Waste heat recovery heat supply system based on injection type heat pump

Abstract

The invention relates to the technical field of system control data processing, in particular to a waste heat recovery heat supply system based on an injection type heat pump, which comprises a multi-source data acquisition module, a genetic algorithm optimization module, a dynamic mode switching module, a thermal stress suppression module and a self-learning updating module. The multi-source data collection module collects industrial waste heat temperature, power grid load and heat supply network backwater flow data through a temperature sensor array and a flow metering device, and feature vectors are extracted through sliding window standardization and principal component analysis. And heat transfer end difference fluctuation is restrained through closed-loop feedback. And the self-learning updating module constructs a multi-parameter incidence matrix to dynamically adjust the weight of a fitness function, and realizes parameter iterative optimization in combination with a historical optimal solution caching mechanism. The problems that the industrial waste heat recovery efficiency is low, thermoelectric coupling adjustment is delayed, and thermal stress of equipment is accumulated are solved.

Description

Technical Field

[0001] The invention relates to the technical field of system control data processing, and in particular to a waste heat recovery heating system based on an ejector heat pump. Background Art

[0002] The waste heat recovery and heating system of the ejector heat pump is based on the principle of thermodynamic ejection. The high-pressure driving medium and the low-pressure waste heat fluid are mixed and pressurized through the ejector, and the low-temperature waste heat quality is improved by using the phase change of the medium and the pressure potential energy conversion. The existing ejector heat pump waste heat recovery and heating system adopts a heat-driven mode, with low-grade heat sources such as industrial waste heat, flue gas or cooling water as energy input, and builds a cycle through core components such as evaporators, ejectors, condensers and throttle valves. The kinetic energy transfer and mixing and pressurization process of the power fluid to the ejector fluid are completed in the ejector, and then the high-temperature mixed medium releases heat to the heating end in the condenser, finally realizing the efficient recovery of waste heat resources and heating temperature adaptation.

[0003] The technical solution of the present invention is aimed at the low utilization rate of industrial waste heat in the existing heating system, the energy waste caused by the close thermoelectric coupling, and the technical defects of the large heat transfer temperature difference in the traditional steam-water heat exchanger causing the accumulation of thermal stress in the equipment. The traditional process relies on steam turbine exhaust for heating, which restricts the flexibility of the unit operation and lacks multi-mode adjustment means when the heating load fluctuates. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a waste heat recovery heating system based on an ejector heat pump to solve the problems of low energy utilization efficiency and accumulated thermal stress of equipment in the existing heating system due to insufficient industrial waste heat recovery, strong dependence on thermoelectric coupling and large heat transfer temperature difference of traditional steam-water heat exchangers.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides a waste heat recovery heating system based on an ejector heat pump, comprising: The multi-source data acquisition module integrates a temperature sensor array, a load monitoring unit and a flow metering device, processes the industrial waste heat temperature data through a sliding window normalization method, extracts the characteristic vector of the power grid peak-shaving demand by principal component analysis, and outputs the heat network load parameters to the genetic algorithm optimization module. The sliding window normalization method uses the Z-score algorithm to normalize the industrial waste heat temperature data, and the window width is dynamically adjusted according to the heat network load change rate; A genetic algorithm optimization module receives the characteristic vector of the multi-source data acquisition module, encodes the ejector mixing ratio parameter into a binary gene fragment, uses decimal encoding for the valve opening parameter to form a mixed chromosome structure, constructs a sliding time window constraint parameter search space based on the real-time data stream, generates an initial control parameter solution set including the condensate split ratio parameter, and transmits it to the dynamic mode switching module; The dynamic mode switching module analyzes the chromosome encoding data of the initial control parameter solution set. When the waste heat-heating matching degree deviation exceeds the set threshold, the electric boiler operating condition data in the historical power mode database is called, and the grid peak load instruction is input into the electric boiler start-stop probability model to generate a candidate solution for the start-stop instruction. At the same time, the candidate solution for the extraction volume adjustment factor is generated in combination with the change trend of the return water flow of the heating network. After the sliding time window weight allocation calculation is performed on the two types of candidate solutions, the steam generation weight instruction is output to the actuator, and the mixing ratio correction parameter is sent to the thermal stress suppression module; The thermal stress suppression module receives the heat transfer end difference time series data collected by the distributed temperature field scanner, generates an optimized valve control sequence, and feeds the optimized valve control sequence back to the air extraction adjustment factor calculation unit of the dynamic mode switching module; The self-learning update module receives the pressure fluctuation suppression data of the thermal stress suppression module and the weight allocation history data of the dynamic mode switching module, and transmits the updated weight coefficient to the population initialization unit of the genetic algorithm optimization module and the candidate solution generation unit of the dynamic mode switching module through a bidirectional data channel.

[0006] Furthermore, the waste heat recovery heating system based on the ejector heat pump of the present invention further includes: Among them, the characteristic vector output end of the multi-source data acquisition module is connected to the chromosome encoding unit of the genetic algorithm optimization module, the initial control parameter solution set output end of the genetic algorithm optimization module is connected to the chromosome analysis unit of the dynamic mode switching module, the mixing ratio correction parameter output end of the dynamic mode switching module is connected to the valve gradient calculation unit of the thermal stress suppression module, the valve control sequence feedback end of the thermal stress suppression module is connected to the extraction volume adjustment factor calculation unit of the dynamic mode switching module, and the weight update signal output end of the self-learning update module is respectively connected to the fitness calculation unit of the genetic algorithm optimization module and the weight distribution calculation unit of the dynamic mode switching module.

[0007] Furthermore, the waste heat recovery heating system based on the ejector heat pump of the present invention, the thermal stress suppression module, comprises: Receive the heat transfer end difference time series data collected by the distributed temperature field scanner, identify the temperature abnormal fluctuation area through the K-means clustering algorithm, generate the valve opening gradient adjustment sequence based on the mixing ratio correction parameter sent by the dynamic mode switching module, reversely calculate the mixed working fluid pressure change rate according to the valve action sequence, select the control scheme that meets the thermal stress accumulation threshold through the elite retention strategy, and feed back the optimized valve control sequence to the suction volume adjustment factor calculation unit of the dynamic mode switching module. The elite retention strategy retains the chromosome individuals ranked in the top 10% of fitness during the iteration process of the genetic algorithm, and directly enters the next generation population to avoid the loss of high-quality solutions; Furthermore, the waste heat recovery heating system based on the induced heat pump of the present invention, the self-learning update module comprises: Receive the pressure fluctuation suppression data of the thermal stress suppression module and the weight allocation history data of the dynamic mode switching module, build a correlation matrix between energy cascade utilization efficiency and equipment reliability index, adjust the parameter weights of the genetic algorithm fitness function based on the correlation matrix, and transmit the updated weight coefficients to the population initialization unit of the genetic algorithm optimization module and the candidate solution generation unit of the dynamic mode switching module through a bidirectional data channel.

[0008] Furthermore, in the waste heat recovery heating system based on the induced heat pump described in the present invention, the dynamic mode switching module includes: a power surplus mode analysis unit, which inputs the power fluctuation amplitude in the power grid peak-shaving instruction into the electric boiler start-stop probability model, and outputs the start-stop threshold parameters matching the current waste heat recovery rate, wherein the electric boiler start-stop probability model is constructed based on historical power peak-shaving data, and calculates the mapping relationship between the power grid power fluctuation amplitude and the electric boiler start-stop threshold through a logistic regression algorithm; The waste heat gap compensation unit receives the condensate split ratio parameter output by the genetic algorithm optimization module, combines the real-time monitoring data of the heat network return water flow meter, and generates a set of candidate solutions for the extraction volume adjustment factor through a sliding average algorithm; The start / stop threshold parameters of the power surplus mode analysis unit and the candidate solution set of the waste heat gap compensation unit are dynamically weighted in a sliding time window based on the heat network load forecasting model, and a steam generation weight instruction is generated and transmitted to the electric boiler control unit, and the mixing ratio correction parameter is sent to the valve timing mapping unit of the thermal stress suppression module; The thermal stress suppression module comprises: The temperature field cluster analysis unit performs K-means cluster analysis on the heat transfer end difference time series data collected by the distributed temperature scanner to identify the coordinates of abnormal areas that exceed the preset fluctuation threshold; a valve action optimization unit, receiving the mixture ratio correction parameter sent by the dynamic mode switching module, generating a valve opening gradient adjustment sequence based on the abnormal area coordinates, and inputting the adjustment sequence to the pressure fluctuation suppression unit; The pressure fluctuation suppression unit calculates the pressure change rate of the mixed working fluid according to the valve gradient adjustment sequence, selects the control scheme that meets the preset thermal stress accumulation rate through the elite retention strategy, and feeds back the optimized valve control sequence to the extraction volume adjustment factor candidate solution generation unit of the dynamic mode switching module.

[0009] Furthermore, in the waste heat recovery heating system based on the induced heat pump of the present invention, the self-learning update module includes: a multi-objective evaluation unit, which receives the working fluid pressure change rate parameter in the pressure fluctuation suppression data of the thermal stress suppression module and the steam generation weight history value in the weight allocation data of the dynamic mode switching module, and constructs a correlation matrix including the energy cascade utilization efficiency coefficient and the equipment reliability attenuation coefficient; The rule base updating unit adjusts the weight ratio of the power grid peak load response speed in the fitness function of the genetic algorithm based on the coefficient correlation analysis result in the association matrix, and transmits the updated weight coefficient to the chromosome encoding weight register in the population initialization unit of the genetic algorithm optimization module through the data bus.

[0010] Furthermore, in the waste heat recovery heating system based on the ejector heat pump described in the present invention, the genetic algorithm optimization module includes: a chromosome encoding unit, which converts the ejector mixing ratio parameter into a binary gene segment according to a preset bit width, and linearly maps the valve opening parameter into a decimal code according to 0-100%, forming a mixed coding structure including a gene type identifier; A fitness calculation unit receives the weight coefficient register data transmitted by the self-learning update module, calculates the waste heat utilization rate in the energy recovery efficiency index, the instruction execution delay time in the power grid peak load response speed index, and the valve action frequency in the equipment loss rate index, and generates a multi-dimensional evaluation index vector; Among them, the mixed encoding data stream of the chromosome encoding unit and the evaluation index vector of the fitness calculation unit are jointly input into the crossover mutation operation unit based on the roulette selection strategy to generate a control parameter solution set that meets the waste heat recovery rate threshold and the equipment loss rate threshold.

[0011] Furthermore, the waste heat recovery heating system based on the induced heat pump of the present invention further comprises: The historical optimal solution cache module stores the optimal chromosome encoding data of all generations generated by the genetic algorithm optimization module and records the corresponding residual heat temperature fluctuation characteristic values; A working condition matching unit receives the principal component analysis dimensionality reduction result in the real-time characteristic parameters output by the multi-source data acquisition module, retrieves similar working condition data by using the cosine similarity algorithm in the historical optimal solution cache module, and generates an acceleration parameter set including an initial population size and a gene mutation rate; Among them, the acceleration parameter set of the working condition matching unit is transmitted to the chromosome preloading buffer area in the population initialization unit of the genetic algorithm optimization module through the DMA channel, so as to realize the matching and recombination of the historical optimal chromosome fragment and the real-time working condition characteristics.

[0012] Furthermore, in the waste heat recovery heating system based on an ejector heat pump described in the present invention, the multi-source data acquisition module includes: The time series data fusion unit implements sliding window smoothing based on Z-score standardization processing on the original sampling data of the industrial waste heat temperature sensor array, and the window width is dynamically adjusted according to the change rate of the heat network load; the feature dimension reduction unit uses the principal component analysis method to screen the variance contribution rate of the standardized multidimensional data, extracts the core feature vectors with a cumulative contribution rate of more than 85%, and generates the initial input parameter set of the genetic algorithm optimization module; Among them, the core feature vector output by the feature dimension reduction unit is matched with the operating condition data stored in the historical optimal solution cache module by Mahalanobis distance similarity through the feature space projection algorithm. When the similarity exceeds the set threshold, the elite retention ratio in the population initialization parameters of the genetic algorithm optimization module is adjusted.

[0013] Beneficial effects of the present invention: The present invention obtains industrial waste heat temperature, power grid load and heat network flow data in real time through a multi-source data acquisition module, extracts core feature vectors through principal component analysis and inputs them into a genetic algorithm optimization module, and adopts a hybrid coding chromosome structure to dynamically optimize the ejector mixing ratio, valve opening and condensate diversion ratio parameters, thereby improving waste heat recovery efficiency and reducing energy waste; the dynamic mode switching module triggers dual-path adjustment based on the waste heat-heating deviation threshold, and realizes precise adaptation of power peak-shaving demand and heating load through the weight fusion of the electric boiler start-stop probability model and the candidate solution of the extraction volume adjustment factor, breaking through the rigid constraints of the thermoelectric coupling of the traditional system; the thermal stress suppression module combines the temperature field clustering analysis and the elite retention strategy to generate a valve gradient control sequence, and corrects the pressure fluctuation of the mixed working fluid in real time through a closed-loop feedback mechanism, effectively reducing the accumulation of thermal stress caused by abnormal fluctuations in the heat transfer end difference; the self-learning update module constructs a multi-parameter association matrix to dynamically adjust the weight of the genetic algorithm fitness function, and combines the historical optimal solution cache with the working condition matching mechanism to form a parameter iterative optimization across time dimensions, so that the system can adapt to the fluctuation of industrial waste heat sources and seasonal load changes, and comprehensively solve the problems of low energy utilization efficiency and poor equipment reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0015] Figure 1 A schematic diagram of the non-heating season system operation of a waste heat recovery heating system based on an ejection heat pump provided in an embodiment of the present invention.

[0016] Figure 2A closed cycle schematic diagram of a non-heating season operation mode of a waste heat recovery heating system based on an ejector heat pump provided in an embodiment of the present invention.

[0017] Figure 3 Schematic diagram of industrial waste heat and high back pressure condensed water in a waste heat recovery heating system based on an ejector heat pump provided in an embodiment of the present invention that can meet the heating load Figure 4 Schematic diagram of the waste heat recovery heating system based on the ejector heat pump provided in the embodiment of the present invention, where the industrial waste heat and high back pressure condensed water cannot meet the heating load, and the power grid has surplus electricity Figure 5 Schematic diagram of the waste heat recovery heating system based on the ejection heat pump provided in the embodiment of the present invention, in which the industrial waste heat and high back pressure condensed water cannot meet the heating load, and the power grid has no surplus electricity. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings. In order to better understand the purpose of the present invention, the present invention is further described in detail below.

[0019] The present invention provides a waste heat recovery heating system based on an ejector heat pump, comprising: See also Figures 1 to 5 The present invention provides a waste heat recovery heating system based on an ejector heat pump, comprising: The multi-source data acquisition module collects industrial waste heat temperature data in real time through the distributed temperature sensor array deployed at the outlet of the waste heat steam generator, the condenser tube bundle area and the return water pipe of the heat network, and obtains the cooling water circulation flow parameters in combination with the electromagnetic flowmeter. The sliding time window algorithm is used to standardize the temperature and flow data. The window length is dynamically adjusted according to the load change rate of the heat network, and the standard deviation of the waste heat temperature fluctuation and the deviation rate of the return water flow of the heat network are extracted as the core feature vector. The multidimensional data is reduced in dimension by the principal component analysis method, and the principal components with a cumulative variance contribution rate of more than 85% are selected as the input parameters of the genetic algorithm optimization module to eliminate the influence of redundant data on the optimization process. The feature dimension reduction unit uses the principal component analysis method to calculate the variance contribution rate of the standardized multidimensional data, and selects the principal components with a cumulative contribution rate of more than 85% as the core feature vector after arranging in descending order, and eliminates redundant data dimensions.

[0020] After receiving the feature vector, the genetic algorithm optimization module converts the ejector mixing ratio parameter into binary code according to the preset bit width, and the valve opening parameter is linearly mapped to generate a decimal code to form a mixed chromosome structure including a gene type identifier. A sliding time window constraint parameter search space is constructed based on the real-time data stream, and a crossover mutation operation is performed within the window. The control parameter solution set that meets the waste heat recovery rate threshold and the equipment loss rate threshold is selected through a roulette selection strategy. The fitness function calculation unit integrates three indicators: waste heat utilization rate, power grid peak load response speed, and valve action frequency. The weight coefficient is dynamically adjusted by the self-learning update module to achieve multi-objective optimization balance. In the chromosome coding unit of the genetic algorithm optimization module, the ejector mixing ratio parameter is converted into a binary gene fragment according to the preset bit width (for example, 4 bits), and the valve opening parameter is linearly mapped from 0 to 100% to a decimal code to form a mixed coding structure including a gene type identifier to ensure the coding compatibility of different parameter types.

[0021] The dynamic mode switching module parses the control parameter solution set output by the genetic algorithm, and triggers the multi-path adjustment mechanism when the deviation rate between the waste heat supply and the heat network load exceeds 15%. In the power surplus mode, the operating condition data of the electric boiler in the historical database is called, the power grid peak load instruction is converted into the valve start and stop probability threshold, and the electric boiler collaborative control instruction is generated; when there is no power surplus, the extraction volume compensation coefficient is calculated based on the PID algorithm to adjust the opening of the steam turbine extraction valve. The two types of candidate solutions are dynamically fused through the sliding time window weight allocation algorithm, and the steam generation weight instruction is output to the actuator, and the mixing ratio correction parameter is sent to the thermal stress suppression module simultaneously. The waste heat-heating matching degree deviation threshold is determined by analyzing the historical operating condition data, and is dynamically adjusted based on the correlation between the heat network load deviation rate and the waste heat temperature fluctuation standard deviation; when the deviation rate exceeds the preset range (for example, 10%-20%), the multi-path adjustment mechanism is triggered.

[0022] After receiving the distributed temperature field scanning data, the thermal stress suppression module uses the K-means clustering algorithm to identify the area of ​​abnormal fluctuation of the heat transfer end difference, and generates a valve opening gradient adjustment sequence according to the temperature gradient distribution. The pressure fluctuation suppression unit reversely calculates the impact of valve action on the pressure of the mixed working fluid, and screens the optimal control scheme with the thermal stress accumulation rate meeting the standard through the elite retention strategy. The optimized valve control sequence is fed back to the candidate solution generation unit of the dynamic mode switching module to form a closed-loop regulation mechanism to suppress the impact of abnormal fluctuation of the heat transfer end difference on the stability of the equipment. The temperature field clustering analysis unit performs K-means clustering analysis on the time series data collected by the distributed temperature scanner, sets the initial cluster center as the median of the temperature distribution, iteratively calculates the Euclidean distance between each temperature measurement point and the cluster center, and identifies the coordinates of the abnormal area that exceeds the preset fluctuation threshold.

[0023] The self-learning update module constructs the correlation matrix between energy cascade utilization efficiency and equipment reliability indicators, and analyzes the parameter correlation of waste heat utilization rate, valve loss rate and peak load response speed. The rule base update operation is performed every 24 hours. When it is detected that the ejector mixing ratio and waste heat utilization rate show a strong correlation, the weight ratio of this parameter in the genetic algorithm fitness function is increased. The updated weight coefficient is transmitted to the chromosome encoding weight register through the data bus, dynamically optimizes the population initialization rules, and reversely corrects the weight allocation calculation logic of the dynamic mode switching module.

[0024] The historical optimal solution cache module stores the optimal chromosome codes of all generations and their corresponding residual heat temperature fluctuation characteristic values, and matches the real-time working conditions with historical data through the cosine similarity algorithm. When the similarity between the core feature vector output by the feature dimension reduction unit and the cached data exceeds the set threshold, the elite retention ratio adjustment mechanism is triggered to accelerate the convergence speed of the genetic algorithm. The initial population size and gene mutation rate parameters generated by the working condition matching unit are directly written into the chromosome preload cache area through the DMA channel to achieve rapid recombination of the historical optimal solution and real-time operation characteristics.

[0025] During the collaborative work of multiple modules, the feature extraction accuracy of the data acquisition module directly affects the optimization effect of the genetic algorithm, and the control parameters output by the optimization module determine the adjustment strategy of the dynamic mode switching. The closed-loop feedback mechanism of the thermal stress suppression module provides pressure fluctuation data support for self-learning updates, and the rule iteration of the self-learning module further optimizes the decision logic of the genetic algorithm and mode switching module. The historical data cache and operating condition matching mechanism form experience reuse across time dimensions, enabling the system to adapt to seasonal load fluctuations and residual heat source instability, and build a full-link intelligent control system from data acquisition, optimization decision-making to execution feedback.

[0026] The non-heating season system operation in the technical solution of the present invention includes the following technical contents: See also Figure 1 , open valves 1 and 3; close valves 2, 4, 5, 6, 7, and 8. The turbine back pressure is switched to about 8 kpa for operation. After absorbing heat in the condenser, the cooling water flows to the cooling tower to dissipate heat, and returns to the condenser after cooling, forming a closed cycle. For specific operation methods, please refer to Figure 2 .

[0027] Embodiment 1; See also Figure 3 ,exist Figure 3In the operation mode shown, the multi-source data acquisition module collects steam temperature and return water flow data at a frequency of 1Hz through the temperature sensor (measurement point T1) deployed at the outlet of the waste heat steam generator and the flowmeter (measurement point F1) of the heat network return water pipe. The sliding time window algorithm is used to calculate the standard deviation of the T1 temperature data for 15 consecutive minutes. When the fluctuation value exceeds 5°C, the genetic algorithm optimization module is triggered, and the ejector mixing ratio parameter is encoded into a 4-bit binary gene fragment (accuracy 0.1), and the opening parameters of valves 2 / 4 / 7 / 8 are linearly mapped from 0-100% to decimal encoding, generating a mixed chromosome including the condensate diversion ratio threshold. The fitness function constructs an evaluation index based on the waste heat utilization rate (actual recovered heat / theoretical maximum value) and valve action frequency (number of opening changes per unit time) calculated in real time, and selects the optimal solution set through the roulette selection strategy, which is output to the dynamic mode switching module to generate valve control instructions.

[0028] Embodiment 2; See also Figure 4 , when the system switches to Figure 4 When the electric boiler is in the supplementary heating mode shown in the figure, the dynamic mode switching module receives the power surplus signal transmitted by the grid load monitoring unit (lasting ≥30 minutes). The electric boiler start-stop probability model is called to convert the grid peak load regulation instruction into the opening probability threshold of valve 6 (start the electric boiler when P≥0.8). At the same time, the condensate split ratio parameter output by the genetic algorithm optimization module is weightedly calculated with the heat network return water flow deviation rate to generate the coordinated control instruction of valves 2 / 4 / 6 / 8. The thermal stress suppression module collects the temperature field data of the condenser tube bundle area in real time (such as Figure 2 The 5×5 temperature measurement matrix deployed in the dotted box area is used to identify abnormal areas with temperature gradient > 2°C / m, generate the opening gradient adjustment instruction of valve 7 (adjustment amount = historical optimal value × 0.8 + real-time temperature gradient × 0.2), and feed the optimized control sequence back to the dynamic mode switching module to form a closed loop.

[0029] Embodiment 3; Please refer to Figure 5. Figure 5In the exhaust adjustment mode shown, the self-learning update module calls similar operating data in the historical database (heating network load deviation rate 15%-20% range) and matches the optimal exhaust volume adjustment factor through the cosine similarity algorithm. The dynamic mode switching module calculates the compensation opening of valve 5 based on the PID control algorithm (K_p=0.8×ΔQ / rated load, ΔQ is the residual heat gap value), and adjusts the opening combination of valves 2 / 4 / 7 / 8 at the same time. The pressure fluctuation suppression unit uses the elite retention strategy to select the control scheme that meets the thermal stress accumulation rate threshold (<0.5MPa / h) according to the mixed working fluid pressure change rate after the valve 5 is actuated, and the optimization parameters are reversely input into the population initialization unit of the genetic algorithm optimization module to update the exhaust volume weight coefficient in the chromosome encoding rule.

[0030] Embodiment 4; See also Figure 2 ,against Figure 2 In the non-heating season operation mode, the multi-source data acquisition module monitors the closed-loop parameters through the condenser outlet temperature sensor (measurement point T2) and the cooling water flow meter (measurement point F2). The feature dimension reduction unit uses the principal component analysis method to extract the T2 temperature fluctuation principal component (cumulative variance contribution rate ≥ 85%). When an abnormal temperature rise is detected (three consecutive sampling points exceed 76±2℃), the thermal stress suppression module is triggered to generate an emergency adjustment instruction for valve 1 / 3. The self-learning module records the cooling tower heat dissipation efficiency parameters in the non-heating season operation data, which is used to optimize the initial value setting of the condensate diversion ratio in the heating season mode.

[0031] The present invention uses a multi-source data acquisition module to monitor the temperature fluctuation of industrial waste heat and the load parameters of the heat network in real time, and combines the genetic algorithm optimization module to dynamically encode and optimize the ejector mixing ratio, valve opening and condensate diversion ratio. The hybrid chromosome structure is used to construct the parameter solution set, and the roulette wheel selection strategy is used to select the optimal control solution, so that the waste heat recovery process can adaptively match the changes in heat network demand, improve the gradient utilization efficiency of low-grade waste heat, and solve the energy waste problem caused by insufficient waste heat recovery in traditional systems.

[0032] In order to solve the problem of strong thermal-electric coupling dependence, the dynamic mode switching module triggers a dual-path adjustment mechanism based on the deviation between the real-time grid peak-shaving instruction and the waste heat-heating matching degree. When there is a surplus of electricity, the electric boiler start-stop probability model is called to generate a heat supplement instruction. When there is no surplus, the PID algorithm is used to calculate the air extraction adjustment factor. The sliding time window weight allocation algorithm is combined to fuse the two types of candidate solutions and dynamically allocate the steam generation weight. This design breaks the traditional system's single reliance on turbine extraction operation mode, realizes thermal-electric decoupling regulation, and enhances the system's response flexibility in power peak-shaving scenarios.

[0033] For the accumulation of thermal stress caused by the heat transfer temperature difference, the thermal stress suppression module uses distributed temperature field scanning and cluster analysis technology to identify the abnormal fluctuation area of ​​the heat transfer end difference and generate a valve gradient adjustment sequence. The pressure fluctuation suppression scheme is screened through the elite retention strategy, and the optimized control parameters are fed back to the dynamic mode switching module to form a closed-loop regulation. At the same time, the self-learning update module constructs a multi-parameter association matrix, dynamically corrects the genetic algorithm fitness function weights and control rule library, continuously optimizes the valve action timing and the mixed working fluid pressure stability, reduces the heat transfer end difference from the source and suppresses the growth of thermal stress.

Claims

1. A waste heat recovery heating system based on an ejector heat pump, characterized in that: include: The multi-source data acquisition module integrates a temperature sensor array, a load monitoring unit, and a flow metering device. It processes industrial waste heat temperature data through a sliding window standardization method, extracts the characteristic vector of the power grid peak-shaving demand using principal component analysis, and outputs the heat network load parameters to the genetic algorithm optimization module. A genetic algorithm optimization module receives the characteristic vector of the multi-source data acquisition module, encodes the ejector mixing ratio parameter into a binary gene fragment, uses decimal encoding for the valve opening parameter to form a mixed chromosome structure, constructs a sliding time window constraint parameter search space based on the real-time data stream, generates an initial control parameter solution set including the condensate split ratio parameter, and transmits it to the dynamic mode switching module; The dynamic mode switching module analyzes the chromosome encoding data of the initial control parameter solution set. When the waste heat-heating matching degree deviation exceeds the set threshold, the electric boiler operating condition data in the historical power mode database is called, and the grid peak load instruction is input into the electric boiler start-stop probability model to generate a candidate solution for the start-stop instruction. At the same time, the candidate solution for the extraction volume adjustment factor is generated in combination with the change trend of the return water flow of the heating network. After the sliding time window weight allocation calculation is performed on the two types of candidate solutions, the steam generation weight instruction is output to the actuator, and the mixing ratio correction parameter is sent to the thermal stress suppression module; The thermal stress suppression module receives the heat transfer end difference time series data collected by the distributed temperature field scanner, generates an optimized valve control sequence, and feeds the optimized valve control sequence back to the air extraction adjustment factor calculation unit of the dynamic mode switching module; The self-learning update module receives the pressure fluctuation suppression data of the thermal stress suppression module and the weight allocation history data of the dynamic mode switching module, and transmits the updated weight coefficient to the population initialization unit of the genetic algorithm optimization module and the candidate solution generation unit of the dynamic mode switching module through a bidirectional data channel.

2. The waste heat recovery heating system based on an ejector heat pump according to claim 1 is characterized in that: Also includes: Among them, the characteristic vector output end of the multi-source data acquisition module is connected to the chromosome encoding unit of the genetic algorithm optimization module, the initial control parameter solution set output end of the genetic algorithm optimization module is connected to the chromosome analysis unit of the dynamic mode switching module, the mixing ratio correction parameter output end of the dynamic mode switching module is connected to the valve gradient calculation unit of the thermal stress suppression module, the valve control sequence feedback end of the thermal stress suppression module is connected to the extraction volume adjustment factor calculation unit of the dynamic mode switching module, and the weight update signal output end of the self-learning update module is respectively connected to the fitness calculation unit of the genetic algorithm optimization module and the weight distribution calculation unit of the dynamic mode switching module.

3. The waste heat recovery heating system based on an ejector heat pump according to claim 1 is characterized in that: Thermal stress suppression module, including: The heat transfer end difference time series data collected by the distributed temperature field scanner is received, the temperature abnormal fluctuation area is identified by the K-means clustering algorithm, the valve opening gradient adjustment sequence is generated based on the mixing ratio correction parameter sent by the dynamic mode switching module, the mixed working fluid pressure change rate is reversely calculated according to the valve action sequence, the control scheme that meets the thermal stress accumulation threshold is screened by the elite retention strategy, and the optimized valve control sequence is fed back to the extraction volume adjustment factor calculation unit of the dynamic mode switching module.

4. The waste heat recovery heating system based on an ejector heat pump according to claim 1 is characterized in that: Self-learning update module, including: Receive the pressure fluctuation suppression data of the thermal stress suppression module and the weight allocation history data of the dynamic mode switching module, build a correlation matrix between energy cascade utilization efficiency and equipment reliability index, adjust the parameter weights of the genetic algorithm fitness function based on the correlation matrix, and transmit the updated weight coefficients to the population initialization unit of the genetic algorithm optimization module and the candidate solution generation unit of the dynamic mode switching module through a bidirectional data channel.

5. The waste heat recovery heating system based on an ejector heat pump according to claim 1, characterized in that: The dynamic mode switching module includes: a power surplus mode analysis unit, which inputs the power fluctuation amplitude in the power grid peak load regulation instruction into the electric boiler start-stop probability model, and outputs the start-stop threshold parameters matching the current waste heat recovery rate; The waste heat gap compensation unit receives the condensate split ratio parameter output by the genetic algorithm optimization module, combines the real-time monitoring data of the heat network return water flow meter, and generates a set of candidate solutions for the extraction volume adjustment factor through a sliding average algorithm; The start / stop threshold parameters of the power surplus mode analysis unit and the candidate solution set of the waste heat gap compensation unit are dynamically weighted in a sliding time window based on the heat network load forecasting model, and a steam generation weight instruction is generated and transmitted to the electric boiler control unit, and the mixing ratio correction parameter is sent to the valve timing mapping unit of the thermal stress suppression module; The thermal stress suppression module comprises: The temperature field cluster analysis unit performs K-means cluster analysis on the heat transfer end difference time series data collected by the distributed temperature scanner to identify the coordinates of abnormal areas that exceed the preset fluctuation threshold; a valve action optimization unit, receiving the mixture ratio correction parameter sent by the dynamic mode switching module, generating a valve opening gradient adjustment sequence based on the abnormal area coordinates, and inputting the adjustment sequence to the pressure fluctuation suppression unit; The pressure fluctuation suppression unit calculates the pressure change rate of the mixed working fluid according to the valve gradient adjustment sequence, selects the control scheme that meets the preset thermal stress accumulation rate through the elite retention strategy, and feeds back the optimized valve control sequence to the extraction volume adjustment factor candidate solution generation unit of the dynamic mode switching module.

6. The waste heat recovery heating system based on an ejector heat pump according to claim 1, characterized in that: The self-learning update module includes: a multi-objective evaluation unit, which receives the working fluid pressure change rate parameter in the pressure fluctuation suppression data of the thermal stress suppression module and the steam generation weight history value in the weight allocation data of the dynamic mode switching module, and constructs a correlation matrix including the energy cascade utilization efficiency coefficient and the equipment reliability attenuation coefficient; The rule base updating unit adjusts the weight ratio of the power grid peak load response speed in the fitness function of the genetic algorithm based on the coefficient correlation analysis result in the association matrix, and transmits the updated weight coefficient to the chromosome encoding weight register in the population initialization unit of the genetic algorithm optimization module through the data bus.

7. The waste heat recovery heating system based on an ejector heat pump according to claim 1, characterized in that: The genetic algorithm optimization module includes: a chromosome encoding unit, which converts the ejector mixing ratio parameter into a binary gene segment according to a preset bit width, and linearly maps the valve opening parameter into a decimal code according to 0-100%, forming a mixed coding structure including a gene type identifier; A fitness calculation unit receives the weight coefficient register data transmitted by the self-learning update module, calculates the waste heat utilization rate in the energy recovery efficiency index, the instruction execution delay time in the power grid peak load response speed index, and the valve action frequency in the equipment loss rate index, and generates a multi-dimensional evaluation index vector; Among them, the mixed encoding data stream of the chromosome encoding unit and the evaluation index vector of the fitness calculation unit are jointly input into the crossover mutation operation unit based on the roulette selection strategy to generate a control parameter solution set that meets the waste heat recovery rate threshold and the equipment loss rate threshold.

8. The waste heat recovery heating system based on an ejector heat pump according to claim 1, characterized in that: The system further comprises: The historical optimal solution cache module stores the optimal chromosome encoding data of all generations generated by the genetic algorithm optimization module and records the corresponding residual heat temperature fluctuation characteristic values; A working condition matching unit receives the principal component analysis dimensionality reduction result in the real-time characteristic parameters output by the multi-source data acquisition module, retrieves similar working condition data by using the cosine similarity algorithm in the historical optimal solution cache module, and generates an acceleration parameter set including an initial population size and a gene mutation rate; Among them, the acceleration parameter set of the working condition matching unit is transmitted to the chromosome preloading buffer area in the population initialization unit of the genetic algorithm optimization module through the DMA channel, so as to realize the matching and recombination of the historical optimal chromosome fragment and the real-time working condition characteristics.

9. The waste heat recovery heating system based on an ejector heat pump according to any one of claims 1 to 8, characterized in that: The multi-source data acquisition module comprises: The time series data fusion unit implements sliding window smoothing based on Z-score standardization processing on the original sampling data of the industrial waste heat temperature sensor array, and the window width is dynamically adjusted according to the change rate of the heat network load; the feature dimension reduction unit uses the principal component analysis method to screen the variance contribution rate of the standardized multidimensional data, extracts the core feature vectors with a cumulative contribution rate of more than 85%, and generates the initial input parameter set of the genetic algorithm optimization module; Among them, the core feature vector output by the feature dimension reduction unit is matched with the operating condition data stored in the historical optimal solution cache module by Mahalanobis distance similarity through the feature space projection algorithm. When the similarity exceeds the set threshold, the elite retention ratio in the population initialization parameters of the genetic algorithm optimization module is adjusted.

Images