WO2018054055A1 - 用于地铁暖通空调系统的负荷预测和控制系统及其方法 - Google Patents

用于地铁暖通空调系统的负荷预测和控制系统及其方法 Download PDF

Info

Publication number
WO2018054055A1
WO2018054055A1 PCT/CN2017/082142 CN2017082142W WO2018054055A1 WO 2018054055 A1 WO2018054055 A1 WO 2018054055A1 CN 2017082142 W CN2017082142 W CN 2017082142W WO 2018054055 A1 WO2018054055 A1 WO 2018054055A1
Authority
WO
WIPO (PCT)
Prior art keywords
load
data
subway
predicted
control
Prior art date
Application number
PCT/CN2017/082142
Other languages
English (en)
French (fr)
Inventor
孙栋军
王升
王娟
刘国林
刘羽松
Original Assignee
珠海格力电器股份有限公司
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 珠海格力电器股份有限公司 filed Critical 珠海格力电器股份有限公司
Priority to EP17852129.0A priority Critical patent/EP3483517B1/en
Publication of WO2018054055A1 publication Critical patent/WO2018054055A1/zh
Priority to US16/280,909 priority patent/US10983542B2/en

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00Control of temperature
    • G05D23/19Control of temperature characterised by the use of electric means
    • G05D23/1917Control of temperature characterised by the use of electric means using digital means
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00Control of temperature
    • G05D23/19Control of temperature characterised by the use of electric means
    • G05D23/1927Control of temperature characterised by the use of electric means using a plurality of sensors
    • G05D23/193Control of temperature characterised by the use of electric means using a plurality of sensors sensing the temperaure in different places in thermal relationship with one or more spaces
    • G05D23/1931Control of temperature characterised by the use of electric means using a plurality of sensors sensing the temperaure in different places in thermal relationship with one or more spaces to control the temperature of one space
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B61RAILWAYS
    • B61DBODY DETAILS OR KINDS OF RAILWAY VEHICLES
    • B61D27/00Heating, cooling, ventilating, or air-conditioning
    • B61D27/0072Means for cooling only
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/30Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/62Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/70Control systems characterised by their outputs; Constructional details thereof
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties
    • F24F2110/20Humidity
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/04Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/042Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D23/00Control of temperature
    • G05D23/19Control of temperature characterised by the use of electric means
    • G05D23/1927Control of temperature characterised by the use of electric means using a plurality of sensors
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60HARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
    • B60H1/00Heating, cooling or ventilating [HVAC] devices
    • B60H1/00642Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
    • B60H1/0073Control systems or circuits characterised by particular algorithms or computational models, e.g. fuzzy logic or dynamic models
    • B60H2001/00733Computational models modifying user-set values
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00Control or safety arrangements
    • F24F11/62Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63Electronic processing
    • F24F11/64Electronic processing using pre-stored data
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2110/00Control inputs relating to air properties
    • F24F2110/10Temperature
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00Control inputs relating to users or occupants
    • F24F2120/10Occupancy
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2130/00Control inputs relating to environmental factors not covered by group F24F2110/00
    • F24F2130/30Artificial light
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2140/00Control inputs relating to system states
    • F24F2140/20Heat-exchange fluid temperature
    • FMECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24HEATING; RANGES; VENTILATING
    • F24FAIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2140/00Control inputs relating to system states
    • F24F2140/50Load
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/20Pc systems
    • G05B2219/26Pc applications
    • G05B2219/2614HVAC, heating, ventillation, climate control
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02TCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T30/00Transportation of goods or passengers via railways, e.g. energy recovery or reducing air resistance

Definitions

  • the present invention relates to the field of HVAC, and more particularly to a load forecasting and control system for a subway HVAC system and a load forecasting and control method for a metro HVAC system.
  • the HVAC system is open all year round and has a long running time.
  • the annual energy consumption level is much larger than that of ordinary buildings.
  • the new energy-saving control strategy for the development of subway HVAC is to reduce the energy consumption level of the subway HVAC. have important meaning.
  • the traditional subway cold station control mode is mostly PID negative feedback control, which has serious hysteresis, which may cause the control result to oscillate, and the energy saving control effect is not ideal.
  • an object of the present invention is to provide a load prediction control system and method for a subway HVAC system (such as a cold station), which solves the problems of poor conventional load prediction accuracy and poorly ideal air conditioning system control.
  • a load forecasting and control system for a metro HVAC system includes a basic database, a sensing system, and a load forecasting unit. And a controller, the base database storing historical data related to the subway HVAC system, the sensing system providing measured data (current measured data) related to the subway HVAC system, the load The prediction section calculates a predicted load value of the subway HVAC system based on the historical data and the measured data and transmits the predicted load value to the control section, the controller based on the predicted load value A control command is issued to control the operation of the subway HVAC system.
  • the historical data and the measured data include strong time-varying data.
  • the strong time-varying data includes at least one of a real-time personnel number in the subway station, a subway departure information (including, for example, the number and timing of departures), an ambient temperature, and an ambient humidity.
  • the base database rejects weak time-varying data including subway station ventilation, subway station equipment, subway station lighting, and/or subway station enclosure temperature differential heat transfer to simplify the base database.
  • the subway HVAC system is implemented as a subway cooling station, and the historical data and/or the measured data further includes a load amount, a predicted load amount, a chilled water supply temperature, a chilled water return water temperature, and/or Or chilled water flow.
  • the sensing system includes a number of access control personnel for providing a number of real-time personnel in the subway station.
  • the sensing system includes a departure information detecting device that communicates with the vehicle operation management system to acquire current subway departure information and/or future subway departure information.
  • the historical data in the base database is time-series based on time-series data
  • the load prediction unit performs load prediction by an exponential smoothing method.
  • the metro HVAC system further includes a plurality of data preprocessing modules, and the sensing data of the sensing system is classified into a corresponding data preprocessing module of the plurality of data preprocessing modules according to the data characteristics. Associated with, and the sensed data is transmitted to the controller after being pre-processed by the data pre-processing module and/or stored in the base database in a classified manner.
  • the sensing data of the sensing system is classifiedly stored in a corresponding data folder classified according to season, date and/or time characteristics in the basic database, the data folder including a working day data file Folder, Saturday data folder, Sunday data folder, and/or holiday data folder.
  • the sensing system transmits the measured data to the load forecasting unit for performing Load prediction, and the sensing system also transmits the measured data to the base database to store historical data as a next load prediction.
  • said sensing system also transmits said measured data to said controller such that said controller issues said control command based on said predicted load value and said measured data.
  • the subway HVAC system is implemented as a subway cooling station, the subway cooling station comprising at least one of the following cold station devices: a cold machine, a chilled water pump, a valve, a cooling water pump, and a cooling tower, and
  • the metro cold station also includes an actuator corresponding to the cold station device, the actuator receiving the control command from the controller to control operation of the cold station device.
  • the subway HVAC system further includes a load amount determining unit that determines an actual load amount based on the sensing data of the sensing system, and the load predicting unit is based on the predicted load The predicted load value of the next load prediction is corrected by the difference between the value and the actual load amount fed back from the load amount determining unit.
  • a load prediction and control method for a subway HVAC system calculates a predicted load value of the subway HVAC system by the load forecasting and control system as described above and controls operation of the subway HVAC system based on the predicted load value.
  • the load prediction and control method comprises the following steps:
  • the load forecasting unit Transmitting, from the sensing system, the real-time personnel number and the ambient temperature in the subway station sensed in real time to the load forecasting unit, and then the load forecasting unit calculates a personnel quantity correction coefficient and a temperature correction coefficient of the first load forecast;
  • the step of calculating the personnel quantity correction coefficient and the temperature correction coefficient of the first predicted load by the load prediction unit comprises: real-time sensing of the number of real-time personnel and the ambient temperature in the subway station obtained from the sensing system The corresponding historical data at the same time on the previous day or the previous days is compared to obtain the personnel quantity correction coefficient and the temperature correction coefficient of the first predicted load.
  • the load prediction and control method further comprises the following steps:
  • the load amount determination section of the subway HVAC system determines an actual load amount based on the sensed data of the sensing system
  • the load predicting unit corrects the level factor and the normalized period factor based on a difference between the first predicted load value and the actual load amount fed back from the load amount determining unit to obtain an updated level factor And updated normalization period factors;
  • the load forecasting unit Transmitting, from the sensing system, the real-time personnel number and the ambient temperature in the subway station sensed in real time to the load forecasting unit, and then the load forecasting unit calculates a personnel quantity correction coefficient and a temperature correction coefficient of the second predicted load; as well as
  • a second predicted load value is calculated based on the updated level factor, the updated normalized period factor, and the second number of predicted load personnel correction coefficients and temperature correction coefficients.
  • the load forecasting control system and method for a subway HVAC system provided by the present invention adopts an improved seasonal exponential smoothing method, based on historical information, combined with measured information at a future time, and calculates and outputs a predicted load value to realize a cold machine. Control of chilled water pumps, cooling water pumps, cooling towers, etc., and through the difference between the measured load of the building (subway station) and the predicted load, the cold output capability is continuously corrected to improve the overall control effect of the subway cold station.
  • the invention solves the problems of poor conventional load prediction accuracy, unsatisfactory control of the air conditioning system, and also has the advantages of saving initial investment, reliable operation, improving energy saving effect of the HVAC system, reducing database storage data, simple load prediction model, and strong practicability. .
  • FIG. 1 is a schematic view showing a load forecasting and control system for a subway HVAC system according to the present invention
  • FIG. 2 is a diagram showing a load forecasting and control system for a subway HVAC system according to the present invention. Another schematic diagram of the system;
  • FIG. 3 is a schematic view showing data acquisition, preprocessing, and storage of a load prediction and control method for a subway HVAC system according to the present invention
  • FIG. 4 is an exemplary flow chart of a load prediction and control method for a metro HVAC system according to the present invention.
  • the present invention provides a load forecasting and control system for a metro HVAC system, such as a cold station.
  • the system may include a base database, load forecasting software (load forecasting section), and a controller.
  • the base database can include historical information (historical data).
  • the history information can be transmitted to the load forecasting software, whereby the load forecasting software can calculate and output the predicted load value in combination with the historical information and the measured information (measured data).
  • the controller issues an instruction based on the predicted load value to perform a power-on action.
  • the load forecasting software corrects the predicted load value based on the measured measured building load (the subway load) and sequentially cycles.
  • the measured information may also be referred to as foresight information.
  • the load forecasting and control system for the subway HVAC system provided by the invention conveniently integrates the historical information (original information) of the subway station, and can obtain the actual measurement of the building load affecting the future time of the subway station without additional investment. (Foreseeable) information, the basic database simplifies the traditional building load forecasting model database, eliminating the influencing factors (ie weak time-varying data) of ventilation, solar radiation, equipment, lighting, and temperature-dependent heat transfer of the envelope structure.
  • a building load forecasting and control system for a subway station also includes an actuator, a communication module, a personnel counter (eg, can be implemented as a doorkeeper number acquisition device), a temperature sensor, a humidity sensor, a flow sensor, data One or more of the pre-processing module and the departure information detecting device.
  • the actuator can feed back the measured building load to the load forecasting software.
  • the metro HVAC system may further include a load amount determining portion (for example, integrated in a controller or a load predicting portion), the load amount determining portion is based on a sensing system (composed of various sensors, and a part of the sensors may The sensing data attached to the corresponding actuator determines the actual load amount, whereby the load predicting portion can calculate the difference between the predicted load value and the actual load amount fed back from the load amount determining portion. Correct the predicted load value of the next load forecast.
  • the temperature sensor and the humidity sensor respectively collect meteorological parameters (eg, dry bulb temperature, relative humidity), transmit to the data preprocessing module, obtain meteorological data (corresponding to ambient temperature and ambient humidity), and store them in the basic database.
  • meteorological parameters eg, dry bulb temperature, relative humidity
  • the personnel counter obtains the current number of real-time personnel from the subway console, and is processed and stored in the basic database.
  • the departure information detecting device determines the number of trains of the subway station at the next moment.
  • the data pre-processing module may include a first data pre-processing module, a second data pre-processing module, a third data pre-processing module, and a fourth data pre-processing module.
  • the data processed by the first data pre-processing module may include a device start-stop state and management information
  • the data processed by the second data pre-processing module may include temperature and humidity
  • the data processed by the third data pre-processing module may include a staff quantity
  • the first The data processed by the four data preprocessing modules includes temperature and flow rate (such as chilled water supply temperature, chilled water return water temperature, chilled water flow rate, cooling water temperature, and cooling water flow rate).
  • the temperature sensor and the flow sensor transmit the collected cold station operation data to the controller through the data preprocessing module as a basis for issuing the control command, and store the calculated cold load in the basic database.
  • the controller controls the actuator, and the actuator issues an instruction to control one or more of the cold machine, the chilled water pump, the cooling water pump, the cooling tower, and the valve (such as the electric butterfly valve), thereby realizing the cooling capacity of the subway cold station. Precise supply.
  • the basic database includes a weather parameter file, a subway personnel data file, the dry bulb temperature and the relative humidity are stored in the weather parameter file, and the current time real-time personnel quantity is stored in the subway personnel data file.
  • the load forecasting calculation is automatically started according to the preset air conditioning time period, the corresponding historical data is retrieved from the basic database, and the number of persons that can be directly measured or obtained by calculation is input in real time. , dry bulb temperature, relative humidity, measured cold load, thereby calculating the predicted load value at the next moment, and transmitting the predicted load value to the controller via the communication module.
  • the controller calculates the number of cold machines, chilled water pumps, cooling water pumps, cooling towers, and electric butterfly valves that need to be turned on based on the predicted load value, and sends a power-on command according to a preset time to perform a power-on action.
  • the controller can also control the capacity rate of each cold station device by the issued control command (for example, for the variable frequency water pump, the output capacity of the variable frequency water pump can be adjusted by controlling the frequency of the variable frequency water pump).
  • the controller adjusts the cooling capacity of the cold station according to the difference between the previous predicted value and the measured value, for example, the cooling water, the chilled water flow rate, etc.; after receiving the next predicted value given by the load forecasting software
  • the controller realizes feedforward control according to the difference between the predicted value and the measured value, and then adjusts the output of the cold machine, the chilled water, the flow rate of the cooling water, and the like.
  • the invention utilizes the existing resources of the subway station to relatively easily determine the number of passengers, the condition of the vehicle, the temperature and humidity, so that the collection of key information in the future is very simple and the cost can be reduced.
  • a fuzzy relationship between the subway building load and the historical information (data) and/or the measured information (data) is established, which facilitates the improvement of the building load prediction accuracy.
  • the historical information includes a dry time temperature based on a time series, a wet bulb temperature, a train departure quantity, a number of people in the subway station, a subway station construction load, a chilled water supply and return water temperature, a chilled water flow rate, and a chilled water supply and return water temperature difference.
  • At least one of the subway cold stations has a lot of historical information and is easy to collect, which can improve the accuracy of building load forecasting and reduce the cost of collecting historical information.
  • the measured information includes at least one of an ambient dry bulb temperature, an ambient wet bulb temperature, a train departure number, and a real-time personnel number in the subway station.
  • the number of real-time personnel in the subway station can be accurately counted by the personnel counter of the access control system, and the vehicle operation management system has planned the next time (the time required for the chilled water cycle for one week) to generate the logarithm of the subway station. Therefore, data collection is very convenient.
  • the influencing factors such as ventilation, solar radiation, equipment, lighting, and temperature difference heat transfer of the envelope structure
  • the number of real-time personnel in the subway station, subway departure information, ambient temperature, and environmental humidity are compared. The data will change over time. For example, in the morning and evening of the working day, the number of real-time personnel in the subway station is large, and the ambient temperature is high at noon in summer. Therefore, these data are referred to as strong time-varying data in this application.
  • a load prediction and control method for a subway subway HVAC system may include a data acquisition and integration processing phase and a prediction calculation phase.
  • the data collection and integration processing stage may include: collecting data and classifying different data folders stored in the basic database, that is, pre-setting the cold load data classification form.
  • the predictive calculation phase can include the following steps.
  • the prediction interval is preset in the program, and the measured cold load Q(t) of d(n-1) and d(n-2) in the near two days is extracted from the basic database of the forecast day, and the near-calculated load is calculated respectively.
  • Two-day measured hourly cold load average (Here, it should be noted that it may be in the past few days or more than two days in recent days).
  • the number of subway indoors and the outdoor air temperature monitored in real time are transmitted to the load forecasting model to calculate the temperature correction coefficient ⁇ (1) of the first load forecast and the indoor personnel quantity correction coefficient ⁇ (1).
  • the first predicted load value Q(1) of the predicted date is calculated.
  • the measured cold load, meteorological parameters, and the number of subway personnel can be stored in the corresponding data folder for backup.
  • the controller transmits a power-on command in advance (for example, advance ( ⁇ + ⁇ 1)) according to the preset first air-conditioning time advance value ⁇ 1 and the chilled water cycle period ⁇ and according to the predicted load value.
  • a power-on command in advance for example, advance ( ⁇ + ⁇ 1)
  • the load forecasting model calculates the forecasting date.
  • the second predicted load value Q(2) At the same time, the measured cold load, meteorological parameters, and the number of subway personnel can be stored in the corresponding data folder for later use.
  • the cold load demand at the subsequent time is sequentially predicted, and after the last air conditioning time point prediction is over, the cold station controller sends a shutdown command to end the day's load forecasting work.
  • the data folder includes a workday data folder, a Saturday data folder, a Sunday data folder, a holiday data folder, wherein each type of folder includes historical weather parameters, historical room personnel, and historical cold load data. At least one of historically predicted cold load data.
  • the average measured hourly cold load in the past two days is:
  • the first predicted load value of the forecast day is:
  • the horizontal factor S and the periodic factor are respectively corrected, and the updated St(i), Ct(i) are obtained. );
  • the temperature correction coefficient ⁇ of the second predicted load value, the correction factor of the indoor personnel quantity ⁇ , and the second predicted load value of the forecast date are:
  • the data collection and integration processing stages include:
  • Data collection phase including meteorological data collection, data collection of subway access control system, data collection of central air conditioning system and management information collection;
  • Data preprocessing stage including implementation of data preprocessing and management information preprocessing
  • the cooling capacity, the cooling capacity prediction value, the personnel room rate, the outdoor dry bulb temperature, and the wet bulb temperature are stored in the load prediction model.
  • the horizontal factor St of the predicted value is corrected, and the period factor Ct;
  • the load forecasting and control system and method for the subway HVAC system utilizes the existing data information of the subway cold station, and can obtain the actual measurement of the building load affecting the future time of the subway cold station without additional investment. Foresee) information, apply the improved seasonal exponential smoothing method to calculate the construction load of the subway station at the next moment (the time required for chilled water circulation for one week), and issue instructions to control the cold machine, chilled water pump, cooling water pump, cooling tower, electric butterfly valve, and then achieve Precise air conditioning at the subway station.
  • the load forecasting and control system and method for the metro HVAC system provided by the invention can solve the problems of poor conventional load forecasting accuracy, unsatisfactory control of the air conditioning system, and the like, saving initial investment, low application difficulty, reliable operation, and improved warming.
  • the energy-saving effect of the air-conditioning system is reduced, the database storage data is reduced, the load prediction model is simple, and the utility is strong.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Atmospheric Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Remote Sensing (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

一种用于地铁暖通空调系统的负荷预测和控制系统。在一个方面中,提供一种用于地铁暖通空调系统的负荷预测和控制系统。该系统包括基础数据库、感测系统、负荷预测部和控制器,基础数据库存储有历史数据,感测系统提供实测数据,负荷预测部基于历史数据和实测数据而计算出地铁暖通空调系统的预测负荷值并且将预测负荷值传输至控制部,控制器基于预测负荷值发出控制指令以控制地铁暖通空调系统的运行。历史数据和实测数据包括强时变性数据。还提供了一种用于地铁暖通空调系统的负荷预测和控制方法。解决了传统负荷预测精度差、空调系统控制欠理想等问题。

Description

用于地铁暖通空调系统的负荷预测和控制系统及其方法
本申请要求于2016年09月20日提交中国专利局、申请号为201610836083.7、发明名称为“用于地铁暖通空调系统的负荷预测和控制系统及其方法”上述中国专利申请的优先权,其全部内容通过引用结合在上述申请中。
技术领域
本发明涉及暖通空调领域,尤其涉及在负荷预测方面做出改进的用于地铁暖通空调系统的负荷预测和控制系统以及用于地铁暖通空调系统的负荷预测和控制方法。
背景技术
在地铁运营过程中,暖通空调系统全年开启,运行时间长,年能耗水平相比普通建筑物大很多,对地铁暖通空调开发新的节能控制策略对于降低地铁暖通空调能耗水平有重要意义。传统地铁冷站控制方式多为PID负反馈控制,存在较为严重的滞后性,可能会导致控制结果的震荡,节能控制效果不够理想。
目前也有些前馈控制方法,主要是采用线性回归法、神经网络算法、指数平滑法等空调负荷预测来实现冷站的提前控制,但应用于地铁的暖通空调系统时这些负荷预测控制系统依然存在较多不足,如线性回归法预测精度较差,而神经网络算法工程应用局限性较多。地铁建筑负荷难预测、多时变性的原因主要是受不可控的环境外界温湿度、地铁人员散热量、散湿潜热影响,因此建筑负荷预测的精确性是空调系统前馈控制策略是否合理的根本性因素。
这里,应当指出的是,本部分中所提供的技术内容旨在有助于本领域技术人员对本发明的理解,而不一定构成现有技术。
发明内容
有鉴于此,本发明的目的是提供一种用于地铁暖通空调系统(比如冷站)的负荷预测控制系统及方法,解决传统负荷预测精度差,空调系统控制欠理想等问题。
根据本发明的一个方面,提供一种用于地铁暖通空调系统的负荷预测和控制系统。所述负荷预测和控制系统包括基础数据库、感测系统、负荷预测部 和控制器,所述基础数据库存储有与所述地铁暖通空调系统相关的历史数据,所述感测系统提供与所述地铁暖通空调系统相关的实测数据(当前实测数据),所述负荷预测部基于所述历史数据和所述实测数据而计算出所述地铁暖通空调系统的预测负荷值并且将所述预测负荷值传输至所述控制部,所述控制器基于所述预测负荷值发出控制指令以控制所述地铁暖通空调系统的运行。所述历史数据和所述实测数据包括强时变性数据。
优选地,所述强时变性数据包括地铁站内实时人员数量、地铁发车信息(例如包括发车数量和时刻)、环境温度和环境湿度中的至少一者。
优选地,所述基础数据库剔除包括地铁站通风、地铁站设备、地铁站照明和/或地铁站围护结构温差传热在内的弱时变性数据,以便简化所述基础数据库。
优选地,所述地铁暖通空调系统实施为地铁冷站,以及,所述历史数据和/或所述实测数据还包括负荷量、预测负荷量、冷冻水供水温度、冷冻水回水温度和/或冷冻水流量。
优选地,所述感测系统包括用于提供所述地铁站内实时人员数量的门禁人员数量采集装置。
优选地,所述感测系统包括发车信息检测装置,所述发车信息检测装置与车辆运行管理系统通信以获取当前地铁发车信息和/或未来地铁发车信息。
优选地,所述基础数据库中的所述历史数据为基于时间序列的逐时数据,以及,所述负荷预测部通过指数平滑法进行负荷预测。
优选地,所述地铁暖通空调系统还包括多个数据预处理模块,所述感测系统的感测数据根据数据特性被分类为与所述多个数据预处理模块中的相应数据预处理模块相关联,以及,所述感测数据在经过所述数据预处理模块进行预处理之后被传输至所述控制器并且/或者被分类地存储在所述基础数据库中。
优选地,所述感测系统的感测数据被分类地存储在所述基础数据库中的根据季节、日期和/或时刻特性分类的相应数据文件夹中,所述数据文件夹包括工作日数据文件夹、星期六数据文件夹、星期日数据文件夹和/或假日数据文件夹。
优选地,所述感测系统将所述实测数据传输至所述负荷预测部以便进行 负荷预测,并且所述感测系统还将所述实测数据传输至所述基础数据库以便存储作为下一负荷预测的历史数据。
优选地,所述感测系统还将所述实测数据传输至所述控制器,使得所述控制器基于所述预测负荷值和所述实测数据发出所述控制指令。
优选地,所述地铁暖通空调系统实施为地铁冷站,所述地铁冷站包括下述冷站装置中的至少一者:冷机、冷冻水泵、阀门、冷却水泵和冷却塔,以及,所述地铁冷站还包括与所述冷站装置对应的执行机构,所述执行机构从所述控制器接收所述控制指令以控制所述冷站装置的运行。
优选地,所述地铁暖通空调系统还包括负荷量确定部,所述负荷量确定部基于所述感测系统的感测数据确定实际负荷量,以及,所述负荷预测部基于所述预测负荷值与从所述负荷量确定部反馈的所述实际负荷量的差修正下一负荷预测的预测负荷值。
根据本发明的另一方面,提供一种用于地铁暖通空调系统的负荷预测和控制方法。所述负荷预测和控制方法通过如上所述的负荷预测和控制系统来计算所述地铁暖通空调系统的预测负荷值并且基于所述预测负荷值来控制所述地铁暖通空调系统的运行。
优选地,所述负荷预测和控制方法包括如下步骤:
从所述基础数据库中提取近两日或更多日的负荷量,然后分别计算近两日或更多日的逐时负荷量平均值;
基于所述逐时负荷量平均值计算近两日或更多日的水平因子;
基于所述逐时负荷量平均值计算近两日或更多日的趋势因子;
计算近两日或更多日中每日的周期因子,然后取平均并进行正态化处理而获得正态化周期因子;
从所述感测系统将实时感测到的地铁站内实时人员数量和环境温度传输至所述负荷预测部,然后所述负荷预测部计算第一个负荷预测的人员数量修正系数和温度修正系数;
基于所述水平因子、所述正态化周期因子以及所述第一个负荷预测的人员数量修正系数和温度修正系数计算第一个预测负荷值;以及
将所述第一个预测负荷值传输至所述控制部,然后所述控制器基于所述第一个预测负荷值发出所述控制指令以控制所述地铁暖通空调系统的运行。
优选地,所述负荷预测部计算第一个预测负荷的人员数量修正系数和温度修正系数的步骤包括:将从所述感测系统获得的实时感测到的地铁站内实时人员数量和环境温度与前一日或前几日同一时刻的相应历史数据进行比较而获得所述第一个预测负荷的人员数量修正系数和温度修正系数。
优选地,所述负荷预测和控制方法还包括如下步骤:
在所述第一个负荷预测结束之后,由所述地铁暖通空调系统的负荷量确定部基于所述感测系统的感测数据确定实际负荷量;
所述负荷预测部基于所述第一个预测负荷值与从所述负荷量确定部反馈的所述实际负荷量的差修正所述水平因子和所述正态化周期因子而获得更新的水平因子和更新的正态化周期因子;
从所述感测系统将实时感测到的地铁站内实时人员数量和环境温度传输至所述负荷预测部,然后所述负荷预测部计算第二个预测负荷的人员数量修正系数和温度修正系数;以及
基于所述更新的水平因子、所述更新的正态化周期因子以及所述第二个预测负荷的人员数量修正系数和温度修正系数计算第二个预测负荷值。
本发明提供的用于地铁暖通空调系统的负荷预测控制系统及方法,采用改进型季节性指数平滑法,基于历史信息,并结合未来时刻的实测信息,通过计算并输出预测负荷值实现冷机、冷冻水泵、冷却水泵、冷却塔等的控制,并且通过实测建筑(地铁站)负荷与预测负荷之差,不断修正冷机输出能力,改善地铁冷站全局控制效果。
本发明解决了传统负荷预测精度差,空调系统控制欠理想等问题,还具有节省初投资,运行可靠,改善暖通空调系统节能效果,减少数据库存储数据,负荷预测模型简单,实用性强等优点。
附图说明
通过以下参照附图对本发明实施例的描述,本发明的上述以及其它目的、特征和优点将更为清楚,在附图中:
附图1是示出本发明涉及的用于地铁暖通空调系统的负荷预测和控制系统的示意图;
附图2是示出本发明涉及的用于地铁暖通空调系统的负荷预测和控制系 统的另一示意图;
附图3是示出本发明涉及的用于地铁暖通空调系统的负荷预测和控制方法的数据采集、预处理及存储的示意图;以及
附图4是本发明涉及的用于地铁暖通空调系统的负荷预测和控制方法的示例性流程图。
具体实施方式
以下基于实施例对本发明进行描述,但是本发明并不仅仅限于这些实施例。
如图1-2所示,本发明提供了一种用于地铁暖通空调系统(比如冷站)的负荷预测和控制系统。该系统可以包括基础数据库、负荷预测软件(负荷预测部)和控制器。基础数据库可以包括历史信息(历史数据)。可以将历史信息传输给负荷预测软件,由此负荷预测软件可以结合历史信息和实测信息(实测数据)而计算并输出预测负荷值。控制器根据预测负荷值发出指令,以便执行开机动作。负荷预测软件根据反馈的实测建筑负荷(地铁负荷量)对预测负荷值进行修正,依次循环运行。这里,实测信息也可以称为预见信息。
本发明提供的用于地铁暖通空调系统的负荷预测和控制系统方便地集成了地铁站历史信息(原有信息),并且无需额外较大投资即可获得影响地铁站未来时刻的建筑负荷的实测(预见)信息,基础数据库中简化了传统建筑负荷预测模型数据库,剔除了通风、太阳辐射、设备、照明、围护结构温差传热等时变性不强的影响因素(即弱时变性数据)。
在一些实施例中,用于地铁站的建筑负荷预测和控制系统还包括执行机构、通讯模块、人员计数器(例如,可以实施为门禁人员数量采集装置)、温度传感器、湿度传感器、流量传感器、数据预处理模块、发车信息检测装置中的一者或多者。
在一些示例中,执行机构可以将实测建筑负荷反馈给负荷预测软件。在其它示例中,地铁暖通空调系统还可以包括负荷量确定部(例如集成在控制器或负荷预测部中),该负荷量确定部基于感测系统(由各种传感器组成,并且一部分传感器可以附接在相应的执行机构中)的感测数据确定实际负荷量,由此,负荷预测部可以基于预测负荷值与从负荷量确定部反馈的实际负荷量的差 修正下一负荷预测的预测负荷值。
温度传感器和湿度传感器分别采集气象参数(比如,干球温度、相对湿度),传送至数据预处理模块,获得气象数据(对应于环境温度和环境湿度),并存储于基础数据库中。
人员计数器从地铁控制台获得当前时刻实时人员数量,经处理后存储于所述基础数据库中。
发车信息检测装置确定下一时刻地铁站发车对数。
数据预处理模块可以包括第一数据预处理模块、第二数据预处理模块、第三数据预处理模块、第四数据预处理模块。然而,应当理解的是,数据预处理模块的数量不限于此。第一数据预处理模块处理的数据可以包括设备启停状态、管理信息,第二数据预处理模块处理的数据可以包括温度、湿度,第三数据预处理模块处理的数据可以包括人员量,而第四数据预处理模块处理的数据包括可以温度、流量(比如冷冻水供水温度、冷冻水回水温度、冷冻水流量、冷却水温度、冷却水流量)。
温度传感器、流量传感器将采集的冷站运行数据经数据预处理模块而传输至控制器作为控制指令发出的依据,并将计算的冷负荷存储于基础数据库中。
优选地,控制器控制执行机构,执行机构发出指令控制冷机、冷冻水泵、冷却水泵、冷却塔、阀门(比如电动蝶阀)中的一者或多者,由此实现对地铁冷站制冷量的精确供给。
优选地,基础数据库包括气象参数文件、地铁人员数据文件,干球温度、相对湿度存储于气象参数文件中,而当前时刻实时人员数量存储于地铁人员数据文件中。
在一些实施例中,启动负荷预测软件后,根据预先设置的空调时间段,自动启动负荷预测计算,从基础数据库中调取相应历史数据,并实时输入可直接测量获得或经过计算获得的人员数量、干球温度、相对湿度、实测冷负荷,由此计算出下一时刻预测负荷值,并经通讯模块将预测负荷值传输至控制器。控制器基于预测负荷值计算出需要开启的冷机、冷冻水泵、冷却水泵、冷却塔、电动蝶阀的数量,根据预先设定时间发送开机命令,执行开机动作。控制器还可通过所发出的控制指令来控制各冷站装置的能力率(例如,对于变频水泵而言,可以通过控制变频水泵的频率而调整变频水泵的输出能力)。当未获得下 一个预测值时,所述控制器根据前一个预测值与实测值之差,调整例如冷却水、冷冻水流量等而调节冷站供冷量;接到负荷预测软件给出的下一个预测值后,控制器根据预测值与实测值之差再调整冷机出力、冷冻水、冷却水流量等而实现前馈控制。
本发明利用地铁站的现有资源能够比较容易地确定乘车人员数量、发车情况、温湿度,因此未来时刻关键信息的采集非常简便,还能够降低成本。
优选地,建立地铁建筑负荷与历史信息(数据)和/或实测信息(数据)的模糊关系式,这便于提高建筑负荷预测精度。
优选地,历史信息包括基于时间序列的干球温度、湿球温度、列车发车数量、地铁站内人员数量、地铁站建筑负荷、冷冻水供回水温度、冷冻水流量、冷冻水供回水温差中的至少一者,地铁冷站的历史信息多,且收集方便,能够提高建筑负荷预测精度,并降低收集历史信息的成本。
优选地,实测信息包括环境干球温度、环境湿球温度、列车发车数量、地铁站内实时人员数量中的至少一者。地铁站内实时人员数量可以由门禁系统的人员计数器来进行准确统计,而车辆运行管理系统已规划下一时刻(冷冻水循环一周所需时间)地铁站发车对数,因此,数据采集非常方便。这里,需要说明的是,与通风、太阳辐射、设备、照明、围护结构温差传热等时变性不强的影响因素相比,地铁站内实时人员数量、地铁发车信息、环境温度和环境湿度等数据会随着时间而变化较大。例如,工作日早晚高峰时地铁站内实时人员数量较多、夏季中午时环境温度较高。因此,这些数据在本申请中被简称为强时变性数据。
如图3所示,根据本发明,用于地铁地铁暖通空调系统的负荷预测和控制方法可以包括数据采集与整合处理阶段和预测计算阶段。
数据采集与整合处理阶段可以包括:采集数据并分类存储在基础数据库中不同数据文件夹,即,预先设定冷负荷数据分类形式。
预测计算阶段可以包括如下步骤。
根据用户需求在程序中预设预测间隔时间,并,从预测日的基础数据库中提取近两日d(n-1)、d(n-2)的实测冷负荷Q(t),分别计算近两日实测逐时冷负荷平均值
Figure PCTCN2017082142-appb-000001
(这里,需要说明的是,也可以是近一日或多于近两日的近几日)。
将实时监测到的地铁室内人员数量、室外气温传给负荷预测模型,以计算第一个负荷预测的气温修正系数ζ(1)、室内人员数量修正系数ξ(1)。接着,计算预测日的第一个预测负荷值Q(1)。与此同时,可以将实测冷负荷、气象参数、地铁人员数量存储于相应数据文件夹中一做备用。
根据预先设定的第一个空调时间提前值τ1和冷冻水循环周期τ以及根据预测负荷值,控制器提前(例如提前(τ+τ1))发送开机命令。
在第一个负荷预测时刻结束并获得实测地铁冷站供冷量Q’(1)之后,将实时监测到的地铁室内人员数量、室外气温传给负荷预测模型,由此负荷预测模型计算预测日的第二个预测负荷值Q(2)。与此同时,可以将实测冷负荷、气象参数、地铁人员数量存储于相应数据文件夹中以作后用。
与预测第二个时刻点的方法一样,依次预测后续时刻的冷负荷需求量,直到最后一个空调时刻点预测结束后,冷站控制器发送关机命令,结束一天的负荷预测工作。
优选地,数据文件夹包括工作日数据文件夹、星期六数据文件夹、星期日数据文件夹、假日数据文件夹,其中,每个类型文件夹包含历史气象参数、历史在室人员数量、历史冷负荷数据、历史预测冷负荷数据中的至少一项。
优选地,近两日实测逐时冷负荷平均值分别为:
Figure PCTCN2017082142-appb-000002
两个负荷日的水平因子为:
Figure PCTCN2017082142-appb-000003
两个负荷日的趋势因子为:
Figure PCTCN2017082142-appb-000004
其中,N表示单个负荷日的冷负荷预测点数(例如,N=1、2、3……24);
计算出每个负荷日的周期因子Ct(j-1,i)、Ct(j-2,i),取平均后正态化处理得到Ct(i);
计算第一个预测负荷值的气温修正系数ζ(1)、室内人员数量修正系数ξ (1),预测日的第一个预测负荷值为:
Q(1)=ζ(1)*ξ(1)*Ct(1)*S。
优选地,在第一个负荷预测时刻结束并获得实测地铁冷站供冷量Q’(1)之后,对水平因子S、周期因子分别进行修正,得更新后的St(i)、Ct(i);
基于实时监测到的地铁室内人员数量、室外气温,计算第二个预测负荷值的气温修正系数ζ、室内人员数量修正系数ξ,预测日的第二个预测负荷值为:
Q(2)=ζ*ξ*Ct(2)*St(2)。
优选地,数据采集与整合处理阶段包括:
数据采集阶段,包括气象数据采集、地铁门禁系统数据采集、中央空调系统数据采集和管理信息采集;
数据预处理阶段,包括实施数据预处理和管理信息预处理;
数据存储(提取)阶段,选择预测模式后,将供冷量、冷量预测值、人员在室率、室外干球温度、湿球温度存储到负荷预测模型。
在如图4所示的用于地铁暖通空调系统的负荷预测和控制方法的另一实施例中,包括如下步骤:
选择预测模式,启动计算;
N=1时,调取最近两个同类型负荷日基于时间序列的负荷实测数据、地铁人员数量、室外干湿球温度数据;
根据调取的两个相似日数据计算得出预测日逐时冷负荷Q;
实时采集中央空调供冷量、气象温度、人数统计,根据当前时刻检测的地铁人员数量、室外干湿球温度条件,与前一相似负荷日同一时刻值进行比较,得出一个当前预测负荷值的修正系数λ,并对上述预测值进行修正,得出预测日第一个空调时刻预测值λ*Q;
负荷预测日数据存储;
N=24,则预测结束;
N≠24,则返回N>1状态,继续运行;
N>1时,调取最近两个同类型负荷日基于时间序列的负荷实测数据、地铁人员数量、室外干湿球温度数据;
根据调取的两个相似日数据计算得出预测日逐时冷负荷Q;
根据上一时刻t(n-1)空调系统供冷量,修正预测值的水平因子St,周期因子Ct;
根据修正预测值的水平因子St,周期因子Ct,得出预测值Q;
实时采集中央空调供冷量、气象温度、人数统计,根据当前的时刻t监测的地铁人员数量、室外干湿球温度条件,与前一相似负荷日同一时刻值进行比较,得出一个当前预测负荷值的修正系数λ,并对上述预测值进行修正,得出预测日第一个空调时刻预测值λ*Q;
负荷预测日数据存储;
N=24,则预测结束;
N≠24,则返回N>1状态,继续运行,依次循环,直至N=24,预测结束。
本发明提供的用于地铁暖通空调系统的负荷预测和控制系统及方法,利用地铁冷站已有数据信息,而无需额外较大投资即可获得影响地铁冷站未来时刻的建筑负荷的实测(预见)信息,应用改进的季节指数平滑法计算下一时刻(冷冻水循环一周所需时间)地铁站建筑负荷,并发出指令控制冷机、冷冻水泵、冷却水泵、冷却塔、电动蝶阀,进而实现对地铁站精确的空气调节。
本发明提供的用于地铁暖通空调系统的负荷预测和控制系统及方法能够解决传统负荷预测精度差,空调系统控制欠理想等问题,还具有节省初投资,应用难度小、运行可靠,改善暖通空调系统节能效果,减少数据库存储数据,负荷预测模型简单,实用性强等优点。
以上所述仅为本发明的优选实施例,并不用于限制本发明,对于本领域技术人员而言,本发明可以有各种改动和变化。凡在本发明的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。

Claims (17)

  1. 一种用于地铁暖通空调系统的负荷预测和控制系统,其特征在于:
    所述负荷预测和控制系统包括基础数据库、感测系统、负荷预测部和控制器,所述基础数据库存储有与所述地铁暖通空调系统相关的历史数据,所述感测系统提供与所述地铁暖通空调系统相关的实测数据,所述负荷预测部基于所述历史数据和所述实测数据而计算出所述地铁暖通空调系统的预测负荷值并且将所述预测负荷值传输至所述控制部,所述控制器基于所述预测负荷值发出控制指令以控制所述地铁暖通空调系统的运行,以及
    所述历史数据和所述实测数据包括强时变性数据。
  2. 根据权利要求1所述的负荷预测和控制系统,其特征在于,所述强时变性数据包括地铁站内实时人员数量、地铁发车信息、环境温度和环境湿度中的至少一者。
  3. 根据权利要求1所述的负荷预测和控制系统,其特征在于,所述基础数据库剔除包括地铁站通风、地铁站设备、地铁站照明和/或地铁站围护结构温差传热在内的弱时变性数据,以便简化所述基础数据库。
  4. 根据权利要求2所述的负荷预测和控制系统,其特征在于:
    所述地铁暖通空调系统实施为地铁冷站,以及
    所述历史数据和/或所述实测数据还包括负荷量、预测负荷量、冷冻水供水温度、冷冻水回水温度和/或冷冻水流量。
  5. 根据权利要求2所述的负荷预测和控制系统,其特征在于,所述感测系统包括用于提供所述地铁站内实时人员数量的门禁人员数量采集装置。
  6. 根据权利要求2所述的负荷预测和控制系统,其特征在于,所述感测系统包括发车信息检测装置,所述发车信息检测装置与车辆运行管理系统通信 以获取当前地铁发车信息和/或未来地铁发车信息。
  7. 根据权利要求1所述的负荷预测和控制系统,其特征在于,所述基础数据库中的所述历史数据为基于时间序列的逐时数据,以及,所述负荷预测部通过指数平滑法进行负荷预测。
  8. 根据权利要求1所述的负荷预测和控制系统,其特征在于:
    所述地铁暖通空调系统还包括多个数据预处理模块,所述感测系统的感测数据根据数据特性被分类为与所述多个数据预处理模块中的相应数据预处理模块相关联,以及
    所述感测数据在经过所述数据预处理模块进行预处理之后被传输至所述控制器并且/或者被分类地存储在所述基础数据库中。
  9. 根据权利要求1所述的负荷预测和控制系统,其特征在于,所述感测系统的感测数据被分类地存储在所述基础数据库中的根据季节、日期和/或时刻特性分类的相应数据文件夹中,所述数据文件夹包括工作日数据文件夹、星期六数据文件夹、星期日数据文件夹和/或假日数据文件夹。
  10. 根据权利要求1所述的负荷预测和控制系统,其特征在于,所述感测系统将所述实测数据传输至所述负荷预测部以便进行负荷预测,并且所述感测系统还将所述实测数据传输至所述基础数据库以便存储作为下一负荷预测的历史数据。
  11. 根据权利要求10所述的负荷预测和控制系统,其特征在于,所述感测系统还将所述实测数据传输至所述控制器,使得所述控制器基于所述预测负荷值和所述实测数据发出所述控制指令。
  12. 根据权利要求1所述的负荷预测和控制系统,其特征在于:
    所述地铁暖通空调系统实施为地铁冷站,所述地铁冷站包括下述冷站装置中的至少一者:冷机、冷冻水泵、阀门、冷却水泵和冷却塔,以及
    所述地铁冷站还包括与所述冷站装置对应的执行机构,所述执行机构从所述控制器接收所述控制指令以控制所述冷站装置的运行。
  13. 根据权利要求1至12中任一项所述的负荷预测和控制系统,其特征在于:
    所述地铁暖通空调系统还包括负荷量确定部,所述负荷量确定部基于所述感测系统的感测数据确定实际负荷量,以及
    所述负荷预测部基于所述预测负荷值与从所述负荷量确定部反馈的所述实际负荷量的差修正下一负荷预测的预测负荷值。
  14. 一种用于地铁暖通空调系统的负荷预测和控制方法,其特征在于,所述负荷预测和控制方法通过如权利要求1至13中任一项所述的负荷预测和控制系统来计算所述地铁暖通空调系统的预测负荷值并且基于所述预测负荷值来控制所述地铁暖通空调系统的运行。
  15. 根据权利要求14所述的负荷预测和控制方法,其特征在于,所述负荷预测和控制方法包括如下步骤:
    从所述基础数据库中提取近两日或更多日的负荷量,然后分别计算近两日或更多日的逐时负荷量平均值;
    基于所述逐时负荷量平均值计算近两日或更多日的水平因子;
    基于所述逐时负荷量平均值计算近两日或更多日的趋势因子;
    计算近两日或更多日中每日的周期因子,然后取平均并进行正态化处理而获得正态化周期因子;
    从所述感测系统将实时感测到的地铁站内实时人员数量和环境温度传输至所述负荷预测部,然后所述负荷预测部计算第一个负荷预测的人员数量修正系数和温度修正系数;
    基于所述水平因子、所述正态化周期因子以及所述第一个负荷预测的人员数量修正系数和温度修正系数计算第一个预测负荷值;以及
    将所述第一个预测负荷值传输至所述控制部,然后所述控制器基于所述第一个预测负荷值发出所述控制指令以控制所述地铁暖通空调系统的运行。
  16. 根据权利要求15所述的负荷预测和控制方法,其特征在于,所述负荷预测部计算第一个预测负荷的人员数量修正系数和温度修正系数的步骤包括:将从所述感测系统获得的实时感测到的地铁站内实时人员数量和环境温度与前一日或前几日同一时刻的相应历史数据进行比较而获得所述第一个预测负荷的人员数量修正系数和温度修正系数。
  17. 根据权利要求15或16所述的负荷预测和控制方法,其特征在于,所述负荷预测和控制方法还包括如下步骤:
    在所述第一个负荷预测结束之后,由所述地铁暖通空调系统的负荷量确定部基于所述感测系统的感测数据确定实际负荷量;
    所述负荷预测部基于所述第一个预测负荷值与从所述负荷量确定部反馈的所述实际负荷量的差修正所述水平因子和所述正态化周期因子而获得更新的水平因子和更新的正态化周期因子;
    从所述感测系统将实时感测到的地铁站内实时人员数量和环境温度传输至所述负荷预测部,然后所述负荷预测部计算第二个预测负荷的人员数量修正系数和温度修正系数;以及
    基于所述更新的水平因子、所述更新的正态化周期因子以及所述第二个预测负荷的人员数量修正系数和温度修正系数计算第二个预测负荷值。
PCT/CN2017/082142 2016-09-20 2017-04-27 用于地铁暖通空调系统的负荷预测和控制系统及其方法 WO2018054055A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP17852129.0A EP3483517B1 (en) 2016-09-20 2017-04-27 System and method for predicting load of and controlling subway heating, ventilation, and air conditioning system
US16/280,909 US10983542B2 (en) 2016-09-20 2019-02-20 Load-predicting and control system and method for subway heating, ventilation and air conditioning system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610836083.7 2016-09-20
CN201610836083.7A CN106338127B (zh) 2016-09-20 2016-09-20 用于地铁暖通空调系统的负荷预测和控制系统及其方法

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/280,909 Continuation US10983542B2 (en) 2016-09-20 2019-02-20 Load-predicting and control system and method for subway heating, ventilation and air conditioning system

Publications (1)

Publication Number Publication Date
WO2018054055A1 true WO2018054055A1 (zh) 2018-03-29

Family

ID=57839063

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/082142 WO2018054055A1 (zh) 2016-09-20 2017-04-27 用于地铁暖通空调系统的负荷预测和控制系统及其方法

Country Status (4)

Country Link
US (1) US10983542B2 (zh)
EP (1) EP3483517B1 (zh)
CN (1) CN106338127B (zh)
WO (1) WO2018054055A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110017560A (zh) * 2019-03-26 2019-07-16 中铁第一勘察设计院集团有限公司 严寒地区地铁区间废热利用系统及其运行方法
CN113991660A (zh) * 2021-11-09 2022-01-28 上海申通地铁集团有限公司 地铁供电系统的动力照明负荷建模方法
CN110017560B (zh) * 2019-03-26 2024-06-07 中铁第一勘察设计院集团有限公司 严寒地区地铁区间废热利用系统及其运行方法

Families Citing this family (43)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106338127B (zh) * 2016-09-20 2018-06-22 珠海格力电器股份有限公司 用于地铁暖通空调系统的负荷预测和控制系统及其方法
CN106895564A (zh) * 2017-03-27 2017-06-27 中国科学院广州能源研究所 一种车站通风空调控制系统及方法
CN109130767B (zh) * 2017-06-28 2020-08-11 北京交通大学 基于客流的轨道交通车站通风空调系统的智能控制方法
CN107401816B (zh) * 2017-08-07 2019-07-09 珠海格力电器股份有限公司 空调系统能耗的确定方法和装置
CN107797581B (zh) * 2017-09-04 2021-01-26 任升莲 一种暖通大数据节能系统
CN107702292B (zh) * 2017-11-08 2020-05-01 四川虹美智能科技有限公司 一种确定多联机空调动态制冷量的方法及室外主机
US10760804B2 (en) 2017-11-21 2020-09-01 Emerson Climate Technologies, Inc. Humidifier control systems and methods
CN108626844A (zh) * 2018-04-18 2018-10-09 芜湖乐锐思信息咨询有限公司 基于大数据技术的暖通空调系统的使用方法
US11421901B2 (en) 2018-04-20 2022-08-23 Emerson Climate Technologies, Inc. Coordinated control of standalone and building indoor air quality devices and systems
US11486593B2 (en) 2018-04-20 2022-11-01 Emerson Climate Technologies, Inc. Systems and methods with variable mitigation thresholds
US11994313B2 (en) 2018-04-20 2024-05-28 Copeland Lp Indoor air quality sensor calibration systems and methods
WO2019204779A1 (en) 2018-04-20 2019-10-24 Emerson Climate Technologies, Inc. Indoor air quality and occupant monitoring systems and methods
EP3781879A4 (en) 2018-04-20 2022-01-19 Emerson Climate Technologies, Inc. SYSTEMS AND METHODS WITH VARIABLE ATTENUATION THRESHOLDS
CN108644980B (zh) * 2018-05-03 2021-01-29 广东工业大学 地铁车站通风空调系统的功耗计算方法、系统及存储介质
CN108759011A (zh) * 2018-06-22 2018-11-06 沈阳建筑大学 一种用于暖通空调系统的控制装置及其方法
CN109028278B (zh) * 2018-07-17 2020-07-31 哈尔滨工业大学 一种风电供暖的区域运行系统及调度策略
CN108870668A (zh) * 2018-08-10 2018-11-23 北京华誉能源技术股份有限公司 一种基于参考日模式的智慧能源管理系统及管理方法
CN109409604B (zh) * 2018-10-30 2022-03-18 北京石油化工学院 一种基于遗传算法-支持向量机的冷负荷预测方法
CN109654665B (zh) * 2018-12-14 2021-01-29 广东美的暖通设备有限公司 空调器的控制方法及装置和空调器
CN111380184A (zh) * 2018-12-28 2020-07-07 麦克维尔空调制冷(武汉)有限公司 压缩机运行控制方法、控制装置和换热系统
CN109829635A (zh) * 2019-01-21 2019-05-31 上海理工大学 基于运营年限负荷演化特征的冷源设备容量动态匹配方法
CN109917646B (zh) * 2019-02-27 2022-04-01 武汉中电节能有限公司 一种区域供冷供热设备优化运行系统及方法
CN110135075A (zh) * 2019-05-17 2019-08-16 中铁二院北方勘察设计有限责任公司 一种地铁环控系统的动态设计方法
CN110186156A (zh) * 2019-06-03 2019-08-30 西安锦威电子科技有限公司 制冷站模糊控制系统
CN110288164B (zh) * 2019-07-02 2022-12-02 广州市特沃能源管理有限公司 一种建筑空调制冷站系统预测控制方法
CN110395286B (zh) * 2019-08-02 2020-08-07 中南大学 一种列车车内空气品质监测与通风调控方法、系统
CN112747413B (zh) * 2019-10-31 2022-06-21 北京国双科技有限公司 空调系统负荷预测方法及装置
CN111023532B (zh) * 2019-12-31 2020-11-27 中维通(北京)科技有限公司 一种地铁通风空调智能调节的方法
CN111582591B (zh) * 2020-05-12 2022-06-07 江苏方天电力技术有限公司 一种面向综合能源系统的冷热电多元负荷预测方法
CN111612112A (zh) * 2020-05-26 2020-09-01 八维通科技有限公司 一种基于数字孪生地铁台站门的识别方法和系统
CN111695733B (zh) * 2020-06-11 2022-09-09 国网天津市电力公司 一种基于改进模糊聚类算法的“煤改电”负荷预测方法
CN112348694A (zh) * 2020-09-16 2021-02-09 贵州电网有限责任公司 一种基于改进季节性指数平滑模型的风力发电量预测方法
CN112254320B (zh) * 2020-10-22 2021-08-24 重庆大学 基于ai的空调变流量水系统自适应变压差控制方法
CN112379648B (zh) * 2020-11-17 2022-06-03 青岛北冰洋冷暖能源科技有限公司 一种冷站控制系统中判断是否增减机组的控制方法
CN113375304B (zh) * 2021-06-01 2022-07-26 深圳地铁建设集团有限公司 一种地铁站空调系统预调节方法
CN113551375B (zh) * 2021-07-23 2022-09-06 贵州汇通华城股份有限公司 一种用于电子工厂的冷负荷预测方法及系统
US11739967B1 (en) * 2021-12-21 2023-08-29 Kentuckiana Curb Company, Inc. System and method for evaluating air conditioner performance at part-load conditions
CN114462171B (zh) * 2022-01-05 2024-05-24 浙江力德节能科技有限公司 一种中央空调需求侧供回水温差预测值的计算方法
CN114459132B (zh) * 2022-01-05 2024-04-12 洛阳市轨道交通集团有限责任公司 基于发车对数的分档调节地铁大系统空调控制方法及系统
CN115454178B (zh) * 2022-09-19 2023-11-24 苏州大学 无线动态负荷预测的地铁站台温湿度控制系统
CN115930373B (zh) * 2023-01-10 2023-07-04 灵汇技术股份有限公司 一种基于负荷预测的地铁空调节能控制方法及系统
CN115962551B (zh) * 2023-03-16 2023-05-26 深圳市森辉智能自控技术有限公司 用于楼宇自动控制的智能空调控制系统和方法
CN116894528B (zh) * 2023-09-11 2023-11-21 中瑞恒(北京)科技有限公司 一种冷热站负荷预测方法、装置和计算机设备

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040255601A1 (en) * 2003-06-19 2004-12-23 Lg Electronics Inc. Central control system of air conditioners and method for operating the same
CN101021914A (zh) * 2006-03-22 2007-08-22 侯春海 暖通空调负荷预测方法和系统
CN101251291A (zh) * 2008-04-03 2008-08-27 上海交通大学 基于模型的集中空调系统全局优化节能控制方法及装置
CN102779228A (zh) * 2012-06-07 2012-11-14 华南理工大学 商场建筑中央空调冷负荷在线预测方法及系统
CN102980272A (zh) * 2012-12-08 2013-03-20 珠海派诺科技股份有限公司 一种基于负荷预测的空调系统节能优化方法
CN106338127A (zh) * 2016-09-20 2017-01-18 珠海格力电器股份有限公司 用于地铁暖通空调系统的负荷预测和控制系统及其方法

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2765630B2 (ja) * 1996-05-23 1998-06-18 東京都地下鉄建設株式会社 地下空間における空気調和・換気シミュレータ
JP3622657B2 (ja) * 2000-09-18 2005-02-23 株式会社日立製作所 空調制御システム
JP4187688B2 (ja) * 2003-06-23 2008-11-26 株式会社創発システム研究所 列車風による自然換気を利用した空調制御システム
CN200953100Y (zh) * 2006-08-29 2007-09-26 深圳市地铁有限公司 带有负反馈的地铁空调控制系统
US8892277B2 (en) * 2009-07-22 2014-11-18 Mitsubishi Electric Corporation Vehicle air-conditioning control method
CN102705957B (zh) * 2012-06-07 2014-06-11 华南理工大学 办公建筑中央空调逐时冷负荷在线预测方法及系统
JPWO2014002137A1 (ja) * 2012-06-27 2016-05-26 三菱電機株式会社 鉄道車両用全熱交換換気システム
US9533550B2 (en) * 2013-01-17 2017-01-03 Mitsubishi Electric Corporation Vehicle air conditioning control device
JP6222649B2 (ja) * 2013-04-10 2017-11-01 東日本旅客鉄道株式会社 地下駅空気調和予測装置、及び、プログラム
TWI503780B (zh) * 2013-12-27 2015-10-11 Delta Electronics Inc 契約容量最佳化系統及最佳化方法
CN104075402A (zh) * 2014-06-19 2014-10-01 珠海格力电器股份有限公司 智能空调控制方法和系统
KR102336642B1 (ko) * 2014-08-21 2021-12-07 삼성전자 주식회사 온도 조절 방법 및 장치
US9967107B2 (en) * 2014-12-24 2018-05-08 Optimum Energy Llc Intelligent equipment sequencing
CN105674500B (zh) * 2016-02-22 2018-11-30 珠海格力电器股份有限公司 一种空调控制系统及其控制方法、装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040255601A1 (en) * 2003-06-19 2004-12-23 Lg Electronics Inc. Central control system of air conditioners and method for operating the same
CN101021914A (zh) * 2006-03-22 2007-08-22 侯春海 暖通空调负荷预测方法和系统
CN101251291A (zh) * 2008-04-03 2008-08-27 上海交通大学 基于模型的集中空调系统全局优化节能控制方法及装置
CN102779228A (zh) * 2012-06-07 2012-11-14 华南理工大学 商场建筑中央空调冷负荷在线预测方法及系统
CN102980272A (zh) * 2012-12-08 2013-03-20 珠海派诺科技股份有限公司 一种基于负荷预测的空调系统节能优化方法
CN106338127A (zh) * 2016-09-20 2017-01-18 珠海格力电器股份有限公司 用于地铁暖通空调系统的负荷预测和控制系统及其方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3483517A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110017560A (zh) * 2019-03-26 2019-07-16 中铁第一勘察设计院集团有限公司 严寒地区地铁区间废热利用系统及其运行方法
CN110017560B (zh) * 2019-03-26 2024-06-07 中铁第一勘察设计院集团有限公司 严寒地区地铁区间废热利用系统及其运行方法
CN113991660A (zh) * 2021-11-09 2022-01-28 上海申通地铁集团有限公司 地铁供电系统的动力照明负荷建模方法
CN113991660B (zh) * 2021-11-09 2023-12-05 上海申通地铁集团有限公司 地铁供电系统的动力照明负荷建模方法

Also Published As

Publication number Publication date
EP3483517A4 (en) 2019-10-09
CN106338127A (zh) 2017-01-18
EP3483517B1 (en) 2021-09-01
CN106338127B (zh) 2018-06-22
EP3483517A1 (en) 2019-05-15
US10983542B2 (en) 2021-04-20
US20190178522A1 (en) 2019-06-13

Similar Documents

Publication Publication Date Title
WO2018054055A1 (zh) 用于地铁暖通空调系统的负荷预测和控制系统及其方法
WO2020107851A1 (zh) 基于既有大型公共建筑空调系统的低成本调适方法及调适系统
EP3614055B1 (en) Heat supply regulation method and apparatus
CN110864414B (zh) 基于大数据分析的空调用电负荷智能控制调度方法
JP5518216B2 (ja) クラウドコンピューティングに基づくエネルギー管理制御システム及び方法
KR101077369B1 (ko) 최적화 에너지 메니지먼트 시스템을 이용한 빌딩 공조 제어 방법
CN106979588B (zh) 一种机房空调能耗的节能管理系统及节能管理方法
CN102043907B (zh) 空调房间实时冷负荷确定方法
CN107797581B (zh) 一种暖通大数据节能系统
CN112013521B (zh) 一种基于天气预报的空调系统调节方法和系统
WO2011106914A1 (zh) 基于云计算的设备监控系统及方法
CN102003772A (zh) 一种水源热泵节能优化控制方法
CN103471171A (zh) 一种集中供热质量调节智能控制系统及方法
CN106568172B (zh) 节能温度控制方法、装置及空调遥控系统
CN114154677A (zh) 空调运行负荷模型构建和预测方法、装置、设备和介质
CN107247407B (zh) 一种基于云架构的大数据自我学习修正控制系统及方法
JPH0835706A (ja) 空調熱負荷予測システム
Wang et al. Field test of Model Predictive Control in residential buildings for utility cost savings
CN211526662U (zh) 一种基于负荷预测的地铁车站通风空调节能系统
CN113091122B (zh) 一种补燃型楼宇换热机组的调控方法
CN107631420B (zh) 基于iBeacon技术的医院空调末端变风量系统节能方法及装置
WO2016198745A1 (en) Method for controlling heating in buildings
CN111720954A (zh) 产品的节能方法及节能运算系统
CN112665123B (zh) 建筑负荷预测方法、装置及中央空调
CN104268719B (zh) 一种铁路车站能量管理系统

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: 17852129

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2017852129

Country of ref document: EP

Effective date: 20190211

NENP Non-entry into the national phase

Ref country code: DE