Tail steam recycling control system and method
Patent Information
- Application Number
- CN202610449191.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-04-07
- Publication Date
- 2026-08-18
AI Technical Summary
[0004]为了解决现有工业生产中尾蒸汽直接排放导致能源浪费严重,以及因尾蒸汽压力温度波动大造成工艺质量不稳定的技术问题,本发明提供了一种尾蒸汽循环利用控制系统及方法
其一,显著提升尾蒸汽能源回收效率。本发明通过预换热单元、主换热单元、闪蒸单元及蒸汽喷射式热泵单元的梯级耦合,充分利用中低温尾蒸汽的潜热与显热,解决了传统技术中尾蒸汽直排造成的巨大能源浪费问题,大幅降低系统整体能耗。
Smart Images

Figure CN122590618A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of industrial waste heat recovery technology, and particularly relates to a control system and method for the recycling of tail steam. Background Technology
[0002] In industrial production processes such as papermaking, chemical manufacturing, and textiles, the drying process in drying cylinders generates a large amount of medium- and low-temperature tail steam. In existing technologies, this tail steam is often difficult to reuse directly due to its low pressure, large fluctuations, and the presence of non-condensable gases. It is often directly vented or subjected to only simple condensation treatment, resulting in a significant waste of sensible and latent heat and low energy utilization.
[0003] Furthermore, existing tail steam recovery systems mostly employ single-stage heat exchange or fixed heat pump structures, lacking the ability to adaptively regulate drastic fluctuations in tail steam pressure and temperature. When production loads switch or raw materials change, heating parameters are prone to instability, leading to quality defects such as uneven product drying, quantitative fluctuations, and wrinkles. Simultaneously, traditional control systems often rely on single temperature or pressure feedback, failing to deeply integrate production process data with online quality monitoring data. They lack feedforward compensation and global optimization mechanisms based on multi-source data fusion, resulting in lagging heat source allocation and difficulty in simultaneously meeting the dual demands of energy conservation, carbon reduction, and high-quality production. Therefore, the development of a tail steam recycling system with cascaded heat exchange, intelligent control, and quality linkage capabilities is urgently needed. Summary of the Invention
[0004] To address the serious energy waste caused by the direct emission of tail steam in existing industrial production, and the unstable process quality caused by large fluctuations in tail steam pressure and temperature, this invention provides a tail steam recycling control system and method.
[0005] To achieve the above objectives, a tail steam recycling control system is provided in a first aspect of the present invention, comprising an energy recovery module and an intelligent control module: The energy recovery module includes a preheat exchange unit, a main heat exchange unit, a flash evaporation unit, and a steam jet heat pump unit; The steam inlet of the preheat exchange unit is used to receive medium- and low-temperature tail steam, and the medium outlet is connected to the medium inlet of the main heat exchange unit. The inlet of the flash evaporation unit is connected to the condensate outlet or tail steam bypass of the preheat exchange unit, and the secondary steam outlet of the flash evaporation unit is connected to the ejector inlet of the steam jet heat pump unit. The working steam inlet of the steam jet heat pump unit is used to connect to high-pressure main steam, and its mixed steam outlet is connected to the heating inlet of the main heat exchange unit. The intelligent control module includes a multi-source data acquisition unit, an edge computing unit, and an intelligent optimization decision-making unit. The multi-source data acquisition unit is used to collect process operating parameters, production process parameters, and product quality inspection parameters in real time. The edge computing unit is communicatively connected to the multi-source data acquisition unit and is used to preprocess and extract features from the acquired data. The intelligent optimization decision-making unit is communicatively connected to the edge computing unit and the execution mechanism of the energy recovery module, and is used to dynamically generate heat source allocation instructions and equipment operation control instructions based on the processed data.
[0006] Furthermore, the preheating unit is used to preheat the incoming ambient temperature medium to the first temperature range by utilizing the latent heat and sensible heat of the medium- and low-temperature tail steam. The main heat exchange unit is used to heat the preheated medium to a second temperature range using mixed steam from the steam jet heat pump unit and supplemented main steam. The lower limit of the second temperature range is higher than the upper limit of the first temperature range.
[0007] Furthermore, including, The steam jet heat pump unit includes a working nozzle, a mixing chamber, and a diffuser. The working nozzle is connected to the supply pipeline of the high-pressure main steam, the mixing chamber is provided with an ejector port that communicates with the flash evaporation unit, and the outlet of the diffuser tube is connected to the main heat exchange unit. The system also includes a pressure balance adjustment component, which is located between the flash evaporation unit and the steam jet heat pump unit, and is used to adjust the ejector flow rate in real time according to the pressure fluctuation of the tail steam to maintain the pressure stability of the mixing chamber.
[0008] Furthermore, it also includes: The multi-source data acquisition unit includes a process sensor group for monitoring temperature, pressure and flow, a process data interface for acquiring production load and operating speed, and a quality inspection instrument for online detection of product physical indicators. The edge computing unit has built-in data filtering and outlier removal algorithms to convert multi-source heterogeneous data into a standard time-series data stream.
[0009] Furthermore, it also includes, The intelligent optimization decision unit is embedded with a dynamic optimization model based on machine learning. The input of the dynamic optimization model receives a standard time-series data stream from the edge computing unit, and the output is connected to the bypass valve of the preheat exchange unit, the steam replenishment regulating valve of the main heat exchange unit, and the working steam regulating valve of the steam jet heat pump unit. The dynamic optimization model is used to calculate the optimal heat source allocation ratio and equipment operating parameter settings in real time, with energy consumption minimization and product quality stability as multiple objective functions.
[0010] A tail steam recycling control method, applied to any of the tail steam recycling control systems described above, includes the following steps: The process operation parameters, production process parameters, and product quality inspection parameters are acquired synchronously through a multi-source data acquisition unit; the acquired parameters are cleaned, aligned, and feature extracted using an edge computing unit to generate a real-time operating condition feature vector. The real-time operating condition feature vector is input into the dynamic optimization model in the intelligent optimization decision unit to calculate the current optimal heat source allocation ratio and equipment operating parameters. Based on the optimal heat source allocation ratio and equipment operating parameters, control commands are generated and sent to the actuator of the energy recovery module to adjust the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit and steam jet heat pump unit. The system monitors the adjusted system feedback data in real time. If the product quality testing parameters deviate from the preset range or the process operating parameters fluctuate abnormally, the feedforward compensation mechanism is triggered to adjust the equipment operating parameters in advance to offset the disturbance.
[0011] Furthermore, the adjustment of the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit, and steam jet heat pump unit specifically includes: Based on the temperature and pressure changes of the tail steam, the medium flow rate and bypass opening of the preheating unit are dynamically adjusted to ensure that the temperature of the medium entering the main heat exchange unit is within the preset preheating range. The working steam flow rate of the steam jet heat pump unit is dynamically adjusted based on the difference between the temperature requirement of the outlet medium of the main heat exchange unit and the available energy of the tail steam, in order to change the ejector coefficient and the mixed steam pressure. Based on the liquid level and pressure status within the flash unit, the condensate drain valve and secondary steam outlet valve are controlled in a coordinated manner to maintain the pressure balance of the flash unit and maximize the secondary steam output.
[0012] Furthermore, the triggering feedforward compensation mechanism specifically includes: Establish a correlation mapping model between production process parameters and product quality inspection parameters; When a trend change in production process parameters is detected, product quality inspection prediction parameters are output according to the correlation mapping model. Before the actual deviation of product quality testing parameters occurs, the amount of steam replenishment in the main heat exchange unit or the injection pressure of the steam jet heat pump unit can be adjusted in advance based on the prediction results to achieve proactive suppression of quality fluctuations.
[0013] Furthermore, it also includes adaptive learning, the adaptive learning working steps of which include: Record the operating condition feature vectors, control commands, and corresponding actual energy consumption data and product quality data during the historical operation process; The dynamic optimization model is periodically trained and its parameters are updated using recorded historical data to correct prediction biases under different production loads and raw material characteristics, thereby improving the adaptability of the heat source allocation strategy.
[0014] Furthermore, it also includes fail-safe switching, the process of which includes: When a hardware failure is detected in the steam jet heat pump unit or the main heat exchange unit, the output of the current dynamic optimization decision unit is immediately locked, and based on the preset safe operation strategy table, the faulty unit is automatically bypassed and the system is switched to the fixed frequency protection mode to maintain basic heat energy recovery.
[0015] The beneficial technical effects of the present invention are at least as follows: Firstly, it significantly improves the energy recovery efficiency of tail steam. This invention fully utilizes the latent and sensible heat of medium- and low-temperature tail steam through the cascade coupling of the pre-heat exchange unit, main heat exchange unit, flash evaporation unit, and steam jet heat pump unit, solving the problem of huge energy waste caused by direct discharge of tail steam in traditional technologies and greatly reducing the overall energy consumption of the system.
[0016] Secondly, it ensures the stability of process heating and product quality. Addressing the pain point of large fluctuations in tail steam pressure, this invention utilizes an intelligent optimization decision-making unit to dynamically adjust heat source distribution, combined with a pressure balance adjustment component to stabilize the mixing chamber pressure in real time, effectively avoiding uneven product drying or quality defects caused by fluctuations in heating parameters.
[0017] Third, it achieves intelligent feedforward control through multi-source data fusion. Overcoming the lag of traditional single feedback control, this invention integrates multi-source data from process operation, production technology, and online quality inspection. By generating feedforward compensation commands through edge computing and AI models, it adjusts the equipment status in advance before quality deviations occur, achieving a leap from "passive response" to "proactive optimization".
[0018] Fourth, it extends equipment lifespan and reduces operation and maintenance costs. By precisely controlling valve opening and steam flow, frequent equipment start-ups and shutdowns and current surges are avoided. At the same time, the adaptive learning mechanism enables the system to evolve itself according to changes in operating conditions, reducing manual intervention and improving long-term operational reliability.
[0019] Fifth, it is highly adaptable and aligns with the trend of green manufacturing. This invention can be flexibly adapted to different load scenarios such as papermaking and chemical industry, ensuring high-quality production while achieving energy conservation and carbon reduction, and has significant economic benefits and environmental value. Attached Figure Description
[0020] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.
[0021] Figure 1 This is a schematic diagram of a tail steam recycling control system according to one embodiment of the present invention; Figure 2 This is a diagram illustrating the working steps of a tail steam recycling control method disclosed in one embodiment of the present invention. Detailed Implementation
[0022] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.
[0023] Example 1 refer to Figure 1 The present invention provides an embodiment of a tail steam recycling control system, comprising an energy recovery module and an intelligent control module: The energy recovery module includes a preheat exchange unit, a main heat exchange unit, a flash evaporation unit, and a steam jet heat pump unit; The steam inlet of the preheat exchange unit is used to receive medium- and low-temperature tail steam, and the medium outlet is connected to the medium inlet of the main heat exchange unit. The inlet of the flash evaporation unit is connected to the condensate outlet or tail steam bypass of the preheat exchange unit, and the secondary steam outlet of the flash evaporation unit is connected to the ejector inlet of the steam jet heat pump unit. The working steam inlet of the steam jet heat pump unit is used to connect to high-pressure main steam, and its mixed steam outlet is connected to the heating inlet of the main heat exchange unit. The intelligent control module includes a multi-source data acquisition unit, an edge computing unit, and an intelligent optimization decision-making unit. The multi-source data acquisition unit is used to collect process operating parameters, production process parameters, and product quality inspection parameters in real time. The edge computing unit is communicatively connected to the multi-source data acquisition unit and is used to preprocess and extract features from the acquired data. The intelligent optimization decision-making unit is communicatively connected to the edge computing unit and the execution mechanism of the energy recovery module, and is used to dynamically generate heat source allocation instructions and equipment operation control instructions based on the processed data.
[0024] This embodiment constructs a tail steam recycling control system, with hardware deployed in the drying section of the paper drying cylinder. In the energy recovery module, the preheating unit uses a plate heat exchanger, its steam inlet connected to the 110℃-130℃ tail steam main pipe discharged from the drying cylinder; the main heat exchange unit is a spiral plate heat exchanger, receiving preheated process water; the flash evaporation unit is a vertical flash tank, its inlet selectively connected to the condensate outlet of the preheating unit or the tail steam bypass via a three-way valve to handle different operating conditions; the high-pressure working steam inlet of the steam jet heat pump unit (heat compressor) is connected to the plant's 0.6MPa new steam network. The intelligent control module is deployed in an industrial control cabinet. The multi-source data acquisition unit aggregates field sensor data via the Modbus TCP protocol, the edge computing unit uses an embedded industrial computer, and the intelligent optimization decision-making unit runs on a cloud or local server, issuing commands to actuators (such as electric regulating valves and frequency converters) via the OPCUA protocol to achieve closed-loop control from physical perception to logical decision-making.
[0025] A systematic modification was carried out on the flash evaporator recovery pipeline: a new stainless steel recovery pipeline with a diameter of Φ100mm was added at the outlet of the flash tank, and the entire pipeline was wrapped with a 50mm thick high-efficiency insulation layer (thermal conductivity ≤0.03W / (m)). K)) to minimize heat loss during transportation; at the same time, high-precision check valves and Y-type filters are installed in series on the pipeline to effectively block the risk of condensate backflow and filter out impurities to prevent blockage, thereby constructing a three-stage linkage recovery path for the flash tank, successfully achieving 100% full recovery of the steam discharged from the flash tank, and significantly improving the thermal energy utilization rate.
[0026] Referring to Table 1, in some embodiments, the steam heat pump system was customized and designed based on the complex and variable load conditions of the ETAD model, and adopted a "two-stage ejector" structure. By optimizing the cascade matching of the nozzle and the mixing chamber, the heat pump can flexibly adapt to the steam flow and pressure fluctuations at different production stages, solving the problem of the efficiency drop of traditional single-stage heat pumps under low or high loads, ensuring that the system can maintain efficient and stable ejector performance over a wide load range, and providing a reliable power source for subsequent cascade utilization of thermal energy.
[0027] Table 1 In this embodiment, considering the multi-unit collaborative operation characteristic of the ETAD model, the main steam unit automatically adjusts the opening of the main steam valve and links it with the heat pump ejector flow rate based on the real-time production load, stabilizing the main steam consumption within the range of 1t / h ± 5%. The warm-up and bypass control unit sets the bypass valve opening to 80% 30 minutes before startup, and then reduces it to 10%-15% after normal operation, shortening the warm-up time by 10 minutes and reducing energy consumption by 5%. The steam heat pump control unit dynamically adjusts the ejector valve according to the exhaust steam pressure, automatically starting the standby ejector pump when the pressure is below 0.11MPa, ensuring the heat pump outlet pressure remains stable within the 0.10-0.35MPa range. The venting control unit operates when the flash tank pressure is above 0. The system automatically opens the vent valve at 2MPa and closes it below 0.1MPa, reducing the amount of vented steam by more than 90%. The flash tank level control unit maintains the liquid level at 1 / 2 to 2 / 3 of its height, adjusts the condensate valve for over-limit adjustments with a feedback delay of ≤2s, and controls the liquid level fluctuation within ±5%. The small drying cylinder outlet differential pressure adjustment unit collects the inlet and outlet pressures of the drying cylinder in real time and adjusts the valve opening with a display accuracy of ±0.005MPa to maintain a stable differential pressure of 0.08-0.1MPa. The recycled steam flow statistics unit is equipped with an electromagnetic flowmeter with a range of 0-500kg / h and an accuracy of ±1%, which uploads the data to the MES system to ensure that the flow data error is ≤2%, achieving refined control and energy efficiency optimization of steam parameters throughout the entire process.
[0028] Furthermore, the preheating unit is used to preheat the incoming ambient temperature medium to the first temperature range by utilizing the latent heat and sensible heat of the medium- and low-temperature tail steam. The main heat exchange unit is used to heat the preheated medium to a second temperature range using mixed steam from the steam jet heat pump unit and supplemented main steam. The lower limit of the second temperature range is higher than the upper limit of the first temperature range.
[0029] It should be noted that the pre-heat exchange unit heats the process water at room temperature (25℃) to 75℃-85℃ (first temperature range) using tail steam. This process mainly recovers the sensible heat and part of the latent heat of condensation of the tail steam, avoiding heat loss caused by direct condensation of the tail steam. Subsequently, the water flows into the main heat exchange unit. At this time, the mixed steam (pressure approximately 0.3MPa) output from the steam jet heat pump unit, together with the supplemented new steam, further raises the water temperature to 95℃-105℃ (second temperature range), meeting the heating requirements of the drying cylinder. The stepped design of the two temperature ranges ensures the maximization of heat energy utilization and prevents irreversible losses caused by the direct heating of the low-temperature medium by the high-temperature heat source.
[0030] Furthermore, including, The steam jet heat pump unit includes a working nozzle, a mixing chamber, and a diffuser. The working nozzle is connected to the supply pipeline of the high-pressure main steam, the mixing chamber is provided with an ejector port that communicates with the flash evaporation unit, and the outlet of the diffuser tube is connected to the main heat exchange unit. The system also includes a pressure balance adjustment component, which is located between the flash evaporation unit and the steam jet heat pump unit, and is used to adjust the ejector flow rate in real time according to the pressure fluctuation of the tail steam to maintain the pressure stability of the mixing chamber.
[0031] It should be noted that, in this embodiment, inside the steam jet heat pump unit, high-pressure working steam is accelerated through a Laval nozzle to form a supersonic jet, creating negative pressure in the mixing chamber, which draws in and mixes with the low-pressure secondary steam generated by the flash evaporation unit. The pressure balance regulating component includes a high-precision differential pressure transmitter and a fast-response pneumatic diaphragm regulating valve, installed on the pipeline from the flash tank outlet to the heat pump ejector port. When fluctuations in the tail steam pressure due to sudden changes in production load are detected, this component adjusts the ejector flow rate within milliseconds to maintain a constant back pressure in the mixing chamber, preventing heating pulsations caused by ejector instability and ensuring stable steam parameters entering the main heat exchange unit.
[0032] Furthermore, it also includes: The multi-source data acquisition unit includes a process sensor group for monitoring temperature, pressure and flow, a process data interface for acquiring production load and operating speed, and a quality inspection instrument for online detection of product physical indicators. The edge computing unit has built-in data filtering and outlier removal algorithms to convert multi-source heterogeneous data into a standard time-series data stream.
[0033] It should be noted that in this embodiment, the multi-source data acquisition unit integrates a Pt100 temperature sensor, a diffused silicon pressure transmitter, and an electromagnetic flowmeter to form a process sensor group, which monitors the pipeline status in real time. The process data interface reads the machine speed, paper type basis weight, and production load information from the DCS system via Ethernet. The quality inspection instruments use an online infrared moisture meter and a quantitative scanner to provide real-time feedback on the paper moisture content. The edge computing unit incorporates a Kalman filter algorithm to eliminate sensor noise and uses timestamp alignment technology to uniformly convert multi-source heterogeneous data with varying frequencies (such as second-level process data and minute-level quality data) into a standard time-series data stream, providing a high-quality data foundation for upper-level decision-making.
[0034] Furthermore, it also includes, The intelligent optimization decision unit is embedded with a dynamic optimization model based on machine learning. The input of the dynamic optimization model receives a standard time-series data stream from the edge computing unit, and the output is connected to the bypass valve of the preheat exchange unit, the steam replenishment regulating valve of the main heat exchange unit, and the working steam regulating valve of the steam jet heat pump unit. The dynamic optimization model is used to calculate the optimal heat source allocation ratio and equipment operating parameter settings in real time, with energy consumption minimization and product quality stability as multiple objective functions.
[0035] The intelligent optimization decision-making unit embeds a dynamic optimization model based on machine learning. This model employs a deep reinforcement learning architecture, using historical operating data as a training set to perceive changes in production conditions in real time. The model's input receives standard time-series data streams from the edge computing unit, covering features such as current vehicle speed, raw paper moisture content, tail steam pressure and temperature, and environmental parameters. The output is directly connected to the bypass electric regulating valve of the pre-heat exchange unit, the new steam replenishment regulating valve of the main heat exchange unit, and the working steam pneumatic regulating valve of the steam jet heat pump unit. During operation, the dynamic optimization model constructs multiple objective functions based on "lowest unit product energy consumption" and "minimum product quality standard deviation." Through real-time iterative calculation via a strategy network, it outputs the optimal heat source allocation ratio (such as the mixing ratio of tail steam and new steam) and the optimal opening setpoints for each actuator. The system no longer relies on fixed PID parameters but generates adaptive control strategies within milliseconds based on the current operating conditions, ensuring that the system maintains global optimality in energy efficiency and heating stability even when tail steam fluctuates.
[0036] refer to Figure 2 This embodiment also provides a tail steam recycling control method, applied to any of the tail steam recycling control systems described above, comprising the following steps: S1. The process operation parameters, production process parameters and product quality inspection parameters are acquired synchronously through the multi-source data acquisition unit. The edge computing unit is used to clean, align and extract features from the acquired parameters to generate a real-time operating condition feature vector. S2. Input the real-time operating condition feature vector into the dynamic optimization model in the intelligent optimization decision unit to calculate the current optimal heat source allocation ratio and equipment operating parameters; S3. Based on the optimal heat source allocation ratio and equipment operating parameters, generate control commands and send them to the actuator of the energy recovery module to adjust the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit and steam jet heat pump unit. S4. Monitor the system feedback data after adjustment in real time. If the product quality testing parameters deviate from the preset range or the process operation parameters fluctuate abnormally, the feedforward compensation mechanism is triggered to adjust the equipment operation parameters in advance to offset the disturbance.
[0037] In this embodiment, it should be noted that, firstly, the entire plant's operational data is collected synchronously, and then cleaned and aligned using an edge computing unit to generate a real-time operating condition vector containing features such as current vehicle speed, raw material humidity, and tail steam pressure. This vector is then input into a trained dynamic optimization model to calculate the current optimal heat source allocation ratio (e.g., tail steam utilization should reach 85%) and equipment setpoints. The system then generates PID control commands to drive the actuators. The key feature is the introduction of a feedforward compensation mechanism: once fluctuations in upstream pulping concentration or changes in vehicle speed are detected, the system, without waiting for deviations in the final product quality, immediately adjusts the injection ratio of the steam jet pump based on model predictions to proactively offset disturbances and eliminate quality fluctuations at their inception.
[0038] Furthermore, the adjustment of the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit, and steam jet heat pump unit specifically includes: Based on the temperature and pressure changes of the tail steam, the medium flow rate and bypass opening of the preheating unit are dynamically adjusted to ensure that the temperature of the medium entering the main heat exchange unit is within the preset preheating range. The working steam flow rate of the steam jet heat pump unit is dynamically adjusted based on the difference between the temperature requirement of the outlet medium of the main heat exchange unit and the available energy of the tail steam, in order to change the ejector coefficient and the mixed steam pressure. Based on the liquid level and pressure status within the flash unit, the condensate drain valve and secondary steam outlet valve are controlled in a coordinated manner to maintain the pressure balance of the flash unit and maximize the secondary steam output.
[0039] In this embodiment, at the execution level, the system dynamically adjusts the bypass valve of the preheating unit based on the real-time tail steam temperature sliding curve to ensure that the water temperature entering the main heat exchanger is always in the optimal preheating range, avoiding overheating or undercooling. Simultaneously, based on the difference between the main heat exchanger outlet temperature setpoint and the usable enthalpy of the tail steam, the system precisely adjusts the heat pump operating steam flow rate, changing the ejector coefficient to adaptively match the mixed steam pressure to the heat load demand. For the flash evaporation unit, the system employs level-pressure cascade control, linking and adjusting the condensate drain valve and the secondary steam outlet valve to maximize flash evaporation output while ensuring no steam leakage, thereby improving the overall thermal efficiency of the system.
[0040] Furthermore, the triggering feedforward compensation mechanism specifically includes: Establish a correlation mapping model between production process parameters and product quality inspection parameters; When a trend change in production process parameters is detected, product quality inspection prediction parameters are output according to the correlation mapping model. Before the actual deviation of product quality testing parameters occurs, the amount of steam replenishment in the main heat exchange unit or the injection pressure of the steam jet heat pump unit can be adjusted in advance based on the prediction results to achieve proactive suppression of quality fluctuations.
[0041] In this embodiment, when the feedforward compensation mechanism is triggered, the system first establishes a dynamic correlation mapping model between production process parameters (disturbance) and product quality detection parameters (controlled variables) based on historical data. When a trend change in production process parameters (such as increased machine speed or increased initial moisture content in raw paper) is detected, the system uses this mapping model to quickly calculate the product quality prediction deviation that will occur if no intervention is given. Based on this, the system pre-calculates the required compensation control quantity according to the magnitude and direction of the disturbance, and adjusts the opening of the main heat exchange unit's steam injection valve or the injection pressure of the steam jet heat pump unit in advance before the actual occurrence of the quality deviation, thereby achieving proactive suppression of quality fluctuations and eliminating the lag in feedback control.
[0042] Feedforward compensation control quantity The calculation formula is as follows: , in, For a moment The feedforward compensation control quantity that needs to be superimposed (such as the increment of steam valve opening); The amount of process disturbance change monitored (such as the change in vehicle speed). The disturbance channel gain represents the degree of impact of a unit disturbance on product quality. To control the channel gain, representing the ability of a unit control quantity to adjust product quality; The pure time lag that affects product quality during disturbances; To control the pure time lag affecting product quality, the core logic of this formula is: through the ratio... Determine the amount of compensation through the time element. Determine the timing of compensation. When > If the disturbance effect is slower than the control response, the system will delay issuing the compensation command; otherwise, it will issue it in advance to ensure that the compensation effect and the disturbance effect are precisely canceled out in time, so as to keep the product quality constant.
[0043] Furthermore, it also includes adaptive learning, the adaptive learning working steps of which include: Record the operating condition feature vectors, control commands, and corresponding actual energy consumption data and product quality data during the historical operation process; The dynamic optimization model is periodically trained and its parameters are updated using recorded historical data to correct prediction biases under different production loads and raw material characteristics, thereby improving the adaptability of the heat source allocation strategy.
[0044] Furthermore, this embodiment also includes fault-safe switching, the working process of which includes: When a hardware failure is detected in the steam jet heat pump unit or the main heat exchange unit, the output of the current dynamic optimization decision unit is immediately locked, and based on the preset safe operation strategy table, the faulty unit is automatically bypassed and the system is switched to the fixed frequency protection mode to maintain basic heat energy recovery.
[0045] Thirdly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the tail steam recycling control method as described in any one of the claims.
[0046] This embodiment innovatively applies a three-tank linkage recovery technology, breaking through the limitations of traditional single-tank systems and achieving an external steam recovery rate of over 95%, significantly addressing the pain point of low recovery efficiency in small drying cylinder systems. Combined with a two-stage ejector heat pump structure, the thermal efficiency is increased to 8%-10% (better than the industry average), and it perfectly adapts to the multi-load conditions of ETAD models, overcoming the poor load adaptability of general-purpose equipment. Simultaneously, a closed-loop intelligent control system of "differential pressure regulation - flow statistics - quality linkage" is constructed, breaking through the technical bottleneck of only basic monitoring in China, and achieving real-time dynamic coupling of steam parameters and paper quality. Supplemented by a customized "temperature-pressure-quality" correlation model for wood pulp mixed raw materials, it effectively avoids the "over-control" risk common in foreign technologies, significantly improving energy utilization while ensuring high stability of paper quality, combining significant energy-saving benefits with excellent product quality assurance capabilities.
[0047] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0048] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes: USB flash drive, mobile hard drive, read-only memory (ROM). ROM (ROM), RAM (Random Access Memory), magnetic disks, optical disks, and other media that can store programs.
Claims
1. A tail steam recycling control system, characterized in that, Includes an energy recovery module and an intelligent control module: The energy recovery module includes a preheat exchange unit, a main heat exchange unit, a flash evaporation unit, and a steam jet heat pump unit; The steam inlet of the preheat exchange unit is used to receive medium- and low-temperature tail steam, and the medium outlet is connected to the medium inlet of the main heat exchange unit. The inlet of the flash evaporation unit is connected to the condensate outlet or tail steam bypass of the preheat exchange unit, and the secondary steam outlet of the flash evaporation unit is connected to the ejector inlet of the steam jet heat pump unit. The working steam inlet of the steam jet heat pump unit is used to connect to high-pressure main steam, and its mixed steam outlet is connected to the heating inlet of the main heat exchange unit. The intelligent control module includes a multi-source data acquisition unit, an edge computing unit, and an intelligent optimization decision-making unit. The multi-source data acquisition unit is used to collect process operating parameters, production process parameters, and product quality inspection parameters in real time. The edge computing unit is communicatively connected to the multi-source data acquisition unit and is used to preprocess and extract features from the acquired data. The intelligent optimization decision-making unit is communicatively connected to the edge computing unit and the execution mechanism of the energy recovery module, and is used to dynamically generate heat source allocation instructions and equipment operation control instructions based on the processed data.
2. The tail steam recycling control system according to claim 1, characterized in that, The preheating unit is used to preheat the incoming ambient temperature medium to the first temperature range by utilizing the latent heat and sensible heat of the medium- and low-temperature tail steam. The main heat exchange unit is used to heat the preheated medium to a second temperature range using mixed steam from the steam jet heat pump unit and supplemented main steam. The lower limit of the second temperature range is higher than the upper limit of the first temperature range.
3. The tail steam recycling control system according to claim 1, characterized in that, include, The steam jet heat pump unit includes a working nozzle, a mixing chamber, and a diffuser. The working nozzle is connected to the supply pipeline of the high-pressure main steam, the mixing chamber is provided with an ejector port that communicates with the flash evaporation unit, and the outlet of the diffuser tube is connected to the main heat exchange unit. The system also includes a pressure balance adjustment component, which is located between the flash evaporation unit and the steam jet heat pump unit, and is used to adjust the ejector flow rate in real time according to the pressure fluctuation of the tail steam to maintain the pressure stability of the mixing chamber.
4. The tail steam recycling control system according to claim 1, characterized in that, Also includes: The multi-source data acquisition unit includes a process sensor group for monitoring temperature, pressure and flow, a process data interface for acquiring production load and operating speed, and a quality inspection instrument for online detection of product physical indicators. The edge computing unit has built-in data filtering and outlier removal algorithms to convert multi-source heterogeneous data into a standard time-series data stream.
5. The tail steam recycling control system according to claim 1, characterized in that, It also includes, The intelligent optimization decision unit is embedded with a dynamic optimization model based on machine learning. The input of the dynamic optimization model receives a standard time-series data stream from the edge computing unit, and the output is connected to the bypass valve of the preheat exchange unit, the steam replenishment regulating valve of the main heat exchange unit, and the working steam regulating valve of the steam jet heat pump unit. The dynamic optimization model is used to calculate the optimal heat source allocation ratio and equipment operating parameter settings in real time, with energy consumption minimization and product quality stability as multiple objective functions.
6. A tail steam recycling control method, applied to the tail steam recycling control system as described in any one of claims 1 to 5, characterized in that, Includes the following steps: Process operating parameters, production process parameters, and product quality inspection parameters are acquired synchronously through a multi-source data acquisition unit. Edge computing units are used to clean, align, and extract features from the acquired parameters to generate real-time operating condition feature vectors. The real-time operating condition feature vector is input into the dynamic optimization model in the intelligent optimization decision unit to calculate the current optimal heat source allocation ratio and equipment operating parameters. Based on the optimal heat source allocation ratio and equipment operating parameters, control commands are generated and sent to the actuator of the energy recovery module to adjust the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit and steam jet heat pump unit. The system monitors the adjusted system feedback data in real time. If the product quality testing parameters deviate from the preset range or the process operating parameters fluctuate abnormally, the feedforward compensation mechanism is triggered to adjust the equipment operating parameters in advance to offset the disturbance.
7. The tail steam recycling control method according to claim 6, characterized in that, The adjustment of the operating status of the preheat exchange unit, main heat exchange unit, flash evaporation unit, and steam jet heat pump unit specifically includes: Based on the temperature and pressure changes of the tail steam, the medium flow rate and bypass opening of the preheating unit are dynamically adjusted to ensure that the temperature of the medium entering the main heat exchange unit is within the preset preheating range. Based on the difference between the temperature requirement of the outlet medium of the main heat exchange unit and the available energy of the tail steam, the working steam flow rate of the steam jet heat pump unit is dynamically adjusted to change the ejector coefficient and the mixed steam pressure. Based on the liquid level and pressure status within the flash unit, the condensate drain valve and secondary steam outlet valve are controlled in a coordinated manner to maintain the pressure balance of the flash unit and maximize the secondary steam output.
8. The tail steam recycling control method according to claim 6, characterized in that, The triggering feedforward compensation mechanism specifically includes: Establish a correlation mapping model between production process parameters and product quality inspection parameters; When a trend change in production process parameters is detected, product quality inspection prediction parameters are output according to the correlation mapping model. Before the actual deviation of product quality testing parameters occurs, the amount of steam replenishment in the main heat exchange unit or the injection pressure of the steam jet heat pump unit can be adjusted in advance based on the prediction results to achieve proactive suppression of quality fluctuations.
9. The tail steam recycling control method according to claim 6, characterized in that, It also includes adaptive learning, the adaptive learning working steps of which include: Record the operating condition feature vectors, control commands, and corresponding actual energy consumption data and product quality data during the historical operation process; The dynamic optimization model is periodically trained and its parameters are updated using recorded historical data to correct prediction biases under different production loads and raw material characteristics, thereby improving the adaptability of the heat source allocation strategy.
10. The tail steam recycling control method according to claim 6, characterized in that, It also includes fail-safe switching, the working process of which includes: When a hardware failure is detected in the steam jet heat pump unit or the main heat exchange unit, the output of the current dynamic optimization decision unit is immediately locked, and based on the preset safe operation strategy table, the faulty unit is automatically bypassed and the system is switched to the fixed frequency protection mode to maintain basic heat energy recovery.