CN-122018591-A - Dynamic adjustment method of multi-mode intelligent controller of sauna room

CN122018591ACN 122018591 ACN122018591 ACN 122018591ACN-122018591-A

Abstract

The invention provides a dynamic adjustment method of a sauna room multi-mode intelligent controller, which belongs to the technical field of sauna room controllers, and aims to solve the technical problems that a sauna room temperature control system cannot predict forward future trend of a heating process in a dynamic thermal environment in a prospective mode, and heating power adjustment lag or overshoot is caused by overlapping feedback adjustment quantity of a gain scheduling proportional integral differential controller to obtain a final heating power command driving electric heating module, triggering an overheat protection strategy according to the temperature of the controller, triggering a low temperature compensation strategy according to the external temperature of the sauna room, continuously optimizing an artificial intelligent model through online parameter updating, uploading monitoring data and pushing abnormal alarms through a wireless communication module.

Inventors

WANG ZHI
LI CHANGJUN
ZHANG DONGJUAN

Assignees

青岛融通泰达新能源有限公司

Dates

Publication Date: 20260512
Application Date: 20260311

Claims (10)

1. A dynamic adjustment method of a multi-mode intelligent controller of a sauna room is characterized by comprising the following steps: The main control module respectively acquires the internal temperature of the sauna room, the self temperature of the controller and the external temperature of the sauna room through an environmental temperature sensor, a controller temperature sensor and an external temperature sensor, continuously acquires three temperature data by taking 100ms as a sampling interval, compresses the three temperature data through a self-adaptive sampling compression algorithm and stores the compressed three temperature data in the external serial peripheral interface flash memory chip; The main control module reads a sauna configuration mode selected by a user through the man-machine interaction module, and activates a corresponding relay output interface and a pulse width modulation dimming interface according to the mode self-adaptive matching logic to complete equipment linkage configuration; The main control module inputs the internal temperature of the sauna room, the self temperature of the controller, the external temperature of the sauna room and a target temperature threshold set by a user into a thermal prediction control model, forward rolls in a latent space to predict a future temperature track sequence by the thermal prediction control model, and outputs an optimal heating power instruction at the current moment according to the deviation between the future temperature track sequence and the target temperature threshold and the minimum feedforward power reference value of entropy production; The main control module is based on an optimal heating power instruction, a proportional-integral-derivative controller based on a gain scheduling mechanism is overlapped to obtain a final heating power instruction according to a feedback adjustment quantity output by the difference between the internal temperature of the sauna room and a target temperature threshold value, and the electric heating module and the sauna furnace module are driven by a pulse width modulation power adjustment circuit; The main control module calculates a controller temperature deviation index according to the temperature of the controller and a controller safety temperature threshold value, triggers a corresponding overheat protection strategy according to an interval to which the controller temperature deviation index belongs, triggers a low-temperature compensation strategy according to a comparison result of the external temperature of the sauna room and a low-temperature compensation threshold value, and inputs three actually-measured temperature data and a final heating power instruction into the thermal prediction control model to execute online parameter updating; the main control module uploads the internal temperature of the sauna room, the temperature of the controller, the final heating power instruction and the pulse width modulation dimming interface state to the mobile phone application program through the wireless communication module, and immediately stops heating and pushes the alarm frame when sensor data abnormality occurs.
2. The dynamic adjustment method of the sauna room multi-mode intelligent controller according to claim 1, wherein the adaptive sampling compression algorithm specifically uses whether the change rate of three paths of temperature data exceeds a set slope threshold as a judgment basis, records the current data point only when the change rate exceeds the slope threshold, skips storage at other moments, compresses the storage amount to 3-8% of the original data, and adopts a differential coding and compression algorithm to reduce bandwidth occupation during uploading.
3. The dynamic adjustment method of the sauna room multi-mode intelligent controller according to claim 2, wherein the mode self-adaptive matching logic, specifically, a device control policy table corresponding to each sauna configuration mode is prestored in a main control module, after a user selects the sauna configuration mode, the main control module looks up a table to obtain corresponding relay output interface power supply logic and pulse width modulation dimming interface preset parameters, and only issues an enabling signal to device interfaces required by the current sauna configuration mode, and other interfaces keep a power-off state.
4. The dynamic adjustment method of the multi-mode intelligent controller of the sauna room according to claim 3, wherein the thermodynamic prediction control model adopts a circulation state space model framework and comprises four submodules of a deterministic gating circulation unit, a random latent variable encoder, a latent space forward rolling predictor and an optimal power sequence solver, wherein the input of the deterministic gating circulation unit is 4 paths of numerical values in total of the internal temperature of the sauna room, the self temperature of the controller, the external temperature of the sauna room and a final heating power instruction at the current moment, and the deterministic gating circulation unit outputs a deterministic hidden state vector at the current moment.
5. The dynamic adjustment method of the sauna room multi-mode intelligent controller according to claim 4, wherein the random latent variable encoder takes a deterministic latent state vector as an input, outputs a random latent variable mean vector and a variance vector representing system uncertainty, and the random latent variable mean vector and the variance vector jointly form a latent space state representation, and the latent space forward rolling predictor takes the latent space state as an initial state and automatically rolls forward in a latent space to predict a temperature track sequence of 30 steps in the future.
6. The dynamic adjustment method of sauna room multi-mode intelligent controller according to claim 5, wherein the optimal power sequence solver takes the square sum of deviation of the future 30-step temperature track sequence and the target temperature threshold value as an objective function, weights the final heating power instruction change amount, searches the optimal heating power sequence minimizing the objective function in the latent space, and takes the value of the first step of the sequence as the current time optimal heating power instruction.
7. The dynamic adjustment method of the multi-mode intelligent controller of the sauna room according to claim 6, wherein training of the thermal prediction control model takes a time sequence sample pair as input, takes the square of the difference between the internal temperature of the sauna room at the next moment predicted by the deterministic gating circulation unit and the internal temperature of the actual sauna room as reconstruction loss, takes the KL divergence of a random latent variable mean vector and a variance vector output by the random latent variable encoder as regularization loss, takes the weighted summation of the two as a total loss function, and adopts a back propagation algorithm to update all parameters.
8. The dynamic adjustment method of the multi-mode intelligent controller of the sauna room according to claim 7, wherein the calculation of the entropy production minimization feedforward power reference value regards a sauna room heating process as an irreversible thermodynamic process, the total entropy production minimization of the heating process is taken as an optimization target, a variation problem is established under the given target temperature threshold and heating time constraint, and an Euler-Lagrange equation is solved to obtain an exponential form asymptotic power curve of the change of optimal heating power along with time.
9. The dynamic adjustment method of the multi-mode intelligent controller of the sauna room according to claim 8, wherein the gain scheduling mechanism loads corresponding proportional coefficients, integral coefficients and differential coefficients from a pre-calibration parameter group table according to a zone to which a difference between an internal temperature of the sauna room and a target temperature threshold value belongs and a zone to which an external temperature of the sauna room belongs, limits an integral term accumulation amount between a set upper limit and a set lower limit by matching with an integral limiting strategy, activates integral term accumulation when the difference between the internal temperature of the sauna room and the target temperature threshold value is greater than 0, and stops accumulation when the difference is less than or equal to 0.
10. The dynamic adjustment method of a sauna room multi-mode intelligent controller according to claim 9, wherein the low temperature compensation strategy refers to loading a low temperature compensation parameter set in a pre-calibration parameter set table of a gain scheduling mechanism when the external temperature of the sauna room is lower than a low temperature compensation threshold by 5 ℃, and prolonging the heating time to compensate for heat dissipation loss.

Description

Dynamic adjustment method of multi-mode intelligent controller of sauna room Technical Field The invention belongs to the technical field of sauna room controllers, and particularly relates to a dynamic adjustment method of a sauna room multi-mode intelligent controller. Background The sauna room temperature control system belongs to the field of industrial thermal closed-loop control, and the traditional implementation mode relies on a proportional-integral-derivative controller to perform feedback adjustment on the deviation between the measured temperature and the target temperature, and is widely deployed in application scenes such as commercial sauna equipment, household infrared sauna rooms, steam bathrooms and the like by combining a solid-state relay or a pulse width modulation circuit to drive an electric heating element. The prior commercial controller generally adopts a fixed parameter proportional-integral-derivative control strategy, and part of high-end products are subjected to fuzzy control or table-look-up gain switching so as to cope with different working conditions. However, the above conventional schemes all belong to a pure feedback control paradigm, and the control decision only depends on the temperature error at the current sampling time, and cannot model or predict the future heating track. In a sauna room thermodynamic system, the thermal inertia of a heating element is large, the thermal capacity of a cavity body is obviously changed along with the change of a sealing state, boundary condition drift is caused by fluctuation of the temperature of an external environment, and the factors jointly cause continuous output of high power due to large temperature difference in the initial temperature rising stage of simple feedback control, and serious overshoot is caused by accumulation of the thermal inertia when the temperature approaches to a target temperature, so that the integral saturation problem further worsens the regulation performance. In the current intelligent control of sauna room, because the dynamic characteristics of a thermodynamic system are complex, system parameters continuously drift along with the aging of a heating element and the change of the sealing performance of a cavity, the traditional proportional-integral-derivative controller lacks forward sensing capability on the heating trend, and can not incorporate the prediction on future temperature tracks in a control decision, so that the power regulation is always in a passive response state, and the prospective power optimization can not be realized. That is, in the prior art, there is a technical problem that a sauna room temperature control system cannot predict future trend of a heating process in advance under a dynamic thermal environment, resulting in delay or overshoot of heating power adjustment. Disclosure of Invention In view of the above, the invention provides a dynamic adjustment method of a multi-mode intelligent controller of a sauna room, which can solve the technical problems that a sauna room temperature control system cannot predict the future trend of a heating process in a forward looking manner under a dynamic thermal environment, and the heating power is adjusted in a delayed or overshoot manner in the prior art. The invention provides a dynamic adjustment method of a multi-mode intelligent controller of a sauna room, which comprises the following steps: The main control module respectively acquires the internal temperature of the sauna room, the self temperature of the controller and the external temperature of the sauna room through an environmental temperature sensor, a controller temperature sensor and an external temperature sensor, continuously acquires three temperature data by taking 100ms as a sampling interval, compresses the three temperature data through a self-adaptive sampling compression algorithm and stores the compressed three temperature data in the external serial peripheral interface flash memory chip; The main control module reads a sauna configuration mode selected by a user through the man-machine interaction module, and activates a corresponding relay output interface and a pulse width modulation dimming interface according to the mode self-adaptive matching logic to complete equipment linkage configuration; The main control module inputs the internal temperature of the sauna room, the self temperature of the controller, the external temperature of the sauna room and a target temperature threshold set by a user into a thermal prediction control model, forward rolls in a latent space to predict a future temperature track sequence by the thermal prediction control model, and outputs an optimal heating power instruction at the current moment according to the deviation between the future temperature track sequence and the target temperature threshold and the minimum feedforward power reference value of entropy production; The main control module is based on an optim