CN112729411A - Distributed drug warehouse environment monitoring method based on GA-RNN - Google Patents
Distributed drug warehouse environment monitoring method based on GA-RNN Download PDFInfo
- 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
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
Description
技术领域technical field
本发明涉及药品信息处理领域,特别设计一种基于GA-RNN的分布式药品库房环境监测方法。The invention relates to the field of drug information processing, and particularly designs a distributed drug storeroom environment monitoring method based on GA-RNN.
背景技术Background technique
生产药品及药品存储仓库的环境温湿度的正常对药品的安全存储是非常重要的,通常药品的存储环境的温湿度都是由监管人员实时观测,然而对于大型的药品存储库房,对温度的全天监测需要浪费大量的人力及财力,造成大量的资源浪费,此外,为了更安全的药品存储环境,仅仅对环境的监测是远远不够,必须对环境有一定的预判能力,这些对监管人员是非常困难的,因此,亟待提出一种药房智能监控系统,来保证药品的安全存储。The normal temperature and humidity of the production of drugs and drug storage warehouses are very important for the safe storage of drugs. Usually, the temperature and humidity of the drug storage environment are observed by supervisors in real time. Daily monitoring requires a lot of waste of manpower and financial resources, resulting in a lot of waste of resources. In addition, for a safer drug storage environment, only monitoring the environment is far from enough. It is necessary to have a certain ability to predict the environment. It is very difficult. Therefore, it is urgent to propose an intelligent monitoring system for pharmacies to ensure the safe storage of medicines.
发明内容SUMMARY OF THE INVENTION
为了解决上述存在问题。本发明提出一种基于GA-RNN的分布式药品库房环境监测方法。为达此目的:In order to solve the above problems. The invention proposes a distributed medicine warehouse environment monitoring method based on GA-RNN. For this purpose:
本发明提出一种基于GA-RNN的分布式药品库房环境监测方法,其特征在于:The present invention proposes a GA-RNN-based distributed drug warehouse environment monitoring method, which is characterized in that:
步骤1:把历史温湿度传感器组采集的数据集S上传到上位机;Step 1: Upload the data set S collected by the historical temperature and humidity sensor group to the host computer;
步骤2:使用历史温度集训练GA-RNN分布式预测模型;Step 2: Use the historical temperature set to train the GA-RNN distributed prediction model;
步骤3:使用训练好的GA-RNN分布式预测模型对仓库实时采集温湿度进行预测;Step 3: Use the trained GA-RNN distributed prediction model to predict the real-time collection of temperature and humidity in the warehouse;
步骤4:如果预测温湿度出现异常,则开启警报系统,否则,在上位机显示界面正常显示温度波形。Step 4: If the predicted temperature and humidity are abnormal, turn on the alarm system, otherwise, display the temperature waveform normally on the display interface of the host computer.
作为本发明的进一步改进,所述步骤1中数据集S包含N个分布式传感器采集的温湿度数据可表示为:As a further improvement of the present invention, in the step 1, the data set S includes the temperature and humidity data collected by N distributed sensors, which can be expressed as:
S=[S1 S2 ... SN] (1)S=[S 1 S 2 ... S N ] (1)
其中,表示采集温度数据组,表示采集湿度数据组,k表示数据长度,且 in, represents the collection of temperature data sets, represents the collected humidity data group, k represents the data length, and
作为本发明的进一步改进,所述步骤2中GA-RNN模型训练分为RNN组训练和GA权重训练,RNN组训练表示为:As a further improvement of the present 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 expressed as:
其中,RNN(·)表示RNN训练模型, Among them, RNN( ) represents the RNN training model,
作为本发明的进一步改进,所述步骤2GA权重训练表示为:As a further improvement of the present invention, the step 2GA weight training is expressed as:
P=GA([R1 R2 ... RN]T) (4)P=GA([R 1 R 2 ... R N ] T ) (4)
P=[P1 P2 ... PN] (5)P=[P 1 P 2 ... P N ] (5)
其中,GA(·)是遗传算法寻优函数,Pi表示第i个传感器组所占权重,|| ||F表示计算向量的Frobenius范数。Among them, GA(·) is the genetic algorithm optimization function, Pi represents the weight of the i -th sensor group, and || || F represents the Frobenius norm of the calculation vector.
作为本发明的进一步改进,所述步骤3温湿度异常情况判别表示为:As a further improvement of the present invention, the abnormal condition of temperature and humidity in the step 3 is discriminated and expressed as:
w=max([RNN(S1) RNN(S2) ... RNN(SN)])·0.6 (9)w=max([RNN(S 1 ) RNN(S 2 ) ... RNN(S N )])·0.6 (9)
其中,w为温湿度异常判断阈值,H=1时,表示温湿度判断异常,max(·)表示求最大值函数。Among them, w is the judgment threshold of abnormal temperature and humidity, when H=1, it means that the judgment of temperature and humidity is abnormal, and max(·) represents the function of finding the maximum value.
本发明一种基于GA-RNN的分布式药品库房环境监测方法,有益效果在于:A GA-RNN-based distributed medicine warehouse environment monitoring method of the present invention has the following beneficial effects:
1.本发明利用分布式温湿度传感器组,能够对库房温度全方位监测。1. The present invention utilizes distributed temperature and humidity sensor groups, which can monitor the temperature of the warehouse in an all-round way.
2.本发明建立GA-RNN温湿度预测模型,增减了温湿度预测的鲁棒性与准确度。2. The present invention establishes a GA-RNN temperature and humidity prediction model, which increases or decreases the robustness and accuracy of temperature and humidity prediction.
3.本发明算法复杂度低,实时性强。3. The algorithm of the present invention has low complexity and strong real-time performance.
4.本发明硬件系统实现简单,成本低。4. The hardware system of the present invention is simple in implementation and low in cost.
附图说明Description of drawings
图1系统流程图。Figure 1 system flow chart.
具体实施方式Detailed ways
本发明提出一种基于GA-RNN的分布式药品库房环境监测方法。The invention proposes a distributed medicine warehouse environment monitoring method based on GA-RNN.
下面结合附图与具体实施方式对本发明进一步描述:The present invention is further described below in conjunction with the accompanying drawings and specific embodiments:
如图1所示,本发明提出一种基于GA-RNN的分布式药品库房环境监测方法主要分为两个部分,首先是离线GA-RNN模型训练阶段,把历史温湿度传感器组采集的数据集S上传到上位机;使用历史温度集训练GA-RNN分布式预测模型,其中,N=128,k=512。As shown in Figure 1, the present invention proposes a GA-RNN-based distributed drug warehouse environment monitoring method which is mainly divided into two parts. The first is the offline GA-RNN model training phase, where the data sets collected by the historical temperature and humidity sensor groups are collected. S is uploaded to the upper computer; the GA-RNN distributed prediction model is trained using the historical temperature set, where N=128, k=512.
数据集S包含N个分布式传感器采集的温湿度数据可表示为:The data set S contains the temperature and humidity data collected by N distributed sensors, which can be expressed as:
S=[S1 S2 ... SN] (1)S=[S 1 S 2 ... S N ] (1)
其中,表示采集温度数据组,表示采集湿度度数据组,k表示数据长度,且 in, represents the collection of temperature data sets, represents the collected humidity data group, k represents the data length, and
GA-RNN模型训练分为RNN组训练和GA权重训练,RNN组训练表示为:The GA-RNN model training is divided into RNN group training and GA weight training. The RNN group training is expressed as:
其中,RNN(·)表示RNN训练模型, Among them, RNN( ) represents the RNN training model,
GA权重训练表示为:GA weight training is expressed as:
P=GA([R1 R2 ... RN]T) (4)P=GA([R 1 R 2 ... R N ] T ) (4)
P=[P1 P2 ... PN] (5)P=[P 1 P 2 ... P N ] (5)
其中,GA(·)是遗传算法寻优函数,Pi表示第i个传感器组所占权重,|| ||F表示计算向量的Frobenius范数。Among them, GA(·) is the genetic algorithm optimization function, Pi represents the weight of the i -th sensor group, and || || F represents the Frobenius norm of the calculation vector.
最后是GA-RNN模型实时监测阶段,使用训练好的GA-RNN分布式预测模型对仓库实时采集温湿度进行预测;如果预测温湿度出现异常,则开启警报系统,否则,在上位机显示界面正常显示温度波形。Finally, in the real-time monitoring stage of the GA-RNN model, the trained GA-RNN distributed prediction model is used to predict the real-time collection of temperature and humidity in the warehouse; if the predicted temperature and humidity are abnormal, the alarm system is turned on, otherwise, the display interface on the host computer is normal. Displays the temperature waveform.
温湿度异常情况判别表示为:The judgment of abnormal temperature and humidity is expressed as:
w=max([RNN(S1) RNN(S2) ... RNN(SN)])·0.6 (9)w=max([RNN(S 1 ) RNN(S 2 ) ... RNN(S N )])·0.6 (9)
其中,w为温湿度异常判断阈值,H=1时,表示温湿度判断异常,max(·)表示求最大值函数。Among them, w is the judgment threshold of abnormal temperature and humidity, when H=1, it means that the judgment of temperature and humidity is abnormal, and max(·) represents the function of finding the maximum value.
以上所述,仅是本发明的较佳实施例而已,并非是对本发明作任何其他形式的限制,而依据本发明的技术实质所作的任何修改或等同变化,仍属于本发明所要求保护的范围。The above are only preferred embodiments of the present invention, and are not intended to limit the present invention in any other form, and any modifications or equivalent changes made according to the technical essence of the present invention still fall within the scope of protection of the present invention. .
具体实施例需要提及所有附图Specific embodiments need to refer to all figures
Claims (5)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110046118.8A CN112729411B (en) | 2021-01-14 | 2021-01-14 | A 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 | A 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 | A distributed drug warehouse environment monitoring method based on GA-RNN |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112729411B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115564282A (en) * | 2022-10-21 | 2023-01-03 | 珠海格力电器股份有限公司 | A kind of early warning method, device, electronic equipment and storage medium |
Citations (7)
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 | Temperature and humidity early warning system for chain pharmacies based on improved long and short-term memory neural network |
CN109959123A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | An energy-saving method for air-conditioning based on genetic algorithm and long short-term memory 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 | A method and device for direct interval prediction of wind energy based on feedback neural network |
-
2021
- 2021-01-14 CN CN202110046118.8A patent/CN112729411B/en active Active
Patent Citations (7)
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 | Temperature and humidity early warning system for chain pharmacies based on improved long and short-term memory neural network |
CN109959123A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | An energy-saving method for air-conditioning based on genetic algorithm and long short-term memory 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 | A method and device for direct interval prediction of wind energy based on feedback neural network |
Non-Patent Citations (1)
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》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115564282A (en) * | 2022-10-21 | 2023-01-03 | 珠海格力电器股份有限公司 | A kind of early warning method, device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN112729411B (en) | 2022-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114894411A (en) | Bridge health monitoring method and system based on wireless sensor network | |
CN105758450A (en) | Fire protection pre-warning sensing system building method based on multiple sensor emergency robots | |
EP4120148A1 (en) | Parameter adjusting device, inference device, parameter adjusting method, and parameter adjusting program | |
CN111755120B (en) | A Cognitive Impairment Prediction Method Based on Edge Intelligence and Multimodal Perception | |
CN118053261B (en) | Anti-spoofing early warning method, device, equipment and medium for smart campus | |
CN114235050A (en) | Marine environment monitoring and early warning method, device and system | |
CN105225007A (en) | A kind of sector runnability method for comprehensive detection based on GABP neural network and system | |
CN104637326A (en) | Vehicle driving safety system based on cloud service | |
CN108926352A (en) | A kind of driving fatigue detection method and system | |
CN115760210A (en) | Medicine sales prediction system and method based on IPSO-LSTM model | |
CN112729411B (en) | A distributed drug warehouse environment monitoring method based on GA-RNN | |
CN113177722A (en) | Intelligent supervision cloud platform for operation safety of construction engineering personnel based on image video real-time monitoring and analyzing technology | |
CN116911610A (en) | Methods and systems for transport vehicle driving safety risk monitoring, assessment and early warning | |
CN116779125A (en) | Intelligent medical management system and method based on big data | |
CN118571081A (en) | Airport bird condition monitoring system and method | |
CN112998661A (en) | Non-contact type children pain identification method and system | |
CN111243214A (en) | A fire monitoring system and method for industrial computer room based on machine learning | |
CN113267217B (en) | Bridge group monitoring system and bridge group monitoring method | |
CN118436309A (en) | Pre-warning model system for inducing unsafe behavior of underground coal mine mining operation personnel in physical and mental states | |
CN117612013A (en) | An online monitoring method and system for forestry pests and diseases | |
CN113762092A (en) | A method, system, robot and storage medium for detecting medical noise of hospital users | |
CN118568638B (en) | Mine car abnormal fault detection method, device, equipment, medium and product | |
CN115862852A (en) | Health detection method and device, computer equipment and storage medium | |
CN119251026B (en) | A smart campus management system based on student safety | |
CN118094135B (en) | A water quality detection method based on big data comparison |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20250417 Address after: Room 1011-1019, 10th Floor, Building A, Lianhui Science and Technology Innovation Center, No. 88 Lianhui Street, Xixing Street, Binjiang District, Hangzhou City, Zhejiang Province 311000 Patentee after: HANGZHOU NENGGONG TECHNOLOGY CO.,LTD. Country or region after: China Address before: No. 99 Jiangning Road, Nanjing District hirokage 210000 cities in Jiangsu Province Patentee before: JINLING INSTITUTE OF TECHNOLOGY Country or region before: China |