Intelligent real-time regulation and control foot tub health management system

Abstract

The invention discloses an intelligent real-time regulation and control foot tub health management system which comprises an automatic water quality purification subsystem, a water temperature regulation and control subsystem, a foot biological signal detection subsystem, a touch-free induction control subsystem and a self-adaptive climate control subsystem. The invention belongs to the technical field of intelligent health, and particularly relates to a double-flow control algorithm combining real-time water temperature control flow and environment adaptation optimization flow in a water temperature regulation and control subsystem in a foot tub, water temperature management combining dynamic and static control is achieved, and on the basis that the double-flow control algorithm is designed in the water temperature regulation and control subsystem, water temperature management is achieved. A time sequence modeling method for power adjustment is provided, a power adjustment model is constructed by using a position Fourier transform bidirectional and conditional generative adversarial network, periodicity and frequency characteristics in time sequence data are extracted from a frequency domain level, heating power is accurately adjusted, unnecessary energy consumption is reduced, and the energy efficiency ratio of a system is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent health technology, and in particular to an intelligent real-time regulated footbath health management system. Background Art

[0002] As people pay more and more attention to health management, footbaths, as a widely used health device, have been favored by more and more consumers. Most of the existing smart footbath health management systems use traditional control methods to adjust water temperature and water quality. However, these traditional methods often have many shortcomings when facing complex environmental changes. Existing systems often rely on simple timed heating or temperature control algorithms to adjust water temperature. This method cannot adapt to fluctuations in ambient temperature and actual needs of users in real time, causing water temperature to fluctuate easily, affecting user comfort and usage experience. In addition, many traditional systems do not take into account the impact of environmental changes, such as air humidity, wind speed and other factors, and cannot dynamically optimize and adjust the heating power, resulting in heat waste and excessive energy consumption. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent real-time control footbath health management system. In view of the problem that water temperature is prone to fluctuations, the present invention designs a dual-flow control algorithm combining real-time water temperature control flow and environmental adaptation optimization flow in the water temperature control subsystem, realizes water temperature management combining dynamic and static control, and realizes accurate and flexible water temperature control through multi-dimensional data input, thereby improving the real-time and adaptability of the system; in view of the problem that water temperature cannot remain stable in a dynamic environment, the present invention proposes a time series modeling method for power adjustment based on the design of a dual-flow control algorithm in the water temperature control subsystem, constructs a power adjustment model using position Fourier transform bidirectional and conditional generative adversarial network, extracts periodicity and frequency characteristics in time series data from the frequency domain level, and deeply captures long-term and short-term dependencies in time series by forward and reverse encoding time series data, effectively captures the impact of environmental fluctuations on heat loss and power demand, accurately adjusts heating power, reduces unnecessary energy consumption, and improves the energy efficiency of the system.

[0004] The technical solution adopted by the present invention is as follows: the present invention provides an intelligent real-time regulated footbath health management system, including an automatic water purification subsystem, a water temperature regulation subsystem, a foot biosignal detection subsystem, a touchless sensing control subsystem and an adaptive climate control subsystem;

[0005] The automatic water purification subsystem includes an ultraviolet germicidal lamp and an activated carbon filtration device;

[0006] The water temperature control subsystem includes an integrated heat exchanger, sets the initial heating power, and adjusts the heating power by designing a dual-flow control algorithm to control the water temperature;

[0007] The foot bio-signal detection subsystem detects the user's bio-signals during the foot bath, including heart rate, blood oxygen and skin galvanic response, by installing bio-sensors in an array on the bottom and inner wall of the foot bath.

[0008] The touchless sensing control subsystem introduces gesture recognition technology to control the functions of the footbath in mid-air through gestures, including adjusting water temperature, starting purification, and turning on massage mode;

[0009] The adaptive climate control subsystem adjusts the temperature, humidity and ventilation of the internal environment of the footbath by detecting the temperature and humidity of the surrounding environment.

[0010] Furthermore, a dual-flow control algorithm is designed in the water temperature control subsystem to control the water temperature, which specifically includes the following contents:

[0011] Real-time water temperature control flow: real-time monitoring of water temperature deviation, dynamic adjustment of heating power, setting of water temperature stability value, and control of footbath water temperature to be stable within the water temperature stability value, specifically including the following steps:

[0012] Step K1: Error calculation, collect the actual water temperature in real time, set the target water temperature, calculate the error and error change rate, the formula used is as follows: ; ;

[0013] in, is the water temperature error, is the target water temperature, is the actual water temperature, is the error change rate, is the current moment error;

[0014] Step K2: Fuzzy control, adjusting the heating power according to the water temperature error and the error change rate, specifically including the following:

[0015] Rapid heating: and When the heating power is increased;

[0016] Reduce power: and When the heating power is reduced or the heating is stopped;

[0017] Fine-tuning stability: When the power is stable;

[0018] Step K3: Set the fuzzy domain, set the value range of water temperature error and error change rate to [-2, 2], the heating power adjustment range to [-3, 3], use fuzzy subsets for water temperature error, error change rate and heating power, including NB, NM, NS, ZO, PS, PM, PB, define fuzzy rules, and calculate the heating power adjustment value;

[0019] Step K4: membership function definition, setting the membership of water temperature error and error change rate;

[0020] Step K5: fuzzy reasoning, using the fuzzy reasoning mechanism to derive the fuzzy value of the heating power;

[0021] Step K6: defuzzification to obtain the output value of heating power;

[0022] Environmental adaptation optimization flow: Detect ambient temperature data and build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network. The specific steps include:

[0023] Step E1: Environmental data collection, collecting environmental factors, including air humidity, ambient temperature, wind speed and water volume;

[0024] Step E2: Heat loss assessment, calculate the heat loss caused by environmental factors, and establish an assessment formula, which is expressed as follows: ;

[0025] in, For heat loss, is the heat transfer coefficient, is the exposed area, is the wind speed heat dissipation coefficient, is the ambient temperature, is the wind speed;

[0026] Step E3: Dynamic adjustment, detect the change range of environmental data, combine heat loss with water temperature error and error change rate, build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network, and adjust the heating power;

[0027] Step E4: environmental data fluctuation detection, detecting the fluctuation amplitude of environmental data, and analyzing the impact of the fluctuation of environmental data on heat loss;

[0028] Step E5: Based on the fuzzy rule of step K3, set the priority adjustment for sudden changes in ambient temperature. The condition for sudden changes in ambient temperature is a sudden increase or decrease in ambient temperature of more than five degrees.

[0029] Further, step E3 uses the position Fourier transform bidirectional and conditional generative adversarial network to build a power adjustment model to adjust the heating power, which specifically includes the following steps:

[0030] Step E31: data preparation, collecting time series data, including the current heating power adjustment value and power output change rate;

[0031] Step E32: constructing a power adjustment model. The power adjustment model specifically includes the following modules:

[0032] Position encoder: captures the positional relationship in time series data and introduces time-dependent characteristics using embedding mechanisms;

[0033] Frequency domain enhancement module: Perform position Fourier transform on time series data to extract frequency domain features;

[0034] Generator: input frequency domain features and generate repaired time series data;

[0035] Discriminator: judges the authenticity of the repaired time series data;

[0036] Bidirectional network: Use the bidirectional LSTM model to encode time series data forward and backward;

[0037] Step E33: loss function design, designing and generating a combination function combining adversarial loss, timing error loss and frequency domain consistency loss;

[0038] Step E34: training the power adjustment model, dividing the time series data into a training set, a validation set, and a test set, and using the training set to perform training through a back propagation algorithm;

[0039] Step E35: Evaluation and verification: Use the verification set and the test set to evaluate and verify the trained power adjustment model to obtain verification results.

[0040] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0041] (1) To address the problem of water temperature fluctuation, the present invention designs a dual-flow control algorithm combining real-time water temperature control flow and environmental adaptation optimization flow in the water temperature control subsystem, thereby realizing water temperature management combining dynamic and static control, and realizing accurate and flexible water temperature control through multi-dimensional data input, thereby improving the real-time and adaptability of the system;

[0042] (2) Aiming at the problem that water temperature cannot remain stable in a dynamic environment, the present invention proposes a time series modeling method for power adjustment based on the design of a dual-flow control algorithm in the water temperature control subsystem. The power adjustment model is constructed using position Fourier transform bidirectional and conditional generative adversarial network. The periodicity and frequency characteristics in the time series data are extracted from the frequency domain. By forward and reverse encoding the time series data, the long-term and short-term dependencies in the time series are deeply captured, and the impact of environmental fluctuations on heat loss and power demand is effectively captured. The heating power is accurately adjusted to reduce unnecessary energy consumption and improve the energy efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of a module of an intelligent real-time regulated footbath health management system provided by the present invention;

[0044] Figure 2 A schematic diagram of a flow chart of water temperature control using a dual-flow control algorithm provided by the present invention.

[0045] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0048] Example 1, see Figure 1 , the present invention provides an intelligent real-time regulated footbath health management system, including an automatic water purification subsystem, a water temperature regulation subsystem, a foot biosignal detection subsystem, a touchless sensing control subsystem and an adaptive climate control subsystem;

[0049] The automatic water purification subsystem includes an ultraviolet germicidal lamp and an activated carbon filtration device;

[0050] The water temperature control subsystem includes an integrated heat exchanger, sets the initial heating power, and adjusts the heating power by designing a dual-flow control algorithm to control the water temperature;

[0051] The foot bio-signal detection subsystem detects the user's bio-signals during the foot bath, including heart rate, blood oxygen and skin galvanic response, by installing bio-sensors in an array on the bottom and inner wall of the foot bath.

[0052] The touchless sensing control subsystem introduces gesture recognition technology to control the functions of the footbath in mid-air through gestures, including adjusting water temperature, starting purification, and turning on massage mode;

[0053] The adaptive climate control subsystem adjusts the temperature, humidity and ventilation of the internal environment of the footbath by detecting the temperature and humidity of the surrounding environment.

[0054] Example 2, see Figure 2 Based on the above embodiment, this embodiment designs a dual-flow control algorithm in the water temperature control subsystem to control the water temperature, which specifically includes the following contents:

[0055] Real-time water temperature control flow: real-time monitoring of water temperature deviation, dynamic adjustment of heating power, setting of water temperature stability value, and control of footbath water temperature to be stable within the water temperature stability value, specifically including the following steps:

[0056] Step K1: Error calculation, collect the actual water temperature in real time, set the target water temperature, calculate the error and error change rate, the formula used is as follows: ; ;

[0057] in, is the water temperature error, is the target water temperature, is the actual water temperature, is the error change rate, is the current moment error;

[0058] Step K2: Fuzzy control, adjusting the heating power according to the water temperature error and the error change rate, specifically including the following:

[0059] Rapid heating: and When the heating power is increased;

[0060] Reduce power: and When the heating power is reduced or the heating is stopped;

[0061] Fine-tuning stability: When the power is stable;

[0062] Step K3: Set the fuzzy domain, set the value range of water temperature error and error change rate to [-2, 2], the heating power adjustment range to [-3, 3], use fuzzy subsets for water temperature error, error change rate and heating power, including NB, NM, NS, ZO, PS, PM, PB, define fuzzy rules, and calculate the heating power adjustment value;

[0063] Define fuzzy subsets, including: NB: large negative value; NM: medium negative; NS: small negative value; ZO: Near zero; PS: small positive value; PM: neutral value; PB: large positive value;

[0064] Step K4: membership function definition, setting the membership of water temperature error and error change rate;

[0065] (1) Water temperature error: NB: The coverage range is [−2,−1.5][-2,-1.5][−2,−1.5], and the membership is 1 when −2 and 0 when −1.5; NM: the coverage range is [−2,−0.5][-2,-0.5][−2,−0.5], and the maximum membership is −1.0; NS: the coverage range is [−1.5, 0][-1.5, 0][−1.5, 0], and the maximum membership is −0.5; ZO: the coverage range is [−0.5, 0.5][-0.5, 0.5][−0.5, 0.5], and the maximum membership is 0; PS, PM, PB: similarly defined and symmetrically distributed in the positive interval;

[0066] (2) Error change rate: NB: The coverage range is [−2,−1.5][-2,-1.5][−2,−1.5]; ZO: the coverage range is [−0.5, 0.5][-0.5, 0.5][−0.5, 0.5]; PB: The coverage range is [1.5,2][1.5,2][1.5,2]; Calculate membership and fuzzy reasoning: Use fuzzy reasoning method to calculate output;

[0067] Input fuzzification:

[0068] current =1.2, the fuzzy memberships of PS and PM are: ; ;

[0069] current =0.8, the fuzzy memberships of PS and PM are: ; ;

[0070] Inference calculation:

[0071] if =PS and =PS, output =ZO;

[0072] if =PM and =PS, output =NS;

[0073] Defuzzification: Use the maximum membership method to defuzzify the output fuzzy subset and calculate the final heating power adjustment value as 1.8;

[0074] The calculated 1.8 is sent to the heater to adjust the heating power.

[0075] Environmental adaptation optimization flow: Detect ambient temperature data and build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network. The specific steps include:

[0076] Step E1: Environmental data collection, collecting environmental factors, including air humidity, ambient temperature, wind speed and water volume;

[0077] Step E2: Heat loss assessment, calculate the heat loss caused by environmental factors, and establish an assessment formula, which is expressed as follows: ;

[0078] in, For heat loss, is the heat transfer coefficient, is the exposed area, is the wind speed heat dissipation coefficient, is the ambient temperature, is the wind speed;

[0079] Step E3: Dynamic adjustment, detect the change range of environmental data, combine heat loss with water temperature error and error change rate, build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network, and adjust the heating power;

[0080] Step E4: environmental data fluctuation detection, detecting the fluctuation amplitude of environmental data, and analyzing the impact of the fluctuation of environmental data on heat loss;

[0081] Step E5: Based on the fuzzy rule of step K3, set the priority adjustment for sudden changes in ambient temperature. The condition for sudden changes in ambient temperature is a sudden increase or decrease in ambient temperature of more than five degrees.

[0082] Embodiment 3, this embodiment is based on the above embodiment. In this embodiment, there is a foot bath, the user sets the target water temperature to 38°C, the current ambient temperature is 20°C, the real-time water temperature is 36°C, and the dual-flow control algorithm is used to perform real-time water temperature control and environmental adaptation optimization, specifically including the following contents:

[0083] Real-time water temperature control flow:

[0084] Step K1: Error calculation, detecting the real-time water temperature The target water temperature is 36°C, and the data is obtained once a second through the NTC temperature sensor. is 38°C, the error change rate is calculated by the difference method, the error at the current moment is 2°C, and it is assumed that the error in the past 1 second is 1.5°C. 0.5°C / s;

[0085] Step K2: Current Error is 2°C, greater than 0.5°C and the error change rate It is 0.5°C / s, which is less than 0. According to the control rule, it means that the temperature is still low and the error change rate is increasing positively, so the heating power needs to be increased;

[0086] Step K3: Water temperature error The range is set to [-2,2]°C, and the error change rate The range is set to [-2,2]°C / s, and the corresponding heating power adjustment range is [-3,3];

[0087] Step K4: Use the triangular membership function to define the membership function of the water temperature error. For the current error of 2°C, the corresponding membership function value is PB, and the error change rate is 0.5°C / s. The corresponding fuzzy set obtained by the membership function is PS. Through the fuzzy reasoning method, the heating power adjustment value is +2;

[0088] Step K5: fuzzy reasoning, using the fuzzy reasoning mechanism to derive the fuzzy value of the heating power;

[0089] Step K6: defuzzification to obtain the output value of heating power;

[0090] Environmental adaptation flow:

[0091] Step E1: The collected air humidity is 60%, the ambient temperature is 20°C, the wind speed is 2m / s, and the collection frequency is 1Hz;

[0092] Step E2: The heat transfer coefficient is 0.5 and the exposed area is , the wind speed heat dissipation coefficient is 0.3. According to the heat loss formula, the heat loss is 8.6w;

[0093] Step E3: Combining the ambient heat loss and water temperature error, the heating power is adjusted using the position Fourier transform and bidirectional LSTM neural network. Assume that the current heating power is +2, but due to environmental factors, the heat loss is 8.6W. The system needs to increase the heating power to compensate for the heat loss.

[0094] Step E4: Environmental data fluctuation detection, assuming that the ambient temperature suddenly rises to 25°C and the wind speed increases to 3m / s, and it is detected that the environmental change exceeds the set threshold (temperature change of more than 5°C and wind speed change of more than 2m / s), the heat loss is re-evaluated and the heating power is adjusted;

[0095] Step E5: Priority adjustment. Assuming that the ambient temperature suddenly increases by 5°C and the wind speed suddenly increases, the system prioritizes the impact of temperature fluctuations according to preset rules and adjusts the heating power. According to heat loss and environmental fluctuations, the heating power is adjusted to +3 to compensate for heat loss and ensure stable water temperature.

[0096] Final operation results:

[0097] Real-time water temperature: The final water temperature is stable around 38°C, which meets the user's set target;

[0098] Heating power: Heating power is dynamically adjusted between +2 and +3 to compensate for environmental factors and ensure temperature stability

[0099] Environmental adaptability: The system dynamically adjusts the heating power through comprehensive analysis of environmental data and water temperature errors to ensure that the water temperature remains within a comfortable range.

[0100] Embodiment 4, based on the above embodiment, step E3, uses position Fourier transform bidirectional and conditional generative adversarial network to build a power adjustment model to adjust the heating power, specifically including the following steps:

[0101] Step E31: data preparation, collecting time series data, including the current heating power adjustment value and power output change rate;

[0102] Step E32: constructing a power adjustment model. The power adjustment model specifically includes the following modules:

[0103] Position encoder: captures the positional relationship in time series data and introduces time-dependent characteristics using embedding mechanisms;

[0104] Frequency domain enhancement module: Perform position Fourier transform on time series data to extract frequency domain features;

[0105] Generator: input frequency domain features and generate repaired time series data;

[0106] Discriminator: judges the authenticity of the repaired time series data;

[0107] Bidirectional network: Use the bidirectional LSTM model to encode time series data forward and backward;

[0108] Step E33: loss function design, designing and generating a combination function combining adversarial loss, timing error loss and frequency domain consistency loss;

[0109] Step E34: training the power adjustment model, dividing the time series data into a training set, a validation set, and a test set, and using the training set to perform training through a back propagation algorithm;

[0110] Step E35: Evaluation and verification: Use the verification set and the test set to evaluate and verify the trained power adjustment model to obtain verification results.

[0111] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0112] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0113] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An intelligent real-time controlled footbath health management system, characterized by: The present invention provides an intelligent real-time regulated footbath health management system, comprising an automatic water purification subsystem, a water temperature regulation subsystem, a foot biological signal detection subsystem, a touchless sensing control subsystem and an adaptive climate control subsystem; The automatic water purification subsystem includes an ultraviolet germicidal lamp and an activated carbon filtration device; The water temperature control subsystem includes an integrated heat exchanger, sets the initial heating power, and adjusts the heating power by designing a dual-flow control algorithm to control the water temperature; The foot bio-signal detection subsystem detects the user's bio-signals during the foot bath by installing bio-sensors in arrays on the bottom and inner wall of the foot bath. The touch-free sensing control subsystem introduces gesture recognition technology to control the functions of the footbath in mid-air through gestures; The adaptive climate control subsystem adjusts the temperature, humidity and ventilation of the internal environment of the footbath by detecting the temperature and humidity of the surrounding environment.

2. The intelligent real-time control footbath health management system according to claim 1 is characterized by: In the water temperature control subsystem, a dual-flow control algorithm is designed to control the water temperature, including real-time water temperature control flow and environmental adaptation optimization flow. The real-time water temperature control flow specifically includes the following contents: Real-time water temperature control flow: real-time monitoring of water temperature deviation, dynamic adjustment of heating power, setting of water temperature stability value, and control of footbath water temperature to be stable within the water temperature stability value, specifically including the following steps: Step K1: Error calculation, collect the actual water temperature in real time, set the target water temperature, calculate the error and error change rate, the formula used is as follows: ； ； in, is the water temperature error, is the target water temperature, is the actual water temperature, is the error change rate, is the current moment error; Step K2: Fuzzy control, adjusting the heating power according to the water temperature error and the error change rate, specifically including the following: Rapid heating: and When the heating power is increased; Reduce power: and When the heating power is reduced or the heating is stopped; Fine-tuning stability: When the power is stable; Step K3: Set the fuzzy domain, set the value range of water temperature error and error change rate to [-2, 2], the heating power adjustment range to [-3, 3], use fuzzy subsets for water temperature error, error change rate and heating power, including NB, NM, NS, ZO, PS, PM, PB, define fuzzy rules, and calculate the heating power adjustment value; Step K4: membership function definition, setting the membership of water temperature error and error change rate; Step K5: fuzzy reasoning, using the fuzzy reasoning mechanism to derive the fuzzy value of the heating power; Step K6: Defuzzification to obtain the output value of heating power.

3. The intelligent real-time control footbath health management system according to claim 2 is characterized by: In the water temperature control subsystem, a dual-flow control algorithm is designed to control the water temperature, including real-time water temperature control flow and environmental adaptation optimization flow. The environmental adaptation optimization flow specifically includes the following contents: Environmental adaptation optimization flow: Detect ambient temperature data and build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network. The specific steps include: Step E1: Environmental data collection, collecting environmental factors, including air humidity, ambient temperature, wind speed and water volume; Step E2: Heat loss assessment, calculate the heat loss caused by environmental factors, and establish an assessment formula, which is expressed as follows: ； in, For heat loss, is the heat transfer coefficient, is the exposed area, is the wind speed heat dissipation coefficient, is the ambient temperature, is the wind speed; Step E3: Dynamic adjustment, detect the change range of environmental data, combine heat loss with water temperature error and error change rate, build a power adjustment model by using position Fourier transform bidirectional and conditional generative adversarial network, and adjust the heating power; Step E4: environmental data fluctuation detection, detecting the fluctuation amplitude of environmental data, and analyzing the impact of the fluctuation of environmental data on heat loss; Step E5: Based on the fuzzy rule of step K3, set the priority adjustment for sudden changes in ambient temperature. The condition for sudden changes in ambient temperature is a sudden increase or decrease in ambient temperature of more than five degrees.

4. The intelligent real-time control footbath health management system according to claim 3 is characterized by: Step E3, using the position Fourier transform bidirectional and conditional generative adversarial network to build a power adjustment model to adjust the heating power, specifically includes the following steps: Step E31: data preparation, collecting time series data, including the current heating power adjustment value and power output change rate; Step E32: constructing a power adjustment model. The power adjustment model specifically includes the following modules: Position encoder: captures the positional relationship in time series data and introduces time-dependent characteristics using embedding mechanisms; Frequency domain enhancement module: Perform position Fourier transform on time series data to extract frequency domain features; Generator: input frequency domain features and generate repaired time series data; Discriminator: judges the authenticity of the repaired time series data; Bidirectional network: Use the bidirectional LSTM model to encode time series data forward and backward; Step E33: loss function design, designing and generating a combination function combining adversarial loss, timing error loss and frequency domain consistency loss; Step E34: training the power adjustment model, dividing the time series data into a training set, a validation set, and a test set, and using the training set to perform training through a back propagation algorithm; Step E35: Evaluation and verification: Use the verification set and the test set to evaluate and verify the trained power adjustment model to obtain verification results.

Images