Automatic control system and method for intelligent gas oven
By introducing artificial intelligence and deep learning technologies into gas ovens, the timing data of oven temperature and heating element output power are monitored and analyzed in real time, precise temperature control is achieved, the problem of temperature fluctuations in traditional gas ovens is solved, and the cooking effect is improved. Security.
Patent Information
- Application Number
- CN202410837542.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-26
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-06-26
AI Technical Summary
Traditional gas oven control systems cannot achieve accurate and real-time adjustment of temperature, resulting in large temperature fluctuations and affecting the cooking effect of food.
Using an automatic control system based on artificial intelligence and deep learning, the timing data of oven temperature and heating element output power is monitored in real time through temperature sensors, and time series collaborative analysis and implicit correlation feature capture are carried out to learn the oven temperature and heating element output power. The timing hides the association mode to realize real-time adaptive control of the power of the heating element.
It achieves precise control of oven temperature, maintains temperature stability, improves cooking quality and consistency, and provides a more intelligent and safe cooking experience.
Smart Images

Figure CN118466365B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of gas ovens, and in particular to an automatic control system and method for an intelligent gas oven. Background Art
[0002] Gas oven is a common kitchen appliance that uses natural gas or liquefied petroleum gas as fuel to heat and cook food through heating elements. Gas ovens usually have independent upper and lower fire heating tubes or surround heating tubes, which can provide high-temperature baking, roasting and grilling functions, and are widely used for baking bread, cakes, barbecue and other foods.
[0003] However, traditional gas oven control systems usually use simple mechanical control or basic temperature controllers to adjust the power output of the heating element. This method can only turn the heating element on and off according to the set temperature, and cannot achieve accurate and real-time temperature adjustment, which easily leads to large temperature fluctuations and affects the cooking effect of food. In addition, some existing gas ovens that can perform temperature control have a slow response speed to temperature changes and cannot quickly adjust the heating power, resulting in temperature fluctuations and instability.
[0004] Therefore, an automatic control system for an intelligent gas oven is desired. Summary of the invention
[0005] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.
[0006] In a first aspect, the present application provides an automatic control system for an intelligent gas oven, the system comprising:
[0007] The oven temperature real-time data acquisition module is used to obtain the time series of the real-time oven temperature collected by the temperature sensor;
[0008] A heating element power acquisition module is used to obtain the time series of the output power of the heating element;
[0009] an oven temperature target offset calculation module, used to calculate the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values;
[0010] a parameter timing feature extraction module, configured to extract timing features from the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset timing associated feature vector, a real-time oven temperature timing associated feature vector, and an output power timing associated feature vector;
[0011] An oven temperature multi-dimensional time series association module, used for adaptively fusing the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain an oven temperature multi-dimensional time series association feature vector;
[0012] An oven temperature-output power nonlinear interactive response module, used for inputting the oven temperature multidimensional time series correlation feature vector and the output power time series correlation feature vector into the nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector;
[0013] The output power control module is used to determine whether the output power at the current time point should increase, decrease or remain unchanged based on the oven temperature-output power timing interaction response representation vector.
[0014] Optionally, the parameter timing feature extraction module is used to: pass the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature and the time series of the output power through a timing pattern feature extractor based on a 1DCNN model to obtain the real-time oven temperature target offset timing association feature vector, the real-time oven temperature timing association feature vector and the output power timing association feature vector.
[0015] Optionally, the oven temperature multidimensional time series association module is used to: input the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector into an equalization threshold feature vector adaptive fusion module to obtain the oven temperature multidimensional time series association feature vector.
[0016] Optionally, the oven temperature multidimensional time series association module includes: a linear transformation and fusion unit, which is used to perform threshold constraints on the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector based on different linear transformation and fusion methods to obtain a first activated linear transformation oven temperature multidimensional time series association representation vector, a second activated linear transformation oven temperature multidimensional time series association representation vector and a third activated linear transformation oven temperature multidimensional time series association representation vector; a vector weighted sum calculation unit, which is used to use each position feature value in the first activated linear transformation oven temperature multidimensional time series association representation vector as a first threshold value, each position feature value in the second activated linear transformation oven temperature multidimensional time series association representation vector as a second threshold value, and each position feature value in the third activated linear transformation oven temperature multidimensional time series association representation vector as a third threshold value to calculate the weighted sum of the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain the oven temperature multidimensional time series association feature vector.
[0017] Optionally, the linear transformation and fusion unit includes: a cascade subunit, used to cascade the real-time oven temperature target offset time series associated feature vector and the real-time oven temperature time series associated feature vector to obtain a first oven temperature multi-dimensional time series associated representation vector; a first vector addition subunit, used to calculate the matrix multiplication of the first oven temperature multi-dimensional time series associated representation vector and the first transformation matrix, and then add the obtained feature vector to the first offset vector by position to obtain a first linear transformation oven temperature multi-dimensional time series associated representation vector; a first activation subunit, used to use The activation function activates the first linear transformation oven temperature multidimensional time series association representation vector to obtain the first activated linear transformation oven temperature multidimensional time series association representation vector; the second vector addition subunit is used to add the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector by position to obtain the second oven temperature multidimensional time series association representation vector; the third vector addition subunit is used to calculate the matrix multiplication of the second oven temperature multidimensional time series association representation vector and the second transformation matrix, and then add the obtained feature vector to the second offset vector by position to obtain the second linear transformation oven temperature multidimensional time series association representation vector; the second activation subunit is used to use The activation function activates the second linear transformation oven temperature multidimensional time series association representation vector to obtain the second activated linear transformation oven temperature multidimensional time series association representation vector; a vector point multiplication subunit is used to perform position point multiplication on the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain a third oven temperature multidimensional time series association representation vector; a fourth vector addition subunit is used to calculate the matrix multiplication of the third measured oven temperature multidimensional time series association representation vector and the third transformation matrix, and then add the obtained feature vector to the third offset vector by position to obtain a third linear transformation oven temperature multidimensional time series association representation vector; a third activation subunit is used to use The activation function activates the third linear transformation oven temperature multi-dimensional time series association representation vector to obtain the third activated linear transformation oven temperature multi-dimensional time series association representation vector.
[0018] Optionally, the vector weighted sum calculation unit includes: a mean calculation subunit, used to calculate the mean between the first threshold value, the second threshold value and the third threshold value to obtain a threshold mean; a first vector product calculation subunit, used to calculate the product of the eigenvalue of each position in the real-time oven temperature target offset timing association feature vector and one minus the threshold mean to obtain a weighted item real-time oven temperature target offset timing association feature vector; a second vector product calculation subunit, used to calculate the product of the eigenvalue of each position in the real-time oven temperature timing association feature vector and the threshold mean to obtain a weighted item real-time oven temperature timing association feature vector; a position addition subunit, used to add the weighted item real-time oven temperature target offset timing association feature vector and the weighted item real-time oven temperature timing association feature vector by position to obtain the oven temperature multi-dimensional timing association feature vector.
[0019] Optionally, the oven temperature-output power nonlinear interactive response module is used to: calculate the position-by-position division between the oven temperature multidimensional time series associated feature vector and the output power time series associated feature vector to obtain the oven temperature-output power time series interactive feature vector; calculate the product between the square value of each position feature value in the oven temperature-output power time series interactive feature vector and the first predetermined adjustment hyperparameter to obtain the first oven temperature-output power time series interactive nonlinear factor quadratic adjustment parameter; calculate the product between each position feature value in the oven temperature-output power time series interactive feature vector and the second predetermined adjustment hyperparameter to obtain the first oven temperature-output power time series interactive nonlinear factor linear adjustment parameter; calculate the sum of the first oven temperature-output power time series interactive nonlinear factor quadratic adjustment parameter and the first oven temperature-output power time series interactive nonlinear factor linear adjustment parameter to obtain the first oven temperature-output power time series interactive nonlinear factor; calculate each position in the oven temperature-output power time series interactive feature vector The method comprises the following steps: calculating the product of the square value of the position eigenvalue and the third predetermined adjustment hyperparameter to obtain the quadratic adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor; calculating the product of the eigenvalues at each position in the oven temperature-output power timing series interaction eigenvector and the fourth predetermined adjustment hyperparameter to obtain the linear adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor; calculating the sum of the quadratic adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor and the linear adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor, and then performing a constant term plus one modulation to obtain the second oven temperature-output power timing series interaction nonlinear factor; calculating the division between the first oven temperature-output power timing series interaction nonlinear factor and the second oven temperature-output power timing series interaction nonlinear factor to obtain the oven temperature-output power timing series interaction nonlinear response value, and vectorizing and regularizing the multiple oven temperature-output power timing series interaction nonlinear response values to obtain the oven temperature-output power timing series interaction response representation vector.
[0020] Optionally, the output power control module is used to: input the oven temperature-output power timing interaction response representation vector into a classifier-based heating element controller to obtain a control instruction, wherein the control instruction is used to indicate whether the output power at the current time point should increase, decrease or remain unchanged.
[0021] Optionally, it also includes a training module for training the timing pattern feature extractor based on the 1DCNN model, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module and the classifier-based heating element controller; wherein the training module includes: a training oven temperature real-time data acquisition unit, used to obtain the time series of the training real-time oven temperature collected by the temperature sensor, and the real value of the output power at the current time point that should increase, decrease or remain unchanged; a training heating element power acquisition unit, used to obtain the time series of the training output power of the heating element; a training oven temperature target offset calculation unit, used to calculate the difference between each training real-time oven temperature in the time series of the training real-time oven temperature and the preset oven temperature to obtain the time series of the training real-time oven temperature target offset value; a training parameter timing feature extraction unit, used to extract the timing features of the time series of the training real-time oven temperature target offset value, the time series of the training real-time oven temperature and the time series of the training output power to obtain the training real-time oven temperature target offset timing association feature vector, the training real-time oven temperature timing association feature vector, the training real-time oven temperature target offset ... a training oven temperature multidimensional time series association unit, used for adaptively fusing the training real-time oven temperature target offset time series association feature vector and the training real-time oven temperature time series association feature vector to obtain a training oven temperature multidimensional time series association feature vector; a training oven temperature-output power nonlinear interactive response unit, used for inputting the training oven temperature multidimensional time series association feature vector and the training output power time series association feature vector into the nonlinear interactive response module to obtain a training oven temperature-output power time series interactive response representation vector; a training classification unit, used for inputting the training oven temperature-output power time series interactive response representation vector into the classifier-based heating element controller to obtain a control instruction; a loss function calculation unit, used for calculating the cross entropy loss function value between the control instruction and the true value to obtain a classification loss function value; a training unit, used for training the 1DCNN model-based time series pattern feature extractor, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module and the classifier-based heating element controller based on the classification loss function value.
[0022] In a second aspect, the present application provides an automatic control method for an intelligent gas oven, the method comprising:
[0023] Get the time series of real-time oven temperature collected by the temperature sensor;
[0024] Obtain the time series of the output power of the heating element;
[0025] Calculating the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values;
[0026] Performing time series feature extraction on the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset time series associated feature vector, a real-time oven temperature time series associated feature vector, and an output power time series associated feature vector;
[0027] Adaptively fusing the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector to obtain an oven temperature multi-dimensional time series correlation feature vector;
[0028] Inputting the oven temperature multi-dimensional time series correlation feature vector and the output power time series correlation feature vector into a nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector;
[0029] Based on the oven temperature-output power time series interactive response representation vector, it is determined whether the output power at the current time point should increase, decrease or remain unchanged.
[0030] The above technical solution is adopted to collect oven temperature value data in real time through temperature sensors, and obtain the time series data of the output power of the heating element. Then, a data processing and analysis algorithm based on artificial intelligence and deep learning is introduced at the back end to perform time series collaborative analysis and implicit correlation feature capture of the oven temperature time series data and the output power time series data, so as to learn and capture the time series hidden correlation pattern between the oven temperature and the output power of the heating element, so as to perform real-time adaptive control of the output power of the heating element based on the real-time temperature of the gas oven. In this way, the power output of the heating element can be adjusted in real time according to the preset cooking program and the real-time heating temperature, so as to achieve precise control of the oven temperature and maintain temperature stability.
[0031] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:
[0033] Figure 1 The invention is a block diagram of an automatic control system of an intelligent gas oven according to an exemplary embodiment.
[0034] Figure 2 It is a structural schematic diagram of an intelligent gas oven according to an exemplary embodiment.
[0035] Figure 3 The present invention is a flow chart of an automatic control method of an intelligent gas oven according to an exemplary embodiment.
[0036] Figure 4 It is a block diagram of an electronic device according to an exemplary embodiment.
[0037] Figure 5 It is an application scenario diagram of an automatic control system of an intelligent gas oven according to an exemplary embodiment. DETAILED DESCRIPTION
[0038] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.
[0039] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.
[0040] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.
[0041] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0042] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0043] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0044] In order to solve the above problems, the present application provides an automatic control system and method for an intelligent gas oven, which collects oven temperature value data in real time through a temperature sensor, and obtains the time series data of the output power of the heating element. Then, a data processing and analysis algorithm based on artificial intelligence and deep learning is introduced at the back end to perform time series collaborative analysis and implicit correlation feature capture of the oven temperature time series data and the output power time series data, so as to learn and capture the time series hidden correlation pattern between the oven temperature and the output power of the heating element, thereby performing real-time adaptive control of the output power of the heating element based on the real-time temperature of the gas oven. In this way, the power output of the heating element can be adjusted in real time according to the preset cooking program and the real-time heating temperature, so as to achieve precise control of the oven temperature and maintain temperature stability.
[0045] The automatic control system of the intelligent gas oven is a technology that integrates advanced sensors, microprocessors, control algorithms and user interfaces. This system can achieve precise control of the oven temperature, providing users with a more convenient and safe cooking experience. The core of the system is a microprocessor that is responsible for receiving data from the temperature sensor and adjusting the power output of the heating element according to the preset cooking program. In this way, whether baking cakes or roasting meat, the oven can maintain the optimal temperature range.
[0046] In addition, the automatic control system of smart gas ovens usually includes multiple cooking modes, such as baking, roasting, and keeping warm, so that users can choose the appropriate mode according to different ingredients and recipe requirements. The system may also include an automatic preheating function that can preheat the oven to the appropriate temperature before starting cooking. For more advanced models, there may also be a remote control function via Wi-Fi or Bluetooth, allowing users to remotely operate the oven via a smartphone or tablet.
[0047] Safety is also an important consideration in the design of intelligent gas oven automatic control systems. The system may include overheat protection, automatic shutdown and fault diagnosis functions. If the system detects abnormal temperature or equipment failure, it can automatically cut off the gas supply to prevent accidents. In addition, some systems may also have a child lock function to prevent children from operating it by mistake.
[0048] In terms of user interface, the control system of a smart gas oven usually features an intuitive touch screen or buttons, as well as a clear display showing the current temperature, remaining cooking time, and other relevant information. Some systems may even support voice control, enabling users to operate the oven with simple voice commands.
[0049] Overall, the automatic control system of the smart gas oven greatly improves the efficiency and comfort of cooking through its high degree of automation and user-friendly interface. It not only makes the cooking process simpler, but also provides an extra layer of protection for the family through its safety features. As technology continues to advance, we can expect these systems to become more intelligent and interconnected, bringing more innovation and convenience to the modern kitchen.
[0050] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.
[0051] Figure 1 FIG. 1 is a block diagram of an automatic control system of an intelligent gas oven according to an exemplary embodiment. Figure 1 As shown, the system 100 includes:
[0052] The oven temperature real-time data acquisition module 101 is used to obtain the time series of the real-time oven temperature collected by the temperature sensor;
[0053] The heating element power acquisition module 102 is used to obtain the time series of the output power of the heating element;
[0054] The oven temperature target offset calculation module 103 is used to calculate the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values;
[0055] A parameter time series feature extraction module 104 is used to extract time series features from the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset time series correlation feature vector, a real-time oven temperature time series correlation feature vector, and an output power time series correlation feature vector;
[0056] The oven temperature multi-dimensional time series association module 105 is used to adaptively fuse the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain the oven temperature multi-dimensional time series association feature vector;
[0057] The oven temperature-output power nonlinear interactive response module 106 is used to input the oven temperature multidimensional time series correlation feature vector and the output power time series correlation feature vector into a nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector;
[0058] The output power control module 107 is used to determine whether the output power at the current time point should be increased, decreased or kept unchanged based on the oven temperature-output power time series interactive response representation vector.
[0059] In view of the above technical problems, in the technical solution of the present application, an automatic control system of an intelligent gas oven is proposed, which can monitor and collect oven temperature value data in real time through a temperature sensor, and obtain the time series data of the output power of the heating element. Then, a data processing and analysis algorithm based on artificial intelligence and deep learning is introduced in the back end to perform time series collaborative analysis and implicit correlation feature capture of the oven temperature time series data and the output power time series data, so as to learn and capture the time series hidden correlation pattern between the oven temperature and the output power of the heating element, so as to perform real-time adaptive control of the output power of the heating element based on the real-time temperature of the gas oven. In this way, the power output of the heating element can be adjusted in real time according to the preset cooking program and the real-time heating temperature, so as to achieve precise control of the oven temperature and maintain temperature stability. In this way, whether it is baking cakes or grilling meat, the oven can automatically maintain a suitable temperature, thereby providing users with a more intelligent and safe cooking experience.
[0060] Specifically, in the technical solution of the present application, first, the time series of the real-time oven temperature collected by the temperature sensor is obtained, and the time series of the output power of the heating element is obtained. It should be understood that since the time series of the real-time oven temperature contains the time series integration information of the temperature data of the gas oven in the time dimension, this information can well reflect the time series change characteristics and pattern information of the oven temperature. In particular, in order to be able to use the time series change of the oven temperature to perform adaptive control of the output power, so as to achieve the purpose of accurately controlling the oven temperature and maintaining the suitability and stability of the temperature, it is necessary to calculate the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain the time series of the real-time oven temperature target offset value. In this way, the deviation between the current temperature state and the expected state can be identified, thereby providing a data basis for the subsequent multi-dimensional feature fusion representation of the oven temperature, so as to achieve more accurate output power control, thereby ensuring that the temperature inside the oven is always close to the preset temperature, and improving the cooking quality and consistency.
[0061] Next, the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power are passed through a timing pattern feature extractor based on a 1DCNN model to obtain a real-time oven temperature target offset timing correlation feature vector, a real-time oven temperature timing correlation feature vector, and an output power timing correlation feature vector. Through the processing of the timing pattern feature extractor based on the 1DCNN model, the timing correlation feature information between the real-time oven temperature target offset value, the real-time oven temperature value, and the output power at different time points in the time dimension can be captured respectively, providing a more accurate data basis for subsequent control decisions.
[0062] In one embodiment of the present application, the parameter timing feature extraction module is used to: pass the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power through a timing pattern feature extractor based on a 1DCNN model to obtain the real-time oven temperature target offset timing association feature vector, the real-time oven temperature timing association feature vector, and the output power timing association feature vector.
[0063] Then, considering that the real-time oven temperature target offset timing association feature vector and the real-time oven temperature timing association feature vector respectively capture the timing dynamic association feature information of the oven temperature target offset and the actual temperature change, these two timing features about the oven temperature express different dimensional information of the oven temperature in the time dimension, wherein the real-time oven temperature timing association feature vector represents the timing absolute quantity change characteristics of the oven temperature, while the real-time oven temperature target offset timing association feature vector represents the timing characteristics of the offset relative quantity between the oven temperature and the target. Therefore, in order to be able to use the characteristics of these two to comprehensively perform the timing analysis of the oven temperature, so as to model the output power timing characteristics in the subsequent time series to better perform the adaptive control of the output power, in the technical solution of the present application, the real-time oven temperature target offset timing association feature vector and the real-time oven temperature timing association feature vector are further input into the equalization threshold feature vector adaptive fusion module to obtain the oven temperature multi-dimensional timing association feature vector.
[0064] In one embodiment of the present application, the oven temperature multidimensional time series association module is used to: input the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector into the equalization threshold feature vector adaptive fusion module to obtain the oven temperature multidimensional time series association feature vector.
[0065] Through the processing of the balanced threshold feature vector adaptive fusion module, the hidden correlation and important information between the oven temperature timing correlation features and the target offset timing features can be automatically learned and captured, so as to fuse the oven temperature timing multi-dimensional features, and adaptively weight and highlight the feature information related to the subsequent output power control task during the fusion process. In this way, the feature importance of different aspects of the oven temperature can be dynamically adjusted, so as to capture more complex temperature change patterns to adapt to different cooking conditions and goals.
[0066] In one embodiment of the present application, the oven temperature multidimensional time series association module includes: a linear transformation and fusion unit, which is used to perform threshold constraints on the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector based on different linear transformation and fusion methods to obtain a first activated linear transformation oven temperature multidimensional time series association representation vector, a second activated linear transformation oven temperature multidimensional time series association representation vector and a third activated linear transformation oven temperature multidimensional time series association representation vector; a vector weighted sum calculation unit, which is used to use each position feature value in the first activated linear transformation oven temperature multidimensional time series association representation vector as a first threshold value, each position feature value in the second activated linear transformation oven temperature multidimensional time series association representation vector as a second threshold value, and each position feature value in the third activated linear transformation oven temperature multidimensional time series association representation vector as a third threshold value to calculate the weighted sum of the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain the oven temperature multidimensional time series association feature vector.
[0067] Further, in one embodiment of the present application, the linear transformation and fusion unit includes: a cascade subunit, which is used to cascade the real-time oven temperature target offset time series associated feature vector and the real-time oven temperature time series associated feature vector to obtain a first oven temperature multi-dimensional time series associated representation vector; a first vector addition subunit, which is used to calculate the matrix multiplication of the first oven temperature multi-dimensional time series associated representation vector and the first transformation matrix, and then add the obtained feature vector to the first offset vector by position to obtain a first linear transformation oven temperature multi-dimensional time series associated representation vector; a first activation subunit, which is used to use The activation function activates the first linear transformation oven temperature multidimensional time series association representation vector to obtain the first activated linear transformation oven temperature multidimensional time series association representation vector; the second vector addition subunit is used to add the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector by position to obtain the second oven temperature multidimensional time series association representation vector; the third vector addition subunit is used to calculate the matrix multiplication of the second oven temperature multidimensional time series association representation vector and the second transformation matrix, and then add the obtained feature vector to the second offset vector by position to obtain the second linear transformation oven temperature multidimensional time series association representation vector; the second activation subunit is used to use The activation function activates the second linear transformation oven temperature multidimensional time series association representation vector to obtain the second activated linear transformation oven temperature multidimensional time series association representation vector; a vector point multiplication subunit is used to perform position point multiplication on the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain a third oven temperature multidimensional time series association representation vector; a fourth vector addition subunit is used to calculate the matrix multiplication of the third measured oven temperature multidimensional time series association representation vector and the third transformation matrix, and then add the obtained feature vector to the third offset vector by position to obtain a third linear transformation oven temperature multidimensional time series association representation vector; a third activation subunit is used to use The activation function activates the third linear transformation oven temperature multi-dimensional time series association representation vector to obtain the third activated linear transformation oven temperature multi-dimensional time series association representation vector.
[0068] Furthermore, in one embodiment of the present application, the vector weighted and calculation unit includes: a mean calculation subunit, used to calculate the mean between the first threshold value, the second threshold value and the third threshold value to obtain a threshold mean; a first vector product calculation subunit, used to calculate the product of the eigenvalue of each position in the real-time oven temperature target offset timing association feature vector and one minus the threshold mean to obtain a weighted item real-time oven temperature target offset timing association feature vector; a second vector product calculation subunit, used to calculate the product of the eigenvalue of each position in the real-time oven temperature timing association feature vector and the threshold mean to obtain a weighted item real-time oven temperature timing association feature vector; a positional addition subunit, used to positionally add the weighted item real-time oven temperature target offset timing association feature vector and the weighted item real-time oven temperature timing association feature vector to obtain the oven temperature multi-dimensional timing association feature vector.
[0069] Specifically, the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector are input into the balanced threshold feature vector adaptive fusion module for processing using the following balanced threshold adaptive fusion formula to obtain the oven temperature multi-dimensional time series correlation feature vector;
[0070] The equalization threshold adaptive fusion formula is: ;in, and are respectively the real-time oven temperature target offset timing associated feature vector and the real-time oven temperature timing associated feature vector, and are respectively the real-time oven temperature target offset timing correlation feature vectors and the real-time oven temperature time series associated feature vector The eigenvalues at each position in , is the characteristic value of each position in the multi-dimensional time series correlation characteristic vector of the oven temperature, represents the concatenation of vectors, , and is the transformation matrix, , and is the bias vector, The first activation linear transformation oven temperature multi-dimensional time series association representation vector, represents vector addition by position, It means vector multiplication by position. is the second activation linear transformation oven temperature multidimensional time series association representation vector, is the third activation linear transformation oven temperature multidimensional time series association representation vector, is the first activation linear transformation oven temperature multidimensional time series association representation vector The threshold value of each position in The second activation linear transformation oven temperature multidimensional time series association representation vector The threshold value of each position in is the third activation linear transformation oven temperature multidimensional time series association representation vector The threshold value of each position in , express Activation function.
[0071] Furthermore, considering that the timing relationship between the oven temperature and the output power of the heating element is often complex and nonlinear, in order to be able to identify and process this complex nonlinear relationship, in the technical solution of the present application, the oven temperature multidimensional timing correlation feature vector and the output power timing correlation feature vector are further input into the nonlinear interactive response module to obtain the oven temperature-output power timing interactive response representation vector. By introducing the nonlinear interactive response module, the system can automatically learn and capture the nonlinear association and dynamic interactive relationship between the oven temperature multidimensional timing expression characteristics and the output power timing characteristics, including the influence of temperature on power, the feedback of power on temperature and other complex relationships. This helps the system to more accurately understand and model the dynamic interactive relationship between temperature and power, reveal the complex association pattern between the two, and provide richer information for subsequent control decisions.
[0072] In one embodiment of the present application, the oven temperature-output power nonlinear interactive response module is used to: calculate the position-by-position division between the oven temperature multidimensional time series association feature vector and the output power time series association feature vector to obtain the oven temperature-output power time series interaction feature vector; calculate the product between the square value of each position feature value in the oven temperature-output power time series interaction feature vector and the first predetermined adjustment hyperparameter to obtain the first oven temperature-output power time series interaction nonlinear factor quadratic adjustment parameter; calculate the product between each position feature value in the oven temperature-output power time series interaction feature vector and the second predetermined adjustment hyperparameter to obtain the first oven temperature-output power time series interaction nonlinear factor linear adjustment parameter; calculate the sum of the first oven temperature-output power time series interaction nonlinear factor quadratic adjustment parameter and the first oven temperature-output power time series interaction nonlinear factor linear adjustment parameter to obtain the first oven temperature-output power time series interaction nonlinear factor; calculate the oven temperature-output power time series interaction feature vector The product of the square value of each position characteristic value and the third predetermined adjustment hyperparameter is used to obtain the quadratic adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor; the product of each position characteristic value in the oven temperature-output power timing series interaction characteristic vector and the fourth predetermined adjustment hyperparameter is calculated to obtain the linear adjustment parameter of the second oven temperature-output power timing series interaction nonlinear factor; the sum of the second oven temperature-output power timing series interaction nonlinear factor quadratic adjustment parameter and the second oven temperature-output power timing series interaction nonlinear factor linear adjustment parameter is calculated, and then a constant term plus one is modulated to obtain the second oven temperature-output power timing series interaction nonlinear factor; the division between the first oven temperature-output power timing series interaction nonlinear factor and the second oven temperature-output power timing series interaction nonlinear factor is calculated to obtain the oven temperature-output power timing series interaction nonlinear response value, and a plurality of the oven temperature-output power timing series interaction nonlinear response values are vectorized and regularized to obtain the oven temperature-output power timing series interaction response representation vector.
[0073] Specifically, the oven temperature multi-dimensional time series correlation feature vector and the output power time series correlation feature vector are input into the nonlinear interactive response module for processing using the following nonlinear interactive response formula to obtain the oven temperature-output power time series interactive response representation vector;
[0074] Wherein, the nonlinear interactive response formula is: ;in, is the first The eigenvalues at the positions, is the output power timing correlation feature vector The eigenvalues at the positions, is the first characteristic vector of the oven temperature-output power time series interaction The eigenvalues at the positions, , , and To tune the hyperparameters, The first element in the vector representing the oven temperature-output power timing interaction response is The feature value at each position.
[0075] Furthermore, the oven temperature-output power time series interactive response representation vector is input into the classifier-based heating element controller to obtain a control instruction, and the control instruction is used to indicate whether the output power at the current time point should increase, decrease, or remain unchanged. In other words, the temporal interactive responsiveness characteristic information between the oven temperature and the output power is used for classification processing, so as to perform real-time adaptive control of the output power of the heating element based on the real-time temperature of the gas oven. In this way, the power output of the heating element can be adjusted in real time according to the preset cooking program and the real-time heating temperature, so as to achieve precise control of the oven temperature and maintain temperature stability. In this way, whether it is baking cakes or grilling meat, the oven can automatically maintain a suitable temperature, thereby providing users with a more intelligent and safe cooking experience.
[0076] In one embodiment of the present application, the output power control module is used to: input the oven temperature-output power timing interaction response representation vector into a classifier-based heating element controller to obtain a control instruction, wherein the control instruction is used to indicate whether the output power at the current time point should increase, decrease, or remain unchanged.
[0077] Further, in one embodiment of the present application, the automatic control system of the intelligent gas oven also includes a training module for training the time series pattern feature extractor based on the 1DCNN model, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module and the classifier-based heating element controller; wherein the training module includes: a training oven temperature real-time data acquisition unit, which is used to obtain the time series of the training real-time oven temperature collected by the temperature sensor, and the real value of the output power at the current time point that should increase, decrease or remain unchanged; a training heating element power acquisition unit, which is used to obtain the time series of the training output power of the heating element; a training oven temperature target offset calculation unit, which is used to calculate the difference between each training real-time oven temperature in the time series of the training real-time oven temperature and the preset oven temperature to obtain the time series of the training real-time oven temperature target offset value; a training parameter time series feature extraction unit, which is used to extract the time series features of the training real-time oven temperature target offset value, the training real-time oven temperature time series and the training output power time series to obtain the training real-time oven temperature target offset time series correlation feature vector; a training oven temperature multidimensional time series association unit, used for adaptively fusing the training real-time oven temperature target offset time series association feature vector and the training real-time oven temperature time series association feature vector to obtain a training oven temperature multidimensional time series association feature vector; a training oven temperature-output power nonlinear interactive response unit, used for inputting the training oven temperature multidimensional time series association feature vector and the training output power time series association feature vector into the nonlinear interactive response module to obtain a training oven temperature-output power time series interactive response representation vector; a training classification unit, used for inputting the training oven temperature-output power time series interactive response representation vector into the classifier-based heating element controller to obtain a control instruction; a loss function calculation unit, used for calculating the cross entropy loss function value between the control instruction and the true value to obtain a classification loss function value; a training unit, used for training the 1DCNN model-based time series pattern feature extractor, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module and the classifier-based heating element controller based on the classification loss function value.
[0078] Preferably, inputting the training oven temperature-output power time series interactive response representation vector into a classifier-based heating element controller to obtain a control instruction comprises:
[0079] Multiply the training oven temperature-output power timing interaction response representation vector by the length of the training oven temperature-output power timing interaction response representation vector and the square root of the length of the training oven temperature-output power timing interaction response representation vector to obtain an oven temperature-output power timing interaction response full-width representation vector and an oven temperature-output power timing interaction response half-width representation vector;
[0080] Performing point subtraction on the oven temperature-output power timing interaction response full-scale representation vector and the norm of the training oven temperature-output power timing interaction response representation vector, and calculating the square root of the absolute value of each position of the point subtraction result vector to obtain the oven temperature-output power timing interaction response full-scale semantic change vector;
[0081] Performing point subtraction on the oven temperature-output power timing interaction response half-width representation vector and the bi-norm of the training oven temperature-output power timing interaction response representation vector, and calculating the square root of the absolute value of each position of the point subtraction result vector to obtain the oven temperature-output power timing interaction response half-width semantic change vector;
[0082] Respectively calculating the logarithmic value with base 2 of each eigenvalue of the oven temperature-output power timing interaction response full-width semantic change vector and the oven temperature-output power timing interaction response half-width semantic change vector to obtain the oven temperature-output power timing interaction response full-width semantic change information vector and the oven temperature-output power timing interaction response half-width semantic change information vector;
[0083] Calculating the weighted sum of the oven temperature-output power timing interaction response full-width semantic change information vector and the oven temperature-output power timing interaction response half-width semantic change information vector using the balance hyperparameter as a weight to obtain an optimized oven temperature-output power timing interaction response representation vector; and
[0084] The optimized oven temperature-output power timing interaction response representation vector is input into a classifier-based heating element controller to obtain a control instruction.
[0085] Here, for the misalignment of timing correlation features caused by the mismatch of source timing distributions of the training real-time oven temperature target offset value, the training real-time oven temperature and the training output power, after the adaptive fusion of the equalization threshold feature vector and the nonlinear interactive response, the training oven temperature-output power timing interactive response representation vector will also have the problem of insufficient fusion-response timing distribution aggregation, thereby affecting its classification convergence efficiency through the classifier, that is, affecting the efficiency of classification training and the accuracy of classification results.
[0086] Based on this, the applicant of the present application takes the training oven temperature-output power timing interaction response representation vector as a feature set, wherein the change semantics represented by the feature value of the training oven temperature-output power timing interaction response representation vector is used as a unit. In order to dynamically aggregate the semantic set composed of different change semantics of the training oven temperature-output power timing interaction response representation vector without ignoring the individual semantic change information, the individual features of the training oven temperature-output power timing interaction response representation vector and the aggregated scale of the training oven temperature-output power timing interaction response representation vector are collectively expressed as the feature full amplitude and half amplitude, and the low-rank negative correlation of different dimensions of the overall semantics of the feature set of the training oven temperature-output power timing interaction response representation vector is used as the phase and scaled to dynamically adjust the change relationship of the semantic content of the training oven temperature-output power timing interaction response representation vector, thereby improving the aggregation of the overall semantic information expression of the feature set of the training oven temperature-output power timing interaction response representation vector, and improving the classification convergence efficiency of the training oven temperature-output power timing interaction response representation vector when it is classified by a classifier-based heating element controller. In this way, the real-time adaptive control of the heating element output power can be more accurately performed based on the real-time temperature of the gas oven to maintain temperature stability, thereby providing users with a more intelligent and safe cooking experience.
[0087] In summary, the above scheme is adopted to collect oven temperature value data in real time through temperature sensors, and obtain the time series data of the output power of the heating element. Then, a data processing and analysis algorithm based on artificial intelligence and deep learning is introduced at the back end to perform time series collaborative analysis and implicit correlation feature capture of the oven temperature time series data and the output power time series data, so as to learn and capture the time series hidden correlation pattern between the oven temperature and the output power of the heating element, so as to perform real-time adaptive control of the output power of the heating element based on the real-time temperature of the gas oven. In this way, the power output of the heating element can be adjusted in real time according to the preset cooking program and the real-time heating temperature, so as to achieve precise control of the oven temperature and maintain temperature stability. In this way, whether it is baking cakes or grilling meat, the oven can automatically maintain a suitable temperature, thereby providing users with a more intelligent and safe cooking experience.
[0088] In one embodiment of the present application, a smart gas oven is provided. Figure 2 shown.
[0089] Figure 3 is a flow chart of an automatic control method of an intelligent gas oven according to an exemplary embodiment. Figure 3 As shown, the method includes:
[0090] Step 201, obtaining a time series of real-time oven temperature collected by a temperature sensor;
[0091] Step 202, obtaining a time series of the output power of the heating element;
[0092] Step 203, calculating the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values;
[0093] Step 204, extracting time series features from the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset time series associated feature vector, a real-time oven temperature time series associated feature vector, and an output power time series associated feature vector;
[0094] Step 205: adaptively fuse the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector to obtain an oven temperature multi-dimensional time series correlation feature vector;
[0095] Step 206: Input the oven temperature multi-dimensional time series correlation feature vector and the output power time series correlation feature vector into a nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector;
[0096] Step 207: Based on the oven temperature-output power time series interactive response representation vector, determine whether the output power at the current time point should increase, decrease, or remain unchanged.
[0097] Reference below Figure 4 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0098] like Figure 4As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0099] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.
[0100] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.
[0101] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0102] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0103] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0104] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0105] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0106] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".
[0107] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0108] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0109] Figure 5 FIG. 1 is an application scenario diagram of an automatic control system of an intelligent gas oven according to an exemplary embodiment. Figure 5 As shown, in this application scenario, first, the time series of the real-time oven temperature collected by the temperature sensor is obtained (for example, Figure 5 C1 shown in FIG); obtaining a time series of the output power of the heating element (for example, Figure 5 Then, the acquired real-time oven temperature time series and output power time series are input to a server (for example, Figure 5 In S) shown in the figure, the server can process the time series of the real-time oven temperature and the time series of the output power based on the automatic control algorithm of the intelligent gas oven to determine whether the output power at the current time point should increase, decrease or remain unchanged.
[0110] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.
[0111] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.
[0112] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims
1. An automatic control system for an intelligent gas oven, characterized in that: include: The oven temperature real-time data acquisition module is used to obtain the time series of the real-time oven temperature collected by the temperature sensor; A heating element power acquisition module is used to obtain the time series of the output power of the heating element; an oven temperature target offset calculation module, used to calculate the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values; a parameter timing feature extraction module, configured to extract timing features from the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset timing associated feature vector, a real-time oven temperature timing associated feature vector, and an output power timing associated feature vector; An oven temperature multi-dimensional time series association module, used for adaptively fusing the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain an oven temperature multi-dimensional time series association feature vector; An oven temperature-output power nonlinear interactive response module, used for inputting the oven temperature multidimensional time series correlation feature vector and the output power time series correlation feature vector into the nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector; An output power control module, used to determine whether the output power at a current time point should be increased, decreased or kept unchanged based on the oven temperature-output power time series interactive response representation vector; The oven temperature multi-dimensional time series association module is used to: input the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector into the equalization threshold feature vector adaptive fusion module to obtain the oven temperature multi-dimensional time series association feature vector; Wherein, the oven temperature multi-dimensional time series association module includes: A linear transformation and fusion unit, used for performing threshold constraints based on different linear transformation and fusion methods on the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain a first activated linear transformation oven temperature multi-dimensional time series association representation vector, a second activated linear transformation oven temperature multi-dimensional time series association representation vector, and a third activated linear transformation oven temperature multi-dimensional time series association representation vector; A vector weighted sum calculation unit is used to use the respective position feature values in the first activated linear transformation oven temperature multidimensional time series association representation vector as the first threshold value, the respective position feature values in the second activated linear transformation oven temperature multidimensional time series association representation vector as the second threshold value, and the respective position feature values in the third activated linear transformation oven temperature multidimensional time series association representation vector as the third threshold value, to calculate the weighted sum of the real-time oven temperature target offset time series association feature vector and the real-time oven temperature time series association feature vector to obtain the oven temperature multidimensional time series association feature vector.
2. The automatic control system of the intelligent gas oven according to claim 1 is characterized in that: The parameter timing feature extraction module is used to: pass the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature and the time series of the output power through a timing pattern feature extractor based on a 1DCNN model to obtain the real-time oven temperature target offset timing associated feature vector, the real-time oven temperature timing associated feature vector and the output power timing associated feature vector.
3. The automatic control system of the intelligent gas oven according to claim 2 is characterized in that: The linear transformation and fusion unit comprises: a cascading subunit, configured to cascade the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector to obtain a first oven temperature multi-dimensional time series correlation representation vector; A first vector addition subunit is used to calculate the matrix multiplication of the first oven temperature multidimensional time series association representation vector and the first transformation matrix, and then add the obtained eigenvector and the first bias vector according to the position to obtain a first linear transformation oven temperature multidimensional time series association representation vector; The first activation subunit is used to use The activation function activates the first linear transformation oven temperature multi-dimensional time series association representation vector to obtain the first activated linear transformation oven temperature multi-dimensional time series association representation vector; A second vector adding subunit is used to add the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector according to position to obtain a second oven temperature multi-dimensional time series correlation representation vector; A third vector addition subunit is used for calculating the matrix multiplication of the second oven temperature multidimensional time series association representation vector and the second transformation matrix, and then adding the obtained eigenvector and the second bias vector by position to obtain a second linear transformation oven temperature multidimensional time series association representation vector; The second activation subunit is used to use The activation function activates the second linear transformation oven temperature multi-dimensional time series association representation vector to obtain the second activated linear transformation oven temperature multi-dimensional time series association representation vector; A vector point multiplication subunit, used for performing position point multiplication on the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector to obtain a third oven temperature multi-dimensional time series correlation representation vector; a fourth vector addition subunit, configured to calculate the matrix multiplication of the third oven temperature multidimensional time series association representation vector and the third transformation matrix, and then add the obtained eigenvector to the third bias vector by position to obtain a third linear transformation oven temperature multidimensional time series association representation vector; The third activation subunit is used to use The activation function activates the third linear transformation oven temperature multi-dimensional time series association representation vector to obtain the third activated linear transformation oven temperature multi-dimensional time series association representation vector.
4. The automatic control system of the intelligent gas oven according to claim 3 is characterized in that: The vector weighted sum calculation unit comprises: a mean value calculating subunit, configured to calculate a mean value among the first threshold value, the second threshold value and the third threshold value to obtain a threshold mean value; A first vector product calculation subunit is used to calculate the product of the feature value of each position in the real-time oven temperature target offset timing associated feature vector and one minus the threshold mean to obtain a weighted item real-time oven temperature target offset timing associated feature vector; A second vector product calculation subunit is used to calculate the product of the feature value of each position in the real-time oven temperature time series associated feature vector and the threshold mean value to obtain a weighted item real-time oven temperature time series associated feature vector; The position adding subunit is used to add the weighted item real-time oven temperature target offset time series correlation feature vector and the weighted item real-time oven temperature time series correlation feature vector by position to obtain the oven temperature multi-dimensional time series correlation feature vector.
5. The automatic control system of the intelligent gas oven according to claim 4, characterized in that: The oven temperature-output power nonlinear interactive response module is used to: Calculating the position-by-position division between the oven temperature multi-dimensional time series associated feature vector and the output power time series associated feature vector to obtain an oven temperature-output power time series interaction feature vector; Calculate the product of the square value of each position characteristic value in the oven temperature-output power time series interaction characteristic vector and the first predetermined adjustment hyperparameter to obtain a first oven temperature-output power time series interaction nonlinear factor quadratic term adjustment parameter; Calculate the product of each position characteristic value in the oven temperature-output power time series interaction characteristic vector and a second predetermined adjustment hyperparameter to obtain a first oven temperature-output power time series interaction nonlinear factor linear term adjustment parameter; Calculate the sum of the first oven temperature-output power timing interaction nonlinear factor quadratic term adjustment parameter and the first oven temperature-output power timing interaction nonlinear factor linear term adjustment parameter to obtain the first oven temperature-output power timing interaction nonlinear factor; Calculate the product of the square value of each position characteristic value in the oven temperature-output power time series interaction characteristic vector and the third predetermined adjustment hyperparameter to obtain a second oven temperature-output power time series interaction nonlinear factor quadratic term adjustment parameter; Calculate the product of each position characteristic value in the oven temperature-output power time series interaction characteristic vector and a fourth predetermined adjustment hyperparameter to obtain a first-order adjustment parameter of a second oven temperature-output power time series interaction nonlinear factor; Calculate the sum of the second oven temperature-output power timing interaction nonlinear factor quadratic term adjustment parameter and the second oven temperature-output power timing interaction nonlinear factor linear term adjustment parameter, and then perform a constant term plus one modulation to obtain the second oven temperature-output power timing interaction nonlinear factor; Calculate the division between the first oven temperature-output power timing interaction nonlinear factor and the second oven temperature-output power timing interaction nonlinear factor to obtain an oven temperature-output power timing interaction nonlinear response value, and vectorize and regularize a plurality of the oven temperature-output power timing interaction nonlinear response values to obtain the oven temperature-output power timing interaction response representation vector.
6. The automatic control system of the intelligent gas oven according to claim 5, characterized in that: The output power control module is used to: input the oven temperature-output power timing interaction response representation vector into a classifier-based heating element controller to obtain a control instruction, wherein the control instruction is used to indicate whether the output power at the current time point should increase, decrease or remain unchanged.
7. The automatic control system of the intelligent gas oven according to claim 6, characterized in that: Also included is a training module for training the 1DCNN model-based temporal pattern feature extractor, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module, and the classifier-based heating element controller; Wherein, the training module includes: A training oven temperature real-time data acquisition unit, used to acquire a time series of the training real-time oven temperature acquired by the temperature sensor, and a real value at a current time point at which the output power should increase, decrease, or remain unchanged; A training heating element power acquisition unit, used to obtain a time series of the training output power of the heating element; a training oven temperature target offset calculation unit, configured to calculate the difference between each training real-time oven temperature in the time series of the training real-time oven temperature and a preset oven temperature to obtain a time series of training real-time oven temperature target offset values; a training parameter time series feature extraction unit, configured to extract time series features from the time series of the training real-time oven temperature target offset value, the time series of the training real-time oven temperature, and the time series of the training output power to obtain a training real-time oven temperature target offset time series associated feature vector, a training real-time oven temperature time series associated feature vector, and a training output power time series associated feature vector; A training oven temperature multi-dimensional time series association unit, used for adaptively fusing the training real-time oven temperature target offset time series association feature vector and the training real-time oven temperature time series association feature vector to obtain a training oven temperature multi-dimensional time series association feature vector; A training oven temperature-output power nonlinear interactive response unit, used for inputting the training oven temperature multidimensional time series correlation feature vector and the training output power time series correlation feature vector into the nonlinear interactive response module to obtain a training oven temperature-output power time series interactive response representation vector; A training classification unit, used for inputting the training oven temperature-output power time series interactive response representation vector into the classifier-based heating element controller to obtain a control instruction; A loss function calculation unit, used to calculate a cross entropy loss function value between the control instruction and the true value to obtain a classification loss function value; A training unit is used to train the 1DCNN model-based temporal pattern feature extractor, the equalization threshold feature vector adaptive fusion module, the nonlinear interactive response module and the classifier-based heating element controller based on the classification loss function value.
8. An automatic control method for an intelligent gas oven, using the automatic control system of the intelligent gas oven according to claim 1, characterized in that: include: Get the time series of real-time oven temperature collected by the temperature sensor; Obtain the time series of the output power of the heating element; Calculating the difference between each real-time oven temperature in the time series of the real-time oven temperature and the preset oven temperature to obtain a time series of real-time oven temperature target offset values; Performing time series feature extraction on the time series of the real-time oven temperature target offset value, the time series of the real-time oven temperature, and the time series of the output power to obtain a real-time oven temperature target offset time series associated feature vector, a real-time oven temperature time series associated feature vector, and an output power time series associated feature vector; Adaptively fusing the real-time oven temperature target offset time series correlation feature vector and the real-time oven temperature time series correlation feature vector to obtain an oven temperature multi-dimensional time series correlation feature vector; Inputting the oven temperature multi-dimensional time series correlation feature vector and the output power time series correlation feature vector into a nonlinear interactive response module to obtain an oven temperature-output power time series interactive response representation vector; Based on the oven temperature-output power time series interactive response representation vector, it is determined whether the output power at the current time point should increase, decrease or remain unchanged.
Citation Information
Patent Citations
Oven temperature control method, oven temperature control device and computer-readable storage medium
CN108420320A
Oven control system and temperature control method thereof
CN112904910A
Oven and temperature control method thereof
CN114711643A
Method and device for controlling oven, oven and storage medium
CN115919160A
Management method and system for Internet of Things equipment
CN116796269A
