Precise temperature control heating uniform intelligent adjusting method and system for phase change heat storage material

Abstract

The invention discloses an intelligent uniform heating adjustment method and system for precise temperature control of a phase change heat storage material, and relates to the technical field of intelligent heating adjustment. Temperature distribution and solar radiation intensity of a heat storage unit are collected in real time, the temperature gradient change trend is predicted, and a phase change abnormal unit is identified; the method comprises the steps that phase change abnormal units are obtained, energy distribution weights are optimized according to the heat charging state difference of the phase change abnormal units, an energy distribution weight coefficient is obtained, then the heat medium flow and the heat dissipation strategy are dynamically adjusted according to the energy distribution weight coefficient and a corresponding flow control instruction, and meanwhile the solar radiation intensity change trend and the indoor temperature requirement are combined. According to the invention, the fine regulation and control phase change process of the phase change heat storage material is realized, the precise regulation of the multi-unit temperature gradient and the dynamic optimization of energy distribution are realized, the uniform temperature distribution is ensured, and the heat energy transfer efficiency is optimized, so that the heat energy utilization efficiency and stability of the system are remarkably improved, and efficient and intelligent heat energy management is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent heating regulation, and in particular to a heating uniform intelligent regulation method and system with precise temperature control of phase change heat storage materials. BACKGROUND

[0002] Solar energy, as a clean energy, is increasingly valued in indoor heating and energy storage. Its efficient utilization is crucial for energy saving and emission reduction and improving living comfort. Reasonable regulation of solar energy collection, storage and release can effectively respond to energy fluctuations and changes in user demand, ensuring stable operation of the heating system. However, current solar heating systems have significant limitations in practical application. Many systems are difficult to flexibly adjust according to dynamic changes in solar radiation and indoor temperature demand, resulting in uneven energy distribution, overheating or overcooling in some areas, affecting heating comfort and system efficiency. In addition, existing solutions lack fine management in multi-unit collaborative control, making it difficult to coordinate between different heat storage units. The core challenge is how to achieve uniform heating of multi-unit heat storage systems through precise temperature gradient control. Phase change heat storage materials are widely used due to their high energy storage density and stable heat release characteristics, but their phase change process is greatly affected by solar radiation intensity and indoor demand fluctuations, leading to uneven temperature distribution between heat storage units. For example, in the early morning of winter, when solar radiation is weak, some heat storage units may not complete the phase change due to insufficient energy input, while other units may waste energy due to excessive heating. This unevenness not only reduces heating effectiveness, but also increases system complexity. Further, the lack of real-time monitoring and intelligent regulation mechanisms makes it difficult for the system to automatically optimize energy distribution according to dynamic changes, thereby affecting the stability of overall heating and user experience.

[0003] Therefore, how to fine-tune the phase change process to achieve precise regulation of multi-unit temperature gradients and dynamic optimization of energy distribution becomes a key issue in improving heating uniformity and thermal energy transfer efficiency. SUMMARY

[0004] The present application provides a heating uniform intelligent regulation method and system with precise temperature control of phase change heat storage materials to fine-tune the phase change process, achieve precise regulation of multi-unit temperature gradients and dynamic optimization of energy distribution, and improve heating uniformity and thermal energy transfer efficiency.

[0005] The present application provides a heating uniform intelligent regulation method with precise temperature control of phase change heat storage materials, executed by a computer, comprising:

[0006] Based on real-time temperature data of the phase change material in each heat storage unit and solar radiation intensity information, determine the temperature distribution state of each heat storage unit;

[0007] Based on the temperature distribution state, the Kalman filtering algorithm is used to predict the temperature gradient change trend of each heat storage unit, and a target unit list of abnormal phase change process of the heat storage unit is determined;

[0008] Based on the heat charging state difference of each heat storage unit in the target unit list, a particle swarm optimization algorithm is used to calculate an energy distribution scheme, and an energy distribution weight coefficient of each heat storage unit is obtained;

[0009] Based on the energy distribution weight coefficient, the heat medium flow distribution of each heat storage unit is adjusted through an intelligent valve control module to obtain a flow control instruction, wherein the flow control instruction includes heat medium flow opening degree increase or decrease of the heat storage unit.

[0010] Based on the flow control instruction, in combination with the solar radiation intensity information and indoor temperature demand data, a fuzzy control algorithm is used to adjust the heat storage preparation state or heat energy release strategy of each heat storage unit to obtain dynamic adjustment execution parameters.

[0011] Based on the dynamic adjustment execution parameters, the heat medium circulation module is driven to execute flow direction adjustment to adjust the heat medium circulation speed and flow direction distribution of each heat storage unit.

[0012] According to the heating uniform intelligent adjustment method for precise temperature control of phase change heat storage material provided by the application, based on the temperature distribution state, the Kalman filtering algorithm is used to predict the temperature gradient change trend of each heat storage unit, and a target unit list of abnormal phase change process of the heat storage unit is determined, including:

[0013] Based on the temperature distribution state, the Kalman filtering algorithm is used to process the temperature distribution state, predict the temperature gradient change trend of each heat storage unit, and obtain a predicted temperature gradient sequence.

[0014] Based on the predicted temperature gradient sequence, the temperature gradient change rate of each heat storage unit is calculated to obtain a change rate sequence.

[0015] The change rate sequence and the preset change rate threshold are compared to determine the heat storage unit with abnormal phase change process, and an abnormal unit set is obtained.

[0016] Based on the unit identification information of the abnormal unit in the abnormal unit set, the target unit list is generated.

[0017] According to the heating uniform intelligent adjustment method for precise temperature control of phase change heat storage material provided by the application, based on the heat charging state difference of each heat storage unit in the target unit list, a particle swarm optimization algorithm is used to calculate an energy distribution scheme, and an energy distribution weight coefficient of each heat storage unit is obtained, including:

[0018] determine a heat charging state of each heat storage unit and a heat charging state difference corresponding to the heat charging state based on real-time temperature data of each heat storage unit in the target unit list;

[0019] determine a heat energy input quantity ratio based on the heat charging state difference, and obtain an adjustment requirement of each heat storage unit;

[0020] based on the adjustment requirement, calculate an initial energy distribution weight coefficient of each heat storage unit by using a particle swarm optimization algorithm;

[0021] based on the initial energy distribution weight coefficient, input into a recurrent neural network model for prediction to obtain an energy distribution scheme of each heat storage unit;

[0022] based on the energy distribution scheme, calculate a heat energy input quantity and a heat dissipation adjustment quantity of each heat storage unit to obtain an energy distribution weight coefficient of each heat storage unit.

[0023] According to the heating uniform intelligent adjustment method for precise temperature control of the phase change heat storage material provided by the application, based on the energy distribution weight coefficient, the heat medium flow distribution of each heat storage unit is adjusted by an intelligent adjustment valve control module to obtain a flow control instruction, which includes:

[0024] if the energy distribution weight coefficient is greater than a preset weight threshold, a first control signal for increasing the valve opening degree is generated;

[0025] if the energy distribution weight coefficient is less than or equal to the preset weight threshold, a second control signal for reducing the valve opening degree is generated;

[0026] based on the first control signal or the second control signal, K-means algorithm is used for cluster analysis to determine a flow distribution mode;

[0027] based on the flow distribution mode and real-time energy requirement, the heat medium flow distribution ratio of each heat storage unit is adjusted to generate an optimized flow control instruction;

[0028] the optimized flow control instruction is executed by the intelligent adjustment valve control module to dynamically adjust the valve opening degree of each heat storage unit to obtain an actual flow distribution result;

[0029] based on the deviation between the actual flow distribution result and the expected energy distribution, a PID control algorithm is used to fine-tune the valve opening degree to obtain the flow control instruction.

[0030] The heating uniform intelligent adjustment method of the phase change heat storage material precise temperature control according to the application, based on the flow control instruction, combines the solar radiation intensity information and the indoor temperature demand data, adopts the fuzzy control algorithm to adjust the heat storage preparation state or the heat energy release strategy of each heat storage unit, obtains the dynamic adjustment execution parameter, including:

[0031] Based on the solar radiation intensity information and the indoor temperature demand data, the time series analysis method is used to determine the change trend of the solar radiation intensity.

[0032] If the change trend is an upward trend, based on the flow control instruction, the heat storage preparation state of each heat storage unit is adjusted through the fuzzy control algorithm to obtain the heat storage state adjustment parameter.

[0033] If the change trend is a downward trend, the heat energy release strategy is optimized through the linear regression algorithm to obtain the heat energy release parameter.

[0034] Through the real-time data processing module, the heat storage state adjustment parameter and the heat energy release parameter are fused to generate the dynamic adjustment execution parameter.

[0035] The heating uniform intelligent adjustment method of the phase change heat storage material precise temperature control according to the application further includes:

[0036] After adjusting the heat medium circulation speed and flow direction distribution of each heat storage unit, the real-time temperature data of the phase change material in each heat storage unit is monitored, and the temperature change is obtained based on the real-time temperature data to obtain a new temperature distribution state.

[0037] If the new temperature distribution state shows that there is local temperature fluctuation, the heat medium circulation speed and flow direction distribution are adjusted in real time to determine the real-time heat charging state of the heat storage unit.

[0038] Based on the real-time heat charging state and the temperature distribution uniformization target, the working mode of the solar collector and the phase change sequence of the heat storage unit are adjusted through the feedback control mechanism to obtain system control strategy parameters.

[0039] The solar collector is connected to the heat storage unit to provide heat energy for the heat storage unit, and the system control strategy parameters are used to control the working mode of the solar collector and the phase change sequence of the heat storage unit, so that the real-time heat charging state of the heat storage unit reaches the temperature distribution uniformization target.

[0040] The heating uniform intelligent adjustment method of the phase change heat storage material precise temperature control according to the application, if the new temperature distribution state shows that there is local temperature fluctuation, the heat medium circulation speed and flow direction distribution are adjusted in real time to determine the real-time heat charging state of the heat storage unit, including:

[0041] If the new temperature distribution state shows that there is local temperature fluctuation, a preset control algorithm is used to adjust the heat medium circulation speed to determine a new circulation speed parameter;

[0042] Based on the adjusted circulation speed parameter, a heat medium flow direction distribution ratio is calculated to obtain a flow direction distribution scheme;

[0043] Based on the flow direction distribution scheme, the heat medium circulation module is driven to perform flow direction adjustment to determine the real-time heat charging state of the heat storage unit.

[0044] The application also provides a heating uniform intelligent adjustment system for precise temperature control of phase change heat storage materials, comprising:

[0045] A temperature distribution determination module is configured to determine the temperature distribution state of each heat storage unit based on real-time temperature data of the phase change material in each heat storage unit and solar radiation intensity information;

[0046] An anomaly determination module is configured to predict the temperature gradient change trend of each heat storage unit based on the temperature distribution state by using a Kalman filtering algorithm, and determine a target unit list of phase change process anomalies of the heat storage unit;

[0047] An energy distribution module is configured to calculate an energy distribution scheme by using a particle swarm optimization algorithm based on the heat charging state difference of each heat storage unit in the target unit list, and obtain energy distribution weight coefficients of each heat storage unit;

[0048] A flow adjustment module is configured to adjust the heat medium flow distribution of each heat storage unit by an intelligent valve control module based on the energy distribution weight coefficients to obtain flow control instructions, wherein the flow control instructions include heat medium flow opening degree increase or decrease of the heat storage unit;

[0049] An execution parameter determination module is configured to adjust the heat storage preparation state or heat energy release strategy of each heat storage unit by using a fuzzy control algorithm based on the flow control instructions, in combination with the solar radiation intensity information and indoor temperature demand data, to obtain dynamic adjustment execution parameters;

[0050] A heat medium adjustment module is configured to drive a heat medium circulation module to perform flow direction adjustment based on the dynamic adjustment execution parameters to adjust the heat medium circulation speed and flow direction distribution of each heat storage unit.

[0051] This invention discloses a method and system for precise temperature control of phase change thermal storage materials to achieve uniform and intelligent heating. Addressing the problems of uneven heat distribution, abnormal phase change processes, and low energy utilization efficiency in solar thermal storage systems, the method collects real-time data on the temperature distribution of the thermal storage units and solar radiation intensity to predict temperature gradient trends, identify abnormal phase change units, and obtain a target unit list. Based on the differences in the charging states of the abnormal phase change units in the target unit list, the energy distribution weights are optimized to obtain energy distribution weight coefficients. Then, based on the energy distribution weight coefficients and corresponding flow control commands, the heat transfer medium flow rate and heat dissipation strategy are dynamically adjusted. Simultaneously, by combining the solar radiation intensity change trend and indoor temperature requirements, the method achieves precise control of the phase change process of the phase change thermal storage material, enabling precise adjustment of the temperature gradient across multiple units and dynamic optimization of energy distribution. This ensures uniform temperature distribution, optimizes heat transfer efficiency, and significantly improves the system's thermal energy utilization efficiency and stability, achieving efficient and intelligent thermal energy management. Attached Figure Description

[0052] Figure 1 This is one of the flowcharts of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in the embodiments of the present invention.

[0053] Figure 2 This is the second flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention.

[0054] Figure 3 This is the third flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention.

[0055] Figure 4 This is the fourth flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention.

[0056] Figure 5 This is the fifth flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention.

[0057] Figure 6 This is the sixth flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention.

[0058] Figure 7 This is the seventh flowchart of the intelligent adjustment method for precise temperature control and uniform heating of phase change thermal storage materials provided in this embodiment of the invention. Detailed Implementation

[0059] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0060] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application. Figure 1 The embodiments of the present application provide a heating uniform intelligent adjustment method for precise temperature control of phase change heat storage materials, comprising the following steps:

[0061] Step 100, based on the real-time temperature data of the phase change material in each heat storage unit and the solar radiation intensity information, the temperature distribution state of each heat storage unit is determined;

[0062] The phase change material is widely used in heat storage units due to its high heat storage density and temperature stability, to store and release heat energy, thereby optimizing energy utilization. Through the temperature sensor deployed in each heat storage unit, the real-time temperature data of the phase change material is continuously collected by the temperature sensor, providing instantaneous heat state information inside each unit. At the same time, since solar radiation will directly affect the heat input of the heat storage unit, which may cause local overheating or uneven heat distribution, therefore, by integrating these real-time temperature data and solar radiation intensity information, a dynamic heat model is constructed, so as to accurately infer the temperature distribution state of each heat storage unit.

[0063] The process of analyzing the temperature distribution state of each heat storage unit involves data fusion and analysis, in which the real-time temperature data reflects the thermal behavior of the phase change material in the phase change process, such as melting or solidification state, and the solar radiation intensity information provides the context of the environmental heat load. For example, the real-time temperature data and solar radiation intensity information can be processed by machine learning or thermal dynamics model to evaluate the temperature distribution state of each heat storage unit, wherein the temperature distribution state includes thermal gradient, heat flow distribution, and potential hot spots or cold zones. Finally, after data analysis, a comprehensive temperature distribution state is obtained, which can represent the temperature distribution state of each heat storage unit through a temperature distribution map, identifying the thermal state of each heat storage unit, such as whether it is in a phase change platform, overheating or underheating state, thereby providing a basis for subsequent intelligent adjustment.

[0064] Step 200, based on the temperature distribution state, a Kalman filter algorithm is used to predict the temperature gradient change trend of each heat storage unit, and a target unit list of phase change process anomalies of the heat storage unit is determined;

[0065] After obtaining and analyzing the temperature distribution state of each thermal storage unit, the Kalman filtering algorithm is introduced to predict the temperature gradient change trend of each thermal storage unit in the future short time domain, using the temperature distribution state as the initial input. The Kalman filtering algorithm, as an optimal recursive data processing algorithm, can efficiently fuse the temperature distribution state with noise and the prediction model. Through the cycle iteration process of prediction and correction, the estimation of the internal state of each thermal storage unit is continuously optimized, and the temperature gradient and its change rate of the core of each thermal storage unit are obtained. The prediction model is a mathematical model that describes the thermal dynamic characteristics of the thermal storage unit, and is obtained based on the temperature distribution state training set and the corresponding temperature gradient change rate training set.

[0066] Through the operation of the Kalman filtering algorithm, a prediction trend of how the temperature of each thermal storage unit evolves is generated. The prediction trend is used to represent the thermal behavior of the phase change material. Through the prediction trend, it can be judged whether the temperature change is in the normal phase change platform period with relatively stable temperature, a large amount of latent heat is absorbed or released, or an abnormal rapid heating or cooling occurs. By comparing and analyzing the prediction trend with the ideal thermophysical property curve of the phase change material, those thermal storage units whose phase change process deviates from the expected mode can be identified. For example, if the temperature gradient change trend of a certain thermal storage unit is predicted to deviate from the phase change platform too early, or the heating rate is significantly higher than the model prediction value, it may indicate that the unit has abnormal conditions such as material aging, packaging failure or unexpected local thermal interference. Finally, based on the analysis results, a target unit list of phase change process abnormalities is generated, which lists the identification of thermal storage units with potential faults or performance deviations, and usually also includes a preliminary judgment of the type of abnormality.

[0067] In step 300, based on the differences in the heat charging state of each thermal storage unit in the target unit list, a particle swarm optimization algorithm is used to calculate an energy distribution scheme, and the energy distribution weight coefficients of each thermal storage unit are obtained.

[0068] After generating the target unit list of phase change process abnormalities, energy distribution is performed. For the abnormal thermal storage units identified in the target list, based on the different heat charging states of each unit in the target list, such as some units may be in the initial phase of under-heating, while others may need to release energy due to overheating, the optimal energy distribution scheme is dynamically calculated. To calculate the optimal energy distribution scheme, the particle swarm optimization algorithm, a powerful swarm intelligence optimization algorithm, is used. The particle swarm optimization algorithm simulates the social behavior of bird or fish groups, and finds the optimal solution through the cooperative search of a group of particles in the solution space.

[0069] It is to be understood that each particle represents a potential energy distribution scheme vector, and the dimension of the particle corresponds to the number of thermal storage units that need to be regulated. The optimization objective of the particle swarm optimization algorithm is the fitness function, which is used to simultaneously weigh multiple key performance indicators, mainly for minimizing the temperature difference between all thermal storage units to ensure uniform heating, secondly for maximizing the overall energy utilization efficiency of the entire system, while also meeting physical constraints such as heat source output limits, unit safety temperature thresholds, etc. During the iteration process, the particle swarm constantly updates the speed and position of all particles by tracking the individual historical optimal position and the global optimal position of the group, thereby gradually guiding the entire population to converge to the optimal solution region. After sufficient iteration and optimization of the particle swarm optimization algorithm, a globally optimal or approximately optimal energy distribution scheme will be determined from the search space. The output of this energy distribution scheme is a set of energy distribution weight coefficients for each thermal storage unit. Among them, the energy distribution weight coefficient is a normalized value between 0 and 1, which reflects the relative proportion of the total energy that should be allocated to the thermal storage unit in the next regulation period. A higher coefficient means that more energy input is needed to correct its underheating state or suppress its abnormal trend, while a lower or zero coefficient indicates that its current thermal state has reached an ideal state or needs to be limited in energy supply.

[0070] At step 400, based on the energy distribution weight coefficients, the intelligent regulating valve control module adjusts the flow distribution of the heat medium of each thermal storage unit to obtain flow control instructions, wherein the flow control instructions include increasing or decreasing the flow opening of the heat medium of the thermal storage unit.

[0071] After calculating the energy distribution weight coefficients of each thermal storage unit by the particle swarm optimization algorithm, the weight coefficients representing abstract energy demand obtained in the previous step are converted into direct and operable control commands for specific execution elements in the heating pipeline. The conversion is realized by the intelligent regulating valve control module, which serves as a key execution interface connecting algorithm decision and physical implementation, and is responsible for regulating the flow of heat medium through each thermal storage unit. The control logic of the intelligent regulating valve control module is directly set according to the energy distribution weight coefficients.

[0072] The intelligent regulating valve control module will independently calculate and generate a corresponding flow control instruction for each heat storage unit in the target unit list. The essence of the flow control instruction is to drive the action command of the regulating valve installed on the corresponding branch. Its specific content is to command the valve opening to increase, decrease, or remain in the current state. For example, for an under-heated unit assigned a high weight coefficient, the intelligent regulating valve control module will calculate an instruction to increase its valve opening, thereby allowing more high-temperature heat medium to flow into its heat exchanger and accelerating its heating process. Conversely, for a unit with a weight coefficient of zero or close to zero, the module will generate an instruction to reduce or even close its valve to limit or cut off its energy supply, prevent it from overheating, and direct energy flow to units that need it more.

[0073] Step 500: Based on the flow control instruction, combine the solar radiation intensity information and indoor temperature demand data, and use a fuzzy control algorithm to adjust the heat storage preparation state or heat energy release strategy of each heat storage unit to obtain dynamic adjustment execution parameters.

[0074] After generating the flow control instruction, a fuzzy control algorithm with advanced decision-making capabilities is introduced. The flow control instruction serves as the basic execution framework, while the real-time changes in solar radiation intensity information and user-set indoor temperature demand data are integrated as two key inputs. The fuzzy control algorithm dynamically adjusts the operation strategy of the entire heating system, aiming to optimize the energy efficiency and comfort level of the entire system and achieve the set indoor temperature demand, which is the ultimate service goal of the system.

[0075] The fuzzy control algorithm is good at handling complex systems with multiple inputs, uncertainties, and nonlinear characteristics. It takes solar radiation intensity and indoor temperature demand as input variables and makes inferences and decisions through a set of pre-set fuzzy rules based on expert knowledge. For example, if the solar radiation is strong and the indoor temperature is lower than the set value, the heat energy release intensity will be moderately reduced. The output of the fuzzy control algorithm is a further fine-tuning and optimization of the current energy distribution strategy, dynamically adjusting the heat storage preparation state or heat energy release strategy of each heat storage unit.

[0076] Step 600: Based on the dynamic adjustment execution parameters, drive the heat medium circulation module to execute flow direction adjustment to adjust the heat medium circulation speed and flow direction distribution of each heat storage unit.

[0077] After the fuzzy control algorithm generates a set of highly optimized dynamic adjustment execution parameters, these digitized decision instructions are converted into actual actions for the heating hardware devices, thereby realizing the final control of the heat energy delivery process. Specifically, it is executed through the heat medium circulation module, which can include the core power and distribution unit of the variable frequency water pump, electric three-way valve, shunt collector and corresponding pipeline. Its function is to respond to the instructions of the upper controller, manage the total flow, pressure and flow direction comprehensively, and execute the established energy distribution strategy.

[0078] Based on the received dynamic adjustment execution parameters, the core controller of the heat medium circulation module will interpret the adjustment of the branch heat medium circulation speed and the adjustment of the heat medium flow direction distribution across the unit or across the region. In the implementation of the adjustment of the branch heat medium circulation speed, the variable frequency water pump is driven, and the total flow rate of the heat medium is changed by adjusting the working frequency of the variable frequency water pump, so as to control the total heating capacity and the circulation efficiency. At the same time, in the implementation of the adjustment of the heat medium flow direction distribution across the unit or across the region, the electric regulating valve installed at the key node, such as the three-way valve or the independent branch valve, is driven, and the flow ratio of the heat medium in different heat storage unit branches is dynamically distributed by changing the opening or passage selection of the valve. For example, for the unit branch that needs to prioritize heat storage or additional heat supply, the instruction will drive the valve to increase its opening, and more main flow of heat medium can be guided to the path; and for the branch that needs to reduce heat supply, the valve opening will be reduced to limit the flow.

[0079] The application discloses a kind of phase change heat storage material precision temperature control Heating Uniform Intelligent Regulating Method and system, to the problem of uneven heat energy distribution, phase change process anomaly and energy utilization efficiency in solar heat storage system, by real-time acquisition heat storage unit temperature distribution and solar radiation intensity, predict temperature gradient variation trend, identify phase change abnormal unit, obtain target unit list, and according to the energy distribution weight coefficient of the heat charging state difference of phase change abnormal unit in target unit list, obtain energy distribution weight coefficient, then, according to energy distribution weight coefficient and corresponding flow control instruction, dynamically adjust heat medium flow and heat dissipation strategy, simultaneously, in combination with solar radiation intensity variation trend and indoor temperature demand, realize the fine regulation and control phase change process of phase change heat storage material, realize the precise regulation of multi-unit temperature gradient and the dynamic optimization of energy distribution, ensure that temperature distribution is uniform, optimize heat energy transfer efficiency, to significantly improve system heat energy utilization efficiency and stability, realize efficient intelligent heat energy management.

[0080] In one embodiment, please refer to Figure 2 Based on the temperature distribution state, the Kalman filtering algorithm is used to predict the temperature gradient variation trend of each heat storage unit, and the target unit list of the phase change process anomaly of the heat storage unit is determined, including:

[0081] Step 201, based on the temperature distribution state, the Kalman filtering algorithm is used to process the temperature distribution state, and the temperature gradient change trend of each thermal storage unit is predicted to obtain a predicted temperature gradient sequence;

[0082] Step 202, based on the predicted temperature gradient sequence, the temperature gradient change rate of each thermal storage unit is calculated to obtain a change rate sequence;

[0083] Step 203, comparing the change rate sequence with the preset change rate threshold, determining the thermal storage unit with abnormal phase change process, and obtaining an abnormal unit set;

[0084] Step 204, based on the unit identification information of the abnormal unit in the abnormal unit set, generating the target unit list.

[0085] The obtained temperature distribution state of each thermal storage unit is taken as the initial input, and the Kalman filtering algorithm is introduced to process this series of temperature distribution states with noise. The Kalman filtering algorithm dynamically fuses real-time measurement values and historical state prediction values through its optimal estimation algorithm, thereby filtering out interference and calculating the evolution path of the temperature gradient of each thermal storage unit in the future period of time, and outputting a smooth and high-confidence predicted temperature gradient sequence. Then, the predicted temperature gradient sequence is deeply analyzed, the difference between the predicted temperature gradients of adjacent time points in the predicted temperature gradient sequence is calculated, and the temperature gradient change rate corresponding to each thermal storage unit is obtained, and a change rate sequence is generated. The change rate sequence reflects the dynamic characteristics of the phase change process of each unit and is a key indicator for judging whether the behavior is normal or not.

[0086] Then, based on the change rate sequence, the temperature gradient change rate of each thermal storage unit is intelligently compared with the change rate threshold based on the ideal thermophysical properties of the phase change material. The preset change rate threshold defines the reasonable range of temperature change rate in the phase change process such as melting or solidification. If the change rate of a certain thermal storage unit continuously and significantly deviates from the range of the change rate threshold, for example, the change is too fast, indicating that the latent heat absorption or release is insufficient, and the change is too slow, which may indicate that the thermal resistance increases, then it is determined that there is an abnormal phase change process. All the identified abnormal thermal storage units form an abnormal unit set. Finally, according to the unit identification information of the abnormal unit in the abnormal unit set, the unique identification information of each abnormal unit in the abnormal unit set can be extracted, and a target unit list with clear structure can be automatically generated for subsequent direct call.

[0087] For example, assume that a thermal storage system contains 10 thermal storage units, the temperature data of each unit is collected by a sensor every minute, the initial temperature distribution [50.0, 52.0, 51.5, 53.0, 50.5, 49.8, 52.5, 51.0, 50.2, 54.0] Celsius, the goal is to predict the temperature gradient change trend of each unit using Kalman filter algorithm, and to determine whether there is a phase change process abnormality, and the preset temperature gradient change rate threshold is 0.5 Celsius / minute. First, the state vector of Kalman filter is defined as temperature and temperature change rate, the state transition matrix is F = [[1, 1], [0, 1]], the time step is 1 minute, the measurement matrix H = [1, 0], the process noise covariance Q = [[0.01, 0], [0, 0.01]], and the measurement noise covariance R = 0.1. Taking the first thermal storage unit as an example, the initial state vector = [50.0, 0.0], and the covariance matrix = [[1, 0], [0, 1]]. Through the Kalman filter prediction step, the next time state prediction = = [50.0, 0.0], and the covariance prediction = [[1.01, 1], [1, 1.01]]. Assuming that the next minute measurement temperature is 50.3 Celsius, the update step calculates the Kalman gain = [0.91, 0.91], the updated state = [50.27, 0.27], and the updated covariance , repeat this process for 5 minutes to obtain the temperature change rate sequence [0.27, 0.31, 0.35, 0.40, 0.45]. Calculate the temperature gradient change trend, use linear regression to fit the change rate, the slope is 0.045 Celsius / minute . If the threshold is 0.5 Celsius / minute, 0.45 does not exceed the threshold, and it is determined that the unit has no phase change abnormality. Repeat the above process for all units, if the change rate of the second unit reaches 0.52 Celsius / minute, which exceeds the threshold, it is included in the target unit list. Finally, the target unit list is unit 2, and the result is stored in the database for subsequent thermal management optimization call to ensure system stability.

[0088] This embodiment greatly improves the accuracy and anti-interference ability of state estimation by applying Kalman filter algorithm to temperature trend prediction; and by analyzing the gradient change rate instead of the absolute value of a single temperature, quantitative diagnosis of the dynamics of the phase change process itself is realized, which can accurately distinguish between normal environmental load changes and material itself or heat transfer link failures, greatly improving the depth and accuracy of fault diagnosis.

[0089] In one embodiment, refer to Figure 3, the energy distribution scheme is calculated by using a particle swarm optimization algorithm based on the charging state difference of each heat storage unit in the target unit list, to obtain the energy distribution weight coefficient of each heat storage unit, including:

[0090] Step 301, based on the real-time temperature data of each heat storage unit in the target unit list, the charging state of each heat storage unit is determined, and the charging state difference corresponding to the charging state is determined;

[0091] Step 302, based on the charging state difference, the heat energy input proportion is determined, and the adjustment requirement of each heat storage unit is obtained;

[0092] Step 303, based on the adjustment requirement, a particle swarm optimization algorithm is used to calculate the initial energy distribution weight coefficient of each heat storage unit;

[0093] Step 304, based on the initial energy distribution weight coefficient, input to the recurrent neural network model for prediction, and the energy distribution scheme of each heat storage unit is obtained;

[0094] Step 305, based on the energy distribution scheme, the heat energy input and heat dissipation adjustment amount of each heat storage unit are calculated, and the energy distribution weight coefficient of each heat storage unit is obtained.

[0095] The embodiment proposes a highly intelligent, adaptive and predictive energy distribution strategy generation mechanism, which takes the real-time temperature data of each abnormal heat storage unit in the target unit list as input, calculates the specific charging state of each heat storage unit by analyzing the deviation of the current temperature value from the ideal phase change temperature of the phase change material, such as "underheating", "charging", "overheating" or "saturation", and quantifies the charging state difference between different units according to the charging state. This charging state difference is the basis for subsequent non-uniform energy allocation.

[0096] Based on the determined charging state difference, it is further converted into a specific energy demand instruction, and a preliminary heat energy input proportion is allocated to units in different states according to the preset energy mapping rule, so as to determine the adjustment direction and amplitude required by each unit to achieve heat balance, that is, to form a quantitative adjustment requirement. Then, a particle swarm optimization algorithm is introduced to solve this multi-objective and multi-constrained optimization problem. The particle swarm optimization algorithm takes the highest total energy utilization efficiency and the smallest temperature difference between units as the optimization objective, takes the above adjustment requirement as the input, and calculates a set of optimal initial energy distribution weight coefficients of each heat storage unit by simulating the search behavior of group intelligence in the solution space.

[0097] Then, the initial energy allocation weight coefficient is input into a pre-trained recurrent neural network model, which can deeply learn the time sequence law of the system thermal dynamics, predict the possible effect of the current allocation scheme in the future short time domain by analyzing the historical energy allocation and temperature response data, and feedback optimize the initial weight coefficient, and finally output the energy allocation scheme. Finally, the energy allocation scheme is converted into a directly executable physical quantity, and according to the weight coefficient in the energy allocation scheme, the specific heat energy input and the necessary heat dissipation adjustment amount of each thermal storage unit in the next control period are calculated, so as to obtain the final energy allocation weight coefficient of each thermal storage unit.

[0098] The particle swarm optimization algorithm and the recurrent neural network are combined in the serial optimization architecture of the embodiment, the particle swarm optimization algorithm is responsible for quickly finding the global optimal solution, and the recurrent neural network has strong time sequence prediction ability, so that the advanced optimization of global optimality and dynamic prediction is combined, and the output energy allocation weight coefficient is the result of calculation and prediction, which meets the balance demand at the current moment, so that the whole control process is more smooth, accurate and efficient.

[0099] In one embodiment, referring to Figure 4 , the heat medium flow distribution of each thermal storage unit is adjusted by an intelligent valve control module based on the energy allocation weight coefficient to obtain a flow control instruction, including:

[0100] Step 401, if the energy allocation weight coefficient is greater than a preset weight threshold, a first control signal for increasing the valve opening degree is generated;

[0101] Step 402, if the energy allocation weight coefficient is less than or equal to the preset weight threshold, a second control signal for reducing the valve opening degree is generated;

[0102] Step 403, based on the first control signal or the second control signal, K-means algorithm is used for cluster analysis to determine the flow distribution mode;

[0103] Step 404, based on the flow distribution mode and the real-time energy demand, the heat medium flow distribution ratio of each thermal storage unit is adjusted to generate an optimized flow control instruction;

[0104] Step 405, the intelligent valve control module is used to execute the optimized flow control instruction to dynamically adjust the valve opening degree of each thermal storage unit to obtain an actual flow distribution result;

[0105] Step 406, based on the deviation between the actual flow distribution result and the expected energy allocation, a PID control algorithm is used to fine-tune the valve opening degree to obtain the flow control instruction.

[0106] First, the calculated energy distribution weight coefficient of each heat storage unit is compared with a preset weight threshold to determine whether flow regulation is needed, and a preliminary control signal is generated based on the comparison result: if the energy distribution weight coefficient of a heat storage unit is greater than the weight threshold, indicating that it needs to increase the heat energy input, a first control signal is generated to increase the valve opening of the pipeline; otherwise, if the energy distribution weight coefficient is less than or equal to the weight threshold, a second control signal is generated to reduce the valve opening to limit or reduce the energy supply.

[0107] After generating the preliminary control signal, a K-means clustering algorithm is introduced to analyze and summarize the first control signal or the second control signal. The K-means clustering algorithm automatically clusters all heat storage units according to the similarity of their control signals, thereby summarizing complex individual instructions into several typical flow distribution modes, such as global reinforcement heating mode, local compensation mode or heat preservation maintenance mode. This pattern recognition enables a macro understanding of the current system state and provides strategic guidance for subsequent regulation.

[0108] Based on the identified flow distribution mode and combined with the real-time updated energy demand data, the heat medium flow distribution ratio of each heat storage unit is dynamically fine-tuned to generate optimized and more coordinated flow control instructions. Then, the intelligent valve control module is used to execute the optimized flow control instructions to drive the actuators on each branch to change the valve opening, thereby achieving dynamic redistribution of heat medium flow and obtaining the actual flow distribution result. Due to actual factors such as pipeline characteristics and pressure fluctuations, there may be deviations between the actual flow and the expected distribution. Therefore, a PID control algorithm is introduced to continuously monitor the deviation between the actual flow distribution result and the expected energy distribution target, and use the powerful correction ability of the PID algorithm to perform real-time calculations on the deviation and output a slight adjustment of the valve opening, thereby continuously fine-tuning the control instructions online to obtain the flow control instructions. The algorithm principle of the PID control algorithm is to calculate a deviation value, which is the error between the expected target value and the actual measured value, and generate a control output based on the proportion, integral and differential of this deviation, so as to eliminate the deviation as quickly, smoothly and accurately as possible, and make the system stable at the target set value.

[0109] For example, the intelligent valve control system for adjusting heat medium flow based on energy distribution weight coefficient can achieve precise control through the following implementation method. First, the system collects the temperature and heat demand data of each heat storage unit in real time through sensors, assuming that the current temperatures of three heat storage units are 50°C, 55°C and 60°C, and the target temperature is 65°C. The energy demand weight coefficient of each unit is calculated. The weight coefficient algorithm is as follows:

[0110]

[0111] wherein, is 65 °C, is the temperature of each unit. Calculation = 0.5, = 0.333, =0.167. The standard weight coefficient is set to 0.3, if > 0.3, the corresponding valve opening is increased; if ≤ 0.3, the opening is reduced. The valve opening adjustment adopts a proportional control algorithm, and the formula of the proportional control algorithm is as follows:

[0112]

[0113] wherein, is a proportional coefficient set to 50, is 0.3. Calculation = 10%, = 1.65%, =-6.65%. Therefore, the unit 1 valve opening is increased by 10%, the unit 2 is increased by 1.65%, and the unit 3 is reduced by 6.65%. The system converts these opening changes into PWM signals to drive the servo motor to adjust the valve angle, ensuring accurate distribution of the heat medium flow. The flow sensor feedbacks the flow data in real time to verify whether the adjusted flow meets the expectation, and if the deviation exceeds 5%, the system further fine-tunes through the PID algorithm until the error is less than 2%.

[0114] The embodiment realizes the mode of control instructions by combining threshold judgment with cluster analysis, retains the accuracy of control, enhances the coordination and strategy of system operation, and avoids instruction conflicts; the K-means algorithm of unsupervised learning is used for control strategy induction, so that different working condition modes can be adaptively identified and adapted.

[0115] In one embodiment, please refer to Figure 5 , based on the flow control instruction, combined with the solar radiation intensity information and indoor temperature demand data, a fuzzy control algorithm is used to adjust the heat storage preparation state or heat energy release strategy of each heat storage unit, to obtain dynamic adjustment execution parameters, including:

[0116] Step 501, based on the solar radiation intensity information and the indoor temperature demand data, a time series analysis method is used to determine the change trend of the solar radiation intensity;

[0117] Step 502, if the change trend is an upward trend, based on the flow control instruction, the heat storage preparation state of each heat storage unit is adjusted by a fuzzy control algorithm to obtain heat storage state adjustment parameters;

[0118] Step 503, if the change trend is a downward trend, the heat energy release strategy is optimized by a linear regression algorithm to obtain heat energy release parameters;

[0119] Step 504, the dynamic adjustment execution parameters are generated by fusing the heat storage state adjustment parameters and the heat energy release parameters through a real-time data processing module.

[0120] First, the real-time collected solar radiation intensity information and the user set indoor temperature demand data are taken as core inputs, and a time series analysis method is used to process the solar radiation intensity data to mine the sequence pattern of historical and current data, so as to accurately infer the change trend of solar radiation intensity in a future period of time, such as a continuous upward, downward or stable trend. The time series analysis method can be an ARIMA model or an exponential smoothing method.

[0121] Based on the change trend of solar radiation intensity, a differentiated optimization strategy is performed. Specifically, if the analysis determines that the trend is an upward trend, indicating that solar energy will soon increase, the original flow control instruction will not be mechanically executed, but a fuzzy control algorithm is used to dynamically adjust the strategy. The fuzzy control algorithm simulates the decision-making thinking of human experts based on a conditional rule base, considers the rising solar radiation intensity, the current heat storage state of the heat storage unit and the indoor temperature demand, and outputs adjustment parameters for the heat storage preparation state of each heat storage unit, such as temporarily suspending electric auxiliary heating and reducing the target heat storage temperature, to reserve space for the coming sufficient solar energy, thereby achieving energy saving.

[0122] On the contrary, if the trend is determined to be a downward trend, indicating that the external heat source will soon weaken or disappear, a linear regression algorithm is called. The linear regression algorithm establishes a linear relationship model between heat demand and time and other factors to more accurately predict the load change in the future period and calculate heat energy release parameters, such as starting to release heat mildly in advance and adjusting the heat release rate, to smooth the temperature transition and prevent large fluctuations in indoor temperature due to external environmental mutations, thereby improving comfort. Finally, the heat storage state adjustment parameters or heat energy release parameters generated by different strategies are coordinated by a real-time data processing module to ensure the consistency and feasibility of the parameters when different strategies are switched or run in parallel, and a set of unified, coordinated and directly executable dynamic adjustment execution parameters are generated.

[0123] The embodiment realizes the collaborative operation with the change of the sun by predictive perception of the external environment through time series analysis, changes from passive response to active regulation, greatly reduces the consumption of traditional energy; for the two different trends of rising and falling, fuzzy control is used to process the uncertain and complex energy saving preparation problem, linear regression is used to process the relatively clear trend of load prediction problem, the advantages of algorithm and the precise matching of business scene are realized, and the scientificity and efficiency of decision-making are improved.

[0124] In one embodiment, referring to Figure 6 , further comprising:

[0125] Step 700, after that, the real-time temperature data of the phase change material in each heat storage unit is monitored, and the temperature change is obtained based on the real-time temperature data, and a new temperature distribution state is obtained;

[0126] Step 800, if the new temperature distribution state shows that there is local temperature fluctuation, the circulating speed and flow direction distribution of the heat medium are adjusted in real time, and the real-time heat charging state of the heat storage unit is determined;

[0127] Step 900, based on the real-time heat charging state and the temperature distribution uniformization target, the working mode of the solar collector and the phase change timing of the heat storage unit are adjusted through the feedback control mechanism, and the system control strategy parameters are obtained;

[0128] Wherein, the solar collector is connected with the heat storage unit, and provides heat energy for the heat storage unit, and the system control strategy parameters are used to control the working mode of the solar collector and the phase change timing of the heat storage unit, so that the real-time heat charging state of the heat storage unit reaches the temperature distribution uniformization target.

[0129] After adjusting the circulating speed and flow direction distribution of the heat medium of each heat storage unit, a new round of monitoring cycle is started, the real-time temperature data of the phase change material in each heat storage unit is continuously collected through a high-precision temperature sensor network, and the temperature change rate and direction of each unit are obtained through real-time calculation and analysis of these time series data, so that a new temperature distribution state map reflecting the latest system state is constructed, and a new temperature distribution state is obtained. The new temperature distribution state is scanned and analyzed in real time, if the new temperature distribution state is detected to exist local temperature fluctuation which does not conform to the uniform heating target, such as overheating or slow heating of individual units, the regulation mechanism is triggered, the circulating speed and flow direction distribution of the heat medium are adjusted in real time, the local temperature fluctuation is tried to be suppressed, and the current real-time heat charging state of the unit is accurately determined according to the real-time temperature data and its change trend.

[0130] The real-time charging state and the global temperature distribution uniformization target are input into an advanced feedback control mechanism, and the core decision of the feedback control mechanism is to coordinate the working mode of the solar collector providing heat source for the heat storage unit, including adjusting the collector loop flow, starting and stopping the auxiliary heater, and the phase change sequence of each heat storage unit, or controlling the order and rate of heat storage or heat release, and outputting the system control strategy parameters through complex optimization calculation.

[0131] Further, the system control strategy parameters can also be obtained by the following method: obtaining real-time heat input data from the solar collector, combining the temperature distribution of the heat storage unit, calculating the heat transfer efficiency, and obtaining the initial heat distribution state. If the initial heat distribution state is lower than the preset transfer efficiency threshold, adjust the working mode of the solar collector through the feedback control mechanism to determine the optimized heat input parameters. According to the optimized heat input parameters, the phase change sequence of the phase change material in the next cycle is predicted by using linear regression algorithm, and the phase change sequence adjustment scheme is obtained. Through the phase change sequence adjustment scheme, the heat release rhythm of each heat storage unit is controlled, the heat transfer efficiency between units is calculated, and the adjusted heat distribution state is obtained. If the adjusted heat distribution state meets the preset uniformization threshold, the control strategy parameters of the next cycle are generated according to the current working mode and the phase change sequence. Obtain the temperature variation trend from the adjusted heat distribution state, analyze the heat transfer characteristics of each heat storage unit by using K-means clustering algorithm, and obtain the heat transfer optimization direction between units. According to the heat transfer optimization direction, update the adjustment parameters of the feedback control mechanism, and generate the system control strategy parameters of the next cycle.

[0132] In this embodiment, the system can continuously approach and maintain the optimal operating state in dynamic changes, greatly improving the stability and reliability of the system; the operation strategy of the solar collector and the phase change sequence management of the heat storage unit are optimized, breaking the independent control mode of the heat source and the heat storage unit in the traditional system. This coordination aims to maximize the global energy efficiency, and flexibly determines whether to prioritize the use of solar energy or to mobilize the energy balance between the heat storage units, thereby realizing the maximum consumption of solar energy and significant improvement of the overall energy efficiency of the system under the premise of ensuring uniform heating.

[0133] In one embodiment, please refer to Figure 7 If the new temperature distribution state shows local temperature fluctuations, the heat medium circulation speed and flow direction distribution are adjusted in real time to determine the real-time charging state of the heat storage unit, including:

[0134] Step 801, if the new temperature distribution state shows local temperature fluctuations, adjust the heat medium circulation speed by using a preset control algorithm to determine the new circulation speed parameter;

[0135] Step 802, based on the adjusted circulation speed parameter, calculate the heat medium flow direction distribution ratio, and obtain a flow direction distribution scheme;

[0136] Step 803, based on the flow direction distribution scheme, drive the heat medium circulation module to perform flow direction adjustment to determine the real-time heat charging state of the heat storage unit.

[0137] When a new temperature distribution state with local temperature fluctuations is monitored, a preset advanced control algorithm, such as a fuzzy PID control or an adaptive control algorithm, is triggered immediately. The control algorithm takes eliminating local fluctuations and restoring temperature uniformity as the core target, quickly outputs an adjustment amount for the total heat medium circulation speed through real-time calculation, and thus determines a new circulation speed parameter that can adapt to the current heat load demand. Based on the adjusted circulation speed parameter, a more refined flow direction distribution decision is further executed, and according to the latest temperature state of each heat storage unit and the global uniformity target, an ideal proportion of heat medium flow to each branch or each heat storage unit is dynamically calculated through an embedded optimization calculation model, and a specific flow direction distribution scheme is generated accordingly. The flow direction distribution scheme is used to compensate for the identified local fluctuations, and the flow ratio needs to be increased or decreased between different pipelines.

[0138] Finally, the flow direction distribution scheme is converted into specific execution instructions to drive the key actuators in the heat medium circulation module to act in coordination to actually change the flow direction of the heat medium in the pipeline and the flow distribution of each branch. At the same time, by continuously monitoring the temperature feedback of each unit after execution, the control effect is confirmed, and the real-time heat charging state of each heat storage unit under the new flow condition is accurately determined, which provides an important state basis for whether the stable equilibrium is reached or whether the next round of regulation needs to be started.

[0139] For example, to achieve dynamic adjustment of execution parameters to drive the phase change process of each heat storage unit for coordinated control, the system first acquires temperature data of a phase change material (PCM) during the solid-liquid conversion process through an embedded sensor array. Assuming that a paraffin-based phase change material with a melting point of 58°C is used, the sensor acquires temperature at an interval of 0.1 seconds with an accuracy of ±0.2°C. The collected data is smoothed by a Kalman filtering algorithm, and the filtering formula is:

[0140]

[0141] wherein, is the Kalman gain, is the observation value, is the observation matrix, and the initial state Based on the historical data mean. After filtering, if the temperature fluctuation of a certain heat storage unit is detected to exceed ±1°C, for example, the temperature of a certain unit oscillates between 57.8°C and 59.2°C, the system judges that the phase change process is unstable, and triggers the heat medium circulation speed adjustment. The heat medium circulation speed is calculated through a proportional-integral-derivative (PID) control algorithm. Assuming that the temperature of a certain unit is 59°C and the error is 1°C, the heat medium flow rate needs to be increased by 10%, from 2L / min to 2.2L / min. At the same time, the flow distribution is optimized through a valve control matrix. Based on the flow distribution formula, the heat medium flow rate is determined according to the proportion of the temperature deviation of each unit to the total temperature deviation. If the temperature deviation of a certain unit accounts for 30% of the total temperature deviation, 30% of the heat medium flow rate is allocated to this unit. The system then analyzes the temperature field uniformity through infrared thermal imaging and calculates the standard deviation of the temperature distribution, with a target standard deviation of less than 0.5°C. If a certain area is detected to have a standard deviation of 0.7°C, the system iteratively adjusts the flow rate and flow direction until the standard deviation is reduced to 0.4°C, confirming that the uniformity target has been achieved.

[0142] In this embodiment, the local anomaly is perceived and responded to at a millisecond level, greatly shortening the regulation lag, effectively suppressing the expansion of temperature waves, and significantly improving the heating uniformity and comfort. The hierarchical regulation strategy is adopted to quickly stabilize the overall energy supply level by adjusting the total flow rate, and to accurately eliminate local imbalance by fine distribution of flow direction, balancing the response speed and control accuracy.

[0143] The phase change heat storage material precise temperature control and heating uniformity intelligent adjustment system provided by the present application will be described below. The phase change heat storage material precise temperature control and heating uniformity intelligent adjustment system described below can be correspondingly referred to the phase change heat storage material precise temperature control and heating uniformity intelligent adjustment method described above.

[0144] The present application also provides a phase change heat storage material precise temperature control and heating uniformity intelligent adjustment system, comprising:

[0145] A temperature distribution determination module is configured to determine the temperature distribution state of each heat storage unit based on the real-time temperature data of the phase change material in each heat storage unit and the solar radiation intensity information.

[0146] An anomaly determination module is configured to predict the temperature gradient change trend of each heat storage unit based on the temperature distribution state using a Kalman filter algorithm, and determine a target unit list of the phase change process anomaly of the heat storage unit.

[0147] An energy distribution module is configured to calculate an energy distribution scheme using a particle swarm optimization algorithm based on the heat charging state difference of each heat storage unit in the target unit list, and obtain the energy distribution weight coefficient of each heat storage unit.

[0148] a flow rate adjusting module, configured to adjust the heat medium flow rate distribution of each heat storage unit by an intelligent valve control module based on the energy distribution weight coefficient to obtain a flow rate control instruction, wherein the flow rate control instruction comprises an increase or decrease of the heat medium flow rate opening of the heat storage unit;

[0149] an execution parameter determining module, configured to adjust the heat storage preparation state or heat energy release strategy of each heat storage unit by a fuzzy control algorithm based on the flow rate control instruction and in combination with the solar radiation intensity information and indoor temperature demand data to obtain dynamic adjustment execution parameters;

[0150] a heat medium adjusting module, configured to drive the heat medium circulating module to perform flow direction adjustment based on the dynamic adjustment execution parameters to adjust the heat medium circulating speed and flow direction distribution of each heat storage unit.

[0151] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for precise temperature control and uniform intelligent regulation of heating using phase change thermal storage materials, characterized in that, Executed by a computer, including: Based on the real-time temperature data of the phase change material in each heat storage unit and the solar radiation intensity information, the temperature distribution state of each heat storage unit is determined. Based on the temperature distribution, the Kalman filter algorithm is used to predict the temperature gradient change trend of each heat storage unit, and to determine the target unit list of the heat storage unit with abnormal phase change process. Based on the differences in the charging state of each heat storage unit in the target unit list, the energy allocation scheme is calculated using the particle swarm optimization algorithm to obtain the energy allocation weight coefficient of each heat storage unit. Based on the energy distribution weighting coefficient, the heat medium flow distribution of each heat storage unit is adjusted by the intelligent regulating valve control module to obtain flow control instructions, wherein the flow control instructions include increasing or decreasing the heat medium flow opening of the heat storage unit. Based on the flow control command, combined with the solar radiation intensity information and indoor temperature demand data, a fuzzy control algorithm is used to adjust the heat storage preparation status or heat release strategy of each heat storage unit to obtain dynamic adjustment execution parameters. Based on the aforementioned dynamic adjustment execution parameters, the heat medium circulation module is driven to perform flow direction adjustment in order to adjust the heat medium circulation speed and flow direction distribution of each heat storage unit.

2. The method for precise temperature control and uniform heating intelligent regulation of phase change thermal storage materials according to claim 1, characterized in that, Based on the temperature distribution, a Kalman filter algorithm is used to predict the temperature gradient change trend of each thermal storage unit, and a list of target units with abnormal phase change processes is determined, including: Based on the temperature distribution state, the Kalman filter algorithm is used to process the temperature distribution state and predict the temperature gradient change trend of each heat storage unit to obtain the predicted temperature gradient sequence. Based on the predicted temperature gradient sequence, the rate of change of temperature gradient for each thermal storage unit is calculated to obtain a rate of change sequence. The change rate sequence is compared with a preset change rate threshold to identify heat storage units with abnormal phase change processes, thus obtaining a set of abnormal units. The target unit list is generated based on the unit identifier information of the abnormal units in the abnormal unit set.

3. The method for precise temperature control and uniform intelligent regulation of heating using phase change thermal storage materials according to claim 1, characterized in that, Based on the differences in the thermal charge state of each thermal storage unit in the target unit list, the particle swarm optimization algorithm is used to calculate the energy allocation scheme, obtaining the energy allocation weight coefficient of each thermal storage unit, including: Based on the real-time temperature data of each heat storage unit in the target unit list, the heat storage state of each heat storage unit and the heat storage state difference corresponding to the heat storage state are determined. Based on the differences in the charging state, the proportion of heat energy input is determined, and the adjustment requirements of each heat storage unit are obtained. Based on the aforementioned adjustment requirements, a particle swarm optimization algorithm is used to calculate the initial energy allocation weight coefficients for each thermal storage unit. Based on the initial energy allocation weight coefficients, the data are input into a recurrent neural network model for prediction to obtain the energy allocation scheme for each thermal storage unit. Based on the energy allocation scheme, the heat input and heat dissipation regulation of each heat storage unit are calculated to obtain the energy allocation weight coefficient of each heat storage unit.

4. The method for precise temperature control and uniform intelligent regulation of heating using phase change thermal storage materials according to claim 1, characterized in that, The process of adjusting the heat medium flow distribution of each heat storage unit based on the energy distribution weighting coefficient through the intelligent regulating valve control module to obtain flow control commands includes: If the energy allocation weight coefficient is greater than the preset weight threshold, a first control signal to increase the valve opening is generated; If the energy allocation weight coefficient is less than or equal to the preset weight threshold, a second control signal to reduce the valve opening is generated; Based on the first control signal or the second control signal, K-means algorithm is used for cluster analysis to determine the traffic allocation pattern; Based on the flow distribution mode and real-time energy demand, the heat medium flow distribution ratio of each heat storage unit is adjusted to generate an optimized flow control command. The optimized flow control command is executed by the intelligent regulating valve control module to dynamically adjust the valve opening of each heat storage unit and obtain the actual flow distribution result. Based on the deviation between the actual flow distribution result and the expected energy distribution, a PID control algorithm is used to fine-tune the valve opening to obtain the flow control command.

5. The method for precise temperature control and uniform intelligent regulation of heating using phase change thermal storage materials according to claim 1, characterized in that, Based on the flow control command, combined with the solar radiation intensity information and indoor temperature demand data, a fuzzy control algorithm is used to adjust the heat storage preparation state or heat release strategy of each heat storage unit to obtain dynamic adjustment execution parameters, including: Based on the solar radiation intensity information and the indoor temperature demand data, a time series analysis method is used to determine the changing trend of solar radiation intensity. If the trend of change is upward, then based on the flow control command, the heat storage preparation state of each heat storage unit is adjusted by a fuzzy control algorithm to obtain the heat storage state adjustment parameters. If the trend of change is downward, the heat release strategy is optimized by linear regression algorithm to obtain the heat release parameters; The real-time data processing module integrates the heat storage state adjustment parameters and the heat release parameters to generate dynamic adjustment execution parameters.

6. The method for precise temperature control and uniform intelligent regulation of heating using phase change thermal storage materials according to claim 1, characterized in that, Also includes: After adjusting the heat medium circulation speed and flow direction distribution of each heat storage unit, monitor the real-time temperature data of the phase change material in each heat storage unit, and obtain the temperature change based on the real-time temperature data to obtain the new temperature distribution state. If the new temperature distribution shows local temperature fluctuations, the heat medium circulation speed and flow direction distribution are adjusted in real time to determine the real-time heat storage unit's charging status. Based on the real-time heating state and the temperature distribution uniformity target, the operating mode of the solar collector and the phase change sequence of the heat storage unit are adjusted through a feedback control mechanism to obtain the system control strategy parameters. The solar collector is connected to the heat storage unit and provides thermal energy to the heat storage unit. The system control strategy parameters are used to control the working mode of the solar collector and the phase change sequence of the heat storage unit so that the real-time charging state of the heat storage unit reaches the temperature distribution uniformity target.

7. The method for precise temperature control and uniform heating intelligent regulation of phase change thermal storage materials according to claim 6, characterized in that, If the new temperature distribution shows local temperature fluctuations, the heat transfer medium circulation speed and flow direction are adjusted in real time to determine the real-time charging state of the heat storage unit, including: If the new temperature distribution shows local temperature fluctuations, a preset control algorithm is used to adjust the heat transfer medium circulation speed and determine new circulation speed parameters. Based on the adjusted circulation velocity parameters, the heat medium flow direction distribution ratio is calculated to obtain the flow direction distribution scheme. Based on the aforementioned flow distribution scheme, the heat medium circulation module is driven to perform flow direction adjustment to determine the real-time heat storage unit's charging status.

8. A precise temperature control and uniform heating intelligent regulation system using phase change thermal storage materials, characterized in that, include: The temperature distribution determination module is used to determine the temperature distribution state of each heat storage unit based on the real-time temperature data of the phase change material in each heat storage unit and the solar radiation intensity information. An anomaly determination module is used to predict the temperature gradient change trend of each heat storage unit based on the temperature distribution state using a Kalman filter algorithm, and to determine a list of target units with anomalies in the phase change process of the heat storage unit. The energy allocation module is used to calculate the energy allocation scheme based on the differences in the charging state of each heat storage unit in the target unit list, using a particle swarm optimization algorithm, and to obtain the energy allocation weight coefficient of each heat storage unit. The flow regulation module is used to adjust the heat medium flow distribution of each heat storage unit based on the energy distribution weight coefficient through the intelligent regulating valve control module to obtain flow control instructions, wherein the flow control instructions include increasing or decreasing the opening degree of the heat medium flow of the heat storage unit; The execution parameter determination module is used to adjust the heat storage preparation state or heat release strategy of each heat storage unit based on the flow control command, combined with the solar radiation intensity information and indoor temperature demand data, using a fuzzy control algorithm to obtain dynamic adjustment execution parameters. The heat medium regulation module is used to drive the heat medium circulation module to perform flow direction regulation based on the dynamic regulation execution parameters, so as to adjust the heat medium circulation speed and flow direction distribution of each heat storage unit.

Images