CN116796406A - Building energy consumption optimization method based on artificial neural network and BIM - Google Patents
Building energy consumption optimization method based on artificial neural network and BIM Download PDFInfo
- Publication number
- CN116796406A CN116796406A CN202310741819.2A CN202310741819A CN116796406A CN 116796406 A CN116796406 A CN 116796406A CN 202310741819 A CN202310741819 A CN 202310741819A CN 116796406 A CN116796406 A CN 116796406A
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- building
- data
- building energy
- 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.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 56
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 239000011521 glass Substances 0.000 claims description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 4
- 229910052799 carbon Inorganic materials 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000013433 optimization analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Structural Engineering (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Civil Engineering (AREA)
- Medical Informatics (AREA)
- Pure & Applied Mathematics (AREA)
- Architecture (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a building energy consumption optimization method based on an artificial neural network and BIM, which relates to the technical field of buildings and comprises the following steps: s1, collecting data affecting building energy consumption; s2, calculating the acquired data to obtain a clustering center of building energy consumption data and attribution conditions of all pieces of data; and S3, taking the obtained clustering center of the energy consumption data as an implicit node of the artificial neural network, and calculating a constant matrix of the implicit node to obtain all information of an implicit layer of the artificial neural network. According to the building energy consumption optimization method based on the artificial neural network and the BIM, due to the self-adaptive characteristic of the clustering method, the clustering center number does not need to be designated in advance, so that the hidden layer node information of the RBF is determined by adopting an AP clustering algorithm, the effectiveness and feasibility of a model are improved, the building energy consumption data can be rapidly analyzed and predicted, and errors caused by different data dimensionalities and numerical ranges in different building energy consumption data sets are reduced.
Description
Technical Field
The invention relates to the technical field of buildings, in particular to a building energy consumption optimization method based on an artificial neural network and BIM.
Background
Along with the increasing of building energy consumption, the influence of carbon emission on the environment is more and more serious, so that the analysis and prediction of the building energy consumption are particularly important to realize energy conservation and emission reduction by reducing the building energy consumption.
The traditional building energy consumption simulation is mainly performed on energy consumption simulation software, the optimization analysis speed is low, and an effective prediction model is difficult to obtain during modeling, so that the scheme effect of energy consumption optimization is poor.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a building energy consumption optimization method based on an artificial neural network and BIM, which solves the problems that the traditional building energy consumption simulation is difficult to obtain an effective prediction model, so that the scheme effect of energy consumption optimization is poor.
In order to achieve the above purpose, the invention is realized by the following technical scheme: the building energy consumption optimization method based on the artificial neural network and the BIM comprises the following steps:
s1, collecting data affecting building energy consumption;
s2, calculating the acquired data to obtain a clustering center of building energy consumption data and attribution conditions of all pieces of data;
s3, taking the obtained clustering center of the energy consumption data as an implicit node of the artificial neural network, and calculating a constant matrix of the implicit node to obtain all information of an implicit layer of the artificial neural network;
s4, initializing a weight matrix for connecting an input layer and an hidden layer in the artificial neural network, inputting building energy consumption training data to train the network until the training iteration number reaches an upper limit or the training error is within an allowable range, ending the training, and finally obtaining a prediction model;
s5, inputting building energy consumption test data, and evaluating generalization capability of the obtained prediction model through predicting heat load and cold load;
s6, analyzing factors of the enclosure structure affecting the energy consumption of the building, and providing a building scheme for reducing the heat load and the cold load of the building so as to achieve the aim of reducing the carbon emission.
Preferably, in the step S1, the data affecting the energy consumption of the building includes relative compactness of the building, surface area of the building, wall area, roof, total height of the building, direction of the building, area of the glass window, and area distribution of the glass window.
Preferably, in the step S2, the clustering center and the attribution condition of each piece of data are obtained by adopting the following formula:
C i =argmin(x i -u j )
wherein x is input data, u is a cluster center, and for each, u j For each cluster center, for each cluster center u j And performing updating iteration until a final clustering result is obtained.
Preferably, in the step S3, a formula for calculating the constant matrix of the hidden node is as follows:
wherein f (x) is an activation function, A k Output value of kth hidden layer node, w 1 To connect the weight matrix of the input layer and the hidden layer, beta k Is the threshold for the hidden layer node.
Preferably, in the step S4, when training the building energy consumption training data on the network, the weight matrix w is adjusted by means of error back propagation, so as to find an optimal solution of the prediction model, improve the generalization ability of the model, and find an optimal solution according to the following formula:
wherein t is k Is the threshold value of the output layer node, w 2 As a weight matrix, obtaining the error E of a single sample by the method i .
Preferably, after the single training error is trained, the weight matrix is updated, and the update formula is as follows:
wherein, alpha is learning rate, when alpha value is smaller than E i And (3) ending training to obtain a prediction model when the error value of the model is detected.
The invention provides a building energy consumption optimization method based on an artificial neural network and BIM, which has the following beneficial effects compared with the prior art:
according to the building energy consumption optimization method based on the artificial neural network and the BIM, due to the self-adaptive characteristic of the clustering method, the clustering center number does not need to be designated in advance, so that the hidden layer node information of the RBF is determined by adopting an AP clustering algorithm, the effectiveness and feasibility of a model are improved, the building energy consumption data can be rapidly analyzed and predicted, errors caused by different data dimensionalities and numerical ranges in different building energy consumption data sets are reduced, the influence of abnormal values on the model is effectively reduced, the training speed of the model is effectively improved, and the fitting effect of the model is optimized.
Drawings
FIG. 1 is a block flow diagram of the method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a technical solution: the building energy consumption optimization method based on the artificial neural network and the BIM comprises the following steps:
s1, collecting data affecting building energy consumption;
s2, calculating the acquired data to obtain a clustering center of building energy consumption data and attribution conditions of all pieces of data;
s3, taking the obtained clustering center of the energy consumption data as an implicit node of the artificial neural network, and calculating a constant matrix of the implicit node to obtain all information of an implicit layer of the artificial neural network;
s4, initializing a weight matrix for connecting an input layer and an hidden layer in the artificial neural network, inputting building energy consumption training data to train the network until the training iteration number reaches an upper limit or the training error is within an allowable range, ending the training, and finally obtaining a prediction model;
s5, inputting building energy consumption test data, and evaluating generalization capability of the obtained prediction model through predicting heat load and cold load;
s6, analyzing factors of the enclosure structure affecting the energy consumption of the building, and providing a building scheme for reducing the heat load and the cold load of the building so as to achieve the aim of reducing the carbon emission.
In the embodiment of the present invention, in step S1, the data affecting the energy consumption of the building includes the relative compactness of the building, the surface area of the building, the wall surface area, the roof, the total height of the building, the direction of the building, the area of the glass window, and the area distribution of the glass window.
In the embodiment of the present invention, in step S2, the following formula is adopted to obtain the clustering center and the attribution condition of each piece of data, where the formula is as follows:
C i =argmin(x i -u j )
wherein x is input data, u is a cluster center, and for each, u j For each cluster center, for each cluster center u j And performing updating iteration until a final clustering result is obtained.
In the embodiment of the present invention, in step S3, the formula for calculating the constant matrix of the hidden node is as follows:
wherein f (x) is an activation function, A k Output value of kth hidden layer node, w 1 To connect the weight matrix of the input layer and the hidden layer, beta k Is the threshold for the hidden layer node.
In the embodiment of the present invention, in step S4, when training the building energy consumption training data on the network, the weight matrix w is adjusted by means of error back propagation, so as to find the optimal solution of the prediction model, and improve the generalization capability of the model, and the formula for finding the optimal solution is as follows:
wherein t is k Is the threshold value of the output layer node, w 2 As a weight matrix, obtaining the error E of a single sample by the method i .
In the embodiment of the invention, after training out the single training error, the weight matrix is updated, and the updating formula is as follows:
wherein, alpha is learning rate, when alpha value is smaller than E i And (3) ending training to obtain a prediction model when the error value of the model is detected.
And all that is not described in detail in this specification is well known to those skilled in the art.
Claims (6)
1. The building energy consumption optimization method based on the artificial neural network and the BIM is characterized by comprising the following steps of: the method comprises the following steps:
s1, collecting data affecting building energy consumption;
s2, calculating the acquired data to obtain a clustering center of building energy consumption data and attribution conditions of all pieces of data;
s3, taking the obtained clustering center of the energy consumption data as an implicit node of the artificial neural network, and calculating a constant matrix of the implicit node to obtain all information of an implicit layer of the artificial neural network;
s4, initializing a weight matrix for connecting an input layer and an hidden layer in the artificial neural network, inputting building energy consumption training data to train the network until the training iteration number reaches an upper limit or the training error is within an allowable range, ending the training, and finally obtaining a prediction model;
s5, inputting building energy consumption test data, and evaluating generalization capability of the obtained prediction model through predicting heat load and cold load;
s6, analyzing factors of the enclosure structure affecting the energy consumption of the building, and providing a building scheme for reducing the heat load and the cold load of the building so as to achieve the aim of reducing the carbon emission.
2. The building energy consumption optimization method based on the artificial neural network and the BIM according to claim 1, wherein: in the step S1, the data affecting the energy consumption of the building include the relative compactness of the building, the surface area of the building, the wall surface area, the roof, the total height of the building, the building direction, the area of the glass window and the area distribution of the glass window.
3. The building energy consumption optimization method based on the artificial neural network and the BIM according to claim 1, wherein: in the step S2, the following formula is adopted to obtain the clustering center and the attribution condition of each piece of data, and the formula is as follows:
C i =argmin(x i -u j )
wherein x is input data, u is a cluster center, and for each, u j For each cluster center, for each cluster center u j And performing updating iteration until a final clustering result is obtained.
4. The building energy consumption optimization method based on the artificial neural network and the BIM according to claim 1, wherein: in the step S3, the formula for calculating the constant matrix of the hidden node is as follows:
wherein f (x) is an activation function, A k For the kth hidden layer sectionOutput value of point, w 1 To connect the weight matrix of the input layer and the hidden layer, beta k Is the threshold for the hidden layer node.
5. The building energy consumption optimization method based on the artificial neural network and the BIM according to claim 1, wherein: in the step S4, when training the building energy consumption training data on the network, the weight matrix w is adjusted by means of error back propagation, so as to find the optimal solution of the prediction model, improve the generalization capability of the model, and find the optimal solution according to the following formula:
wherein t is k Is the threshold value of the output layer node, w 2 As a weight matrix, obtaining the error E of a single sample by the method i。
6. The building energy consumption optimization method based on the artificial neural network and the BIM according to claim 5, wherein the building energy consumption optimization method is characterized by comprising the following steps of: after the single training error is trained, the weight matrix is updated according to the following update formula:
wherein, alpha is learning rate, when alpha value is smaller than E i And (3) ending training to obtain a prediction model when the error value of the model is detected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310741819.2A CN116796406A (en) | 2023-06-21 | 2023-06-21 | Building energy consumption optimization method based on artificial neural network and BIM |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310741819.2A CN116796406A (en) | 2023-06-21 | 2023-06-21 | Building energy consumption optimization method based on artificial neural network and BIM |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116796406A true CN116796406A (en) | 2023-09-22 |
Family
ID=88039200
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310741819.2A Pending CN116796406A (en) | 2023-06-21 | 2023-06-21 | Building energy consumption optimization method based on artificial neural network and BIM |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116796406A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117634006A (en) * | 2024-01-26 | 2024-03-01 | 新疆三联工程建设有限责任公司 | BIM technology-based sleeve embedded engineering management system and method |
-
2023
- 2023-06-21 CN CN202310741819.2A patent/CN116796406A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117634006A (en) * | 2024-01-26 | 2024-03-01 | 新疆三联工程建设有限责任公司 | BIM technology-based sleeve embedded engineering management system and method |
CN117634006B (en) * | 2024-01-26 | 2024-04-26 | 新疆三联工程建设有限责任公司 | BIM technology-based sleeve embedded engineering management system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108900346B (en) | Wireless network flow prediction method based on LSTM network | |
CN110363344B (en) | Probability integral parameter prediction method for optimizing BP neural network based on MIV-GP algorithm | |
CN111598224B (en) | Air conditioner cold load prediction method for optimizing BP neural network based on simulated annealing algorithm | |
CN108399470B (en) | Indoor PM2.5 prediction method based on multi-example genetic neural network | |
CN116796406A (en) | Building energy consumption optimization method based on artificial neural network and BIM | |
CN112085254A (en) | Prediction method and model based on multi-fractal cooperative measurement gating cycle unit | |
CN115374995A (en) | Distributed photovoltaic and small wind power station power prediction method | |
CN112363896A (en) | Log anomaly detection system | |
CN112700326A (en) | Credit default prediction method for optimizing BP neural network based on Grey wolf algorithm | |
CN111667189A (en) | Construction engineering project risk prediction method based on one-dimensional convolutional neural network | |
CN109543914B (en) | Method for predicting RBF building operation energy consumption based on AP clustering algorithm | |
CN112149883A (en) | Photovoltaic power prediction method based on FWA-BP neural network | |
CN113743538A (en) | Intelligent building energy consumption prediction method, equipment and medium based on IPSO-BP neural network | |
CN117909888B (en) | Intelligent artificial intelligence climate prediction method | |
CN113239654B (en) | IGBT remaining life prediction method based on FIG and IPSO algorithm | |
CN113868765A (en) | Ship main scale parameter optimization method based on approximate model | |
CN117668743A (en) | Time sequence data prediction method of association time-space relation | |
CN115310727B (en) | Building cooling, heating and power load prediction method and system based on transfer learning | |
CN103983332A (en) | Method for error compensation of sensor based on HGSA-BP algorithm | |
CN116415713A (en) | Building energy consumption prediction method based on E+ and artificial intelligence | |
CN113177675A (en) | Air conditioner cold load prediction method based on optimization neural network of longicorn group algorithm | |
CN115796327A (en) | Wind power interval prediction method based on VMD (vertical vector decomposition) and IWOA-F-GRU (empirical mode decomposition) -based models | |
CN113188243B (en) | Comprehensive prediction method and system for air conditioner energy consumption | |
CN115330085A (en) | Wind speed prediction method based on deep neural network and without future information leakage | |
CN114862007A (en) | Short-period gas production rate prediction method and system for carbonate gas well |
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 |