Front heat extraction type heat pump energy recovery system and method thereof

By introducing a pre-heat extraction heat pump energy recovery system and optimization algorithm into the distillation tower system, the problem of large steam consumption at the bottom of the distillation tower is solved, and the energy recovery efficiency and energy consumption are improved, which has significantly improved The economical and environmentally friendly performance of the system.

CN118949451AInactive Publication Date: 2024-11-15JIANGSU KECHENG ENERGY SAVING TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411092868.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing distillation towers have a large amount of steam at the bottom in industrial production, resulting in low energy utilization efficiency and limiting the practical application effect of the heat pump energy recovery system.

Method used

Adopt the energy recovery system of pre-heat extraction heat pump, including distillation tower, heat exchanger, material separator, condenser and vapor compressor, combining the optimal planning algorithm for energy recovery path, nuclear limit learning machine (KELM) model and improvement The whale optimization algorithm (IWOA+WOA) optimizes system operation strategies to improve energy recovery efficiency through sensor data acquisition and preprocessing.

Benefits of technology

It effectively reduces the load of the distillation section of the distillation tower, reduces the steam consumption at the bottom of the tower, reduces energy consumption by 45-65%, and improves the energy utilization efficiency and the economic benefits and environmental performance of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118949451A_ABST
    Figure CN118949451A_ABST
Patent Text Reader

Abstract

The invention discloses a front heat extraction type heat pump energy recovery system and method. The system comprises a rectifying tower, a heat exchanger, a material separator, a condenser, a steam compressor and a water pump. Steam generated by the rectifying tower enters a heat exchanger and exchanges heat with the decompressed material, so that the material with lower original temperature is heated and vaporized; the material separator is used for carrying out gas-liquid separation on the materials after heat exchange is completed; the water pump is used for pumping a liquid phase separated by the material separator to the rectifying tower; the steam compressor is used for compressing a gas phase separated by the separator into the rectifying tower; and the condenser is used for condensing the material gas phase of the heat exchanger. According to the front heat extraction type heat pump energy recovery system, materials are vaporized into high gas phase fraction or dew point feeding from original low temperature, and the pressure and enthalpy value are increased through compression of the compressor. And the load of the stripping section of the rectifying tower is effectively reduced. The steam consumption at the bottom of the original rectifying tower is greatly reduced, and the energy consumption of the rectifying tower can be reduced by 45-65%.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of heat pump energy recovery, and in particular relates to a pre-heating heat pump energy recovery system and a method thereof. Background Art

[0002] In industrial production, improving energy efficiency has always been the focus of attention. As a technical means to achieve the recovery and utilization of heat energy, heat pumps have been widely used in industrial production and life. However, in the stripping section of the distillation tower, there will be a large load and a large amount of steam at the bottom of the distillation tower, which makes the original distillation tower use a large amount of steam at the bottom, limiting its effect in practical applications.

[0003] Therefore, the present invention aims to provide a pre-heating heat pump energy recovery system and method to solve the problem of large energy loss in the prior art. Summary of the invention

[0004] The purpose of the present invention is to provide a preheating heat pump energy recovery system and method thereof to solve the technical problems raised in the background technology.

[0005] To achieve the above object, the specific technical scheme of the present invention is as follows: a preheating heat pump energy recovery system, comprising a distillation tower, a heat exchanger, a material separator, a condenser, a steam compressor and a water pump;

[0006] The steam generated by the distillation tower is sent to the heat exchanger to exchange heat with the decompressed material so that the material with a lower original temperature is heated and vaporized;

[0007] The material separator is used to separate the material into gas and liquid after the heat exchange is completed;

[0008] The water pump is used to pump the liquid phase separated by the material separator to the distillation tower;

[0009] The steam compressor is used to compress the gas phase separated by the separator into the distillation tower;

[0010] The condenser is used to condense the gas phase of the material in the heat exchanger.

[0011] The specific steps of the method for heat pump energy recovery are as follows:

[0012] Step 1: The steam generated by the distillation tower exchanges heat with the material after decompression in the heat exchanger, so that the material with a lower original temperature is heated and the high gas phase fraction or dew point feed is vaporized;

[0013] Step 2: After the heat exchange is completed, part of the material is separated into gas and liquid through the separator, the gas phase is compressed into the distillation tower by the compressor, and the liquid phase is pumped into the distillation tower by the water pump;

[0014] Step 3: After the heat exchange is completed, part of the material is condensed through a condenser, and part of the liquid phase produced by the condensation is refluxed to the distillation tower, and part of the liquid phase is extracted.

[0015] The specific steps of heat pump energy recovery include adding an energy recovery path optimal planning algorithm to improve energy recovery efficiency and reduce system energy consumption. The specific steps are as follows:

[0016] Step 1: Sensor selection and installation:

[0017] First is the temperature sensor, installation location:

[0018] Distillation tower: installed at the bottom, middle and top of the tower to monitor temperature changes at different heights;

[0019] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the temperature of the materials entering and leaving the heat exchanger;

[0020] Condenser: Installed at the inlet and outlet of the condenser to monitor the gas temperature entering and leaving the condenser;

[0021] Steam compressor: Installed at the inlet and outlet of the compressor to monitor the steam temperature before and after compression;

[0022] Water pump: Installed at the inlet and outlet of the water pump to monitor the water temperature;

[0023] Temperature change rate = (T2-T1) / Δt

[0024] Where T1 is the initial temperature of the sensor, T2 is the current temperature of the sensor, and Δt is the time interval;

[0025] Pressure sensor, installation location:

[0026] Steam compressor: installed at the inlet and outlet of the compressor to monitor the pressure before and after steam compression;

[0027] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the pressure entering and leaving the heat exchanger;

[0028] Pressure change rate = (P2-P1) / Δt

[0029] Among them, P1 is the initial pressure of the sensor, and P2 is the current pressure of the sensor;

[0030] Flow sensor, installation location:

[0031] Material separator: Installed at the inlet and outlet of the separator to monitor the inlet and outlet fluid flow;

[0032] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the flow of the fluid;

[0033] Condenser: Installed at the inlet and outlet of the condenser to monitor the flow of the fluid;

[0034] Flow rate change = (F2-F1) / Δt

[0035] Among them, F1 is the initial flow rate of the sensor, and F2 is the current flow rate of the sensor;

[0036] Liquid level sensor, installation location:

[0037] Distillation tower: installed at different heights in the tower to monitor liquid level changes;

[0038] Material separator: installed at different positions in the separator to monitor liquid level changes;

[0039] Liquid level change rate = (L2-L1) / Δt

[0040] Among them, L1 is the initial liquid level of the sensor, and L2 is the current liquid level of the sensor;

[0041] Step 2: Data collection and preprocessing

[0042] The first step is data cleaning:

[0043] Use a smoothing filter to smooth the data and remove high-frequency noise, and use a median filter to remove spike noise; use 3σ to detect and remove outliers, and use the box plot method to detect and remove outliers;

[0044]

[0045] Abnormal value range = [μ-3σ, μ+3σ]

[0046] Among them, x i is the i-th data point, N is the total number of data, and μ is the mean value of the data;

[0047] Next, data standardization:

[0048] Transform the data into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0049]

[0050] Among them, X std is the standardized data, and x is the original data;

[0051] Finally, select the features:

[0052] Temperature gradient: reflects the rate of change of temperature over time or location.

[0053]

[0054] Pressure change rate: reflects the rate at which pressure changes with time or position.

[0055]

[0056] Flow rate of change: reflects the rate of change of flow over time or location.

[0057]

[0058] Liquid level change rate: reflects the rate of change of liquid level over time.

[0059]

[0060] Among them, ΔT is the temperature change, Δt is the time change, ΔP is the pressure change, ΔF is the flow change, and ΔL is the liquid level change;

[0061] Step 3: Definition of system energy recovery model

[0062] Establish the energy recovery model of the system. The objective function of the model includes energy recovery rate and system efficiency. These two indicators can effectively evaluate the performance and optimization effect of the system:

[0063] The energy recovery rate is defined as the ratio of the energy recovered by the system to the input energy, which is used to measure the efficiency of the system in recovering energy;

[0064]

[0065] System efficiency is defined as the ratio of effective energy output to total energy input, which is used to measure the overall energy utilization efficiency of the system;

[0066]

[0067] Where η is the energy recovery rate, E recovered is the recovered energy, E input is the input energy, E is the system efficiency, E useful is the effective energy output, E total is the total energy input;

[0068] Step 4: Improved whale algorithm to optimize kernel extreme learning machine

[0069] Kernel Extreme Learning Machine (KELM) is a fast and effective regression and classification method suitable for dealing with nonlinear relationships. It maps data into high-dimensional space through kernel functions, thereby achieving the learning of complex relationships.

[0070] Input: pre-processed sensor data, including temperature, pressure, flow and level;

[0071] Output: system energy recovery rate and system efficiency;

[0072] Collect and pre-process sensor data;

[0073] Split the data into training and testing sets;

[0074] KELM model training:

[0075] Select radial basis function RBF as the kernel function;

[0076] Set the kernel function parameters, kernel width σ and regularization parameter λ;

[0077] Train the model to minimize the training error;

[0078] H = kernel(X,X)

[0079] Hβ=T

[0080]

[0081] Among them, H is the hidden layer output matrix, β is the output weight, T is the target output, is a pseudo-example of H;

[0082] The test set data was used to verify the predictive performance of the model and ensure that the model had good generalization ability, using mean square error (MSE), coefficient of determination (R 2 ) is the basis for judgment:

[0083]

[0084] Among them, y i is the true value, is the predicted value, N is the number of samples, is the mean of the true value, i represents the i-th sample;

[0085] Finally, in order to optimize the prediction performance of the KELM model, the improved whale optimization algorithm (IWOA+WOA) is used for parameter optimization;

[0086] The improved whale optimization algorithm (IWOA) is an improvement on the traditional whale optimization algorithm (WOA), which improves the convergence speed and global search capability.

[0087] X(t+1)=X * (t)-A·D

[0088] Among them, X * (t) is the current optimal position, X(t+1) is the latest whale position, X(t) is the current whale position, A and D are control parameters;

[0089] A=2a·ra

[0090] D=|C·X * (t)-X(t)|

[0091] a decreases over time, linearly decreasing from 2 to 0, r is a random number between [0,1], and C is twice the random number r;

[0092]

[0093] Among them, t is the current iteration number, T is the maximum iteration number, r min and r max is the adaptive range, and the optimization stops when the number of iterations T is reached;

[0094] Step 5: Adjust system operation strategy in real time

[0095] According to the energy recovery path predicted by the KELM model, control signals are generated to adjust the actuators (compression ratio of the steam compressor and flow rate of the heat exchanger). First, the optimized KELM model is used for prediction:

[0096]

[0097] is the predicted system output, X is the input feature vector, f is the KELM model, and β is the KELM model parameter;

[0098] Then, according to the prediction results, the corresponding control signal is generated:

[0099]

[0100] Among them, u is the control signal vector, including compression ratio and flow control parameters, and g is the control signal generation function, which maps the prediction results to specific control signals;

[0101] Next, the actuator adjusts operating parameters in real time based on the control signal to ensure that the system runs along the optimal path:

[0102] Steam compressor compression ratio adjustment:

[0103]

[0104] Heat exchanger flow adjustment:

[0105] Q=m·c p ΔT

[0106] Where CR is the compression ratio, P out is the compressor outlet pressure, P in is the compressor inlet pressure, Q is the heat flow, m is the material flow, c p is the specific heat capacity of the material, ΔT is the temperature change;

[0107] Finally, the system operation status is monitored in real time, and the operating parameters are continuously adjusted through the feedback control mechanism to maintain the stability and efficient operation of the system:

[0108] Error calculation:

[0109] e(t)=y ref (t)-y(t)

[0110] Controller output:

[0111]

[0112] Parameter adjustment:

[0113] u(t+1)=u(t)+Δu(t)

[0114] Among them, e(t) is the error, y ref (t) is the reference output, y(t) is the actual output, u(t) is the controller output, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(τ) is the error value at time τ, u(t+1) is the control signal at the next moment, and Δu(t) is the adjustment amount of the control signal.

[0115] The preheating heat pump energy recovery system of the present invention has the following advantages:

[0116] The preheating heat pump energy recovery system vaporizes the material from the original low temperature to a high gas phase fraction or dew point feed, and increases the pressure and enthalpy value through compression by the compressor. It effectively reduces the load of the distillation section of the distillation tower. It greatly reduces the amount of steam used at the bottom of the original distillation tower, and can reduce the energy consumption of the distillation tower by 45-65%.

[0117] Introducing the IWOA+WOA optimized KELM model and real-time PID control strategy into the front heat extraction heat pump energy recovery system can achieve optimal planning of the energy recovery path. Through the IWOA+WOA optimization algorithm, we can accurately adjust the KELM model parameters to improve the energy recovery rate and system efficiency. Real-time PID control ensures that the system continuously adjusts the operating parameters according to real-time data during operation, eliminates steady-state errors, and enhances the stability and response speed of the system. The overall solution effectively reduces energy consumption, improves energy utilization efficiency, and significantly improves the economic benefits and environmental performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0118] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0119] Figure 1 It is the overall system principle block diagram of the present invention;

[0120] Figure 2 Flow chart of the optimal planning algorithm for energy recovery path in the present invention DETAILED DESCRIPTION

[0121] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the embodiments of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0122] In the description of the embodiments of the present invention, it should be understood that the terms "length", "vertical", "horizontal", "top", "bottom", etc. indicating the orientation or positional relationship are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present invention.

[0123] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0124] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0125] The disclosure below provides many different embodiments or examples to implement different structures of the embodiments of the present invention. In order to simplify the disclosure of the embodiments of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the embodiments of the present invention. In addition, the embodiments of the present invention can repeat reference numbers and / or reference letters in different examples, and this repetition is for the purpose of simplification and clarity, which itself does not indicate the relationship between the various embodiments and / or settings discussed.

[0126] In order to better understand the purpose, structure and function of the present invention, the pre-heating heat pump energy recovery system of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0127] like Figure 1 As shown, the pre-heating heat pump energy recovery system of the present invention includes a distillation tower, a heat exchanger, a material separator, a condenser, a steam compressor and a water pump; the steam generated by the distillation tower goes to the heat exchanger to exchange heat with the material after decompression so that the material with a lower original temperature is heated and vaporized; the material separator is used to separate the gas and liquid of the material after the heat exchange is completed; the water pump is used to pump the liquid phase separated by the material separator to the distillation tower; the steam compressor is used to compress the gas phase separated by the separator into the distillation tower; the condenser is used to condense the gas phase of the material in the heat exchanger.

[0128] The specific steps for heat pump energy recovery are as follows:

[0129] Step 1: The steam generated by the distillation tower exchanges heat with the material after decompression in the heat exchanger, so that the material with a lower original temperature is heated and the high gas phase fraction or dew point feed is vaporized;

[0130] Step 2: After the heat exchange is completed, part of the material is separated into gas and liquid through the separator, the gas phase is compressed into the distillation tower by the compressor, and the liquid phase is pumped into the distillation tower by the water pump;

[0131] Step 3: After the heat exchange is completed, part of the material is condensed through a condenser, and part of the liquid phase produced by the condensation is refluxed to the distillation tower, and part of the liquid phase is extracted.

[0132] The material is vaporized from the original low temperature to a high gas phase fraction or dew point feed, and the pressure and enthalpy value are increased by the compressor. The load of the distillation section of the distillation tower is effectively reduced. The original steam consumption at the bottom of the distillation tower is greatly reduced, and the energy consumption of the distillation tower can be reduced by 45-65%.

[0133] like Figure 2 , add an energy recovery path optimal planning algorithm to improve energy recovery efficiency and reduce system energy consumption. The specific steps are as follows:

[0134] Step 1: Sensor selection and installation:

[0135] First is the temperature sensor, installation location:

[0136] Distillation tower: installed at the bottom, middle and top of the tower to monitor temperature changes at different heights;

[0137] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the temperature of the materials entering and leaving the heat exchanger;

[0138] Condenser: Installed at the inlet and outlet of the condenser to monitor the gas temperature entering and leaving the condenser;

[0139] Steam compressor: Installed at the inlet and outlet of the compressor to monitor the steam temperature before and after compression;

[0140] Water pump: Installed at the inlet and outlet of the water pump to monitor the water temperature;

[0141] Temperature change rate = (T2-T1) / Δt

[0142] Where T1 is the initial temperature of the sensor, T2 is the current temperature of the sensor, and Δt is the time interval;

[0143] Pressure sensor, installation location:

[0144] Steam compressor: installed at the inlet and outlet of the compressor to monitor the pressure before and after steam compression;

[0145] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the pressure entering and leaving the heat exchanger;

[0146] Pressure change rate = (P2-P1) / Δt

[0147] Among them, P1 is the initial pressure of the sensor, and P2 is the current pressure of the sensor;

[0148] Flow sensor, installation location:

[0149] Material separator: Installed at the inlet and outlet of the separator to monitor the inlet and outlet fluid flow;

[0150] Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the flow of the fluid;

[0151] Condenser: Installed at the inlet and outlet of the condenser to monitor the flow of the fluid;

[0152] Flow rate change = (F2-F1) / Δt

[0153] Among them, F1 is the initial flow rate of the sensor, and F2 is the current flow rate of the sensor;

[0154] Liquid level sensor, installation location:

[0155] Distillation tower: installed at different heights in the tower to monitor liquid level changes;

[0156] Material separator: installed at different positions in the separator to monitor liquid level changes;

[0157] Liquid level change rate = (L2-L1) / Δt

[0158] Among them, L1 is the initial liquid level of the sensor, and L2 is the current liquid level of the sensor;

[0159] Step 2: Data collection and preprocessing

[0160] The first step is data cleaning:

[0161] Use a smoothing filter to smooth the data and remove high-frequency noise, and use a median filter to remove spike noise; use 3σ to detect and remove outliers, and use the box plot method to detect and remove outliers;

[0162]

[0163] Abnormal value range = [μ-3σ, μ+3σ]

[0164] Among them, x i is the i-th data point, N is the total number of data, and μ is the mean value of the data;

[0165] Next, data standardization:

[0166] Transform the data into a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0167]

[0168] Among them, X std is the standardized data, and x is the original data;

[0169] Finally, select the features:

[0170] Temperature gradient: reflects the rate of change of temperature over time or location.

[0171]

[0172] Pressure change rate: reflects the rate at which pressure changes with time or position.

[0173]

[0174] Flow rate of change: reflects the rate of change of flow over time or location.

[0175]

[0176] Liquid level change rate: reflects the rate of change of liquid level over time.

[0177]

[0178] Among them, ΔT is the temperature change, Δt is the time change, ΔP is the pressure change, ΔF is the flow change, and ΔL is the liquid level change;

[0179] Step 3: Definition of system energy recovery model

[0180] Establish the energy recovery model of the system. The objective function of the model includes energy recovery rate and system efficiency. These two indicators can effectively evaluate the performance and optimization effect of the system:

[0181] The energy recovery rate is defined as the ratio of the energy recovered by the system to the input energy, which is used to measure the efficiency of the system in recovering energy;

[0182]

[0183] System efficiency is defined as the ratio of effective energy output to total energy input, which is used to measure the overall energy utilization efficiency of the system;

[0184]

[0185] Where η is the energy recovery rate, E recovered is the recovered energy, E input is the input energy, E is the system efficiency, E useful is the effective energy output, E total is the total energy input;

[0186] Step 4: Improved whale algorithm to optimize kernel extreme learning machine

[0187] Kernel Extreme Learning Machine (KELM) is a fast and effective regression and classification method suitable for dealing with nonlinear relationships. It maps data into high-dimensional space through kernel functions, thereby achieving the learning of complex relationships.

[0188] Input: pre-processed sensor data, including temperature, pressure, flow and level;

[0189] Output: system energy recovery rate and system efficiency;

[0190] Collect and pre-process sensor data;

[0191] Split the data into training and testing sets;

[0192] KELM model training:

[0193] Select radial basis function RBF as the kernel function;

[0194] Set the kernel function parameters, kernel width σ and regularization parameter λ;

[0195] Train the model to minimize the training error;

[0196] H = kernel(X,X)

[0197] Hβ=T

[0198]

[0199] Among them, H is the hidden layer output matrix, β is the output weight, T is the target output, is a pseudo-example of H;

[0200] The test set data was used to verify the predictive performance of the model and ensure that the model had good generalization ability, using mean square error (MSE), coefficient of determination (R 2 ) is the basis for judgment:

[0201]

[0202] Among them, y i is the true value, is the predicted value, N is the number of samples, is the mean of the true value, i represents the i-th sample;

[0203] Finally, in order to optimize the prediction performance of the KELM model, the improved whale optimization algorithm (IWOA+WOA) is used for parameter optimization;

[0204] The improved whale optimization algorithm (IWOA) is an improvement on the traditional whale optimization algorithm (WOA), which improves the convergence speed and global search capability.

[0205] X(t+1)=X * (t)-A·D

[0206] Among them, X * (t) is the current optimal position, X(t+1) is the latest whale position, X(t) is the current whale position, A and D are control parameters;

[0207] A=2a·ra

[0208] D=|C·X * (t)-X(t)|

[0209] a decreases over time, linearly decreasing from 2 to 0, r is a random number between [0,1], and C is twice the random number r;

[0210]

[0211] Among them, t is the current iteration number, T is the maximum iteration number, r min and r max is the adaptive range, and the optimization stops when the number of iterations T is reached;

[0212] Step 5: Adjust system operation strategy in real time

[0213] According to the energy recovery path predicted by the KELM model, control signals are generated to adjust the actuators (compression ratio of the steam compressor and flow rate of the heat exchanger). First, the optimized KELM model is used for prediction:

[0214]

[0215] is the predicted system output, X is the input feature vector, f is the KELM model, and β is the KELM model parameter;

[0216] Then, according to the prediction results, the corresponding control signal is generated:

[0217]

[0218] Among them, u is the control signal vector, including compression ratio and flow control parameters, and g is the control signal generation function, which maps the prediction results to specific control signals;

[0219] Next, the actuator adjusts operating parameters in real time based on the control signal to ensure that the system runs along the optimal path:

[0220] Steam compressor compression ratio adjustment:

[0221]

[0222] Heat exchanger flow adjustment:

[0223] Q=m·c p ΔT

[0224] Where CR is the compression ratio, P out is the compressor outlet pressure, P in is the compressor inlet pressure, Q is the heat flow, m is the material flow, c p is the specific heat capacity of the material, ΔT is the temperature change;

[0225] Finally, the system operation status is monitored in real time, and the operating parameters are continuously adjusted through the feedback control mechanism to maintain the stability and efficient operation of the system:

[0226] Error calculation:

[0227] e(t)=y ref (t)-y(t)

[0228] Controller output:

[0229]

[0230] Parameter adjustment:

[0231] u(t+1)=u(t)+Δu(t)

[0232] Among them, e(t) is the error, y ref (t) is the reference output, y(t) is the actual output, u(t) is the controller output, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(τ) is the error value at time τ, u(t+1) is the control signal at the next moment, and Δu(t) is the adjustment amount of the control signal.

[0233] Specific numerical examples:

[0234] Distillation tower bottom temperature (T1): 200°C;

[0235] Distillation tower top temperature (T2): 100°C;

[0236] Heat exchanger inlet temperature (T3): 150°C;

[0237] Heat exchanger outlet temperature (T4): 120°C;

[0238] Condenser inlet temperature (T5): 90°C;

[0239] Condenser outlet temperature (T6): 60°C;

[0240] Steam compressor inlet pressure (P1): 2MPa;

[0241] Steam compressor outlet pressure (P2): 3MPa;

[0242] Heat exchanger inlet pressure (P3): 1.5MPa;

[0243] Heat exchanger outlet pressure (P4): 1MPa;

[0244] Material separator inlet flow (F1): 500L / h;

[0245] Material separator outlet flow (F2): 450L / h;

[0246] Heat exchanger inlet flow (F3): 600L / h;

[0247] Heat exchanger outlet flow (F4): 550L / h;

[0248] Distillation tower liquid level (L1): 5m;

[0249] Material separator liquid level (L2): 3m;

[0250] If the steam flow rate is 500kg / h and the inlet steam enthalpy is 2800kJ / kg:

[0251] E input =500kg / h·2800kJ / kg=1400000kJ / h;

[0252] The material flow rate is 450kg / h, the specific heat capacity is 4.18kJ / (kg·℃), and the material temperature change is 30℃:

[0253] E recovered =450kg / h·4.18kJ / (kg·℃)·30℃=56430kJ / h;

[0254] but,

[0255]

[0256] Temperature (T): [200, 100, 150, 120, 90, 60] °C;

[0257] Pressure (P): [2, 3, 1.5, 1] ​​MPa;

[0258] Flow rate (F): [500, 450, 600, 550] L / h;

[0259] Energy recovery rate (η): 0.0403;

[0260] System efficiency (E): 0.0403;

[0261] Training set: 80% of the data is used for training and 20% of the data is used for testing;

[0262] Kernel function: RBF kernel, initial parameters σ=1, λ=0.01;

[0263] Training model: Minimize the training error and obtain the output weight β;

[0264] Improved whale algorithm optimization:

[0265] Initial population: randomly generate 10 sets of parameter combinations;

[0266] Fitness calculation: Calculate the prediction error of each set of parameters;

[0267] Iterative optimization: Use the IWOA+WOA algorithm to iteratively update and find the optimal parameters;

[0268] Termination condition: stop after 100 iterations;

[0269] It is to be understood that the present invention is described by some embodiments, and it is known to those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. Preheating heat pump energy recovery system, characterized by: Includes distillation tower, heat exchanger, material separator, condenser, steam compressor and water pump; The steam generated by the distillation tower is sent to the heat exchanger to exchange heat with the decompressed material so that the material with a lower original temperature is heated and vaporized; The material separator is used to separate the gas and liquid of the material after the heat exchange in the heat exchanger is completed; The water pump is used to pump the liquid phase separated by the material separator to the distillation tower; The steam compressor is used to compress the gas phase separated by the material separator into the distillation tower; The condenser is used to condense the gas phase of the material in the heat exchanger.

2. The method of the preheating heat pump energy recovery system according to claim 1, characterized in that: The specific steps for heat pump energy recovery are as follows: Step 1: The steam generated by the distillation tower exchanges heat with the material after decompression in the heat exchanger, so that the material with a lower original temperature is heated and the high gas phase fraction or dew point feed is vaporized; Step 2: After the heat exchange is completed, part of the material is separated into gas and liquid by the material separator, the gas phase is compressed into the distillation tower by the compressor, and the liquid phase is pumped into the distillation tower by the water pump; Step 3: After the heat exchange is completed, part of the material is condensed through a condenser, and part of the liquid phase produced by the condensation is refluxed to the distillation tower, and part of the liquid phase is extracted.

3. The method for recovering energy from a preheating heat pump according to claim 2, characterized in that: It also includes adding an energy recovery path optimal planning algorithm to improve energy recovery efficiency and reduce system energy consumption. The specific steps are as follows: Step 1: Sensor selection and installation: First is the temperature sensor, installation location: Distillation tower: installed at the bottom, middle and top of the tower to monitor temperature changes at different heights; Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the temperature of the materials entering and leaving the heat exchanger; Condenser: Installed at the inlet and outlet of the condenser to monitor the gas temperature entering and leaving the condenser; Steam compressor: Installed at the inlet and outlet of the compressor to monitor the steam temperature before and after compression; Water pump: Installed at the inlet and outlet of the water pump to monitor the water temperature; Temperature change rate = (T2-T1) / Δt Where T1 is the initial temperature of the sensor, T2 is the current temperature of the sensor, and Δt is the time interval; Pressure sensor, installation location: Steam compressor: installed at the inlet and outlet of the compressor to monitor the pressure before and after steam compression; Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the pressure entering and leaving the heat exchanger; Pressure change rate = (P2-P1) / Δt Among them, P1 is the initial pressure of the sensor, and P2 is the current pressure of the sensor; Flow sensor, installation location: Material separator: Installed at the inlet and outlet of the separator to monitor the inlet and outlet fluid flow; Heat exchanger: Installed at the inlet and outlet of the heat exchanger to monitor the flow rate of the fluid; Condenser: Installed at the inlet and outlet of the condenser to monitor the flow of the fluid; Flow rate change = (F2-F1) / Δt Among them, F1 is the initial flow rate of the sensor, and F2 is the current flow rate of the sensor; Liquid level sensor, installation location: Distillation tower: installed at different heights in the tower to monitor liquid level changes; Material separator: installed at different positions in the separator to monitor liquid level changes; Liquid level change rate = (L2-L1) / Δt Among them, L1 is the initial liquid level of the sensor, and L2 is the current liquid level of the sensor; Step 2: Data collection and preprocessing The first step is data cleaning: Use a smoothing filter to smooth the data and remove high-frequency noise, and use a median filter to remove spike noise; use 3σ to detect and remove outliers, and use the box plot method to detect and remove outliers; Abnormal value range = [μ-3σ, μ+3σ] Among them, x i is the i-th data point, N is the total number of data, and μ is the mean value of the data; Next, data standardization: Transform the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. Among them, X std is the standardized data, and x is the original data; Finally, select the features: Temperature gradient: reflects the rate of change of temperature over time or location. Pressure change rate: reflects the rate at which pressure changes with time or position. Flow rate of change: reflects the rate of change of flow over time or location. Liquid level change rate: reflects the rate of change of liquid level over time. Among them, ΔT is the temperature change, Δt is the time change, ΔP is the pressure change, ΔF is the flow change, and ΔL is the liquid level change; Step 3: Definition of system energy recovery model Establish the energy recovery model of the system. The objective function of the model includes energy recovery rate and system efficiency. These two indicators can effectively evaluate the performance and optimization effect of the system: The energy recovery rate is defined as the ratio of the energy recovered by the system to the input energy, which is used to measure the efficiency of the system in recovering energy; System efficiency is defined as the ratio of effective energy output to total energy input, which is used to measure the overall energy utilization efficiency of the system; Where η is the energy recovery rate, E recovered is the recovered energy, E input is the input energy, E is the system efficiency, E useful is the effective energy output, E total is the total energy input; Step 4: Improved whale algorithm to optimize kernel extreme learning machine KELM is a fast and effective regression and classification method suitable for processing nonlinear relationships. It maps data into high-dimensional space through kernel functions to achieve the learning of complex relationships. Input: pre-processed sensor data, including temperature, pressure, flow and level; Output: system energy recovery rate and system efficiency; Collect and pre-process sensor data; Split the data into training and testing sets; KELM model training: Select radial basis function RBF as the kernel function; Set the kernel function parameters, kernel width σ and regularization parameter λ; Train the model to minimize the training error; H = kernel(X, X) Hβ=T Among them, H is the hidden layer output matrix, β is the output weight, T is the target output, is a pseudo-example of H; The test set data was used to verify the predictive performance of the model and ensure that the model had good generalization ability, using mean square error (MSE) and determination coefficient (R) 2 For judging basis: Among them, y i is the true value, is the predicted value, N is the number of samples, is the mean of the true value, i represents the i-th sample; Finally, in order to optimize the prediction performance of the KELM model, the improved whale optimization algorithm IWOA+WOA is used for parameter optimization; The improved whale optimization algorithm IWOA is an improvement on the traditional whale optimization algorithm WOA, which improves the convergence speed and global search capability. X(t+1)=X * (t)-A·D Among them, X * (t) is the current optimal position, X(t+1) is the latest whale position, X(t) is the current whale position, A and D are control parameters; A=2a·ra D=|C·X * (t)-X(t)| a decreases over time, linearly decreasing from 2 to 0, r is a random number between [0, 1], and C is twice the random number r; Among them, t is the current iteration number, T is the maximum iteration number, r min and r max is the adaptive range, and the optimization stops when the number of iterations T is reached; Step 5: Adjust system operation strategy in real time According to the energy recovery path predicted by the KELM model, control signals are generated to adjust the actuators (compression ratio of the steam compressor and flow rate of the heat exchanger). First, the optimized KELM model is used for prediction: is the predicted system output, X is the input feature vector, f is the KELM model, and β is the KELM model parameter; Then, according to the prediction results, the corresponding control signal is generated: Among them, u is the control signal vector, including compression ratio and flow control parameters, and g is the control signal generation function, which maps the prediction results to specific control signals; Next, the actuator adjusts operating parameters in real time based on the control signal to ensure that the system runs along the optimal path: Steam compressor compression ratio adjustment: Heat exchanger flow adjustment: Q=m·c p ·ΔT Where CR is the compression ratio, P out is the compressor outlet pressure, P in is the compressor inlet pressure, Q is the heat flow, m is the material flow, c p is the specific heat capacity of the material, ΔT is the temperature change; Finally, the system operation status is monitored in real time, and the operating parameters are continuously adjusted through the feedback control mechanism to maintain the stability and efficient operation of the system: Error calculation: e(t)=y ref (t)-y(t) Controller output: Parameter adjustment: u(t+1)=u(t)+Δu(t) Among them, e(t) is the error, y ref (t) is the reference output, y(t) is the actual output, u(t) is the controller output, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(τ) is the error value at time τ, u(t+1) is the control signal at the next moment, and Δu(t) is the adjustment amount of the control signal.