CN111310257A - Regional building energy consumption prediction method under BIM environment - Google Patents
Regional building energy consumption prediction method under BIM environment Download PDFInfo
- Publication number
- CN111310257A CN111310257A CN201911375174.5A CN201911375174A CN111310257A CN 111310257 A CN111310257 A CN 111310257A CN 201911375174 A CN201911375174 A CN 201911375174A CN 111310257 A CN111310257 A CN 111310257A
- Authority
- CN
- China
- Prior art keywords
- building
- parameters
- energy consumption
- regional
- neural network
- Prior art date
- Legal status (The legal status 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 status listed.)
- Withdrawn
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 138
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 82
- 238000013461 design Methods 0.000 claims abstract description 53
- 238000004088 simulation Methods 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000008878 coupling Effects 0.000 claims abstract description 8
- 238000010168 coupling process Methods 0.000 claims abstract description 8
- 238000005859 coupling reaction Methods 0.000 claims abstract description 8
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 8
- 230000003993 interaction Effects 0.000 claims abstract description 6
- 230000000750 progressive effect Effects 0.000 claims abstract description 5
- 239000002245 particle Substances 0.000 claims description 27
- 230000035945 sensitivity Effects 0.000 claims description 27
- 210000002569 neuron Anatomy 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 9
- 238000011835 investigation Methods 0.000 claims description 8
- 230000002068 genetic effect Effects 0.000 claims description 7
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000010438 heat treatment Methods 0.000 claims description 4
- 238000005057 refrigeration Methods 0.000 claims description 4
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract description 2
- 230000007547 defect Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000007619 statistical method Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000254032 Acrididae Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a regional building energy consumption prediction method under a BIM environment, which comprises the following steps: A. building various BIM building typical models based on the actually measured and researched areas; B. establishing a coupling model between a climate simulation platform and a building energy consumption simulation platform to complete the simulation of various building energy consumption; C. constructing a data interaction program, carrying out regional building energy consumption design parameter sensitivity analysis based on a progressive gradient regression tree algorithm, and determining input parameters of an improved PSO-GA-BP neural network; D. constructing various BIM building typical model energy consumption prediction modules in the region based on an improved PSO-GA-BP neural network; E. and (3) constructing a future regional climate and building parameter BP neural network prediction module, and predicting various BIM building energy consumption and regional building total energy consumption in a region. Compared with the prior art, the invention has the beneficial effects that: the integration of energy consumption prediction workflows of various regional buildings is realized, and the rapid and accurate prediction of the energy consumption of various regional buildings based on the improved PSO-GA-BP neural network is realized.
Description
Technical Field
The invention relates to the technical field of regional building energy consumption prediction, in particular to a regional building energy consumption prediction method in a BIM environment.
Background
Nowadays, the building energy consumption of China accounts for 40% of the total energy consumption, and has great energy-saving potential; in addition, the energy-saving design of the building not only needs to consider the single building, but also needs to evaluate the energy consumption of the regional building. The regional building refers to a building group with the scale of 1 square kilometer in a regional range, and the scheme design of the building group in the planning stage has important significance for energy conservation of the region.
At present, the statistical method of the energy consumption of the regional building mainly comprises a physical model, a statistical analysis model and a mixed model. The physical model is used for estimating the total energy consumption of the regional building by constructing various typical building models and carrying out simulation on various building energy consumption values, the building performance measured by the method has good fitting property with the actual building performance, but the method needs a large amount of data for supporting; the statistical analysis model is a method for calculating the building energy consumption value by constructing a regression analysis equation or a neural network, and the method has the advantages that detailed data is not required to be relied on, but has the defects of poor flexibility and dependence on historical data; the hybrid model may combine the advantages of the statistical analysis model and the physical model, respectively. However, the three energy consumption statistical methods lack certain building information data, and the BIM technology can make up for the defect of less building information data, and integrates a complete building engineering information base by constructing a virtual three-dimensional building model and utilizing a digitization technology.
The existing regional building energy-saving design has more problems, for example, a statistical analysis model depends on historical energy consumption data, and domestic building energy consumption audit data lack records related to building planning, building envelope and building indoor environment data; the physical model of the energy consumption of the regional building has the defects of large information amount of the building model, long time consumption of the simulation calculation of the energy consumption of the building, lack of consideration of regional characteristics of climate data in an energy consumption simulation result and the like, and the energy consumption simulation analysis is performed on a single building or a plurality of buildings with detailed building information and design parameters in most of the existing regional building energy consumption simulation, so that the model has no typicality.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the prior art, provides a regional building energy consumption prediction method based on an improved PSO-GA-BP neural network under a BIM environment, and realizes accurate prediction of regional building energy consumption by constructing an improved PSO-GA-BP neural network regional building energy consumption prediction module. The method comprises the steps of obtaining regional building geographic information by applying an Openstreetmap network public map, and generating software to construct a regional building geometric model based on a regional building parameterized model; acquiring regional building height information by using an Arcmap plug-in of a GIS platform and combining the regional building height information with a regional building geometric model to generate a regional building model; completing manual statistics of the type of the regional building, the parameters of the enclosure structure and the parameters of indoor equipment based on field investigation, and constructing various BIM building typical models of the region by combining the regional building model; building energy consumption simulation coupling models between the urban microclimate simulation platform and the building energy consumption simulation platform are constructed, so that a building energy consumption simulation result based on climate parameters of the microclimate simulation platform and building design parameters of the building energy consumption simulation platform can be obtained, and the building energy consumption simulation result is combined with various BIM building typical model information data of the region to generate various BIM building typical model energy consumption information databases of the region; building energy consumption prediction modules based on the improved PSO-GA-BP neural network are constructed on a GH platform by applying Python programming, and then various BIM building typical model energy consumption information databases in the region and the improved PSO-GA-BP neural network modules are combined to be trained to generate various BIM building typical model energy consumption prediction modules in the region; the prediction of future regional climate parameters and regional building design parameters can be realized based on the construction of a prediction module of the future regional building design parameters and the climate parameters, and the prediction of the energy consumption of various regional building typical models and the calculation of the total energy consumption of regional buildings can be realized based on the energy consumption prediction module of various regional BIM building typical models.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: a regional building energy consumption prediction method under a BIM environment comprises the following steps:
A. building various BIM building typical models based on the actually measured and researched areas;
B. establishing a coupling model between a climate simulation platform and a building energy consumption simulation platform, and completing the simulation of various building energy consumption by inputting climate parameters and various building typical model design parameters;
C. constructing a data interaction program, carrying out regional building energy consumption design parameter sensitivity analysis based on a progressive gradient regression tree algorithm, and determining input parameters of an improved PSO-GA-BP neural network;
D. constructing various BIM building typical model energy consumption prediction modules in the region based on an improved PSO-GA-BP neural network;
E. and (3) constructing a future regional climate and building parameter BP neural network prediction module, and predicting various BIM building energy consumption and regional building total energy consumption in a region.
Compared with the prior art, the invention has the advantages that: compared with the prior art, the invention has the beneficial effects that:
1. the integration of various regional building energy consumption prediction workflows is realized:
the method comprises the steps of generating a basic regional building geometric model constructed by software based on a regional building parameterized model; acquiring regional building height information by applying an Arcmap plug-in of a GIS platform, combining the regional building height information with a basic model to generate a regional building model, constructing a building energy consumption simulation coupling model between an urban microclimate simulation platform and a building energy consumption simulation platform based on the regional building model, and simulating the building energy consumption; the energy consumption information database of various BIM building typical models in the region is generated through a data interaction program, the defect of incomplete domestic energy consumption statistical data is overcome, and the database comprehensively considers the characteristics of the region building; training of the improved BP neural network and prediction of energy consumption of various regional buildings in a BIM environment are completed by constructing an improved PSO-GA-BP neural network prediction module, the whole working process can be completed based on a Grasshopper platform, the problem that files need to be manually stored and converted among multiple software platforms in the past is reduced, and the energy consumption prediction efficiency is improved.
2. The method realizes the rapid and accurate prediction of the energy consumption of various regional buildings based on the improved PSO-GA-BP neural network:
according to the invention, through the construction of the GBRT regional building energy consumption sensitivity analysis module, the screening of the regional building energy consumption sensitivity design parameters is realized, the number of input parameters for the later neural network training is reduced, and the network training and prediction efficiency is improved on the premise of ensuring the prediction accuracy; the PSO-GA algorithm improves the traditional BP neural network, and realizes the early-stage optimization of the weight value w and the threshold value b of the BP neural network so as to meet the set prediction error value; and the optimized weight value w and the threshold value b are substituted into the BP neural network, so that the learning of the energy consumption information database of various BIM building typical models in the region and the prediction of the energy consumption values of various building typical models in the region are realized, the defects of large data quantity and insufficient generalization capability of the traditional BP neural network in processing the medium-term and long-term complex prediction problems are overcome, and the PSO-GA-BP neural network is improved to enable the prediction process to be faster and more accurate.
Preferably, the step a includes:
(1) based on field investigation and investigation, carrying out manual statistics on the types of regional buildings, the parameters of the enclosure structure and the parameters of indoor equipment, wherein the types of the regional buildings comprise regional residential buildings, regional office buildings, regional industrial buildings and regional commercial buildings;
(2) the building envelope parameters comprise a roof heat transfer coefficient, an outer wall heat transfer coefficient, an outer window heat transfer coefficient and an outer window shading coefficient, and the data can be obtained by counting the building envelope type and looking up data to obtain corresponding values;
(3) the indoor equipment parameters comprise personnel density, fresh air index, illumination power and equipment power, and the data can be obtained by consulting regional public building energy-saving design standards to obtain corresponding values; obtaining the proportion of buildings in various regions based on the statistical region building types;
(4) and constructing various BIM building typical models of the region based on the statistical geometric parameters of the region building, the building envelope parameters and the building indoor equipment setting parameters.
Preferably, the step B includes:
(1) the value ranges of the experiment variable enclosure structure parameters, the building geometric parameters and the indoor equipment parameters are based on manual statistics of the exchange and research area parameters; the climate parameters are based on statistics of historical climate parameters for the region;
(2) the energy consumption simulation result comprises a winter heating energy consumption value, a summer refrigeration energy consumption value, a lighting energy consumption value and a total annual energy consumption value of the building, and the energy consumption simulation values of various buildings in the area can reflect typical model information and regional climate information of various BIM buildings in the area.
Preferably, the step D includes:
(1) constructing a basic BP neural network model;
(2) initializing each variable setting of the particle swarm m;
(3) calculating the fitness value of the particle swarm, and calculating the fitness value and the best position p passed by the fitness value in each particle swarmbestComparing to determine the global best position;
(4) after each update, the copy, cross and variation operations of the genetic algorithm can be introduced to the population with moderate particle population adaptation, and the variation probability is used for the particle population with poor adaptation degree to operate;
(5) updating the individual extreme value and the global extreme value of the particle swarm, comparing the current fitness value of the particle with the fitness value of the individual extreme value and updating after copying, crossing and variation operations in the genetic algorithm of the step (4), updating after comparing the fitness value of the individual extreme value with the fitness value of the global extreme value, and repeating the steps (3) to (5) until the iteration times reach the standard or the objective function reaches the convergence precision;
(6) after the algorithm is finished, substituting the weight value and the threshold value of the BP neural network corresponding to the global optimal solution into the neural network to complete the construction of the BIM building energy consumption prediction module of the region;
(7) and (4) based on the energy consumption training sample sets of different types of regional buildings, operating according to the steps (1) to (6), and constructing various BIM building energy consumption prediction modules of the regions.
Preferably, the step E includes:
(1) determining sensitivity design parameters in the parameters of the enclosure structure as E, sensitivity design parameters in the parameters of the indoor equipment as S, sensitivity design parameters in the climate parameters as F, energy consumption sensitivity design parameters in the geometric parameters of the building as D and time parameters, and constructing a BP neural network training set;
(2) determining climate parameters, building geometric parameters and indoor equipment parameters, mapping the envelope parameters to a basic structure of a BP neural network to be three-layer neurons, wherein the number of the neuron nodes of an input layer is NinThe neuron nodes are:
wherein,
respectively designing F sensitivity design parameters in climate parameters, and D energy consumption sensitivity design parameters and time parameters in building geometric parameters;
(3) determining number of output layer neuron nodes to be NoutThe neural nodes are:
wherein,
respectively designing E sensitivity design parameters in the parameters of the enclosure structure, and S sensitivity design parameters and time parameters in the parameters of the indoor equipment;
(4) number of hidden layer neuron nodes is NhiAnd the neuron nodes satisfy: n is a radical ofhiSqrt (n + p) + a, where a is a constant between 1 and 10;
(5) updating the weight of the neural network node, and then using a gradient descent method to the connection weight omega of the new generation neural network according to the formula and the operation mode of the BP neural networki1，ωj2Updating is carried out;
(6) updating the neural network node threshold value to complete the new generation of the neural network threshold value, and updating the neural network;
(7) repeating the steps (5) and (6) until the iteration times reach the standard or the target function reaches the convergence precision, and obtaining a climate parameter, a building geometric parameter, a time parameter, an indoor equipment parameter and an envelope parameter BP neural network module;
(8) and (3) constructing a BP neural network module based on the steps (6) and (7) to generate a prediction module of future regional climate and building parameters, realizing prediction of the regional future climate and building design parameters by inputting 4 types of sensitive building design parameters (sensitive indoor equipment parameters, sensitive enclosure structure parameters, sensitive climate parameters and sensitive building geometric parameters) and the future year, and realizing prediction of regional building energy consumption based on the predicted regional future climate and building design parameters.
Drawings
FIG. 1 is a flow chart of energy consumption prediction of various buildings in an area based on an improved PSO-GA-BP neural network.
Detailed Description
The present invention will be described in further detail with reference to the attached drawings, and in order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the attached drawings in the examples of the present application. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. Based on the embodiments of the invention. All other embodiments obtained by a person skilled in the art without making any inventive step should be within the scope of protection of the present application.
The technical scheme of the invention is further described by combining the accompanying drawings and the implementation mode:
step one, constructing various BIM building typical models in an area based on actual measurement investigation:
obtaining a building base map of 1 square kilometer around the Ministry of the Haerban Seaman building in south sentry by using a network public map, placing the building base map into a GH platform to generate a basic building geometric model, obtaining the area base map by using a geographic information system, adding an XY coordinate derivation coordinate break point attribute text file in the range to extract the height information of the area building, and placing the area building height information into the GH platform to be combined with the building geometric model of the Nansentry to generate the area building model.
Based on field investigation and investigation, carrying out manual statistics on the construction type, the enclosure structure parameters and the indoor equipment parameters of the south sentry area; the construction types of the south sentry area comprise residential buildings, office buildings, industrial buildings and commercial buildings; the building envelope parameters comprise a roof heat transfer coefficient, an outer wall heat transfer coefficient, an outer window heat transfer coefficient and an outer window shading coefficient, and the data can be obtained by counting the building envelope type and looking up data to obtain corresponding values; the indoor equipment parameters comprise personnel density, fresh air index, illumination power and equipment power, and the data can be obtained by looking up the energy-saving design standard of the public building to obtain corresponding values; obtaining the proportion of various buildings based on the statistical building types of the area; and finally, constructing various BIM building typical models in the area based on the statistical building geometric parameters, building envelope parameters and building indoor equipment setting parameters.
Step two, establishing a coupling model between the climate simulation platform and the building energy consumption simulation platform, and completing the simulation of various building energy consumption by inputting climate parameters and various building typical model design parameters:
in order to obtain various building energy consumption simulation values capable of reflecting climate information, the invention establishes a coupling model between a climate simulation platform and a building energy consumption simulation platform, carries out energy consumption simulation on the coupling model based on an orthogonal test method, and generates various BIM building typical model energy consumption information data in the area by combining simulation results with various BIM building typical model information data. The evaluation ranges of the experiment variable enclosure structure parameters, the building geometric parameters and the indoor equipment parameters are based on manual statistics of the exchange and research area parameters; the climate parameters are based on statistics of historical climate parameters in the southern post area; the energy consumption simulation result comprises a winter heating energy consumption value, a summer refrigeration energy consumption value, a lighting energy consumption value and a whole-year total energy consumption value of the building, and the energy consumption simulation values of various buildings in the region can reflect typical model information and regional climate information of various BIM buildings in the south sentry region.
Step three, constructing a data interaction program, carrying out regional building energy consumption design parameter sensitivity analysis based on a progressive gradient regression tree algorithm, and determining input parameters of the improved PSO-GA-BP neural network:
a data interaction program between a GH platform and a data storage platform is established based on Python programming, various BIM building typical model information data, microclimate data and various BIM building energy consumption simulation values of the area can be integrated into various BIM building typical model energy consumption information databases of the area, the databases comprise various building geometric design parameters, building envelope parameters, indoor equipment parameters, climate parameters and corresponding building energy consumption simulation values (specifically set as the following table) of residential buildings, office buildings, industrial buildings and commercial buildings of the area, and a Harbin south sentry district climate parameter, various BIM building typical model information data and energy consumption simulation value database is established. A progressive gradient regression tree (GBRT) sensitivity analysis module is constructed on a GH platform by using Python programming, sensitivity analysis is carried out on the basis of an energy consumption simulation value database of various regional buildings and the GBRT sensitivity analysis module, and sensitivity design parameters obtained by various building analysis are determined as input parameters of an improved PSO-GA-BP neural network.
Step four, constructing various BIM building typical model energy consumption prediction modules in south sentry areas of Harbin city based on the improved PSO-GA-BP neural network:
the energy consumption prediction module of various BIM building typical models in the Nangang district of Harbin city is constructed by Python programming based on a GH platform, and the advantages of high convergence rate of the neural network and global search of a genetic algorithm by adopting a particle swarm optimization algorithm make up the defects that the traditional BP neural network is low in convergence rate and easy to fall into a local minimum value. And optimizing the weight and the threshold of the BP neural network based on a PSO-GA algorithm, then bringing the weight and the threshold into the BP neural network for learning training, and constructing various BIM building typical model energy consumption prediction modules in the Nangang region of Harbin city based on the improved PSO-GA-BP neural network. The method for realizing the energy consumption prediction module of various BIM building typical models in the region based on the improved PSO-GA-BP neural network comprises the following steps:
(1) constructing a basic BP neural network model:
determining that the basic structure of the BP neural network is three layers of neurons, wherein the number of input layer neuron nodes is N, and the neuron nodes are as follows:
the number of neuron nodes in the output layer is 4, and the neuron nodes are as follows:
the number of hidden layer neuron nodes is l, and the neuron nodes are:
Nhi＝sqrt(n+p)+a
a is a constant between 1 and 10;
(2) initializing respective variable settings of the particle group m:
setting the position of a particle i in the current particle swarm as the combination x of the optimized weight value and the threshold value of the BP neural networki：
Xi＝[v11…v21…vn1…w11…w12…w1p]T
The velocity of the ith particle is calculated as:
wherein,
adjusting the kth generation position vector of the particle for the current required speed; c. C1，c2，c3，c4Is a learning factor; r is1，r2，r3，r4Is [0, 1 ]]
A random number in between; w is an inertia weight, and a larger weight value can enhance the global searching capability, wherein a linear decreasing weight strategy is adopted:
wherein, wmax、wminwminThe maximum and minimum values of the weight w, respectively; t, tmaxCurrent iteration number and maximum iteration number respectively
(3) Calculating the fitness value of the particle swarm, and calculating the fitness value and the best position p passed by the fitness value in each particle swarmbestAnd comparing to determine a global best position, wherein the neural network training error can be used as an evaluation function of the particles:
where d and Y represent the desired output and the actual output at the input of the ith sample. And when the evaluation function meets the error precision requirement or reaches the maximum iteration number, the iteration loop can be terminated.
(4) After each update, the copy, cross and variation operations of the genetic algorithm can be introduced to the population with moderate particle population adaptation, and the variation probability is used for the particle population with poor adaptation to operate.
(5) And (4) updating the individual extreme value and the global extreme value of the particle swarm, comparing the current fitness value of the particle with the fitness value of the individual extreme value and updating after copying, crossing and mutation operations in the genetic algorithm in the step (4), updating after comparing the fitness value of the individual extreme value with the fitness value of the global extreme value, and repeating the steps (3) to (5) until the iteration times reach the standard or the objective function reaches the convergence precision.
(6) And (5) after the algorithm is finished, substituting the weight value and the threshold value of the BP neural network corresponding to the global optimal solution into the neural network to complete the construction of the BIM building energy consumption prediction module in the region.
(7) And (4) based on the energy consumption training sample sets of the buildings in different types of areas, operating according to the steps (1) to (6), and constructing various BIM building energy consumption prediction modules in the areas.
Step five: and (3) constructing a future climate and building parameter BP neural network prediction module in a region of 1 square kilometer around the Ministry of Haerbin construction in the Nangang district of Harbin city, and predicting various BIM building energy consumption and total building energy consumption in the region.
And constructing a future climate and building parameter prediction module of the area in the GH platform by applying Python programming based on the statistical results of the building envelope parameters, the indoor equipment parameters, the climate parameters and the building geometric parameters and the BP neural network. Considering the relevance of four types of statistical input parameters, two BP neural network prediction modules are constructed, wherein one is a climate parameter, a building geometric parameter, a time parameter and an indoor equipment parameter, the envelope parameter is mapped to the BP neural network module, the other is an envelope parameter, an indoor equipment parameter, a time parameter and an envelope parameter, the climate parameter is mapped to the BP neural network module, and the two modules are combined to obtain a future regional climate and building parameter BP neural network prediction combination module of the region (the basic prediction frame is shown in the figure).
The prediction of the future climate and four types of sensitive building parameters of the area based on the time parameters and the four types of building parameters can be realized through the combined module, the prediction result is placed into various BIM building typical model energy consumption prediction modules based on the improved PSO-GA-BP neural network, the prediction of various BIM building energy consumption is realized, and the total energy consumption of the area can be estimated according to the proportion of the building total area of the area occupied by the building typical models.
The construction of the climate and building parameter prediction combination module for the 1-square-kilometer future area around the institute of architecture of Hadamard building based on the BP neural network comprises the following steps:
(1) determining sensitivity design parameters in the building envelope parameters as E, sensitivity design parameters of S in the indoor equipment parameters, sensitivity design parameters of F in the climate parameters, energy consumption sensitivity design parameters of D in the building geometric parameters and time parameters, and constructing a BP neural network training set;
(2) determining climate parameters, building geometric parameters and indoor equipment parameters, mapping the envelope parameters to a basic structure of a BP neural network to be three-layer neurons, wherein the number of neuron nodes of an input layer is D + F +1, and the neuron nodes are:
wherein,
f sensitivity design parameters in climate parameters, D energy consumption sensitivity design parameters in building geometric parameters and time parameters are respectively set;
(3) determining the number of neuron nodes of an output layer as E + S +1, wherein the neuron nodes are as follows:
wherein
Respectively designing E sensitivity design parameters in the parameters of the enclosure structure, S sensitivity design parameters in the parameters of the indoor equipment and time parameters;
(4) number of hidden layer neuron nodes is NhiAnd the neuron nodes satisfy: n is a radical ofhiSqrt (n + p) + a, where a is a constant between 1 and 10;
(5) updating the weight of the neural network node, and then using a gradient descent method to the connection weight omega of the new generation neural network according to the formula and the operation mode of the BP neural networki1，ωj2Updating is carried out;
(6) updating the neural network node threshold value to complete the new generation of the neural network threshold value, and updating the neural network;
(7) repeating the steps (5) and (6) until the iteration times reach the standard or the target function reaches the convergence precision, and obtaining a climate parameter, a building geometric parameter, a time parameter, an indoor equipment parameter and an envelope parameter BP neural network module;
(8) and (4) constructing a BP neural network module based on the steps (6) and (7) to generate a prediction module of future climate and building parameters of the Nangang district, and realizing the prediction of the energy consumption of the regional building based on the predicted future climate and building design parameters of the region by inputting four types of sensitive building design parameters (indoor equipment parameters, building envelope parameters, climate parameters and building geometric parameters) and the future year.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the invention, "plurality" means two or more unless explicitly defined otherwise.
In the present invention, unless otherwise specifically stated or limited, the terms "mounted," "connected," "fixed," and the like are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, "above" or "below" a first feature means that the first and second features are in direct contact, or that the first and second features are not in direct contact but are in contact with each other via another feature therebetween. Also, the first feature being "on," "above" and "over" the second feature includes the first feature being directly on and obliquely above the second feature, or merely indicating that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature includes the first feature being directly above and obliquely above the second feature, or simply meaning that the first feature is at a lesser level than the second feature.
In the description herein, reference to the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention.
Claims (5)
1. A regional building energy consumption prediction method under a BIM environment comprises the following steps:
A. building various BIM building typical models based on the actually measured and researched areas;
B. establishing a coupling model between a climate simulation platform and a building energy consumption simulation platform, and completing the simulation of various building energy consumption by inputting climate parameters and various building typical model design parameters;
C. constructing a data interaction program, carrying out regional building energy consumption design parameter sensitivity analysis based on a progressive gradient regression tree algorithm, and determining input parameters of an improved PSO-GA-BP neural network;
D. constructing various BIM building typical model energy consumption prediction modules in the region based on an improved PSO-GA-BP neural network;
E. and (3) constructing a future regional climate and building parameter BP neural network prediction module, and predicting various BIM building energy consumption and regional building total energy consumption in a region.
2. The method for predicting the regional building energy consumption of the improved PSO-GA-BP neural network in the BIM environment according to claim 1, characterized in that: the step A comprises the following steps:
(1) based on field investigation and investigation, carrying out manual statistics on the types of regional buildings, the parameters of the enclosure structure and the parameters of indoor equipment, wherein the types of the regional buildings comprise regional residential buildings, regional office buildings, regional industrial buildings and regional commercial buildings;
(2) the building envelope parameters comprise a roof heat transfer coefficient, an outer wall heat transfer coefficient, an outer window heat transfer coefficient and an outer window shading coefficient, and the data can be obtained by counting the building envelope type and looking up data to obtain corresponding values;
(3) the indoor equipment parameters comprise personnel density, fresh air index, illumination power and equipment power, and the data can be obtained by consulting regional public building energy-saving design standards to obtain corresponding values; obtaining the proportion of buildings in various regions based on the statistical region building types;
(4) and constructing various BIM building typical models of the region based on the statistical geometric parameters of the region building, the building envelope parameters and the building indoor equipment setting parameters.
3. The method for predicting the energy consumption of the regional building in the BIM environment according to claim 1, wherein the method comprises the following steps: the step B comprises the following steps:
(1) the value ranges of the experiment variable enclosure structure parameters, the building geometric parameters and the indoor equipment parameters are based on manual statistics of the exchange and research area parameters; the climate parameters are based on statistics of historical climate parameters for the region;
(2) the energy consumption simulation result comprises a winter heating energy consumption value, a summer refrigeration energy consumption value, a lighting energy consumption value and a total annual energy consumption value of the building, and the energy consumption simulation values of various buildings in the area can reflect typical model information and regional climate information of various BIM buildings in the area.
4. The method for predicting the energy consumption of the regional building in the BIM environment according to claim 1, wherein the method comprises the following steps: the step D comprises the following steps:
(1) constructing a basic BP neural network model;
(2) initializing each variable setting of the particle swarm m;
(3) calculating the fitness value of the particle swarm, and calculating the fitness value and the best position p passed by the fitness value in each particle swarmbestComparing to determine the global best position;
(4) after each update, the copy, cross and variation operations of the genetic algorithm can be introduced to the population with moderate particle population adaptation, and the variation probability is used for the particle population with poor adaptation degree to operate;
(5) updating the individual extreme value and the global extreme value of the particle swarm, comparing the current fitness value of the particle with the fitness value of the individual extreme value and updating after copying, crossing and variation operations in the genetic algorithm of the step (4), updating after comparing the fitness value of the individual extreme value with the fitness value of the global extreme value, and repeating the steps (3) to (5) until the iteration times reach the standard or the objective function reaches the convergence precision;
(6) after the algorithm is finished, substituting the weight value and the threshold value of the BP neural network corresponding to the global optimal solution into the neural network to complete the construction of the BIM building energy consumption prediction module of the region;
(7) and (4) based on the energy consumption training sample sets of different types of regional buildings, operating according to the steps (1) to (6), and constructing various BIM building energy consumption prediction modules of the regions.
5. The method for predicting the energy consumption of the regional building in the BIM environment according to claim 1, wherein the method comprises the following steps: the step E comprises the following steps:
(1) determining sensitivity design parameters in the parameters of the enclosure structure as E, sensitivity design parameters in the parameters of the indoor equipment as S, sensitivity design parameters in the climate parameters as F, energy consumption sensitivity design parameters in the geometric parameters of the building as D and time parameters, and constructing a BP neural network training set;
(2) determining climate parameters, building geometric parameters and indoor equipment parameters, mapping the envelope parameters to a basic structure of a BP neural network to be three-layer neurons, wherein the number of the neuron nodes of an input layer is NinThe neuron nodes are:
wherein,
respectively designing F sensitivity design parameters in climate parameters, and D energy consumption sensitivity design parameters and time parameters in building geometric parameters;
(3) determining number of output layer neuron nodes to be NoutThe neural nodes are:
wherein,
respectively designing E sensitivity design parameters in the parameters of the enclosure structure, and S sensitivity design parameters and time parameters in the parameters of the indoor equipment;
(4) hidden layerNumber of neuron nodes is NhiAnd the neuron nodes satisfy: n is a radical ofhiSqrt (n + p) + a, where a is a constant between 1 and 10;
(5) updating the weight of the neural network node, and then using a gradient descent method to the connection weight omega of the new generation neural network according to the formula and the operation mode of the BP neural networki1，ωj2Updating is carried out;
(6) updating the neural network node threshold value to complete the new generation of the neural network threshold value, and updating the neural network;
(7) repeating the steps (5) and (6) until the iteration times reach the standard or the target function reaches the convergence precision, and obtaining a climate parameter, a building geometric parameter, a time parameter, an indoor equipment parameter and an envelope parameter BP neural network module;
(8) and (3) constructing a BP neural network module based on the steps (6) and (7) to generate a prediction module of future regional climate and building parameters, realizing prediction of the regional future climate and building design parameters by inputting 4 types of sensitive building design parameters (sensitive indoor equipment parameters, sensitive enclosure structure parameters, sensitive climate parameters and sensitive building geometric parameters) and the future year, and realizing prediction of regional building energy consumption based on the predicted regional future climate and building design parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375174.5A CN111310257A (en) | 2019-12-27 | 2019-12-27 | Regional building energy consumption prediction method under BIM environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911375174.5A CN111310257A (en) | 2019-12-27 | 2019-12-27 | Regional building energy consumption prediction method under BIM environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111310257A true CN111310257A (en) | 2020-06-19 |
Family
ID=71145280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911375174.5A Withdrawn CN111310257A (en) | 2019-12-27 | 2019-12-27 | Regional building energy consumption prediction method under BIM environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310257A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329113A (en) * | 2020-11-13 | 2021-02-05 | 杭州绿锦建筑设计咨询有限公司 | Building energy-saving design method, system, device and storage medium based on BIM |
| CN112712213A (en) * | 2021-01-15 | 2021-04-27 | 上海交通大学 | Method and system for predicting energy consumption of deep migration learning of centralized air-conditioning house |
| CN113850412A (en) * | 2021-08-18 | 2021-12-28 | 华建数创(上海)科技有限公司 | Method for predicting regional energy consumption in building based on bim model and graph convolution neural network |
| CN113987306A (en) * | 2021-11-03 | 2022-01-28 | 广东工业大学 | City block energy consumption time-varying graph set construction method, device, equipment and storage medium |
| CN114239972A (en) * | 2021-12-20 | 2022-03-25 | 广州汇锦能效科技有限公司 | Campus energy efficiency and electrical safety management method and system based on artificial intelligence technology |
| CN114611201A (en) * | 2022-05-12 | 2022-06-10 | 北京中建协认证中心有限公司 | Multi-objective energy-saving optimization method and system for future climate building |
-
2019
- 2019-12-27 CN CN201911375174.5A patent/CN111310257A/en not_active Withdrawn
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112329113A (en) * | 2020-11-13 | 2021-02-05 | 杭州绿锦建筑设计咨询有限公司 | Building energy-saving design method, system, device and storage medium based on BIM |
| CN112712213A (en) * | 2021-01-15 | 2021-04-27 | 上海交通大学 | Method and system for predicting energy consumption of deep migration learning of centralized air-conditioning house |
| CN112712213B (en) * | 2021-01-15 | 2023-07-04 | 上海交通大学 | Method and system for predicting deep migration learning energy consumption of concentrated air conditioning house |
| CN113850412A (en) * | 2021-08-18 | 2021-12-28 | 华建数创(上海)科技有限公司 | Method for predicting regional energy consumption in building based on bim model and graph convolution neural network |
| CN113987306A (en) * | 2021-11-03 | 2022-01-28 | 广东工业大学 | City block energy consumption time-varying graph set construction method, device, equipment and storage medium |
| CN114239972A (en) * | 2021-12-20 | 2022-03-25 | 广州汇锦能效科技有限公司 | Campus energy efficiency and electrical safety management method and system based on artificial intelligence technology |
| CN114611201A (en) * | 2022-05-12 | 2022-06-10 | 北京中建协认证中心有限公司 | Multi-objective energy-saving optimization method and system for future climate building |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111310257A (en) | Regional building energy consumption prediction method under BIM environment | |
| Deng et al. | AutoBPS: A tool for urban building energy modeling to support energy efficiency improvement at city-scale | |
| Wang et al. | From simulation to data-driven approach: A framework of integrating urban morphology to low-energy urban design | |
| Li et al. | A review of operational energy consumption calculation method for urban buildings | |
| CN114692265B (en) | Zero-carbon building optimization design method based on deep reinforcement learning | |
| CN106651036A (en) | Air quality forecasting system | |
| Guo et al. | Prediction of heating and cooling loads based on light gradient boosting machine algorithms | |
| CN111210082A (en) | Optimized BP neural network algorithm-based precipitation prediction method | |
| Liu et al. | A multi-objective optimization framework for designing urban block forms considering daylight, energy consumption, and photovoltaic energy potential | |
| CN111159884A (en) | Cold region office building energy-saving design decision support system and method | |
| Liu et al. | Building information modelling-enabled multi-objective optimization for energy consumption parametric analysis in green buildings design using hybrid machine learning algorithms | |
| CN116205425A (en) | Low-carbon park cold-hot electric load prediction method based on typical database | |
| Song et al. | Framework on low-carbon retrofit of rural residential buildings in arid areas of northwest China: A case study of Turpan residential buildings | |
| CN115329425A (en) | Air quality driven building group form optimization design method and system | |
| CN117332971A (en) | Regional comprehensive energy planning method and system considering city morphology | |
| CN115879652B (en) | Hierarchical collaborative planning method and device for energy network, electronic equipment and storage medium | |
| Nzengue et al. | Planning city refurbishment: An exploratory study at district scale how to move towards positive energy districts–approach of the SINFONIA project | |
| Shen et al. | Utilizing interpretable stacking ensemble learning and NSGA-III for the prediction and optimisation of building photo-thermal environment and energy consumption | |
| CN117291302A (en) | Method for predicting energy consumption hybrid model of underground building internal equipment | |
| CN115660338A (en) | Typical building cooling, heating and power load model construction method for southwest border area | |
| CN115187133A (en) | Traditional residential building operation phase carbon emission accounting method based on dynamic monitoring | |
| CN113254554A (en) | Urban block heat island modeling method and system based on map capture and cluster learning | |
| CN112712213A (en) | Method and system for predicting energy consumption of deep migration learning of centralized air-conditioning house | |
| CN112418668A (en) | Natural gas distributed energy resource area user cooling, heating and power load prediction method and system | |
| Yechao et al. | Integrated Strategy of Green Building Model Optimization Based on BIM Technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200619 |