CN111426344B - Building energy consumption intelligent detection system - Google Patents

Building energy consumption intelligent detection system Download PDF

Info

Publication number
CN111426344B
CN111426344B CN202010201101.0A CN202010201101A CN111426344B CN 111426344 B CN111426344 B CN 111426344B CN 202010201101 A CN202010201101 A CN 202010201101A CN 111426344 B CN111426344 B CN 111426344B
Authority
CN
China
Prior art keywords
energy consumption
building
neural network
temperature
output
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.)
Active
Application number
CN202010201101.0A
Other languages
Chinese (zh)
Other versions
CN111426344A (en
Inventor
陈亚娟
罗灏
马从国
丁晓红
马海波
王建国
金德飞
张利兵
李广浩
丁百湛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujian Tangtou Construction Engineering Group Co.,Ltd.
Yuwang Construction Engineering Group Co ltd
Fuzhou University
Original Assignee
Huaiyin Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huaiyin Institute of Technology filed Critical Huaiyin Institute of Technology
Priority to CN202010201101.0A priority Critical patent/CN111426344B/en
Publication of CN111426344A publication Critical patent/CN111426344A/en
Application granted granted Critical
Publication of CN111426344B publication Critical patent/CN111426344B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • 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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses an intelligent detection system for building energy consumption, which is characterized in that: the system comprises a building energy consumption parameter acquisition platform based on a wireless sensor network and a building energy consumption grade classification system, wherein the building energy consumption parameter acquisition platform based on the wireless sensor network realizes the detection and monitoring of parameters affecting the environment of a building, and the building energy consumption grade classification system comprises a temperature detection module, a illuminance detection module, a humidity detection module, an energy consumption prediction module and an interval number kohonen neural network building energy consumption state classifier; the invention effectively solves the problems that the energy consumption of the existing building does not have the characteristics of nonlinearity, large hysteresis, complicated influence on the energy consumption change of the building and the like according to the change of the environmental factors of the building, and the energy consumption of the building is intelligently detected, so that the accuracy of the detection of the building is greatly influenced.

Description

Building energy consumption intelligent detection system
Technical Field
The invention relates to the technical field of building energy consumption automation equipment, in particular to an intelligent building energy consumption detection system.
Background
The building energy consumption analysis is one of research hotspots in the field of building energy conservation, is the basis for realizing a reasonable energy-saving scheme, and is a precondition for realizing the optimized operation of building energy consumption equipment. According to the characteristics of the building, a prediction model influencing the reflection of the energy consumption change of the building is established. The accurate building energy consumption prediction model can predict and master the building energy consumption condition in advance, provides basis for a scheduling strategy of energy supply equipment, realizes energy supply according to needs, and can better promote the building energy saving work. Therefore, the building energy can be planned in advance, and the national energy policy is better implemented. The invention discloses an intelligent detection system for building energy consumption according to building environmental factors influencing the building energy consumption and historical data of the building energy consumption.
Disclosure of Invention
The invention provides an intelligent detection system for building energy consumption, which effectively solves the problem that the energy consumption of the existing building is not intelligently detected according to the characteristics of nonlinearity, large hysteresis, complex energy consumption change influence on the building and the like of the change of environmental factors of the building, so that the detection accuracy of the building can be greatly influenced.
The invention is realized by the following technical scheme:
an intelligent building energy consumption detection system is composed of a wireless sensor network-based building energy consumption parameter acquisition platform and a building energy consumption grade classification system, wherein the wireless sensor network-based building energy consumption parameter acquisition platform is used for detecting and monitoring parameters influencing the environment of a building, and the building energy consumption grade classification system is composed of a temperature detection module, a light illumination detection module, a humidity detection module, an energy consumption prediction module and an interval number kohonen neural network building energy consumption state classifier; the outputs of the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module are used as the inputs of the section number kohonen neural network building energy consumption state classifier, the output of the section number kohonen neural network building energy consumption state classifier is the section number representing the energy consumption grade of the detected building, and the building energy consumption grade classification system realizes the detection, prediction and classification of the building energy consumption grade.
The invention further adopts the technical improvement scheme that:
the temperature detection module consists of a temperature interval number neural network model, 2 temperature subtraction cluster classifiers, 2 groups of a plurality of Elman neural network temperature prediction models and 2 temperature GM (1,1) grey prediction models, the output of a plurality of detection point temperature sensors is used as the input of the temperature interval number neural network model, the upper limit value and the lower limit value of the output interval number of the temperature interval number neural network model are respectively used as the input of the 2 corresponding temperature subtraction cluster classifiers, the upper limit value and the lower limit value of the 2 groups of a plurality of types of temperature intervals output by the 2 temperature subtraction cluster classifiers are respectively used as the input of the 2 groups of a plurality of Elman neural network temperature prediction models, the output of the 2 groups of a plurality of Elman neural network temperature prediction models is respectively used as the input of the 2 corresponding temperature GM (1,1) grey prediction models, and the output of the 2 temperature GM (1,1) grey prediction models is used as the output of the temperature detection module and the interval number kohonen neural network building energy consumption state component And inputting the classifier.
The invention further adopts the technical improvement scheme that:
the energy consumption prediction module consists of an energy consumption subtraction cluster classifier, a plurality of Elman neural network energy consumption prediction models, an energy consumption GM (1,1) gray prediction model, a Jordan neural network energy consumption residual prediction model, 2 beat delay line-based TDL (delay line-based histogram) and an interval number RBF (radial basis function) neural network, building energy consumption historical data serve as the input of the energy consumption subtraction cluster classifier, a plurality of types of building energy consumption historical data output by the energy consumption subtraction cluster classifier respectively serve as the input of the corresponding Elman neural network energy consumption prediction models, the output of the Elman neural network energy consumption prediction models serve as the input of the energy consumption GM (1,1) gray prediction model, the difference between the building energy consumption historical data and the energy consumption GM (1,1) gray prediction model serves as the input of the Jordan neural network energy consumption residual prediction model, and the output of the energy consumption GM (1,1) gray prediction model and the Jordan neural network residual prediction model respectively serve as the input of the 2 beat delay line-based TDL And the output of the 2 beat-to-beat delay lines TDL is used as the input of an interval number RBF neural network, and the output of the interval number RBF neural network is used as the output of an energy consumption prediction module and the input of an interval number kohonen neural network building energy consumption state classifier.
The invention further adopts the technical improvement scheme that:
the input of the section number kohonen neural network building energy consumption state classifier is the section number output by the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module, and the output of the section number kohonen neural network building energy consumption state classifier is the section number representing the energy consumption grade of the detected building; according to the influence of meteorological parameters of the building on the energy consumption of the building, engineering practice of historical data of the energy consumption of the building and civil building energy conservation regulations, a corresponding relation table of 5 interval numbers and 5 energy consumption levels of the building is built by an interval number kohonen neural network building energy consumption state classifier, the energy consumption state of the building to be detected is divided into 5 different interval numbers of low, normal, high and high 5 energy consumption levels, the similarity between the interval number output by the interval number kohonen neural network building energy consumption state classifier and the 5 interval numbers representing the 5 different levels of the energy consumption of the building is calculated, and the building energy consumption level corresponding to the interval number with the maximum similarity is determined as the energy consumption level of the building.
The invention further adopts the technical improvement scheme that:
the temperature interval number neural network model consists of a plurality of RR time recurrent neural networks, the interval number wavelet neural network comprises an interval number wavelet neural network and 2 beat Delay lines TDL (tapped Delay line), wherein the interval number wavelet neural network converts a plurality of temperature sensors of a building in a period of time to a dynamic interval numerical value of the temperature of the building, the output of each temperature sensor at each detection point is the input of the corresponding RR time recurrent neural network, the output of the RR time recurrent neural network is used as the input of the interval number wavelet neural network, the output of 2 beat Delay lines TDL is used as the input of the interval number wavelet neural network, the output of the interval number wavelet neural network is the output of a temperature interval number neural network model and the interval number formed by the upper limit value and the lower limit value representing the temperature of the building in the period of time, and the upper limit value and the lower limit value of the output interval number of the interval number wavelet neural network are respectively used as the input of the corresponding 2 beat Delay lines TDL.
The invention further adopts the technical improvement scheme that:
the illuminance detection module consists of an illuminance interval number neural network model, 2 illuminance subtraction cluster classifiers, 2 groups of a plurality of Elman neural network illuminance prediction models and 2 illuminance GM (1,1) gray prediction models, and the output of the illuminance detection module is used as the input of the interval number kohonen neural network building energy consumption state classifier.
The invention further adopts the technical improvement scheme that:
the humidity detection module consists of a humidity interval number neural network model, 2 humidity subtraction cluster classifiers, 2 groups of a plurality of Elman neural network humidity prediction models and 2 humidity GM (1,1) gray prediction models, and the output of the humidity detection module is used as the input of the interval number kohonen neural network building energy consumption state classifier.
The invention further adopts the technical improvement scheme that:
the building energy consumption parameter acquisition platform based on the wireless sensor network consists of a detection node, a control node and a field monitoring end, wherein the detection node, the control node and the field monitoring end construct a building environment parameter acquisition and building energy consumption intelligent prediction system through a wireless communication module NRF2401 in a self-organizing manner, the detection node respectively consists of a sensor group module, a single chip microcomputer MSP430 and a wireless communication module NRF2401, the sensor group module is responsible for detecting temperature, illuminance, wind speed and humidity parameters of the building environment parameters, and the single chip microcomputer controls sampling intervals and sends the parameters to the field monitoring end through the wireless communication module NRF 2401; the control node realizes control of the adjusting equipment of the building environmental parameters; the on-site monitoring end consists of an industrial control computer, and realizes the management of detecting the environmental parameters of the building by the detection nodes and the early warning of the energy consumption of the building.
The invention further adopts the technical improvement scheme that:
the functional structures of the illuminance detection module and the humidity detection module and the temperature detection module have similar characteristics
Compared with the prior art, the invention has the following obvious advantages:
the invention relates to a method for measuring temperature, illuminance and humidity of a building, aiming at uncertainty and randomness of problems of sensor precision error, interference, measurement parameter abnormity and the like in the measurement process of the temperature, illuminance and humidity parameters of the building.
Secondly, the RNN time recursive neural network is a neural network used for processing time series data of building temperature, illumination intensity and humidity. In the network, the loop structure will keep the state value of the hidden neuron at the current time and input it into the hidden layer neuron at the next time as a part of the input signal of the next loop input. The input signal of RNN is the building temperature, illuminance and humidity time sequence input, each layer shares the network weight and bias when inputting one step, which greatly reduces the parameters needed to learn in the network and reduces the complexity of the network.
The RNN time recursive neural network fully utilizes the correlation among time sequence data based on the building temperature, the illuminance and the humidity, is a neural network with a directional circulating structure added in a hidden layer, has a special structure and can better process the problem of the data based on the time sequence building temperature, the illuminance and the humidity, shows stronger capability of learning essential characteristics of a data set of the building temperature, the illuminance and the humidity by representing and inputting the distributed representation of the data of the building temperature, the illuminance and the humidity, realizes the approximation of a complex function, better describes rich intrinsic information of the data of the building temperature, the illuminance and the humidity, has stronger generalization capability, and improves the accuracy and the reliability of calculating the building temperature, the illuminance and the humidity.
The RNN time recursive neural network is a neural network introducing the concept of 'time sequence' of building temperature, illuminance and humidity, has a feedback mechanism, and is widely applied to time sequence data modeling. The RNN can store the learned information in the network, so that the model can learn the current time and the pastThe dependency of the information. Given an input sequence, the RNN time-recursive neural network hides the layer state h at any time ttAll are based on the building temperature, illuminance and humidity input X at the current momenttAnd hidden layer state h at past timet－1The state of the hidden layer at each moment can be transmitted to the next moment by the RNN time recursive neural network; and finally, mapping the building temperature, the illumination intensity and the humidity for a period of time by the RNN time recursive neural network through an output layer to obtain the output quantity of the building temperature, the illumination intensity and the humidity.
And fifthly, the plurality of Elman neural network prediction models adopted by the invention realize the prediction of the temperature, the illuminance and the humidity of the building within a period of time at the detected point, the Elman neural network prediction models are generally divided into 4 layers, namely an input layer, an intermediate layer (hidden layer), a carrying layer and an output layer, the connection of the input layer, the hidden layer and the output layer is similar to a feedforward network, the unit of the input layer only plays a role in signal transmission, and the unit of the output layer plays a role in linear weighting. The transfer function of the hidden layer unit can adopt a linear or non-linear function, and the accepting layer is also called a context layer or a state layer, and is used for memorizing the output value of the hidden layer unit at the previous moment, which can be regarded as a time delay operator. The Elman neural network prediction model is characterized in that the output of the hidden layer is self-connected to the input of the hidden layer through the delay and storage of the supporting layer, the self-connection mode enables the output to have sensitivity to the data of the historical state, and the addition of the internal feedback network increases the capability of the network for processing dynamic information, so that the purpose of dynamic modeling is achieved. The regression neural network of the Elman neural network prediction model is characterized in that the output of a hidden layer is self-connected to the input of the hidden layer through the delay and storage of a structural unit, the self-connection mode enables the prediction model to have sensitivity to data of a historical state, and the addition of an internal feedback network increases the capability of the network for processing dynamic information, thereby being beneficial to modeling of a dynamic process; the neural network fuses information of a future prediction network and information of a past prediction network by utilizing feedback connection of dynamic neurons of a related layer, so that the memory of the network to time series characteristic information is enhanced, and the accuracy and robustness of prediction of the temperature, illuminance and humidity of a detected building are improved.
The energy consumption prediction module is composed of an energy consumption subtraction clustering classifier, a plurality of Elman neural network energy consumption prediction models, an energy consumption GM (1,1) gray prediction model, a Jordan neural network energy consumption residual prediction model, 2 beat delay line TDL and interval number RBF neural networks, historical data of energy consumption is converted into a predicted value of the interval number, and prediction accuracy and robustness are improved.
The input of the section number kohonen neural network building energy consumption state classifier of the invention is a predicted value of 3 meteorological section numbers representing the building energy consumption performance, a building energy consumption predicted value and a kohonen neural network outputting 1 section number, the output of the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module is the input of the section number kohonen neural network building energy consumption state classifier, and the output of the section number kohonen neural network building energy consumption state classifier is the section number representing the size of the building energy consumption state of the detected building; according to the influence of meteorological parameters of the building on the energy consumption of the building, engineering practice of historical data of the energy consumption of the building and civil building energy conservation regulations, the energy consumption state classifier of the kohonen neural network building with the interval numbers divides the energy consumption of the building into 5 different interval numbers corresponding to 5 energy consumption levels of low, normal, high and poor energy consumption levels and constructs a corresponding relation table of the 5 interval numbers and the 5 energy consumption levels of the high energy consumption state of the building, so that the dynamic performance and scientific classification of the energy consumption state level classification of the building are realized.
Drawings
FIG. 1 is a building energy consumption parameter acquisition platform based on a wireless sensor network according to the invention;
FIG. 2 is a system for classifying energy consumption levels of a building according to the present invention;
FIG. 3 is a functional diagram of a detection node according to the present invention;
FIG. 4 is a functional diagram of a control node according to the present invention;
FIG. 5 is a functional diagram of the site monitoring software of the present invention;
FIG. 6 is a temperature interval number neural network model according to the present invention.
Detailed Description
The technical scheme of the invention is further described by combining the attached drawings 1-6:
1. design of overall system function
The invention relates to an intelligent detection system for building energy consumption, which realizes detection of building environment factor parameters and intelligent prediction of building energy consumption according to the influence of the building environment parameters on the building energy consumption. The building energy consumption parameter acquisition platform based on the wireless sensor network comprises a detection node 1 for building environmental parameters, a control node 2 for adjusting the building environmental parameters and a field monitoring terminal 3, wherein the detection node 1, the control node 2 and the field monitoring terminal 3 are in wireless communication by respectively adopting NRF2401 and MSP430 series microprocessors; the detection node 1 and the control node 2 are installed in the monitored building environment to form a parameter acquisition and measurement and control network in a self-organizing mode, and the parameter acquisition and measurement and control network and the field monitoring terminal 3 carry out information interaction. The detection node 1 sends the detected building environmental parameters to the field monitoring terminal 3 and performs primary processing on the sensor data; the field monitoring terminal 3 transmits control information to the detection node 1 and the control node 2. The whole system structure is shown in figure 1.
2. Design of detection node
A large number of detection nodes 1 based on a wireless sensor network are used as building environmental parameter sensing terminals, and the mutual information interaction between the field monitoring terminals 3 is realized by the detection nodes 1 and the control nodes 2 through a self-organizing wireless network. The detection node 1 comprises a sensor for acquiring temperature, humidity, illuminance and wind speed parameters of building environmental parameters, a corresponding signal conditioning circuit, an MSP430 microprocessor and an NRF2401 wireless transmission module; the software of the detection node mainly realizes wireless communication and acquisition and pretreatment of building environmental parameters. The software is designed by adopting a C language program, so that the compatibility degree is high, the working efficiency of software design and development is greatly improved, and the reliability, readability and transportability of program codes are enhanced. The structure of the detection node is shown in fig. 3.
3. Design of control node
The control node 2 is provided with a 4-channel D/A conversion circuit for outputting and adjusting temperature, humidity, illuminance and wind speed, a relay control circuit, an MSP430 microprocessor and a wireless communication module interface in an output channel, so as to realize control of the building environmental parameter control equipment, and the control node is shown in figure 4.
4. Software design of field monitoring terminal
The on-site monitoring terminal 3 is an industrial control computer, the on-site monitoring terminal 3 mainly realizes the collection of building environment parameters and the intelligent prediction of building energy consumption and realizes the information interaction with the detection node 1 and the control node 2, the on-site monitoring terminal 3 mainly has the functions of communication parameter setting, data analysis and data management and the intelligent prediction of building energy consumption through a building energy consumption grade classification system, the management software selects Microsoft Visual + +6.0 as a development tool and calls an Mscomm communication control of the system to design a communication program, and the software function of the on-site monitoring terminal is shown in figure 5. The building energy consumption grade classification system consists of a temperature detection module, a illuminance detection module, a humidity detection module, an energy consumption prediction module and a section number kohonen neural network building energy consumption state classifier; the illuminance detection module and the humidity detection module refer to the same design method of the temperature detection module; the functional structure of the building energy consumption level classification system is shown in fig. 2, and the design of the building energy consumption level classification system is as follows:
(1) temperature detection module design
The temperature detection module consists of a temperature interval number neural network model, 2 temperature subtraction cluster classifiers, 2 groups of a plurality of Elman neural network temperature prediction models and 2 temperature GM (1,1) gray prediction models, the humidity detection module design and illuminance detection module design method refers to a temperature detection module design method, and the temperature detection module is designed as follows:
A. temperature interval number neural network model design
Interval of temperature countingBy a plurality of RR time recurrent neural networks via the network model, the temperature interval number wavelet neural network model converts a plurality of temperature sensors of a building in a period of time to a dynamic interval numerical value of the temperature of the building, the output of each temperature sensor at a detection point is the input of a corresponding RR time recurrent neural network, the output of the RR time recurrent neural network model is the input of the interval number wavelet neural network model, the output of 2 time beat Delay lines TDL is the input of the interval number wavelet neural network model, the output of the interval number wavelet neural network is the interval number formed by the upper and lower limit values representing the temperature of the building in a period of time, and the upper and lower limit values of the interval number output by the interval number wavelet neural network are respectively used as the input of the corresponding 2 beat Delay lines TDL; the output of the interval number wavelet neural network is u1(k) And u2(k)，u1(k) And u2(k) Respectively as inputs to corresponding beat delay lines TDL, u1(k) And u2(k) The upper limit value and the lower limit value respectively represent the output of the temperature interval numerical neural network model, and the output interval numerical value of a plurality of temperature sensors forming the building for detecting the temperature in a period of time is [ u ]2,u1]The structure of the neural network model for the number of temperature intervals of the building is shown in FIG. 6, wherein X (l), …, X (n) are the output of a plurality of RR time recurrent neural networks, U1(k-1)，…，U1(k-d) historical data of the upper limit value of the neural network model output value for the building temperature interval number, U2(k-1)，…，U2(k-d) historical data of lower limit value of numerical neural network model output value of building temperature interval, u1(k) And u2(k) The output value of the interval number wavelet neural network represents the output of the building temperature interval numerical value neural network model, k represents the current time, and d represents the lag point of U respectively. The building temperature interval number neural network model can be described as:
U(k)＝[u2(k),u1(k)]＝F[X(k),X(1),…,X(n)；u1(k),…,u1(k-d)；u2(k),…,u2(k-d)] (1)
the RNN time recursive neural network can process the sequential information of the building temperature, uses the output of the previous state of the building temperature as a part of the input of the predicted subsequent temperature, and has the function of 'memorizing' the building temperature in a general sense. The RNN time recursive neural network may retain a previous sequence of building temperatures as outputs, and the next sequence of building temperature inputs and the retained previous sequence of temperature outputs are jointly computed to obtain a next sequence of building temperature outputs. x is the number oftIs the input at time t, stRepresenting the state of a memory unit of the network at time t, stState s by previous stept-1And input x at the current timetJointly calculating to obtain:
st＝f(Uxt+Wst-1) (2)
the stimulus function f is a non-linear function tanh in the RNN neural network, usually the first hidden state st-1The value of (c) will be initialized with 0, but actually initializing with a minimum value will cause the gradient to drop faster. otIs the output at time t, typically a probability vector calculated by a normalized exponential function:
ot＝softmax(Vst) (3)
the interval number wavelet neural network WNN (wavelet neural networks) is a feedforward network which is provided by taking a wavelet function as an excitation function of a neuron and combining an artificial neural network, wherein the input of the interval number wavelet neural network WNN (wavelet neural networks) theoretical basis construction is a plurality of RR time recurrent neural network output values, and the output feedback value and the output are temperature interval numbers. The expansion and contraction of wavelets, the translation factor and the connection weight in the range number wavelet neural network are adaptively adjusted in the optimization process of the error energy function. The input signal of the wavelet neural network with the interval number can be represented as an input one-dimensional vector xi(i ═ 1,2, …, n), the output signal is denoted yk(k is 1,2, …, m), and the calculation formula of the interval number wavelet neural network output layer is as follows:
Figure BDA0002419399630000101
in the formula omegaijInputting the connection weight between the i node of the layer and the j node of the hidden layer,
Figure BDA0002419399630000102
as wavelet basis functions, bjIs a shift factor of the wavelet basis function, ajScale factor, omega, of wavelet basis functionsjkIs the connection weight between the hidden layer j node and the output layer k node, wherein k is 2. The output of the interval number wavelet neural network is u1(k) And u2(k) The interval number of the temperature value of the building to be detected is formed, the output of the RNN time recurrent neural network in a period of time is used as the input of the interval number wavelet neural network, and the output of the interval number wavelet neural network is the interval number of the temperature of the building; the temperature sensors at a plurality of detection points detect the temperature of the building within a period of time and output interval numerical value is [ u [ ]2,u1]。
B. Temperature subtraction clustering classifier design
The upper limit value and the lower limit value of the temperature interval number neural network model output interval number are respectively used as the input of 2 corresponding temperature subtraction cluster classifiers, and the upper limit value and the lower limit value of 2 groups of temperature intervals of multiple types output by the 2 temperature subtraction cluster classifiers are respectively used as the input of 2 groups of Elman neural network temperature prediction models. Compared with other clustering methods, the subtractive clustering of the upper limit value and the lower limit value of the temperature interval number does not need to determine the clustering number in advance, the position and the clustering number of the clustering center of the upper limit value and the lower limit value of the temperature interval number can be quickly determined only according to the sample data density of the upper limit value and the lower limit value of the temperature interval number, and the upper limit data point and the lower limit data point of each temperature interval value are used as the characteristic of a potential clustering center, so that the clustering result of the upper limit value and the lower limit value of the temperature interval number is irrelevant to the dimension of a problem. Therefore, the subtractive clustering algorithm of the upper and lower limit values of the number of temperature intervals is a rule automatic extraction method suitable for data modeling based on the upper and lower limit values of the number of temperature intervals. Data points (X) setting the upper and lower limits of the N temperature intervals in the m-dimensional space1,X2,…XN) Each data point Xi＝(xi,1,xi,1,…,xi,m) Are all candidates for cluster centers, i-1, 2, …, N, data point XiThe density function of (a) is defined as:
Figure BDA0002419399630000111
in the formula, the radius raIs a positive number, raAn influence neighborhood of the point is defined, and data points outside the radius contribute very little to the density index of the point and are generally ignored. Calculate each point XiSelecting the density value with the highest density index Dc1As the first cluster center Xc1(ii) a And then correcting the density value to eliminate the influence of the existing cluster center. The density value is corrected according to the following formula:
Figure BDA0002419399630000112
wherein D isc1Is the highest density value corresponding to the initial clustering center, and the corrected radius rbIs set to avoid the second cluster center point being too close to the previous one, and is generally set to rb＝ηraEta is more than or equal to 1.25 and less than or equal to 1.5. After correcting the density index of each data point, when D isckAnd Dc1And when the following formula is satisfied, the clustering center corresponding to the density index is the Kth clustering center. This process is repeated until a new cluster center XckCorresponding density index DckAnd Dc1Terminating clustering when the following equation is satisfied:
Dck/Dc1＜δ (7)
in the formula, δ is a threshold value set in advance according to actual conditions. The basic idea of the online clustering method provided by the invention is that if the distance from the upper and lower limit data points of a temperature interval number to the center of a group is less than the clustering radius raThen the point belongs to this group and when new data is obtained, the group and the center of the group change accordingly. Along with the continuous increase of upper and lower limit number spatial data of input temperature interval numberIn addition, the algorithm of the invention obtains better upper and lower limit values of the temperature interval number through the real-time dynamic adjustment of the upper and lower limit number clustering centers and the clustering number of the temperature interval number to perform space division.
C. Design of multiple Elman neural network temperature prediction models
The upper and lower limit values of 2 groups of temperature intervals of multiple types output by the 2 temperature subtraction cluster classifiers are respectively used as the input of a plurality of corresponding Elman neural network temperature prediction models of the 2 groups, the output of the plurality of Elman neural network temperature prediction models of the 2 groups is respectively used as the input of a gray prediction model of 2 corresponding temperatures GM (1,1), and the plurality of Elman neural network temperature prediction models can be regarded as a forward neural network with a local memory unit and local feedback connection, and have a special related layer besides a hidden layer; the correlation layer receives the feedback signal from the hidden layer, and each hidden layer node is connected with the corresponding correlation layer node. The association layer takes the hidden layer state at the previous moment and the network input at the current moment as the input of the hidden layer, which is equivalent to state feedback. The transfer function of the hidden layer is generally a Sigmoid function, the output layer is a linear function, and the associated layer is also a linear function. In order to effectively solve the problem of approximation accuracy in temperature prediction, the function of the correlation layer is enhanced. Setting the number of an input layer, an output layer and a hidden layer of the Elman neural network as m, n and r respectively; w is a1，w2，w3And w4Respectively representing the connection weight matrixes from the structural layer unit to the hidden layer, from the input layer to the hidden layer, from the hidden layer to the output layer and from the structural layer to the output layer, wherein the expressions of the hidden layer, the associated layer and the output layer of the ELman neural network building pavement usability classifier are respectively as follows:
Figure BDA0002419399630000121
cp(k)＝xp(k-1) (9)
Figure BDA0002419399630000122
the input of each Elman neural network prediction model is the upper and lower limit values of various temperature intervals subjected to subtractive clustering analysis, and the output of each Elman neural network prediction model is the input of the corresponding temperature GM (1,1) gray prediction model.
D. Temperature GM (1,1) grey prediction model design
The outputs of the 2 groups of the Elman neural network temperature prediction models are respectively used as the inputs of 2 corresponding temperature GM (1,1) gray prediction models, and the outputs of the 2 temperature GM (1,1) gray prediction models are used as the inputs of the interval number kohonen neural network building energy consumption state classifier; the temperature GM (1,1) gray prediction model is a modeling process for predicting the temperature of a building after accumulating historical data prediction values of the temperature of the building output by various irregular Elman neural network prediction models to obtain a generated data sequence with stronger regularity, and the data obtained by generating the gray prediction model for predicting the temperature of the building is accumulated to obtain the prediction value of original data. Assuming that the number of output data of a set of a plurality of Elman neural network temperature prediction models for predicting the temperature of the building is as follows:
x(0)＝(x(0)(1),x(0)(2),…x(0)(n)) (11)
the new sequence generated after the first order accumulation is: x is the number of(1)＝(x(1)(1),x(1)(2),…x(1)(n))(12)
Wherein:
Figure BDA0002419399630000135
x is then(1)The sequence has an exponential growth law, i.e. satisfies the first order linear differential equation:
Figure BDA0002419399630000132
a in the formula becomes the development gray number, which reflects x(1)And x(0)The development trend of (1); u is the number of the endogenous control ash,
reflecting the changing relationship between the data. Solving the differential equation of the above equation to obtain x(1)The predicted building temperature value is:
Figure BDA0002419399630000133
obtaining the original sequence x by the cumulative reduction of the following formula(0)The building temperature prediction model is as follows:
Figure BDA0002419399630000134
by constructing a GM (1,1) gray prediction building temperature model, the upper and lower limit values of the building temperature interval number of the patent can be predicted, and a GM (1,1) gray prediction model corresponding to the upper and lower limit values of the building temperature is constructed. The output values of the 2 temperature GM (1,1) grey prediction models form upper and lower limit prediction values of the temperature intervals of the building.
(2) Energy consumption prediction module design
The energy consumption prediction module consists of an energy consumption subtraction cluster classifier, a plurality of Elman neural network energy consumption prediction models, an energy consumption GM (1,1) gray prediction model, a Jordan neural network energy consumption residual prediction model, 2 beat delay line TDL and interval number RBF neural networks, and the energy consumption subtraction cluster classifier, the plurality of Elman neural network energy consumption prediction models and the energy consumption GM (1,1) gray prediction model are designed by referring to 2 temperature subtraction cluster classifiers in a temperature detection module, 2 groups of a plurality of Elman neural network temperature prediction models and a design method of 2 temperature GM (1,1) gray prediction models. The Jordan neural network energy consumption residual prediction model and the interval number RBF neural network design process are as follows:
A. jordan neural network energy consumption residual prediction model design
The difference between the historical building energy consumption data and the output of an energy consumption GM (1,1) grey prediction model is used as the input of a Jordan neural network energy consumption residual prediction model, the output of the Jordan neural network energy consumption residual prediction model is used as the input of a corresponding beat delay line TDL, the Jordan neural network energy consumption residual prediction model is provided with a special unit layer for memorizing the output value of the system at the previous moment besides an input layer, a hidden layer and an output layer, the special unit layer can be regarded as a delay operator, and the state of the hidden layer is fed back; the Jordan neural network energy consumption residual prediction model has an output feedback link, can reflect the output characteristics of a system, and can reflect the state characteristics by feeding back the state of a hidden layer, so that the Jordan neural network energy consumption residual prediction model has richer properties, is wider in application range, is more suitable for dynamic energy consumption residual prediction, and has obvious advantages compared with a forward network. The input layer has n nodes, the hidden layer has m nodes, and the output layer has r nodes. The output of the hidden layer and the target layer of the Jordan neural network energy consumption residual prediction model is as follows:
Figure BDA0002419399630000141
ot＝f(xi(k)-θi) (17)
where f is the sigmoid function, which is the threshold. Wherein:
Figure BDA0002419399630000142
B. interval number RBF neural network design
The output of the energy consumption GM (1,1) gray prediction model and the output of the Jordan neural network energy consumption residual prediction model are respectively used as the input of 2 corresponding beat delay lines TDL, the output of the 2 beat delay lines TDL is used as the input of an interval number RBF neural network, and the output of the interval number RBF neural network is used as the input of an interval number kohonen neural network building energy consumption state classifier. The radial basis vector of the interval number RBF neural network is H ═ H1,h2,…,hp]T，hpFor basis functions, a commonly used radial basis function in a radial basis function neural network is a gaussian function, and its expression is:
Figure BDA0002419399630000151
wherein X is the time sequence output of 2 outputs of the beat-to-beat delay line TDL, C is the coordinate vector of the central point of the Gaussian basis function of the neuron in the hidden layer, and deltajThe width of the Gaussian base function of the jth neuron of the hidden layer; the output connection weight vector of the network is wijThe output expression of the RBF neural network is as follows:
Figure BDA0002419399630000152
the number of the intervals output by the RBF neural network is the energy consumption historical data predicted value and the output of the energy consumption prediction module.
(3) Energy consumption state classifier design for interval number kohonen neural network building
The input of the section number kohonen neural network building energy consumption state classifier is the section number output by the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module, and the output of the section number kohonen neural network building energy consumption state classifier is the section number representing the energy consumption grade of the detected building; according to the influence of meteorological parameters of the building on the energy consumption of the building, engineering practices of historical data of the energy consumption of the building and civil building energy conservation regulations, a section number kohonen neural network building energy consumption state classifier divides the energy consumption of the building into 5 different section numbers corresponding to 5 energy consumption levels of low, normal, high and constructs a corresponding relation table 1 of the 5 section numbers and 5 energy consumption levels of the energy consumption of the building, the similarity between the section number output by the section number kohonen neural network building energy consumption state classifier and the 5 section numbers representing the different levels of the energy consumption of the 5 buildings is calculated, and the building energy consumption level corresponding to the section number with the maximum similarity is determined as the energy consumption level of the building. The correction algorithm of the weight and the threshold of the energy consumption state classifier of the kohonen neural network building in the patent adopts a gradient correction method to update the network weight and the wavelet basis function parameters, so that the output of the wavelet neural network prediction model is continuously close to the expected output.
TABLE 1 corresponding relationship table of building energy consumption grade and interval number
Serial number Building energy consumption class Number of intervals
1 Is low in [0.00，0.20]
2 Is lower than [0.20，0.40]
3 Normal state [0.40，0.60]
4 Is higher than [0.60，0.80]
5 Height of [0.80，1.0]
The energy consumption state classifier input layer of the interval number kohonen neural network building receives an input signal mode, and the number of neurons corresponds to the characteristic number of the input mode; output layer neurons are also known as mapping neurons. The input neuron and the output neuron of the interval number kohonen neural network building energy consumption state classifier are all connected and have strong connectionThe degree is controlled by the weight, and the self-organizing process of the network is a process of dynamically adjusting the weight according to the input signal mode. The neural network is composed of a fully interconnected neuron array, the network is composed of an input layer and an output layer, the input layer collects external information to each neuron of the output layer through weight vectors, the form of the input layer is the same as that of a BP network, and the number of input nodes corresponds to an r-dimensional input vector x ═ x1,x2,…,xr]Where r is the dimension of the input data. The output layer is also a competition layer, and the most typical structure of the output layer is a two-dimensional form, assuming that m × n nodes are provided, and each node corresponds to one r-dimensional weight vector m ═ m1,m2,…,mr]. The energy consumption state classifier of the Kohonen neural network building with the interval number adopts a Kohonen algorithm, and the main process of the algorithm is as follows: (a) initializing network, learning rate lr, neighborhood radius r0Randomly initializing the connection weight w of the input layer node and the competition layer nodeij(i-1, …, n; j-1, …, m). (b) Inputting a training sample X, and calculating Euclidean distance d between the sample and each output nodejFinding the corresponding node with the minimum distance, then the node is called the winning node v, and the distance is calculated as:
Figure BDA0002419399630000161
(c) the neighborhood of the winning neuron v is determined. (d) And correcting the weight according to the weight learning rule. (e) Inputting again, and repeating the steps (b) - (d) until the training is finished. The input of the section number kohonen neural network building energy consumption state classifier is a predicted value of a meteorological parameter and a predicted value of energy consumption of a building, and the output is a section number representing the size of the detected building energy consumption state grade, so that the classification of the building energy consumption grade is realized, and the classification accuracy is improved.
5. Design example of building energy consumption parameter acquisition platform based on wireless sensor network
According to the distribution condition of the building environmental parameters, the system designs a plane layout installation diagram of a detection node 1, a control node 2 and a field monitoring terminal 3, wherein the detection node 1 is arranged in the building environment in a balanced manner to realize the detection of the environmental parameters influencing the building energy consumption, and the system realizes the collection of the building environmental parameters and the intelligent prediction of the building energy consumption. .
The technical means disclosed in the invention scheme are not limited to the technical means disclosed in the above embodiments, but also include the technical scheme formed by any combination of the above technical features. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and such improvements and modifications are also considered to be within the scope of the present invention.

Claims (6)

1. The utility model provides a building energy consumption intelligent detection system which characterized in that: the system comprises a building energy consumption parameter acquisition platform based on a wireless sensor network and a building energy consumption grade classification system, wherein the building energy consumption parameter acquisition platform based on the wireless sensor network realizes the detection and monitoring of parameters influencing the building environment, and the building energy consumption grade classification system comprises a temperature detection module, a illuminance detection module, a humidity detection module, an energy consumption prediction module and an interval number kohonen neural network building energy consumption state classifier; the outputs of the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module are used as the inputs of an interval number kohonen neural network building energy consumption state classifier, the output of the interval number kohonen neural network building energy consumption state classifier is an interval number representing the energy consumption grade of a detected building, and the building energy consumption grade classification system realizes the detection, prediction and classification of the building energy consumption grade;
the temperature detection module consists of a temperature interval number neural network model, 2 temperature subtraction cluster classifiers, 2 groups of a plurality of Elman neural network temperature prediction models and 2 temperature GM (1,1) grey prediction models, the output of a plurality of detection point temperature sensors is used as the input of the temperature interval number neural network model, the upper limit value and the lower limit value of the output interval number of the temperature interval number neural network model are respectively used as the input of the 2 corresponding temperature subtraction cluster classifiers, the upper limit value and the lower limit value of the 2 groups of a plurality of types of temperature intervals output by the 2 temperature subtraction cluster classifiers are respectively used as the input of the 2 groups of a plurality of Elman neural network temperature prediction models, the output of the 2 groups of a plurality of Elman neural network temperature prediction models is respectively used as the input of the 2 corresponding temperature GM (1,1) grey prediction models, and the output of the 2 temperature GM (1,1) grey prediction models is used as the output of the temperature detection module and the interval number kohonen neural network building energy consumption state component Input of a classifier;
the energy consumption prediction module consists of an energy consumption subtraction cluster classifier, a plurality of Elman neural network energy consumption prediction models, an energy consumption GM (1,1) gray prediction model, a Jordan neural network energy consumption residual prediction model, 2 beat delay line-based TDL (delay line-based histogram) and an interval number RBF (radial basis function) neural network, building energy consumption historical data serve as the input of the energy consumption subtraction cluster classifier, a plurality of types of building energy consumption historical data output by the energy consumption subtraction cluster classifier respectively serve as the input of the corresponding Elman neural network energy consumption prediction models, the output of the Elman neural network energy consumption prediction models serve as the input of the energy consumption GM (1,1) gray prediction model, the difference between the building energy consumption historical data and the energy consumption GM (1,1) gray prediction model serves as the input of the Jordan neural network energy consumption residual prediction model, and the output of the energy consumption GM (1,1) gray prediction model and the Jordan neural network residual prediction model respectively serve as the input of the 2 beat delay line-based TDL The method comprises the steps of inputting, wherein the output of 2 beat-to-beat delay lines TDL is used as the input of an interval number RBF neural network, and the output of the interval number RBF neural network is used as the output of an energy consumption prediction module and the input of an interval number kohonen neural network building energy consumption state classifier;
the input of the section number kohonen neural network building energy consumption state classifier is the section number output by the temperature detection module, the illuminance detection module, the humidity detection module and the energy consumption prediction module, and the output of the section number kohonen neural network building energy consumption state classifier is the section number representing the energy consumption grade of the detected building; according to the influence of meteorological parameters of the building on the energy consumption of the building, engineering practices of historical data of the energy consumption of the building and national identification standards about the energy consumption of the building, a corresponding relation table of 5 interval numbers and 5 energy consumption levels of the building is built by an interval number kohonen neural network building energy consumption state classifier, the energy consumption state of the building to be detected is divided into 5 energy consumption levels of low, normal, high and high, 5 different interval numbers are corresponded, the similarity between the interval number output by the interval number kohonen neural network building energy consumption state classifier and the 5 interval numbers representing the different levels of the energy consumption of the 5 buildings is calculated, and the building energy consumption level corresponding to the interval number with the maximum similarity is determined as the energy consumption level of the building.
2. The intelligent building energy consumption detection system according to claim 1, characterized in that: the temperature interval number neural network model consists of a plurality of RR time recurrent neural networks, the temperature measurement system comprises an interval number wavelet neural network and 2 beat delay lines TDL, wherein the interval number wavelet neural network converts a plurality of temperature sensors of a building in a period of time to perceive the temperature value of the measured building into a dynamic interval numerical value of the temperature of the building, the output of each detection point temperature sensor is the input of each corresponding RR time recurrent neural network, the output of the RR time recurrent neural networks is used as the input of the interval number wavelet neural network, the output of the 2 beat delay lines TDL is the input of the interval number wavelet neural network, the output of the interval number wavelet neural network is the output of a temperature interval number neural network model and the interval number formed by the upper limit value and the lower limit value representing the temperature size of the building in a period of time, and the upper limit value and the lower limit value of the output interval number of the interval number wavelet neural network are respectively used as the input of the corresponding 2 beat delay lines TDL.
3. The intelligent building energy consumption detection system according to claim 1, characterized in that: the illuminance detection module consists of an illuminance interval number neural network model, 2 illuminance subtraction cluster classifiers, 2 groups of a plurality of Elman neural network illuminance prediction models and 2 illuminance GM (1,1) gray prediction models, and the output of the illuminance detection module is used as the input of the interval number kohonen neural network building energy consumption state classifier.
4. The intelligent building energy consumption detection system according to claim 1, characterized in that: the humidity detection module consists of a humidity interval number neural network model, 2 humidity subtraction cluster classifiers, 2 groups of a plurality of Elman neural network humidity prediction models and 2 humidity GM (1,1) gray prediction models, and the output of the humidity detection module is used as the input of the interval number kohonen neural network building energy consumption state classifier.
5. The intelligent building energy consumption detection system according to claim 1, characterized in that: the building energy consumption parameter acquisition platform based on the wireless sensor network is composed of detection nodes, control nodes and a field monitoring terminal, information interaction is achieved through a wireless communication module NRF2401 in a self-organizing mode, the detection nodes are respectively composed of a sensor group module, a single chip microcomputer MSP430 and the wireless communication module NRF2401, the sensor group module is responsible for detecting temperature, illuminance, wind speed and humidity parameters of building environment parameters, and sampling intervals are controlled by the single chip microcomputer and are sent to the field monitoring terminal through the wireless communication module NRF 2401.
6. The intelligent building energy consumption detection system according to claim 5, wherein: the control node controls the adjusting equipment of the building environmental parameters; the on-site monitoring end consists of an industrial control computer, and realizes the management of detecting the environmental parameters of the building by the detection nodes and the early warning of the energy consumption of the building.
CN202010201101.0A 2020-03-20 2020-03-20 Building energy consumption intelligent detection system Active CN111426344B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010201101.0A CN111426344B (en) 2020-03-20 2020-03-20 Building energy consumption intelligent detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010201101.0A CN111426344B (en) 2020-03-20 2020-03-20 Building energy consumption intelligent detection system

Publications (2)

Publication Number Publication Date
CN111426344A CN111426344A (en) 2020-07-17
CN111426344B true CN111426344B (en) 2021-10-12

Family

ID=71548396

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010201101.0A Active CN111426344B (en) 2020-03-20 2020-03-20 Building energy consumption intelligent detection system

Country Status (1)

Country Link
CN (1) CN111426344B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112183826B (en) * 2020-09-15 2023-08-01 湖北大学 Building energy consumption prediction method based on deep cascade generation countermeasure network and related products
CN112070317A (en) * 2020-09-17 2020-12-11 四川长虹电器股份有限公司 Hotel air conditioner energy consumption prediction method
CN112462648A (en) * 2020-11-13 2021-03-09 东南大学 System for monitoring and predicting building comprehensive environment
CN113219871B (en) * 2021-05-07 2022-04-01 淮阴工学院 Curing room environmental parameter detecting system
CN117875187B (en) * 2024-01-28 2024-07-12 红珊科技有限公司 Simulation system and method for living environment
CN118149901B (en) * 2024-03-22 2024-11-05 淮阴工学院 Intelligent energy consumption detection method based on Internet of things technology and management system thereof

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5497430A (en) * 1994-11-07 1996-03-05 Physical Optics Corporation Method and apparatus for image recognition using invariant feature signals
CN105159216B (en) * 2015-08-31 2018-10-02 淮阴工学院 Environment of chicken house ammonia concentration intelligent monitor system
US11112784B2 (en) * 2016-05-09 2021-09-07 Strong Force Iot Portfolio 2016, Llc Methods and systems for communications in an industrial internet of things data collection environment with large data sets
EP3662331A4 (en) * 2017-08-02 2021-04-28 Strong Force Iot Portfolio 2016, LLC Methods and systems for detection in an industrial internet of things data collection environment with large data sets
CN110045771B (en) * 2019-04-19 2020-12-08 淮阴工学院 Intelligent monitoring system for water quality of fishpond
CN110276393A (en) * 2019-06-19 2019-09-24 西安建筑科技大学 A kind of compound prediction technique of green building energy consumption
CN110569883B (en) * 2019-08-16 2023-03-31 淮阴工学院 Air quality index prediction method based on Kohonen network clustering and Relieff feature selection

Also Published As

Publication number Publication date
CN111426344A (en) 2020-07-17

Similar Documents

Publication Publication Date Title
CN111426344B (en) Building energy consumption intelligent detection system
CN111476278B (en) Intelligent gas concentration detection system
CN111461413B (en) Highway road surface performance detecting system
CN110580021B (en) Granary environmental safety intelligent monitoring system based on field bus
CN111474094B (en) Intelligent dust concentration detection system
CN110766132B (en) Orchard yield intelligent prediction system based on Internet of things
CN107808212B (en) Solar energy collection power prediction method based on grey neural network
CN111444947B (en) Bridge settlement intelligent detection system
CN111461187B (en) Intelligent building settlement detection system
CN115016276B (en) Intelligent water content adjustment and environment parameter Internet of things big data system
CN114397043B (en) Multi-point temperature intelligent detection system
CN111429718B (en) Intelligent detection system for road traffic safety
CN114418183B (en) Livestock and poultry health sign big data internet of things detection system
CN110083190A (en) A kind of green pepper greenhouse intelligent monitor system based on subtractive clustering classifier
CN115128978A (en) Internet of things environment big data detection and intelligent monitoring system
CN116405875A (en) ISSA-Elman neural network-based low-power consumption Bluetooth indoor positioning method
CN114417242B (en) Big data detection system for livestock and poultry activity information
CN114386672B (en) Environment big data Internet of things intelligent detection system
CN115062764B (en) Intelligent illuminance adjustment and environmental parameter Internet of things big data system
CN117306608A (en) Foundation pit big data acquisition and intelligent monitoring method and Internet of things system thereof
CN114399024B (en) Oil gas concentration big data intelligent detection system
CN114358244B (en) Big data intelligent detection system of pressure based on thing networking
CN114390376B (en) Fire big data remote detection and early warning system
CN111473768B (en) Building safety intelligent detection system
CN116520734A (en) Intelligent Internet of things environment parameter detection and dust monitoring method and system

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
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20200717

Assignee: SUZHOU YOUPAKE PACKAGING MATERIALS Co.,Ltd.

Assignor: HUAIYIN INSTITUTE OF TECHNOLOGY

Contract record no.: X2021980013449

Denomination of invention: An intelligent detection system for building energy consumption

Granted publication date: 20211012

License type: Common License

Record date: 20211130

EC01 Cancellation of recordation of patent licensing contract
EC01 Cancellation of recordation of patent licensing contract

Assignee: SUZHOU YOUPAKE PACKAGING MATERIALS Co.,Ltd.

Assignor: HUAIYIN INSTITUTE OF TECHNOLOGY

Contract record no.: X2021980013449

Date of cancellation: 20220804

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220929

Address after: 350000 No.2 Xuefu Road, Xiazhu village, Minqing County, Fuzhou City, Fujian Province

Patentee after: Yuwang Construction Engineering Group Co.,Ltd.

Patentee after: Fujian Tangtou Construction Engineering Group Co.,Ltd.

Patentee after: FUZHOU University

Address before: 223005 Jiangsu Huaian economic and Technological Development Zone, 1 East Road.

Patentee before: HUAIYIN INSTITUTE OF TECHNOLOGY