CN211601023U - Air conditioner energy consumption diagnosis system based on BP neural network - Google Patents
Air conditioner energy consumption diagnosis system based on BP neural network Download PDFInfo
- Publication number
- CN211601023U CN211601023U CN201922479726.9U CN201922479726U CN211601023U CN 211601023 U CN211601023 U CN 211601023U CN 201922479726 U CN201922479726 U CN 201922479726U CN 211601023 U CN211601023 U CN 211601023U
- Authority
- CN
- China
- Prior art keywords
- data processor
- irradiator
- air conditioner
- energy consumption
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The utility model discloses an air conditioner energy consumption diagnostic system based on BP neural network in the technical field of air conditioner energy consumption diagnosis, including data processor, data processor passes through the cable respectively with building autonomous system, router electric connection, data processor passes through the connecting wire respectively with baroceptor, temperature sensor, anemorumbometer, direct solar radiation irradiator, solar scattering irradiator, total solar irradiator, electron hygrometer fixed connection, in the system through baroceptor, temperature sensor, anemorumbometer, direct solar radiation irradiator, total solar irradiator, electron hygrometer pass through RS485/232 connecting wire and be connected to data processor, data processor passes through network line connection to internet and building autonomous system, can diagnose the energy efficiency state of equipment, be in high efficiency, medium efficiency or inefficiency, and when the system is in the low-efficiency state, a warning is given to inform the equipment maintenance personnel to adjust the equipment.
Description
Technical Field
The utility model relates to an air conditioner energy consumption diagnosis technical field specifically is an air conditioner energy consumption diagnostic system based on BP neural network.
Background
The traditional building equipment management system only collects, monitors and alarms relevant parameters of equipment, and a conventional equipment diagnosis system carries out fault diagnosis based on a rule set, but cannot monitor the energy efficiency performance of system operation, so that equipment management personnel cannot be informed to adjust the equipment to enable the equipment to operate in an efficient state.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide an air conditioner energy consumption diagnostic system based on BP neural network to solve the problem that proposes among the above-mentioned background art.
In order to achieve the above object, the utility model provides a following technical scheme: the air conditioner energy consumption diagnosis system based on the BP neural network comprises a data processor, wherein the data processor is electrically connected with a building automatic control system and a router through cables respectively, and the data processor is fixedly connected with an air pressure sensor, a temperature sensor, an air speed and wind direction sensor, a direct solar radiation irradiator, a scattered solar irradiator, a total solar irradiator and an electronic hygrometer through connecting wires respectively.
Preferably, the connecting line is an RS485/232 connecting line, and the cable is a network cable.
Preferably, the building automatic control system comprises an air-conditioning electric quantity detection unit.
Compared with the prior art, the beneficial effects of the utility model are that: the system is connected to a data processor through an RS485/232 connecting line through an air pressure sensor, a temperature sensor, an anemorumbometer, a direct solar radiation irradiator, a solar scattering irradiator, a total solar irradiator and an electronic hygrometer, the data processor is connected with the Internet and a building automatic control system through a network cable and used for receiving external data information and data information of building air-conditioning equipment and processing and analyzing the data information, so that the energy efficiency state of the equipment can be diagnosed, the equipment is efficient, medium-efficiency or low-efficiency, a warning is given when the equipment is in a low-efficiency state, and equipment maintenance personnel are informed to adjust the equipment.
Drawings
Fig. 1 is a schematic structural diagram of the present invention.
In the figure: 1. an air pressure sensor; 2. a temperature sensor; 3. a wind speed and direction sensor; 4. a direct solar irradiation instrument; 5. a sun scattering irradiator; 6. a total sun exposure apparatus; 7. an electronic hygrometer; 8. a cable; 9. a building automatic control system; 10. a connecting wire; 11. a data processor.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.
The utility model provides a technical scheme: referring to fig. 1, an air conditioner energy consumption diagnosis system based on a BP neural network includes a data processor 11, where the data processor 11 runs an artificial neural network program for processing and calculating acquired information data;
referring to fig. 1, a data processor 11 is electrically connected with a building automatic control system 9 and a router through a cable 8, the building automatic control system 9 sends real-time electric quantity data of air-conditioning equipment to the data processor 11, the data processor 11 is connected with the router through a circuit, the data processor 11 is connected with the internet or an ethernet, and weather forecast information is collected through the internet;
referring to fig. 1, a data processor 11 is respectively and fixedly connected with an air pressure sensor 1, a temperature sensor 2, a wind speed and direction sensor 3, a direct solar radiation irradiator 4, a solar scattering irradiator 5, a total solar irradiator 6 and an electronic hygrometer 7 through connecting wires 10, collects real-time data such as atmospheric pressure, temperature, wind speed, wind direction, total solar radiation, direct solar radiation, and scattered solar radiation through the devices, and transmits the data to the data processor 11;
referring to fig. 1, a connection line 10 is an RS485/232 connection line, a data processor 11 is connected with an air pressure sensor 1, a temperature sensor 2, a wind speed and direction sensor 3, a direct solar radiation irradiator 4, a scattered solar irradiator 5, a total solar irradiator 6 and an electronic hygrometer 7 through the RS485/232 connection line, data are collected through the devices, and a cable 8 is a network cable;
referring to fig. 1 again, the building automation system 9 includes an air conditioner power detection unit, and the building automation system 9 detects real-time power data of the air conditioner for transmitting the data to the data processor 11 for calculation.
The working principle is as follows:
step 1: the data processor 11 collects real-time electric quantity data of the air conditioning equipment sent by the building automatic control system 9, and collects real-time data such as atmospheric pressure, temperature, wind speed, wind direction, total solar radiation, direct solar radiation and scattered solar radiation through the air pressure sensor 1, the temperature sensor 2, the wind speed and direction sensor 3, the direct solar radiation irradiator 4, the scattered solar irradiator 5, the total solar irradiator 6 and the electronic hygrometer 7;
step 2: analyzing the data acquired in the step 1, and performing characteristic value extraction and dimension reduction work on the data;
and step 3: carrying out on-line training on the characteristic values extracted in the step 1 to obtain an on-line neural network, wherein an algorithm of the on-line training is as follows:
step 31: if the k-1 training samples are subjected to off-line training and the optimal weight wk-1 and the deviation bk-1 are obtained, taking the weight wk-1 and the deviation bk-1 as the kth training sample to carry out initial weight and deviation of an on-line training network;
step 32: calculating the actual output of the online neural network under the conditions of the initial weight and the deviation;
step 33: calculating the output error of each neuron by using the actual output and the expected output of the online neural network, and further calculating the accumulated error energy, wherein the output error calculation formula of the neuron is as follows:
ekp(n)=Σykp(n)ln(dkp(n))+(1-ykp(n))ln(1-dkp(n))
the accumulated error energy calculation formula is as follows:
wherein n is the number of iterations, ekp is the output error value of the P-th neuron when executing the kth set of training samples, dkp is the expected output value of the P-th neuron when executing the kth set of training samples, ykp is the actual output value of the P-th neuron when executing the kth set of training samples, e (n) is the accumulated error energy, and P is the number of neurons;
step 34: updating the weight and the deviation according to a gradient descent learning rule, finally obtaining a new weight wk and a new deviation bk through multiple iterations, taking the obtained new weight wk and the obtained new deviation bk as the initial weight and the deviation of the next group of training samples, and repeating the steps 32-34 to complete the online training of the next group of training samples;
wherein the gradient descent learning rule defines a local gradient according to the following formula:
wherein a is the number of derived parameters and is the local gradient of the P-th neuron in the P neurons;
and 4, step 4: the data processor 11 collects weather forecast information through the internet, extracts and processes the information in the weather forecast to obtain required data information, and then inputs the data, such as atmospheric pressure, temperature, wind speed, wind direction, total solar radiation, direct solar radiation and scattered solar radiation, collected by the baroceptor 1, the temperature sensor 2, the wind speed and wind direction sensor 3, the direct solar radiation irradiator 4, the scattered solar irradiator 5, the total solar irradiator 6 and the electronic hygrometer 7 from the weather forecast into a trained neural network for electric quantity prediction, if the actually monitored electric quantity data is more than 20% higher than the actually predicted data, the equipment is in an inefficient operation state, and the diagnosis system gives an alarm.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. An air conditioner energy consumption diagnosis system based on a BP neural network comprises a data processor (11), and is characterized in that: the data processor (11) is electrically connected with the building automatic control system (9) and the router respectively through cables (8), and the data processor (11) is fixedly connected with the air pressure sensor (1), the temperature sensor (2), the wind speed and wind direction sensor (3), the direct solar radiation irradiator (4), the scattered solar irradiator (5), the total solar irradiator (6) and the electronic hygrometer (7) respectively through connecting wires (10).
2. The BP neural network-based air conditioner energy consumption diagnosis system according to claim 1, wherein: the connecting line (10) is an RS485/232 connecting line, and the cable (8) is a network cable.
3. The BP neural network-based air conditioner energy consumption diagnosis system according to claim 1, wherein: the building automatic control system (9) comprises an air-conditioning electric quantity detection unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201922479726.9U CN211601023U (en) | 2019-12-31 | 2019-12-31 | Air conditioner energy consumption diagnosis system based on BP neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201922479726.9U CN211601023U (en) | 2019-12-31 | 2019-12-31 | Air conditioner energy consumption diagnosis system based on BP neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN211601023U true CN211601023U (en) | 2020-09-29 |
Family
ID=72599101
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201922479726.9U Expired - Fee Related CN211601023U (en) | 2019-12-31 | 2019-12-31 | Air conditioner energy consumption diagnosis system based on BP neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN211601023U (en) |
-
2019
- 2019-12-31 CN CN201922479726.9U patent/CN211601023U/en not_active Expired - Fee Related
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109376801B (en) | Wind driven generator blade icing diagnosis method based on integrated deep neural network | |
WO2019080367A1 (en) | Method for evaluating health status of mechanical device | |
CN110259646B (en) | Wind generating set component state early warning method based on historical data | |
CN110735769A (en) | method, device and system for predicting fan faults | |
CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
CN116505663B (en) | Farm power consumption safety state monitoring and early warning system | |
CN109491339B (en) | Big data-based substation equipment running state early warning system | |
CN109711664B (en) | Power transmission and transformation equipment health assessment system based on big data | |
CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
CN113822418A (en) | Wind power plant power prediction method, system, device and storage medium | |
CN115979349A (en) | Power station space environment monitoring method and system | |
CN114997745B (en) | Photovoltaic fault diagnosis tracing method based on depth feature extraction | |
CN115060312A (en) | Building material safety monitoring system based on artificial intelligence | |
CN211601023U (en) | Air conditioner energy consumption diagnosis system based on BP neural network | |
CN116667783A (en) | Distributed photovoltaic power station maintenance system | |
CN116365713A (en) | Photovoltaic power station cluster monitoring method and system | |
CN109190841A (en) | Offshore wind farm approaches of predictive maintenance based on the random degradation model of blower probability | |
CN110765486A (en) | Asset fault identification method | |
Tan et al. | Denoising convolutional neural networks based dust accumulation status evaluation of photovoltaic panel | |
CN215299796U (en) | Anti-condensation system of electric power cabinet | |
CN114118553A (en) | Method for identifying degradation of double-row tapered roller bearing of permanent magnet direct-drive wind driven generator | |
CN116886735B (en) | Hydropower station operation monitoring system based on double star-type Ethernet structure | |
CN115711206B (en) | Wind driven generator blade icing state monitoring system based on clustering weight | |
CN117493498B (en) | Electric power data mining and analysis system based on industrial Internet | |
CN117494618B (en) | Wind farm intelligent image monitoring system based on real-time network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200929 Termination date: 20211231 |