A hair dryer automatic control method and system

Abstract

The present invention discloses a method and system for automatic control of a hair dryer, and relates to the technical field of hair dryer control. A hair dryer automatic control system includes: a hair dryer parameter processing module, a hair dryer risk assessment module and a hair dryer automatic control module. The present invention can dynamically grasp the operating status of the equipment and improve the response speed to potential abnormalities by acquiring the electrical variable parameter information of the hair dryer main circuit in real time; the hair dryer electricity feature extraction model performs multi-dimensional feature analysis on the monitoring parameters, effectively combines the stable working mode, can accurately identify risk features, and provide reliable data support for subsequent risk level assessment; the double convolution form combining CNN and SVM is adopted to achieve high efficiency of feature extraction and accuracy of classification, and based on risk features and monitoring models, it can provide graded warning of the risk level of the hair dryer, help identify high-risk states in advance, and avoid further expansion of faults.

Description

Technical Field

[0001] The present invention relates to the technical field of hair dryer control, and in particular to an automatic control method and system for a hair dryer. Background Art

[0002] With the diversification of functions and increase in power of modern hair dryers, their electricity demand has increased significantly. However, in actual use, problems such as unstable voltage, overload or circuit abnormality may pose potential safety hazards to equipment and users. At present, most hair dryers still use a fixed power operation mode and lack the ability to monitor and adjust electrical parameters in real time, making it difficult to respond to risks caused by electrical abnormalities in a timely manner. Traditional overheating protection technology is mainly based on the principle of temperature control. Although it can reduce the hazards caused by high temperature, it cannot provide effective protection against electrical failures.

[0003] Therefore, there is a need for an intelligent adjustment technology based on real-time electrical variable monitoring, which can quickly adjust the operating status of the hair dryer when abnormal changes in voltage or current are detected, such as dynamically adjusting power or automatically stopping operation, thereby effectively preventing accidents and improving the safety of the equipment and user experience. Summary of the invention

[0004] The present invention aims to provide a hair dryer automatic control method and system, which automatically monitor the power safety of the hair dryer and provide an automatic control strategy.

[0005] A method for automatically controlling a hair dryer comprises the following steps:

[0006] When the hair dryer starts to work, the hair dryer stable working mode is obtained; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current Monitoring data at all times; based on the electrical variable parameter information to be analyzed and the hair dryer electricity consumption feature extraction model, the hair dryer electricity consumption risk characteristics are obtained;

[0007] The hair dryer electricity consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features based on the hair dryer's stable working mode, providing data support for subsequent risk level analysis.

[0008] Risk monitoring is performed based on the hair dryer electricity risk characteristics, the hair dryer stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on the double convolution form;

[0009] The corresponding blower control strategy is matched according to the blower risk level warning; when the blower risk level warning exceeds the preset highest blower risk level warning, the working circuit of the blower is switched from the blower main circuit to the blower auxiliary circuit to realize automatic control of the blower.

[0010] As a preferred technical solution of the present invention, the hair dryer power consumption feature extraction model includes a weight factor calculation layer, a power load calculation layer and a power consumption feature output layer;

[0011] The weight factor calculation layer is used to utilize the formula Calculate the power disturbance factor ;in, Indicates the first Monitoring data at all times, Indicates the first Voltage value, represents the power consumption constraint index, represents a risk assessment indicator; Indicates The power consumption disturbance factor at the moment is the predicted power consumption disturbance factor at the next moment; the power consumption constraint index and risk assessment index are determined based on the hair dryer's historical data and the hair dryer's stable working mode;

[0012] The power load calculation layer is used to utilize the formula Calculate the first Predicted power load value at the time ;

[0013] The power consumption feature output layer is used to predict the power load value Perform feature extraction to obtain the risk characteristics of electricity consumption of hair dryers.

[0014] As a preferred technical solution of the present invention, the specific steps of determining the power consumption constraint index and the risk assessment index include:

[0015] Collect the target user's hair dryer operation history data; perform work mode cluster analysis based on the target user's hair dryer operation history data, and build a user hair dryer use work mode matching library;

[0016] According to the target user's hair dryer operation history data and the user's hair dryer usage work mode matching library, K hair dryer electricity constraint indicator individuals H are constructed. k , k=1,2,…,K; where the hair dryer electricity consumption constraint index individual H k It contains the power consumption constraint index and risk assessment index of each standard user in the stable working mode; the K hair dryer power consumption constraint index individuals H kCombination, get the iterative population of hair dryer electricity consumption constraint index; set the maximum number of iterations, set the hair dryer electricity consumption constraint index individual H k The fitness is D k ;

[0017] Specific steps to calculate fitness:

[0018] Build a digital twin model of the hair dryer's electricity consumption, using formula A k =α*C k -β*R k Calculate the hair dryer evaluation index A k , where C k H is the electricity consumption constraint indicator of the hair dryer k The power consumption constraint index in R k H is the electricity consumption constraint indicator of the hair dryer k The risk assessment index in is, α is the weight value of the power consumption constraint index, β is the weight value of the risk assessment index; using formula B k =Q1*(|X k1 -X b1 |) / X k1 +…+Q m *(|X km -X bm |) / X km +…+Q M *(|X kM -X bM |) / X kM The actual hair dryer evaluation index B is calculated by the hair dryer electricity digital twin model. k ; where m = 1, 2, ..., M; X km represents the mth actual hair dryer electrical variable parameter value, X bm represents the target value corresponding to the mth actual hair dryer electrical variable parameter value, Q m Represents the weight value corresponding to the mth item;

[0019] The hair dryer is rated A k And the actual hair dryer evaluation index B k The inverse of the Euclidean distance is taken as the fitness D k ;

[0020] The population iteration of the hair dryer electricity consumption constraint index iteration population is carried out. In the population iteration process, the championship method is used to select the hair dryer electricity consumption constraint index iteration population; the chromosome crossover method is used to crossover the hair dryer electricity consumption constraint index iteration population; the interchange mutation operator is used to mutate the hair dryer electricity consumption constraint index iteration population to generate a new hair dryer electricity consumption constraint index iteration population;

[0021] When the maximum number of iterations is reached, the hair dryer electricity constraint indicator individual corresponding to the maximum fitness is output, which is the optimal hair dryer electricity constraint indicator individual; the optimal hair dryer electricity constraint indicator individual and the user hair dryer working mode matching library are combined to obtain the user hair dryer mode indicator matching library; wherein the user hair dryer mode indicator matching library contains several groups of standard user stable working modes and corresponding electricity constraint indicators and risk assessment indicators.

[0022] As a preferred technical solution of the present invention, the hair dryer risk monitoring model includes a pattern feature matching layer, a risk monitoring feature recognition layer and a risk level warning output layer;

[0023] The mode feature matching layer is used to match the current working mode feature according to the stable working mode of the hair dryer;

[0024] The risk monitoring feature recognition layer is used to perform feature recognition based on the current working mode characteristics and the hair dryer electricity risk characteristics to obtain a hair dryer risk level warning;

[0025] The risk level warning output layer is used to output hair dryer risk level warnings.

[0026] As a preferred technical solution of the present invention, the specific steps of performing feature recognition at the risk monitoring feature recognition layer include:

[0027] A risk monitoring feature recognition layer is constructed based on the improved CNN model. The risk monitoring feature recognition layer includes an activation layer, three parallel convolutional layers, a pooling layer, a fully connected layer, and an SVM classifier.

[0028] The activation layer is used to process the current working mode characteristics and the hair dryer electricity risk characteristics using the activation function to obtain the current working mode feature tensor and the hair dryer electricity risk feature tensor;

[0029] In three parallel rows of convolutional layers, feature learning and recognition are performed on the current working mode feature tensor and the hair dryer electricity risk feature tensor at the same time to obtain a multi-channel convolution risk monitoring feature tensor;

[0030] The pooling layer is used to reduce the dimension of the multi-channel convolution risk monitoring feature tensor to obtain the multi-channel convolution risk monitoring reduced dimension feature tensor;

[0031] The fully connected layer is used to perform feature mapping on the multi-channel convolution risk monitoring dimensionality reduction feature tensor to obtain the multi-channel convolution risk monitoring feature vector;

[0032] The SVM classifier is used to label the multi-channel convolution risk monitoring feature vector with the risk level of hair dryer electricity consumption and obtain the risk level warning of the hair dryer.

[0033] As a preferred technical solution of the present invention, the specific steps of training the risk monitoring feature recognition layer include:

[0034] Collect several groups of verified hair dryer electricity usage feature recognition training samples; each group of verified hair dryer electricity usage feature recognition training samples contains a labeled risk level and hair dryer electricity usage feature pair; combine several groups of verified hair dryer electricity usage feature recognition training samples to obtain a hair dryer electricity usage feature recognition training set;

[0035] The hair dryer electricity consumption feature recognition training set is input into the risk monitoring feature recognition layer for model training to obtain the initial risk monitoring feature recognition layer; the initial risk monitoring feature recognition layer is evaluated; if the initial risk monitoring feature recognition layer passes the model evaluation, the initial risk monitoring feature recognition layer is used as the risk monitoring feature recognition layer in the hair dryer risk monitoring model; otherwise, the hair dryer electricity consumption feature recognition training set is used to continue model training.

[0036] As a preferred technical solution of the present invention, the specific steps of switching the working circuit of the hair dryer from the main circuit of the hair dryer to the auxiliary circuit of the hair dryer to realize automatic control of the hair dryer include:

[0037] When the monitored hair dryer risk level warning exceeds the preset highest hair dryer risk level warning, the connection of the hair dryer main circuit will be cut off and an alarm will be issued; at the same time, the hair dryer auxiliary circuit will be connected to switch the hair dryer from the current hair dryer stable working mode to the hair dryer safe working mode; when the hair dryer risk level warning is lower than the preset highest hair dryer risk level warning, the hair dryer's working circuit will be switched from the hair dryer auxiliary circuit to the hair dryer main circuit.

[0038] A hair dryer automatic control system, comprising:

[0039] The hair dryer parameter processing module includes a feature extraction unit; the feature extraction unit is used to obtain the stable working mode of the hair dryer when the hair dryer starts to work; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current The monitoring data at each moment; based on the electrical variable parameter information to be analyzed and the hair dryer power consumption feature extraction model, the hair dryer power consumption risk feature is obtained; the hair dryer power consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features in combination with the hair dryer's stable working mode, providing data support for subsequent risk level analysis;

[0040] The hair dryer risk assessment module includes a risk assessment unit; the risk assessment unit is used to perform risk monitoring based on the hair dryer's electricity risk characteristics, the hair dryer's stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on a double convolution form;

[0041] The blower automatic control module includes an automatic control unit; the automatic control unit is used to match the corresponding blower control strategy according to the blower risk level warning; when the blower risk level warning exceeds the preset highest blower risk level warning, the blower working circuit is switched from the blower main circuit to the blower auxiliary circuit to realize automatic control of the blower.

[0042] The present invention has the following advantages:

[0043] 1. The present invention can dynamically grasp the operating status of the equipment and improve the response speed to potential abnormalities by acquiring the electrical variable parameter information of the main circuit of the hair dryer in real time; the hair dryer electricity feature extraction model performs multi-dimensional feature analysis on the monitoring parameters, effectively combines the stable working mode, and can accurately identify risk characteristics, providing reliable data support for subsequent risk level assessment; the double convolution form combining CNN and SVM is adopted to achieve high efficiency of feature extraction and accuracy of classification. Based on risk characteristics and monitoring models, the risk level of the hair dryer can be graded and warned, which helps to identify high-risk states in advance and avoid further expansion of faults.

[0044] 2. The present invention collects the target user's hair dryer operation history data and performs work mode cluster analysis to build a user hair dryer use work mode matching library, realizes the adaptation and analysis of different user-specific work modes, and provides personalized electricity consumption constraints and risk assessments; through the weight factor calculation layer, the power load calculation layer and the power consumption feature output layer, the hair dryer power consumption data is subjected to multi-dimensional feature extraction, and combined with the stable working mode, the power consumption risk characteristics can be accurately identified, providing reliable data support for risk level warning and control strategies; through the comprehensive analysis and optimization of the hair dryer's power consumption behavior, not only the safety of the hair dryer operation is improved, but also fault downtime and energy waste are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The present invention is a schematic structural diagram of a hair dryer automatic control system used in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0047] Embodiment 1, a hair dryer automatic control method, comprising the following steps:

[0048] When the hair dryer starts to work, the hair dryer stable working mode is obtained; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current Monitoring data at all times; based on the electrical variable parameter information to be analyzed and the hair dryer electricity consumption feature extraction model, the hair dryer electricity consumption risk characteristics are obtained;

[0049] The hair dryer electricity consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features based on the hair dryer's stable working mode, providing data support for subsequent risk level analysis.

[0050] The electric variable parameter information to be analyzed represents the parameter information at the current monitoring moment, including voltage, current, real-time power and other information; the hair dryer stable working mode is the hair dryer current gear adjustment mode;

[0051] The hair dryer electricity consumption feature extraction model includes a weight factor calculation layer, a power load calculation layer and a power consumption feature output layer;

[0052] The weight factor calculation layer is used to utilize the formula Calculate the power disturbance factor ;in, Indicates the first Monitoring data at all times, Indicates the first Voltage value, represents the power consumption constraint index, represents a risk assessment indicator; Indicates The power consumption disturbance factor at the moment is the predicted power consumption disturbance factor at the next moment; the power consumption constraint index and risk assessment index are determined based on the hair dryer's historical data and the hair dryer's stable working mode;

[0053] The power load calculation layer is used to utilize the formula Calculate the first Predicted power load value at the time ;

[0054] The power consumption feature output layer is used to predict the power load value Perform feature extraction to obtain the risk characteristics of electricity consumption of hair dryers;

[0055] By collecting the target users' hair dryer operation history data and performing cluster analysis of the working modes, a user hair dryer working mode matching library was built, which enabled the adaptation and analysis of different users' specific working modes and provided personalized power consumption constraints and risk assessments. Through the weight factor calculation layer, power load calculation layer and power consumption feature output layer, multi-dimensional feature extraction was performed on the hair dryer power consumption data. Combined with the stable working mode, it can accurately identify the power consumption risk characteristics and provide reliable data support for risk level warning and control strategies.

[0056] The specific steps for determining power consumption constraint indicators and risk assessment indicators include:

[0057] Collect the target user's hair dryer operation history data; perform cluster analysis on the operation mode based on the target user's hair dryer operation history data, and build a user hair dryer usage work mode matching library; By collecting the target user's hair dryer operation history data and performing cluster analysis, a user-specific work mode matching library is built, which achieves accurate modeling of the user's power consumption constraint indicators and risk assessment indicators, and meets the diversified power consumption needs; different users have different usage conditions, and this user usage analysis technology can meet the actual needs of most users;

[0058] According to the target user's hair dryer operation history data and the user's hair dryer usage work mode matching library, K hair dryer electricity constraint indicator individuals H are constructed. k , k=1,2,…,K; where the hair dryer electricity consumption constraint index individual H k It contains the power consumption constraint index and risk assessment index of each standard user in the stable working mode; the K hair dryer power consumption constraint index individuals H k Combination, get the iterative population of hair dryer electricity consumption constraint index; set the maximum number of iterations, set the hair dryer electricity consumption constraint index individual H k The fitness is D k ;The maximum number of iterations is set by professional technicians based on actual conditions;

[0059] Specific steps to calculate fitness:

[0060] Build a digital twin model of the hair dryer's electricity consumption, using formula A k =α*C k -β*R k Calculate the hair dryer evaluation index A k , where C k H is the electricity consumption constraint indicator of the hair dryer k The power consumption constraint index in R k H is the electricity consumption constraint indicator of the hair dryer kThe risk assessment index in is, α is the weight value of the power consumption constraint index, β is the weight value of the risk assessment index; using formula B k =Q1*(|X k1 -X b1 |) / X k1 +…+Q m *(|X km -X bm |) / X km +…+Q M *(|X kM -X bM |) / X kM The actual hair dryer evaluation index B is calculated by the hair dryer electricity digital twin model. k ; where m = 1, 2, ..., M; X km represents the mth actual hair dryer electrical variable parameter value, X bm represents the target value corresponding to the mth actual hair dryer electrical variable parameter value, Q m Represents the weight value corresponding to the mth item;

[0061] The digital twin model combines historical data and real-time parameters to dynamically simulate and predict the electricity consumption behavior of the hair dryer, which can monitor and evaluate the operating status of the equipment in real time and improve the accuracy and timeliness of risk assessment.

[0062] The hair dryer is rated A k And the actual hair dryer evaluation index B k The inverse of the Euclidean distance is taken as the fitness D k ;

[0063] The population iteration of the hair dryer electricity consumption constraint index iteration population is carried out. In the population iteration process, the championship method is used to select the hair dryer electricity consumption constraint index iteration population; the chromosome crossover method is used to crossover the hair dryer electricity consumption constraint index iteration population; the interchange mutation operator is used to mutate the hair dryer electricity consumption constraint index iteration population to generate a new hair dryer electricity consumption constraint index iteration population;

[0064] By constructing an iterative population of power consumption constraint indicators for hair dryers and using the tournament method, crossover method and mutation operator to iteratively optimize the population, the optimal power consumption constraint indicator individual with the largest fitness can be effectively found to ensure the reliability and optimality of the control method.

[0065] When the maximum number of iterations is reached, the hair dryer power consumption constraint indicator individual corresponding to the maximum fitness is output, which is the optimal hair dryer power consumption constraint indicator individual; the optimal hair dryer power consumption constraint indicator individual and the user hair dryer working mode matching library are combined to obtain the user hair dryer mode indicator matching library; wherein the user hair dryer mode indicator matching library contains several groups of standard user stable working modes and corresponding power consumption constraint indicators and risk assessment indicators;

[0066] By iteratively optimizing the population and combining the digital twin model, the operating parameters and power consumption characteristics of the hair dryer are dynamically adjusted, ensuring the efficient adaptability of the system under various working modes. Through precise power consumption constraint indicator setting and risk prediction, the operating parameters of the hair dryer are optimized, effectively reducing energy consumption and improving energy efficiency. Through risk assessment and dynamic adjustment, the risk of failure caused by abnormal power consumption or excessive load during the operation of the hair dryer is reduced, and the reliability of equipment operation is improved. The optimal power consumption constraint indicator individual is combined with the user matching library to form a standardized mode indicator database, which is convenient for subsequent expansion and maintenance and has good portability and scalability.

[0067] Risk monitoring is performed based on the hair dryer electricity risk characteristics, the hair dryer stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on the double convolution form;

[0068] The hair dryer risk monitoring model includes a pattern feature matching layer, a risk monitoring feature identification layer, and a risk level warning output layer;

[0069] The mode feature matching layer is used to match the current working mode feature according to the stable working mode of the hair dryer;

[0070] The risk monitoring feature recognition layer is used to perform feature recognition based on the current working mode characteristics and the hair dryer electricity risk characteristics to obtain a hair dryer risk level warning;

[0071] The risk level warning output layer is used to output the hair dryer risk level warning;

[0072] The mode feature matching layer can quickly identify the deviation of the current operating state by matching the current working mode with the stable working mode, thereby improving the accuracy of risk identification. The risk monitoring feature recognition layer combines the CNN model and SVM classifier in the form of double convolution, combining the feature extraction capability of deep learning with the high efficiency of traditional classifiers, and can achieve efficient feature recognition and classification in complex data scenarios. Based on the real-time collected power consumption risk characteristics and the current working mode, the risk monitoring feature recognition layer can dynamically evaluate the operating status of the hair dryer, output risk level warnings in real time, and enhance the dynamic adaptability of the system. The risk level warning output layer provides multi-level risk warnings, which can effectively indicate potential operating risks and provide a reference for system management and maintenance decisions.

[0073] The specific steps of feature identification at the risk monitoring feature identification layer include:

[0074] A risk monitoring feature recognition layer is constructed based on the improved CNN model. The risk monitoring feature recognition layer includes an activation layer, three parallel convolutional layers, a pooling layer, a fully connected layer, and an SVM classifier.

[0075] The activation layer is used to process the current working mode characteristics and the hair dryer electricity risk characteristics using the activation function to obtain the current working mode feature tensor and the hair dryer electricity risk feature tensor;

[0076] In three parallel rows of convolutional layers, feature learning and recognition are performed on the current working mode feature tensor and the hair dryer electricity risk feature tensor at the same time to obtain a multi-channel convolution risk monitoring feature tensor;

[0077] The pooling layer is used to reduce the dimension of the multi-channel convolution risk monitoring feature tensor to obtain the multi-channel convolution risk monitoring reduced dimension feature tensor;

[0078] The fully connected layer is used to perform feature mapping on the multi-channel convolution risk monitoring dimensionality reduction feature tensor to obtain the multi-channel convolution risk monitoring feature vector;

[0079] The SVM classifier is used to label the multi-channel convolution risk monitoring feature vector with the risk level of the hair dryer electricity consumption, and obtain the risk level warning of the hair dryer;

[0080] The activation layer processes the current working mode characteristics and electricity risk characteristics through nonlinear activation functions, enhancing the nonlinear ability of feature expression and providing richer input for subsequent feature learning; three parallel convolution layers simultaneously perform multi-scale feature learning on the input tensor, capturing the detailed information and global pattern of the current working mode and risk characteristics, and improving the comprehensiveness and robustness of feature extraction; the pooling layer retains key information while reducing the dimension of the risk monitoring feature tensor, reducing the data dimension, reducing the computational complexity, and avoiding the risk of overfitting; the fully connected layer realizes the integration of deep features by mapping the reduced feature tensor into a feature vector of fixed length, providing high-quality input for classification; the SVM classifier, combined with the high-dimensional expression ability of the multi-channel convolution feature vector, can realize accurate risk level labeling and provide reliable risk warning for the operation status of the hair dryer; combined with the improved CNN model and SVM classifier, the powerful feature extraction ability of deep learning is combined with the high efficiency of traditional classifiers, greatly improving the accuracy and interpretability of risk monitoring;

[0081] The specific steps for training the risk monitoring feature recognition layer include:

[0082] Collect several groups of verified hair dryer electricity usage feature recognition training samples; each group of verified hair dryer electricity usage feature recognition training samples contains a labeled risk level and hair dryer electricity usage feature pair; combine several groups of verified hair dryer electricity usage feature recognition training samples to obtain a hair dryer electricity usage feature recognition training set;

[0083] Input the hair dryer electricity consumption feature recognition training set into the risk monitoring feature recognition layer for model training to obtain the initial risk monitoring feature recognition layer; perform model evaluation on the initial risk monitoring feature recognition layer. If the initial risk monitoring feature recognition layer passes the model evaluation, the initial risk monitoring feature recognition layer is used as the risk monitoring feature recognition layer in the hair dryer risk monitoring model; otherwise, continue model training using the hair dryer electricity consumption feature recognition training set;

[0084] By building a high-quality training set, iteratively optimizing model performance and evaluating feedback mechanisms, we successfully achieved efficient training of the hair dryer risk monitoring feature recognition layer. Based on the continuous iterative training method of the training set, the risk monitoring feature recognition layer can be continuously optimized according to evaluation feedback to adapt to different scenarios and task requirements.

[0085] Match the corresponding hair dryer control strategy according to the hair dryer risk level warning; when the hair dryer risk level warning exceeds the preset highest hair dryer risk level warning, switch the hair dryer working circuit from the hair dryer main circuit to the hair dryer auxiliary circuit to realize automatic control of the hair dryer; the corresponding hair dryer control strategy and the preset highest hair dryer risk level warning are set by professional technicians according to actual conditions;

[0086] The specific steps of switching the working circuit of the hair dryer from the main circuit of the hair dryer to the auxiliary circuit of the hair dryer to realize automatic control of the hair dryer include:

[0087] When the monitored hair dryer risk level warning exceeds the preset highest hair dryer risk level warning, the connection of the hair dryer main circuit will be cut off and an alarm will be issued; at the same time, the hair dryer auxiliary circuit will be connected to switch the hair dryer from the current hair dryer stable working mode to the hair dryer safe working mode; when the hair dryer risk level warning is lower than the preset highest hair dryer risk level warning, the hair dryer working circuit will be switched from the hair dryer auxiliary circuit to the hair dryer main circuit;

[0088] According to the dynamic changes of the risk level warning, the working circuit is automatically switched from the main circuit to the auxiliary circuit to avoid human intervention, thus realizing the intelligent control of the hair dryer; when the risk level exceeds the preset threshold, the main circuit is promptly cut off and the auxiliary circuit is connected to effectively prevent equipment failure or safety accidents caused by abnormalities in the main circuit, thus significantly improving the safety of the hair dryer operation; after switching to the auxiliary circuit, the hair dryer operation state is switched from stable mode to safe mode to ensure that the equipment can continue to operate under low-risk conditions; when the risk level warning is reduced to a safe range, the hair dryer can be automatically switched back to the main circuit to restore the stable working mode, making full use of the high-efficiency performance of the main circuit to realize efficient and safe automatic control of the hair dryer.

[0089] Example 2, a hair dryer automatic control system, see Figure 1 As shown, including:

[0090] The hair dryer parameter processing module includes a feature extraction unit; the feature extraction unit is used to obtain the stable working mode of the hair dryer when the hair dryer starts to work; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current The monitoring data at each moment; based on the electrical variable parameter information to be analyzed and the hair dryer power consumption feature extraction model, the hair dryer power consumption risk feature is obtained; the hair dryer power consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features in combination with the hair dryer's stable working mode, providing data support for subsequent risk level analysis;

[0091] The hair dryer risk assessment module includes a risk assessment unit; the risk assessment unit is used to perform risk monitoring based on the hair dryer's electricity risk characteristics, the hair dryer's stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on a double convolution form;

[0092] The blower automatic control module includes an automatic control unit; the automatic control unit is used to match the corresponding blower control strategy according to the blower risk level warning; when the blower risk level warning exceeds the preset highest blower risk level warning, the blower working circuit is switched from the blower main circuit to the blower auxiliary circuit to realize automatic control of the blower.

[0093] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A method for automatically controlling a hair dryer, characterized in that: The following steps are involved: When the hair dryer starts to work, the hair dryer stable working mode is obtained; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current Monitoring data at all times; based on the electrical variable parameter information to be analyzed and the hair dryer electricity consumption feature extraction model, the hair dryer electricity consumption risk characteristics are obtained; The hair dryer electricity consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features based on the hair dryer's stable working mode, providing data support for subsequent risk level analysis. Risk monitoring is performed based on the hair dryer electricity risk characteristics, the hair dryer stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on the double convolution form; The corresponding blower control strategy is matched according to the blower risk level warning; when the blower risk level warning exceeds the preset highest blower risk level warning, the working circuit of the blower is switched from the blower main circuit to the blower auxiliary circuit to realize automatic control of the blower.

2. A hair dryer automatic control method according to claim 1, characterized in that: The hair dryer electricity consumption feature extraction model includes a weight factor calculation layer, a power load calculation layer and a power consumption feature output layer; The weight factor calculation layer is used to utilize the formula Calculate the power disturbance factor ;in, Indicates the first Monitoring data at all times, Indicates the first Voltage value, represents the power consumption constraint index, represents a risk assessment indicator; Indicates The power consumption disturbance factor at the moment is the predicted power consumption disturbance factor at the next moment; the power consumption constraint index and risk assessment index are determined based on the hair dryer's historical data and the hair dryer's stable working mode; The power load calculation layer is used to utilize the formula Calculate the first Predicted power load value at the time ; The power consumption feature output layer is used to predict the power load value Perform feature extraction to obtain the risk characteristics of electricity consumption of hair dryers.

3. A hair dryer automatic control method according to claim 2, characterized in that: The specific steps for determining power consumption constraint indicators and risk assessment indicators include: Collect the target user's hair dryer operation history data; perform work mode cluster analysis based on the target user's hair dryer operation history data, and build a user hair dryer use work mode matching library; According to the target user's hair dryer operation history data and the user's hair dryer usage work mode matching library, K hair dryer electricity constraint indicator individuals H are constructed. k , k=1,2,…,K; where the hair dryer electricity consumption constraint index individual H k It contains the power consumption constraint index and risk assessment index of each standard user in the stable working mode; the K hair dryer power consumption constraint index individuals H k Combination, get the iterative population of hair dryer electricity consumption constraint index; set the maximum number of iterations, set the hair dryer electricity consumption constraint index individual H k The fitness is D k ; Specific steps to calculate fitness: Build a digital twin model of the hair dryer's electricity consumption, using formula A k =α*C k -β*R k Calculate the hair dryer evaluation index A k , where C k H is the electricity consumption constraint indicator of the hair dryer k The power consumption constraint index in R k H is the electricity consumption constraint indicator of the hair dryer k The risk assessment index in is, α is the weight value of the power consumption constraint index, β is the weight value of the risk assessment index; using formula B k =Q1*(|X k1 -X b1 |) / X k1 +…+Q m *(|X km -X bm |) / X km +…+Q M *(|X kM -X bM |) / X kM The actual hair dryer evaluation index B is calculated by the hair dryer electricity digital twin model. k ; where m = 1, 2, ..., M; X km represents the mth actual hair dryer electrical variable parameter value, X bm represents the target value corresponding to the mth actual hair dryer electrical variable parameter value, Q m Represents the weight value corresponding to the mth item; The hair dryer is rated A k And the actual hair dryer evaluation index B k The inverse of the Euclidean distance is taken as the fitness D k ; The population iteration of the hair dryer electricity consumption constraint index iteration population is carried out. In the population iteration process, the championship method is used to select the hair dryer electricity consumption constraint index iteration population; the chromosome crossover method is used to crossover the hair dryer electricity consumption constraint index iteration population; the interchange mutation operator is used to mutate the hair dryer electricity consumption constraint index iteration population to generate a new hair dryer electricity consumption constraint index iteration population; When the maximum number of iterations is reached, the hair dryer electricity constraint indicator individual corresponding to the maximum fitness is output, which is the optimal hair dryer electricity constraint indicator individual; the optimal hair dryer electricity constraint indicator individual and the user hair dryer working mode matching library are combined to obtain the user hair dryer mode indicator matching library; wherein the user hair dryer mode indicator matching library contains several groups of standard user stable working modes and corresponding electricity constraint indicators and risk assessment indicators.

4. A hair dryer automatic control method according to claim 3, characterized in that: The hair dryer risk monitoring model includes a pattern feature matching layer, a risk monitoring feature identification layer, and a risk level warning output layer; The mode feature matching layer is used to match the current working mode feature according to the stable working mode of the hair dryer; The risk monitoring feature recognition layer is used to perform feature recognition based on the current working mode characteristics and the hair dryer electricity risk characteristics to obtain a hair dryer risk level warning; The risk level warning output layer is used to output hair dryer risk level warnings.

5. A hair dryer automatic control method according to claim 4, characterized in that: The specific steps of feature identification at the risk monitoring feature identification layer include: A risk monitoring feature recognition layer is constructed based on the improved CNN model. The risk monitoring feature recognition layer includes an activation layer, three parallel convolutional layers, a pooling layer, a fully connected layer, and an SVM classifier. The activation layer is used to process the current working mode characteristics and the hair dryer electricity risk characteristics using the activation function to obtain the current working mode feature tensor and the hair dryer electricity risk feature tensor; In three parallel rows of convolutional layers, feature learning and recognition are performed on the current working mode feature tensor and the hair dryer electricity risk feature tensor at the same time to obtain a multi-channel convolution risk monitoring feature tensor; The pooling layer is used to reduce the dimension of the multi-channel convolution risk monitoring feature tensor to obtain the multi-channel convolution risk monitoring reduced dimension feature tensor; The fully connected layer is used to perform feature mapping on the multi-channel convolution risk monitoring dimensionality reduction feature tensor to obtain the multi-channel convolution risk monitoring feature vector; The SVM classifier is used to label the multi-channel convolution risk monitoring feature vector with the risk level of hair dryer electricity consumption and obtain the risk level warning of the hair dryer.

6. A hair dryer automatic control method according to claim 5, characterized in that: The specific steps for training the risk monitoring feature recognition layer include: Collect several groups of verified hair dryer electricity usage feature recognition training samples; each group of verified hair dryer electricity usage feature recognition training samples contains a labeled risk level and hair dryer electricity usage feature pair; combine several groups of verified hair dryer electricity usage feature recognition training samples to obtain a hair dryer electricity usage feature recognition training set; The hair dryer electricity consumption feature recognition training set is input into the risk monitoring feature recognition layer for model training to obtain the initial risk monitoring feature recognition layer; the initial risk monitoring feature recognition layer is evaluated; if the initial risk monitoring feature recognition layer passes the model evaluation, the initial risk monitoring feature recognition layer is used as the risk monitoring feature recognition layer in the hair dryer risk monitoring model; otherwise, the hair dryer electricity consumption feature recognition training set is used to continue model training.

7. A hair dryer automatic control method according to claim 6, characterized in that: The specific steps of switching the working circuit of the hair dryer from the main circuit of the hair dryer to the auxiliary circuit of the hair dryer to realize automatic control of the hair dryer include: When the monitored hair dryer risk level warning exceeds the preset highest hair dryer risk level warning, the connection of the hair dryer main circuit will be cut off and an alarm will be issued; at the same time, the hair dryer auxiliary circuit will be connected to switch the hair dryer from the current hair dryer stable working mode to the hair dryer safe working mode; when the hair dryer risk level warning is lower than the preset highest hair dryer risk level warning, the hair dryer's working circuit will be switched from the hair dryer auxiliary circuit to the hair dryer main circuit.

8. A hair dryer automatic control system, characterized in that: The system applies a hair dryer automatic control method according to any one of claims 1 to 7, comprising: The hair dryer parameter processing module includes a feature extraction unit; the feature extraction unit is used to obtain the stable working mode of the hair dryer when the hair dryer starts to work; the electric variable parameter information of the hair dryer main circuit is monitored in real time to obtain the electric variable parameter information to be analyzed; wherein the electric variable parameter information to be analyzed indicates the current The monitoring data at each moment; based on the electrical variable parameter information to be analyzed and the hair dryer power consumption feature extraction model, the hair dryer power consumption risk feature is obtained; the hair dryer power consumption feature extraction model extracts multiple features from the hair dryer monitoring parameters, and identifies risk features in combination with the hair dryer's stable working mode, providing data support for subsequent risk level analysis; The hair dryer risk assessment module includes a risk assessment unit; the risk assessment unit is used to perform risk monitoring based on the hair dryer's electricity risk characteristics, the hair dryer's stable working mode and the hair dryer risk monitoring model to obtain a hair dryer risk level warning; the hair dryer risk monitoring model combines the CNN model and the SVM classifier to perform feature recognition based on a double convolution form; The blower automatic control module includes an automatic control unit; the automatic control unit is used to match the corresponding blower control strategy according to the blower risk level warning; when the blower risk level warning exceeds the preset highest blower risk level warning, the blower working circuit is switched from the blower main circuit to the blower auxiliary circuit to realize automatic control of the blower.

Images