Oven load mass calculation method and system

Abstract

The invention discloses an oven load mass calculation method and system, and the method comprises the steps: obtaining a denoised temperature time sequence according to the temperature data in an oven body periodically collected in the working process of an oven heating tube; according to the temperature time sequence, piecewise fitting is conducted on the change relation of the temperature along with time, and a piecewise heating fitting function is obtained; according to the initial temperature, the environment temperature difference value and the heating slope in the segmented heating fitting function, the thermodynamic characteristics of the oven are combined, the heat conduction coefficient and the heat capacity parameters are optimized in real time, and optimized thermodynamic parameters are obtained; according to the thermodynamic parameters, the load mass is calculated, and a final load mass calculation result is obtained. By utilizing the embodiment of the invention, the calculation precision of the load quality can be improved, and more intelligent cooking experience is provided for a user.

Description

Technical Field

[0001] The present invention belongs to the field of metrology technology, and particularly relates to a method and system for calculating the mass of an oven load. Background Art

[0002] With the rise of home cooking culture, the use of ovens has become increasingly common. Accurately calculating the mass of the load inside the oven is particularly important to optimize cooking time and improve energy efficiency. However, there are several deficiencies in the existing technology for calculating the load mass, including the inability to effectively remove noise from temperature sensor data, insufficient linearity in fitting the temperature change relationship, limitations in dynamically adjusting thermodynamic parameters, and deficiencies in applying the load mass calculation formula to the law of conservation of energy. These defects lead to inaccurate estimation of the load mass and affect the user's cooking experience. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for calculating the mass of an oven load to solve the deficiencies in the existing technology, improve the calculation accuracy of the load mass, and provide a more intelligent cooking experience for users.

[0004] An embodiment of the present application provides a method for calculating the mass of an oven load, the method comprising: During the operation of the oven heating tube, periodically collect the temperature data inside the oven cavity. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove noise interference in the temperature data in real time and obtain a denoised temperature time series; According to the denoised temperature time series, use a fitting algorithm based on piecewise polynomial regression to perform piecewise fitting on the relationship between temperature and time. Through an adaptive piecewise point selection technique, dynamically adjust the fitting interval to ensure the fitting accuracy and obtain a piecewise heating fitting function; According to the initial temperature, ambient temperature difference, and heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, use a parameter estimation algorithm based on the nonlinear least squares method, and through a heat capacity dynamic adjustment technique, optimize the heat conduction coefficient and heat capacity parameters in real time to obtain optimized thermodynamic parameters; According to the optimized thermodynamic parameters, use a load mass calculation algorithm based on the law of conservation of energy, combined with the oven heating power and thermodynamic parameters, to calculate the mass of the load. Among them, dynamically adjust the estimated value of the load mass through a temperature change rate correction factor, and verify it by comparing with a preset load mass range to obtain the final load mass calculation result.

[0005] Optionally, during the operation of the oven heating tube, temperature data inside the oven cavity is periodically collected. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove noise interference in the temperature data in real time, and a denoised temperature time series is obtained, including: According to the temperature distribution inside the oven cavity, a data acquisition framework based on a distributed temperature sensor network is adopted, and temperature data is obtained in real time through multiple sensor nodes. Each sensor node is equipped with lightweight data caching technology to ensure the real-time and continuous nature of data acquisition; For the collected temperature data, a format recognition model based on deep learning is used to automatically identify the format types of different data sources. Through an adaptive data cleaning algorithm, noise filtering and missing value filling are performed on the data to generate a preliminary standardized data set; For the preliminary standardized data set, a dynamic noise cancellation algorithm based on Kalman filtering is adopted. Combining the temporal characteristics of the temperature data, noise interference is removed in real time. Through dynamic threshold adjustment technology, the accuracy and stability of the denoising process are ensured, and a preliminary denoised data set is generated; For the preliminary denoised data set, a data integration method based on time series analysis is adopted to map the temperature data of different sensor nodes into a unified time series. Through an interpolation filling method, missing data is supplemented to generate the final denoised temperature time series.

[0006] Optionally, based on the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is used to perform piecewise fitting on the relationship between temperature and time. Through an adaptive piecewise point selection technology, the fitting interval is dynamically adjusted to ensure the fitting accuracy, and a piecewise heating fitting function is obtained, including: For the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is adopted. Combining the local characteristics of temperature changes, piecewise points are initially selected. Through dynamic threshold adjustment technology, the rationality and accuracy of the piecewise points are ensured, and a preliminary set of piecewise points is generated; For the preliminary set of piecewise points, a fitting method based on piecewise polynomial regression is adopted. Combining the local characteristics of the temperature time series, piecewise fitting is performed. Through error calculation technology, the fitting error of each segment is calculated to generate a preliminary fitting function; For the preliminary fitting function, an adjustment method based on adaptive piecewise point selection technology is adopted. Combining the fitting error and the temperature change trend, the piecewise points are dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary set of optimized piecewise points is generated; For the preliminary set of optimized piecewise points, a fitting method based on piecewise polynomial regression is adopted. Combining the global characteristics of the temperature time series, the final piecewise heating fitting function is generated.

[0007] Optionally, based on the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, a parameter estimation algorithm based on the nonlinear least squares method is used. Through the heat capacity dynamic adjustment technology, the heat conduction coefficient and the heat capacity parameters are optimized in real time to obtain the optimized thermodynamic parameters, including: For the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, a parameter estimation algorithm based on the nonlinear least squares method is used. Combined with the thermodynamic characteristics of the oven, the heat conduction coefficient and the heat capacity parameters are initialized. Through the dynamic weight allocation technology, the rationality and accuracy of the parameter initialization are ensured, and the preliminary thermodynamic parameters are generated. For the preliminary thermodynamic parameters, a parameter estimation algorithm based on the nonlinear least squares method is used. Combined with the piecewise heating fitting function and the thermodynamic characteristics of the oven, parameter estimation is performed. Through the error calculation technology, the error of the parameter estimation is calculated, and the preliminary parameter estimation result is generated. For the preliminary parameter estimation result, an optimization method based on the heat capacity dynamic adjustment technology is used. Combined with the thermodynamic characteristics of the oven and the real-time temperature data, the heat conduction coefficient and the heat capacity parameters are dynamically adjusted. Through multiple rounds of iterative optimization, the preliminary optimized thermodynamic parameters are generated. For the preliminary optimized thermodynamic parameters, a verification method based on simulation is used. Combined with the thermodynamic characteristics of the oven and the real-time temperature data, the accuracy and stability of the parameters are verified. Through the feedback correction technology, the parameters are dynamically adjusted to generate the final optimized thermodynamic parameters.

[0008] Optionally, based on the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is used. Combined with the oven heating power and the thermodynamic parameters, the mass of the load is calculated. Among them, the estimated value of the load mass is dynamically adjusted through the temperature change rate correction factor, and through comparison and verification with the preset load mass range, the final load mass calculation result is obtained, including: For the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is used. Combined with the oven heating power and the thermodynamic parameters, the mass of the load is preliminarily calculated. Through the temperature change rate correction factor, the estimated value of the load mass is dynamically adjusted to generate the preliminary load mass calculation result. For the preliminary load mass calculation result, a comparison and verification method based on the preset load mass range is used. Combined with the thermodynamic characteristics of the oven and the real-time temperature data, the rationality and accuracy of the load mass are verified. Through the dynamic threshold adjustment technology, the accuracy and stability of the verification process are ensured, and the preliminary verification result is generated. For the preliminary verification result, an optimization method based on the feedback correction technology is used. Combined with the thermodynamic characteristics of the oven and the real-time temperature data, the estimated value of the load mass is dynamically adjusted. Through multiple rounds of iterative optimization, the preliminary optimized load mass calculation result is generated. For the preliminary optimized load mass calculation results, an output method based on visualization technology is adopted to integrate the load mass calculation results and verification results into the final load mass calculation result report.

[0009] Another embodiment of the present application provides a calculation system for the load mass of an oven, and the system includes: An acquisition module, configured to periodically acquire the temperature data inside the oven cavity during the operation of the oven heating tube. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time, and obtain the denoised temperature time series; A fitting module, configured to perform piecewise fitting on the relationship between temperature and time according to the denoised temperature time series by using a fitting algorithm based on piecewise polynomial regression, and dynamically adjust the fitting interval through an adaptive piecewise point selection technique to ensure the fitting accuracy, and obtain a piecewise heating fitting function; An optimization module, configured to combine the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, and combine with the thermodynamic characteristics of the oven, and adopt a parameter estimation algorithm based on the nonlinear least squares method, and dynamically adjust the heat conduction coefficient and heat capacity parameters in real time through a heat capacity dynamic adjustment technique to obtain the optimized thermodynamic parameters; A calculation module, configured to calculate the mass of the load according to the optimized thermodynamic parameters by using a load mass calculation algorithm based on the law of conservation of energy, in combination with the oven heating power and thermodynamic parameters. Among them, the estimated value of the load mass is dynamically adjusted through a temperature change rate correction factor, and the final load mass calculation result is obtained through comparison and verification with a preset load mass range.

[0010] Another embodiment of the present application provides a storage medium, in which a computer program is stored, and the computer program is configured to execute the method described in any one of the above when running.

[0011] Another embodiment of the present application provides an electronic device, including a memory and a processor, a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of the above.

[0012] Compared with the prior art, a method for calculating the load mass of an oven provided by the present invention periodically collects temperature data inside the oven cavity during the operation of the oven heating tube to obtain a denoised temperature-time series; based on the temperature-time series, the change relationship between temperature and time is segmented and fitted to obtain a segmented heating fitting function; according to the initial temperature, the ambient temperature difference, and the heating slope in the segmented heating fitting function, combined with the thermodynamic characteristics of the oven, the heat conduction coefficient and the heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; according to the thermodynamic parameters, the mass of the load is calculated to obtain the final calculation result of the load mass, thereby being able to improve the calculation accuracy of the load mass and provide a more intelligent cooking experience for users. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a hardware structure block diagram of a computer terminal for a method for calculating the load mass of an oven provided by an embodiment of the present invention; Figure 2 It is a schematic flow chart of a method for calculating the load mass of an oven provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of a system for calculating the load mass of an oven provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0015] An embodiment of the present invention first provides a method for calculating the load mass of an oven. This method can be applied to electronic devices, such as computer terminals, specifically ordinary computers, etc.

[0016] The following takes running on a computer terminal as an example to explain it in detail. Figure 1 It is a hardware structure block diagram of a computer terminal for a method for calculating the load mass of an oven provided by an embodiment of the present invention. As Figure 1 shown, the computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the memory can include a non-volatile storage medium and an internal memory.

[0017] The non-volatile storage medium can store an operating system and a computer program. This computer program includes program instructions. When the program instructions are executed, the processor can execute any method for calculating the load mass of an oven.

[0018] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0019] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by a processor, it enables the processor to execute any method for calculating the mass of the oven load.

[0020] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 1 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0021] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0022] See Figure 2 , an embodiment of the present invention provides a method for calculating the mass of an oven load, which may include the following steps: S201, according to the working process of the oven heating tube, periodically collect the temperature data inside the oven cavity. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time, and obtain a denoised temperature time series; The steps in this method involve periodically collecting the temperature data inside the oven cavity according to the working process of the oven heating tube. This process uses a distributed temperature sensor network, and temperature sensor nodes can be set at multiple positions inside the oven to obtain temperature information in real time. At the same time, in order to ensure the reliability and accuracy of the data, a dynamic noise cancellation algorithm based on Kalman filtering is used to process the collected temperature data to remove noise interference, so as to obtain a clear temperature time series. This method effectively overcomes the instability of temperature data caused by environmental changes, equipment performance, or defects of the sensors themselves, and ensures the accuracy and reliability of the basic data for subsequent calculations.

[0023] Periodically collecting the internal temperature of the oven and applying a noise cancellation algorithm not only provides the basic data for subsequent load quality calculation but also significantly improves the credibility and analytical ability of the data. Through denoising processing, it can more accurately reflect the true temperature change trend of the oven during the heating process. In promoting the application and development of smart oven technology, the implementation of this step helps to improve the control accuracy and efficiency of the oven, ultimately enhancing the user experience and cooking effect.

[0024] Specifically, according to the temperature distribution inside the oven cabinet, a data acquisition framework based on a distributed temperature sensor network can be adopted. Temperature data is obtained in real time through multiple sensor nodes, and each sensor node is equipped with lightweight data caching technology to ensure the real-time and continuous nature of data acquisition. This step involves establishing a temperature acquisition system based on a distributed sensor network, with multiple temperature sensor nodes installed inside the oven to collect temperature data at different locations in real time. Each sensor node is equipped with lightweight data caching technology to ensure stable operation even in a high-temperature environment and can effectively reduce latency during data transmission. This design greatly improves the accuracy and coverage of temperature acquisition, laying a good foundation for subsequent data processing and analysis. Through the application of a distributed temperature sensor network, the temperature changes inside the oven can be comprehensively monitored, eliminating the problem of local data deviation that may be caused by a single sensor. This technology ensures the temperature control accuracy of the oven at different cooking stages, thereby improving the cooking effect and food quality and ensuring that users can obtain an ideal cooking experience.

[0025] During the implementation process, first, an architecture based on a distributed temperature sensor network is designed, which can collect the temperature data at different locations inside the oven in real time. Each sensor node is installed in a different area of the oven to ensure full coverage of the temperature distribution inside the oven. To achieve efficient data acquisition, each sensor node is equipped with lightweight data caching technology, which can temporarily store the latest temperature data during data transmission to cope with instantaneous fluctuations or network delays.

[0026] For example, assume there are five sensor nodes inside the oven, located at the top, middle, bottom, and left and right sides respectively. After each node collects the temperature data, it will first save the data in the local cache and then send the data to the central processing unit through the wireless network at regular intervals. This not only achieves the real-time nature of the data but also ensures that critical data is not lost in case of emergencies (such as signal interference), improving the system stability.

[0027] With such a design, the system can ensure that the temperature data inside the oven is accurately and timely collected as high-quality input data, providing a solid foundation for subsequent noise elimination and analysis. Especially during the baking process, where the temperature changes rapidly and frequently, timely data collection can help better grasp the baking status.

[0028] For the collected temperature data, a format recognition model based on deep learning is adopted to automatically identify the format types of different data sources. Through an adaptive data cleaning algorithm, the data is filtered for noise and missing values are filled to generate a preliminary standardized dataset. After data collection, the system uses deep learning algorithms for format recognition, analyzes the data formats provided by different sensors, and automatically normalizes the data structure. This process ensures that the data from different sensor nodes can be analyzed and applied within the same framework. Subsequently, through the adaptive data cleaning algorithm, the system can promptly identify the noise and missing values in the data, perform effective filtering and supplementation, and generate a standardized dataset for subsequent analysis. This step ensures the consistency of data processing, reduces the difficulty of data parsing caused by inconsistent formats, and at the same time, through noise filtering and missing value filling, greatly improves the integrity and effectiveness of the data. This is of great significance for achieving efficient data analysis and improving the prediction accuracy of the model.

[0029] In this step, first, a format recognition model based on deep learning is applied to analyze the collected temperature data. This model can automatically identify the data formats transmitted by each sensor, ensuring the uniformity of data from different sensors. Through the trained neural network, the system can quickly judge the validity of the data and distinguish outliers and noisy data.

[0030] For example, assume that the data transmitted by a certain sensor node has a format error or logical inconsistency (such as a sudden temperature change). The deep learning model will mark these abnormal data and eliminate them. Then, the system will use the adaptive data cleaning algorithm to conduct a more in-depth analysis of the suspicious data, including noise filtering and filling of missing values. For instance, if a sensor fails to send data during a certain period, the system will supplement the missing values according to the data of adjacent times through interpolation method, thus generating a preliminary standardized dataset.

[0031] The generated standardized dataset will be the basis for the next step of denoising, ensuring more accurate subsequent analysis. This process is crucial for handling inconsistent formats of different sensors and data integrity, and can effectively reduce human interference in the data processing process and improve the data quality.

[0032] For the preliminary standardized data set, a dynamic noise cancellation algorithm based on Kalman filtering is adopted. Combining the temporal characteristics of temperature data, it removes noise interference in real time. Through dynamic threshold adjustment technology, it ensures the accuracy and stability of the denoising process and generates a preliminary denoised data set; After obtaining the preliminary standardized data set, the system further denoises it through the Kalman filtering algorithm. This algorithm combines the temporal characteristics of real-time temperature data and can dynamically adjust the threshold of noise cancellation to adapt to the changing trend of the data. This process aims to eliminate random noise and systematic errors, ensuring that the final data set can truly reflect the changing trend of temperature while maintaining stability. By adopting the dynamic noise cancellation algorithm, the accuracy of temperature data can be significantly improved, making it closer to the real temperature state. This provides reliable data support for subsequent thermodynamic parameter calculations and load mass evaluations, thereby enhancing the intelligence level and performance of the entire system.

[0033] When implementing this step, the system will use a dynamic noise cancellation algorithm based on Kalman filtering to process the preliminary standardized data set. The Kalman filter is a recursive filter that can effectively extract signals from noise, especially suitable for processing data with temporal characteristics. The system will make dynamic predictions based on the past data of each sensor and the currently collected data, and use the predicted values to judge the accuracy of the current temperature data.

[0034] For example, assume that the temperature data collected by a certain sensor shows abnormal fluctuations at a certain moment (possibly due to external interference or sensor failure). Then, through Kalman filtering, the system can predict the current temperature value using the temperature data at previous time points and compare it with the actually collected data to identify and remove the noise data. In addition, the dynamic threshold adjustment technology can adaptively adjust the noise filtering standard according to the fluctuation range of real-time data to ensure the accuracy and stability of noise removal.

[0035] After this processing, the system will generate a preliminary denoised data set, which will provide clear and reliable basic data for subsequent time series analysis and fitting. The accuracy of this step directly affects the effectiveness of subsequent analysis results and is a key link in the entire process.

[0036] For the preliminary denoised data set, a data integration method based on time series analysis is adopted to map the temperature data of different sensor nodes into a unified time series. Through the interpolation filling method, the missing data is supplemented to generate the final denoised temperature time series.

[0037] After generating the preliminary denoised dataset, this step integrates the temperature data from different sensor nodes into a unified time series through time series analysis. During this process, the interpolation filling method is used to handle missing values while avoiding misalignment of data time points, thereby ensuring that the final temperature time series can completely and accurately reflect the temperature dynamics inside the oven. The implementation of this step ensures the integrity and coherence of the data, laying a good foundation for subsequent model fitting and load evaluation. The unified time series data can better display the temperature change trend, thereby enhancing the scientificity and accuracy of data analysis.

[0038] In this step, a time series analysis-based method is adopted to integrate the denoised temperature data collected by different sensors into a unified time series. At this time, the system will consider the time synchronization problem between different sensors because the data collection of each sensor is not always completely synchronized. Through timestamp alignment, the system can integrate the temperature values of different sensors at the same time point.

[0039] For example, assume that five sensors record temperature data at different time periods. By analyzing the timestamps of each data point, the system will integrate and map them into a unified time series. For any missing data points, the system will apply interpolation filling methods, such as linear interpolation or spline interpolation, to automatically calculate reasonable temperature data to fill in the missing values. This method not only improves the integrity of the data but also ensures the smoothness and continuity of the entire time series.

[0040] Finally, the generated denoised temperature time series will provide reliable data input for subsequent fitting of temperature changes and is the basis for achieving high-precision load quality calculation. The successful execution of this step ensures the efficiency and accuracy of the data processing flow and lays a solid foundation for the intelligent control of the entire baking process.

[0041] S202. According to the denoised temperature time series, adopt a fitting algorithm based on piecewise polynomial regression to perform piecewise fitting on the relationship between temperature and time. Through the adaptive piecewise point selection technique, dynamically adjust the fitting interval to ensure the fitting accuracy and obtain the piecewise heating fitting function. In this step, through the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is used to perform piecewise fitting on the relationship between temperature and time. The key to this method lies in the adaptive piecewise point selection technique, which dynamically adjusts the fitting interval according to the change characteristics of the temperature sequence to better adapt to the non-linear change of temperature. This piecewise regression design enables different time periods to use different polynomials for local fitting according to the actual temperature change situation, thereby improving the fitting accuracy and finally generating a piecewise heating fitting function that contains all the piecewise temperature change characteristics.

[0042] The implementation of this step is crucial for accurately describing the temperature change law inside the oven. By effectively capturing the dynamic change of temperature over time, this fitting function provides accurate temperature data support for subsequent load mass calculation. Piecewise polynomial regression can not only effectively address the non-linear problems brought about by temperature changes, but also improve the system's understanding ability of complex baking processes, thereby optimizing the cooking process, enhancing baking efficiency and food quality, and bringing a better experience to users.

[0043] Specifically, for the denoised temperature-time series, a fitting algorithm based on piecewise polynomial regression can be adopted. Combining the local characteristics of temperature changes, preliminary segmentation points can be selected. Through dynamic threshold adjustment technology, the rationality and accuracy of the segmentation points can be ensured to generate a preliminary set of segmentation points. In this step, the system first analyzes the denoised temperature-time series. By observing the temperature change trend and local characteristics, potential segmentation points are initially selected. These segmentation points are usually in areas where the temperature changes significantly, such as moments of temperature mutation or high change rate. Then, by applying dynamic threshold adjustment technology, based on the characteristic changes of the selected segmentation points, the system will evaluate the rationality of the segmentation points to ensure that the selected segmentation points can truly reflect the characteristics of temperature fluctuations.

[0044] The selection of reasonable segmentation points is the basis for achieving accurate fitting. By ensuring that the selected segmentation points reflect the key characteristics of temperature changes, information loss during the fitting process can be effectively avoided, and the performance of the fitting model can be improved. In this way, the subsequent piecewise regression model will be more capable of accurately reflecting the actual situation of temperature changes, laying a solid foundation for the subsequent load mass calculation.

[0045] At this stage, the system will rely on the denoised temperature-time series data and conduct a detailed analysis of temperature changes through a fitting algorithm based on piecewise polynomial regression. First, the system will conduct a preliminary check on the time series data to identify intervals with large price fluctuations or significant changes as possible segmentation points. Combining the local characteristics of temperature changes, the algorithm automatically selects possible segmentation points to ensure that these points can reflect the trend and characteristics of temperature changes.

[0046] For example, assume that during the oven heating process, the recorded temperature data steadily rises during a certain period of time, while there are rapid fluctuations during another period. The system will use dynamic threshold adjustment technology to screen and adjust the possible segmentation points. This dynamic threshold can not only ensure the rationality of the selected segmentation points, but also prevent misjudgment caused by short-term abnormal fluctuations in temperature data, thereby generating a preliminary set of segmentation points.

[0047] With this method, the system can accurately identify different temperature change patterns, providing an important basis for subsequent segmented fitting. By ensuring the accuracy of the segmentation points, the system lays a good foundation for the accuracy of the fitting results from the beginning.

[0048] For example, during the oven heating process, the temperature change record shows that the temperature rises from room temperature (25°C) to 150°C between 0 and 5 minutes, then remains at 150°C between 5 and 10 minutes, and then quickly rises to 250°C between 10 and 15 minutes. When the system analyzes this data, it first observes that the temperature change from 0 to 5 minutes is large and the rate of change is fast, so the system initially selects 0 minutes and 5 minutes as segmentation points. Between 5 and 10 minutes, the temperature remains unchanged, so 5 minutes and 10 minutes can be selected as a segment again. Between 10 and 15 minutes, the temperature rises rapidly again, and the system uses 10 minutes and 15 minutes as new segmentation points. Finally, after dynamic threshold adjustment, the system returns the initial segmentation point set as {0 minutes, 5 minutes, 10 minutes, 15 minutes} to facilitate more accurate temperature change fitting in the future.

[0049] For the preliminary segmented point set, a fitting method based on segmented polynomial regression is used, combined with the local characteristics of the temperature time series, to perform segmented fitting. The fitting error of each segment is calculated through error calculation technology to generate a preliminary fitting function. The core of this step is to apply the piecewise polynomial regression method to fit the initially selected set of segment points. The system uses a polynomial model of appropriate order to perform fitting calculations based on the characteristics of each segment, and adjusts the model parameters to improve the overall fitting effect by calculating the fitting error of each segment. Finally, multiple segmented fitting functions are generated, which will better characterize the relationship between temperature and time.

[0050] By fitting the temperature change in sections, the temperature characteristics of different stages can be effectively captured. This segmented fitting model makes the description of temperature fluctuations more accurate and helps optimize the subsequent load mass calculation. Accurate fitting functions will enhance the prediction and control capabilities of the entire system, thereby further improving the accuracy and consistency of the baking process.

[0051] In this step, the system will analyze the preliminary segment point set in detail and apply the fitting method based on segmented polynomial regression to perform actual data fitting. The system first divides the data into multiple segments and applies polynomial regression to each segment separately to generate its own fitting function. The polynomial of each fitting segment needs to be designed according to the local characteristics to ensure accurate capture of temperature changes within a specific time period.

[0052] Taking the heating process of an oven as an example, assume that the first segment is the "preheating stage" and the second segment is the "high-temperature stage". For each segment, the system will calculate the error between the fitting function and the actual temperature data. Through error calculation techniques, the fitting accuracy of each segment can be identified. This includes calculating metrics such as mean square error and absolute error for comparison and optimization.

[0053] The generated preliminary fitting function reflects the relationship between temperature and time within each segment, providing a theoretical basis for subsequent steps. Through this process, the system can simplify the complex temperature changes into a segmented model that is easy to analyze, thus laying a solid foundation for more in-depth thermal dynamic analysis.

[0054] For example, in this step, for the set of segmentation points {0 minutes, 5 minutes, 10 minutes, 15 minutes} generated previously, the system will perform polynomial regression fitting for each segment separately. For the first segment (0 to 5 minutes), the system will establish a first-degree polynomial (a straight line) to fit a temperature change curve from 25°C to 150°C. Then, in the stage from 5 to 10 minutes, since the temperature remains at 150°C, a constant function is used for fitting. For the segment from 10 to 15 minutes, a quadratic polynomial is used for fitting considering the temperature change during reheating from 250°C. Finally, the system calculates the fitting errors for each segment. For example, the fitting error for the first segment is 1°C, the second segment has an error of 0°C, and the third segment has an error of 2°C. The ultimately generated preliminary fitting function includes these polynomials corresponding to each segment respectively.

[0055] For the preliminary fitting function, an adjustment method based on the adaptive segmentation point selection technique is adopted. Combining the fitting error and the temperature change trend, the segmentation points are dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary set of optimized segmentation points is generated; In this step, based on the output of the preliminary fitting function, the system uses the adaptive segmentation point selection technique to dynamically adjust the segmentation points. Combining the fitting error and the temperature change trend, the system continuously evaluates the performance of each segment and iteratively optimizes the position of the segmentation points according to the situation, thereby ensuring that each segment can fully respond to the dynamic change characteristics of the temperature.

[0056] Through multiple rounds of iterative optimization, the accuracy of the fitting model can be significantly improved, ensuring that temperature changes can be captured in great detail. This dynamic adjustment mechanism not only enhances the flexibility of the model but also effectively avoids fitting deviations caused by improper selection of segmentation points, providing a reliable data basis for subsequent analysis and calculation.

[0057] At this stage, the system will dynamically adjust the segmentation points using adaptive segmentation point selection technology based on the preliminary fitting function and the calculated error. This process combines the fitting error and the temperature change trend. The system will automatically judge the fitting accuracy of each segment. If the error of a certain segment is too large, it will consider adjusting its segmentation point to improve the overall fitting accuracy.

[0058] For example, assume that within a certain segment, the system detects that the fitting error exceeds the preset threshold. By analyzing the data change trend within this segment, the system may decide to adjust the segmentation point towards the sharp position of the data change to more accurately reflect the real temperature change. Through multiple rounds of iterative optimization, the system will continuously correct and adjust the segmentation points to ensure that the fitting function of each segment can reach the expected accuracy.

[0059] The generated set of optimized segmentation points will further improve the accuracy of the segmented fitting, ensuring that the temperature change characteristics can be more reliably described during different heating stages. This process not only improves the accuracy of the thermal dynamic model but also provides more detailed basic data for subsequent optimization of thermodynamic parameters.

[0060] For example, after obtaining the preliminary fitting function, the system notices that in the first segment, although the fitting error is 1°C, the temperature has a significant rise after 5 minutes. Therefore, it may be necessary to further refine the segmentation. Using the adaptive segmentation point selection technology, the system attempts to further divide this temperature change into two smaller segments and selects the temperature value (100°C) at 3 minutes as the new segmentation point. After multiple rounds of iteration, the system continuously evaluates the error of each new segment. The finally generated set of optimized segmentation points is {0 minutes, 3 minutes, 5 minutes, 10 minutes, 15 minutes}. In this way, the system can more accurately model the temperature change during the operation process and improve the fitting accuracy.

[0061] For the preliminary set of optimized segmentation points, use the fitting method based on piecewise polynomial regression and combine the global characteristics of the temperature time series to generate the final piecewise heating fitting function.

[0062] In this step, the system will finally use the piecewise polynomial regression method to generate the complete piecewise heating fitting function based on the optimized set of segmentation points. Combining the global characteristics of the temperature time series, the system will perform the final fine adjustment on each segment to ensure that the final fitting function can accurately represent the law of temperature change over time.

[0063] The finally generated piecewise heating fitting function is the core output of the entire model. It not only provides an effective basis for calculating the load mass but also lays a foundation for the intelligent control of the cooking process. Through this high-precision model, the system can better achieve precise control of oven heating in practical applications, improving the quality and consistency of baked products.

[0064] In the last step, the system will perform a final fit on the optimized set of segmentation points to generate a complete piecewise heating fitting function. At this time, based on the global temperature-time series characteristics, the system will use a method based on piecewise polynomial regression to fit each segment again. The key point in the whole process is to ensure that the fitting of each segment can take into account both local characteristics and global consistency.

[0065] For example, assume that after previous optimization, there are now four segments, each corresponding to a different heating stage (such as: preheating stage, continuous heating stage, cooling stage, etc.). For each segment, the system will select the best polynomial order so that the fitting function can accurately reflect the temperature change within this stage and at the same time maintain smooth switching with other stages.

[0066] The finally generated piecewise heating fitting function will serve as the basis for subsequent optimization of thermodynamic parameters and calculation of load mass. Through this refined fitting, the system can comprehensively and accurately analyze the temperature change of the oven, ensuring precise control and optimization throughout the baking process.

[0067] For example, at this stage, the system has generated an optimized set of segmentation points {0 minutes, 3 minutes, 5 minutes, 10 minutes, 15 minutes}. Next, the system will perform a final fit for each segment using piecewise polynomial regression. In the segment from 0 to 3 minutes, a first-order polynomial is used to describe the temperature rising from 25°C to 100°C; between 3 and 5 minutes, a first-order polynomial is used to continue describing the rapid temperature rise; in the stage from 5 to 10 minutes, a constant function still applies, maintaining at 150°C; while between 10 and 15 minutes, the system will use a second-order polynomial to more carefully describe the temperature rise, taking into account the change in heating power. Finally, the complete piecewise heating fitting function generated by the system will combine the global data change to ensure the smoothness and continuity of the fitting, providing an accurate temperature change analysis model and laying a foundation for subsequent calculation of thermodynamic parameters.

[0068] S203, according to the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, using a parameter estimation algorithm based on the nonlinear least squares method, through the heat capacity dynamic adjustment technology, optimize the heat conduction coefficient and heat capacity parameters in real time to obtain the optimized thermodynamic parameters; In this step, the method combines the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, and uses a parameter estimation algorithm based on the nonlinear least squares method to analyze the thermal conductivity characteristics of the oven. Through this algorithm, the system can accurately estimate the thermal conductivity coefficient and the heat capacity parameter from the actually measured temperature data. This is achieved through multiple iterations. In each iteration, the algorithm adjusts the parameters targeted according to the existing temperature data and the model output, uses the heat capacity dynamic adjustment technology to optimize the results to be closer to the actual thermodynamic performance, and then obtains the optimized thermodynamic parameters to ensure the accuracy and reliability of the model.

[0069] The implementation of this step is crucial for accurately describing the thermodynamic behavior of the oven. By real-time optimizing the thermal conductivity coefficient and the heat capacity parameter, it can ensure the accurate modeling of the heat transfer and storage processes by the system. This level of accuracy not only improves the control ability of the baking process but also enhances the energy efficiency, making the oven more efficient and intelligent during the actual baking process, and ultimately providing users with high-quality cooking effects and experiences.

[0070] Specifically, for the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, a parameter estimation algorithm based on the nonlinear least squares method can be used. Combining with the thermodynamic characteristics of the oven, the thermal conductivity coefficient and the heat capacity parameter are initialized. Through the dynamic weight allocation technology, the rationality and accuracy of the parameter initialization are ensured, and preliminary thermodynamic parameters are generated. In this step, the system uses the initial temperature, the ambient temperature difference, and the heating slope provided by the piecewise heating fitting function, and applies the nonlinear least squares method to initialize the thermal conductivity coefficient and the heat capacity parameter of the oven. The dynamic weight allocation technology plays a key role in this process. It quantifies the influence according to the importance of each parameter on the overall prediction, thereby reasonably allocating weights to ensure that the generated preliminary thermodynamic parameters have sufficient accuracy in practical applications. This process lays a solid foundation for the subsequent parameter optimization.

[0071] This step ensures the rationality of the initialization of the thermodynamic parameters. By scientifically initializing these parameters, the system can more accurately simulate the heat transfer process of the oven, reducing the uncertainty in the subsequent calculation process. This not only improves the stability of the model but also enhances the adaptability of the oven under different heating conditions, providing a reliable basis for achieving accurate load mass calculation.

[0072] At this stage, we first need to determine the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function. Assume that the initial temperature is set at 150°C, the ambient temperature is 25°C, and the heating slope is 5°C / min. Next, based on these parameters, we will use the non-linear least squares method for parameter initialization. This process involves constructing a mathematical model for the thermal conductivity and heat capacity parameters, and we will derive reasonable initial values based on the thermodynamic characteristics of the oven, such as the material's thermal conductivity properties and heat capacity. For example, the thermal conductivity may be initialized at 0.4 W / (m·K), and the heat capacity parameter at 2.0 J / (kg·K).

[0073] To ensure the reasonableness and accuracy of these initial parameters, we introduce the dynamic weight allocation technique. By monitoring the data obtained from multiple sensors in real-time, the system can evaluate the accuracy of each sensor. For example, if the temperature readings of a certain sensor are relatively stable and consistent with the data of other sensors, it will be given a higher weight; conversely, if the data of a certain sensor fluctuates greatly, its weight will be reduced. In this way, we can extract more reliable information from data of different sources, thereby generating preliminary thermodynamic parameters, which will be used for optimization and verification in subsequent steps.

[0074] Finally, after parameter initialization and weight allocation, we will obtain a set of preliminary thermodynamic parameters. These parameters will serve as the basis for subsequent calculation of the load mass and optimization. Through this series of steps, we ensure that the parameters not only conform to physical meaning but also contribute to improving the accuracy and stability of the entire calculation process, laying a good foundation for subsequent calculations.

[0075] For example, at the start of the heating process of an oven, the initial temperature is first recorded as 150°C, and the external ambient temperature is 25°C. Assume the heating slope is 5°C / min. Based on these data, the researchers establish a temperature change model to describe the heat transfer behavior during the heating process. Based on the non-linear least squares method, the researchers set the initial value of the thermal conductivity at 0.4 W / (m·K) and the initial value of the heat capacity parameter at 2.0 J / (kg·K). During the subsequent experimental process, the researchers record the temperature changes at different positions inside the oven through multiple distributed temperature sensors. To improve the accuracy of parameter initialization, the researchers use the dynamic weight allocation technique to assign weights based on the data stability of each sensor. For example, for a certain sensor with consistent results in multiple measurements, the weight is set at 0.8, while for another sensor with large fluctuations due to environmental interference, the weight is set at 0.2. Through this dynamic weighting, the preliminary thermodynamic parameters are finally adjusted to a thermal conductivity of 0.42 W / (m·K) and a heat capacity parameter of 2.1 J / (kg·K).

[0076] For the preliminary thermodynamic parameters, a parameter estimation algorithm based on the nonlinear least squares method is adopted. Combining the piecewise heating fitting function and the thermodynamic characteristics of the oven, parameter estimation is carried out. Through the error calculation technique, the error of the parameter estimation is calculated to generate the preliminary parameter estimation result; In this step, based on the previously generated preliminary thermodynamic parameters, combining the piecewise heating fitting function and the thermodynamic characteristics of the oven, the system continues to use the nonlinear least squares method for parameter estimation. By calculating the error between the model output and the actual measurement, the system can evaluate the accuracy of the current parameter estimation and adjust the parameters accordingly to approximate the actual situation. This iterative process makes the parameter estimation result gradually converge and improves the overall model accuracy. Through this step, the system can achieve refined estimation of the parameters, thereby improving the accuracy of the oven thermal behavior model. This is the basis for the entire load mass calculation. Ensuring that the thermal characteristics are characterized by accurate parameters can greatly improve the reliability and effectiveness of subsequent calculations. Ultimately, this will directly affect the user's cooking quality and experience.

[0077] Next, we will use the preliminary thermodynamic parameters and combine them with the piecewise heating fitting function to perform further parameter estimation. First, the system will set an objective function based on the previous thermodynamic model, attempting to minimize the difference between the predicted temperature and the actually measured temperature. For example, assuming that the real-time temperature data of the oven varies over different time periods, the system will compare these temperature data with the preliminarily estimated model to form a temperature error array.

[0078] We will use the nonlinear least squares method to update the thermal conductivity and heat capacity parameters iteratively. In each iteration, the system will calculate the prediction error brought by the new parameters and compare it with the previous error. If the newly estimated error is less than the current error, then the current parameter update will be accepted. For example, if the preliminary thermal conductivity is 0.4 W / (m·K), and it is found through iterative calculation that the optimal value is 0.45 W / (m·K), the system will record the new parameter value.

[0079] Through this iterative process, we will gradually generate a set of parameter estimation results that are closer to the actual situation. At the end of each iteration, the system will output the current error report to help engineers intuitively evaluate the accuracy of the parameters. This series of calculation and verification processes will ensure that the parameters we obtain not only conform to the thermodynamic principles but also can be effectively applied to the load calculation of the actual oven, thereby providing a basis for subsequent dynamic adjustment.

[0080] For example, after obtaining the initial thermal conductivity and heat capacity parameters, the researchers used the temperature-time series data inside the oven for parameter estimation. The thermal conductivity was set to 0.42 W / (m·K), and the heat capacity parameter was 2.1 J / (kg·K). The real-time temperature change data was recorded as follows: as time increased, the temperature inside the oven gradually rose from 150°C to 200°C. The researchers constructed an objective function through the nonlinear least squares method to minimize the difference between the temperature predicted by the model and the actually measured temperature. By comparing the temperature data at each moment, the calculated temperature prediction error was 2°C. After multiple iterations, the researchers found that adjusting the thermal conductivity to 0.45 W / (m·K) could significantly reduce the error. In this way, the final parameter estimation result was a thermal conductivity of 0.45 W / (m·K), while the heat capacity parameter remained unchanged at 2.1 J / (kg·K).

[0081] For the initial parameter estimation results, an optimization method based on the heat capacity dynamic adjustment technology is adopted. Combining the thermodynamic characteristics of the oven and the real-time temperature data, the thermal conductivity and heat capacity parameters are dynamically adjusted. Through multiple rounds of iterative optimization, preliminary optimized thermodynamic parameters are generated; This step mainly focuses on using the heat capacity dynamic adjustment technology to optimize and adjust the initial parameter estimation results. Combining the real-time temperature data, the system will dynamically adjust the thermal conductivity and heat capacity parameters each time according to the thermodynamic characteristics of the oven. Through multiple rounds of iteration, the system can reflect the actual thermal behavior in real time, thereby gradually improving the thermodynamic parameters and ensuring their adaptation to different working conditions. The implementation of this step enables the thermodynamic parameters to adapt to the actual operating state, improving the flexibility and accuracy of the model. Through dynamic adjustment, the system can maximize the reflection of the impact brought by temperature changes, making the load mass calculation more accurate. This high-precision thermal dynamic model not only improves the control ability of the baking process but also significantly optimizes the energy efficiency and resource utilization.

[0082] After obtaining the initial parameter estimation, we will apply the heat capacity dynamic adjustment technology to continuously and dynamically adjust the thermal conductivity and heat capacity parameters based on the real-time temperature data. This process first requires real-time monitoring of the temperature change inside the oven. For example, within a certain time period, the temperature monitoring data may rapidly rise from 150°C to 200°C. In this case, if the previous parameters cannot match the new temperature response, we need to dynamically adjust the parameters.

[0083] Specifically, the system utilizes the thermodynamic characteristics of the current oven and optimizes the heat transfer coefficient and heat capacity parameters through a heat capacity dynamic adjustment algorithm. For example, if the currently set heat transfer coefficient is 0.45 W / (m·K), and the newly measured temperature change rate indicates that this parameter needs to be increased, the system may adjust it to 0.48 W / (m·K). This adjustment process is based on real-time data feedback. The system continuously monitors the temperature change and issues an alarm when necessary to remind relevant personnel to make adjustments.

[0084] Through multiple rounds of iterative optimization, the system will continuously update these parameters to ensure that they always remain optimal during the operation of the oven. After each round of iteration, the system will compare the errors before and after optimization and calculate the magnitude of error improvement to ensure the effectiveness of the optimization process. For example, after multiple rounds of adjustment, assuming that the heat transfer coefficient stabilizes at 0.50 W / (m·K) and the heat capacity parameter is adjusted to 2.1 J / (kg·K), these optimized parameters will be used for subsequent load mass calculations to improve the performance and efficiency of the entire system.

[0085] For example, based on the preliminary parameter estimation, the research team continued to optimize. Along with the temperature change during the oven heating process, real-time data showed that the oven temperature rapidly increased from 150°C to 230°C in a short period of time. Against this background, the researchers decided to utilize the heat capacity dynamic adjustment technology to optimize the heat transfer coefficient and heat capacity parameters in real time. Through temperature monitoring, it was found that the heat transfer coefficient failed to reflect the change in a timely manner when dealing with the rapid temperature rise, and real-time feedback required it to be adjusted to 0.48 W / (m·K). At the same time, considering the rapid temperature rise response, the heat capacity parameter was dynamically adjusted to 2.15 J / (kg·K). In the following multiple rounds of iteration, the new heat transfer parameter and heat capacity parameter were input into the model, and the system continued to monitor the difference between the actual temperature and the temperature predicted by the model. After optimization and adjustment, the final determined heat transfer coefficient was 0.49 W / (m·K) and the heat capacity parameter was 2.13 J / (kg·K), and these parameters will be used for subsequent load mass calculations.

[0086] For the preliminary optimized thermodynamic parameters, a verification method based on simulation is adopted. Combining the thermodynamic characteristics of the oven and real-time temperature data, the accuracy and stability of the parameters are verified. Through feedback correction technology, the parameters are dynamically adjusted to generate the final optimized thermodynamic parameters.

[0087] In the final step, the system verifies the optimized thermodynamic parameters using simulation technology. Combining the thermodynamic characteristics of the oven and real-time temperature data, the system will run multiple scenario simulations to detect how the parameters perform under different conditions. Through feedback correction technology, based on the differences between the simulation results and actual data, the parameters are further dynamically adjusted to ensure their accuracy and stability. This verification process is extremely important, ensuring the practicality and reliability of the optimized thermodynamic parameters. Accurate thermal parameters can significantly improve subsequent load mass calculations and energy predictions, enhancing the performance of the oven in actual operation. Ultimately, it improves cooking consistency and food quality, bringing a higher level of user experience.

[0088] After optimizing the thermodynamic parameters, we need to verify their accuracy and stability, and this process will be carried out using a simulation-based method. First, the system will build a detailed thermodynamic model that can reflect the thermal characteristics of the oven and the impact of environmental changes. In this model, the system will input the optimized heat transfer coefficient and heat capacity parameters and simulate the temperature change process under different conditions.

[0089] By comparing with the actually measured data, the system will evaluate the gap between the simulation results and the actual results in real time. For example, if the simulation results show that the temperature change is 195°C while the actual temperature is 200°C, the system will record this error and analyze the reason. If the parameter settings lead to obvious deviations, the system will automatically adjust these parameters through feedback correction technology to achieve a better fitting effect. This process often involves adjusting the heat transfer coefficient or other related parameters to eliminate the error.

[0090] After multiple rounds of verification and feedback adjustment, we will generate the final optimized thermodynamic parameters. These parameters must show high accuracy and stability both in simulation and in actual situations. For example, the finally determined heat transfer coefficient is 0.52 W / (m·K), and the heat capacity parameter is 2.15 J / (kg·K). These parameters will be used as the basis for calculating the load mass of the oven, ensuring that the entire system can operate efficiently under various working conditions and meet the expected performance indicators.

[0091] For example, after completing the parameter optimization, the research team began to verify the accuracy and stability of these thermodynamic parameters. A thermodynamic model was constructed using simulation technology, and the latest thermal conductivity of 0.49 W / (m·K) and heat capacity parameter of 2.13 J / (kg·K) were input into the model. By running the model for simulation, the environmental temperature change and heat distribution inside the oven were simulated. The researchers observed that the simulation results showed that the temperature peak reached 225°C, with a 5°C difference from the actual measurement of 230°C. In view of this, the researchers adopted a feedback correction technique, that is, fine-tuned the thermal conductivity and tried to increase its value to 0.50 W / (m·K). After re-simulation, the new results showed that the temperature difference from the actual value was reduced to 2°C. Finally, through continuous feedback adjustment and verification, the research team confirmed that the combination of a thermal conductivity of 0.50 W / (m·K) and a heat capacity parameter of 2.13 J / (kg·K) could stably adapt to different operating conditions, so the final optimized thermodynamic parameters were generated and prepared for subsequent load mass calculation.

[0092] S204. According to the optimized thermodynamic parameters, use the load mass calculation algorithm based on the law of conservation of energy, combine the oven heating power and thermodynamic parameters to calculate the mass of the load. Among them, the estimated value of the load mass is dynamically adjusted through the temperature change rate correction factor, and the final load mass calculation result is obtained through comparison and verification with the preset load mass range.

[0093] The core of this step is to accurately calculate the mass of the load according to the optimized thermodynamic parameters, using the load mass calculation algorithm based on the law of conservation of energy, and combining the heating power and thermodynamic parameters of the oven. By correcting the temperature change rate during the oven heating process, the system can dynamically adjust the estimated value of the load mass to more accurately reflect the actual load situation. Finally, compare and verify with the preset load mass range to ensure the rationality and accuracy of the calculation result, and finally obtain a reliable load mass calculation result.

[0094] The implementation of this step not only improves the accuracy of load mass calculation, but also ensures consistency under different baking conditions through the dynamic correction factor. By comparing with the preset range, the system can timely identify potential deviations and ensure the operation stability of the oven under different conditions. This process plays an important role in improving the scientific and intelligent level of oven cooking, and helps to improve the user experience and the cooking quality of food.

[0095] Specifically, for the optimized thermodynamic parameters, use the load mass calculation algorithm based on the law of conservation of energy, combine the oven heating power and thermodynamic parameters to preliminarily calculate the mass of the load, dynamically adjust the estimated value of the load mass through the temperature change rate correction factor, and generate a preliminary load mass calculation result; In this step, the system first calculates the mass of the load using the optimized thermodynamic parameters in combination with the real-time oven heating power, based on the law of conservation of energy. The basic formula generally shows that the input heat is equal to the output heat plus the heat absorbed by the load. By first calculating the preliminary mass of the load and then dynamically adjusting it using the temperature change rate correction factor, a more accurate mass estimation can be achieved. This calculation process ensures the scientificity and rationality of the preliminary estimation of the load mass. Through the precise correlation between the input heat and the load mass, the actual situation during the operation of the oven can be promptly reflected, laying a foundation for subsequent refined operations. The accuracy of this process directly affects the accuracy of all subsequent calculations, and thus affects the cooking effect of the food and the optimization of energy consumption.

[0096] In this step, the research team first needs to obtain the optimized thermodynamic parameters, such as the heat transfer coefficient and heat capacity parameters, and combine them with the heating power of the oven to perform a preliminary calculation of the load mass. Assuming the heating power of the oven is 1500 watts, by using this power in combination with the time and temperature difference, the team can deduce the mass of the load using the law of conservation of energy. For example, if the oven heats up from the ambient temperature of 25°C to 175°C during the heating process, using the heat formula Q = m*c*ΔT, where Q is the heat, m is the mass, c is the specific heat capacity, and ΔT is the temperature change, the mass of the load can be preliminarily calculated as 8.0 kg.

[0097] To further improve the accuracy of the load mass calculation, the system introduces a temperature change rate correction factor. The value of this factor is dynamically adjusted according to the ratio of the actual temperature change rate to the theoretical change rate. Suppose it is found in the experiment that the actual temperature rise speed is faster than expected, which indicates that the load may be lighter than the preliminary estimate. Therefore, the research team will adjust the estimated value of the load mass in a timely manner based on the analysis of the temperature change rate, adjusting the initially calculated 8.0 kg to 7.5 kg. In this way, the team will generate a relatively more accurate preliminary load mass calculation result.

[0098] Finally, after the above steps, the obtained preliminary estimation result will become the basis for subsequent verification and optimization. Suppose after these calculations, the preliminary load mass calculation result finally output by the system is 7.5 kg. This result will be compared and verified with the preset load mass range in the next step to ensure its rationality and accuracy.

[0099] For example, regularly record the temperature change inside the oven. Suppose within the first 5 minutes of heating, the temperature of the oven rises from 25°C to 100°C, with a change of 75°C. The temperature change rate can be calculated as: actual temperature change rate = Delta T / Delta t = {100°C - 25°C} / {5*60s} = {75°C} / {300s} = 0.25°C / s.

[0100] Based on the initial load mass (8.0 kg) and the heat transfer model, predict the temperature change of the oven. If the theoretically expected temperature change rate is 0.2 °C / s. The theoretical temperature change rate can be calculated according to the heat conduction formula and the set heating power, assuming it is 0.2 °C / s. The temperature change rate correction factor can be defined as the ratio of the actual temperature change rate to the theoretical temperature change rate: k = actual temperature change rate / theoretical temperature change rate = 0.25 / 0.2 = 1.25. According to the analysis of the temperature change rate, adjust the estimated value of the load mass: It is found that the actual temperature rise rate (0.25 °C / s) is higher than the theoretical rate (0.2 °C / s), which means that the efficiency of heat transfer to the load is higher, probably because the actual mass of the load is lighter than the initially calculated 8.0 kg. Use the correction factor to dynamically adjust the estimated mass of the load. A linear or non-linear formula can be set to update the estimated load mass, for example: m_adjusted = m_initial / k = 8.0 / 1.25 = 6.4 kg.

[0101] For the initial load mass calculation result, adopt a comparison and verification method based on the preset load mass range, combine the thermodynamic characteristics of the oven and the real-time temperature data to verify the rationality and accuracy of the load mass, and ensure the accuracy and stability of the verification process through dynamic threshold adjustment technology to generate the initial verification result; In this step, the system compares the initially calculated load mass with the preset load mass range to check the rationality and accuracy of the calculation result. By combining the thermodynamic characteristics of the oven and the real-time temperature data, the system can more comprehensively evaluate the current load state and optimize the verification process through dynamic threshold adjustment technology to ensure the stability and accuracy of the judgment. This step provides an important verification mechanism to ensure that the calculated load mass is within an acceptable range. In this way, the system can promptly detect any abnormal situations and make necessary adjustments. This proactive monitoring is essential for improving the safety and operational reliability of the oven and further enhancing the stability of the cooking effect.

[0102] In this step, the research team uses the preset load mass range (for example, between 6 kg and 9 kg) to verify the initially calculated load mass result. By comparing the previously calculated initial result of 6.4 kg with the preset range, the team can initially judge whether the mass is reasonable. Through comparison, it can be found that 6.4 kg is within the preset range, so the initial result is in a reasonable range.

[0103] To ensure the accuracy of the verification process, the team adopted a dynamic threshold adjustment technique. In actual operation, if temperature changes, external environment, or other influencing factors cause the calculated load mass result to approach the boundary of the preset range, the system will automatically adjust the verification threshold. For example, if in subsequent multiple measurements, it is found that the temperature read by the temperature sensor is higher than expected, it may mean that the true value of the load mass may be lower than 6.4 kg. At this time, the system will dynamically lower the upper verification threshold to ensure the adaptability and accuracy of the verification process.

[0104] Finally, based on these analyses, the team will generate preliminary verification results. In this example, after verification, there is no significant deviation between the initially calculated 6.4 kg and the preset range, so it is confirmed that this calculated result is acceptable. This result will provide a reliable basis for subsequent optimization and adjustment.

[0105] For the preliminary verification results, an optimization method based on feedback correction technology is adopted. Combining the thermodynamic characteristics of the oven and real-time temperature data, the estimated value of the load mass is dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary optimized load mass calculation result is generated;

[0106] At this stage, the system will conduct a detailed analysis of the verification results generated in the previous stage and apply feedback correction technology to optimize the estimated value of the load mass. By deeply combining the thermodynamic characteristics of the oven with real-time temperature data, the system can identify and adjust the estimation of the load mass to ensure its continuous accuracy throughout the baking process. The multiple-round iterative process will continuously refine the estimation until the expected accurate value is achieved. This optimization process significantly improves the flexibility and accuracy of the load mass calculation. Through real-time feedback, the system can make timely adjustments according to the actual working performance of the oven to ensure that the calculation always conforms to the actual situation. This not only improves the baking performance but also effectively saves energy consumption and enhances the working efficiency of the oven.

[0107] In this step, the research team, based on the preliminary verification results, combines the thermodynamic characteristics and real-time temperature data, and adopts feedback correction technology to further optimize the calculation of the load mass. After the result obtained from the preliminary verification is 6.4 kg, the team identifies that under different heating conditions, the actual value of the load mass may change, so dynamic adjustment and optimization are required.

[0108] To this end, the team will use the temperature data obtained in real time from the system for multiple rounds of iterative feedback correction. For example, by monitoring the rate of temperature change, the team finds that the rate of temperature rise is different from the previous assumption. This means that it may be necessary to re-evaluate the heat conduction coefficient and heat capacity value to further optimize the calculation result of the load mass.

[0109] After several rounds of iteration, assuming that after each feedback adjustment, the estimated value of the load mass gradually stabilizes at 7 kg. This result, through continuous verification and feedback correction, confirms that the new calculated load mass is more in line with the actual thermodynamic conditions and the actually measured temperature data. The finally obtained preliminary optimized calculated load mass result is 7 kg, which will provide a more accurate load mass prediction for the research team.

[0110] For the preliminary optimized calculated load mass result, an output method based on visualization technology is adopted to integrate the calculated load mass result and the verification result into the final load mass calculation result report.

[0111] In the final stage, the system combines the obtained preliminary optimized calculated load mass result with the verification information and uses visualization technology to generate the final load mass calculation result report. Such a report not only contains the calculation result, but also through charts and data display, enabling users to intuitively understand the change situation of the load mass and the data support behind it. This output result is very important for users. It provides a comprehensive and intuitive analysis of the load mass, helping users gain insights into the performance of the oven and the cooking quality. This visual output not only improves the user experience, but also provides valuable information for subsequent decision-making, helping users make more scientific choices in actual use.

[0112] In the last step, the research team visualizes the optimized calculated load mass result for better data presentation and interpretation. The team uses visualization tools to generate charts and reports, clearly showing the preliminary calculation result, the verification process, the dynamic adjustment situation, and the final optimized load mass result. In this process, the chart not only includes the calculated load mass (7 kg), but also the relevant temperature change curves, thermodynamic parameters, and trends of real-time data.

[0113] For example, the team can use a bar chart to show the comparison between the preliminary calculation result and the final optimized result, and at the same time add a comparison of the preset load mass range in the report to emphasize the rationality and accuracy during the verification process. In addition, the report will also incorporate the results of real-time data analysis to illustrate how environmental factors affect temperature changes and thus the estimation of the load mass throughout the experiment.

[0114] Finally, the integrated report will provide detailed load mass calculation results and relevant background information for subsequent research reports, technical documents, and customers, helping decision-makers understand and apply this calculation method. For example, the team may submit the finally generated visual report to the relevant engineering department as a reference for equipment performance optimization and quality control. This will help the team continuously improve the load mass calculation method in future experiments.

[0115] It can be seen that during the operation of the oven heating tube, the temperature data inside the oven cavity is periodically collected to obtain a denoised temperature-time series. According to the temperature-time series, the relationship between temperature and time is segmented and fitted to obtain a segmented heating fitting function. Based on the initial temperature, the difference between the ambient temperature, and the heating slope in the segmented heating fitting function, combined with the thermodynamic characteristics of the oven, the heat conduction coefficient and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters. According to the thermodynamic parameters, the mass of the load is calculated to obtain the final calculation result of the load mass, thereby improving the calculation accuracy of the load mass and providing a more intelligent cooking experience for users.

[0116] Another embodiment of the present invention provides a calculation system for the mass of an oven load. Refer to Figure 3 , the system may include: An acquisition module 301, configured to periodically collect the temperature data inside the oven cavity during the operation of the oven heating tube. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time and obtain a denoised temperature-time series. A fitting module 302, configured to segment and fit the relationship between temperature and time according to the denoised temperature-time series by using a fitting algorithm based on segmented polynomial regression. Through an adaptive segmented point selection technique, the fitting interval is dynamically adjusted to ensure the fitting accuracy and obtain a segmented heating fitting function. An optimization module 303, configured to optimize the heat conduction coefficient and heat capacity parameters in real time according to the initial temperature, the difference between the ambient temperature, and the heating slope in the segmented heating fitting function, combined with the thermodynamic characteristics of the oven, by using a parameter estimation algorithm based on nonlinear least squares and through a heat capacity dynamic adjustment technique to obtain optimized thermodynamic parameters. A calculation module 304, configured to calculate the mass of the load according to the optimized thermodynamic parameters by using a load mass calculation algorithm based on the law of conservation of energy, combined with the oven heating power and thermodynamic parameters. Among them, the estimated value of the load mass is dynamically adjusted through a temperature change rate correction factor, and the final calculation result of the load mass is obtained through comparison and verification with a preset load mass range.

[0117] It can be seen that during the operation of the oven heating tube, the temperature data inside the oven cavity is periodically collected to obtain a denoised temperature time series; according to the temperature time series, the relationship between temperature and time is piecewise fitted to obtain a piecewise heating fitting function; according to the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, the thermal conductivity and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; according to the thermodynamic parameters, the mass of the load is calculated to obtain the final calculation result of the load mass, thereby improving the calculation accuracy of the load mass and providing a more intelligent cooking experience for users.

[0118] An embodiment of the present invention also provides a storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in any one of the above method embodiments when running.

[0119] Specifically, in this embodiment, the above storage medium can be configured to store a computer program for executing the following steps: S201, during the operation of the oven heating tube, the temperature data inside the oven cavity is periodically collected. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time to obtain a denoised temperature time series; S202, according to the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is used to piecewise fit the relationship between temperature and time. Through an adaptive piecewise point selection technique, the fitting interval is dynamically adjusted to ensure the fitting accuracy, and a piecewise heating fitting function is obtained; S203, according to the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, a parameter estimation algorithm based on the nonlinear least squares method is used. Through a heat capacity dynamic adjustment technique, the thermal conductivity and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; S204, according to the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is used. Combined with the oven heating power and thermodynamic parameters, the mass of the load is calculated. Among them, the estimated value of the load mass is dynamically adjusted through a temperature change rate correction factor, and the final calculation result of the load mass is obtained through comparison and verification with a preset load mass range.

[0120] It can be seen that during the operation of the oven heating tube, temperature data inside the oven cavity is periodically collected to obtain a denoised temperature time series. According to the temperature time series, the relationship between temperature and time is piecewise fitted to obtain a piecewise heating fitting function. Based on the initial temperature, ambient temperature difference, and heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, the heat conduction coefficient and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters. According to the thermodynamic parameters, the mass of the load is calculated to obtain the final calculation result of the load mass, thereby improving the calculation accuracy of the load mass and providing a more intelligent cooking experience for users.

[0121] An embodiment of the present invention also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0122] Specifically, the above electronic device may further include a transmission device and an input / output device. Among them, the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0123] Specifically, in this embodiment, the above processor may be configured to execute the following steps through a computer program: S201, During the operation of the oven heating tube, temperature data inside the oven cavity is periodically collected. Among them, a distributed temperature sensor network is used, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove noise interference in the temperature data in real time, and a denoised temperature time series is obtained; S202, According to the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is used to piecewise fit the relationship between temperature and time. Through an adaptive piecewise point selection technique, the fitting interval is dynamically adjusted to ensure the fitting accuracy, and a piecewise heating fitting function is obtained; S203, According to the initial temperature, ambient temperature difference, and heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, a parameter estimation algorithm based on nonlinear least squares is used. Through a heat capacity dynamic adjustment technique, the heat conduction coefficient and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; S204, According to the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is used. Combining the oven heating power and thermodynamic parameters, the mass of the load is calculated. Among them, the estimated value of the load mass is dynamically adjusted through a temperature change rate correction factor, and the final calculation result of the load mass is obtained through comparison and verification with a preset load mass range.

[0124] It can be seen that according to the periodic collection of temperature data inside the oven cavity during the operation of the oven heating tube, a denoised temperature time series is obtained; according to the temperature time series, the variation relationship between temperature and time is segmented and fitted to obtain a segmented heating fitting function; according to the initial temperature, the ambient temperature difference, and the heating slope in the segmented heating fitting function, combined with the thermodynamic characteristics of the oven, the heat conduction coefficient and heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; according to the thermodynamic parameters, the mass of the load is calculated to obtain the final calculation result of the load mass, thereby improving the calculation accuracy of the load mass and providing a more intelligent cooking experience for users.

[0125] The above has detailed the structure, features, and effects of the present invention based on the illustrated embodiments. The above is only the preferred embodiment of the present invention, but the present invention is not limited to the scope defined by the drawings. Any changes made according to the concept of the present invention, or modified into equivalent embodiments with equivalent changes, should still be within the protection scope of the present invention as long as they do not exceed the spirit covered by the description and the drawings.

Claims

1. A method for calculating the load mass of an oven, characterized in that, The method includes: During the operation of the oven heating tube, periodically collect the temperature data inside the oven cavity. Among them, a distributed temperature sensor network is adopted, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time, and obtain a denoised temperature time series; According to the denoised temperature time series, adopt a fitting algorithm based on piecewise polynomial regression to perform piecewise fitting on the relationship between temperature and time. Through the adaptive piecewise point selection technology, dynamically adjust the fitting interval to ensure the fitting accuracy, and obtain a piecewise heating fitting function; According to the initial temperature, ambient temperature difference, and heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, adopt a parameter estimation algorithm based on the nonlinear least squares method, and through the heat capacity dynamic adjustment technology, optimize the heat conduction coefficient and heat capacity parameters in real time to obtain optimized thermodynamic parameters; According to the optimized thermodynamic parameters, adopt a load mass calculation algorithm based on the law of conservation of energy, combined with the oven heating power and thermodynamic parameters, to calculate the mass of the load. Among them, through the temperature change rate correction factor, dynamically adjust the estimated value of the load mass, and verify it by comparing with the preset load mass range to obtain the final load mass calculation result.

2. The method according to claim 1, wherein During the operation of the oven heating tube, periodically collect the temperature data inside the oven cavity. Among them, a distributed temperature sensor network is adopted, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove the noise interference in the temperature data in real time, and obtain a denoised temperature time series, including: According to the temperature distribution inside the oven cavity, adopt a data acquisition framework based on a distributed temperature sensor network, and obtain temperature data in real time through multiple sensor nodes. Each sensor node is equipped with a lightweight data caching technology to ensure the real-time and continuous nature of data acquisition; For the collected temperature data, adopt a format recognition model based on deep learning to automatically identify the format types of different data sources. Through an adaptive data cleaning algorithm, filter the noise and fill in the missing values in the data to generate a preliminary standardized data set; For the preliminary standardized data set, adopt a dynamic noise cancellation algorithm based on Kalman filtering, combined with the time series characteristics of the temperature data, to remove the noise interference in real time. Through the dynamic threshold adjustment technology, ensure the accuracy and stability of the denoising process, and generate a preliminary denoised data set; For the preliminary denoised data set, adopt a data integration method based on time series analysis to map the temperature data of different sensor nodes into a unified time series, and supplement the missing data through the interpolation filling method to generate the final denoised temperature time series.

3. The method according to claim 2, wherein According to the denoised temperature time series, adopt a fitting algorithm based on piecewise polynomial regression to perform piecewise fitting on the relationship between temperature and time. Through the adaptive piecewise point selection technology, dynamically adjust the fitting interval to ensure the fitting accuracy, and obtain a piecewise heating fitting function, including: For the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is adopted. Combining the local characteristics of temperature changes, the segmentation points are initially selected. Through dynamic threshold adjustment technology, the rationality and accuracy of the segmentation points are ensured, and a preliminary set of segmentation points is generated; For the preliminary set of segmentation points, a fitting method based on piecewise polynomial regression is adopted. Combining the local characteristics of the temperature time series, piecewise fitting is performed. Through error calculation technology, the fitting error of each segment is calculated, and a preliminary fitting function is generated; For the preliminary fitting function, an adjustment method based on adaptive segmentation point selection technology is adopted. Combining the fitting error and the temperature change trend, the segmentation points are dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary set of optimized segmentation points is generated; For the preliminary set of optimized segmentation points, a fitting method based on piecewise polynomial regression is adopted. Combining the global characteristics of the temperature time series, the final piecewise heating fitting function is generated.

4. The method according to claim 3, characterized in that According to the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, combined with the thermodynamic characteristics of the oven, a parameter estimation algorithm based on the nonlinear least squares method is adopted. Through the heat capacity dynamic adjustment technology, the thermal conductivity and heat capacity parameters are optimized in real time, and the optimized thermodynamic parameters are obtained, including: For the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, a parameter estimation algorithm based on the nonlinear least squares method is adopted. Combining the thermodynamic characteristics of the oven, the thermal conductivity and heat capacity parameters are initialized. Through the dynamic weight allocation technology, the rationality and accuracy of the parameter initialization are ensured, and a preliminary set of thermodynamic parameters is generated; For the preliminary set of thermodynamic parameters, a parameter estimation algorithm based on the nonlinear least squares method is adopted. Combining the piecewise heating fitting function and the thermodynamic characteristics of the oven, parameter estimation is performed. Through error calculation technology, the error of the parameter estimation is calculated, and a preliminary parameter estimation result is generated; For the preliminary parameter estimation result, an optimization method based on the heat capacity dynamic adjustment technology is adopted. Combining the thermodynamic characteristics of the oven and the real-time temperature data, the thermal conductivity and heat capacity parameters are dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary set of optimized thermodynamic parameters is generated; For the preliminary set of optimized thermodynamic parameters, a verification method based on simulation is adopted. Combining the thermodynamic characteristics of the oven and the real-time temperature data, the accuracy and stability of the parameters are verified. Through the feedback correction technology, the parameters are dynamically adjusted, and the final optimized thermodynamic parameters are generated.

5. The method according to claim 4, wherein According to the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is adopted. Combining the oven heating power and the thermodynamic parameters, the mass of the load is calculated. Among them, through the temperature change rate correction factor, the estimated value of the load mass is dynamically adjusted, and through comparison and verification with the preset load mass range, the final load mass calculation result is obtained, including: For the optimized thermodynamic parameters, a load mass calculation algorithm based on the law of conservation of energy is adopted. Combining the oven heating power and the thermodynamic parameters, the mass of the load is initially calculated. Through the temperature change rate correction factor, the estimated value of the load mass is dynamically adjusted, and a preliminary load mass calculation result is generated; For the preliminary load mass calculation results, a comparison and verification method based on a preset load mass range is adopted. Combining the thermodynamic characteristics of the oven and the real-time temperature data, the rationality and accuracy of the load mass are verified. Through dynamic threshold adjustment technology, the accuracy and stability of the verification process are ensured, and preliminary verification results are generated; For the preliminary verification results, an optimization method based on feedback correction technology is adopted. Combining the thermodynamic characteristics of the oven and the real-time temperature data, the estimated value of the load mass is dynamically adjusted. Through multiple rounds of iterative optimization, preliminary optimized load mass calculation results are generated; For the preliminary optimized load mass calculation results, an output method based on visualization technology is adopted to integrate the load mass calculation results and the verification results into the final load mass calculation result report.

6. A calculation system for the mass of an oven load, characterized in that, The system includes: An acquisition module for periodically acquiring temperature data inside the oven chamber during the operation of the oven heating tube. Among them, a distributed temperature sensor network is adopted, combined with a dynamic noise cancellation algorithm based on Kalman filtering, to remove noise interference in the temperature data in real time and obtain a denoised temperature time series; A fitting module for segmentally fitting the relationship between temperature and time according to the denoised temperature time series by using a fitting algorithm based on piecewise polynomial regression. Through an adaptive segment point selection technique, the fitting interval is dynamically adjusted to ensure the fitting accuracy and obtain a piecewise heating fitting function; An optimization module for combining the initial temperature, the ambient temperature difference, and the heating slope in the piecewise heating fitting function, and combining the thermodynamic characteristics of the oven, adopting a parameter estimation algorithm based on nonlinear least squares method. Through a heat capacity dynamic adjustment technology, the heat conduction coefficient and the heat capacity parameters are optimized in real time to obtain optimized thermodynamic parameters; A calculation module for calculating the mass of the load according to the optimized thermodynamic parameters by using a load mass calculation algorithm based on the law of conservation of energy, combining the oven heating power and the thermodynamic parameters. Among them, the estimated value of the load mass is dynamically adjusted through a temperature change rate correction factor, and the final load mass calculation result is obtained through comparison and verification with the preset load mass range.

7. The system according to claim 6, wherein The acquisition module specifically is used for: According to the temperature distribution inside the oven chamber, adopting a data acquisition framework based on a distributed temperature sensor network, and obtaining temperature data in real time through multiple sensor nodes. Each sensor node is equipped with a lightweight data caching technology to ensure the real-time and continuous data acquisition; For the acquired temperature data, adopting a format recognition model based on deep learning to automatically identify the format types of different data sources. Through an adaptive data cleaning algorithm, the data is filtered for noise and filled with missing values to generate a preliminary standardized data set; For the preliminary standardized data set, adopting a dynamic noise cancellation algorithm based on Kalman filtering, combining the temporal characteristics of the temperature data, removing noise interference in real time, and ensuring the accuracy and stability of the denoising process through dynamic threshold adjustment technology to generate a preliminary denoised data set; For the preliminary denoised dataset, a data integration method based on time series analysis is adopted to map the temperature data of different sensor nodes into a unified time series. Through the interpolation filling method, the missing data is supplemented to generate the final denoised temperature time series.

8. The system according to claim 7, wherein The fitting module is specifically used for: For the denoised temperature time series, a fitting algorithm based on piecewise polynomial regression is adopted. Combining the local characteristics of temperature changes, the segmentation points are initially selected. Through the dynamic threshold adjustment technology, the rationality and accuracy of the segmentation points are ensured to generate a preliminary set of segmentation points; For the preliminary set of segmentation points, a fitting method based on piecewise polynomial regression is adopted. Combining the local characteristics of the temperature time series, piecewise fitting is performed. Through the error calculation technology, the fitting error of each segment is calculated to generate a preliminary fitting function; For the preliminary fitting function, an adjustment method based on the adaptive segmentation point selection technology is adopted. Combining the fitting error and the temperature change trend, the segmentation points are dynamically adjusted. Through multiple rounds of iterative optimization, a preliminary set of optimized segmentation points is generated; For the preliminary set of optimized segmentation points, a fitting method based on piecewise polynomial regression is adopted. Combining the global characteristics of the temperature time series, the final piecewise heating fitting function is generated.

9. A storage medium, characterized in that, The computer program is stored in the storage medium, wherein the computer program is set to execute the method according to any one of claims 1-5 when running.

10. An electronic device, comprising a memory and a processor, characterized in that, The computer program is stored in the memory, and the processor is set to run the computer program to execute the method according to any one of claims 1-5.

Images