CN113867167A - Household environment intelligent monitoring method and system based on artificial neural network - Google Patents
Household environment intelligent monitoring method and system based on artificial neural network Download PDFInfo
- Publication number
- CN113867167A CN113867167A CN202111266452.0A CN202111266452A CN113867167A CN 113867167 A CN113867167 A CN 113867167A CN 202111266452 A CN202111266452 A CN 202111266452A CN 113867167 A CN113867167 A CN 113867167A
- Authority
- CN
- China
- Prior art keywords
- neural network
- artificial neural
- data
- neurons
- hidden layer
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 70
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 55
- 239000013598 vector Substances 0.000 claims abstract description 47
- 230000004927 fusion Effects 0.000 claims abstract description 39
- 230000009471 action Effects 0.000 claims abstract description 11
- 210000002569 neuron Anatomy 0.000 claims description 120
- 238000004364 calculation method Methods 0.000 claims description 43
- 230000006870 function Effects 0.000 claims description 24
- 238000004891 communication Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000012986 modification Methods 0.000 claims description 3
- 230000004048 modification Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 11
- 238000001514 detection method Methods 0.000 description 16
- 239000007789 gas Substances 0.000 description 16
- 238000005286 illumination Methods 0.000 description 13
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 11
- 229910002091 carbon monoxide Inorganic materials 0.000 description 11
- 230000007613 environmental effect Effects 0.000 description 9
- 239000000779 smoke Substances 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000007499 fusion processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- XOLBLPGZBRYERU-UHFFFAOYSA-N tin dioxide Chemical group O=[Sn]=O XOLBLPGZBRYERU-UHFFFAOYSA-N 0.000 description 4
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 3
- 229910006404 SnO 2 Inorganic materials 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000002964 excitative effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 210000000225 synapse Anatomy 0.000 description 2
- 238000004887 air purification Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000011540 sensing material Substances 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 230000035939 shock Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of intelligent home furnishing, in particular to a home furnishing environment intelligent monitoring method and system based on an artificial neural network, wherein the method comprises the following steps: collecting data of a plurality of sensors in a home environment; extracting characteristic values and characteristic vectors from the sensor data; performing data fusion on the feature vectors based on the artificial neural network; and acquiring decision information of data fusion and taking feedback action. The invention provides a household environment intelligent monitoring method and system based on an artificial neural network, wherein a multi-sensor data fusion technology is introduced into an indoor air quality monitoring and control system, information data are acquired in an all-dimensional and multi-angle manner, the human residence monitoring system is promoted to be more intelligent in the using process, and the monitoring reliability is improved.
Description
Technical Field
The invention relates to the technical field of intelligent home, in particular to a home environment intelligent monitoring method and system based on an artificial neural network.
Background
In recent years, with the development of science and technology in China, the living conditions of people are continuously improved, so that the requirements of people on living environments are higher and higher, particularly indoor environments, and therefore the intelligent home monitoring system gradually enters the lives of people. The intelligent home monitoring system can monitor and adjust indoor environment parameters, so that a user can live in a safe and comfortable environment.
In the field of design and research and development of novel intelligent home, house disaster alarm and the like, countries in the world have taken a long distance, and American companies research and produce a control4 intelligent home system which can monitor environmental parameters such as the temperature and humidity, the formaldehyde concentration and the illumination intensity in the home in real time by using advanced technologies such as an intelligent sensor technology, a Zigbee wireless network technology and Wifi and automatically adjust the environmental parameters in the home to the optimum state; the Panasonic company mainly studies the lighting control system, the FULL-WAY lighting control system studied by the Panasonic company is more convenient than the traditional system, all required control panels can be connected to form a network only by two specific signal lines, so that complicated wiring in the traditional mode is avoided, the system uses pulse signals to control a lighting module, a timing device and various sensing devices are used for monitoring the indoor lighting intensity, and the lighting is automatically adjusted according to the brightness of indoor light. The smart home systems of foreign companies cannot be well popularized to each household.
China also has few companies with small achievements on the research and development of intelligent home systems, such as King force China technology company, and products of the company are mainly biased to monitoring various indoor environmental parameters and controlling intelligent light. The JU-BUS system is a main control system used for intelligent home of the company and mainly comprises a control module, an execution module and other necessary elements of the system. The JU-BUS intelligent control system is a relatively high-end control system at present, adopts 845 buses, has a very wide range of covered functions, and comprises functions of safety precaution, on-off control of an electric curtain, control of a light switch, real-time acquisition and display of home environment parameters and the like. The control module comprises a temperature detection control panel, an intelligent parameter acquisition panel, a touch screen, various sensors and the like. The control module can send a control command according to indoor environment parameter values (such as air quality, environment temperature and humidity, illumination intensity and the like) collected by the sensors, and the command can control the execution module to execute corresponding actions (such as opening and closing of household appliances, opening or closing of curtains and the like) according to the environment parameter values. Therefore, the functions of detecting indoor environmental parameters, controlling household appliances, alarming and the like are achieved.
However, various smart home devices and smart products in the domestic market currently have some problems, such as low practicability, low cost performance, and the like, which are not applicable to complex occasions, and cannot process large sensor data in a good amount in smart home environment monitoring, and the actual effect may not be ideal.
Disclosure of Invention
In view of the above, the invention provides a household environment intelligent monitoring method and system based on an artificial neural network, which introduces a multi-sensor data fusion technology into an indoor air quality monitoring and control system, collects information data in all directions and at multiple angles, promotes the human residence monitoring system to be more intelligent in the use process, and improves the monitoring reliability.
In order to achieve the purpose, the invention is realized by the following technical scheme:
the invention provides a household environment intelligent monitoring method based on an artificial neural network, which comprises the following steps:
collecting data of a plurality of sensors in a home environment;
extracting characteristic values and characteristic vectors from the sensor data;
performing data fusion on the feature vectors based on the artificial neural network;
and acquiring decision information of data fusion and taking feedback action.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, after acquiring data of a plurality of sensors in the home environment, the method further includes:
and preprocessing the sensor data to generate a sensor data vector.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, the extracting feature values and feature vectors from sensor data includes:
obtaining feature vector X of sensor dataR；
Establishing a set of characteristic vectors [ x ] for a plurality of sensors1,x2,…xR]T。
In the above intelligent home environment monitoring method based on an artificial neural network, as a preferred scheme, the performing data fusion on the feature vector based on the artificial neural network includes:
will sensor feature vector [ x1,x2,…xR]TInputting the data into a plurality of input layer neurons for calculation, and acquiring calculation results of the plurality of input layer neurons;
respectively inputting the calculation results of the plurality of input layer neurons into the plurality of hidden layer neurons for calculation to obtain the calculation results of the plurality of hidden layer neurons;
inputting the calculation results of the plurality of hidden layer neurons into the output layer neurons for calculation,
and acquiring a calculation result of the neuron of the output layer.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, the calculating by the neuron in the input layer includes:
the input data for the input layer neurons is represented as:
the output function of the input layer neurons is: a isi＝f(neti)；
Wherein, thetaiFor the threshold set for the input layer neurons, f () is a sigmoid function.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, the calculating by using the hidden layer neuron includes:
the input data for hidden layer neurons is represented as:
the output function of hidden layer neurons is: a isj＝f(netj)；
Wherein, wijFor hidden layer neuron weights, θjA threshold set for hidden layer neurons.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, the output layer neurons perform computations, including the steps of.
The input data for the output layer neurons is represented as:
the output function of the output layer neurons is: y isk＝f(netk)；
Wherein, wjkAs output layer neuron weights, θkA threshold set for output layer neurons.
In the above intelligent monitoring method for a home environment based on an artificial neural network, as a preferred scheme, the performing data fusion on the feature vector based on the artificial neural network further includes:
respectively calculating reverse error signals of neurons of an output layer and neurons of a hidden layer;
correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron respectively;
preferably, the inverse error signal δ of the output layerkThe calculation formula is as follows:
δk＝(ypk-yk)f(netk)＝yk(1-yk)(ypk-yk)；
reverse error signal delta of the hidden layerjThe calculation formula of (2) is as follows:
preferably, the modification formula of the hidden layer neuron weight is as follows:
wij(k+1)＝wij(k)+ηjδjai+ai(wij(k)-wij(k-1))；
the formula for correcting the neuron weight of the output layer is as follows:
wjk(k+1)＝wjk(k)+ηkδkaj+aj(wjk(k)-wjk(k-1))；
wherein, a is a memory factor, which is a coefficient representing the influence of the change of the past weight values of each layer on the change of the current weight value, and η is a learning rate coefficient.
The invention also provides an intelligent home environment monitoring system based on the artificial neural network, which comprises a control center, a communication module and an acquisition terminal, wherein the acquisition terminal comprises a plurality of sensors and a data preprocessing module, the data preprocessing module is used for preprocessing data acquired by the sensors, the communication module is used for carrying out real-time communication between the acquisition terminal and the control center, and the control center is used for carrying out data fusion on the characteristic vectors based on the artificial neural network, acquiring decision information of the data fusion and taking feedback action.
In the above intelligent home environment monitoring system based on an artificial neural network, as a preferred scheme, the control center includes:
the characteristic vector extraction module is used for extracting characteristic values and characteristic vectors from the sensor data;
the fusion calculation module is used for carrying out data fusion on the feature vectors based on the artificial neural network;
an error signal calculation module for calculating inverse error signals of the output layer neurons and the hidden layer neurons, respectively;
and the weight correction module is used for correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron respectively.
The invention provides an intelligent home environment monitoring method based on an artificial neural network, which has the following beneficial effects:
1. the invention provides a household environment intelligent monitoring method based on an artificial neural network, wherein a multi-sensor data fusion technology is introduced into an indoor air quality monitoring and control system, information data are acquired in an all-dimensional and multi-angle manner, a dynamic and static combination manner is used for sensor layout, and each parameter object in a household environment is monitored in real time and dynamically to obtain reliable and accurate information;
2. the invention provides a home environment intelligent monitoring method based on an artificial neural network, which is characterized in that in order to improve the performance of multiple sensors in terms of coordination, real-time performance, reliability and the like in management, a neural network information fusion algorithm is introduced, a more intelligent and effective information fusion scheme is designed in terms of indoor environment early warning decision, the human residence monitoring system is promoted to be more intelligent in the using process, and the reliability is further improved;
3. the invention provides a home environment intelligent monitoring method based on an artificial neural network, which introduces various and numerous sensors for improving comprehensiveness and effectiveness of information acquisition, performs information fusion, processes information acquired by the multiple sensors, reduces interference caused by invalid or redundant information, and provides decision guarantee for controlling air quality regulation equipment;
4. the invention provides an intelligent home environment monitoring method based on an artificial neural network, which aims to realize timely and accurate early warning for monitoring the condition of poor air quality of a human home environment and improve the accuracy of alarm decision, effectively fuses an information fusion technology and a multi-sensing technology, supplements each other in function and establishes a reliable early warning decision model.
The invention also provides an artificial neural network-based intelligent home environment monitoring system, which has the beneficial effects similar to those of the artificial neural network-based intelligent home environment monitoring method and is not repeated.
Drawings
Fig. 1 is a schematic flow chart of a first implementation of an intelligent home environment monitoring method based on an artificial neural network according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a second implementation of the intelligent home environment monitoring method based on the artificial neural network according to the embodiment of the present invention;
fig. 3 is a schematic diagram of an artificial neural network topology structure of a home environment intelligent monitoring method based on an artificial neural network according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of a home environment intelligent monitoring system based on an artificial neural network according to an embodiment of the present invention;
fig. 5 is a block diagram of a hardware structure of the home environment intelligent monitoring system based on the artificial neural network according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Exemplary embodiments of the present invention are described below in conjunction with specific cases:
referring to fig. 1, fig. 1 is a schematic flowchart illustrating a first implementation manner of an intelligent home environment monitoring method based on an artificial neural network according to an embodiment of the present invention; according to the embodiment of the invention, the invention provides a household environment intelligent monitoring method based on an artificial neural network, which comprises the following steps:
s101, collecting data of a plurality of sensors in a home environment.
And S102, extracting characteristic values and characteristic vectors from the sensor data.
And S103, carrying out data fusion on the feature vectors based on the artificial neural network.
And step S104, obtaining decision information of data fusion and taking feedback action.
In the intelligent home environment monitoring method based on the artificial neural network of the embodiment, a plurality of sensors are arranged in the home environment, and the sensors are sense organs of the home environment monitoring system. The multi-sensing characteristic data fusion result is used as a judgment basis of an intelligent system through an artificial neural network data fusion algorithm, so that the intelligent information processing capability is improved. The information fusion technology is a process of comprehensively processing information, identifying states and logically reasoning events, and in the multi-source information fusion process, information detected by each sensor is usually incomplete and inaccurate, and comprises certain uncertainty and ambiguity, even contradiction. In order to realize target identification and attribute judgment, reasoning can be carried out according to the uncertain information and data fusion.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating a second implementation manner of an intelligent home environment monitoring method based on an artificial neural network according to an embodiment of the present invention; according to an embodiment of the present invention, the present invention further provides a home environment intelligent monitoring method based on an artificial neural network, which specifically includes the following steps:
step S201, collecting data of a plurality of sensors in a home environment. Firstly, arranging a plurality of sensors such as a temperature and humidity sensor, a smoke concentration sensor, a carbon monoxide sensor, an air quality sensor, an illumination intensity sensor, an air pressure sensor and the like in a home environment, respectively acquiring various environmental parameter indexes in the home environment, wherein a temperature and humidity detection module can monitor temperature and humidity parameters in the environment in real time; the smoke concentration detection module can collect the smoke concentration in real time; the illumination intensity sensor can detect the ambient illumination intensity value in real time; the carbon monoxide sensor can monitor the concentration of carbon monoxide in the air in real time; the air pressure intensity sensor can acquire a local atmospheric pressure value in real time; the air quality sensor can detect the air quality index in real time.
Step S202, preprocessing the sensor data to generate a sensor data vector. In order to realize the decision processing of a subsequent control system, the process of information fusion firstly needs a sensor to acquire signals, then the signals provided by the sensor are preprocessed, and the raw data acquired by the field sensor is preprocessed by amplification, filtering and the like.
Step S203, extracting a feature value and a feature vector for the sensor data vector. And extracting characteristic values and characteristic vectors from the preprocessed data vectors to facilitate subsequent calculation.
And step S204, establishing a characteristic vector set of a plurality of sensors. Artificial neural netThe basic components of the network are neurons, a set of characteristic vectors [ x ]1,x2,…xR]TRefers to the input vector of the neuron.
And S205, inputting the sensor feature vectors into a plurality of input layer neurons for calculation, and acquiring calculation results of the plurality of input layer neurons.
The input data for the input layer neurons is represented as:
the output function of the input layer neurons is: a isi＝f(neti)；
Wherein, thetaiFor the threshold set for the input layer neurons, f () is a sigmoid function.
And S206, respectively inputting the calculation results of the plurality of input layer neurons into the plurality of hidden layer neurons for calculation, and acquiring the calculation results of the plurality of hidden layer neurons.
The input data for hidden layer neurons is represented as:
the output function of hidden layer neurons is: a isj＝f(netj)；
Wherein, wijFor hidden layer neuron weights, θjA threshold set for hidden layer neurons.
And step S207, inputting the calculation results of the plurality of hidden layer neurons into the output layer neurons for calculation, and acquiring the calculation results of the output layer neurons.
The input data for the output layer neurons is represented as:
the output function of the output layer neurons is: y isk＝f(netk)；
Wherein, wjkAs output layer neuron weights, θkAs neurons of the output layerA set threshold value.
As shown in fig. 3, the sensor feature vectors are input to a plurality of input layer neurons, the calculation result of each input layer neuron is transmitted to the hidden layer neuron in a one-to-many manner, the calculation result of the hidden layer neuron is transmitted to the output layer neuron in a many-to-one manner, the final data fusion is performed, and the result is output.
The neural network mainly comprises an input layer, a hidden layer and an output layer, wherein the input layer, the hidden layer and the output layer are connected through neurons. [ w ]1,w2,…wR]Is the vector of the weight coefficient of the connection between a neuron on the upper layer of the BP neural network and the neuron, similar to the synapse of a human neuron, if a synapse is excitatory, [ w ]1,w2,…wR]The corresponding element in the vector is a positive value, and if the result is non-excitatory, the element in the vector is a negative value. The net input value for this neuron is therefore:
when S is larger than a threshold value theta, the neuron is activated, and the threshold value is adjusted to be: s + θ, f is the excitation function of the neuron, which is a monotonically incrementally bounded function. Then the output of the neuron is:
and step S208, calculating the reverse error signals of the output layer neuron and the hidden layer neuron respectively. Inverse error signal delta of the output layerkThe calculation formula is as follows:
δk＝(ypk-yk)f(netk)＝yk(1-yk)(ypk-yk)；
reverse error signal delta of the hidden layerjThe calculation formula of (2) is as follows:
and S209, respectively correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron. The modification formula of the hidden layer neuron weight is as follows:
wij(k+1)＝wij(k)+ηjδjai+ai(wij(k)-wij(k-1))；
the formula for correcting the neuron weight of the output layer is as follows:
wjk(k+1)＝wjk(k)+ηkδkaj+aj(wjk(k)-wjk(k-1))；
wherein, a is a memory factor, which is a coefficient representing the influence of the change of the past weight values of each layer on the change of the current weight value, and η is a learning rate coefficient.
The essence of the learning process of the artificial neural network is to dynamically adjust each connection weight. According to the sample data input into the network, the mapping relation among the layers is changed by continuously adjusting the connection weight between the network layers, and finally the network output numerical value is as close as possible to the expected numerical value
And S210, obtaining decision information of data fusion and taking feedback action. And the sensor data is subjected to total fusion processing and then reacts, and sound and image early warning, automatic opening of a fan, automatic opening of a curtain, automatic starting of a fire extinguishing device and the like are performed.
Referring to fig. 4, fig. 4 is a schematic block diagram of a home environment intelligent monitoring system based on an artificial neural network according to an embodiment of the present invention; the invention also provides an artificial neural network-based intelligent home environment monitoring system which comprises a control center 403, a communication module 402 and an acquisition terminal 401, wherein the acquisition terminal comprises a plurality of sensors 404 and a data preprocessing module 405, the data preprocessing module 405 is used for preprocessing data acquired by the sensors, the communication module 402 is used for carrying out real-time communication between the acquisition terminal 401 and the control center 403, and the control center 403 is used for carrying out data fusion on characteristic vectors based on the artificial neural network, acquiring decision information of the data fusion and taking feedback action.
In the above home environment intelligent monitoring system based on an artificial neural network, as a preferred scheme, the control center 403 includes:
a feature vector extraction module 406, wherein the feature vector extraction module 406 is configured to extract feature values and feature vectors from the sensor data;
a fusion calculation module 407, where the fusion calculation module 407 is configured to perform data fusion on the feature vectors based on an artificial neural network;
an error signal calculation module 408, said error signal calculation module 408 configured to calculate inverse error signals for output layer neurons and hidden layer neurons, respectively;
and the weight correction module 409 is used for correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron respectively.
Referring to fig. 5, fig. 5 is a block diagram of a hardware structure of a home environment intelligent monitoring system based on an artificial neural network according to an embodiment of the present invention; the intelligent monitoring system for the home environment comprises a control center, a communication module and an acquisition terminal; the acquisition terminal comprises a sensor and a data preprocessing module to realize data preprocessing acquired by the sensor; the communication module realizes the real-time communication functions of the acquisition terminal and the control slave terminal; the control center realizes the fusion processing of the multi-sensing data, the sending of early warning information and the execution of control operation. The control center not only completes the functions of multi-data fusion processing, display, early warning, control operation, data storage and the like, but also starts the environment control facility. The acquisition terminal is firstly required to realize real-time communication with a control center through a controller and a communication module, information acquired by the sensor is sent to the control center, the control center performs fusion processing on the acquired data through an artificial neural network, and once the processed sensor data exceeds a threshold value set by a system, the environment adjusting device is triggered to give an alarm signal.
The main hardware equipment comprises the following components:
(1) temperature and humidity sensor module. The pin port of the digital temperature and humidity change sensor for measuring parameters is very simple, and the port of a single input data pin can directly and simultaneously realize bidirectional data transmission of two data inputs and the other output. Each data storage packet of the system consists of 5byte (40bit) units.
(2) And a smoke concentration detection module. The smoke concentration detection module is one of gas sensors widely used for directly sensing external gas, and the gas-sensitive material for sensing the external gas in the sensor is tin dioxide (SnO 2). The sensor principle is that the conductivity of the sensor gradually becomes higher and higher as the concentration of various combustible substances in the air is increased. According to this principle, the phenomenon that the conductivity changes with the change of the concentration of the combustible gas is converted into an output signal, thereby realizing the function of detecting the smoke concentration. The sensor can accurately detect whether the gas contains carbon monoxide and other various gases with combustible properties, and is a low-power-consumption and low-cost gas sensor which is particularly safe and suitable for various gas applications.
(3) And a carbon monoxide detection module. The carbon monoxide detection module is a device widely used for sensing externally generated gas in a gas sensor of the gas sensor, and the sensing material of the carbon monoxide detection module is mainly tin dioxide (SnO 2). The principle is that the conductivity of the sensor becomes larger and larger along with the increase of the concentration of the carbon monoxide in the air, and the phenomenon that the conductivity changes along with the change of the concentration of the combustible gas is converted into an output signal, so that the function of detecting the concentration of the carbon monoxide is realized. The sensor is particularly suitable for various places to use, and has low price and low cost.
(4) And an air quality detection module. The MQ135 air quality sensor is a widely used sensor, and when the sensor detects that the outside air contains a highly polluting organic gas, the conductivity of the sensor gradually increases as the concentration of the polluting gas increases. Based on this characteristic, it is contemplated to employ a simple input control circuit that converts the maximum change in conductivity to an output control signal corresponding to the concentration of the gas species.
(5) And an illumination intensity detection module. The illumination module of the design adopts a sensitive type photoresistor sensor.
(6) And an air pressure detection module. The design adopts a BMP280-3.3 air pressure sensor module. BMP280 is a common air pressure sensor, and is widely used in various fields due to its characteristics of high precision (the absolute precision can reach 0.2Pa at the lowest), small size, low energy consumption (2.7 μ a), and the like.
(7) And a motor driving module. The stepping motor is a motor which changes a rotation angle by identifying pulse change, and the pulse frequency is in direct proportion to the rotation angle. When the corresponding pins (IN0-IN4) of the driving board correspondingly receive pulse signals consisting of PB5, PB8, PB1 and PB13, the INx sequentially receives the signals, and then the INx outputs level to drive the stepping motor to rotate IN the positive direction; the reverse rotation is the reverse rotation. The number of the pulses is set to set the angular position of the movement, and the pulse frequency is set to determine the rotating speed of the motor.
(8) And a control and processing module. The micro control and processing module selects an STM32F407ZET6 single chip microcomputer (Microcontrollers) based on an ARM core. The processing comprises functional modules such as a central processing unit CPU, a read only memory ROM, a random access memory RAM, various I/O ports, an interrupt system, a display driving circuit, an analog multiplexer, a timer/counter, an A/D converter and the like. The system is a microcomputer system with high shock sinking, and is widely applied to the field of industrial control.
(9) And an alarm module. The early warning of fire is realized through the alarm module, firstly, the operator on duty can check the fire through the image acquisition equipment and quickly judge whether to start the fire extinguishing device (if no treatment is carried out within a certain time, the system automatically starts the fire extinguishing equipment); secondly, according to the fire alarm bell, personnel can evacuate rapidly to reduce unnecessary loss.
(10) And a display module. The display module can display the environmental parameters such as temperature, humidity, illumination, air pressure, PM2.5 and the like of the processed environmental parameters measured by the sensor in the environment in real time.
The intelligent home environment monitoring system based on the artificial neural network mainly comprises functional modules such as a monitoring module and a control module. The basic functions of the system are to accurately monitor environmental parameters through various sensors, set threshold values according to the environmental parameters set by the system, start the electromagnetic valve when the threshold values are exceeded, start air purification equipment, sun shading equipment and the like, and ensure that the living environment is kept in a comfortable and healthy environment. The hardware takes microprocessing as a control core main control module; temperature and humidity monitoring module, smoke concentration monitoring module, illumination intensity detection module, CO detection module, air pressure detection module, stepping motor control module (controlling the opening and closing of the curtain), alarm module and other monitoring modules; and combining the voice processing module, the communication module and other modules to form the hardware of the system. The sensor monitoring module is connected with a pin interface of the microprocessor through the design of the amplifier to realize data acquisition. The bus topology structure is adopted, data monitoring is carried out by a bidirectional half-duplex transmission mode, information calibration is carried out, and the functions of the communication module in the monitoring module and the comprehensive management module are better played. The temperature and humidity detection module can monitor temperature and humidity parameters in the environment in real time; the smoke concentration detection module can collect the smoke concentration in real time; the illumination intensity sensor can detect the ambient illumination intensity value in real time; the carbon monoxide sensor can monitor the concentration of carbon monoxide in the air in real time; the air pressure intensity sensor can acquire a local atmospheric pressure value in real time; the air quality sensor can detect the air quality index in real time; the parameters in the home environment can be set to a certain threshold value through the controller, and once the result of data detected by the sensor after data fusion processing exceeds the threshold value, the system can automatically alarm and automatically start the control equipment. For example, when the illumination intensity is greater than the threshold value, the system is bright at the moment, the system automatically extinguishes the light at the moment, and the motor is driven to open the curtain; conversely, when the illumination intensity is less than the threshold value, indicating that the day is dark, the system automatically lights the small lamp and closes the curtain.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing detailed description of the embodiments of the present invention has been presented for purposes of illustration and description, and is intended to be exemplary only and is not intended to be exhaustive or to limit the invention to the precise forms disclosed; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An intelligent home environment monitoring method based on an artificial neural network is characterized by comprising the following steps:
collecting data of a plurality of sensors in a home environment;
extracting characteristic values and characteristic vectors from the sensor data;
performing data fusion on the feature vectors based on the artificial neural network;
and acquiring decision information of data fusion and taking feedback action.
2. The intelligent home environment monitoring method based on the artificial neural network according to claim 1, wherein after the collection of the data of the plurality of sensors in the home environment, the method further comprises:
and preprocessing the data acquired by the sensor to generate a sensor data vector.
3. The intelligent home environment monitoring method based on the artificial neural network as claimed in claim 2, wherein the extracting feature values and feature vectors from the sensor data comprises:
obtaining feature vector X of sensor dataR；
Establishing a set of characteristic vectors [ x ] for a plurality of sensors1,x2,…xR]T。
4. The intelligent home environment monitoring method based on the artificial neural network as claimed in claim 3, wherein the data fusion of the feature vectors based on the artificial neural network comprises:
will sensor feature vector [ x1,x2,…xR]TInputting the data into a plurality of input layer neurons for calculation, and acquiring calculation results of the plurality of input layer neurons;
respectively inputting the calculation results of the plurality of input layer neurons into the plurality of hidden layer neurons for calculation to obtain the calculation results of the plurality of hidden layer neurons;
and inputting the calculation results of the plurality of hidden layer neurons into the output layer neurons for calculation to obtain the calculation results of the output layer neurons.
5. The intelligent home environment monitoring method based on the artificial neural network as claimed in claim 4, wherein the input layer neuron performs calculation, and the method comprises the following steps:
the input data for the input layer neurons is represented as:
the output function of the input layer neurons is: a isi＝f(neti)；
Wherein, thetaiFor the threshold set for the input layer neurons, f () is a sigmoid function.
6. The intelligent home environment monitoring method based on the artificial neural network as claimed in claim 5, wherein the hidden layer neuron performs calculation, and the method comprises:
the input data for hidden layer neurons is represented as:
the output function of hidden layer neurons is: a isj＝f(netj)；
Wherein, wijFor hidden layer neuron weights, θjA threshold set for hidden layer neurons.
7. The intelligent home environment monitoring method based on the artificial neural network as claimed in claim 6, wherein the output layer neuron performs computation including.
The input data for the output layer neurons is represented as:
the output function of the output layer neurons is: y isk＝f(netk)；
Wherein, wjkAs output layer neuron weights, θkA threshold set for output layer neurons.
8. The intelligent home environment monitoring method based on the artificial neural network according to claim 7, wherein the data fusion of the feature vectors based on the artificial neural network further comprises:
respectively calculating reverse error signals of neurons of an output layer and neurons of a hidden layer;
correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron respectively;
preferably, the inverse error signal δ of the output layerkThe calculation formula is as follows:
δk＝(ypk-yk)f(netk)＝yk(1-yk)(ypk-yk)；
reverse error signal delta of the hidden layerjThe calculation formula of (2) is as follows:
preferably, the modification formula of the hidden layer neuron weight is as follows:
wij(k+1)＝wij(k)+ηjδjai+ai(wij(k)-wij(k-1))；
the formula for correcting the neuron weight of the output layer is as follows:
wjk(k+1)＝wjk(k)+ηkδkaj+aj(wjk(k)-wjk(k-1))；
wherein, a is a memory factor, which is a coefficient representing the influence of the change of the past weight values of each layer on the change of the current weight value, and η is a learning rate coefficient.
9. The utility model provides a house environment intelligence monitored control system based on artificial neural network, its characterized in that, includes control center, communication module and acquisition terminal, acquisition terminal is including a plurality of sensors and data preprocessing module, data preprocessing module is used for right the data that the sensor was gathered carry out the preliminary treatment, communication module is used for acquisition terminal with carry out real-time communication between the control center, control center is used for carrying out data fusion to the eigenvector based on artificial neural network to acquire data fusion's decision-making information, take feedback action.
10. The intelligent home environment monitoring system based on the artificial neural network as claimed in claim 9, wherein the control center comprises:
the characteristic vector extraction module is used for extracting characteristic values and characteristic vectors from the sensor data;
the fusion calculation module is used for carrying out data fusion on the feature vectors based on the artificial neural network;
an error signal calculation module for calculating inverse error signals of the output layer neurons and the hidden layer neurons, respectively;
and the weight correction module is used for correcting the weights of the output layer neuron and the hidden layer neuron according to the reverse error signals of the output layer neuron and the hidden layer neuron respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111266452.0A CN113867167A (en) | 2021-10-28 | 2021-10-28 | Household environment intelligent monitoring method and system based on artificial neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111266452.0A CN113867167A (en) | 2021-10-28 | 2021-10-28 | Household environment intelligent monitoring method and system based on artificial neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113867167A true CN113867167A (en) | 2021-12-31 |
Family
ID=78985835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111266452.0A Pending CN113867167A (en) | 2021-10-28 | 2021-10-28 | Household environment intelligent monitoring method and system based on artificial neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113867167A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102736607A (en) * | 2012-07-06 | 2012-10-17 | 重庆邮电大学 | Living security health remote monitoring system based on data integration |
| US20170082988A1 (en) * | 2013-12-05 | 2017-03-23 | Bayer Technology Services Gmbh | Computer-implemented method and system for automatically monitoring and determining the status of entire process segments in a process unit |
| CN107678410A (en) * | 2017-09-30 | 2018-02-09 | 中国农业大学 | It is a kind of towards the intelligent control method of greenhouse, system and controller |
| US20190041811A1 (en) * | 2017-08-03 | 2019-02-07 | Johnson Controls Technology Company | Building management system with augmented deep learning using combined regression and artificial neural network modeling |
| CN111077780A (en) * | 2019-12-23 | 2020-04-28 | 湖北理工学院 | Intelligent window adjusting method and device based on neural network |
| CN111353425A (en) * | 2020-02-28 | 2020-06-30 | 河北工业大学 | Sleeping posture monitoring method based on feature fusion and artificial neural network |
| CN112034766A (en) * | 2020-09-15 | 2020-12-04 | 广州邦禾检测技术有限公司 | Laboratory safety management system based on Internet of things |
| CN113359502A (en) * | 2021-07-05 | 2021-09-07 | 信阳农林学院 | Intelligent home multi-sensor detection method and system based on artificial intelligence and storage medium |
-
2021
- 2021-10-28 CN CN202111266452.0A patent/CN113867167A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102736607A (en) * | 2012-07-06 | 2012-10-17 | 重庆邮电大学 | Living security health remote monitoring system based on data integration |
| US20170082988A1 (en) * | 2013-12-05 | 2017-03-23 | Bayer Technology Services Gmbh | Computer-implemented method and system for automatically monitoring and determining the status of entire process segments in a process unit |
| US20190041811A1 (en) * | 2017-08-03 | 2019-02-07 | Johnson Controls Technology Company | Building management system with augmented deep learning using combined regression and artificial neural network modeling |
| CN107678410A (en) * | 2017-09-30 | 2018-02-09 | 中国农业大学 | It is a kind of towards the intelligent control method of greenhouse, system and controller |
| CN111077780A (en) * | 2019-12-23 | 2020-04-28 | 湖北理工学院 | Intelligent window adjusting method and device based on neural network |
| CN111353425A (en) * | 2020-02-28 | 2020-06-30 | 河北工业大学 | Sleeping posture monitoring method based on feature fusion and artificial neural network |
| CN112034766A (en) * | 2020-09-15 | 2020-12-04 | 广州邦禾检测技术有限公司 | Laboratory safety management system based on Internet of things |
| CN113359502A (en) * | 2021-07-05 | 2021-09-07 | 信阳农林学院 | Intelligent home multi-sensor detection method and system based on artificial intelligence and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 许琪: "多传感器信息融合算法研究及其应用", 中国优秀硕士学位论文全文数据库信息科技辑, no. 3, pages 140 - 379 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105388187A (en) | Measuring method of humidity-controllable semiconductor gas sensitive element | |
| CN204754586U (en) | Domestic intelligent window system | |
| CN202041839U (en) | Multi-state monitoring automatic window system | |
| CN109947071A (en) | Smart home system | |
| CN109872487A (en) | One kind being based on Lora domestic safety prevention system | |
| CN114076819A (en) | Home environment monitoring circuit, detection device and robot | |
| CN113867167A (en) | Household environment intelligent monitoring method and system based on artificial neural network | |
| CN101937201B (en) | Delay self-adaption method of controller and controller based on method | |
| CN216525792U (en) | Home environment monitoring circuit, detection device and robot | |
| CN116311760A (en) | Civil building fire monitoring and early warning system based on Internet of things | |
| CN104333945A (en) | Indoor intelligent lamp control system | |
| CN205450738U (en) | Multi -functional cloud terminal | |
| CN205038466U (en) | Take garage monitored control system of warning function | |
| CN206609114U (en) | Atmosphere quality monitoring device with IR remote controller | |
| CN106125652A (en) | Cell management system based on wireless senser | |
| CN105804576A (en) | Automatic window opener and control method | |
| AU2021104034A4 (en) | Smart healthcare system for monitoring and control of the indoor environment using iot technology and artificial intelligence | |
| CN205942291U (en) | Thing networking home systems | |
| CN218213828U (en) | Low-power-consumption wide area network-oriented electrical fire early warning system | |
| CN206684600U (en) | A kind of intelligent glass greenhouse control system | |
| Ou | Intelligent Opening and Closing System of Doors and Windows | |
| CN219609248U (en) | Intelligent human body infrared detector | |
| CN113487848A (en) | Fuzzy control's intelligent fire alarm system | |
| CN210639459U (en) | Environment monitoring intelligent home control system | |
| CN214033066U (en) | Intelligent clothes hanger 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 |