Constant temperature system for boiling pepper soup

Abstract

The invention relates to the technical field of constant-temperature boiling, and discloses a peppery soup boiling constant-temperature system which comprises the following steps: S1, collecting temperature, pressure, humidity and material concentration data of soup in a boiling pot; s2, performing fusion processing on the acquired data to generate comprehensive monitoring data; s3, a fuzzy control algorithm and a neural network control algorithm are alternately adopted, adjusting instructions of the heating power and the stirring speed are generated according to the comprehensive monitoring data, the fuzzy control algorithm is adopted in the initial boiling stage to stabilize the temperature, and the neural network control algorithm is adopted in the stable boiling stage to optimize the constant-temperature precision; and S4, controlling the heating system and the stirrer to work according to the adjusting instruction. According to the invention, the fuzzy control algorithm is adopted to quickly stabilize the temperature in the initial boiling stage, and the neural network control algorithm is switched to optimize the constant temperature precision in the stable stage, so that the staged accurate temperature control is realized, the temperature stability in the peppery soup boiling process is ensured, and the quality consistency of finished products is improved.

Description

Technical Field

[0001] The invention relates to the technical field of boiling constant temperature, in particular to a constant temperature system for boiling spicy soup. Background Art

[0002] Hu La Tang, a traditional soup snack common in northern China for breakfast, has a profound historical and cultural heritage. In the production process, Hu La Tang needs to go through stages such as boiling over high heat, simmering over low heat, and aging. Temperature control is crucial. Maintaining a constant temperature of 85 degrees Celsius for boiling can not only avoid high temperature destroying the nutrients of the ingredients, but also ensure that the effective ingredients are fully dissolved, thereby increasing the content of free amino acids in the soup.

[0003] In traditional cooking systems, local overheating or slow heating may occur due to the rapid introduction of heat in the initial stage, and the temperature in the stable stage may deviate from the target value, resulting in uneven heating of the ingredients, destruction of nutrients or deterioration of flavor. Summary of the Invention

[0004] In order to make up for the above shortcomings, the present invention provides a constant temperature system for making spicy soup, which aims to improve the problems of uneven heating of ingredients, destruction of nutrients or deterioration of flavor due to local overheating or slow heating due to rapid heat introduction in the initial stage and temperature deviation from the target value in the stable stage.

[0005] In a first aspect, the present invention provides the following technical solution: a method for preparing Hu La Tang at a constant temperature, comprising the following steps:

[0006] S1. Collect the temperature, pressure, humidity and material concentration data of the soup in the pot;

[0007] S2. Fusing the collected data to generate comprehensive monitoring data;

[0008] S3. Alternately using fuzzy control algorithms and neural network control algorithms to generate adjustment instructions for heating power and stirring speed based on comprehensive monitoring data. The fuzzy control algorithm is used to stabilize the temperature in the initial stage of boiling, and the neural network control algorithm is used to optimize the constant temperature accuracy in the stable boiling stage.

[0009] S4, controlling the heating system and the agitator according to the adjustment instructions;

[0010] S5. Upload the collected data to the cloud platform for analysis to generate equipment operation status prediction data and parameter combination data;

[0011] S6. Recover waste heat from the cooking process and use it to preheat new materials. At the same time, monitor the energy consumption of the heating system and perform intelligent scheduling.

[0012] Preferably, in S2, the Kalman filter algorithm is used to fuse the collected data. The core formula of the Kalman filter algorithm is as follows:

[0013] Prediction steps:

[0014] Update steps:

[0015]

[0016] P k∣k =(IK k H k )P k|k-1

[0017] in, is the state prediction value at the previous moment, is the optimal estimated value of the state at the previous moment, F k is the state transfer matrix, B k Control matrix, u k is the control vector, P k∣k-1 is the prediction covariance, P k-1∣k-1 is the covariance at the previous moment, Q k is the process noise covariance matrix, K k is the Kalman gain, H k is the observation matrix, z k is the observed value, R k is the measurement noise covariance matrix, is the optimal estimated value of the current state, P k∣k is the covariance at the current moment.

[0018] Preferably, in S3, the fuzzy control algorithm adopts the following rules for control:

[0019] The domain of temperature deviation E is {-5,-4,-3,-2,-1,0,1,2,3,4,5}, and the domain of deviation change rate EC is {-3,-2,-1,0,1,2,3};

[0020] The domain of heating power adjustment value U1 is {-3,-2,-1,0,1,2,3}, and the domain of stirring speed adjustment value U2 is {-2,-1,0,1,2};

[0021] The centroid method is used for defuzzification, and the calculation formula is: where u i is an element in the fuzzy set, μ(u i ) is the membership degree of the corresponding element.

[0022] Preferably, in S3, the neural network control algorithm adopts a three-layer feedforward neural network, the number of input layer nodes is 4, the number of hidden layer nodes is 8-16, and the hidden layer adopts Sigmoid activation function, the formula is The number of nodes in the output layer is 2, and the output layer uses a linear activation function f(x) = x. The network is trained by back propagation algorithm and stochastic gradient descent method. The learning rate is set to 0.01-0.1, the batch size is 32-128, and the maximum number of iterations is 1000-2000. When the loss function converges to less than 0.01, the training is stopped. The loss function uses the mean square error function. Where n is the number of samples, y i is the true value, is the predicted value.

[0023] Preferably, in S5, a K-means algorithm is used to perform cluster analysis on the data, and the objective function is:

[0024]

[0025] Where k is the number of clusters, C i is the i-th cluster, μ i is the centroid of the i-th cluster;

[0026] The decision tree algorithm is used to select the split attribute by calculating the information gain. The calculation formula is:

[0027]

[0028] Where S is the sample set, A is the attribute, Values(A) is the value set of attribute A, S v is the sample subset when the attribute A takes the value v, H(S) is the information entropy of the sample set S v ) is the sample subset S v Information entropy.

[0029] Preferably, in S1, data is collected using temperature sensors, pressure sensors, humidity sensors and material concentration sensors. Each sensor is installed in a distributed manner. The temperature sensor is arranged at the center of the bottom of the pot, the middle of the side wall and the center of the soup. The pressure sensor is installed on the top of the pot, the humidity sensor is installed at the steam outlet, and the material concentration sensor is installed near the stirring paddle.

[0030] Preferably, in S6, waste heat is recovered by a waste heat recovery device and used to preheat new materials, and the energy consumption of the heating system is monitored and scheduled by an intelligent energy management system. The waste heat recovery device adopts a spiral tube heat exchanger, and the intelligent energy management system preheats at 80%-90% of the rated power during the off-peak period according to the peak and off-peak electricity price period of the power grid, and dynamically adjusts the working combination of the heating elements during the peak period.

[0031] In a second aspect, the present invention provides the following technical solution: a constant temperature system for boiling spicy soup, the system comprising:

[0032] The sensor acquisition module is used to collect data on the temperature, pressure, humidity and material concentration of the soup in the boiling pot;

[0033] The data fusion module is connected to the sensor acquisition module and is used to fuse the collected data to generate comprehensive monitoring data;

[0034] The artificial intelligence control module is connected to the data fusion module and is used to automatically switch between the fuzzy control algorithm and the neural network control algorithm according to the initial stage or the stable stage of boiling, and to generate adjustment instructions for heating power and stirring speed based on the comprehensive monitoring data;

[0035] The heating system control module is connected to the artificial intelligence control module and is used to control the operation of the heating system according to the heating power adjustment instruction;

[0036] The agitator control module is connected to the artificial intelligence control module and is used to control the operation of the agitator according to the stirring speed adjustment instruction;

[0037] The IoT transmission module is connected to the sensor acquisition module and is used to upload the collected data to the cloud platform;

[0038] The cloud platform module is connected to the IoT transmission module to analyze the data and generate equipment operation status prediction data and parameter combination data;

[0039] Waste heat recovery module, used to recover waste heat from the cooking process and use it to preheat new materials;

[0040] The intelligent energy management module is connected to the heating system control module and is used to monitor the energy consumption of the heating system and perform intelligent scheduling.

[0041] In a third aspect, the invention provides the following technical solution: a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned constant temperature method for cooking spicy soup when executing the computer program.

[0042] In a fourth aspect, the present invention provides the following technical solution: a readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements the above-mentioned method for cooking Hu La Tang at a constant temperature.

[0043] The present invention has the following beneficial effects:

[0044] 1. In the present invention, by using a fuzzy control algorithm to quickly stabilize the temperature in the initial stage of boiling, and switching to a neural network control algorithm to optimize the constant temperature accuracy in the stable stage, the problems of violent initial temperature fluctuations and insufficient accuracy in the stable stage in traditional boiling are solved, and precise temperature control in stages is achieved, ensuring the temperature stability during the boiling process of spicy soup and improving the quality consistency of the finished product.

[0045] 2. In the present invention, the Kalman filter algorithm is used to fuse the temperature, pressure and other multi-sensor data, and the noise interference is filtered out through the prediction and update steps, so that the data error is controlled within a reasonable range, providing high-precision input for the subsequent control algorithm, making the heating power and stirring speed adjustment instructions more in line with the actual brewing needs, and ensuring stable and reliable system operation.

[0046] 3. In the present invention, by using the K-means algorithm to cluster and analyze the characteristics of the brewing data, combined with the decision tree algorithm to mine the correlation between the equipment status and the data, the intelligent identification of the brewing stage and the early prediction of equipment failure are realized, the optimal parameter combination is generated to feed back the control module, the brewing process is optimized, and the intelligence and automation level of the system are improved.

[0047] 4. In the present invention, data is distributed and accurately collected through the sensor acquisition module, and after denoising processing by the data fusion module, the artificial intelligence control module coordinates the heating system, agitator and other modules to solve the problems of data distortion, energy waste and regulation lag in traditional technologies, achieve multiple effects of precise temperature control, waste heat recovery and energy saving and consumption reduction, and promote the intelligent upgrade of the brewing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a flow chart of the method for boiling Hu La Tang at a constant temperature proposed by the present invention;

[0049] Figure 2 This is a system architecture diagram of an image recognition system proposed in the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0051] Example 1

[0052] Reference Figure 1 In a first embodiment of the present invention, the present invention provides a method for boiling spicy soup at a constant temperature, comprising the following steps:

[0053] S1. Collect the temperature, pressure, humidity and material concentration data of the soup in the pot;

[0054] S2. Fusing the collected data to generate comprehensive monitoring data;

[0055] S3. Alternately using fuzzy control algorithms and neural network control algorithms to generate adjustment instructions for heating power and stirring speed based on comprehensive monitoring data. The fuzzy control algorithm is used to stabilize the temperature in the initial stage of boiling, and the neural network control algorithm is used to optimize the constant temperature accuracy in the stable boiling stage.

[0056] S4, controlling the heating system and the agitator according to the adjustment instructions;

[0057] S5. Upload the collected data to the cloud platform for analysis to generate equipment operation status prediction data and parameter combination data;

[0058] S6. Recover waste heat from the cooking process and use it to preheat new materials. At the same time, monitor the energy consumption of the heating system and perform intelligent scheduling.

[0059] Specifically, in step S1, the temperature, pressure, temperature and material concentration data of the soup in the boiling pot are collected, which is the basis for subsequent data processing and control adjustment. By obtaining these basic data, a basis is provided for the subsequent precise control of the Hu La Tang boiling process;

[0060] In step S2, the collected data is fused and processed to generate comprehensive monitoring data. This can integrate the original data of multiple dimensions to obtain more representative and effective data that can reflect the brewing status, facilitating subsequent accurate analysis and application.

[0061] In step S3, fuzzy control algorithms and neural network control algorithms are used alternately to generate adjustment instructions for heating power and stirring speed based on comprehensive monitoring data. The fuzzy control algorithm is used to stabilize the temperature in the initial stage of boiling, quickly responding to large temperature fluctuations in the initial stage and allowing the temperature to quickly stabilize. In the stable boiling stage, the neural network control algorithm is used to optimize the constant temperature accuracy. By leveraging learning optimization capabilities, the temperature control is made more precise, ensuring the constant temperature effect of the Hu La Tang.

[0062] In step S4, the heating system and the stirrer are controlled according to the adjustment instructions, and the control instructions generated in S3 are converted into actual actions, which are directly applied to the boiling equipment to achieve precise control of heating and stirring, ensuring that the boiling process is carried out according to the preset temperature and stirring state. This is the existing technology and will not be described in detail.

[0063] In step S5, the collected data is uploaded to the cloud platform for analysis to generate equipment operating status prediction data and parameter combination data. With the data analysis capabilities of the cloud platform, the equipment operating status can be predicted in advance and a more optimal brewing parameter combination can be obtained, providing support for subsequent brewing process optimization.

[0064] In step S6, waste heat from the cooking process is recovered and used to preheat new materials, achieving energy recycling and reuse, reducing energy consumption. At the same time, the energy consumption of the heating system is monitored and intelligent scheduling is performed, which can reasonably allocate energy, improve energy utilization efficiency, and save costs.

[0065] Through the above steps, the problems of unstable temperature in the initial stage and insufficient constant temperature accuracy in the stable stage during the cooking process of Hu La Tang are solved, and the effects of accurately controlling the cooking temperature of Hu La Tang, optimizing energy utilization, and ensuring the cooking quality are achieved. This makes the temperature of Hu La Tang more stable, energy more economical, and the quality of the finished product more controllable during the cooking process.

[0066] In S2, the Kalman filter algorithm is used to fuse the collected data. The core formula of the Kalman filter algorithm is as follows:

[0067] Prediction steps:

[0068] Update steps:

[0069]

[0070] P k∣k =(IK k H k )P k|k-1

[0071] in, is the state prediction value at the previous moment, is the optimal estimated value of the state at the previous moment, F k is the state transfer matrix, B k Control matrix, u k is the control vector, P k∣k-1 is the prediction covariance, P k-1∣k-1 is the covariance at the previous moment, Q k is the process noise covariance matrix, K k is the Kalman gain, H k is the observation matrix, z k is the observed value, R k is the measurement noise covariance matrix, is the optimal estimated value of the current state, P k∣k is the covariance at the current moment.

[0072] Specifically, the Kalman filter algorithm is used to fuse the collected temperature, pressure, humidity and material concentration data. The core formula is to use the state transfer matrix F k The prediction step of estimating the state and covariance of the next moment and combining the observation value z k The updated step of correcting the predicted value and obtaining the optimal estimate at the current moment can effectively deal with the errors in the collected data caused by the sensor's own noise and the interference of the cooking environment. For example, suppose that at a certain time k, the temperature sensor collects the soup temperature z k The temperature value predicted based on the state at the previous moment is 85.3℃. is 85.0℃. At this time, the algorithm calculates the prediction covariance P through the prediction step. k∣k-1 = 0.5, combined with the measurement noise covariance R determined by the sensor accuracy k = 0.2 and the observation matrix H of direct temperature observation k =1, calculate Kalman gain Then, in the update step, the algorithm combines the predicted values ​​with the observed values ​​to obtain the optimal estimated temperature The impact of random noise is significantly reduced, and the algorithm continues to operate during the brewing process through a dynamic data fusion mechanism. For example, when steam interference causes a temperature fluctuation of ±0.5°C, the algorithm controls the temperature estimation error within ±0.1°C through iterative calculations.

[0073] In S3, the fuzzy control algorithm uses the following rules for control:

[0074] The domain of temperature deviation E is {-5,-4,-3,-2,-1,0,1,2,3,4,5}, and the domain of deviation change rate EC is {-3,-2,-1,0,1,2,3};

[0075] The domain of heating power adjustment value U1 is {-3,-2,-1,0,1,2,3}, and the domain of stirring speed adjustment value U2 is {-2,-1,0,1,2};

[0076] The centroid method is used for defuzzification, and the calculation formula is: where u i is an element in the fuzzy set, μ(u i ) is the membership degree of the corresponding element.

[0077] Specifically, the temperature deviation E domain covers -5 to 5, and the deviation change rate EC domain is set to -3 to 3. The domains corresponding to the heating power adjustment amount U1 and the stirring speed adjustment amount U2 can fully cover the temperature fluctuation and change trend during boiling. For example, if the temperature deviation E is detected to be 2, that is, the current temperature is 2°C higher than the target, and the deviation change rate EC is 1, that is, the temperature is rising at a rate of 1 unit, the membership of each domain element is first determined according to the fuzzy rules. Assuming that the u1 in the fuzzy set that matches this situation is -2, -1, 0, etc., the corresponding membership μ(u i ) are 0.3, 0.5, and 0.2 respectively, using the centroid method formula Calculation, that is It was concluded that the heating power adjustment amount needed to be adjusted to -1.1, that is, the power needed to be reduced. At the same time, the stirring speed adjustment amount needed to be determined accordingly to quickly respond to temperature changes. This can effectively stabilize the temperature in the initial stage of cooking and solve the problems of local overheating or insufficient heating caused by large temperature fluctuations. This lays the foundation for the subsequent optimization accuracy of the neural network control algorithm, ensures the timeliness and rationality of temperature control during the cooking process of Hu La Tang, and helps achieve stable constant temperature.

[0078] In S3, the neural network control algorithm uses a three-layer feedforward neural network, with 4 input layer nodes and 8-16 hidden layer nodes. The hidden layer uses the Sigmoid activation function, and the formula is: The number of nodes in the output layer is 2, and the output layer uses a linear activation function f(x) = x. The network is trained by back propagation algorithm and stochastic gradient descent method. The learning rate is set to 0.01-0.1, the batch size is 32-128, and the maximum number of iterations is 1000-2000. When the loss function converges to less than 0.01, the training is stopped. The loss function uses the mean square error function. Where n is the number of samples, y i is the true value, is the predicted value.

[0079] Specifically, the neural network control algorithm adopts a three-layer feedforward neural network. The four nodes in the input layer correspond to the collected temperature, pressure, humidity, and material concentration data, and the 8-16 nodes in the hidden layer are activated by Sigmoid function. To process nonlinear relationships, the two nodes of the output layer correspond to the output heating power adjustment instructions and the stirring speed adjustment instructions, and the heating power and stirring speed adjustment instructions are output through the linear activation function f(x)=x. For example, the input layer inputs data such as the soup temperature of 85℃, pressure of 0.2MPa, humidity of 60%, and material concentration of 15% at a certain moment. The hidden layer uses the Sigmoid function to perform nonlinear transformation on these data to simulate the correlation between parameters under a complex boiling environment. During training, the learning rate is set to 0.01-0.1, batch size 32-128, and the maximum number of iterations is 1000-2000 times. The mean square error function is used. We measure predictions, such as the difference between the predicted heating power adjustment and the true value. When the MSE converges to less than 0.01, we stop training. This allows the network to accurately learn the mapping relationship between the cooking parameters and the control instructions. This can optimize the adjustment of heating power and stirring speed, solve the problem of decreased constant temperature accuracy caused by parameter drift during long-term operation, continuously improve the constant temperature control effect of Hu La Tang, and ensure the stable quality of the finished product.

[0080] In S5, the K-means algorithm is used to perform cluster analysis on the data, and the objective function is:

[0081]

[0082] Where k is the number of clusters, C i is the i-th cluster, μ i is the centroid of the i-th cluster;

[0083] The decision tree algorithm is used to select the split attribute by calculating the information gain. The calculation formula is:

[0084]

[0085] Where S is the sample set, A is the attribute, Values(A) is the value set of attribute A, S v is the sample subset when the attribute A takes the value v, H(S) is the information entropy of the sample set S v ) is the sample subset S v Information entropy.

[0086] Specifically, the K-means algorithm works in conjunction with the decision tree algorithm to deeply analyze data, where the K-means algorithm uses the objective function Cluster the boiling data. For example, multiple groups of data such as temperature 85℃ / 83℃ and pressure 0.2MPa / 0.18MPa constitute samples. According to the number of k clusters, such as k=3, they are divided into heating, constant temperature and cooling stages. C i is the data cluster at each stage, μ iIt is the centroid of the cluster. By minimizing the distance between the data in the cluster and the centroid, the characteristic patterns of data at different stages of cooking are identified. The decision tree algorithm is based on the information gain formula Select splitting attributes. Taking the brewing data sample set S containing attributes such as temperature and power as an example, calculate the information gain of the temperature attribute A, select the attribute with high gain as the splitting point, build a decision tree, and explore the association between the equipment operation status and data characteristics. It can cluster and analyze the characteristics of different stages from massive brewing data, build a decision model to predict the equipment status, provide data support for optimizing brewing parameters and ensuring stable equipment operation, and make the equipment operation status prediction data and parameter combination data generated by cloud platform analysis more accurate.

[0087] In S1, data is collected using temperature sensors, pressure sensors, humidity sensors and material concentration sensors. Each sensor is installed in a distributed manner. The temperature sensor is arranged at the center of the bottom of the pot, the middle of the side wall and the center of the soup. The pressure sensor is installed on the top of the pot, the humidity sensor is installed at the steam outlet, and the material concentration sensor is installed near the stirring paddle.

[0088] Specifically, by selecting temperature sensors, pressure sensors, humidity sensors, and material concentration sensors, and using distributed installation of temperature sensors at the center of the bottom of the pot, the middle of the side wall, and the center of the soup, pressure sensors at the top of the pot, humidity sensors at the steam outlet, and material concentration sensors near the stirring paddle, it is possible to collect temperature, pressure, humidity, and material concentration data of the soup in the pot in all directions, ensuring the accuracy and effectiveness of monitoring and control of the entire boiling process, and helping to achieve stable and high-quality Hu La Tang boiling effects.

[0089] In S6, waste heat is recovered through the waste heat recovery device and used to preheat new materials. The energy consumption of the heating system is monitored and scheduled through the intelligent energy management system. The waste heat recovery device uses a spiral tube heat exchanger. The intelligent energy management system preheats at 80%-90% of the rated power during off-peak periods according to the peak and off-peak electricity price periods of the power grid, and dynamically adjusts the working combination of the heating elements during peak periods.

[0090] Specifically, the waste heat recovery device of the spiral tube heat exchanger is used to recover the waste heat from the cooking process, which can be used to preheat new materials, realize energy recycling, and reduce energy waste. At the same time, the intelligent energy management system preheats at 80%-90% of the rated power during the off-peak period according to the peak and off-peak electricity price period of the power grid, and dynamically adjusts the working combination of the heating elements during the peak period. It can effectively adapt to the power grid electricity price policy and reduce energy costs. From the perspective of energy recovery and intelligent scheduling, it optimizes the energy utilization of the Hu La Tang cooking process, which not only improves the energy utilization efficiency, but also provides support for the stable and economical operation of the entire constant temperature cooking system, helping to achieve the goal of energy saving and efficient cooking.

[0091] Example 2:

[0092] Reference Figure 2 In a second embodiment of the present invention, the present invention provides a constant temperature system for boiling spicy soup, the system comprising:

[0093] The sensor acquisition module is used to collect data on the temperature, pressure, humidity and material concentration of the soup in the boiling pot;

[0094] The data fusion module is connected to the sensor acquisition module and is used to fuse the collected data to generate comprehensive monitoring data;

[0095] The artificial intelligence control module is connected to the data fusion module and is used to automatically switch between the fuzzy control algorithm and the neural network control algorithm according to the initial stage or the stable stage of boiling, and to generate adjustment instructions for heating power and stirring speed based on the comprehensive monitoring data;

[0096] The heating system control module is connected to the artificial intelligence control module and is used to control the operation of the heating system according to the heating power adjustment instruction;

[0097] The agitator control module is connected to the artificial intelligence control module and is used to control the operation of the agitator according to the stirring speed adjustment instruction;

[0098] The IoT transmission module is connected to the sensor acquisition module and is used to upload the collected data to the cloud platform;

[0099] The cloud platform module is connected to the IoT transmission module to analyze the data and generate equipment operation status prediction data and parameter combination data;

[0100] Waste heat recovery module, used to recover waste heat from the cooking process and use it to preheat new materials;

[0101] The intelligent energy management module is connected to the heating system control module and is used to monitor the energy consumption of the heating system and perform intelligent scheduling.

[0102] Specifically, the sensor acquisition module, as the data acquisition portal, collects data on the temperature, pressure, humidity, and material concentration of the soup in the boiling pot through a variety of sensors, providing real and comprehensive raw information for subsequent modules. It is the basis for the precise control of the entire system.

[0103] The data fusion module receives multi-dimensional raw data and uses algorithms to fuse the data, filter noise, integrate effective information, and generate comprehensive monitoring data that can accurately reflect the brewing status, so that subsequent control modules can obtain input.

[0104] The artificial intelligence control module, based on the comprehensive monitoring data provided by the data fusion module, automatically switches between the fuzzy control algorithm and the neural network control algorithm according to whether the cooking process is in the initial stage or the stable stage, and generates targeted adjustment instructions for the heating power and stirring speed, achieving precise control at different cooking stages and ensuring temperature stability and precision optimization.

[0105] The heating system control module receives the heating power adjustment instructions output by the artificial intelligence control module, directly acts on the heating system, accurately controls the heating power, and ensures that the temperature of the boiling process changes according to the set target.

[0106] The stirrer control module controls the stirrer according to the stirring speed adjustment instructions generated by the artificial intelligence control module. By adjusting the stirring speed and coordinating with the heating system, the soup is heated more evenly.

[0107] The IoT transmission module transmits the collected real-time data to the cloud platform, providing a data channel for remote analysis and decision-making;

[0108] The cloud platform module receives data uploaded by the IoT transmission module, analyzes it using K-means algorithms and decision tree algorithms, and generates equipment operation status prediction data and parameter combination data, providing a basis for system optimization control and prediction of equipment failures.

[0109] The waste heat recovery module actively recovers waste heat from the cooking process and uses it to preheat new materials, thus realizing energy recycling, reducing energy waste, and making the system run more efficiently from an energy perspective;

[0110] The intelligent energy management module works in conjunction with the heating system control module to monitor the energy consumption of the heating system and perform intelligent scheduling based on strategies such as peak and valley electricity prices in the power grid, thus ensuring stable and economical operation of the heating system while saving energy costs.

[0111] Example 3

[0112] The third embodiment of the present invention is based on the same inventive concept and proposes a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the constant temperature method for boiling spicy soup in the above embodiment are implemented.

[0113] Example 4

[0114] The fourth embodiment of the present invention is based on the same inventive concept. The present invention proposes a computer device, the terminal including: a processor, a memory; the processor and the memory communicate with each other; the memory is used to store instructions; the processor is used to execute the instructions in the memory to execute the constant temperature method for making spicy soup in the above embodiment.

[0115] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0116] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A constant temperature method for preparing spicy soup, characterized in that: The following steps are involved: S1. Collect the temperature, pressure, humidity and material concentration data of the soup in the pot; S2. Fusing the collected data to generate comprehensive monitoring data; S3. Alternately using fuzzy control algorithms and neural network control algorithms to generate adjustment instructions for heating power and stirring speed based on comprehensive monitoring data. The fuzzy control algorithm is used to stabilize the temperature in the initial stage of boiling, and the neural network control algorithm is used to optimize the constant temperature accuracy in the stable boiling stage. S4, controlling the heating system and the agitator according to the adjustment instructions; S5. Upload the collected data to the cloud platform for analysis to generate equipment operation status prediction data and parameter combination data; S6. Recover waste heat from the cooking process and use it to preheat new materials. At the same time, monitor the energy consumption of the heating system and perform intelligent scheduling.

2. The method for boiling spicy soup at a constant temperature according to claim 1, wherein: In S2, the Kalman filter algorithm is used to fuse the collected data. The core formula of the Kalman filter algorithm is as follows: Prediction steps: Update steps: P k∣k =(I-K k H k )P k|k-1 in, is the state prediction value at the previous moment, is the optimal estimated value of the state at the previous moment, F k is the state transfer matrix, B k Control matrix, u k is the control vector, P k∣k-1 is the prediction covariance, P k-1∣k-1 is the covariance at the previous moment, Q k is the process noise covariance matrix, K k is the Kalman gain, H k is the observation matrix, z k is the observed value, R k is the measurement noise covariance matrix, is the optimal estimated value of the current state, P k∣k is the covariance at the current moment.

3. The method for boiling Hu La Tang at a constant temperature according to claim 1, wherein: In S3, the fuzzy control algorithm uses the following rules for control: The domain of temperature deviation E is {-5,-4,-3,-2,-1,0,1,2,3,4,5}, and the domain of deviation change rate EC is {-3,-2,-1,0,1,2,3}; The domain of heating power adjustment value U1 is {-3,-2,-1,0,1,2,3}, and the domain of stirring speed adjustment value U2 is {-2,-1,0,1,2}; The centroid method is used for defuzzification, and the calculation formula is: where u i is an element in the fuzzy set, μ(u i ) is the membership degree of the corresponding element.

4. The method for boiling spicy soup at a constant temperature according to claim 1, wherein: In S3, the neural network control algorithm adopts a three-layer feedforward neural network, the number of input layer nodes is 4, the number of hidden layer nodes is 8-16, and the hidden layer adopts Sigmoid activation function, the formula is The number of nodes in the output layer is 2, and the output layer uses a linear activation function f(x) = x. The network is trained by back propagation algorithm and stochastic gradient descent method. The learning rate is set to 0.01-0.1, the batch size is 32-128, and the maximum number of iterations is 1000-2000. When the loss function converges to less than 0.01, the training is stopped. The loss function uses the mean square error function. Where n is the number of samples, y i is the true value, is the predicted value.

5. The constant temperature method for boiling spicy soup according to claim 1, characterized in that: In S5, the K-means algorithm is used to perform cluster analysis on the data, and the objective function is: Where k is the number of clusters, C i is the i-th cluster, μ i is the centroid of the i-th cluster; The decision tree algorithm is used to select the split attribute by calculating the information gain. The calculation formula is: Where S is the sample set, A is the attribute, Values(A) is the value set of attribute A, S v is the sample subset when the attribute A takes the value v, H(S) is the information entropy of the sample set S v ) is the sample subset S v Information entropy.

6. The constant temperature method for boiling spicy soup according to claim 1, characterized in that: In S1, data is collected using temperature sensors, pressure sensors, humidity sensors and material concentration sensors. Each sensor is installed in a distributed manner. The temperature sensor is arranged at the center of the bottom of the pot body, the middle of the side wall and the center of the soup. The pressure sensor is installed on the top of the pot body, the humidity sensor is installed at the steam outlet, and the material concentration sensor is installed near the stirring paddle.

7. The constant temperature method for boiling spicy soup according to claim 1, characterized in that: In S6, waste heat is recovered by a waste heat recovery device and used to preheat new materials. The energy consumption of the heating system is monitored and scheduled by an intelligent energy management system. The waste heat recovery device adopts a spiral tube heat exchanger. The intelligent energy management system preheats at 80%-90% of the rated power during off-peak periods according to the peak and off-peak electricity price periods of the power grid, and dynamically adjusts the working combination of the heating elements during peak periods.

8. The constant temperature system for boiling spicy soup is characterized by: The method for constant temperature boiling of spicy hot soup according to any one of claims 1 to 7, wherein the system comprises: The sensor acquisition module is used to collect data on the temperature, pressure, humidity and material concentration of the soup in the boiling pot; The data fusion module is connected to the sensor acquisition module and is used to fuse the collected data to generate comprehensive monitoring data; The artificial intelligence control module is connected to the data fusion module and is used to automatically switch between the fuzzy control algorithm and the neural network control algorithm according to the initial stage or the stable stage of boiling, and to generate adjustment instructions for heating power and stirring speed based on the comprehensive monitoring data; The heating system control module is connected to the artificial intelligence control module and is used to control the operation of the heating system according to the heating power adjustment instruction; The agitator control module is connected to the artificial intelligence control module and is used to control the operation of the agitator according to the stirring speed adjustment instruction; The IoT transmission module is connected to the sensor acquisition module and is used to upload the collected data to the cloud platform; The cloud platform module is connected to the IoT transmission module to analyze the data and generate equipment operation status prediction data and parameter combination data; Waste heat recovery module, used to recover waste heat from the cooking process and use it to preheat new materials; The intelligent energy management module is connected to the heating system control module and is used to monitor the energy consumption of the heating system and perform intelligent scheduling.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the constant temperature method for boiling spicy soup according to any one of claims 1 to 7 is implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by the processor, the constant temperature method for boiling spicy soup according to any one of claims 1 to 7 is implemented.

Images