CN108240679B

CN108240679B - A kind of heat supply method based on building heating load prediction, device and system

Info

Publication number: CN108240679B
Application number: CN201810153898.4A
Authority: CN
Inventors: 丁爱军; 王福林
Original assignee: Yantai Kechuang Jieneng Electromechanical Engineering Co Ltd
Current assignee: Yantai Kechuang Jieneng Electromechanical Engineering Co Ltd
Priority date: 2018-02-22
Filing date: 2018-02-22
Publication date: 2019-07-02
Anticipated expiration: 2038-02-22
Also published as: CN108240679A

Abstract

The present invention provides a kind of heat supply methods based on building heating load prediction, device and system, this method comprises: based on get target heating user's architectural exterior-protecting construction situation, it is adjacent between the room temperature that needs of heat transfer conditions, instant out door climatic parameter and user predict dynamic space heating load；The practical heating load data detected based on dynamic space heating load and heat meter generate the control signal controlled target valve, controlling carrying opening information and/or make-and-break time information, target valve in signal is the valve controlled the heating water flow of target heating user；Control signal is sent to target valve, so that target valve executes corresponding movement according to control signal.The present invention solves the problems, such as the technical issues of existing room temperature thermometric erection of equipment position difference causes thermometric offset issue and user that can realize heating according to need to different user difference room temperature demand to temperature measuring equipment interference and heat supply company.

Description

A kind of heat supply method based on building heating load prediction, device and system

Technical field

The present invention relates to building heating and control technology fields, pre- based on building heating dynamic load more particularly, to one kind The heat supply method of survey, device and system.

Background technique

The heating system in China causes cold and hot distribution not substantially without automatic control device at the heat user of end at present , phenomena such as some users wear cotta indoors, open a window, and some users wear cotton dress indoors.Such case not only user Comfort level, satisfaction it is poor, and be unfavorable for the health of user, also result in the waste of the heating energy.External heating System is mounted on the heating water pipe of every group of radiator and can control the autocontrol valve that valve opening is come outside regulation room, But due to higher cost, use energy behavior high to heating water quality requirement, user etc., it can not temporarily popularize and answer in China With.Many researchers attempt to solve the problems, such as this, for example, patent " public building energy heating control device " discloses one kind The heating control system being made of control valve, detector and controller, and the switch based on ambient parameter information control control valve State controls the heating-amount of target heat exchange station, and as can be seen from the above description, existing power supply technique has non-with heat supply user Often close connection.Patent " heating control system " discloses a kind of heating control being made of water storage unit and rooms unit System processed only provides bath hot water for water heater and designs without having heating function, in the water storage box of original water heater It installs a series of devices additional, shower can be realized and can realize the functions such as heating.Patent " a kind of collection real-time monitoring and facilitates maintenance Heating control system " a kind of heating control system for collecting real-time monitoring and facilitating maintenance is developed, pass through the automatic heat pump of controller Power supply and power-off control indoor temperature, and can prevent that heat pump crosses heat-induced damage or room temperature is excessively high.Patent " one Kind of central heating control system and method " a kind of heating control system is disclosed, it can be realized that user is adjustable, heat supply is controllable, neck Lead can pipe central heating control system, while realizing regulation to heat supply end and user terminal, realize energy conservation to the greatest extent With improve heat supply efficiency, but the patent controls to adjust valve, the different installation positions of temperature measuring point using the method by indoor thermometric Setting, which leads to detect temperature and normal room temperature, relatively large deviation, in addition if caused at room temperature by indoor thermometric to control to adjust valve Drop, many users understand human interference temperature measuring equipment to make thrashing.It is " temperature area by a kind of mode of charging per heat Method ", in the case where user area is certain, the subscriber payment amount of money is related to the room temperature of requirement, and room temperature is higher, and payment is higher, Unrelated with user position direction etc., this method is seemingly reasonable, but just because of many user's human interference temperature measuring equipments And the program is caused to be difficult to promote.In addition, many cities have carried out pressing in order to save for thermal energy consumption, avoid heat supply energy waste Area charging and double portion's caloric value systems by heat charging.Purpose by heat charging caloric value system is by " with how many heat flowers How much " charging means encourage the heat user correctly with can, avoid wasting, realize heating according to need, behavior energy saving, and force new It builds heating system and is respectively mounted household-based heat metering table, can be charged by heat with realizing every household.However, for various reasons, Although being mounted with a large amount of heat meters, charged by heat almost without being implemented, the project exposure that pilot has been implemented Many problems, it is difficult to balance the interests between heat supply company and heat user, therefore most of heat supply expenses are received still according to area It takes, not only promotes energy-efficient purpose not have by " how much is spent with how many heat " accomplished, but also cause a large amount of calorimeter Idle and investment the waste of resource.

Summary of the invention

In view of this, the purpose of the present invention is to provide it is a kind of based on dynamic building heat load prediction heat supply method, Device and system cause thermometric offset issue and user to fill thermometric to solve existing room temperature thermometric erection of equipment position difference It sets interference problem and heat supply company is able to satisfy the technical issues of realizing heating according to need to different user difference room temperature demand.

In a first aspect, the embodiment of the invention provides a kind of heat supply method based on the prediction of dynamic building heat load, packet It includes: the outdoor weather data prediction dynamic space heating load based on the target heating user's local environment got, wherein described Dynamic space heating load is the heat demand of the target heating user predicted；Based on the dynamic space heating load and heat The actually detected heating load data of gauge table generate the control signal controlled target valve, wherein the control signal Middle carrying opening information and/or make-and-break time information, the target valve are the heating water flow to the target heating user The valve controlled；The control signal is sent to the target valve, so that the target valve is believed according to the control Number execute corresponding movement.

Further, the method also includes: obtain the heating target of the target heating user；Based on the mesh got The outdoor weather data prediction dynamic space heating load of mark heating user local environment includes: to be used based on the target heating got The heating target prediction dynamic space heating load of the outdoor weather data of family local environment and the target heating user.

Further, outdoor weather data and the target heating based on the target heating user's local environment got The heating target prediction dynamic space heating load of user includes: to transfer target nerve network, and the target nerve network is preparatory The neural network that training is completed；Using the outdoor weather data and the heating target as the defeated of the target nerve network Enter, so that the target nerve network handles the outdoor weather data and the heating target, and exports described dynamic State space heating load.

Further, the target nerve network is expressed as following formula:

Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., m, m are described The node in hidden layer of target nerve network；x_iFor the neuron node value of i-th of input layer in the target nerve network； y_j,inFor the input value of j-th of hidden layer neuron node in the target nerve network, y_j,outFor the target nerve network In j-th of hidden layer neuron node output valve；w_i,jFor i-th of input layer section in the target nerve network O'clock to j-th of hidden layer neuron node calculating weight；u_jFor j-th of hidden layer neuron section in the target nerve network Point arrives the calculating weight of output layer neuron node；Q_inAnd Q_outIt is the input value and output valve of output layer neuron node respectively, Wherein, the output valve is the dynamic space heating load of prediction.

Further, the control controlled target valve is generated based on the dynamic space heating load and heating load data Signal processed includes: to compare the dynamic space heating load and the heating load data, with the determination dynamic for warm heat Deviation between load and the heating load data；The deviation is carried out by pid algorithm or FUZZY ALGORITHMS FOR CONTROL Processing, to obtain the opening information and the make-and-break time information；Based on the opening information and the make-and-break time information Generate the control signal controlled target valve.

Further, the deviation is handled by pid algorithm, to obtain the opening information and the on-off Temporal information includes: to be handled by the calculation formula of pid algorithm the deviation, to obtain the opening information and institute State make-and-break time information:

Wherein, V is the opening information of the target valve；K is rate mu-factor；Q_pThe dynamic to predict supplies Warm heat load；Q_mThe heating load data measured for calorimeter；T_IFor the time of integration；T_DFor derivative time；τ is the time.

Further, the deviation is handled by FUZZY ALGORITHMS FOR CONTROL, to obtain the opening information and institute Stating make-and-break time information includes: to be handled by the calculation formula of FUZZY ALGORITHMS FOR CONTROL the deviation, described to obtain Opening information and the make-and-break time information:

Wherein, V is the make-and-break time information；K is rate mu-factor；Q_pThe dynamic to predict is born for warm heat Lotus；Q_mThe heating load data measured for calorimeter；τ is the time, and fuzzy is ambiguity function.

Further, before transferring target nerve network, the method also includes: the target nerve network is carried out Training, with the weight coefficient between each neuron node in the determination target nerve network, specifically includes: passing through iteration public affairs Target nerve network described in formula is iterated training, and with the determination weight coefficient, the iterative formula isWherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., M, m are the node in hidden layer of the target nerve network；x_iFor i-th of input layer section in the target nerve network Point value；y_j,outFor the defeated output valve of j-th of hidden layer neuron node in the target nerve network；WithRespectively J-th of hidden layer neuron node to output layer neuron node calculating weight in n-th and the N+1 times repetitive exercise Value；WithIt is meter of i-th of input layer node to j-th of hidden layer neuron node respectively Weight is calculated in the value of n-th and the N+1 times repetitive exercise；η is iteration efficiency factor；δ is the output layer neuron node Partial derivative of the departure function of output valve and desired value to output layer node weights.

Further, the outdoor weather data include at least one of: outdoor temperature change information, and outdoor wind speed becomes Change information, outdoor intensity of solar radiation change information；The heating target is the target heating user purpose to be achieved Temperature.

Further, the method also includes: obtain it is adjacent between Heat Transfer Data, wherein it is described it is adjacent between Heat Transfer Data be described Heat Transfer Data between target heating user heating user adjacent thereto；Based on the target heating user's local environment got Outdoor weather data and the target heating user heating target prediction dynamic space heating load further include: be based on the neighbour Between Heat Transfer Data, dynamic described in the heating target prediction of the outdoor weather data and the target heating user is negative for warm heat Lotus.

Second aspect, the embodiment of the invention provides a kind of heating systems based on building heating load prediction, comprising: the One controller, sensor, calorimeter and target valve, the target valve are the heating water flow to the target heating user The valve controlled；The sensor is used to acquire the outdoor weather data of target heating user's local environment；The heat Table is used to acquire the heating load data of target heating user；First controller is used to predict based on the outdoor weather data Dynamic space heating load, and the control controlled target valve is generated based on the dynamic space heating load and heating load data Signal processed, wherein the dynamic space heating load is the heat demand of the target heating user predicted；The control letter Opening information and/or make-and-break time information are carried in number；The target valve is used to execute according to the control signal corresponding Movement, to adjust the heating water flow of the target heating user.

Further, first controller is also used to obtain the heating target of the target heating user, and is based on institute State outdoor weather data and the heating target prediction dynamic space heating load.

Further, the target nerve network that training is completed in advance is embedded in the control chip of first controller； Wherein, the target nerve network is used to be based on the outdoor weather data and the heating target prediction dynamic space heating load Predict dynamic space heating load.

Further, the heating system further include: second controller, wherein the second controller is mounted on and institute The controller in target heating user's neighboring user is stated, the second controller and first controller communicate to connect；It is described Second controller is used to transmit adjacent heating user heating load to first controller, is based on adjacent heating user heat supply meter Calculate it is adjacent between Heat Transfer Data so that first controller be based on it is described it is adjacent between Heat Transfer Data, outdoor weather data and described Dynamic space heating load described in the heating target prediction of target heating user, wherein Heat Transfer Data is the target between the neighbour Heat Transfer Data between heating user heating user adjacent thereto.

Further, fuzzy controller or PID controller are embedded in the control chip of first controller；It is described Fuzzy controller or the PID controller are used to generate based on the dynamic space heating load and heating load data to target valve The control signal that door is controlled.

Further, the sensor includes: temperature sensor, air velocity transducer, intensity of solar radiation sensor, In: the temperature sensor is used to acquire the outdoor temperature change information of target heating user's local environment；The wind speed Sensor is used to acquire the outdoor wind speed change information of target heating user's local environment；The intensity of solar radiation sensing Device is used to acquire the outdoor intensity of solar radiation change information of target heating user's local environment.

Further, first controller by wired or wireless connection type respectively with the sensor, institute Calorimeter is stated to be connected with the target valve.

Further, when the connection type be wired connection mode when, first controller by M-Bus bus with The calorimeter is connected；First controller is connected by 485 buses with the sensor, alternatively, passing through analog quantity Signal wire is connected with the sensor, and first controller is connected by 485 buses with the target valve, alternatively, It is connected by analog signals line with the target valve.

Further, when the connection type is radio connection, first controller passes through following at least one Kind mode is connected with the sensor, the calorimeter and the target valve respectively: GPRS, 3G network, 4G network, 5G net Network, WIFI network are connected with internet.

Further, the calorimeter is respectively used to detect the temperature of return pipe and water supplying pipe in the heating system, water Flow successively obtains return water temperature, supply water temperature and water flow, wherein the return water temperature, the supply water temperature and the water Flow is for determining the heating load data.

Further, the target valve includes following any: the electrically operated valve that aperture can continuously adjust, Neng Goulian The continuous electromagnetic valve for carrying out on-off control, can be carried out continuously the electric heating valve of on-off control, by mechanical device drive from Power formula control valve.

The third aspect, the embodiment of the invention provides a kind of heating plants based on building load prediction, comprising: prediction is single Member predicts dynamic space heating load for the outdoor weather data based on the target heating user's local environment got, wherein The dynamic space heating load is the heat demand of the target heating user predicted；Generation unit, for based on described Dynamic space heating load and heating load data generate the control signal controlled target valve, wherein the control signal Middle carrying opening information and/or make-and-break time information, the target valve are the heating water flow to the target heating user The valve controlled；Transmission unit, for sending the control signal to the target valve, so that the target valve is pressed Corresponding movement is executed according to the control signal.

Further, described device further include: acquiring unit, for obtaining the heating target of the target heating user； Predicting unit is used for: outdoor weather data and the target heating user based on the target heating user's local environment got Heating target prediction dynamic space heating load.

Further, the predicting unit is also used to: transferring target nerve network, the target nerve network is to instruct in advance Practice the neural network completed；Using the outdoor weather data and the heating target as the input of the target nerve network, So that the target nerve network handles the outdoor weather data and the heating target, and exports the dynamic and supply Warm heat load.

Further, the network structure for the target nerve network being arranged in the heating plant is expressed as following public affairs Formula:Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., M, m are the node in hidden layer of the target nerve network；x_iFor the neuron of i-th of input layer in the target nerve network Nodal value；y_j,inFor the input value of j-th of hidden layer neuron node in the target nerve network, y_j,outFor the target mind Output valve through j-th of hidden layer neuron node in network；w_i,jFor i-th of input layer mind in the target nerve network Through first node to the calculating weight of j-th of hidden layer neuron node；u_jFor j-th of hidden layer mind in the target nerve network Calculating weight through first node to output layer neuron node；Q_inAnd Q_outBe respectively output layer neuron node input value and Output valve, wherein the output valve is the dynamic space heating load of prediction.

Further, generation unit is used for: the dynamic space heating load and the heating load data are compared, with Determine the deviation between the dynamic space heating load and the heating load data；It is calculated by pid algorithm or fuzzy control Method handles the deviation, to obtain the opening information and the make-and-break time information；Based on the opening information The control signal controlled target valve is generated with the make-and-break time information.

Further, generation unit is also used to: the deviation is handled by the calculation formula of pid algorithm, with Obtain the opening information and the make-and-break time information:

Wherein, V is the target valve Opening information；K is rate mu-factor；Q_pFor the dynamic space heating load predicted；Q_mThe confession measured for calorimeter Thermal data；T_IFor the time of integration；T_DFor derivative time；τ is the time.

Further, generation unit is also used to: by the calculation formula of FUZZY ALGORITHMS FOR CONTROL to the deviation at Reason, to obtain the opening information and the make-and-break time information:

Wherein, V is the make-and-break time information；Q_pFor the institute predicted State dynamic space heating load；Q_mThe heating load data measured for calorimeter；τ is the time, and fuzzy is ambiguity function.

Further, which is also used to: before transferring target nerve network, instructing to the target nerve network Practice, with the weight coefficient between each neuron node in the determination target nerve network, specifically includes: passing through iterative formula The target nerve network is iterated training, and with the determination weight coefficient, the iterative formula isWherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., M, m are the node in hidden layer of the target nerve network；x_iFor i-th of input layer section in the target nerve network Point value；y_j,outFor the defeated output valve of j-th of hidden layer neuron node in the target nerve network；WithRespectively J-th of hidden layer neuron node to output layer neuron node calculating weight in n-th and the N+1 times repetitive exercise Value；WithIt is meter of i-th of input layer node to j-th of hidden layer neuron node respectively Weight is calculated in the value of n-th and the N+1 times repetitive exercise；η is iteration efficiency factor；δ is the output layer neuron node Partial derivative of the departure function of output valve and desired value to output layer node weights.

Fourth aspect, the embodiment of the invention provides a kind of meters of non-volatile program code that can be performed with processor Calculation machine readable medium, said program code make the processor execute method described above.

In embodiments of the present invention, firstly, the outdoor weather data based on the target heating user's local environment got Predict dynamic space heating load, wherein the dynamic space heating load is that the heat supply of the target heating user predicted needs It asks；Then, the control signal controlled target valve is generated based on the dynamic space heating load and heating load data, In, opening information and/or make-and-break time information are carried in the control signal, the target valve is to use the target heating The valve that the heating water flow at family is controlled；Finally, the control signal is sent to the target valve, so that the target Valve executes corresponding movement according to the control signal.In embodiments of the present invention, pass through the survey of load prediction and calorimeter The accurate heat supply on demand of point family may be implemented in amount data, meets the different room temperature demands of different heat supply users, can also avoid being subcooled The problem of overheat, to avoid heat supply energy waste, and then solves existing room temperature thermometric erection of equipment to improve comfort level Position difference causes thermometric offset issue and user to be able to satisfy to different user temperature measuring equipment interference problem and heat supply company Different room temperature demands realize the technical issues of heating according to need.

Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims And specifically noted structure is achieved and obtained in attached drawing.

To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate Appended attached drawing, is described in detail below.

Detailed description of the invention

It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor It puts, is also possible to obtain other drawings based on these drawings.

Fig. 1 is a kind of schematic diagram of heating system based on building heating load prediction according to an embodiment of the present invention；

Fig. 2 is the schematic diagram of another heating system based on building heating load prediction according to an embodiment of the present invention；

Fig. 3 is a kind of flow chart of heat supply method based on building heating load prediction according to an embodiment of the present invention；

A kind of Fig. 4 structural schematic diagram of neural network according to an embodiment of the present invention；

Fig. 5 is a kind of schematic diagram of heating plant based on building heating load prediction according to an embodiment of the present invention.

Specific embodiment

In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise Under every other embodiment obtained, shall fall within the protection scope of the present invention.

Embodiment one:

According to embodiments of the present invention, a kind of embodiment of heating system based on building heating load prediction is provided.

Fig. 1 is a kind of schematic diagram of heating system based on building load prediction according to an embodiment of the present invention, such as Fig. 1 institute Show, which includes: the first controller 100, sensor 200, calorimeter 300 and target valve 400, the target valve 400 The valve controlled for the heating water flow to the target heating user.

Specifically, the sensor is used to acquire the outdoor weather data of target heating user's local environment；

The calorimeter is used to acquire the heating load data of target heating user；

In the present embodiment, if being already installed with calorimeter in existing heating system, it can establish the heat Communication connection between table and the first controller, to read the thermal data that the calorimeter detects.If in existing confession It is fitted without calorimeter in hot systems, then calorimeter can be separately provided in existing heating system, and establish the calorimeter With the communication connection between the first controller, to read the thermal data that the calorimeter detects.

First controller is used to predict dynamic space heating load based on the outdoor weather data, and based on described dynamic State space heating load and heating load data generate the control signal controlled target valve, wherein the dynamic is for warm heat Load is the heat demand of the target heating user predicted；Opening information and/or on-off are carried in the control signal Temporal information (for example, make-and-break time ratio)；

The target valve is used to execute corresponding movement according to the control signal, to adjust the target heating user Heating water flow.

Specifically, in embodiments of the present invention, controller is properly termed as heating intelligent controller again, and target valve again can be with Referred to as heat water control valve, and sensor is properly termed as outdoor weather data pick-up again.Wherein, controller can be cloud service Center (alternatively, master system) replaces；Controller can also be and cloud service center (alternatively, master system) communication link The controller connect at this point, controller can upload local data to cloud service center (alternatively, master system), or receives Data or instruction from cloud service center (alternatively, master system).

Brain of the controller 100 as heating system, the room measured for reading sensor 200 (outdoor weather sensor) Outer meteorological data, and dynamic space heating load is predicted by intelligent algorithm；Controller 100 is also used to read calorimeter 300 The heating load data measured, to be generated according to heating load data and dynamic space heating load for the opening information to target valve Or the signal that on-off is controlled.

The execution node that target valve 400 is adjusted as heating load adjusts heating load by changing heating water flow.Tool Body, target valve 400 for example receives the control signal (for example, voltage control signal) exported from controller 100, by valve Adjust the corresponding aperture of the ratio between voltage value and full gate voltage value.

Sensor 200, as the sensing node of heating system, for measuring one or more outdoor weather data, including But it is not limited to: gas epidemic disaster, intensity of solar radiation, wind speed, air pressure.Specifically, sensor 200 can be by wire communication side Outside air temperature measured value is sent to controller 100 by formula.

Heating field main target is to solve the consistent of room temperature between each user solving to balance heat supply at present Property, which is unable to satisfy user to the individual demand of room temperature.In embodiments of the present invention, which uses The concept of Dynamic Load Forecasting can accurately predict workload demand to indoor different demands according to different user, and by heat It is detected as sensor and compares thermic load, to realize accurate control.

It, can device for installing and adjusting, heating user can be in the interior of heating user in traditional temperature control mode Indoor temperature is manually adjusted by the regulating device.But in embodiments of the present invention, it is adjusted manually without user Temperature by the controller can be realized as that the room temperature of heating user is adjusted automatically.

In an alternative embodiment, heating user can preset desired heat supply temperature, that is, for thermal target.

At this point, above-mentioned first controller can obtain the heating target of the target heating user, and it is based on the room Outer meteorological data and the heating target prediction dynamic space heating load.

Optionally, if first controller is cloud service center, which is that target heating user is preparatory It sets, and is stored in cloud service center.If first controller is to be mounted on the controller of hotlist well, at this point, can With in the acquisition device of the indoor location one heating target of target heating user, the acquisition device and controller are communicated to connect. It should be noted that target heating user can depending on the temperature demand the acquisition device adjust heating target.For example, In three nine-day periods after the winter solstice weather, after outdoor weather data and heating target prediction dynamic space heating load, by this dynamically for warm heat The temperature that load carries out after heat supply target heating user is not ideal temperature.At this point, target heating user can be at this Interior adjusts heating target by the acquisition device, at this point, acquisition device is by the heating object transmission to controller, so that control Device predicts dynamic space heating load according to the heating target newly got again, to realize more accurate temperature control, thus The energy can more be saved.For example, temperature is when being heated by the dynamic space heating load predicted to target heating user 20 degree, but in fact, temperature required for target heating user is 18 degree, at this point, target heating user can be adopted by this Acquisition means reduce heating target, and are transmitted in controller, so that controller is based on the heating target and carries out prediction dynamic again Space heating load.By aforesaid operations, energy can be further saved during meeting user individual heating demand Source.

It should be noted that in embodiments of the present invention, being input to target nerve net using heating target as input data When being predicted in network, it can be realized the personalized heating demands of different user.That is, the different user of heating target it Between dynamic space heating load be different.

In embodiments of the present invention, controller or cloud service center can be according to outdoor outdoor weather data and heating mesh Mark predicts dynamic space heating load, and the operation Jing Guo control algolithm, the aperture or on-off of output heating Water flow control valve The control signal of time ratio.

Optionally, the target nerve network that training is completed in advance is embedded in the control chip of first controller；Its In, the target nerve network is used for pre- based on the outdoor weather data and the heating target prediction dynamic space heating load Survey dynamic space heating load.

As shown in Figure 1, in embodiments of the present invention, heating system further include: second controller 500, wherein described second Controller 500 is mounted on and the controller in target heating user's neighboring user, the second controller and described first Controller communication connection.

In an alternative embodiment, the second controller is used to transmit adjacent heating to first controller and use The heating load at family, based on Heat Transfer Data between adjacent heating user heating load calculating neighbour, so that first controller is based on described Dynamic described in the heating target prediction of Heat Transfer Data between neighbour, the outdoor weather data and the target heating user is negative for warm heat Lotus, wherein Heat Transfer Data is the Heat Transfer Data between target heating user heating user adjacent thereto between the neighbour.

In an alternative embodiment, be embedded in the control chip of first controller fuzzy controller or PID controller.

Wherein, the fuzzy controller or the PID controller are used to be based on the dynamic space heating load and heat supply Amount data generate the control signal controlled target valve.

It should be noted that controller uses the intelligent algorithms such as proportional integral differential (PID) controller, fuzzy controller, According to the heating load data that the dynamic space heating load and calorimeter of prediction measure, the opening information of required target valve is calculated Or make-and-break time information (for example, make-and-break time ratio).

In an alternative embodiment, the sensor includes: temperature sensor, air velocity transducer, and solar radiation is strong Spend sensor.

The temperature sensor is used to acquire the outdoor temperature change information of target heating user's local environment；

The air velocity transducer is used to acquire the outdoor wind speed change information of target heating user's local environment；

The intensity of solar radiation sensor is used to acquire the outdoor solar radiation of target heating user's local environment Strength Changes information.

In embodiments of the present invention, temperature sensor, air velocity transducer and intensity of solar radiation sensor are to be mounted on Outdoor sensor, to detect the outdoor temperature change information of target heating user's local environment, ring locating for target heating user The outdoor wind speed change information in border, the environment weathers such as outdoor intensity of solar radiation change information of target heating user's local environment Information.

It should be noted that in embodiments of the present invention, selected sensor is outdoor sensor, with sensing chamber outside Environment temperature, rather than be that can be avoided interior sensor measurement error, artificial damage etc. to lead with the reason of indoor sensor The control deviation of cause, and the cost of investment and operation maintenance cost of sensor can be exempted.

In an alternative embodiment, the sensor of outdoor weather data is non-required, and outdoor weather data may be used also To be obtained from cloud service center (master system).

In embodiments of the present invention, as shown in Fig. 2, intelligent heating controller (that is, first controller) can be set in heat In table well, which may be replaced by cloud service center (or host computer).In heat Calorimeter in table well is by the water temperature sensor and flowmeter that are arranged in return pipe, the water temperature sensor structure being arranged in water supplying pipe At.The calorimeter is connected with the water temperature sensor and flowmeter being arranged on return pipe respectively, to acquire the temperature of return pipe, obtains To return water temperature, and acquire the flow information of the flowmeter.The calorimeter is also connected with the water temperature sensor on water supplying pipe It connects, with the temperature of water supplying pipe, obtains supply water temperature.As shown in Fig. 2, target valve (that is, heating water control valve in Fig. 2) It is arranged on water supplying pipe.As shown in Fig. 2, sensor (that is, outdoor weather data pick-up) is arranged in target heating user institute In the outdoor environment at place, with meteorological data outside collection room.

First controller by wired or wireless connection type respectively with the sensor, the calorimeter and described Target valve is connected.

Wherein, when the connection type is wired connection mode, as shown in Fig. 2, first controller passes through M-Bus Bus is connected with the calorimeter；First controller is by 485 buses, alternatively, analog signals line and the sensing Device is connected, and first controller is by 485 buses, alternatively, analog signals line and the target valve are (that is, heating water Control valve) it is connected.

When the connection type is radio connection, first controller is (that is, cloud service center or upper Machine) it is connected respectively with the sensor, the calorimeter and the target valve by way of following at least one: GPRS, 3G network, 4G network, 5G network, WIFI network are connected with internet.

In embodiments of the present invention, the target valve includes following any: the motor-driven valve that aperture can continuously adjust Door can be carried out continuously the electromagnetic valve of on-off control, can be carried out continuously the electric heating valve of on-off control, pass through mechanical device The self force type control valve door of driving.

As can be seen from the above description, in embodiments of the present invention, the heating system is by the first controller (that is, intelligent heating Controller), target valve (that is, heating water control valve), sensor constitute, pass through meteorological data prediction dynamic outside measuring chamber and supply Warm heat load, by reading heating load data that existing calorimeter measures and compared with predict thermic load, adjust and supply user's The size of heat reaches the target of prediction thermic load, realizes the utilization to calorimeter slack resources, meets different Indoor Temperatures The demand of degree avoids supercooling overheat, improves thermal comfort level, avoiding the waste for heat energy.

Embodiment two:

According to embodiments of the present invention, a kind of embodiment of heat supply method based on building load prediction is provided, is needed Bright, step shown in the flowchart of the accompanying drawings can be held in a computer system such as a set of computer executable instructions Row, although also, logical order is shown in flow charts, and it in some cases, can be to be different from sequence herein Execute shown or described step.

Fig. 3 is a kind of flow chart of heat supply method based on building heating load prediction according to an embodiment of the present invention, such as Shown in Fig. 3, this method comprises the following steps:

Step S302, the outdoor weather data prediction dynamic based on the target heating user's local environment got is for warm heat Load, wherein the dynamic space heating load is the heat demand of the target heating user predicted；

The outdoor weather data include at least one of: outdoor temperature change information, outdoor wind speed change information, room Outer intensity of solar radiation change information；The heating target is target heating user purpose temperature to be achieved.

Step S304 is generated based on the actually detected heating load data of the dynamic space heating load and heat meter to mesh The control signal that mark valve is controlled, wherein opening information and/or make-and-break time information, institute are carried in the control signal Stating target valve is the valve controlled the heating water flow of the target heating user；

Step S306, Xiang Suoshu target valve sends the control signal, so that the target valve is according to the control Signal executes corresponding movement.

In embodiments of the present invention, above-mentioned steps S302 to step S306 can through the foregoing embodiment in controller (alternatively, cloud service center) Lai Zhihang.

In an alternative embodiment, the method also includes: obtain the heating target of the target heating user；

Outdoor weather data based on the target heating user's local environment got predict that dynamic space heating load includes: The heating target of outdoor weather data and the target heating user based on the target heating user's local environment got is pre- Survey dynamic space heating load.

In embodiments of the present invention, controller can also obtain the heating target of target heating user, that is, target heating The room temperature reached desired by user.Then, outdoor weather data of the controller based on target heating user's local environment With the heating target prediction dynamic space heating load of target heating user.

In embodiments of the present invention, controller is also based on the target heating user's architectural exterior-protecting construction shape got Heat transfer conditions, instant out door climatic parameter and heating target (that is, room temperature that user needs) prediction dynamic heating between condition, neighbour Thermic load.

As can be seen from the above description, in one embodiment, the cell building A for the area A and the cell for the area B Building B.The controller for being mounted on the area A can acquire the outdoor weather data of cell building A local environment, then, be based on the outdoor The dynamic space heating load of meteorological data prediction cell building A；And it is mounted on the controller in the area B and can acquire cell building B institute Locate the outdoor weather data of environment, then, the dynamic space heating load based on outdoor weather data prediction cell building B.Herein In the case of, the dynamic space heating load of each heating user may be identical (or being not much different) in cell building A, at this point, It can determine to be not much different for each heating user heating load.But the dynamic space heating load of cell building A and cell building B Be it is different, have different at this time for cell building A and cell building the B heat supplied.By the above-mentioned means, can be real The personalized heating demands of existing different regions, while a large amount of energy can also be saved.

Further, for each heating user in cell building A, for example, heating user A1 and heating user A2, also has not Same heating demands.At this point, controller can be according to the heating target and outdoor weather data of each heating user to each Heating user in predicting dynamic space heating load, to realize the personalized heating demands of different heating users.For example, heating user A1 The same cell building is in heating user A2, wherein the heating target of heating user A1 is 22 degree, the heating of heating user A2 Target is 20 degree.At this point, the controller of heating user A1 can the ring according to locating for the heating target of heating user A1 and cell building A The meteorologic parameter in border is that heating user A1 predicts dynamic space heating load；The controller of heating user A2 can be according to heating user The heating target of A2 and the meteorologic parameter of cell building A local environment are that heating user A2 predicts dynamic space heating load.By upper State processing mode, can satisfy in the same cell building, the temperature between different user be it is different, so as to meet The heating demands of different user, additionally it is possible to further save the energy.

In an alternative embodiment, outdoor weather data based on the target heating user's local environment got and The heating target prediction dynamic space heating load of the target heating user includes the following steps:

Firstly, transferring target nerve network, wherein the target nerve network is the neural network that training is completed in advance；

Then, using the outdoor weather data and the heating target as the input of the target nerve network, so that The target nerve network handles the outdoor weather data and the heating target, and exports the dynamic for warm heat Load.

In embodiments of the present invention, after getting outdoor weather data and heating target, controller can be transferred Target nerve network.Then using outdoor weather data and the heating target as the input of target nerve network, so that the mesh Mark neural network handles outdoor weather data and the heating target, and exports dynamic space heating load, to realize not With the personalized heat demand between user.

Optionally, the target nerve network is expressed as following formula:

Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., m, m are described The node in hidden layer of target nerve network；x_iFor the neuron node value of i-th of input layer in the target nerve network；y_j, In is the input value of j-th of hidden layer neuron node in the target nerve network, y_j,outFor in the target nerve network The output valve of j-th of hidden layer neuron node；w_i,jFor i-th of input layer node in the target nerve network To the calculating weight of j-th of hidden layer neuron node；u_jFor j-th of hidden layer neuron node in the target nerve network To the calculating weight of output layer neuron node；Q_inAnd Q_outIt is the input value and output valve of output layer neuron node respectively, In, the output valve is the dynamic space heating load of prediction.

After obtaining dynamic space heating load, so that it may be generated based on dynamic space heating load and heating load data to mesh The control signal that mark valve is controlled.

Optionally, step S104 is generated based on the dynamic space heating load and heating load data and is carried out to target valve The control signal of control includes the following steps:

Step S1041 compares the dynamic space heating load and the heating load data, with the determination dynamic Deviation between space heating load and the heating load data；

Step S1042 is handled the deviation by pid algorithm or FUZZY ALGORITHMS FOR CONTROL, described to obtain Opening information and the make-and-break time information；

Step S1043 controls target valve based on the opening information and make-and-break time information generation Control signal.

In embodiments of the present invention, controller is after getting dynamic space heating load, and controller supplies dynamic first Warm heat load is compared with from the heating load data got for hotlist, in turn, determines dynamic for warm heat according to comparing result Deviation between load and the heating load data.Next, pid algorithm or FUZZY ALGORITHMS FOR CONTROL carry out the deviation Processing, processing obtain opening information and make-and-break time information (for example, make-and-break time ratio).Finally, based on the opening information and leading to Disconnected temporal information generates the control signal controlled target valve.

After generating and controlling signal, so that it may target valve is sent control signals to, so that the target valve (that is, Water flow control valve) the control signal that provides of controller is obtained, valve opening is adjusted to required aperture or by valve on-off State is adjusted to required state.

Optionally, the deviation is handled by pid algorithm, when obtaining the opening information and the on-off Between information include:

The deviation is handled by the calculation formula of pid algorithm, to obtain the opening information and described logical Disconnected temporal information:

Optionally, the deviation is handled by FUZZY ALGORITHMS FOR CONTROL, to obtain the opening information and described Make-and-break time information includes:

The deviation is handled by the calculation formula of FUZZY ALGORITHMS FOR CONTROL, to obtain the opening information and institute State make-and-break time information:

In embodiments of the present invention, before transferring target nerve network, the method also includes: to the target nerve Network is trained, and with the weight coefficient between each neuron node in the determination target nerve network, is specifically included:

It is iterated training by target nerve network described in iterative formula, with the determination weight coefficient, the iteration Formula is

Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., m, m are described The node in hidden layer of target nerve network；x_iFor i-th of input layer nodal value in the target nerve network；y_j,out For the defeated output valve of j-th of hidden layer neuron node in the target nerve network；WithRespectively described j-th hidden Neuron node containing layer to output layer neuron node calculating weight n-th and the N+1 times repetitive exercise value；WithI-th of input layer node respectively to j-th of hidden layer neuron node calculating weight in N Secondary and the N+1 times repetitive exercise value；η is iteration efficiency factor；δ is the output valve and expectation of the output layer neuron node Partial derivative of the departure function of value to output layer node weights.

As shown in Figure 4 is the structural schematic diagram of neural network.In embodiments of the present invention, it is used in the controller Before, by pre-debug data, target nerve network is trained, is determined in target nerve network between each neuron node Weight coefficient.For example, target nerve network shown in Fig. 4 includes the hidden layer of 401, two nodes of input layer of six nodes 402 and a node output layer 403.Six input layers may include outside air temperature, intensity of solar radiation, last moment Heating load, indoor target temperature, the heating load at adjacent family and wind pressure (or hot pressing etc.).Before target nerve network training, The initial value of node weights is provided at random, then using the neuroid with initial weight, using formula (1) heat load calculation Predicted value, and compared with heating load data, obtain deviation δ；Then, calculating, more new node are iterated using formula (4) The numerical value of weight then completes target nerve net until the prediction total deviation value of target nerve network meets preset required precision The training of network.

In an alternative embodiment, this method further include: obtain Heat Transfer Data between neighbour, wherein conduct heat between the neighbour Data are the Heat Transfer Data between target heating user heating user adjacent thereto；It is used based on the target heating got The heating target prediction dynamic space heating load of the outdoor weather data of family local environment and the target heating user further include: Based on Heat Transfer Data between the neighbour, dynamic described in the heating target prediction of the outdoor weather data and the target heating user Space heating load.

In embodiments of the present invention, controller can also obtain the biography between the heating user adjacent with target heating user Dsc data；Then, based on Heat Transfer Data between adjacent, dynamic described in the heating target prediction of outdoor weather data and target heating user Space heating load.

Optionally, controller can also be by Heat Transfer Data between neighbour, the heating mesh of outdoor weather data and target heating user It is denoted as the input of above-mentioned target nerve network, so that target nerve network is between Heat Transfer Data neighbour, outdoor weather data and mesh The heating target of mark heating user is predicted, dynamic space heating load is obtained.

In conclusion in embodiments of the present invention, controller can be pre- to target heating user based on outdoor weather data Survey dynamic space heating load；The heating target prediction target heating for being also based on outdoor weather data and target heating user is used Predict dynamic space heating load in family；It is also based on Heat Transfer Data between neighbour, the heating of outdoor weather data and target heating user Target prediction target heating user in predicting dynamic space heating load.That is, Heat Transfer Data between neighbour, outdoor weather can be passed through At least one of data and the heating target of target heating user predict dynamic space heating load, to guarantee different user Different demands meet plurality of application scenes.

To sum up, the embodiment of the present invention proposes a kind of heat supply method based on building load prediction, and this method is based on building Load prediction and calorimeter data carry out point family precisely for thermal control.This method is joined using neural network method by outdoor weather Number, indoor target temperature predict dynamic space heating load；By reading the heating load data and pre- calorimetric that existing calorimeter measures Load compares, and by the methods of pid algorithm or fuzzy algorithmic approach, calculates the aperture or make-and-break time ratio of heating water regulating valve, The thermic load that the size of the heat of supply user reaches prediction is adjusted by changing heating water, is realized idle to calorimeter The utilization of resource, the demand for meeting different room temperatures avoid supercooling overheat, improve thermal comfort level, avoid confession The waste of heat energy.

The above method is introduced with a specific embodiment below.

Table 1

As shown in table 1 below is to be provided in the affordable housing of XXXXX army (10X hospital) using the embodiment of the present invention Method and system carry out heat supply when for dsc data.In table 1, the heat supply of 2013~2014 annual affordable housings be by The heat supply of estate management, 2014~2015 years and 2015~2016 annual affordable housings is using institute of the embodiment of the present invention The method and system of offer is realized.That is, 2013~2014 years were not implemented using the present invention for dsc data For dsc data obtained by method and system provided by example；, 2014~2015 years and 2015~2016 years are for dsc data For using method and system provided by the embodiment of the present invention obtain for dsc data.As shown in table 1, heat supply data include heating Area, actual energy consumption, wherein heating area includes mating construction area and heating building area；Actual energy consumption includes heating rate, Real heating duration, practical year heating load, entire heating season heating load and entire heating season power supply volume.By the table it is found that 2013 ~2014 years, the heating area in 2014~2015 years and 2015~2016 years, heating rate and heating number of days are all year by year The trend of growth.But practical year heating load, entire heating season heating load and entire heating season power supply volume decline year by year. By being analyzed the data in table 1 it is found that adjusting point family flow using technology of the present invention, heat amount of energy saving is about 24%, power consumption about saves 60%.It, can be with by the measurement data of load prediction and calorimeter that is, in embodiments of the present invention Realization divides family accurate heat supply on demand, meets the different room temperature demands of different heat supply users, can also avoid the problem that supercooling overheat, To improve comfort level, to avoid heat supply energy waste, and then alleviating can not dynamically be heating user in the prior art The technical issues of carrying out room temperature adjusting.

Embodiment three:

The embodiment of the invention also provides a kind of heating plants based on building load prediction, should be predicted based on building load Heating plant be mainly used for execute above content of the embodiment of the present invention provided by based on building load prediction heat supply method, Specific introduction is done to the heating plant provided in an embodiment of the present invention based on building load prediction below.

Fig. 5 is a kind of schematic diagram of heating plant based on building load prediction according to an embodiment of the present invention, such as Fig. 5 institute Showing, the heating plant that should be predicted based on building load mainly includes predicting unit 10, generation unit 20 and transmission unit 30, In:

Predicting unit 10 predicts dynamic for the outdoor weather data based on the target heating user's local environment got Space heating load, wherein the dynamic space heating load is the heat demand of the target heating user predicted；

Generation unit 20, for raw based on the actually detected heating load data of the dynamic space heating load and heat meter The control signal that pairs of target valve is controlled, wherein opening information and/or make-and-break time letter are carried in the control signal Breath, the target valve is the valve controlled the heating water flow of the target heating user；

Transmission unit 30, for sending the control signal to the target valve, so that the target valve is according to institute It states control signal and executes corresponding movement.

In addition, in the description of the embodiment of the present invention unless specifically defined or limited otherwise, term " installation ", " phase Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected；It can To be mechanical connection, it is also possible to be electrically connected；It can be directly connected, can also can be indirectly connected through an intermediary Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition Concrete meaning in invention.

In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical", The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation, It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ", " third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.

Provided by the embodiment of the present invention it is a kind of based on building load prediction heat supply method, device and system computer Program product, the computer readable storage medium including storing the executable non-volatile program code of processor, the journey The instruction that sequence code includes can be used for executing previous methods method as described in the examples, and specific implementation can be found in method and implement Example, details are not described herein.

It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description, The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.

In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with It realizes by another way.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, Only a kind of logical function partition, there may be another division manner in actual implementation, in another example, multiple units or components can To combine or be desirably integrated into another system, or some features can be ignored or not executed.Another point, it is shown or beg for The mutual coupling, direct-coupling or communication connection of opinion can be through some communication interfaces, device or unit it is indirect Coupling or communication connection can be electrical property, mechanical or other forms.

The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme 's.

It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.

It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, of the invention Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words The form of product embodies, which is stored in a storage medium, including some instructions use so that One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the present invention State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read- Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can be with Store the medium of program code.

Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. a kind of heat supply method based on building heating load prediction characterized by comprising

The confession of instant outdoor weather data and each target heating user based on the target heating user's local environment got Warm target prediction dynamic space heating load, wherein the dynamic space heating load is the target heating user predicted Heat demand, the dynamic space heating load are the workload demand predicted according to different user to indoor different demands, institute Stating user is the room temperature reached desired by target heating user to indoor demand；

Target valve is controlled based on the actually detected heating load data generation of the dynamic space heating load and calorimeter Control signal, wherein opening information and/or make-and-break time information are carried in the control signal, the target valve is pair The valve that the heating water flow of the target heating user is controlled, the calorimeter and the target valve are arranged in hotlist In well；

The control signal is sent to the target valve, so that the target valve executes accordingly according to the control signal Movement；

Wherein, instant outdoor weather data and the target heating user based on the target heating user's local environment got Heating target prediction dynamic space heating load include:

Target nerve network is transferred, the target nerve network is the neural network that training is completed in advance；

By Heat Transfer Data, architectural exterior-protecting construction situation, instant outdoor weather data and the confession between the heating load of last moment, neighbour Warm input of the target as the target nerve network, so that the target nerve network is to outdoor weather data and described Heating target is handled, and exports the dynamic space heating load, and Heat Transfer Data is the target heating user between the neighbour Heat Transfer Data between heating user adjacent thereto, the instant outdoor weather data are to pass through outdoor weather data pick-up Collected data, the instant outdoor weather data include but is not limited to: gas epidemic disaster, intensity of solar radiation, wind speed, gas Pressure.

2. heat supply method according to claim 1, which is characterized in that the target nerve network is expressed as following public affairs Formula:

Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., m, m are the target The node in hidden layer of neural network；x_iFor the neuron node value of i-th of input layer in the target nerve network；y_j,inFor The input value of j-th of hidden layer neuron node, y in the target nerve network_j,outIt is j-th in the target nerve network The output valve of hidden layer neuron node；w_i,jFor i-th of input layer node in the target nerve network to jth The calculating weight of a hidden layer neuron node；u_jIt is j-th of hidden layer neuron node in the target nerve network to defeated The calculating weight of layer neuron node out；Q_inAnd Q_outIt is the input value and output valve of output layer neuron node respectively, wherein The output valve is the dynamic space heating load of prediction.

3. heat supply method according to claim 1, which is characterized in that be based on the dynamic space heating load and heating load number Include: according to the control signal controlled target valve is generated

The dynamic space heating load and the heating load data are compared, with the determination dynamic space heating load and institute State the deviation between heating load data；

The deviation is handled by pid algorithm or FUZZY ALGORITHMS FOR CONTROL, to obtain the opening information and described Make-and-break time information；

The control signal controlled the target valve is generated based on the opening information and the make-and-break time information.

4. heat supply method according to claim 3, which is characterized in that the deviation is handled by pid algorithm, To obtain the opening information and the make-and-break time information includes:

The deviation is handled by the calculation formula of pid algorithm, when obtaining the opening information and the on-off Between information:

Wherein, V is the opening information of the target valve；K is rate mu-factor；Q_pIt is the dynamic that predicts for warm heat Load；Q_mThe heating load data measured for calorimeter；T_IFor the time of integration；T_DFor derivative time；τ is the time.

5. heat supply method according to claim 3, which is characterized in that carried out by FUZZY ALGORITHMS FOR CONTROL to the deviation Processing, to obtain the opening information and the make-and-break time information includes:

The deviation is handled by the calculation formula of FUZZY ALGORITHMS FOR CONTROL, to obtain the opening information and described logical Disconnected temporal information:

Wherein, V is the make-and-break time information；K is rate mu-factor；Q_pFor the dynamic space heating load predicted；Q_m The heating load data measured for calorimeter；τ is the time, and fuzzy is ambiguity function.

6. heat supply method according to claim 1, which is characterized in that before transferring target nerve network, the method Further include: the target nerve network is trained, between each neuron node in the determination target nerve network Weight coefficient, specifically include:

It is iterated training by target nerve network described in iterative formula, with the determination weight coefficient, the iterative formula For

Wherein, i=1,2 ..., n, n are the input number of nodes of the target nerve network；J=1,2 ..., m, m are the target The node in hidden layer of neural network；x_iFor i-th of input layer nodal value in the target nerve network；y_j,outFor institute State the defeated output valve of j-th of hidden layer neuron node in target nerve network；WithRespectively described j-th of hidden layer Neuron node to output layer neuron node calculating weight n-th and the N+1 times repetitive exercise value；With I-th of input layer node respectively to j-th of hidden layer neuron node calculating weight in n-th and The value of the N+1 times repetitive exercise；η is iteration efficiency factor；δ is the output valve and desired value of the output layer neuron node Partial derivative of the departure function to output layer node weights.

7. heat supply method according to any one of claim 1 to 6, which is characterized in that the outdoor weather data include At least one of: outdoor temperature change information, outdoor wind speed change information, outdoor intensity of solar radiation change information；It is described Heating target is target heating user purpose temperature to be achieved.

8. heat supply method according to claim 7, which is characterized in that the method also includes: Heat Transfer Data between acquisition is adjacent, Wherein, Heat Transfer Data of the Heat Transfer Data between target heating user heating user adjacent thereto between the neighbour；

The heating mesh of outdoor weather data and the target heating user based on the target heating user's local environment got Mark prediction dynamic space heating load further include: based on Heat Transfer Data between the neighbour, the outdoor weather data and the target are adopted Dynamic space heating load described in the heating target prediction of warm user.

9. a kind of heating system based on building heating load prediction characterized by comprising the first controller, sensor, heat Scale and target valve, the target valve are the valve controlled the heating water flow of the target heating user；

The sensor is used to acquire the instant outdoor weather data of target heating user's local environment；

First controller is dynamic for the heating target prediction based on the outdoor weather data and each target heating user State space heating load, and the control controlled target valve is generated based on the dynamic space heating load and heating load data Signal, wherein the dynamic space heating load is the heat demand of the target heating user predicted；The control signal Middle carrying opening information and/or make-and-break time information, the dynamic space heating load are according to different user to indoor difference The workload demand that requirement forecasting goes out, the calorimeter and the target valve are arranged in hotlist well, and the user is to indoor need Seek the room temperature to reach desired by target heating user；

The target valve is used to execute corresponding movement according to the control signal, to adjust the confession of the target heating user Warm water flow；

First controller is also used to: transferring target nerve network, the target nerve network is the mind that training is completed in advance Through network；

10. heating system according to claim 9, which is characterized in that embedded in the control chip of first controller There is the target nerve network that training is completed in advance；

Wherein, the target nerve network is used for based on the outdoor weather data and heating target prediction dynamic for warm heat Load prediction dynamic space heating load.

11. heating system according to claim 10, which is characterized in that the heating system further include: second controller, Wherein, the second controller is mounted on and the controller in target heating user's neighboring user, the second controller It is communicated to connect with first controller；

The second controller is used to transmit adjacent heating user heating load to first controller, is based on adjacent heating user Heating load calculates Heat Transfer Data between neighbour, so that first controller is based on Heat Transfer Data between the neighbour, the outdoor weather number According to dynamic space heating load described in the heating target prediction with the target heating user, wherein Heat Transfer Data is between the neighbour Heat Transfer Data between target heating user heating user adjacent thereto.

12. heating system according to claim 10, which is characterized in that embedded in the control chip of first controller There are fuzzy controller or PID controller；

The fuzzy controller or the PID controller are used to generate based on the dynamic space heating load and heating load data The control signal that target valve is controlled.

13. heating system according to claim 10, which is characterized in that the sensor includes: temperature sensor, wind speed Sensor, intensity of solar radiation sensor, in which:

The intensity of solar radiation sensor is used to acquire the outdoor intensity of solar radiation of target heating user's local environment Change information.

14. heating system according to claim 10, which is characterized in that first controller passes through wired or wireless Connection type respectively with the sensor, the calorimeter is connected with the target valve.

15. heating system according to claim 14, which is characterized in that when the connection type is wired connection mode When, first controller is connected by M-Bus bus with the calorimeter；First controller by 485 buses with The sensor is connected, alternatively, being connected by analog signals line with the sensor, first controller passes through 485 buses are connected with the target valve, alternatively, being connected by analog signals line with the target valve.

16. heating system according to claim 14, which is characterized in that when the connection type is radio connection When, first controller by way of following at least one respectively with the sensor, the calorimeter and the target valve Door is connected: GPRS, 3G network, 4G network, 5G network, WIFI network are connected with internet.

17. heating system according to claim 10, which is characterized in that the calorimeter is respectively used to detect the heat supply The temperature of return pipe and water supplying pipe, water flow, successively obtain return water temperature, supply water temperature and water flow, wherein described in system Return water temperature, the supply water temperature and the water flow are for determining the heating load data.

18. heating system according to claim 10, which is characterized in that the target valve includes following any: being opened The electrically operated valve that can be continuously adjusted is spent, the electromagnetic valve of on-off control can be carried out continuously, on-off control can be carried out continuously Electric heating valve, pass through mechanical device drive self force type control valve door.

19. a kind of heating plant based on building heating load prediction characterized by comprising

Predicting unit, for instant outdoor weather data and each target based on the target heating user's local environment got The heating target prediction dynamic space heating load of heating user, wherein the dynamic space heating load is the mesh predicted The heat demand of heating user is marked, the dynamic space heating load predicts indoor different demands according to different user Workload demand, the user are the room temperature reached desired by target heating user to indoor demand；

Generation unit, for generating the control controlled target valve based on the dynamic space heating load and heating load data Signal processed, wherein opening information and/or make-and-break time information are carried in the control signal, the target valve is to described The valve that the heating water flow of target heating user is controlled, the calorimeter and the target valve are arranged in hotlist well In；

Transmission unit, for sending the control signal to the target valve, so that the target valve is according to the control Signal executes corresponding movement；

Wherein, the predicting unit is also used to:

20. heating plant according to claim 19, which is characterized in that the target in the heating plant is arranged in The network structure of neural network is expressed as following formula:

21. heating plant according to claim 20, which is characterized in that generation unit is used for:

The control signal controlled target valve is generated based on the opening information and the make-and-break time information.

22. heating plant according to claim 21, which is characterized in that generation unit is also used to:

23. heating plant according to claim 21, which is characterized in that generation unit is also used to:

24. heating plant according to claim 19, which is characterized in that the device is also used to: transferring target nerve net Before network, the target nerve network is trained, between each neuron node in the determination target nerve network Weight coefficient, specifically include:

25. a kind of computer-readable medium for the non-volatile program code that can be performed with processor, which is characterized in that described Program code makes the processor execute method described in any one of the claims 1 to 8.