

[0002] The patent with the patent announcement number CN116398413A discloses an intelligent power control method and device for an electric compressor, the method includes collecting the collected temperatures corresponding to each bus capacitor through a temperature sensor; obtaining the current working state information of the electric compressor, and obtaining the corresponding target fitting curve from multiple fitting curves; determining the collected temperature error value corresponding to each collected temperature based on the target fitting curve; summing each collected temperature with the corresponding collected temperature error value to obtain the real internal temperature to form a real internal temperature set; if it is determined that the corresponding bus capacitor real internal temperature is greater than or equal to the temperature threshold, a power reduction signal is generated and the operating power is reduced based on the corresponding temperature. The implementation of the embodiment of the present invention can accurately sample the working temperature of the bus capacitor to make the capacitor work within the rated working range. It can not only effectively monitor the heating condition of the bus capacitor during operation, but also effectively prevent the bus capacitor from over-temperature failure, thereby improving the reliability of the operation of the electric compressor.

[0003] The conventional intelligent power control method and system of a food processor has the following main problems: The device fails to judge the working status in time, which may cause the blender to operate under inappropriate load conditions. When it is unloaded, the motor power of the device may be higher than the actual demand, resulting in ineffective energy consumption. When the load is too high, the device may not be able to fully exert its performance, resulting in low blending efficiency. The adaptive algorithm was not considered to dynamically adjust the motor power. The food processor may be in an overloaded state for a long time, which will not only increase energy consumption, but also damage the motor and its key components, shortening the service life of the device. There is a lack of a mechanism to flexibly adjust the motor power. The system cannot flexibly adjust the power according to the actual workload, resulting in the device being unable to adapt to different working environments and needs, affecting performance and work efficiency. The proportional adjustment formula was not considered to dynamically adjust the weight factor. The system may rely too much on the local optimal solution when searching for the optimal solution, making it difficult to effectively explore the global optimal solution. This causes the algorithm to fall into the local optimal solution when facing complex problems, and it is impossible to obtain the global optimal motor power setting. Failure to use the smell optimization mechanism to expand the search range may cause the algorithm to converge early in the search space and fail to find the global optimal solution; especially in complex optimization problems, premature convergence means failure to fully explore the possible solution space, thus missing out on a better motor power configuration; without a mechanism to enhance the breadth and diversity of the search, the algorithm's exploration process may fall into a narrow solution domain, resulting in the solution found being limited to certain local areas, lacking a comprehensive consideration of motor power optimization under different working conditions; when local perturbation optimization is not performed, stagnation may occur in the search process, especially when approaching the local optimal solution, the current state cannot be broken, causing the optimization process to stagnate; the lack of a combination of smell optimization and physical attack optimization means that the system lacks global optimization capabilities. When faced with complex loads and working conditions, it may rely solely on local optimization methods to adjust the motor power, resulting in falling into the local optimal solution and failing to find the true global optimal solution.

[0004] In view of this, the present invention proposes an intelligent power control method and system for a food processor to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an intelligent power control method of a food processor, comprising: S1. Collect comprehensive operation data of the food stick; S2, preprocessing the collected comprehensive operation data of the food stick to obtain a comprehensive operation feature data set; S3, training an operation power prediction model according to the comprehensive operation feature data set, and predicting the operation power of the food processor by the operation power prediction model; S4, comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal; S5. If the operating power of the food processor is abnormal, a warning message is automatically generated to the intelligent power control terminal; and the motor power is automatically adjusted by improving the adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

[0006] Furthermore, the comprehensive operation data of the cooking stick includes working status data, working position data and safety monitoring data of the cooking stick; the working status data includes the stirring resistance, load size and rotation speed of the cooking stick; the working position data includes the stirring depth and stirring angle of the cooking stick; the safety monitoring data includes the temperature of the motor, the working time of the motor, the vibration amplitude and the vibration frequency.

[0007] Furthermore, the method of preprocessing the collected comprehensive operation data of the food processor to obtain a comprehensive operation feature data set includes: The density clustering algorithm is used to identify and eliminate outliers in the working status data, working position data and safety monitoring data of the cooking stick, and the processed working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the working status feature data set, working position feature data set and safety monitoring feature data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, and finally the normalized working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the normalized working status feature data set, working position feature data set and safety monitoring feature data set are fused through a weighted formula to obtain a comprehensive feature data set.

[0008] Furthermore, the method of fusing the normalized working state feature data set, working position feature data set and safety monitoring feature data set to obtain a comprehensive feature data set includes: The normalized working state feature data set, working position feature data set and safety monitoring feature data set are fused through a weighted formula to obtain a comprehensive feature data set; the normalized working state feature data set is recorded as , the normalized working position feature dataset is recorded as ; The normalized safety monitoring feature data set is recorded as ; The weighted formula is: ; in, It is a comprehensive feature dataset; is the weight coefficient of the normalized working status feature data set; is the normalized work position feature dataset; is the weight coefficient of the normalized safety monitoring feature data set.

[0009] Furthermore, the training method of the operating power prediction model includes: The dataset is divided into training set, validation set and test set to train the model, evaluate the model performance and verify the generalization ability of the model; the sample set is a subset of the dataset, each sample set includes the historical comprehensive operation feature dataset and the corresponding operation power of the cooking stick; GBDT is selected as the specific implementation of the gradient boosting tree model to handle the regression task; Initialize GBDT parameters and define the objective function; GBDT parameters include the maximum number of leaf nodes in each tree, learning rate, number of trees, and maximum depth of trees; use the historical comprehensive operation feature data set as input data and the corresponding operation power of the food stick as output label to train the operation power prediction model; the operation power prediction model is a gradient boosting tree model; Use mean squared error as the loss function to measure the difference between the model's predicted value and the actual value; In each iteration, GBDT builds a new decision tree to fit the negative gradient of the loss function of the previous step, uses the negative gradient of the objective function as the learning target of the new tree, and adjusts the contribution of the new tree to the final result through the learning rate to minimize the loss function. Use the validation set to evaluate the performance of the model, tune the model, and adjust the model parameters based on its performance feedback until the model performance no longer improves or reaches the preset stopping condition; use the trained operating power prediction model to predict the current comprehensive operating feature data set to obtain the operating power of the food stick.

[0010] Furthermore, the method of comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal includes: If the predicted operating power of the cooking stick is less than or greater than the preset operating power of the cooking stick, it is determined that the operating power of the cooking stick is abnormal; If the predicted operating power of the cooking stick is equal to the preset operating power of the cooking stick, it is determined that there is no abnormality in the operating power of the cooking stick.

[0011] Further, the different working states include a high-load working state, a normal-load working state and a no-load state; The working status of the cooking stick is evaluated by the status evaluation formula, which is: ; in, is the working status value of the cooking stick; is the stirring resistance of the food processor; The load size of the cooking stick; is the rotation speed of the food processor; is the factor affecting the working state of the stirring resistance of the food processor; is the factor affecting the working state of the food processor's load size; is the factor affecting the working state of the food processor's rotation speed; The preset first load working state threshold of the food processor is , the second load working state threshold of the cooking stick is ;like , then the working state of the cooking stick is judged to be no-load state; if , then the working state of the cooking stick is judged to be a normal working state; if , it is judged that the working state of the cooking stick is a high-load working state.

[0012] Furthermore, the method of automatically adjusting the motor power by improving the adaptive algorithm so that the food processor maintains an optimal power range under different working conditions includes: S81, generate by initializing the candidate solution population formula motor power candidate solutions, each of which is an individual in the population; The motor power candidate solutions constitute a population; the population of motor power candidate solutions is initialized to find the optimal motor power; each individual in the population represents a motor power setting scheme, and the motor power search range is determined by the upper and lower limits of the motor power; the formula for initializing the candidate solution population is: ;in, For the The motor power value of each individual; is the lower limit of the motor power value; is the upper limit of the motor power value; It is a randomly generated value between 0 and 1, which is used to ensure the randomness of the motor power value; is the index of the individual, ; is the population size, i.e., the number of candidate solutions for motor power; S82. Use cyclic population reduction technology to reduce the population size through the cyclic population reduction formula. The cyclic population reduction formula is: ; Among them, if the current number of iterations When it is divisible by the periodic parameter that controls the frequency of population reduction, the population size is dynamically adjusted according to the number of iterations through the cosine function, that is, ; If the current number of iterations If it cannot be divided by the period parameter that controls the frequency of population reduction, then The population size at the iteration is the maximum size of the population. ; For the The population size at the iteration; is the minimum size of the population; is the maximum size of the population; is the number of current iterations; is the maximum number of iterations; is the floor rounding symbol; A cosine function is used to make the population size change periodically during the iteration process; Cycle parameters for controlling the frequency of population reduction; S83. The motor power adjustment mechanism is simulated by simulating different defense strategies of crested porcupines against predators. Each defense strategy corresponds to a different adjustment method of the motor power to cope with different working conditions. The defense strategies include a first defense strategy, a second defense strategy, a third defense strategy and a fourth defense strategy. The first defense strategy includes: In each iteration, the motor power of each individual is updated by the individual motor power update formula; the individual motor power update formula is: ; in, For the The individual in The motor power of the iteration; is the optimal motor power in the current population; are other individuals randomly selected from the population; is the weight factor that controls the speed at which individuals move toward the optimal motor power in the current population; A weight factor that controls the speed at which individuals move toward other randomly selected individuals; The weight factor is adjusted by the proportional adjustment formula and weight factor The ratio is dynamically adjusted; the ratio adjustment formula is: ; in, is the change amplitude adjustment factor; is the balance factor; is the speed adjustment factor; is the maximum limit value.

[0013] Furthermore, the second defense strategy includes: When an individual deviates from the optimal power, the perturbation update formula is introduced to accelerate the individual to approach the average objective function of the population through the perturbation of the objective function; The perturbation update formula is: ; in, is a symbolic function; is the objective function; is the average objective function of the current population; is the disturbance adjustment factor; The third defense strategy includes: The global motor power candidate solution search is perturbed and enhanced by the smell optimization update formula; the smell optimization update formula is: ; in, is the search direction control factor; It is a defense factor; A tuning parameter to control the breadth of the search; Adjustment parameters to control search accuracy; The search direction control factor is constrained by the dynamic disturbance limitation formula, and the dynamic disturbance limitation formula is: ;in, is the control factor of the search direction after restriction; The current iteration progress; is the progress influencing factor; is the population size influencing factor; The fourth defense strategy includes: The motor power candidate solution is locally disturbed through the physical attack optimization update formula to adjust the motor power; the physical attack optimization update formula is: ; in, is the convergence speed factor, controlling the intensity of the disturbance; A factor to control the perturbation intensity in physical attack optimization; For the The fitness value of each individual; Through the objective function To verify the fitness value of the candidate solution of motor power, so as to determine whether the motor power is optimal; objective function for: ; in, is the target motor power value; To preset the optimal motor power threshold; Motor power deviation influencing factors; At the end of each iteration, the objective function value of the current motor power candidate solution is evaluated to see whether it reaches the preset optimal motor power value. If it is reached, the iteration is stopped; if it is not reached, the iteration is continued until the maximum number of iterations is reached; when the preset optimal motor power threshold is reached , take it as the final motor power, which is the optimal motor power.

[0014] The intelligent power control system of the food processor includes: A data collection module is used to collect comprehensive operation data of the food stick; A data processing module, used for pre-processing the collected comprehensive operation data of the food processor to obtain a comprehensive operation characteristic data set; An intelligent power evaluation module, used to obtain an operating power prediction model based on a comprehensive operating characteristic data set, and to predict the operating power of the food processor through the operating power prediction model; A power anomaly detection module, used to compare the predicted operating power of the food processor with the preset operating power of the food processor to determine whether there is an anomaly in the operating power of the food processor; The power control adjustment module automatically generates a warning message to the intelligent power control terminal if the operating power of the food processor is abnormal; and automatically adjusts the motor power through an improved adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

[0015] The technical effects and advantages of the intelligent power control method and system of the cooking stick of the present invention are as follows: By continuously evaluating the working status of the cooking stick, users can know in time whether the device is in an unloaded, normal load or high load state, helping users to better adjust the usage or perform maintenance. Judging the working status of the cooking stick helps to determine whether the device is running at the optimal workload, avoiding unnecessary energy consumption and improving work efficiency. By dynamically adjusting the motor power through a population-based adaptive algorithm, it is possible to ensure that the food processor always stays within the optimal power range under different working conditions to avoid overload; this can improve the working efficiency of the equipment and improve performance stability; by simulating the defense strategy of the crested porcupine, a variety of adjustment methods are used in the process of motor power adjustment, which allows the system to flexibly respond to different working conditions (such as high load, normal load, no load, etc.), thereby achieving intelligent self-adjustment and reducing human intervention; each defense strategy can be dynamically adjusted for specific situations, making the system more intelligent and able to automatically optimize the motor power in actual operation to cope with different load requirements; through the proportional adjustment formula, the proportion of the weight factor is dynamically adjusted, which helps to balance the relationship between exploration and utilization, so that the system can flexibly find the best compromise between the global optimum and the local optimum, thereby better coping with the uncertainty in the process of motor power adjustment; By simulating the mechanism of smell optimization to enhance global search, expand the search range, avoid early convergence, improve the breadth and diversity of the search, and find the possible optimal motor power configuration in a larger search space; by optimizing the candidate motor power solutions through local perturbations, it is possible to quickly adjust undesirable solutions, increase the diversity of solutions, avoid stagnation in the search process, and promote the algorithm to quickly reach the local optimal solution; by limiting the search direction control factor, the breadth and accuracy of the search are adjusted, so that the algorithm can widely explore the solution space in the early stage, and gradually focus on fine-tuning in the later stage, so as to avoid premature convergence or falling into the local optimum; by performing local perturbations through physical attack optimization, undesirable solutions can be quickly corrected, and smell optimization provides a global perspective to help the algorithm avoid falling into the local optimal solution; this combination makes the system more robust and able to adapt to complex and changeable working conditions; the fitness of the candidate motor power solutions is evaluated through the objective function to ensure that only the motor power configuration that best meets the requirements will be retained, ensuring that each candidate solution can be close to the optimal motor power value after optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic flow chart of the intelligent power control method of the food processor of the present invention; Figure 2 It is a schematic diagram of the structure of the intelligent power control system of the food processor of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 See also Figure 1 As shown, the intelligent power control method of the food processor in this embodiment includes: S1. Collect comprehensive operation data of the food stick; S2, preprocessing the collected comprehensive operation data of the food stick to obtain a comprehensive operation feature data set; S3, training an operation power prediction model according to the comprehensive operation feature data set, and predicting the operation power of the food processor by the operation power prediction model; S4, comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal; S5. If the operating power of the food processor is abnormal, a warning message is automatically generated to the intelligent power control terminal; and the motor power is automatically adjusted by improving the adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

[0019] The comprehensive operation data of the cooking stick includes the working status data, working position data and safety monitoring data of the cooking stick; the working status data includes the stirring resistance, load size and rotation speed of the cooking stick; the working position data includes the stirring depth and stirring angle of the cooking stick; the safety monitoring data includes the temperature of the motor, the working time of the motor, the vibration amplitude and the vibration frequency.

[0020] The working status data is collected through the torque sensor, current sensor and speed sensor; the torque sensor is used to measure the stirring resistance of the food processor, and indirectly reflects the resistance during the stirring process by measuring the torque of the rotating shaft (i.e. the torque applied during rotation). The greater the stirring resistance, the greater the torque value; the current sensor is used to reflect the load of the food processor by monitoring the current consumption. When the load of the food processor increases, the motor needs more current to maintain operation. The speed sensor is used to accurately measure the speed of the food processor and can sense the rotation rate of the rotating shaft. The working position data is collected through the ultrasonic sensor and the angle sensor. The ultrasonic sensor is used to measure the stirring depth of the food processor and uses the ultrasonic propagation time to detect the distance between the food processor and the liquid surface or the bottom of the container, thereby determining the stirring depth. The angle sensor is used to measure the angle of the stirring rod relative to the vertical axis, so as to determine the stirring angle of the food processor and ensure that the food processor is stirred at an ideal angle. The safety monitoring data is collected through temperature sensors, timers and vibration sensors. The temperature sensor is used to monitor the temperature of the motor during the operation of the food processor in real time to ensure that the temperature control of the motor is normal during operation and prevent damage caused by overheating. The timer is used to record the running time of the motor, helping to analyze the working status and predict the service life of the motor; the vibration sensor is used to monitor the vibration amplitude and frequency generated during the operation of the food processor, which helps to judge the stability and working condition of the motor, as well as to detect potential failure risks at an early stage.

[0021] The method of preprocessing the collected comprehensive operation data of the food stick to obtain a comprehensive operation feature data set includes: The density clustering algorithm is used to identify and eliminate outliers in the working status data, working position data and safety monitoring data of the cooking stick, and the processed working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the working status feature data set, working position feature data set and safety monitoring feature data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, and finally the normalized working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the normalized working status feature data set, working position feature data set and safety monitoring feature data set are fused through a weighted formula to obtain a comprehensive feature data set.

[0022] The method of fusing the normalized working state feature data set, working position feature data set and safety monitoring feature data set through a weighted formula to obtain a comprehensive feature data set includes: The normalized working state feature data set, working position feature data set and safety monitoring feature data set are fused through a weighted formula to obtain a comprehensive feature data set; the normalized working state feature data set is recorded as , the normalized working position feature dataset is recorded as ; The normalized safety monitoring feature data set is recorded as ; The weighted formula is: ; in, It is a comprehensive feature dataset; is the weight coefficient of the normalized working status feature data set; is the normalized work position feature dataset; is the weight coefficient of the normalized safety monitoring feature data set.

[0023] The training method for running the power prediction model includes; The dataset is divided into training set, validation set and test set to train the model, evaluate the model performance and verify the generalization ability of the model; the sample set is a subset of the dataset, each sample set includes the historical comprehensive operation feature dataset and the corresponding operation power of the cooking stick; GBDT is selected as the specific implementation of the gradient boosting tree model to handle the regression task; Initialize GBDT parameters and define the objective function; GBDT parameters include the maximum number of leaf nodes in each tree, learning rate, number of trees, and maximum tree depth; use the historical comprehensive operation feature dataset as input data and the corresponding cooking stick operation power as output label to train the operation power prediction model; the operation power prediction model is a gradient boosting tree model; Use mean squared error as the loss function to measure the difference between the model's predicted value and the actual value; In each iteration, GBDT builds a new decision tree to fit the negative gradient of the loss function of the previous step, uses the negative gradient of the objective function as the learning target of the new tree, and adjusts the contribution of the new tree to the final result through the learning rate to minimize the loss function. Use the validation set to evaluate the performance of the model, tune the model, and adjust the model parameters based on its performance feedback until the model performance no longer improves or reaches the preset stopping condition; use the trained operating power prediction model to predict the current comprehensive operating feature data set to obtain the operating power of the food stick.

[0024] The method of comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal includes: If the predicted operating power of the cooking stick is less than or greater than the preset operating power of the cooking stick, it is determined that the operating power of the cooking stick is abnormal; If the predicted operating power of the cooking stick is equal to the preset operating power of the cooking stick, it is determined that there is no abnormality in the operating power of the cooking stick.

[0025] Different working states include high-load working state, normal-load working state and no-load state; The working status of the cooking stick is evaluated by the status evaluation formula, which is: ; in, is the working status value of the cooking stick; is the stirring resistance of the blender; The load size of the cooking stick; is the rotation speed of the food processor; is the factor affecting the working state of the stirring resistance of the food processor; is the factor affecting the working state of the food processor's load size; is the factor affecting the working state of the food processor's rotation speed; The preset first load working state threshold of the food processor is , the second load working state threshold of the cooking stick is ;like , then the working state of the cooking stick is judged to be no-load state; if , then the working state of the cooking stick is judged to be a normal working state; if , it is judged that the working state of the cooking stick is a high-load working state.

[0026] The method of automatically adjusting the motor power by improving the adaptive algorithm so that the food processor maintains the optimal power range under different working conditions includes: S81, generate by initializing the candidate solution population formula motor power candidate solutions, each of which is an individual in the population; The motor power candidate solutions constitute a population; the population of motor power candidate solutions is initialized to find the optimal motor power; each individual in the population represents a motor power setting scheme, and the motor power search range is determined by the upper and lower limits of the motor power; the formula for initializing the candidate solution population is: ;in, For the The motor power value of each individual; is the lower limit of the motor power value; is the upper limit of the motor power value; It is a randomly generated value between 0 and 1, which is used to ensure the randomness of the motor power value; is the index of the individual, ; is the population size, i.e., the number of candidate solutions for motor power; S82. In order to improve search efficiency and maintain diversity, a cyclic population reduction mechanism is introduced to make the population size change dynamically. The cyclic population reduction technology is used to reduce the population size through the cyclic population reduction formula. The cyclic population reduction formula is: ; Among them, if the current number of iterations When it is divisible by the periodic parameter that controls the frequency of population reduction, the population size is dynamically adjusted according to the number of iterations through the cosine function, that is, ; If the current number of iterations If it cannot be divided by the period parameter that controls the frequency of population reduction, then The population size at the iteration is the maximum size of the population. ; For the The population size at the iteration; is the minimum size of the population; is the maximum size of the population; is the number of current iterations; is the maximum number of iterations; is the floor rounding symbol; In order to make the population size present a cosine function that changes periodically during the iteration process, as the number of iterations increases As increases, the cosine value decreases from 1 to -1, from the maximum size of the population to the minimum size. This periodic adjustment helps the algorithm to keep more individuals in the early stage, thereby exploring a wider solution space, and gradually reduce the population size in the later stage to accelerate convergence; Cycle parameters for controlling the frequency of population reduction; S83. The motor power adjustment mechanism is simulated by simulating different defense strategies of crested porcupines against predators. Each defense strategy corresponds to a different adjustment method of the motor power to cope with different working conditions. The defense strategies include a first defense strategy, a second defense strategy, a third defense strategy and a fourth defense strategy. The first defense strategy includes: In each iteration, the motor power of each individual is updated by the individual motor power update formula; the individual motor power update formula is: ; in, For the The individual in The motor power of the iteration; is the optimal motor power in the current population; are other individuals randomly selected from the population; is the weight factor that controls the speed at which individuals move toward the optimal motor power in the current population; A weight factor that controls the speed at which individuals move toward other randomly selected individuals; The weight factor is adjusted by the proportional adjustment formula and weight factor The ratio is dynamically adjusted; the ratio adjustment formula is: ;in, is the change amplitude adjustment factor, used to control the weight factor and weight factor How much the proportion of changes when the population size changes; is the balance factor, controlling the weight factor and weight factor The benchmark value of the ratio plays a role in balancing the effect of population size on the ratio; Speed ​​adjustment factor, used to control the weight factor and weight factor How fast the proportion of changes as population size increases; is the maximum limit value, used to control The upper limit prevents Become too big.

[0027] For example, the weight factor is 0.5, the change range adjustment factor 1, the balance factor 2, speed adjustment factor 0.5, the maximum limit value is 2, the current population size is 100, then the control weight factor for ,because Less than , so the final control weight factor is 0.26.

[0028] The second defense strategy includes: When an individual deviates from the optimal power, the perturbation update formula is introduced to accelerate the individual to approach the average objective function of the population through the perturbation of the objective function; The perturbation update formula is: ; in, is a sign function used to control the direction of motor power update to ensure that the algorithm is optimized in the correct direction; is the objective function, which evaluates the performance of the current motor power; is the average objective function of the current population; is the disturbance adjustment factor, which controls the intensity of the sound disturbance; The third defense strategy includes: The global motor power candidate solution search is perturbed and enhanced by the smell optimization update formula; the smell optimization update formula is: ; in, is the search direction control factor, which adjusts the breadth of the search and controls the intensity of the disturbance. , which can balance the global exploration and local development of the search process; is the defense factor, which gradually decreases with the increase of the number of iterations, indicating that the intensity of the perturbation gradually weakens as the search progresses, which means that in the initial stage, the search range is wider to increase the exploration of the solution space, and as the number of iterations increases, it gradually converges to a more refined solution; A tuning parameter to control the breadth of the search; Adjustment parameters to control search accuracy; The search direction control factor is constrained by the dynamic disturbance limitation formula, and the dynamic disturbance limitation formula is: ;in, is the control factor of the search direction after restriction; The current iteration progress; It is the progress influencing factor, which is used to control the current iteration progress. Control factor for search direction The impact of is the population size influencing factor, used to control the population size Control factor for search direction The impact of When the number of iterations When it is small, the progress impact factor Smaller, resulting in The larger the value, the more extensive the search and the more potential solutions are explored; The increase in progress impact factor Also increases, resulting in the progress impact factor The value of gradually decreases. In this way, the algorithm gradually converges, focusing on refining the search and avoiding over-exploration. The larger the population, the wider the search space, and the population size in the formula By increasing the diversity of search, the exploration space is more extensive; by adjusting , and , the balance between exploration and exploitation can be finely adjusted to ensure that the optimization process neither converges prematurely nor wastes too much search resources.

[0029] The fourth defense strategy includes: The motor power candidate solution is locally disturbed through the physical attack optimization update formula to adjust the motor power; the physical attack optimization update formula is: ;in, It is the convergence speed factor, which controls the intensity of the disturbance. By adjusting this factor, the intensity of the attack can be controlled and the magnitude of the disturbance can be affected. A factor to control the perturbation intensity in physical attack optimization, which mainly serves to make strong local perturbations in the search space in the late stages of optimization to help fine-tune the motor power; For the The fitness value of each individual represents the fitness of the candidate solution of the motor power; Through the objective function To verify the fitness value of the candidate solution of motor power, so as to determine whether the motor power is optimal; objective function for: ;in, is the target motor power value; To preset the optimal motor power threshold; Motor power deviation influence factor, used to control the influence of motor power deviation on the objective function; For the The fitness value of each individual; At the end of each iteration, the objective function value of the current motor power candidate solution is evaluated to see whether it reaches the preset optimal motor power value. If it is reached, the iteration is stopped; if it is not reached, the iteration is continued until the maximum number of iterations is reached; when the preset optimal motor power threshold is reached , take it as the final motor power, which is the optimal motor power.

[0030] The preset operating power of the food processor is set by the staff. The operating powers of different food processors are collected through the intelligent power control terminal, and the average value of the operating powers of multiple food processors is taken as the preset operating power of the food processor. Similarly, the preset optimal motor power threshold is set.

[0031] In this embodiment, by continuously evaluating the working state of the food stick, it is possible to timely understand whether the device is in an unloaded, normal load or high load state, thereby helping the user to better adjust the usage mode or perform maintenance; judging the working state of the food stick helps to judge whether the device is operating under the optimal workload, thereby avoiding unnecessary energy consumption and improving work efficiency; By dynamically adjusting the motor power through a population-based adaptive algorithm, it is possible to ensure that the food processor always stays within the optimal power range under different working conditions to avoid overload; this can improve the working efficiency of the equipment and improve performance stability; by simulating the defense strategy of the crested porcupine, a variety of adjustment methods are used in the process of motor power adjustment, which allows the system to flexibly respond to different working conditions (such as high load, normal load, no load, etc.), thereby achieving intelligent self-adjustment and reducing human intervention; each defense strategy can be dynamically adjusted for specific situations, making the system more intelligent and able to automatically optimize the motor power in actual operation to cope with different load requirements; through the proportional adjustment formula, the proportion of the weight factor is dynamically adjusted, which helps to balance the relationship between exploration and utilization, so that the system can flexibly find the best compromise between the global optimum and the local optimum, thereby better coping with the uncertainty in the process of motor power adjustment; By simulating the mechanism of smell optimization to enhance global search, expand the search range, avoid early convergence, improve the breadth and diversity of the search, and find the possible optimal motor power configuration in a larger search space; by optimizing the candidate motor power solutions through local perturbations, it is possible to quickly adjust undesirable solutions, increase the diversity of solutions, avoid stagnation in the search process, and promote the algorithm to quickly reach the local optimal solution; by limiting the search direction control factor, the breadth and accuracy of the search are adjusted, so that the algorithm can widely explore the solution space in the early stage, and gradually focus on fine-tuning in the later stage, so as to avoid premature convergence or falling into the local optimum; by performing local perturbations through physical attack optimization, undesirable solutions can be quickly corrected, and smell optimization provides a global perspective to help the algorithm avoid falling into the local optimal solution; this combination makes the system more robust and able to adapt to complex and changeable working conditions; the fitness of the candidate motor power solutions is evaluated through the objective function to ensure that only the motor power configuration that best meets the requirements will be retained, ensuring that each candidate solution can be close to the optimal motor power value after optimization.

[0032] Example 2 See also Figure 2 As shown, the intelligent power control system of the food processor in this embodiment includes: A data collection module is used to collect comprehensive operation data of the food stick; A data processing module, used for pre-processing the collected comprehensive operation data of the food processor to obtain a comprehensive operation characteristic data set; A power evaluation module, used to obtain an operating power prediction model based on a comprehensive operating characteristic data set, and to predict the operating power of the food processor by using the operating power prediction model; A power anomaly detection module, used to compare the predicted operating power of the food processor with the preset operating power of the food processor to determine whether there is an anomaly in the operating power of the food processor; The power control adjustment module automatically generates a warning message to the intelligent power control terminal if the operating power of the food processor is abnormal; and automatically adjusts the motor power through an improved adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

[0033] Since the electronic device introduced in this embodiment is an electronic device used to implement the intelligent power control method and system based on the food stick in the embodiment of this application, based on the intelligent power control method and system of the food stick introduced in the embodiment of this application, the technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel in this field implement the electronic device used by the intelligent power control method and system of the food stick in the embodiment of this application, it belongs to the scope of protection of this application.

[0034] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0035] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent power control method for a food processor, characterized in that: include: S1. Collect comprehensive operation data of the food stick; S2, preprocessing the collected comprehensive operation data of the food stick to obtain a comprehensive operation feature data set; S3, training an operation power prediction model according to the comprehensive operation feature data set, and predicting the operation power of the food processor by the operation power prediction model; S4, comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal; S5. If the operating power of the food processor is abnormal, a warning message is automatically generated to the intelligent power control terminal; and the motor power is automatically adjusted by improving the adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

2. The intelligent power control method of the food processor according to claim 1, characterized in that: The comprehensive operation data of the cooking stick includes the working status data, working position data and safety monitoring data of the cooking stick; the working status data includes the stirring resistance, load size and rotation speed of the cooking stick; the working position data includes the stirring depth and stirring angle of the cooking stick; the safety monitoring data includes the temperature of the motor, the working time of the motor, the vibration amplitude and the vibration frequency.

3. The intelligent power control method of the food processor according to claim 2, characterized in that: The method of preprocessing the collected comprehensive operation data of the food processor to obtain a comprehensive operation feature data set includes: The density clustering algorithm is used to identify and eliminate outliers in the working status data, working position data and safety monitoring data of the cooking stick, and the processed working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the working status feature data set, working position feature data set and safety monitoring feature data set are normalized by standard deviation and converted into a standard normal distribution with a mean of 0 and a standard deviation of 1, and finally the normalized working status feature data set, working position feature data set and safety monitoring feature data set are obtained; the normalized working status feature data set, working position feature data set and safety monitoring feature data set are fused through a weighted formula to obtain a comprehensive feature data set.

4. The intelligent power control method of the food processor according to claim 3, characterized in that: The method of fusing the normalized working state feature data set, working position feature data set and safety monitoring feature data set through a weighted formula to obtain a comprehensive feature data set includes: The normalized working status feature dataset is recorded as , the normalized working position feature dataset is recorded as ; The normalized safety monitoring feature data set is recorded as ; The weighted formula is: ； in, It is a comprehensive feature dataset; is the weight coefficient of the normalized working status feature data set; is the normalized work position feature dataset; is the weight coefficient of the normalized safety monitoring feature data set.

5. The intelligent power control method of the food processor according to claim 4, characterized in that: The training method of the operating power prediction model includes: Divide the data set into training set, validation set and test set to train the model, evaluate model performance and verify the model generalization ability; The sample set is a subset of the data set. Each sample set includes a historical comprehensive operation feature data set and the corresponding operation power of the cooking stick. GBDT is selected as the specific implementation of the gradient boosting tree model to handle the regression task. Initialize GBDT parameters and define the objective function; GBDT parameters include the maximum number of leaf nodes in each tree, learning rate, number of trees, and maximum depth of trees; use the historical comprehensive operation feature data set as input data and the corresponding operation power of the food stick as output label to train the operation power prediction model; the operation power prediction model is a gradient boosting tree model; Use mean squared error as the loss function to measure the difference between the model's predicted value and the actual value; In each iteration, GBDT builds a new decision tree to fit the negative gradient of the loss function of the previous step, uses the negative gradient of the objective function as the learning target of the new tree, and adjusts the contribution of the new tree to the final result through the learning rate to minimize the loss function. Use the validation set to evaluate the performance of the model, tune the model, and adjust the model parameters based on its performance feedback until the model performance no longer improves or reaches the preset stopping condition; use the trained operating power prediction model to predict the current comprehensive operating feature data set to obtain the operating power of the food stick.

6. The intelligent power control method of the food processor according to claim 5, characterized in that: The method of comparing the predicted operating power of the cooking stick with the preset operating power of the cooking stick to determine whether the operating power of the cooking stick is abnormal includes: If the predicted operating power of the cooking stick is less than or greater than the preset operating power of the cooking stick, it is determined that the operating power of the cooking stick is abnormal; If the predicted operating power of the cooking stick is equal to the preset operating power of the cooking stick, it is determined that there is no abnormality in the operating power of the cooking stick.

7. The intelligent power control method of the food processor according to claim 6, characterized in that: The different working states include a high-load working state, a normal-load working state and a no-load state; The working status of the cooking stick is evaluated by the status evaluation formula, which is: ； in, is the working status value of the cooking stick; is the stirring resistance of the food processor; The load size of the cooking stick; is the rotation speed of the food processor; is the factor affecting the working state of the stirring resistance of the food processor; is the factor affecting the working state of the food processor's load size; is the factor affecting the working state of the food processor's rotation speed; The preset first load working state threshold of the food processor is , the second load working state threshold of the cooking stick is ;like , then the working state of the cooking stick is judged to be no-load state; if , then the working state of the cooking stick is judged to be a normal working state; if , it is judged that the working state of the cooking stick is a high-load working state.

8. The intelligent power control method of the food processor according to claim 7, characterized in that: The method of automatically adjusting the motor power by improving the adaptive algorithm so that the food processor maintains the optimal power range under different working conditions includes: S81, generate by initializing the candidate solution population formula motor power candidate solutions, each of which is an individual in the population; The motor power candidate solutions constitute a population; the population of motor power candidate solutions is initialized to find the optimal motor power; each individual in the population represents a motor power setting scheme, and the motor power search range is determined by the upper and lower limits of the motor power; the formula for initializing the candidate solution population is: ;in, For the The motor power value of each individual; is the lower limit of the motor power value; is the upper limit of the motor power value; It is a randomly generated value between 0 and 1, which is used to ensure the randomness of the motor power value; is the index of the individual, ; is the population size, i.e., the number of candidate solutions for motor power; S82. Use cyclic population reduction technology to reduce the population size through the cyclic population reduction formula. The cyclic population reduction formula is: ； Among them, if the current number of iterations When it is divisible by the periodic parameter that controls the frequency of population reduction, the population size is dynamically adjusted according to the number of iterations through the cosine function, that is, ; If the current number of iterations If it cannot be divided by the period parameter that controls the frequency of population reduction, then The population size at the iteration is the maximum size of the population. ; For the The population size at the iteration; is the minimum size of the population; is the maximum size of the population; is the number of current iterations; is the maximum number of iterations; is the floor rounding symbol; A cosine function is used to make the population size change periodically during the iteration process; Cycle parameters for controlling the frequency of population reduction; S83. The motor power adjustment mechanism is simulated by simulating different defense strategies of crested porcupines against predators. Each defense strategy corresponds to a different adjustment method of the motor power to cope with different working conditions. The defense strategies include a first defense strategy, a second defense strategy, a third defense strategy and a fourth defense strategy. The first defense strategy includes: In each iteration, the motor power of each individual is updated by the individual motor power update formula; the individual motor power update formula is: ； in, For the The individual in The motor power of the iteration; is the optimal motor power in the current population; are other individuals randomly selected from the population; is the weight factor that controls the speed at which individuals move toward the optimal motor power in the current population; A weight factor that controls the speed at which individuals move toward other randomly selected individuals; The weight factor is adjusted by the proportional adjustment formula and weight factor The ratio is dynamically adjusted; the ratio adjustment formula is: ;in, is the change amplitude adjustment factor; is the balance factor; is the speed adjustment factor; is the maximum limit value.

9. The intelligent power control method of the food processor according to claim 8, characterized in that: The second defense strategy includes: When an individual deviates from the optimal power, the perturbation update formula is introduced to accelerate the individual to approach the average objective function of the population through the perturbation of the objective function; The perturbation update formula is: ； in, is a symbolic function; is the objective function; is the average objective function of the current population; is the disturbance adjustment factor; The third defense strategy includes: The global motor power candidate solution search is perturbed and enhanced by the smell optimization update formula; the smell optimization update formula is: ； in, is the search direction control factor; It is a defense factor; A tuning parameter to control the breadth of the search; Adjustment parameters to control search accuracy; The search direction control factor is constrained by the dynamic disturbance limitation formula, and the dynamic disturbance limitation formula is: ;in, is the control factor of the search direction after restriction; The current iteration progress; is the progress influencing factor; is the population size influencing factor; The fourth defense strategy includes: The motor power candidate solution is locally disturbed through the physical attack optimization update formula to adjust the motor power; the physical attack optimization update formula is: ;in, is the convergence speed factor, controlling the intensity of the disturbance; A factor to control the perturbation intensity in physical attack optimization; For the The fitness value of each individual; Through the objective function To verify the fitness value of the candidate solution of motor power, so as to determine whether the motor power is optimal; objective function for: ;in, is the target motor power value; To preset the optimal motor power threshold; Motor power deviation influencing factors; At the end of each iteration, the objective function value of the current motor power candidate solution is evaluated to see whether it reaches the preset optimal motor power value. If it is reached, the iteration is stopped; if it is not reached, the iteration is continued until the maximum number of iterations is reached; when the preset optimal motor power threshold is reached , take it as the final motor power, which is the optimal motor power.

10. An intelligent power control system for a food stick, used to implement the intelligent power control method for a food stick according to any one of claims 1 to 9, characterized in that: include: A data collection module is used to collect comprehensive operation data of the food stick; A data processing module, used for pre-processing the collected comprehensive operation data of the food processor to obtain a comprehensive operation characteristic data set; An intelligent power evaluation module, used to obtain an operating power prediction model based on a comprehensive operating characteristic data set, and to predict the operating power of the food processor through the operating power prediction model; A power anomaly detection module, used to compare the predicted operating power of the food processor with the preset operating power of the food processor to determine whether there is an anomaly in the operating power of the food processor; The power control adjustment module automatically generates a warning message to the intelligent power control terminal if the operating power of the food processor is abnormal; and automatically adjusts the motor power through an improved adaptive algorithm, so that the food processor maintains the optimal power range under different working conditions.

Images