WO2022062339A1 - 一种变风量布风器风阀的控制系统及其控制方法 - Google Patents

一种变风量布风器风阀的控制系统及其控制方法 Download PDF

Info

Publication number
WO2022062339A1
WO2022062339A1 PCT/CN2021/082253 CN2021082253W WO2022062339A1 WO 2022062339 A1 WO2022062339 A1 WO 2022062339A1 CN 2021082253 W CN2021082253 W CN 2021082253W WO 2022062339 A1 WO2022062339 A1 WO 2022062339A1
Authority
WO
WIPO (PCT)
Prior art keywords
air volume
neural network
main controller
distributor
control system
Prior art date
Application number
PCT/CN2021/082253
Other languages
English (en)
French (fr)
Inventor
冯国增
孟博
包国治
顾鑫鑫
顾忱
徐彤
Original Assignee
江苏科技大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 江苏科技大学 filed Critical 江苏科技大学
Priority to US17/439,812 priority Critical patent/US12129010B2/en
Publication of WO2022062339A1 publication Critical patent/WO2022062339A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63J—AUXILIARIES ON VESSELS
    • B63J2/00—Arrangements of ventilation, heating, cooling, or air-conditioning
    • B63J2/02—Ventilation; Air-conditioning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
    • B63J—AUXILIARIES ON VESSELS
    • B63J2/00—Arrangements of ventilation, heating, cooling, or air-conditioning
    • B63J2/02—Ventilation; Air-conditioning
    • B63J2/04—Ventilation; Air-conditioning of living spaces
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00—Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/00735—Control systems or circuits characterised by their input, i.e. by the detection, measurement or calculation of particular conditions, e.g. signal treatment, dynamic models
    • B60H1/00792—Arrangement of detectors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00—Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/00814—Control systems or circuits characterised by their output, for controlling particular components of the heating, cooling or ventilating installation
    • B60H1/00821—Control systems or circuits characterised by their output, for controlling particular components of the heating, cooling or ventilating installation the components being ventilating, air admitting or air distributing devices
    • B60H1/00835—Damper doors, e.g. position control
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/70—Control systems characterised by their outputs; Constructional details thereof
    • F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
    • F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
    • F24F11/755—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity for cyclical variation of air flow rate or air velocity
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/10—Temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00—Control inputs relating to air properties
    • F24F2110/40—Pressure, e.g. wind pressure
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
    • Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating

Definitions

  • the invention relates to the technical field of industrial control, in particular to a control system and a control method of a damper of a variable air volume distributor.
  • variable air volume has the function of automatically adjusting the air volume, and automatically matches the air supply volume required by the temperature in the cabin according to the changes in the indoor load.
  • variable air volume control system of the variable air volume distributor is the key link to ensure the automatic variable air volume supply.
  • Shanghai Johnson Controls Co., Ltd. uses proportional band adaptive and pattern recognition adaptive control algorithms
  • Siemens and York companies directly use PID control
  • Honeywell uses PID control and adaptive control methods .
  • a nonlinear model predictive control for variable air volume (VAV) system was proposed by Chen Jiongde of Shanghai Jiaotong University.
  • the control method adopts nonlinear autoregressive network (NARX) with external input and particle swarm optimization (PSO) algorithm. Aiming to predict the controlled parameters (room temperature) of the VAV system, PSO acts as an optimizer to obtain the optimal control variables of the VAV system.
  • NARX nonlinear autoregressive network
  • PSO particle swarm optimization
  • BP neural network is mainly used in function approximation, pattern recognition, classification application, data compression and so on.
  • Jia Chao from University of Science and Technology Beijing studied the multi-mode adaptive control method based on neural network, and proposed an adaptive controller based on OEM-ELM neural network. Errors are better controlled. So it can be seen that the BP neural network prediction model has high practical application value in the actual production process.
  • the improvement and optimization of the control system of the air valve of the variable air volume distributor is to ensure that the variable air volume air supply is more stable, improve the degree of automation of the equipment, reduce equipment loss, and reduce energy consumption. It is of great significance to promote the development of domestic air distributor products.
  • the present invention provides a BP neural network-based air valve control system and a control method thereof.
  • a control system for the air valve of a variable air volume distributor including a variable air volume distributor air volume regulating valve, a valve actuator, a main controller based on a BP neural network, a data collector, a user operation panel, and the user operation panel sets the temperature
  • the signal is connected to the input end of the main controller
  • the data collector collects the room temperature and the static pressure at the inlet of the air distributor
  • the collected data is connected to the input end of the main controller through different sensors
  • the output end of the main controller is executed with the valve. connection to the input of the device.
  • the main controller based on the BP neural network includes a BP neural network prediction control module and a proportional adjustment control module;
  • the data collector includes a temperature sensor and a pressure sensor.
  • the BP neural network prediction control module is a dual-input and single-output module; the two inputs of the neural network model for setting the opening action of the air valve are the static pressure u in the air duct and the required air volume v, and one output is the valve opening. degree y, the established mathematical model of the damper opening action is as follows:
  • m is the number of neurons in the input layer
  • k is the number of neurons in the output layer
  • the output value of the above model is continuously corrected by the negative gradient descent method.
  • the calculation formula of the error function is:
  • r k (n) is the expected output value
  • y k (n) is the actual output value
  • a control method for a control system of a variable air volume air distributor damper the specific steps are as follows:
  • Step 1 The data collector collects the room temperature, the temperature set by the user operation panel and the static pressure at the inlet of the air distributor in real time, and inputs them to the main controller;
  • Step 2 The input temperature signal is converted into an air volume signal in the main controller
  • Step 3 The data is transmitted to the main controller. First, the working conditions are matched in the storage unit. If the matching is successful, step 5 is performed. Otherwise, step 4 is performed online modeling learning;
  • Step 4 The BP neural network prediction model module models and trains the neural network model of the damper opening action according to the input data, and establishes a corresponding input-output mapping;
  • Step 5 The main controller outputs the control parameters optimized by the BP neural network model module to the proportional adjustment control module, and then controls the action of the valve actuator to realize automatic variable air volume.
  • the temperature signal in the above-mentioned step 2 includes the collected room temperature and the temperature set by the user operation panel.
  • the control method in the above-mentioned step 3 has two functions of online modeling learning and offline matching working condition, wherein the matching working condition is a prediction model constructed by sample data of factory test, and is stored in the main controller after training and learning.
  • the fourth step above includes the following processes:
  • the calculation of the BP neural network prediction model module is to establish a mathematical model based on the data obtained by the data collector, and the learning is to verify the validity of the modeling based on the temperature set by the user operation panel;
  • the BP neural network prediction model module modifies and optimizes the nonlinear model established by the module according to the verification results
  • the BP neural network prediction model module stores the optimization results in the storage unit of the main controller.
  • step 4 the opening action of the air valve includes the forward action of the air valve and the reverse action of the air valve.
  • the present invention provides a control system and a control method for the opening degree of the air valve of a variable air volume distributor, which fully utilizes advanced control theory, neural network and predictive control compared with the prior art. , intelligent algorithm, etc., to realize monitoring, modeling, control, optimization, management and decision-making of the control system of the variable air volume distributor damper, to avoid the frequent action of the damper due to temperature fluctuation factors, to achieve the purpose of automatic variable air volume, and to improve the User comfort and reduced energy consumption are of great significance.
  • FIG. 1 is a system block diagram of a control system in the present invention.
  • FIG. 2 is a schematic diagram of the control method in the present invention.
  • Fig. 3 is the BP neural network structure diagram of the control method in the present invention.
  • FIG. 4 is a graph showing the prediction result of the actual air volume by 40% of the valve opening of the network model in the present invention.
  • FIG. 5 is a graph showing the prediction error of the actual air volume by 40% of the valve opening of the network model in the present invention.
  • FIG. 6 is a graph showing the prediction result of the actual air volume by 65% of the valve opening of the network model in the present invention.
  • FIG. 7 is a graph showing the prediction error of the actual air volume by 65% of the valve opening of the network model in the present invention.
  • the invention is aimed at the control system of the air valve of the variable air volume distributor, and the adjustment of the variable air volume air valve is the key of the control system.
  • the traditional feedback control adjustment response speed is slow, and the valve actuator moves frequently.
  • the present invention applies the BP neural network prediction model, and establishes a nonlinear model of temperature, static pressure and valve opening according to the collected room temperature and static pressure at the inlet of the air distributor.
  • the optimization algorithm is applied to optimize the output valve opening, and the optimal value under this working condition is obtained, which is calibrated as the set value of the controller to control the action of the valve actuator to realize automatic variable air volume.
  • Fig. 1 is the control system block diagram of the variable air volume air distributor damper of the present invention, including air volume regulating valve, valve actuator, user operation panel, data collector, main controller based on BP neural network (BP neural network prediction model module and Proportional regulation control module).
  • the data collector is connected with the input end of the main controller, and the output end of the main controller is respectively connected with the valve actuator and the user operation panel.
  • the working process of the system is as follows: the room temperature is measured by the data collector, and the air volume is converted into the air volume in the main controller and transmitted to the BP neural network prediction model module; the static pressure in the pipeline is measured by the pressure sensor at the inlet of the air distributor, and the static pressure signal Passed to the BP neural network prediction model module.
  • the main controller takes the demand air volume and static pressure signal as two input terminals. After the neural network modeling calculation, it first determines the valve adjustment direction, selects the forward stroke or reverse stroke model, predicts the valve opening, and feeds it back to the main controller. And send an instruction to the valve actuator, the valve actuator moves directly to the position of predicting the valve opening after receiving the controller instruction, and finally achieves the purpose of automatic variable air volume.
  • FIG. 2 is a schematic diagram of the control method of the air valve of the variable air volume air distributor according to the present invention. Its working principle is: the proportional adjustment control module is mainly used to receive the data of the data collector, establish the action process and correction of the valve actuator.
  • the BP neural network prediction model module will use the received air volume and static pressure sample data to establish a nonlinear mathematical model and simulate it by using the neural network learning algorithm; complete the calculation and learning of the neural network by comparing the temperature set by the user operation panel, and then use the sample data. Feedback to the proportional adjustment control module for correction.
  • the BP neural network prediction model is a dual-input single-output model
  • the two inputs of the neural network model of the air valve opening action are the static pressure u in the air duct and the required air volume v, and one output is the valve opening y.
  • the established mathematical model of the valve opening action is as follows:
  • m is the number of neurons in the input layer
  • k is the number of neurons in the output layer
  • the output value of the above model is continuously corrected by the negative gradient descent method.
  • the calculation formula of the error function is:
  • r k (n) is the expected output value
  • y k (n) is the actual output value
  • control method of the automatic variable air volume of the air distributor the specific steps include:
  • the data collector collects the room temperature, the temperature set by the user operation panel and the static pressure at the inlet of the air distributor in real time, and inputs them to the main controller;
  • the input temperature signal is converted into air volume signal in the main controller
  • the data is transmitted to the main controller.
  • the preset working conditions are matched in the storage unit. If the matching is successful, go to step 5; otherwise, go to step 4 for online modeling learning;
  • the BP neural network prediction model module models and trains the neural network model of the valve opening action according to the input data, and establishes the corresponding input-output mapping
  • the main controller outputs the control parameters optimized by the BP neural network model module to the proportional adjustment control module, and then controls the action of the valve actuator to realize automatic variable air volume.
  • the temperature signal in the step 2 includes the collected room temperature and the temperature set by the user operation panel.
  • control method has two functions of online modeling learning and offline matching of working conditions.
  • the matching working condition in the step 3 is the prediction model constructed by the sample data of the factory test, which is stored in the main controller after training and learning.
  • step 4 includes:
  • the calculation of the BP neural network prediction model module is based on the data obtained by the data collector to establish a mathematical model, and the validity of the model is verified and learned by setting the temperature on the user operation panel;
  • the BP neural network prediction model module modifies and optimizes the nonlinear model established by the module according to the verification results
  • the BP neural network prediction model module stores the optimization results in the storage unit of the main controller.
  • the opening degree action of the damper in the step 4 includes a forward action of the damper and a reverse action of the damper.
  • the network model predicts the actual air volume as shown in Figures 4-7.
  • control system and the control method of the variable air volume air distributor air valve provided by this system can optimize the design and transformation of the variable air volume control system of the existing variable air volume air distributor on the market, improve the automation degree of the air distributor, and improve the The comfort of living in the cabin and the reduction of equipment energy consumption are of great significance.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Physics & Mathematics (AREA)
  • Ocean & Marine Engineering (AREA)
  • Thermal Sciences (AREA)
  • Signal Processing (AREA)
  • General Engineering & Computer Science (AREA)
  • Fluid Mechanics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

一种变风量布风器风阀的控制系统及其控制方法。控制系统包括变风量布风器风量调节阀门、阀门执行器、基于BP神经网络的主控制器、数据采集器、用户操作面板，数据采集器采集室温和布风器入口处静压，采集到的数据通过不同的传感器与主控制器的输入端连接，主控制器的输出端与阀门执行器的输入端连接。该控制系统可以提高系统的自动化程度，降低设备能耗。

Description

一种变风量布风器风阀的控制系统及其控制方法 技术领域
本发明涉及工业控制技术领域，具体地说，是一种变风量布风器风阀的控制系统及其控制方法。
背景技术
近年来，国内外船舶行业正积极向低噪音、节能、环保、智能等方面进行技术改造。布风器作为常用的船用空调末端，在空调送风系统中起着终端散流作用，是一种节流型变风量末端装置。所谓变风量，就是具有自动调节风量功能，根据室内负荷变化自动匹配舱室内温度需求的送风量。随着变风量空调系统技术的发展以及全球节能意识的不断提高，变风量布风器作为新一代船舶配套产品的需求量激增。
变风量布风器的变风量控制系统是保证自动变风量送风的关键环节。对于变风量控制系统的研究，上海江森自控有限公司采用比例带自适应和模式识别自适应的控制算法，西门子和约克公司则直接采用PID控制，而霍尼韦尔采用PID控制和自适应控制方式。上海交通大学陈炯德等人提出一种用于变风量(VAV)系统的非线性模型预测控制，该控制方式采用具有外部输入的非线性自回归网络(NARX)和粒子群优化算法(PSO),NARX旨在预测VAV系统的受控参数(室温)，PSO作为优化器，以获得VAV系统最优控制变量。
BP神经网络作为一种具有较强的非线性映射能力和柔性的网络结构，主要应用于函数逼近,模式识别,分类应用,数据压缩等方面。北京科技大学贾超基于神经网络对多模式自适应控制方法进行研究，并提出一种基于OEM-ELM神经网络自适应控制器，对被控对象参数突变具有较好的适应性，系统的瞬态误差得到较好的控制。所以可以看出BP神经网络预测模型在实际生产过程中具有较高的实际应用价值。
因此，对变风量布风器风阀的控制系统改进和优化，是为了能够保证变风量送风更加平稳，提高设备自动化程度、降低设备损耗、降低能耗。对推动国产布风器产品发展具有重要意义。
发明内容
针对现有技术中变风量布风器变风量控制系统中存在的问题，本发明提供一种基于BP神经网络的风阀控制系统及其控制方法。
本发明所采用的具体技术方案如下：
一种变风量布风器风阀的控制系统，包括变风量布风器风量调节阀门、阀门执行器、基于BP神经网络的主控制器、数据采集器、用户操作面板，用户操作面板设定温度的信号与主控制器的输入端连接，数据采集器采集室温和布风器入口处静压，采集到的数据通过不同的传感器与主控制器的输入端连接，主控制器的输出端与阀门执行器的输入端连接。
在上述技术方案中，基于BP神经网络的主控制器包括BP神经网络预测控制模块和比例调节控制模块；数据采集器包括温度传感器和压力传感器。
在上述技术方案中，BP神经网络预测控制模块为双输入单输出模块；设定风阀开度动作的神经网络模型两个输入分别是风管内静压u和需求风量v，一个输出为阀门开度y，建立的风阀开度动作的数学模型如下：
Figure PCTCN2021082253-appb-000001
式(1)中，m为输入层的神经元数量，k为输出层的神经元数量，
Figure PCTCN2021082253-appb-000002
上述模型输出值是采用负梯度下降方式不断修正输出值，误差函数计算公式为：
Figure PCTCN2021082253-appb-000003
式(2)中，r k(n)为期望输出值，y k(n)为实际输出值。
一种变风量布风器风阀的控制系统的控制方法，具体步骤如下：
步骤一、数据采集器实时采集室温、用户操作面板设定温度以及布风器入口处静压，输入到主控制器；
步骤二、输入的温度信号在主控制器内转换为风量信号；
步骤三、数据传递给主控制器，首先在存储单元内匹配工况，匹配成功则进行步骤五，否则进行步骤四在线建模学习；
步骤四、BP神经网络预测模型模块根据输入数据对风阀开度动作的神经网络模型进行建模训练，并建立相应的输入-输出映射；
步骤五、主控制器将经过BP神经网络模型模块优化后的控制参数输出到比例调节控制模块，进而控制阀门执行器动作，实现自动变风量。
上述步骤二中的温度信号包括采集到的室温和用户操作面板设定温度。
上述步骤三中的控制方法具有在线建模学习和离线匹配工况两种功能，其中匹配工况为出厂试验的样本数据所构建的预测模型，经训练学习后存储在主控制器内。
上述步骤四包括以下流程：
A1、BP神经网络预测模型模块计算是依据数据采集器获得的数据进行建立数学模型，学习是依据用户操作面板设定温度对建模进行有效性验证；
A2、BP神经网络预测模型模块依据验证结果对模块建立的非线性模型进行修正优化；
A3、BP神经网络预测模型模块将优化结果存储到主控制器的存储单元。
步骤四中风阀开度动作包括风阀正向动作和风阀反向动作。
本发明的有益效果：本发明提供一种用于变风量布风器风阀开度的控制系统及其控制方法,与现有技术相比，充分利用了先进的控制理论、神经网络、预测控制、智能算法等，对变风量布风器风阀的控制系统实现监测、建模、控制，优化、管理和决策，避免由于温度波动因素的风阀频繁动作，达到自动变风量的目的，对于提高用户舒适度、降低能耗有非常重要意义。
附图说明
图1是本发明中控制系统的系统框图。
图2是本发明中控制方法的原理图。
图3是本发明中控制方法的BP神经网络结构图。
图4是本发明中网络模型阀门开度40％对实际风量的预测结果图。
图5是本发明中网络模型阀门开度40％对实际风量的预测误差图。
图6是本发明中网络模型阀门开度65％对实际风量的预测结果图。
图7是本发明中网络模型阀门开度65％对实际风量的预测误差图。
具体实施方式
为了加深对本发明的理解，下面将结合附图和实施例对本发明做进一步详细描述，该实施例仅用于解释本发明，并不对本发明的保护范围构成限定。
本发明针对变风量布风器风阀的控制系统，变风量风阀调节是控制系统的关键。传统的反馈控制调节响应速度慢，阀门执行器频繁动作。通过对变风量原理的分析，本发明应用BP神经网络预测模型，根据采集的室温和布风器入口处静压，建立温度和静压与阀门开度的非线性模型。根据建立的神经网络模型，应用优化算法，对输出的阀门开度寻优，得到该工况下最优值，并标定为控制器的设定值，控制阀门执行器动作，实现自动变风量。
图1是本发明变风量布风器风阀的控制系统框图，包括风量调节阀门、阀门执行器、用户操作面板、数据采集器、基于BP神经网络的主控制器(BP神经网络预测模型模块和比例调节控制模块)。数据采集器与主控制器的输入端连接，主控制器的输出端分别与阀门执行器和用户操作面板连接。
系统的工作过程为：由数据采集器测得室温，经主控制器内转换为风量传递给BP神经网络预测模型模块；由布风器入口处压力传感器测得管道内静压，并将静压信号传递给BP神经网络预测模型模块。主控制器将需求风量和静压信号作为两个输入端，经过神经网络建模计算后首先判断是阀门调节方向，选择正行程或反行程模型，预测得出阀门开度，反馈到主控制器并向阀门执行器发出指令，阀门执行器接受控制器指令后直接移动到预测阀门开度的位置，最终达到自动变风量的目的。
图2是本发明变风量布风器风阀的控制方法原理图。其工作原理为：比例调节控制模块主要用于接受数据采集器的数据、建立阀门执行器的动作过程和校正。BP神经网络预测模型模块将接收到的风量和静压样本数据，运用神经网络 学习算法建立非线性数学模型并进行仿真；通过对比用户操作面板设定温度完成神经网络的计算学习，随后将样本数据反馈给比例调节控制模块进行修正。
进一步地，所述BP神经网络预测模型为双输入单输出模型；
风阀开度动作的神经网络模型两个输入分别是风管内静压u和需求风量v，一个输出为阀门开度y。建立的风阀开度动作的数学模型如下：
Figure PCTCN2021082253-appb-000004
式(1)中，m为输入层的神经元数量，k为输出层的神经元数量，
Figure PCTCN2021082253-appb-000005
上述模型输出值是采用负梯度下降方式不断修正输出值，误差函数计算公式为：
Figure PCTCN2021082253-appb-000006
式(2)中，r k(n)为期望输出值，y k(n)为实际输出值。
上述的布风器自动变风量的控制方法，具体步骤包括：
1、数据采集器实时采集室温、用户操作面板设定温度以及布风器入口处静压，输入到主控制器；
2、输入的温度信号在主控制器内转换为风量信号；
3、数据传递给主控制器，首先在存储单元内匹配预置工况，匹配成功则进行步骤5；否则进行步骤4在线建模学习；
4、BP神经网络预测模型模块根据输入数据对风阀开度动作的神经网络模型进行建模训练，并建立相应的输入-输出映射；
5、主控制器将经过BP神经网络模型模块优化后的控制参数输出到比例调节控制模块，进而控制阀门执行器动作，实现自动变风量。
进一步地，所述步骤2中的温度信号包括采集到的室温和用户操作面板设定温度。
进一步地，本控制方法具有在线建模学习和离线匹配工况两种功能。所述步骤3中的匹配工况为出厂试验的样本数据所构建的预测模型，经训练学习后存储在主控制器内。
进一步地，所述步骤4包括：
A1、BP神经网络预测模型模块计算是依据数据采集器获得的数据进行建立数学模型，通过用户操作面板设定温度对建模进行有效性验证并学习；
A2、BP神经网络预测模型模块依据验证结果对模块建立的非线性模型进行修正优化；
A3、BP神经网络预测模型模块将优化结果存储到主控制器的存储单元。
进一步地，所述步骤4中的风阀开度动作包括风阀正向动作和风阀反向动作。
实施例：
通过公式(1)和公式(2)的函数和试验采集的数据，对建立的双输入单输出神经网络预测模型进行风阀正向动作和反向动作训练，训练后的网络结构的各连接权值和阈值计算结果如下表所示。
训练后的神经网络各神经元连接权值和阈值
Figure PCTCN2021082253-appb-000007
根据不同给定静压指令下，应用上述神经元连接权值和阈值，当输入需求风量呈现阶跃变化，网络模型对实际风量的预测结果如图4-图7所示。
风阀开度一定时，静压越大，预测误差越大；静压越小，预测误差越小。而在船用布风器日常使用过程中，小静压小流量工况的使用占比大，在大部分情况下模型都会具有很好的预测效果。误差计算结果表明，实际神经网络输出与期望输出跟随效果良好，平均误差在5％以内。
本系统提供的变风量布风器风阀的控制系统及其控制方法可以对市场上现有变风量布风器的变风量控制系统进行优化设计和改造，提高布风器的自动化程度，对改善舱室内居住的舒适度、降低设备能耗有着重要意义。
以上显示和描述了本发明的基本原理、主要特征及优点。本行业的技术人员应该了解，本发明不受上述实施例的限制，上述实施例和说明书中描述的只是说明本发明的原理，在不脱离本发明精神和范围的前提下，本发明还会有各种变化和改进，这些变化和改进都落入要求保护的本发明范围内。本发明要求保护范围由所附的权利要求书及其等效物界定。

Claims (9)

  1. 一种变风量布风器风阀的控制系统，其特征在于，包括变风量布风器风量调节阀门、阀门执行器、基于BP神经网络的主控制器、数据采集器、用户操作面板，所述用户操作面板设定温度的信号与主控制器的输入端连接，所述数据采集器采集室温和布风器入口处静压，采集到的数据通过不同的传感器与主控制器的输入端连接，所述主控制器的输出端与阀门执行器的输入端连接。
  2. 根据权利要求1中所述的变风量布风器风阀的控制系统，其特征在于，所述基于BP神经网络的主控制器包括BP神经网络预测控制模块和比例调节控制模块。
  3. 根据权利要求2中所述的变风量布风器风阀的控制系统，其特征在于，所述数据采集器包括温度传感器和压力传感器。
  4. 根据权利要求3中所述的变风量布风器风阀的控制系统，其特征在于，所述BP神经网络预测控制模块为双输入单输出模块；设定风阀开度动作的神经网络模型两个输入分别是风管内静压u和需求风量v，一个输出为阀门开度y，建立的风阀开度动作的数学模型如下：
    Figure PCTCN2021082253-appb-100001
    Figure PCTCN2021082253-appb-100002
    y＝f(f([u，v][w 1(i)，w 2(j)，w 3(k)]))  (1)
    式(1)中，m为输入层的神经元数量，k为输出层的神经元数量，
    Figure PCTCN2021082253-appb-100003
    上述模型输出值是采用负梯度下降方式不断修正输出值，误差函数计算公式为：
    Figure PCTCN2021082253-appb-100004
    式(2)中，r k(n)为期望输出值，y k(n)为实际输出值。
  5. 一种变风量布风器风阀的控制系统的控制方法，其特征在于，具体步骤如下：
    步骤一、数据采集器实时采集室温、用户操作面板设定温度以及布风器入口处静压，输入到主控制器；
    步骤二、输入的温度信号在主控制器内转换为风量信号；
    步骤三、数据传递给主控制器，首先在存储单元内匹配工况，匹配成功则进行步骤五，否则进行步骤四在线建模学习；
    步骤四、BP神经网络预测模型模块根据输入数据对风阀开度动作的神经网络模型进行建模训练，并建立相应的输入-输出映射；
    步骤五、主控制器将经过BP神经网络模型模块优化后的控制参数输出到比例调节控制模块，进而控制阀门执行器动作，实现自动变风量。
  6. 根据权利要求5所述的变风量布风器风阀的控制系统的控制方法，其特征在于，所述步骤二中的温度信号包括采集到的室温和用户操作面板设定温度。
  7. 根据权利要求5所述的变风量布风器风阀的控制系统的控制方法，其特征在于，所述步骤三中的控制方法具有在线建模学习和离线匹配工况两种功能，其中匹配工况为出厂试验的样本数据所构建的预测模型，经训练学习后存储在主控制器内。
  8. 根据权利要求5所述的变风量布风器风阀的控制系统的控制方法，其特征在于，所述步骤四包括以下流程：
    A1、BP神经网络预测模型模块计算是依据数据采集器获得的数据进行建立数学模型，学习是依据用户操作面板设定温度对建模进行有效性验证；
    A2、BP神经网络预测模型模块依据验证结果对模块建立的非线性模型进行修正优化；
    A3、BP神经网络预测模型模块将优化结果存储到主控制器的存储单元。
  9. 根据权利要求5所述的变风量布风器风阀的控制系统的控制方法，其特 征在于，所述步骤四中风阀开度动作包括风阀正向动作和风阀反向动作。
PCT/CN2021/082253 2020-09-23 2021-03-23 一种变风量布风器风阀的控制系统及其控制方法 WO2022062339A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/439,812 US12129010B2 (en) 2020-09-23 2021-03-23 Control system of damper of variable-air-volume air distributor and control method thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011011502.6 2020-09-23
CN202011011502.6A CN112093025B (zh) 2020-09-23 2020-09-23 一种变风量布风器风阀的控制系统及其控制方法

Publications (1)

Publication Number Publication Date
WO2022062339A1 true WO2022062339A1 (zh) 2022-03-31

Family

ID=73755997

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/082253 WO2022062339A1 (zh) 2020-09-23 2021-03-23 一种变风量布风器风阀的控制系统及其控制方法

Country Status (3)

Country Link
US (1) US12129010B2 (zh)
CN (1) CN112093025B (zh)
WO (1) WO2022062339A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114647221A (zh) * 2022-05-23 2022-06-21 承德京联电子科技有限公司 一种基于物联网的矿山生产链智能管控系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112093025B (zh) * 2020-09-23 2022-12-09 江苏科技大学 一种变风量布风器风阀的控制系统及其控制方法
CN115743504B (zh) * 2023-01-07 2023-04-07 中国海洋大学 一种海洋平台多舱室通风多目标优化控制方法
CN116736713A (zh) * 2023-06-13 2023-09-12 天津国能津能滨海热电有限公司 基于narx预测模型的电厂燃烧控制系统及方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010003904A1 (en) * 1999-12-20 2001-06-21 Bruno Hamery Device for air conditioning a motor-vehicle passenger compartment, with improved ventilation control
JP2013221427A (ja) * 2012-04-13 2013-10-28 Toyota Motor Corp 内燃機関の制御装置
CN109533264A (zh) * 2018-11-19 2019-03-29 江苏科技大学 一种螺旋形流道变风量船用布风器
CN110441065A (zh) * 2019-07-04 2019-11-12 杭州华电江东热电有限公司 基于lstm的燃气轮机在线检测方法与装置
CN111288610A (zh) * 2020-02-13 2020-06-16 西安建筑科技大学 一种变风量空调系统变静压自适应模糊控制方法
CN112093025A (zh) * 2020-09-23 2020-12-18 江苏科技大学 一种变风量布风器风阀的控制系统及其控制方法

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5579993A (en) * 1995-01-06 1996-12-03 Landis & Gyr Powers, Inc. HVAC distribution system identification
JP3334068B2 (ja) * 1996-01-31 2002-10-15 株式会社山武 Ｖａｖ制御システム
US6250560B1 (en) * 1998-12-21 2001-06-26 Acutherm L.P. Variable-air-volume diffuser actuator assembly and method
US7036559B2 (en) * 2003-07-08 2006-05-02 Daniel Stanimirovic Fully articulated and comprehensive air and fluid distribution, metering, and control method and apparatus for primary movers, heat exchangers, and terminal flow devices
JP4312027B2 (ja) * 2003-10-24 2009-08-12 協立エアテック株式会社 空調システムおよび空調方法
CN102129259B (zh) * 2010-01-20 2014-05-14 北京航空航天大学 用于砂尘环境试验风洞的基于神经网络pi的智能温度控制系统和方法
CN102353119B (zh) * 2011-08-09 2013-04-24 北京建筑工程学院 一种vav变风量空调系统控制方法
CN104654538A (zh) * 2013-11-21 2015-05-27 深圳市中兴康讯电子有限公司 一种控制风量输出的方法及装置
WO2019040067A1 (en) * 2017-08-24 2019-02-28 Siemens Industry, Inc. SYSTEM AND METHOD FOR CONTROLLING FLUID DISTRIBUTION IN A BUILDING
JP2019203670A (ja) * 2018-05-25 2019-11-28 アズビル株式会社 空調制御装置および方法
CN109798646B (zh) * 2019-01-31 2021-03-30 上海真聂思楼宇科技有限公司 一种基于大数据平台的变风量空调控制系统和方法
CN111059690B (zh) * 2019-11-04 2021-03-19 珠海格力电器股份有限公司 一种变风量空调的内模解耦控制方法及控制系统
CN111238851B (zh) * 2020-02-24 2022-11-08 江苏科技大学 船用变风量空调可靠性测试系统及测试方法
CN111520878A (zh) * 2020-05-02 2020-08-11 苏州科技大学 一种基于rbf神经网络的空调温控系统及其控制方法
CN111594996A (zh) * 2020-05-29 2020-08-28 桂林电子科技大学 一种基于深度置信神经网络的变风量空调送风量的预测方法
CN113446683B (zh) * 2021-06-30 2023-01-17 广州地铁设计研究院股份有限公司 一种地铁车站设备及管理用房智能空调

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010003904A1 (en) * 1999-12-20 2001-06-21 Bruno Hamery Device for air conditioning a motor-vehicle passenger compartment, with improved ventilation control
JP2013221427A (ja) * 2012-04-13 2013-10-28 Toyota Motor Corp 内燃機関の制御装置
CN109533264A (zh) * 2018-11-19 2019-03-29 江苏科技大学 一种螺旋形流道变风量船用布风器
CN110441065A (zh) * 2019-07-04 2019-11-12 杭州华电江东热电有限公司 基于lstm的燃气轮机在线检测方法与装置
CN111288610A (zh) * 2020-02-13 2020-06-16 西安建筑科技大学 一种变风量空调系统变静压自适应模糊控制方法
CN112093025A (zh) * 2020-09-23 2020-12-18 江苏科技大学 一种变风量布风器风阀的控制系统及其控制方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LEI, SHUYA: "Study on Resistance and Aerodynamic Noise Performance of Low Noise VAV Marine Air Distributor", CHINESE MASTER'S THESES FULL-TEXT DATABASE, 9 June 2020 (2020-06-09), pages 1 - 96, XP055914070 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114647221A (zh) * 2022-05-23 2022-06-21 承德京联电子科技有限公司 一种基于物联网的矿山生产链智能管控系统

Also Published As

Publication number Publication date
CN112093025A (zh) 2020-12-18
CN112093025B (zh) 2022-12-09
US12129010B2 (en) 2024-10-29
US20220306265A1 (en) 2022-09-29

Similar Documents

Publication Publication Date Title
WO2022062339A1 (zh) 一种变风量布风器风阀的控制系统及其控制方法
WO2022166919A1 (zh) 一种畜禽舍养殖环境温度预测控制系统及其调控方法
CN109270842B (zh) 一种基于贝叶斯网络的区域供热模型预测控制系统及方法
Li et al. Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system
CN109253494B (zh) 一种基于热负荷预测的电蓄热装置的控制方法
CN109798646B (zh) 一种基于大数据平台的变风量空调控制系统和方法
CN104019526A (zh) 改进pso算法模糊自适应pid温湿度控制系统及方法
CN114216256B (zh) 离线预训练-在线学习的通风系统风量控制方法
CN114265306A (zh) 海洋平台通风系统在线风平衡控制方法及控制系统
CN112855513A (zh) 基于遗传算法的空压机集群控制系统能耗优化方法及系统和装置
CN115329659B (zh) 废物焚烧炉二噁英排放实时预警及智能控制的方法及系统
CN113606650A (zh) 基于机器学习算法的智慧供热室温调控系统
CN109857177B (zh) 一种建筑电气节能监测方法
CN110684547A (zh) 一种生物质热解炭化窑优化控制方法
CN116258049A (zh) 一种模块化空调系统的室内热环境智能预测控制方法
CN112747477B (zh) 一种安全节能的燃气热水锅炉智能控制系统及方法
CN210033605U (zh) 一种发动机电控硅油风扇的节能优化控制系统
CN113606649A (zh) 基于机器学习算法的智慧供热站控预测系统
Wang et al. Application of an intelligent PID control in heating ventilating and air-conditioning system
CN113625557A (zh) 一种在线优化模型的hvac系统模型预测控制方法
CN118066564B (zh) 一种加热炉低氧燃烧的多变量控制系统
CN215336607U (zh) 一种可环境自适应温度调节地暖设备
Liu Application of Improved Particle Swarm Optimization Algorithm in Converter Differential Pressure
CN117781428B (zh) 一种超低能耗建筑空气循环调控系统
CN103353161A (zh) 变风量空调压力无关型末端装置控制系统及其控制方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21870728

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21870728

Country of ref document: EP

Kind code of ref document: A1