CN107945472A - A kind of Laboratory Monitoring early warning system based on cloud service - Google Patents

A kind of Laboratory Monitoring early warning system based on cloud service Download PDF

Info

Publication number
CN107945472A
CN107945472A CN201711406828.7A CN201711406828A CN107945472A CN 107945472 A CN107945472 A CN 107945472A CN 201711406828 A CN201711406828 A CN 201711406828A CN 107945472 A CN107945472 A CN 107945472A
Authority
CN
China
Prior art keywords
mrow
msubsup
data acquisition
acquisition node
laboratory
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
Application number
CN201711406828.7A
Other languages
Chinese (zh)
Inventor
王仕民
江文燕
王明文
叶继华
余彤仑
罗文兵
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.)
Jiangxi Normal University
Original Assignee
Jiangxi Normal University
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 Jiangxi Normal University filed Critical Jiangxi Normal University
Priority to CN201711406828.7A priority Critical patent/CN107945472A/en
Publication of CN107945472A publication Critical patent/CN107945472A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/10—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using wireless transmission systems
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Alarm Systems (AREA)

Abstract

The present invention provides a kind of Laboratory Monitoring early warning system based on cloud service, including：Cloud Server, wireless alarmer, remote monitoring terminal, wireless sensor gateway and the temperature control data acquisition node with the wireless sensor gateway wireless connection, waterproof data acquisition node, fire prevention data acquisition node and antitheft data acquisition node respectively, wherein, wireless sensor gateway is used to the temperature control data acquisition node, waterproof data acquisition node, fire prevention data acquisition node and the monitoring data of antitheft data acquisition node collection being transmitted to Cloud Server；Cloud Server is used to analyze the monitoring data with wireless alarmer and remote monitoring terminal wireless connection, Cloud Server respectively, and when monitoring data exceed threshold value, control wireless alarmer alarm, while send alert information to remote monitoring terminal.By technical solution provided by the invention, existing laboratory temperature control, leak, fire prevention and the safety problem such as antitheft can be solved.

Description

A kind of Laboratory Monitoring early warning system based on cloud service
Technical field
The present invention relates to Laboratory Monitoring early warning technology field, and in particular to a kind of Laboratory Monitoring based on cloud service is pre- Alert system.
Background technology
With expanding economy, scientific and technical progress, the popularization of Scientific Research in University Laboratory and going deep into for course, it is desirable to real Testing device category also becomes to become increasingly complex, and equipment frequency of use increases all the more.Simple data registration in the past and the people of statistics Work management mode, can not meet this demand.In order to mitigate the work load of Lab Manager, improve work efficiency and Service level, Laboratory Information Management System of new generation slowly are shown one's talent.This system is by computer as auxiliary tube Reason, can effectively handle the working procedure of substantial amounts of data volume and complexity.
Increasing with the lab construction scale of domestic colleges and universities, the kind and quantity of equipment are more and more.In the past Artificial treatment pattern can not meet needs under the new situation, the substitute is Design of Laboratory Management System.It is but many The foundation that colleges and universities only focus on Design of Laboratory Management System is convenient caused by artificial management to substitute, and ignores present in laboratory Temperature control, leak, fire prevention and the safety problem such as antitheft.Now the laboratory of many colleges and universities mainly using anti-theft net, burglary-resisting window, Safety door and Lab Manager are antitheft to carry out, and are prevented fires using fire extinguisher, fire hydrant etc., this measure relatively falls Afterwards, good effect is not played.
One important link of Design of Laboratory Management System is ensuring that the property in laboratory and the safety of personnel.Colleges and universities are real It is the important base for cultivating university student's manipulative ability and scientific research to test room.The device category in laboratory complicates all the more and variation, This just needs substantial amounts of personnel to carry out management service, this requires that school will put into substantial amounts of management cost, and efficiency is again very Low, leak, fire, the theft in laboratory happen occasionally.Therefore, the waterproof in laboratory, fire prevention and anti-theft prewarning system are colleges and universities The indispensable part of laboratory room managing.In view of the big and safe importance of the amount of investment of laboratory equipment, all realities Temperature control, leak, fire prevention and the anti-theft module for testing room combine management, form a network system.Thus, Scientific Research in University Laboratory A laboratory monitoring early-warning system should be established, to temperature control, leak, fire, theft phenomena such as strick precaution in advance and early warning, protect Demonstrate,prove laboratory property and the safety of personnel.
The content of the invention
In view of this, it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of experiment based on cloud service Room monitoring and warning system, for solving existing laboratory temperature control, leak, fire prevention and the safety problem such as antitheft.
In order to achieve the above object, the present invention adopts the following technical scheme that：
A kind of Laboratory Monitoring early warning system based on cloud service, including：Cloud Server, wireless alarmer, long-range prison Control terminal, wireless sensor gateway and the temperature control data acquisition node with the wireless sensor gateway wireless connection, anti-respectively Water data acquisition node, fire prevention data acquisition node and antitheft data acquisition node, wherein,
The wireless sensor gateway is used for the temperature control data acquisition node, waterproof data acquisition node, fire prevention number The monitoring data gathered according to acquisition node and antitheft data acquisition node are transmitted to the Cloud Server；The Cloud Server difference With the wireless alarmer and remote monitoring terminal wireless connection, the Cloud Server is used to analyze the monitoring data, and When monitoring data exceed threshold value, control the wireless alarmer to alarm, while alert is sent to the remote monitoring terminal Information.
Preferably, the temperature control data acquisition node includes：Humiture for gathering data of the Temperature and Humidity module in laboratory passes Sensor and the first ZigBee module being electrically connected with the Temperature Humidity Sensor；
The waterproof data acquisition node includes：For gather in laboratory the water sensor of water leakage situation and with it is described The second ZigBee module that water sensor is electrically connected；
The fire prevention data acquisition node includes：For gather smoke condition in laboratory cigarette propagated sensation sensor and with it is described The 3rd ZigBee module that cigarette propagated sensation sensor is electrically connected；
The antitheft data acquisition node includes：4th ZigBee module and it is electrically connected respectively with the 4th ZigBee module The infrared human body heat releasing electric transducer and vibrating sensor connect；
First ZigBee module, the second ZigBee module, the 3rd ZigBee module and the 4th ZigBee module difference With the wireless sensor gateway wireless connection.
Preferably, the antitheft data acquisition node further includes the Image Acquisition being electrically connected with the 4th ZigBee module Device.
Preferably, the antitheft data acquisition node further includes the electronic anti-theft being electrically connected with the 4th ZigBee module Lock warning device.
Preferably, the Laboratory Monitoring early warning system based on cloud service, further includes：Toxic gas leak data gathers Node, the toxic gas leak data acquisition node include：Toxic gas for the leakage of testing laboratory's toxic gas passes Sensor and the 5th ZigBee module being electrically connected with the toxic gas sensor；Wherein, the toxic gas includes：One oxidation Carbon, sulfur dioxide, chlorine, phosgene, surpalite, hydrogen cyanide.
Preferably, the wireless alarmer is audible-visual annunciator, SMS alarming device, mail warning device, phone report Combination more than one or both of alarm device.
Preferably, the wireless alarmer is based on fuzzy comprehensive evaluation method and artificial neural network method to the monitoring number According to progress early warning analysis.
Preferably, the wireless alarmer is based on fuzzy comprehensive evaluation method and carries out early warning analysis to the monitoring data, Specifically include：
Step S11, set of factors is established：X={ X1,X2,…,Xm, Xi={ Xi1,Xi2,…,XinWherein, set of factors X includes M subset of factors, each subset of factors XiThere is n index, wherein, m=4, X1For temperature control monitoring data, X2For water leakage monitoring number According to X3For fire monitoring data, X4For anti-thefting monitoring data；1≤i≤m, n >=1；
Step S12, X={ X are determined1,X2,…,XmWeight be W={ W1,W2,…,Wm}；Determine Xi={ Xi1,Xi2,…, XinWeight be Wi={ Wi1,Wi2,…,Win,
Step S13, determine to judge collection M={ M1,M2,…,MK, wherein, K=4, M1To be outstanding, M2To be good, M3For one As, M4For difference；
Step S14, the relation between set of factors X and judge collection M is represented with fuzzy comprehensive evoluation matrix, to step Subset of factors X in S11iJudged to obtain the fuzzy set p judged on collection MijWith jdgement matrix P,
Wherein：pij={ pi1,pi2,…,pim, P=(pij)n×m；
Step S15, the Result of Fuzzy Comprehensive Evaluation of subset of factors index is first calculated：Wherein, obscure OperatorAccording to matrix multiplication rule computing；Wherein, 1≤i≤m, PiFor the i-th row of jdgement matrix P, then calculate set of factors index Result of Fuzzy Comprehensive Evaluation：Wherein P=[A1,A2,…An]T；
Step S16, normalized：
Wherein, aiExpression is rated object and sees on the whole to rating level fuzzy subset's element MiSubjection degree；Represent the evaluation result after normalization；
Step S17, collection is carried out to evaluation result using segmentation assignment method, calculation formula is:Its In, fiRepresent the assignment of each safe class；f1=1, f2=0.75, f3=0.50, f4=0.25；
S represents collectionization result：If S ∈ [0,0.25), represent that current state is attached most importance to police, safety problem is very serious；If S ∈ [0.25,0.5), expression current state is middle police, and safety problem is more serious；If S ∈ [0.5,0.75), represent that current state is Light alert, safety problem is slight；If S ∈ [0.75,1), represent that current state is no police, show that system is currently very safe.
Preferably, the wireless alarmer is based on artificial neural network method and carries out early warning analysis to the monitoring data, Specifically include：
Step S21, initialization inputs N number of training sample (Ek,F* k), k=1,2 ..., N；The quantity n of input layer by Training sample input vector EkLength n determine, equally, export the quantity m of node layer by training sample output vector F* k's Length determines that hidden layer Q, determines the network number of plies L of more than three layers (containing three layers) and the number of nodes of each layer, wherein, l The number of nodes of layer is denoted as n(l)And n(l)=n, m(l)=m；Training speed is v, training precision ε；List the connection of each interlayer Weight matrix, initialization calculating is carried out by the element value of each connection weight matrix；
Connection weight matrix between l layers and l+1 layers is：W(l)=[w(l) ij]n (l)×n(l+1), wherein, l=1,2 ..., L-1；
Step S22, order iterative calculation number s=1, the sequence number c=1 of training sample, choose k-th training sample (Ek,F* k),EkWith F* kRespectively：
Ek=(e1k,e2k,…,enk), F* k=(f* 1k,f* 2k,…,f* mk)
Forward direction calculates each node of input layer, obtains the output of input layerFor：Wherein, J=1,2 ..., n；
Then, the input of every layer of each node is calculated one by oneWith outputIt is inputted is with the calculation formula exported：Wherein, l=2,3 ..., L；J=1,2 ..., m；
If there is any training sample, make calculation error value GjkNo more than allowable error value ε, i.e. Gjk≤ ε is set up, its In, j=1,2 ..., m, then terminate to train；Otherwise, error is subjected to anti-pass, to correct each connection weight matrix；
Step S23, error-duration model calculating is if desired carried out, corrects L-1 layers of hidden layer to the connection weight of L layers of output layer Matrix computations process is as follows：
Wherein, j=1,2 ..., m；I=1,2 ..., n(L-1)
The connection weight matrix being connected with hidden layer is corrected one by one：
Wherein, l=L-1 ..., 2,1；J=1,2 ..., n(l)；I=1,2 ..., n(l-1)；
Step S24, k=k+1, t=t+1 are made, comes back for circuit training, until GjkUntill≤ε, i.e. network convergence.
Preferably, the remote monitoring terminal includes：Desktop computer, laptop, tablet computer, smart mobile phone And/or intelligent watch.
The present invention uses above technical scheme, at least possesses following beneficial effect：
As shown from the above technical solution, this Laboratory Monitoring early warning system based on cloud service provided by the invention, temperature Experiment indoor temperature and humidity situation can be carried out data acquisition by controlling data acquisition node, and waterproof data acquisition node can be to experiment Indoor water leakage situation carries out data acquisition, and fire prevention data acquisition node can carry out data acquisition to the fire behavior in laboratory, prevent Data acquisition can be carried out to testing indoor theft situation by stealing data acquisition node, and Cloud Server can analyze each data acquisition Monitoring data of node, and when monitoring data exceed threshold value, control wireless alarmer alarm, while to remote monitoring terminal Send alert information.Pass through technical solution provided by the invention, it is possible to achieve laboratory temperature control, leak, fire prevention and the peace such as antitheft The monitoring of full hidden danger, user experience are high.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of schematic block for Laboratory Monitoring early warning system based on cloud service that one embodiment of the invention provides Figure.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical scheme will be carried out below Detailed description.Obviously, described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Base Embodiment in the present invention, those of ordinary skill in the art are obtained all on the premise of creative work is not made Other embodiment, belongs to the scope that the present invention is protected.
Below by drawings and examples, technical scheme is described in further detail.
Referring to Fig. 1, a kind of Laboratory Monitoring early warning system based on cloud service of one embodiment of the invention offer, including： Cloud Server 1, wireless alarmer 2, remote monitoring terminal 3, wireless sensor gateway 4 and respectively with the wireless sensor network Close temperature control data acquisition node 5, waterproof data acquisition node 6, fire prevention data acquisition node 7 and the antitheft data of 4 wireless connections Acquisition node 8, wherein,
The wireless sensor gateway 4 is used for the temperature control data acquisition node 5, waterproof data acquisition node 6, fire prevention The monitoring data that data acquisition node 7 and antitheft data acquisition node 8 gather are transmitted to the Cloud Server 1；The cloud service Device 1 is used to analyze the prison with 3 wireless connection of the wireless alarmer 2 and remote monitoring terminal, the Cloud Server 1 respectively Data are surveyed, and when monitoring data exceed threshold value, control the wireless alarmer 2 to alarm, at the same it is whole to the remote monitoring End 3 sends alert information.
As shown from the above technical solution, this Laboratory Monitoring early warning system based on cloud service provided by the invention, temperature Experiment indoor temperature and humidity situation can be carried out data acquisition by controlling data acquisition node, and waterproof data acquisition node can be to experiment Indoor water leakage situation carries out data acquisition, and fire prevention data acquisition node can carry out data acquisition to the fire behavior in laboratory, prevent Data acquisition can be carried out to testing indoor theft situation by stealing data acquisition node, and Cloud Server can analyze each data acquisition Monitoring data of node, and when monitoring data exceed threshold value, control wireless alarmer alarm, while to remote monitoring terminal Send alert information.Pass through technical solution provided by the invention, it is possible to achieve laboratory temperature control, leak, fire prevention and the peace such as antitheft The monitoring of full hidden danger, user experience are high.
Preferably, the temperature control data acquisition node 5 includes：Humiture for gathering data of the Temperature and Humidity module in laboratory passes Sensor and the first ZigBee module being electrically connected with the Temperature Humidity Sensor；
The waterproof data acquisition node 6 includes：For gather in laboratory the water sensor of water leakage situation and with institute State the second ZigBee module of water sensor electrical connection；
The fire prevention data acquisition node 7 includes：For gather smoke condition in laboratory cigarette propagated sensation sensor and with institute State the 3rd ZigBee module of cigarette propagated sensation sensor electrical connection；
The antitheft data acquisition node 8 includes：4th ZigBee module and respectively with the 4th ZigBee module electricity The infrared human body heat releasing electric transducer and vibrating sensor of connection；
First ZigBee module, the second ZigBee module, the 3rd ZigBee module and the 4th ZigBee module difference With 4 wireless connection of wireless sensor gateway.
Preferably, the antitheft data acquisition node 8 further includes the image being electrically connected with the 4th ZigBee module and adopts Acquisition means.
Preferably, the antitheft data acquisition node 8 further includes the electronics being electrically connected with the 4th ZigBee module and prevents Steal lock warning device.
Preferably, the Laboratory Monitoring early warning system based on cloud service, further includes：Toxic gas leak data gathers Node 9, the toxic gas leak data acquisition node 9 include：Toxic gas for the leakage of testing laboratory's toxic gas Sensor and the 5th ZigBee module being electrically connected with the toxic gas sensor；Wherein, the toxic gas includes：One oxygen Change carbon, sulfur dioxide, chlorine, phosgene, surpalite, hydrogen cyanide.
Preferably, the wireless alarmer 2 is audible-visual annunciator, SMS alarming device, mail warning device, phone report Combination more than one or both of alarm device.
Preferably, the wireless alarmer 2 is based on fuzzy comprehensive evaluation method and artificial neural network method to the monitoring Data carry out early warning analysis.
Preferably, the wireless alarmer 2 is based on fuzzy comprehensive evaluation method and carries out early warning analysis to the monitoring data, Specifically include：
Step S11, set of factors is established：X={ X1,X2,…,Xm, Xi={ Xi1,Xi2,…,XinWherein, set of factors X includes M subset of factors, each subset of factors XiThere is n index, wherein, m=4, X1For temperature control monitoring data, X2For water leakage monitoring number According to X3For fire monitoring data, X4For anti-thefting monitoring data；1≤i≤m, n >=1；
Step S12, X={ X are determined1,X2,…,XmWeight be W={ W1,W2,…,Wm}；Determine Xi={ Xi1,Xi2,…, XinWeight be Wi={ Wi1,Wi2,…,Win,
Step S13, determine to judge collection M={ M1,M2,…,MK, wherein, K=4, M1To be outstanding, M2To be good, M3For one As, M4For difference；
Step S14, the relation between set of factors X and judge collection M is represented with fuzzy comprehensive evoluation matrix, to step Subset of factors X in S11iJudged to obtain the fuzzy set p judged on collection MijWith jdgement matrix P,
Wherein：pij={ pi1,pi2,…,pim, P=(pij)n×m；
Step S15, the Result of Fuzzy Comprehensive Evaluation of subset of factors index is first calculated：Wherein, obscure OperatorAccording to matrix multiplication rule computing；Wherein, 1≤i≤m, PiFor the i-th row of jdgement matrix P, then calculate set of factors index Result of Fuzzy Comprehensive Evaluation：Wherein P=[A1,A2,…An]T；
Step S16, normalized：
Wherein, aiExpression is rated object and sees on the whole to rating level fuzzy subset's element MiSubjection degree；Represent the evaluation result after normalization；
Step S17, collection is carried out to evaluation result using segmentation assignment method, calculation formula is:Its In, fiRepresent the assignment of each safe class；f1=1, f2=0.75, f3=0.50, f4=0.25；
S represents collectionization result：If S ∈ [0,0.25), represent that current state is attached most importance to police, safety problem is very serious；If S ∈ [0.25,0.5), expression current state is middle police, and safety problem is more serious；If S ∈ [0.5,0.75), represent that current state is Light alert, safety problem is slight；If S ∈ [0.75,1), represent that current state is no police, show that system is currently very safe.
Preferably, the wireless alarmer 2 is based on artificial neural network method and carries out early warning analysis to the monitoring data, The operation principle of BP neural network wherein in artificial neural network is：Data are inputted by input layer, by input layer with it is hidden It is applied to containing the weights between layer up to hidden layer, and by obtaining median after the function effect of hidden layer, this median is passed through again Exported after the processing of the function of hidden layer and output layer as a result, if the error of acquired results and preset value is allowing model In enclosing, then calculate and stop, error is otherwise subjected to anti-pass, to correct each weights, until error stops in allowed band.This Sample, obtained weights can be used for being calculated and simulation and forecast.Specifically include：
Step S21, initialization inputs N number of training sample (Ek,F* k), k=1,2 ..., N；The quantity n of input layer by Training sample input vector EkLength n determine, equally, export the quantity m of node layer by training sample output vector F* k's Length determines that hidden layer Q, determines the network number of plies L of more than three layers (containing three layers) and the number of nodes of each layer, wherein, l The number of nodes of layer is denoted as n(l)And n(l)=n, m(l)=m；Training speed is v, training precision ε；List the connection of each interlayer Weight matrix, initialization calculating is carried out by the element value of each connection weight matrix；
Connection weight matrix between l layers and l+1 layers is：W(l)=[w(l) ij]n (l)×n(l+1), wherein, l=1,2 ..., L-1；
Step S22, order iterative calculation number s=1, the sequence number c=1 of training sample, choose k-th training sample (Ek,F* k),EkWith F* kRespectively：
Ek=(e1k,e2k,…,enk), F* k=(f* 1k,f* 2k,…,f* mk)
Forward direction calculates each node of input layer, obtains the output of input layerFor：Wherein, J=1,2 ..., n；
Then, the input of every layer of each node is calculated one by oneWith outputIt is inputted is with the calculation formula exported：Wherein, l=2,3 ..., L；J=1,2 ..., m；
If there is any training sample, make calculation error value GjkNo more than allowable error value ε, i.e. Gjk≤ ε is set up, its In, j=1,2 ..., m, then terminate to train；Otherwise, error is subjected to anti-pass, to correct each connection weight matrix；
Step S23, error-duration model calculating is if desired carried out, corrects L-1 layers of hidden layer to the connection weight of L layers of output layer Matrix computations process is as follows：
Wherein, j=1,2 ..., m；I=1,2 ..., n(L-1)
The connection weight matrix being connected with hidden layer is corrected one by one：
Wherein, l=L-1 ..., 2,1；J=1,2 ..., n(l)；I=1,2 ..., n(l-1)；
Step S24, k=k+1, t=t+1 are made, comes back for circuit training, until GjkUntill≤ε, i.e. network convergence.
Preferably, the remote monitoring terminal 3 includes：Desktop computer, laptop, tablet computer, smart mobile phone And/or intelligent watch.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims. Term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint relative importance.Term " multiple " refers to Two or more, unless otherwise restricted clearly.

Claims (10)

  1. A kind of 1. Laboratory Monitoring early warning system based on cloud service, it is characterised in that including：Cloud Server, radio alarming dress Put, remote monitoring terminal, wireless sensor gateway and the temperature control data with the wireless sensor gateway wireless connection are adopted respectively Collect node, waterproof data acquisition node, fire prevention data acquisition node and antitheft data acquisition node, wherein,
    The wireless sensor gateway is used to adopt the temperature control data acquisition node, waterproof data acquisition node, fire prevention data Collection node and the monitoring data of antitheft data acquisition node collection are transmitted to the Cloud Server；The Cloud Server respectively with institute Wireless alarmer and remote monitoring terminal wireless connection are stated, the Cloud Server is used to analyze the monitoring data, and is supervising When survey data exceed threshold value, control the wireless alarmer to alarm, while alert information is sent to the remote monitoring terminal.
  2. 2. the Laboratory Monitoring early warning system according to claim 1 based on cloud service, it is characterised in that
    The temperature control data acquisition node includes：For gather in laboratory the Temperature Humidity Sensor of data of the Temperature and Humidity module and with it is described The first ZigBee module that Temperature Humidity Sensor is electrically connected；
    The waterproof data acquisition node includes：For gather in laboratory the water sensor of water leakage situation and with the water logging The second ZigBee module that sensor is electrically connected；
    The fire prevention data acquisition node includes：For gather smoke condition in laboratory cigarette propagated sensation sensor and with the cigarette sense The 3rd ZigBee module that sensor is electrically connected；
    The antitheft data acquisition node includes：4th ZigBee module and respectively it is electrically connected with the 4th ZigBee module Infrared human body heat releasing electric transducer and vibrating sensor；
    First ZigBee module, the second ZigBee module, the 3rd ZigBee module and the 4th ZigBee module respectively with institute State wireless sensor gateway wireless connection.
  3. 3. the Laboratory Monitoring early warning system according to claim 2 based on cloud service, it is characterised in that the antitheft number The image collecting device being electrically connected with the 4th ZigBee module is further included according to acquisition node.
  4. 4. the Laboratory Monitoring early warning system according to claim 3 based on cloud service, it is characterised in that the antitheft number The electronic safety lock warning device being electrically connected with the 4th ZigBee module is further included according to acquisition node.
  5. 5. the Laboratory Monitoring early warning system according to claim 2 based on cloud service, it is characterised in that further include：Have Poisonous gas leak data acquisition node, the toxic gas leak data acquisition node include：There is poison gas for testing laboratory The toxic gas sensor of body leakage and the 5th ZigBee module being electrically connected with the toxic gas sensor；Wherein, it is described Toxic gas includes：Carbon monoxide, sulfur dioxide, chlorine, phosgene, surpalite, hydrogen cyanide.
  6. 6. the Laboratory Monitoring early warning system according to claim 1 based on cloud service, it is characterised in that the no report from a liner Alarm device is more than one or both of audible-visual annunciator, SMS alarming device, mail warning device, telephone alarm device Combination.
  7. 7. the Laboratory Monitoring early warning system according to claim 1 based on cloud service, it is characterised in that the no report from a liner Alarm device is based on fuzzy comprehensive evaluation method and artificial neural network method and carries out early warning analysis to the monitoring data.
  8. 8. the Laboratory Monitoring early warning system according to claim 7 based on cloud service, it is characterised in that the no report from a liner Alarm device is based on fuzzy comprehensive evaluation method and carries out early warning analysis to the monitoring data, specifically includes：
    Step S11, set of factors is established：X={ X1,X2,…,Xm, Xi={ Xi1,Xi2,…,XinWherein, set of factors X include m because Sub-prime collection, each subset of factors XiThere is n index, wherein, m=4, X1For temperature control monitoring data, X2For water leakage monitoring data, X3 For fire monitoring data, X4For anti-thefting monitoring data；1≤i≤m, n >=1；
    Step S12, X={ X are determined1,X2,…,XmWeight be W={ W1,W2,…,Wm}；Determine Xi={ Xi1,Xi2,…,Xin} Weight be Wi={ Wi1,Wi2,…,Win,
    Step S13, determine to judge collection M={ M1,M2,…,MK, wherein, K=4, M1To be outstanding, M2To be good, M3To be general, M4For Difference；
    Step S14, the relation between set of factors X and judge collection M is represented with fuzzy comprehensive evoluation matrix, in step S11 Subset of factors XiJudged to obtain the fuzzy set p judged on collection MijWith jdgement matrix P,
    Wherein：pij={ pi1,pi2,…,pim, P=(pij)n×m；
    Step S15, the Result of Fuzzy Comprehensive Evaluation of subset of factors index is first calculated：Wherein, fuzzy operator According to matrix multiplication rule computing；Wherein, 1≤i≤m, PiFor the i-th row of jdgement matrix P, then calculate the fuzzy of set of factors index Comprehensive Evaluation result：Wherein P=[A1,A2,…An]T；
    Step S16, normalized：
    Wherein, aiExpression is rated object and sees on the whole to rating level fuzzy subset's element MiSubjection degree；Represent the evaluation result after normalization；
    Step S17, collection is carried out to evaluation result using segmentation assignment method, calculation formula is:Wherein, fiTable Show the assignment of each safe class；f1=1, f2=0.75, f3=0.50, f4=0.25；
    S represents collectionization result：If S ∈ [0,0.25), represent that current state is attached most importance to police, safety problem is very serious；If S ∈ [0.25, 0.5), represent that current state is middle police, safety problem is more serious；If S ∈ [0.5,0.75), current state is represented to be light alert, Safety problem is slight；If S ∈ [0.75,1), represent that current state is no police, show that system is currently very safe.
  9. 9. the Laboratory Monitoring early warning system according to claim 7 based on cloud service, it is characterised in that the no report from a liner Alarm device is based on artificial neural network method and carries out early warning analysis to the monitoring data, specifically includes：
    Step S21, initialization inputs N number of training sample (Ek,F* k), k=1,2 ..., N；The quantity n of input layer is by training Sample input vector EkLength n determine, equally, export the quantity m of node layer by training sample output vector F* kLength To determine, hidden layer Q, determines the network number of plies L of more than three layers (containing three layers) and the number of nodes of each layer, wherein, l layers Number of nodes is denoted as n(l)And n(l)=n, m(l)=m；Training speed is v, training precision ε；List the connection weight square of each interlayer Battle array, initialization calculating is carried out by the element value of each connection weight matrix；
    Connection weight matrix between l layers and l+1 layers is：W(l)=[w(l) ij]n (l)×n(l+1), wherein, l=1,2 ..., L-1；
    Step S22, order iterative calculation number s=1, the sequence number c=1 of training sample, choose k-th training sample (Ek,F* k),Ek With F* kRespectively：
    Ek=(e1k,e2k,…,enk), F* k=(f* 1k,f* 2k,…,f* mk)
    Forward direction calculates each node of input layer, obtains the output of input layerFor：Wherein, j=1, 2,…,n；
    Then, the input of every layer of each node is calculated one by oneWith outputIt is inputted is with the calculation formula exported：Wherein, l=2,3 ..., L；J=1,2 ..., m；
    If there is any training sample, make calculation error value GjkNo more than allowable error value ε, i.e. Gjk≤ ε is set up, wherein, j= 1,2 ..., m, then terminate to train；Otherwise, error is subjected to anti-pass, to correct each connection weight matrix；
    Step S23, error-duration model calculating is if desired carried out, corrects L-1 layers of hidden layer to the connection weight matrix of L layers of output layer Calculating process is as follows：
    <mrow> <msubsup> <mi>&amp;delta;</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>)</mo> </mrow> </msubsup> <mo>=</mo> <mo>-</mo> <mrow> <mo>(</mo> <msubsup> <mi>f</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mo>*</mo> </msubsup> <mo>-</mo> <msub> <mi>f</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> </msub> <mo>)</mo> </mrow> <msup> <mi>f</mi> <mo>&amp;prime;</mo> </msup> <mrow> <mo>(</mo> <msubsup> <mi>I</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>)</mo> </mrow> </msubsup> <mo>)</mo> </mrow> </mrow>
    <mrow> <msubsup> <mi>&amp;Delta;w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>&amp;eta;&amp;delta;</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <msubsup> <mi>O</mi> <mrow> <mi>i</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>)</mo> </mrow> </msubsup> </mrow>
    <mrow> <msubsup> <mi>w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>+</mo> <msubsup> <mi>&amp;Delta;w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow>
    Wherein, j=1,2 ..., m；I=1,2 ..., n(L-1)
    The connection weight matrix being connected with hidden layer is corrected one by one：
    <mrow> <msubsup> <mi>&amp;delta;</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>)</mo> </mrow> </msubsup> <mo>=</mo> <msup> <mi>f</mi> <mo>&amp;prime;</mo> </msup> <mrow> <mo>(</mo> <msubsup> <mi>i</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>)</mo> </mrow> </msubsup> <mo>)</mo> </mrow> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>q</mi> <mo>=</mo> <mn>1</mn> </mrow> <msup> <mi>n</mi> <mrow> <mo>(</mo> <mi>l</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> </msup> </munderover> <msubsup> <mi>&amp;delta;</mi> <mrow> <mi>q</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <msubsup> <mi>w</mi> <mrow> <mi>j</mi> <mi>q</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> </mrow>
    <mrow> <msubsup> <mi>&amp;Delta;w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>=</mo> <mo>-</mo> <msubsup> <mi>&amp;eta;&amp;delta;</mi> <mrow> <mi>j</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>)</mo> </mrow> </msubsup> <msubsup> <mi>O</mi> <mrow> <mi>i</mi> <mi>k</mi> </mrow> <mrow> <mo>(</mo> <mi>l</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mo>,</mo> </mrow>
    <mrow> <msubsup> <mi>w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>+</mo> <mn>1</mn> <mo>)</mo> </mrow> <mo>=</mo> <msubsup> <mi>w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> <mo>+</mo> <msubsup> <mi>&amp;Delta;w</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mrow> <mo>(</mo> <mi>L</mi> <mo>-</mo> <mn>1</mn> <mo>)</mo> </mrow> </msubsup> <mrow> <mo>(</mo> <mi>t</mi> <mo>)</mo> </mrow> </mrow>
    Wherein, l=L-1 ..., 2,1；J=1,2 ..., n(l)；I=1,2 ..., n(l-1)；
    Step S24, k=k+1, t=t+1 are made, comes back for circuit training, until GjkUntill≤ε, i.e. network convergence.
  10. 10. the Laboratory Monitoring early warning system according to claim 1 based on cloud service, it is characterised in that described long-range Monitor terminal includes：Desktop computer, laptop, tablet computer, smart mobile phone and/or intelligent watch.
CN201711406828.7A 2017-12-22 2017-12-22 A kind of Laboratory Monitoring early warning system based on cloud service Pending CN107945472A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711406828.7A CN107945472A (en) 2017-12-22 2017-12-22 A kind of Laboratory Monitoring early warning system based on cloud service

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711406828.7A CN107945472A (en) 2017-12-22 2017-12-22 A kind of Laboratory Monitoring early warning system based on cloud service

Publications (1)

Publication Number Publication Date
CN107945472A true CN107945472A (en) 2018-04-20

Family

ID=61941834

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711406828.7A Pending CN107945472A (en) 2017-12-22 2017-12-22 A kind of Laboratory Monitoring early warning system based on cloud service

Country Status (1)

Country Link
CN (1) CN107945472A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111350945A (en) * 2018-12-24 2020-06-30 无锡热能在线科技有限公司 Method for detecting medium leakage of system pipeline
CN109443669B (en) * 2018-09-30 2021-03-26 深圳市英威腾电源有限公司 Water leakage detection method and device
CN113671887A (en) * 2021-08-30 2021-11-19 济南诚博信息科技有限公司 Multi-piece equipment state monitoring system based on point inspection customized repair reference

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05197891A (en) * 1991-03-12 1993-08-06 Babcock Hitachi Kk Method and device for detecting abnormality
CN201345049Y (en) * 2008-12-05 2009-11-11 深圳职业技术学院 Distributed data monitoring and early warning system in experimental environment
CN104463363A (en) * 2014-12-03 2015-03-25 浙江图讯科技有限公司 Method, device and system for giving early warning about production risk
CN205281726U (en) * 2016-01-01 2016-06-01 朱立才 Laboratory security protection monitored control system based on video analysis
CN106530633A (en) * 2016-09-28 2017-03-22 中国人民解放军国防科学技术大学 Intelligent in-event disposal-based security protection method and system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05197891A (en) * 1991-03-12 1993-08-06 Babcock Hitachi Kk Method and device for detecting abnormality
CN201345049Y (en) * 2008-12-05 2009-11-11 深圳职业技术学院 Distributed data monitoring and early warning system in experimental environment
CN104463363A (en) * 2014-12-03 2015-03-25 浙江图讯科技有限公司 Method, device and system for giving early warning about production risk
CN205281726U (en) * 2016-01-01 2016-06-01 朱立才 Laboratory security protection monitored control system based on video analysis
CN106530633A (en) * 2016-09-28 2017-03-22 中国人民解放军国防科学技术大学 Intelligent in-event disposal-based security protection method and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
罗春贺: "基于物联网技术的地铁安全监控系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109443669B (en) * 2018-09-30 2021-03-26 深圳市英威腾电源有限公司 Water leakage detection method and device
CN111350945A (en) * 2018-12-24 2020-06-30 无锡热能在线科技有限公司 Method for detecting medium leakage of system pipeline
CN113671887A (en) * 2021-08-30 2021-11-19 济南诚博信息科技有限公司 Multi-piece equipment state monitoring system based on point inspection customized repair reference

Similar Documents

Publication Publication Date Title
CN105092811B (en) Remote supervising system and method for city secondary water supply quality safety
CN107945472A (en) A kind of Laboratory Monitoring early warning system based on cloud service
CN107578599A (en) A kind of intelligent wireless cigarette sense fire alarm monitoring system
CN108648124A (en) A kind of smart city fire-fighting Internet of Things big data management system
CN107748945A (en) A kind of wisdom site staff management system
CN108898528A (en) A kind of reasoning by cases method towards hazardous chemical accident emergency aid decision
CN103325205B (en) Based on inside fire Forecasting Methodology and the system of radial base neural net
CN102708645B (en) Ship-cabin chain fire-disaster alarming priority assessment method
CN207587126U (en) A kind of intelligent wireless cigarette sense fire alarm monitoring system
CN107918993A (en) Wisdom Safe Campus big data safe early warning platform
Sung et al. Multi-sensor wireless signal aggregation for environmental monitoring system via multi-bit data fusion
CN107403158A (en) A kind of personnel video frequency identifying method on duty and intelligent subscriber information carrying means
CN107294213A (en) A kind of grid equipment intelligent monitor system
CN105898898A (en) Information monitoring system based on wireless sensor network
CN109118704A (en) A kind of ship networking fire-proof and theft-proof intelligent fire fighting alarm system
CN208172972U (en) A kind of smart home system based on zigbee
CN201445722U (en) Automatic alarming and extinguishing system for fire disaster of large building
Khalid et al. A smart wireless sensor network node for fire detection
CN114584597A (en) Intelligent monitoring fire-fighting system based on cloud system
CN106703887B (en) Secondary gas explosion determination method during mine heat power disaster assistance
CN206557950U (en) A kind of prairie fire monitoring warning device based on satellite remote sensing images
Upadhyay et al. An architecture for an integrated fire emergency response system for the built environment
Ganesh et al. SMART system for hazardous gases detection and alert system using internet of things
CN104522926A (en) Fire disaster rescue positioning helmet
CN208077386U (en) Equipment working state monitors 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
RJ01 Rejection of invention patent application after publication

Application publication date: 20180420

RJ01 Rejection of invention patent application after publication