CN112729411A - Distributed drug warehouse environment monitoring method based on GA-RNN - Google Patents

Distributed drug warehouse environment monitoring method based on GA-RNN Download PDF

Info

Publication number
CN112729411A
CN112729411A CN202110046118.8A CN202110046118A CN112729411A CN 112729411 A CN112729411 A CN 112729411A CN 202110046118 A CN202110046118 A CN 202110046118A CN 112729411 A CN112729411 A CN 112729411A
Authority
CN
China
Prior art keywords
temperature
rnn
humidity
distributed
monitoring method
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.)
Granted
Application number
CN202110046118.8A
Other languages
Chinese (zh)
Other versions
CN112729411B (en
Inventor
王逸之
杨忠
林敏�
张艳
余振中
满朝媛
周雨
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.)
Jinling Institute of Technology
Original Assignee
Jinling Institute of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jinling Institute of Technology filed Critical Jinling Institute of Technology
Priority to CN202110046118.8A priority Critical patent/CN112729411B/en
Publication of CN112729411A publication Critical patent/CN112729411A/en
Application granted granted Critical
Publication of CN112729411B publication Critical patent/CN112729411B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Genetics & Genomics (AREA)
  • Physiology (AREA)
  • Emergency Alarm Devices (AREA)

Abstract

A distributed drug warehouse environment monitoring method based on GA-RNN. Aiming at the problems that the requirements of medicines on the temperature and the humidity of the environment of a storage warehouse are high, the quality of the medicines is easily damaged by abnormal temperature and humidity, and the like, the distributed type medicine warehouse environment monitoring method is designed, and temperature and humidity monitoring is carried out on each space of the medicine warehouse in real time by using a distributed type temperature and humidity monitoring instrument set. Comprises an upper computer and a lower computer. The lower computer part mainly comprises a distributed temperature and humidity monitor group and a wireless sensor, and the upper computer cloud platform is mainly used for data receiving, data analysis, data display, data early warning and the like. The upper computer platform firstly trains a genetic algorithm-recurrent neural network prediction model by using historical temperature and humidity information, then predicts the environment temperature by using temperature and humidity data acquired by a distributed temperature and humidity sensor in real time, and carries out abnormal temperature early warning by using the upper computer when the abnormal temperature and humidity condition is predicted to appear. So as to effectively early warn the abnormal state of the drug environment and ensure the drug safety.

Description

Distributed drug warehouse environment monitoring method based on GA-RNN
Technical Field
The invention relates to the field of medicine information processing, in particular to a distributed medicine storehouse environment monitoring method based on GA-RNN.
Background
The environment humiture of production medicine and medicine storage warehouse is normal to the safe storage of medicine very important, the humiture of the storage environment of medicine is all observed by supervisory personnel in real time usually, however to large-scale medicine storage warehouse, to the whole day monitoring of temperature need waste a large amount of manpower and financial resources, cause a large amount of wasting of resources, in addition, in order to safer medicine storage environment, only be far away not enough to the monitoring of environment, must have certain prejudgement ability to the environment, these are very difficult to supervisory personnel, therefore, need to propose a drugstore intelligent monitoring system urgently, guarantee the safe storage of medicine.
Disclosure of Invention
To solve the above existing problems. The invention provides a distributed drug warehouse environment monitoring method based on GA-RNN. To achieve this object:
the invention provides a GA-RNN-based distributed drug warehouse environment monitoring method, which is characterized by comprising the following steps of:
step 1: uploading a data set S collected by a historical temperature and humidity sensor group to an upper computer;
step 2: training a GA-RNN distributed prediction model by using a historical temperature set;
and step 3: forecasting real-time temperature and humidity collection of the warehouse by using a trained GA-RNN distributed forecasting model;
and 4, step 4: if the temperature and the humidity are predicted to be abnormal, an alarm system is started, otherwise, the temperature waveform is normally displayed on a display interface of the upper computer.
As a further improvement of the present invention, the data set S in step 1 includes temperature and humidity data collected by N distributed sensors, which can be represented as:
S＝[S1 S2 ... SN] (1)
Figure BDA0002897398370000011
wherein,
Figure BDA0002897398370000012
it is indicated that the temperature data set is collected,
Figure BDA0002897398370000013
representing the acquisition of a moisture data set, k represents the data length, and
Figure BDA0002897398370000021
as a further improvement of the invention, the GA-RNN model training in the step 2 is divided into RNN group training and GA weight training, and the RNN group training is represented as:
Figure BDA0002897398370000022
wherein RNN (-) represents the RNN training model,
Figure BDA0002897398370000023
as a further improvement of the present invention, the step 2GA weight training is represented as:
P＝GA([R1 R2 ... RN]T) (4)
P＝[P1 P2 ... PN] (5)
Figure BDA0002897398370000024
wherein GA (-) is a genetic algorithm optimization function, PiRepresents the weight occupied by the ith sensor group, | | | | | non-woven phosphorFRepresenting the Frobenius norm of the calculated vector.
As a further improvement of the present invention, in the step 3, the determination of the abnormal temperature and humidity condition is represented as:
Figure BDA0002897398370000025
Figure BDA0002897398370000026
w＝max([RNN(S1) RNN(S2) ... RNN(SN)])·0.6 (9)
where w is a temperature and humidity abnormality determination threshold, and when H is 1, it indicates that the temperature and humidity determination is abnormal, and max (·) indicates a maximum value calculation function.
The invention discloses a GA-RNN-based distributed drug warehouse environment monitoring method, which has the beneficial effects that:
1. the invention can monitor the temperature of the storehouse in all directions by utilizing the distributed temperature and humidity sensor group.
2. According to the invention, a GA-RNN temperature and humidity prediction model is established, and the robustness and accuracy of temperature and humidity prediction are increased and decreased.
3. The algorithm of the invention has low complexity and strong real-time performance.
4. The hardware system of the invention is simple to realize and has low cost.
Drawings
FIG. 1 is a system flow diagram.
Detailed Description
The invention provides a distributed drug warehouse environment monitoring method based on GA-RNN.
The invention is further described in the following detailed description with reference to the drawings in which:
as shown in fig. 1, the distributed pharmacy warehouse environment monitoring method based on GA-RNN provided by the present invention is mainly divided into two parts, and firstly, an off-line GA-RNN model training phase is performed to upload a data set S collected by a historical temperature and humidity sensor group to an upper computer; the GA-RNN distributed prediction model is trained using a historical temperature set, where N is 128 and k is 512.
The data set S contains humiture data collected by N distributed sensors, which can be expressed as:
S＝[S1 S2 ... SN] (1)
Figure BDA0002897398370000031
wherein,
Figure BDA0002897398370000032
it is indicated that the temperature data set is collected,
Figure BDA0002897398370000033
indicating the collection of a humidity data set, k indicates the data length, and
Figure BDA0002897398370000034
the GA-RNN model training is divided into RNN group training and GA weight training, and the RNN group training is expressed as follows:
Figure BDA0002897398370000035
wherein RNN (-) represents the RNN training model,
Figure BDA0002897398370000036
GA weight training is expressed as:
P＝GA([R1 R2 ... RN]T) (4)
P＝[P1 P2 ... PN] (5)
Figure BDA0002897398370000037
wherein GA (-) is a genetic algorithm optimization function, PiRepresents the weight occupied by the ith sensor group, | | | | | non-woven phosphorFRepresenting the Frobenius norm of the calculated vector.
Finally, a GA-RNN model real-time monitoring stage, wherein a trained GA-RNN distributed prediction model is used for predicting the temperature and humidity acquired by the warehouse in real time; if the temperature and the humidity are predicted to be abnormal, an alarm system is started, otherwise, the temperature waveform is normally displayed on a display interface of the upper computer.
The judgment of the temperature and humidity abnormal condition is expressed as follows:
Figure BDA0002897398370000041
Figure BDA0002897398370000042
w＝max([RNN(S1) RNN(S2) ... RNN(SN)])·0.6 (9)
where w is a temperature and humidity abnormality determination threshold, and when H is 1, it indicates that the temperature and humidity determination is abnormal, and max (·) indicates a maximum value calculation function.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.
Detailed description of the preferred embodimentsreference is made to the accompanying drawings

Claims (5)

1. A GA-RNN-based distributed drug warehouse environment monitoring method comprises the following specific steps:
step 1: uploading a data set S collected by a historical temperature and humidity sensor group to an upper computer;
step 2: training a GA-RNN distributed prediction model by using a historical temperature set;
and step 3: forecasting real-time temperature and humidity collection of the warehouse by using a trained GA-RNN distributed forecasting model;
and 4, step 4: if the temperature and the humidity are predicted to be abnormal, an alarm system is started, otherwise, the temperature waveform is normally displayed on a display interface of the upper computer.
2. The distributed GA-RNN-based drug storage environment monitoring method according to claim 1, wherein the method comprises the following steps:
in the step 1, the data set S includes temperature and humidity data acquired by N distributed sensors, which may be represented as:
S＝[S1 S2 ... SN] (1)
Figure FDA0002897398360000011
wherein,
Figure FDA0002897398360000012
it is indicated that the temperature data set is collected,
Figure FDA0002897398360000013
indicating the collection of a humidity data set, k indicates the data length, and
Figure FDA0002897398360000014
3. the distributed GA-RNN-based drug storage environment monitoring method according to claim 1, wherein the method comprises the following steps:
in the step 2, the GA-RNN model training is divided into RNN group training and GA weight training, wherein the RNN group training is represented as:
Figure FDA0002897398360000015
wherein RNN (-) represents the RNN training model,
Figure FDA0002897398360000018
4. the distributed GA-RNN-based drug storage environment monitoring method according to claim 1, wherein the method comprises the following steps:
the step 2GA weight training is represented as:
P＝GA([R1 R2 ... RN]T) (4)
P＝[P1 P2 ... PN] (5)
Figure FDA0002897398360000016
wherein GA (-) is a genetic algorithm optimization function, PiRepresents the weight occupied by the ith sensor group, | | | | | non-woven phosphorFRepresenting the Frobenius norm of the calculated vector.
5. The distributed GA-RNN-based drug storage environment monitoring method according to claim 1, wherein the method comprises the following steps:
and 3, judging the abnormal temperature and humidity conditions in the step:
Figure FDA0002897398360000017
Figure FDA0002897398360000021
w＝max([RNN(S1) RNN(S2) ... RNN(SN)])·0.6 (9)
where w is a temperature and humidity abnormality determination threshold, and when H is 1, it indicates that the temperature and humidity determination is abnormal, and max (·) indicates a maximum value calculation function.
CN202110046118.8A 2021-01-14 2021-01-14 Distributed drug warehouse environment monitoring method based on GA-RNN Active CN112729411B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110046118.8A CN112729411B (en) 2021-01-14 2021-01-14 Distributed drug warehouse environment monitoring method based on GA-RNN

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110046118.8A CN112729411B (en) 2021-01-14 2021-01-14 Distributed drug warehouse environment monitoring method based on GA-RNN

Publications (2)

Publication Number Publication Date
CN112729411A true CN112729411A (en) 2021-04-30
CN112729411B CN112729411B (en) 2022-09-13

Family

ID=75592897

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110046118.8A Active CN112729411B (en) 2021-01-14 2021-01-14 Distributed drug warehouse environment monitoring method based on GA-RNN

Country Status (1)

Country Link
CN (1) CN112729411B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060234382A1 (en) * 2005-04-19 2006-10-19 Iaq Laboratories International, Llc System and Method for Predicting Mold Growth in an Environment
CN106228034A (en) * 2016-07-12 2016-12-14 丽水学院 A kind of method for mixing and optimizing of tumor-related gene search
CN109243172A (en) * 2018-07-25 2019-01-18 华南理工大学 Traffic flow forecasting method based on genetic algorithm optimization LSTM neural network
CN109708689A (en) * 2018-11-14 2019-05-03 沈阳理工大学 Based on the chain pharmacy temperature and humidity early warning system for improving long Memory Neural Networks in short-term
CN109959123A (en) * 2019-03-11 2019-07-02 浙江工业大学 A kind of energy-saving method for air conditioner based on genetic algorithm and shot and long term memory Recognition with Recurrent Neural Network
CN111060815A (en) * 2019-12-17 2020-04-24 西安工程大学 GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method
CN111784535A (en) * 2020-06-29 2020-10-16 中国人民解放军国防科技大学 Wind energy direct interval prediction method and device based on feedback neural network

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060234382A1 (en) * 2005-04-19 2006-10-19 Iaq Laboratories International, Llc System and Method for Predicting Mold Growth in an Environment
CN106228034A (en) * 2016-07-12 2016-12-14 丽水学院 A kind of method for mixing and optimizing of tumor-related gene search
CN109243172A (en) * 2018-07-25 2019-01-18 华南理工大学 Traffic flow forecasting method based on genetic algorithm optimization LSTM neural network
CN109708689A (en) * 2018-11-14 2019-05-03 沈阳理工大学 Based on the chain pharmacy temperature and humidity early warning system for improving long Memory Neural Networks in short-term
CN109959123A (en) * 2019-03-11 2019-07-02 浙江工业大学 A kind of energy-saving method for air conditioner based on genetic algorithm and shot and long term memory Recognition with Recurrent Neural Network
CN111060815A (en) * 2019-12-17 2020-04-24 西安工程大学 GA-Bi-RNN-based high-voltage circuit breaker fault diagnosis method
CN111784535A (en) * 2020-06-29 2020-10-16 中国人民解放军国防科技大学 Wind energy direct interval prediction method and device based on feedback neural network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李树刚 等: "基于循环神经网络的煤矿工作面瓦斯浓度预测模型研究", 《煤炭科学技术》 *

Also Published As

Publication number Publication date
CN112729411B (en) 2022-09-13

Similar Documents

Publication Publication Date Title
CN105979220B (en) Household old age monitoring intelligent mobile trolley, monitoring system and monitoring method thereof
CN105758450B (en) Met an urgent need based on multisensor the fire-fighting early warning sensory perceptual system construction method of robot
CN107808139B (en) Real-time monitoring threat analysis method and system based on deep learning
CN111392619B (en) Tower crane early warning method, device and system and storage medium
CN113793234B (en) Wisdom garden platform based on digit twin technique
CN104156819B (en) Method for correcting error and device are observed in a kind of key post unsafe acts automatically
CN116227363B (en) Flood early warning method based on sensor distribution optimization
CN113204229B (en) Intelligent self-checking system of control system of thermal generator set
CN114235050A (en) Marine environment monitoring and early warning method, device and system
WO2023063887A2 (en) Method and apparatus for predicting state of wind turbine blade, and device and storage medium therefor
CN113177722A (en) Intelligent supervision cloud platform for operation safety of construction engineering personnel based on image video real-time monitoring and analyzing technology
CN117235443A (en) Electric power operation safety monitoring method and system based on edge AI
CN118244126A (en) New energy automobile battery detection method and system based on integrated sensor
CN112729411B (en) Distributed drug warehouse environment monitoring method based on GA-RNN
CN109649166A (en) Vehicle drive method for managing and monitoring, device and system
CN108921223B (en) Server cooling system, control method, computer program and computer
CN110278285A (en) Intelligent safety helmet remote supervision system and method based on ONENET platform
Pangione et al. A taxonomy approach to failure mode analysis for use in predictive condition monitoring
CN110031043B (en) Civil engineering building structure real-time intelligent monitoring system
CN109959820A (en) Monitor the intelligent Detection and its method of steel tower real-time status
CN117113255A (en) Liquefied natural gas safety monitoring system based on status monitoring and automatic content identification
CN107505892A (en) A kind of method and system of miniature data center's refrigeration plant intellectual monitoring
CN115641549B (en) Health monitoring method and system for main propulsion diesel unit
CN110517731A (en) Genetic test quality monitoring data processing method and system
CN113267217B (en) Bridge group monitoring system and bridge group monitoring method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant