Lithium bromide heat pump regulation and control method for coupling solar photo-thermal and computing power waste heat

Abstract

The invention relates to the technical field of multi-energy complementation and waste heat recovery, in particular to a lithium bromide heat pump regulation and control method for coupling solar photo-thermal and computing power waste heat. The method comprises the steps of data acquisition, model calculation, dynamic regulation and control and safety monitoring. The method comprises the steps of collecting multi-source operation data and inputting the data into a thermodynamic matching model; the method is characterized in that coupling heat source exergy efficiency and a thermal response time constant are solved, a flow regulation and heat source switching instruction is generated, and a generator is kept in a high-efficiency temperature range; meanwhile, the crystallization safety margin is calculated in real time, and the anti-crystallization process is triggered when the crystallization safety margin is lower than a threshold value; according to the method, the conversion from static threshold dependence to dynamic thermodynamic matching is realized, the problem of high-grade heat energy waste caused by source-load asynchronization is solved, and the thermodynamic perfection of the system is maximized.

Description

Technical Field

[0001] This invention relates to the field of multi-energy complementarity and waste heat recovery technology, specifically a lithium bromide heat pump control method that couples solar thermal energy with computing power waste heat. Background Technology

[0002] In existing multi-energy coupled heating systems, solar thermal energy and waste heat from data center computing power are often used together as the driving heat source for lithium bromide absorption heat pumps. These two types of heat sources have significant time asynchronicity and volatility. Solar irradiance is affected by meteorological cloud cover, which generates high-frequency noise, while computing load changes suddenly with business throughput. Existing control schemes generally adopt simple logic control based on static temperature thresholds, lacking in-depth evaluation of heat source energy quality and system dynamic thermal response characteristics. When facing source load fluctuations, this lagging control method is difficult to achieve precise matching of flow and heat, which can easily cause violent fluctuations in generator inlet temperature, leading to frequent deviations of the unit from the high-efficiency operating range and resulting in energy efficiency degradation. In addition, due to the lack of an internal state mapping mechanism based on externally measurable parameters, existing technologies cannot quantify the crystallization safety margin of lithium bromide solution in real time, resulting in the inability to trigger anti-crystallization protection in time under low temperature difference or low load conditions, which seriously threatens the continuous safe operation of the unit. Therefore, how to achieve efficient thermodynamic matching of heterogeneous heat sources and improve system stability under complex operating conditions has become an urgent technical problem to be solved. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a lithium bromide heat pump control method that couples solar thermal energy with waste heat from computing power. Specifically, the technical solution of this invention includes: Data acquisition steps: Collect solar irradiance data, computing load data, and heat pump unit operating parameters through a multi-source data sensing layer. The heat pump unit operating parameters include dilute solution concentration, concentrated solution concentration, and generator inlet temperature. Model solution steps: Input the collected data into the thermodynamic matching model and solve for the exergy efficiency and thermal response time constant of the coupled heat source; Dynamic control steps: Based on the exergy efficiency and thermal response time constant of the coupled heat source, generate flow regulation commands and heat source switching commands to maintain the generator inlet temperature within the preset high-efficiency temperature range; Safety monitoring steps: Calculate the crystallization safety margin in real time, and trigger the anti-crystallization dilution process when the crystallization safety margin is lower than the preset safety threshold.

[0004] Preferably, the calculation of the exergy efficiency of the coupled heat source includes: Analyzing source-load asynchronous characteristics: based on the time series characteristics of solar irradiance data and computing power load data, identifying the time deviation of energy supply peak and heat pump demand peak; Calculating weighted exergy efficiency: determining the weight coefficient of solar photo-thermal and computing power waste heat based on the time deviation, calculating the Carnot factor corresponding to the solar photo-thermal temperature and the computing power waste heat temperature respectively, and using the weight coefficient to weight and sum the Carnot factors of the two, to obtain the coupling heat source exergy efficiency; the Carnot factor represents the work potential of the heat source temperature relative to the ambient temperature.

[0005] Preferably, the generation of flow regulation instructions and heat source switching instructions comprises: If the coupling heat source exergy efficiency is greater than the preset efficiency threshold, a first regulation instruction is generated to control the solar photo-thermal circuit and the computing power waste heat circuit to perform direct series heating; If the coupling heat source exergy efficiency is less than or equal to the preset efficiency threshold and greater than or equal to the minimum running threshold, a second regulation instruction is generated to control the auxiliary heat source to intervene and adjust the mixing ratio; If the coupling heat source exergy efficiency is less than the minimum running threshold, a third regulation instruction is generated to shut off the heat pump unit heating and switch to standby circulation mode.

[0006] Preferably, the method further comprises: Before inputting the data into the multi-source data perception layer, pre-processing the data to obtain pre-processed data; Wherein, the pre-processing comprises: Using Kalman filtering algorithm to smooth the solar irradiance data, eliminating high-frequency noise caused by cloud cover; Using moving average method to extract the trend of computing power load data, to suppress the disturbance of computing power business burst fluctuation to heat source flow.

[0007] Preferably, the safety monitoring step specifically comprises: Based on the generator inlet temperature and the concentrated solution concentration, using the Duoling diagram equation to solve the saturation crystallization temperature under the current working condition; Calculate the difference between the current solution temperature and the saturation crystallization temperature to obtain the crystallization safety margin; Compare the crystallization safety margin with the preset safety threshold: if the crystallization safety margin is less than the preset safety threshold, it is determined that there is a crystallization risk; if the crystallization safety margin is greater than or equal to the preset safety threshold, it is determined that the system is running safely.

[0008] Preferably, the anti-crystallization dilution process comprises: In response to determining that there is a crystallization risk, a melt-crystal heating instruction is generated to increase the generator inlet temperature; Meanwhile, bypass regulation instructions are generated to open the coolant water bypass valve, directly mix the coolant water into the concentrated solution circuit, and reduce the concentration of the concentrated solution until the crystallization safety margin is restored to above the preset recovery threshold.

[0009] Preferably, the generation of the flow regulation instruction according to the coupled heat source exergy efficiency and the thermal response time constant comprises: The thermal response time constant is calculated, and the thermal response time constant is defined as the time required for the system to reach 63.2% of the steady-state value of the generator inlet temperature from receiving the heat source temperature step change signal; The execution step of the flow regulation instruction is corrected based on the thermal response time constant: If the thermal response time constant is less than the preset response threshold, a first step adjustment strategy is adopted to quickly respond to fluctuations; If the thermal response time constant is greater than or equal to the preset response threshold, a second step gradual adjustment strategy smaller than the first step is adopted to prevent system oscillation.

[0010] Preferably, the method further comprises: A computing power heat dissipation guarantee mechanism is constructed, and a standby heat dissipation bypass is forcibly activated when the heat pump unit fails or is shut down for maintenance; The change rate of the computing power load data is monitored, and if the change rate is greater than a preset surge threshold, the flow of the computing power waste heat circuit is preferentially locked, and the flow of the solar light heat circuit is adjusted to balance the total heat input, ensuring uninterrupted heat dissipation of the computing power equipment; if the change rate is less than or equal to the preset surge threshold, the current flow regulation strategy is maintained.

[0011] Preferably, the analysis of the source-load asynchronous characteristics specifically comprises: The long short-term memory network model is used to predict the solar irradiance and computing power load in a future preset time period; Based on the prediction result, a supply-demand matching degree index in a future preset time period is calculated, and the supply-demand matching degree index is the ratio of the predicted solar supply to the computing power heat load demand; If the supply-demand matching degree index is less than a preset matching threshold, a heat storage device intervention instruction is generated in advance to use the heat storage device to suppress source-load asynchronous fluctuations.

[0012] Compared with the prior art, the present application has the following beneficial effects: 1. The method proposes a regulation method based on a thermodynamic matching model, which is no longer simply dependent on static temperature threshold, but controls by solving the coupled heat source exergy efficiency and thermal response time constant; by analyzing the source-load asynchronous characteristics of solar light heat and computing the weighted exergy efficiency, the working potential of different temperature heat sources can be accurately quantified and the weight distribution can be optimized; this effectively solves the problem of high-grade heat waste caused by the mismatch of solar energy and computing load in time and grade, so that the system can always maintain in the high-efficiency temperature range under complex working conditions, avoiding the performance degradation of the unit caused by heat source fluctuation, and maximizing the thermodynamic perfection of the system; 2. The method adopts an adaptive flow regulation strategy based on the heat response time constant; by calculating the time constant of the system from the step signal to the steady state in real time, the fast and slow characteristics of the system are intelligently distinguished, and the execution step of the regulation instruction is corrected accordingly: small step incremental regulation in fast response and large step fast response in slow response; combined with Kalman filtering and moving average method for preprocessing of original data, meteorological high-frequency noise and computing burst fluctuation are effectively filtered out; this design avoids the frequent oscillation of valves and temperature overshoot caused by lag or over-regulation in traditional control, thereby ensuring the stability of flow regulation and prolonging the service life of valve pump set and other hardware; 3. In view of the problem that the existing technology cannot directly evaluate the internal crystallization risk, the method establishes a mathematical model for calculating the crystallization safety margin of the algorithm; using the Duoling equation and the heat exchange terminal difference model, the external collected temperature and concentration parameters are mapped to the saturation crystallization temperature of the internal solution, realizing real-time quantization of the risk; once the safety margin is lower than the threshold, the dual defense process of melt-crystal heating and bypass dilution is triggered immediately, which eliminates the crystallization core in the shortest time by simultaneously increasing the solution temperature and reducing the solution concentration; this effectively prevents the pipeline blockage failure of lithium bromide unit under low temperature difference or low load working condition, ensuring the continuous and safe operation of the equipment; 4. The method introduces a source-load prediction and computing heat dissipation guarantee mechanism based on deep learning; the long short-term memory network model is used to predict the future supply-demand matching degree, and the heat storage device is scheduled in advance to smooth fluctuations; more importantly, the principle of computing power safety priority is established, and by monitoring the computing load change rate, the standby heat dissipation bypass is automatically locked and activated when the load increases; this mechanism ensures that the data center does not interrupt the heat dissipation under extreme load impact, solves the contradiction between the pursuit of heat recovery efficiency and the operation safety of computing equipment, and improves the reliability and robustness of the entire energy system. BRIEF DESCRIPTION OF DRAWINGS

[0013] The application will be further explained in conjunction with the drawings and examples: Figure 1 is the flow chart of the method of the application. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with specific examples.

[0015] Example 1 Please refer to Figure 1 A lithium bromide heat pump regulation method coupled with solar light heat and computing waste heat, comprising: Data acquisition step: acquiring solar irradiance data, computing load data and heat pump unit operating parameters through a multi-source data perception layer, wherein the heat pump unit operating parameters include dilute solution concentration, concentrated solution concentration and generator inlet temperature; Model solving step: inputting the collected data into a thermodynamic matching model to solve the coupled heat source exergy efficiency and thermal response time constant; Dynamic regulation step: generating flow regulation instructions and heat source switching instructions according to the coupled heat source exergy efficiency and thermal response time constant to maintain the generator inlet temperature in the preset high-efficiency temperature range; Safety monitoring step: real-time calculation of crystallization safety margin, and triggering the anti-crystallization dilution process when the crystallization safety margin is lower than the preset safety threshold.

[0016] The present embodiment proposes a lithium bromide heat pump regulation method coupled with solar light heat and computing waste heat. The method relies on a system architecture including a solar collector, a data center liquid cooling heat dissipation loop, a lithium bromide absorption heat pump unit and an intelligent control center. The system performs a data acquisition step to obtain the boundary conditions and operating state of the system in real time through a multi-source data perception layer. The multi-source data perception layer is composed of a hardware system composed of a high-precision sensor network and a data acquisition card DAQ deployed in the physical system; The system acquires solar irradiance data in real time through a pyranometer installed in the heat collection field The server power consumption or CPU utilization rate index read through the data center infrastructure management system DCIM interface is used as the computing load data Unit: kilowatt kW; if the read data is the CPU utilization rate index, the system converts it into a power value through a pre-set power-load nonlinear fitting curve and assigns it to In order to ensure the uniqueness of the dimension of subsequent energy calculation, the server power consumption value is directly read in priority in the present embodiment; and the dilute solution concentration , the concentrated solution concentration and the generator inlet temperature are measured through an online refractometer and a PT100 temperature sensor respectively; The system performs a model solving step, inputting the collected data into a thermodynamic matching model, which is not a simple logical judgment, but a calculation kernel based on the second law of thermodynamics, aiming to solve the coupled heat source exergy efficiency And the thermal response time constant These two key control indicators; the model regards the solar collector and the computing power waste heat circuit as two independent non-isothermal heat sources, and constructs the input parameter and work potential mapping according to the Carnot theorem; item And Respectively represent the maximum theoretical work potential of the solar working medium and the computing power waste heat fluid relative to the environmental reference state , that is, the physical exergy, the model correlates the physical structure parameters of the two through a weight coefficient , and thus derives the following mapping relationship: the system calculates the exergy efficiency according to the formula: , wherein is the environmental thermodynamic absolute temperature K, are the solar and computing power waste heat supply water thermodynamic absolute temperatures K, is the weight coefficient; according to the formula: The time constant is calculated according to the formula: , wherein represents the equivalent heat capacity of the system, and the subscript eq represents equivalent, that is, equivalent, and the calculation method is: , which covers the heat capacity components of the heat exchanger metal wall, the internal fluid and the external insulation layer; is the comprehensive heat transfer coefficient, the value of which is determined according to the initial experiment identification, although will slowly drift due to long-term running scaling, but it is considered constant within a single control period, and this embodiment is periodically corrected through heat exchange efficiency feedback in subsequent operation; is the effective heat exchange area, which is a design constant, and the scaling reduction coefficient estimated in long-term operation has been deducted in calculation; In the dynamic control step, the controller generates corresponding hardware action instructions according to the calculated , including adjusting the opening degree of the electric regulating valve on the solar circuit and the computing power waste heat circuit to change the mixed flow entering the generator, and controlling the on-off of the three-way valve to determine the use of series, parallel or single heat source heating mode, the purpose of which is to maintain the generator inlet temperature Always within the preset high-efficiency temperature range , to ensure that the unit COP is in the optimal interval; in the safety monitoring step, the system calculates the crystallization safety margin in real time, and responds to If the safety threshold is lower than the preset safety threshold Immediately trigger the anti-crystallization dilution process to prevent the concentrated solution from freezing and clogging in the heat exchanger. This embodiment introduces a thermodynamic matching model, no longer relying solely on temperature control, but combining the energy quality, i.e., exergy efficiency, and the dynamic characteristics of the system, i.e., time constant. This enables the system to predict and smooth the transition in advance in complex scenarios of solar energy mutations or sudden increases in computing power loads, effectively avoiding the performance degradation of the unit due to fluctuations in the heat source, and achieving efficient coupling of dual heat sources.

[0017] Solving the exergy efficiency of the coupled heat source includes: Analyzing the source-load asynchronous characteristics: based on the time series characteristics of solar irradiance data and computing power load data, identify the time deviation of energy supply peak and heat pump demand peak; Calculating the weighted exergy efficiency: based on the time deviation, determine the weight coefficient of solar photothermal and computing power waste heat, calculate the Carnot factor corresponding to the solar photothermal temperature and the computing power waste heat temperature respectively, and use the weight coefficient to weight and sum the Carnot factors of the two, to get the exergy efficiency of the coupled heat source; the Carnot factor represents the work potential of the heat source temperature relative to the ambient temperature.

[0018] This embodiment details the specific process of calculating the exergy efficiency of the coupled heat source. Since solar energy and computing power load are often asynchronous in time, direct mixing may lead to waste of high-grade heat energy, so it is necessary to calculate the weighted exergy efficiency to guide the matching; the system analyzes the source-load asynchronous characteristics, based on the solar irradiance data and computing power load data in the sliding time window, identifies the time points of the peaks of the two, and the system uses a rolling update mechanism, i.e., every 15 minutes, based on the rolling time window containing 12 hours of historical data and 12 hours of forecast data, re-scans and updates and ; To avoid the subjectivity of manual observation, the system constructs a data vector with a length of , corresponding to a 24-hour window and a 15-minute resolution , respectively performs vector extreme value index search algorithm: and , and converts the index to physical time: , , and defines the time deviation as follows: wherein : derived from historical data statistics or short-term prediction, physically means the time when solar supply reaches the peak; : Source from load analysis, physical meaning is the time when the computing power heat pump demand reaches the peak; the system calculates the weighted exergy efficiency, determines the weight based on time deviation, and calculates the comprehensive exergy efficiency combined with the Carnot factor, the calculation formula is as follows: Wherein, : Source from calculation result, physical meaning is the coupling heat source exergy efficiency; : Source from real-time acquisition of outdoor weather station, specific measurement position is temperature sensor installed in louver box 1.5 meters high from ground in outdoor well-ventilated place to eliminate direct interference of solar radiation, physical meaning is environment reference thermodynamic absolute temperature K; : Source from sensor acquisition, specific measurement position is total outlet manifold of solar collector array, and is located before any mixing valve or heat loss link to accurately obtain heat source side water supply temperature, physical meaning is solar photothermal loop water supply thermodynamic absolute temperature K; : Source from sensor acquisition, specific measurement position is on the connecting pipeline between the outlet of data center liquid cooling CDU secondary side heat exchanger and the inlet of heat pump unit, arranged close to the heat pump inlet, physical meaning is the water supply thermodynamic absolute temperature K of computing power waste heat loop; if the acquisition value is in Celsius, 273.15 needs to be added for conversion; : Source from calculation result, physical meaning is the dynamic weight coefficient of solar photothermal; Weight coefficient The calculation is based on time deviation And system thermal inertia factor : Here is the natural logarithm base; parameter , here is specifically the adjustment coefficient, the physical unit of time index is , used to represent the asynchronous growth rate, set to is based on the system response curve fitting under typical working conditions; is the maximum asynchronous tolerance time, unit is hour h, its value is proportional to the effective adjustment capacity of water tank, the correlation meets ; : Source from preset constant, physical meaning is adjustment sensitivity constant, or called adjustment coefficient, to ensure that the exponential term is dimensionless value; in this formula calculation, time deviation must be converted to hour h as unit input; : Source from capacity parameter of heat storage water tank, physical meaning is the maximum asynchronous tolerance time allowed by the system; To ensure that the calculation results conform to the actual dynamic characteristics of the system and can be reproduced by those skilled in the art, in this embodiment... Set as This value was determined through on-site debugging and can effectively balance the smoothness and sensitivity of weight changes. The setting is 4 hours, which matches the maintenance time of the 50 cubic meter hot water storage tank under full load in the system configuration; This embodiment introduces the Carnot factor to accurately quantify the work potential of heat sources at different temperatures. By utilizing the weighting coefficients determined by the asynchronous characteristics of the source and load, the control strategy can favor the heat source that is more suitable at the current moment when facing asynchronous scenarios such as strong solar energy at noon but low computing power load, thereby maximizing the thermodynamic perfection of the system and reducing irreversible losses.

[0019] Generate flow regulation commands and heat source switching commands, including: If the exergy efficiency of the coupled heat source is greater than the preset efficiency threshold, the first adjustment command is generated to control the solar thermal circuit and the computing power waste heat circuit to be directly connected in series for heating. If the exergy efficiency of the coupled heat source is less than or equal to the preset efficiency threshold and greater than or equal to the minimum operating threshold, a second adjustment command is generated to control the intervention of the auxiliary heat source and adjust the mixing ratio. If the exergy efficiency of the coupled heat source is less than the minimum operating threshold, a third adjustment command is generated to cut off the heat pump unit's heating supply and switch to standby cycle mode.

[0020] This embodiment details the hierarchical control logic for generating flow regulation commands and heat source switching commands, with an efficiency threshold preset within the controller. With minimum operating threshold In the specific parameter configuration of this embodiment, considering the COP decay characteristics of lithium bromide units under low heat source quality, a preset efficiency threshold is used. The value is set to 0.55. This value is determined based on the thermodynamic perfection test data of the lithium bromide unit under rated operating conditions. In the laboratory environment, when the exergy efficiency of the coupled heat source is lower than 0.55, the heating performance coefficient COP of the unit begins to decrease significantly and deviates from the linear high-efficiency zone, indicating that the heat source quality is no longer sufficient to support a high-efficiency thermodynamic cycle. Minimum operating threshold The value is set at 0.25. This value is an empirical value determined based on the unit's minimum start-up temperature difference characteristics. During multiple on-site commissionings, it was found that when the exergy efficiency is below 0.25, corresponding to a heat source temperature of approximately 65 degrees Celsius, the absorption capacity of the dilute solution decreases sharply, and the unit's COP approaches 1.0, thus losing its energy-saving significance as a heat pump. This is in response to the exergy efficiency of the coupled heat source. Greater than , the system generates a first adjustment instruction, controls the solar circuit and the computing power waste heat circuit in series, so that the computing power waste heat is used as a preheating source to heat the working medium to a medium temperature, and then the working medium enters the solar collector to be heated to a high temperature, so that the high matching degree of the two heat sources is used to realize gradient heating; in response to between and , the system generates a second adjustment instruction to start the auxiliary heat source and adjust the mixing ratio of the three-way regulating valve; in order to avoid temperature fluctuations caused by simple open-loop control, the system calculates the specific opening degree of the auxiliary heat source mixing valve based on an incremental PI control algorithm , and the calculation logic is to use an incremental PI control algorithm: wherein, the error term , is the error of the last time; is a preset gain, is the target generator inlet temperature, so as to accurately introduce an external high-grade heat source for supplementary combustion and maintain the stability of the generator inlet temperature; in response to less than , the system generates a third adjustment instruction to close the main steam or hot water valve of the heat pump unit, so that the unit enters an internal solution circulation standby state, and the computing power waste heat is switched to a standby dry cooler for heat dissipation, so as to prevent crystallization failure in the extremely low COP working condition; The hierarchical control strategy constructed in this embodiment maximizes the system benefit by using series gradient when the heat source is sufficient, clearly defines the mode switching boundary when the heat source grade is insufficient, avoids the invalid operation of the heat pump in the low energy efficiency area, and ensures the determinacy and stability of the system control under complex working conditions of multiple heat sources.

[0021] Embodiment 2: The method further comprises: preprocessing the data before inputting the data into the multi-source data perception layer to obtain preprocessed data; The preprocessing comprises: using a Kalman filtering algorithm to smooth the solar irradiance data and eliminate high-frequency noise caused by cloud cover; using a moving average method to extract the trend of the computing power load data and suppress the interference of computing power service burst fluctuations on the heat source flow.

[0022] This embodiment describes the data preprocessing process before the data input perception layer, aiming to eliminate the noise and glitches contained in the original data and prevent the actuator from frequent oscillation; for the timing described in the embodiment before the data is input into the multi-source data perception layer, in the specific execution logic of the physical system, it refers to the preprocessing step performed by the edge computing unit after the physical signal collection is completed by the front-end sensor, but before the transmission and writing into the perception layer core database or input into the upper control model, so as to ensure that the data flow conforms to the logic closed loop of collection first, processing second and input third; For solar irradiance data, the system uses Kalman filtering algorithm to eliminate high-frequency noise caused by cloud cover. In the univariate state estimation model of this embodiment, it is assumed that the irradiance change conforms to the local constant process, so the state transition matrix and the measurement matrix are both scalar 1.0, and the above simplified assumption is applicable to the working condition of the system in quasi-steady state operation; wherein the process noise covariance , the measurement noise covariance and the initial error covariance are determined by the experience value based on statistical analysis of historical operation data and system identification experiment; in addition to the state update equation, the time update step and Kalman gain calculation step are also defined, and the specific complete algorithm flow is as follows: Time update: Calculate Kalman gain: State update: Covariance update: Wherein, : predicted irradiance prior estimate; : prior estimation error covariance; : posterior estimation error covariance; : measured irradiance value of sensor at time k; : optimal irradiance estimate at time k; For computing power load data, the system uses moving average method to suppress computing power business burst fluctuation, and the calculation formula is as follows: Wherein, : the source is the calculation result, and the physical meaning is the smoothed load value at time t after processing; : Originated from collection, physically means the original load value of the past i th sampling point; : Originated from preset value, physically means the length of sliding window; To ensure the convergence and effectiveness of the algorithm in the physical system, the process noise covariance of Kalman filter is set to , the measurement noise covariance is set to 0.1, and the initial covariance is set to 1.0; the length of sliding window of moving average method is specifically set to 60 sampling points, and if the sampling frequency is 5 seconds / time, it corresponds to a time span of 5 minutes. This parameter setting aims to cover a typical short-term fluctuation period of computing power load and prevent instantaneous computing task throughput from causing the misoperation of flow valve; The embodiment effectively filters out the false and sharp fluctuations of irradiance caused by the rapid passing of clouds through Kalman filtering, and filters out the spikes caused by the instantaneous start and stop of computing power task through moving average method, so that the preprocessed data can better reflect the real trend of energy change, thereby making the subsequent flow regulation more stable under variable weather conditions and prolonging the service life of the valve and pump set.

[0023] The safety monitoring step specifically includes: Based on the generator inlet temperature and the concentrated solution concentration, the saturation crystallization temperature under the current working condition is solved by using the Duoling diagram equation; The difference between the current solution temperature and the saturation crystallization temperature is calculated to obtain the crystallization safety margin; The crystallization safety margin is compared with the preset safety threshold: if the crystallization safety margin is less than the preset safety threshold, it is determined that there is a crystallization risk; if the crystallization safety margin is greater than or equal to the preset safety threshold, it is determined that the system is safe to run.

[0024] The embodiment details the specific algorithm of crystallization safety monitoring. Since crystallization is the most fatal failure of lithium bromide unit, this step aims to quantitatively determine the risk boundary in real time. Based on the generator inlet temperature and the concentrated solution concentration, the saturation crystallization temperature under the current working condition is solved by using the Duoling diagram equation. The coefficient in the formula is the Duoling diagram coefficient, which is derived from experimental fitting data and corresponds to the fitting slope and bias term under different temperature intervals, respectively. The approximate fitting formula is as follows: Wherein, : Originated from calculation result, physically means the saturation crystallization temperature; represents the solution concentration, which needs to be uniformly in the form of percentage numerical value when inputting calculation, that is, taking the value before the percentage sign, such as needs to be substituted into Calculations are performed; in this embodiment, for example, the concentration is... The time value is ; The source is an empirical constant obtained by performing least-squares nonlinear regression fitting on standard solubility data of lithium bromide aqueous solution within the working concentration range, with the following values: , , , The vertical asymptote characterizing the crystallization curve ensures formula convergence within the working concentration range; System calculates crystallization safety margin To strictly respond to the generator inlet temperature-based response in Example 1 To limit the control, and considering that the data acquisition steps in Example 1 did not include direct measurement of the solution temperature inside the generator, the system introduces a heat exchange terminal difference model to measure the acquired generator inlet heat source temperature. Mapped to the estimated temperature of the concentrated solution at the generator outlet The calculation formula is as follows: in, The source is a preset thermodynamic constant, which physically represents the nodal temperature difference of the generator heat exchanger tube bundle. This value is a fixed value determined based on the unit design parameters and does not change with operating conditions. In this embodiment, it is set based on the heat exchanger design parameters. Celsius; Considering that the actual crystallization risk in lithium bromide generators typically occurs at the lowest temperature point in the concentrated solution loop, i.e., the outlet of the solution heat exchanger or the inlet of the absorber, rather than the higher temperature generator outlet, the system needs to calculate the temperature of the critical low temperature point to avoid false negatives in safety monitoring. The calculation formula is as follows: in, The characteristic temperature drop of the concentrated solution in the solution heat exchanger is also treated as a design constant, and in this embodiment, it is set based on the rated operating conditions of the unit. Celsius; based on this, the revised formula for calculating the crystallization safety margin is: The system performs a risk assessment and will With preset safety threshold A comparison is performed, including a preset safety threshold. The method for obtaining this value is based on systematic error analysis, specifically set at 8 degrees Celsius. This value consists of three parts: the measurement error boundary of the temperature sensor, ±0.5°C; the crystallization point drift calculated from the concentration sensor error, ±2.5°C; and the thermal inertia temperature drop margin before the anti-crystallization measures take effect, 5.0°C. The sum of these three values ​​is the safety alarm baseline value. (In response to...) , determine that there is a risk of crystallization, otherwise determine that the system is safe; This embodiment not only quantifies the crystallization point by using the Duoling diagram, but also introduces an end difference model and heat exchanger temperature drop correction , establishes a clear mathematical correlation between the external heat source temperature and the internal solution critical risk point state, solves the logical fault that only collecting external parameters cannot directly evaluate the internal crystallization risk, and realizes non-invasive safety monitoring based on the existing sensor group.

[0025] Anti-crystallization dilution process, including: In response to determining that there is a risk of crystallization, generating a melt-crystal heating instruction to increase the generator inlet temperature; At the same time, a bypass adjustment instruction is generated to open the coolant water bypass valve to directly mix the coolant water into the concentrated solution loop to reduce the concentration of the concentrated solution until the crystallization safety margin is restored to above the preset recovery threshold.

[0026] This embodiment details the anti-crystallization dilution process. When it is determined that there is a risk, the system performs dual protection actions; the system generates a melt-crystal heating instruction to control the auxiliary heat source to increase power or reduce the solution circulation amount of the generator to increase the outlet temperature, directly increasing the actual solution temperature , thereby increasing the safety margin; the system generates a bypass adjustment instruction to open the coolant water bypass valve between the condenser capsule and the absorber capsule to directly introduce pure water in the condenser, i.e. coolant water, into the concentrated solution loop, aiming to physically reduce the concentration of the concentrated solution , thereby causing the saturation crystallization temperature to drop significantly; this process continues until the crystallization safety margin is restored to the preset recovery threshold ; In order to avoid frequent oscillation of the system near the critical point, this embodiment uses a hysteresis control logic to set the preset recovery threshold to 12 degrees Celsius, which is 4 degrees Celsius higher than the alarm threshold , ensuring that the risk is eliminated before resetting; This embodiment uses a combination of heating and dilution strategies. Compared to a single heating reaction that is slow or a single dilution that affects refrigeration capacity, this combined control can eliminate the crystallization core in the shortest time and is a key defense line for the algorithm power waste heat pump system to ensure continuous operation under low temperature difference operating conditions.

[0027] According to the coupled heat source exergy efficiency and thermal response time constant, a flow adjustment instruction is generated, including: Calculate the thermal response time constant, which is defined as the time required for the system to reach 63.2% of the steady-state value of the generator inlet temperature after receiving a heat source temperature step change signal; The execution step of the flow regulation instruction is corrected based on the thermal response time constant: If the thermal response time constant is less than a preset response threshold, a first step adjustment strategy is adopted to quickly respond to fluctuations; If the thermal response time constant is greater than or equal to the preset response threshold, a second step gradual adjustment strategy smaller than the first step is adopted to prevent system oscillation.

[0028] This embodiment details the flow regulation strategy based on the thermal response time constant; the system calculates the thermal response time constant ; In order to ensure that the technical scheme is fully disclosed, this embodiment clearly defines the theoretical calculation formula of the thermal response time constant, which is derived based on the lumped parameter method: Here contains the circulating pipeline and the total heat capacity of the fluid, unit: ; The specific heat capacity is set as a function of concentration, which is obtained by real-time online monitoring of concentration and retrieval of physical property table; The heat transfer coefficient has an online updating mechanism, and the system automatically re-identifies value every hours according to the operating power and temperature difference; Among them, : The source is the factory parameter of the equipment, and the physical meaning is the equivalent thermal mass of the generator assembly; : The source is the physical property database, and the physical meaning is the specific heat capacity of the lithium bromide solution under the current concentration; : The source is the thermal design parameter, and the physical meaning is the comprehensive heat transfer coefficient of the generator; : The source is the geometric parameter, and the physical meaning is the effective heat exchange area of the generator; In actual operation, the value of will change due to factors such as fouling, so in view of the physical definition of , the system needs to go through a complete step response process to obtain accurate values, in order to solve the timing contradiction between real-time control and lag calculation, this embodiment adopts an asynchronous updating mechanism of background iterative identification-front real-time application to correct the above theoretical value; A current effective time constant is maintained in the memory of the controller, the subscript cur represents current, and the initial value is set as the theoretical value calculated by the above formula; The background identification process adopts an online passive event triggered identification mechanism: the system real-time monitors the rate of change of the heat source temperature, and when is detected, the current time is marked as the step start time , and the steady-state temperature before that time is recorded , among them, The threshold for step detection is set to 0.5. This threshold is obtained based on the spectral analysis of the noise substrate of the field temperature sensor. Three times the standard deviation of the noise amplitude is selected as the detection threshold to prevent measurement noise from falsely triggering step detection. Subsequently, data is continuously buffered, and the controller utilizes pre-allocated data of length [missing information]. The subscript `buf` indicates `buffer`, meaning the circular buffer stores the historical temperature sequence. This length is based on a 1Hz sampling frequency and is calculated by multiplying the generator's maximum thermal time constant under full load by a safety factor of 1.33. It aims to cover a data window of at least 20 minutes to prevent data loss due to excessively long system thermal response times. Key historical data at any given moment is overwritten or lost, thus ensuring the integrity of the backtracking calculation; The process continues until the temperature is detected to have returned to a steady state. The logic for determining when the temperature has returned to a steady state is as follows: the calculation length is... Variance of temperature data within the sliding time window And monitor the rate of temperature change in real time. When satisfied and continued At a certain time, the system is determined to have reached a new steady state; the above thresholds are selected based on empirical parameters set according to the fluctuation characteristics of the system under rated flow; step identification threshold. This is an adjustable parameter, and its value is linearly scaled according to the system's water capacity. Then, the new steady-state asymptotic value was locked. The system backtracks the buffer data when the generator inlet temperature... First crossing of target value Record the time. ,in, ; Calculate the value of a single measurement And update the stored parameters using the exponentially weighted average method: The weighting coefficients of 0.8 and 0.2 are determined based on autocorrelation analysis of the system's historical operating data. They aim to balance the smoothness and sensitivity of parameter updates, so as to smooth measurement noise and adapt to characteristic drift caused by equipment fouling. The foreground control loop directly reads data from memory. As under the current working conditions Correct the execution step size of the flow regulation command. Among them, the preset response threshold Set as The value, measured in seconds, is determined based on the inherent thermal inertia of the generator components and their connecting pipes, and is used to distinguish between the fast and slow changing characteristics of the system; if The first step is a long adjustment strategy. 5% of the full stroke of the valve, which is an empirical value determined by step response experiments, aims to ensure that a single adjustment can produce a change of about 1.5 in the outlet temperature to quickly eliminate the deviation; if , a second step incremental adjustment strategy is adopted, 0.8% of the full stroke of the valve, which is determined according to the minimum resolution of 0.5% of the electric regulating valve positioner and an additional 0.3% dead zone allowance, to prevent overshoot; In order to convert the corrected step size into specific execution actions to form a closed-loop control, the controller executes the following discrete incremental adjustment algorithm: Real-time calculation of the current temperature deviation , wherein, is the preset center value of the high-efficiency temperature range; determine the adjustment direction using the sign function; generate the final valve opening control instruction ; wherein, when , i.e. the target temperature is higher than the current actual temperature, , the instruction controls the electric regulating valve to open to increase the heat medium flow, and vice versa, so as to eliminate steady-state error and suppress oscillation using dynamic step size ; The embodiment solves the causality paradox in the traditional method that the parameters must be obtained after waiting for the end of the response, and combines incremental adjustment logic, so that the control strategy can utilize the latest identification results and guarantee real-time response capability.

[0029] Embodiment 3: The method further comprises: A computing power heat dissipation guarantee mechanism is constructed, and when the heat pump unit fails or is shut down for maintenance, a standby heat dissipation bypass is forcibly activated; The change rate of the computing power load data is monitored, if the change rate is greater than a preset surge threshold, the flow of the computing power waste heat circuit is preferentially locked, and the total heat input is balanced by adjusting the flow of the solar light heat circuit to ensure uninterrupted heat dissipation of the computing power equipment; if the change rate is less than or equal to the preset surge threshold, the current flow adjustment strategy is maintained.

[0030] The embodiment constructs a computing power heat dissipation guarantee mechanism. Given that the safety of computing power equipment is higher than the economy of heat recovery, it is necessary to ensure uninterrupted heat dissipation. The system is configured with a standby heat dissipation bypass activation logic. In response to a heat pump unit reporting a fault code or performing shutdown maintenance, the controller immediately outputs a signal to open the electric valve leading to the dry cooler or cooling tower, and forcibly activates the standby heat dissipation bypass to take over the cooling load of the data center. The system monitors the computing power load change rate in real time , and the calculation formula is as follows: wherein, : derived from the calculation result, and the physical meaning is the change rate; : derived from the constant, and the physical meaning is the sampling interval; In response to being greater than a preset surge threshold, the system determines that the computing power load surges, enters the flow locking mode, locks the flow regulating valve on the computing power waste heat circuit side to keep it fully open or at the current opening degree, and no longer participates in the fine adjustment of the heat pump, but only adjusts the flow of the solar light and heat circuit or the auxiliary heat source to balance the total heat input; The embodiment establishes the control principle of giving priority to the safety of computing power. By monitoring the change rate, it distinguishes between normal fluctuations and sudden surges, actively gives up the pursuit of heat recovery efficiency in extreme cases, and prioritizes flow dissipation, thereby ensuring the essential safety of the data center infrastructure under any load impact.

[0031] The analysis of the source-load asynchronous characteristics includes the following aspects: The long short-term memory network model is used to predict the solar radiation and computing power load in a future preset time period; Based on the prediction results, the supply-demand matching index in the future preset time period is calculated. The supply-demand matching index is the ratio of the predicted solar supply to the computing power heat load demand; If the supply-demand matching index is less than a preset matching threshold, a heat storage device intervention instruction is generated in advance to use the heat storage device to smooth the source-load asynchronous fluctuations.

[0032] The embodiment details the prediction and heat storage intervention of the source-load asynchronous characteristics. The system uses a long short-term memory network (LSTM) model for prediction. In order to ensure the reproducibility of the algorithm, the time scale of the prediction is defined as follows: wherein, is the batch size, which is set to 1 in the online inference stage and 64 in the offline training stage; the time step is set to , and the feature dimension is set to ; wherein, when constructing the input tensor , the last dimension of the feature channel index is explicitly specified corresponding to the normalized solar irradiance data sequence, index corresponding to the normalized computing power load data sequence to ensure feature alignment between the inference stage and the training stage; the model output layer is configured to predict a data sequence of the future 4 hours with a time resolution of 15 minutes, i.e., the output sequence length is 16 time steps; The LSTM model includes two hidden layers, the first hidden layer has 64 nodes, and the activation function uses tanh, the second hidden layer has 32 nodes, and a linear activation function is used to connect the output layer; the training loss function uses mean square error; in order to prevent gradient vanishing or model divergence due to large differences in the dimensions of input data, the system must perform a normalization preprocessing step before inputting the data into the LSTM, and the specific formula is as follows: wherein, and is a dynamically updated value, and the system re-collects the extreme value once every quarter according to the load peak-valley change; the normalization process is performed independently for each input feature; wherein, for solar irradiance data , take ; for computing power load data , take ; After the LSTM model outputs the predicted value, perform the reverse normalization operation to restore the physical dimension: Based on the restored predicted sequence, calculate the supply-demand matching degree index ; in order to accurately reflect the total energy balance in the future time window, this step integrates and sums all time steps of the future predicted sequence, and in order to prevent calculation abnormalities with a denominator of zero during low computing power load or maintenance, a numerical stability factor is introduced, and the calculation formula is as follows: Before calculation, the energy supply item and the energy demand item are unified into joules as the unit of measurement through an energy conversion coefficient; the time step involved in the formula is uniformly set to seconds in the logic throughout the text; wherein, is set to ; in this calculation, in order to convert the predicted physical quantity into an energy value, define a single-step energy item: wherein, The physical true irradiance value obtained after the inverse normalization step, i.e. corresponding Numerical values ​​are used to ensure the accuracy of energy calculations; To predict the time interval of the sequence, this embodiment uses 0.25 hours. To ensure that the energy calculation results are consistent in units of joules, the time variable is used in the following formulas. The value must be 900; it is strictly forbidden to use hourly units for calculation. The effective light-receiving area of ​​the solar collector is set at 500 square meters. The solar collector's photothermal conversion efficiency is set to 0.6; this is based on the computational heat load demand. Considering the computing load data Unlike the unit of solar irradiance, strict dimensional uniformity is required; this embodiment introduces a unit conversion factor. The calculation formula is as follows: in, The heat exchange efficiency of the plate heat exchanger is set to 0.95. The value 1000 is used to unify the power unit to watts before combining it with the time unit in seconds. Multiplying ensures that both the numerator and denominator are in Joules; in this embodiment, a preset matching threshold is used. The subscript 't' represents the threshold, which is set to... ; in response This means that the predicted future solar energy supply will be insufficient to cover [the area]. When the system detects a supply-demand imbalance during the heat recovery demand, it generates an intervention command for the thermal storage device in advance. This command is not a simple on / off switch, but includes specific flow rate setpoints. The calculation logic is as follows: in, To adjust the gain, the heat release valve of the hot water storage tank is opened for energy compensation; This is the rated flow rate of the thermal storage circuit circulation pump; This embodiment clarifies the key preprocessing steps for the engineering implementation of neural network models. By clarifying the reference of physical quantities after denormalization and the specific sequence summation boundary and dimension unification process, it eliminates the logical hidden dangers of physical dimensions in energy matching calculations, ensuring the generalization ability of the prediction model under different seasons and load rates, thereby providing a reliable decision-making basis for the precise intervention of thermal storage devices.

[0033] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for regulating a lithium bromide heat pump coupled with solar light heat and computing power waste heat, characterized in that, The method comprises the following steps: Data acquisition step: collecting solar irradiance data, computing power load data and heat pump unit operating parameters through a multi-source data perception layer, wherein the heat pump unit operating parameters include dilute solution concentration, concentrated solution concentration and generator inlet temperature; Model solving step: inputting the collected data into a thermodynamic matching model to solve the coupled heat source exergy efficiency and heat response time constant; Dynamic regulation step: generating flow regulation instructions and heat source switching instructions based on the coupled heat source exergy efficiency and heat response time constant to maintain the generator inlet temperature within a preset high-efficiency temperature range; Safety monitoring step: real-time calculation of crystallization safety margin, and triggering an anti-crystallization dilution process when the crystallization safety margin is lower than a preset safety threshold.

2. The method according to claim 1, wherein, The solving of the coupled heat source exergy efficiency comprises: Analysis of source-load asynchronous characteristics: based on the time series characteristics of solar irradiance data and computing power load data, the time deviation between energy supply peak and heat pump demand peak is identified; Calculation of weighted exergy efficiency: based on the time deviation, the weight coefficients of solar thermal and computing power waste heat are determined, the Carnot factors corresponding to the solar thermal temperature and the computing power waste heat temperature are calculated respectively, and the Carnot factors of the two are weighted and summed using the weight coefficients to obtain the coupled heat source exergy efficiency; the Carnot factor represents the work potential of the heat source temperature relative to the environment temperature.

3. The method of claim 1, wherein the method is characterized by, The generation of flow regulation instructions and heat source switching instructions comprises: If the coupled heat source exergy efficiency is greater than a preset efficiency threshold, a first regulation instruction is generated to control the solar thermal circuit and the computing power waste heat circuit to directly series heat supply; If the coupled heat source exergy efficiency is less than or equal to the preset efficiency threshold and greater than or equal to the minimum operating threshold, a second regulation instruction is generated to control the auxiliary heat source to intervene and adjust the mixing ratio; If the coupled heat source exergy efficiency is less than the minimum operating threshold, a third regulation instruction is generated to shut down the heat pump unit heat supply and switch to standby circulation mode.

4. The method of claim 1, wherein the method is characterized by, The method further comprises: Before inputting the data into the multi-source data perception layer, the data is preprocessed to obtain preprocessed data; The preprocessing comprises: Using Kalman filtering algorithm to smooth the solar irradiance data to eliminate high-frequency noise caused by cloud cover; Using moving average method to extract the trend of computing power load data to suppress the disturbance of computing power business burst fluctuation to heat source flow.

5. The method of claim 1, wherein the method is characterized by, The safety monitoring step specifically comprises: Based on the generator inlet temperature and the concentrated solution concentration, the saturation crystallization temperature under the current working condition is solved by using the Duhring chart equation; The difference between the current solution temperature and the saturation crystallization temperature is calculated to obtain the crystallization safety margin; Comparing the crystallization safety margin with the preset safety threshold: if the crystallization safety margin is less than the preset safety threshold, it is determined that there is a risk of crystallization; if the crystallization safety margin is greater than or equal to the preset safety threshold, it is determined that the system is running safely.

6. The method of claim 5, wherein the method is characterized by, The anti-crystallization dilution process comprises: In response to the determination of the risk of crystallization, a melt-crystal heating instruction is generated to increase the generator inlet temperature; At the same time, a bypass regulation instruction is generated to open the coolant water bypass valve to directly mix the coolant water into the concentrated solution circuit to reduce the concentrated solution concentration until the crystallization safety margin recovers to above the preset recovery threshold.

7. The method of claim 1, wherein the method is characterized by, The flow regulation instruction is generated according to the coupling heat source exergy efficiency and the thermal response time constant, and comprises: The thermal response time constant is calculated, and the thermal response time constant is defined as the time required for the system to reach 63.2% of the steady-state value of the generator inlet temperature from receiving the heat source temperature step change signal; The execution step of the flow regulation instruction is corrected based on the thermal response time constant: If the thermal response time constant is less than the preset response threshold, a first step adjustment strategy is used to quickly respond to fluctuations; If the thermal response time constant is greater than or equal to the preset response threshold, a second step gradual adjustment strategy smaller than the first step is used to prevent system oscillation.

8. The method of claim 1, wherein the method is characterized by, The method further comprises: A computing power heat dissipation guarantee mechanism is constructed, and when the heat pump unit fails or is shut down for maintenance, a standby heat dissipation bypass is forcibly activated; The change rate of computing power load data is monitored, and if the change rate is greater than the preset surge threshold, the flow of the computing power waste heat circuit is preferentially locked, the flow of the solar light heat circuit is adjusted to balance the total heat input, and the computing power device heat dissipation is ensured not to be interrupted; if the change rate is less than or equal to the preset surge threshold, the current flow regulation strategy is maintained.

9. The method of claim 2, wherein the method is characterized by, The analysis of the source-load asynchronous characteristics specifically comprises: The long short-term memory network model is used to predict the solar irradiance and computing power load in a future preset time period; Based on the prediction result, a supply-demand matching degree index in a future preset time period is calculated, and the supply-demand matching degree index is the ratio of the predicted solar supply to the computing power heat load demand; If the supply-demand matching degree index is less than the preset matching threshold, a heat storage device intervention instruction is generated in advance to use the heat storage device to suppress source-load asynchronous fluctuations.

Images