CN111256943A - Laboratory ventilation abnormity detection method and system - Google Patents
Laboratory ventilation abnormity detection method and systemDownload PDFInfo
- Publication number
- CN111256943A CN111256943ACN202010093761.1ACN202010093761ACN111256943ACN 111256943 ACN111256943 ACN 111256943ACN 202010093761 ACN202010093761 ACN 202010093761ACN 111256943 ACN111256943 ACN 111256943A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- data
- real
- ventilation
- speed data
- 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
Images
Classifications
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M9/00—Aerodynamic testing; Arrangements in or on wind tunnels
- G01M9/08—Aerodynamic models
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Ventilation (AREA)
Abstract
Description
Technical Field
The invention relates to the technical field of laboratory safety, in particular to a laboratory ventilation abnormity detection method and system.
Background
The laboratory is an important place for scientific research units to practice teaching and engage in scientific research, and has important position and function in cultivating innovative talents and developing scientific technology. In the chemical experiment, poisonous and harmful gas can be generated, if the harmful gas is not discharged from a laboratory in time, not only certain damage can be caused to equipment, but also air quality in the laboratory can be polluted, and harm can be caused to the body and mind of experimenters. To avoid inhalation of some harmful chemicals by laboratory workers, the laboratory should have good ventilation conditions. A fume hood is used to vent some of the vapors, gases and particulates (fumes, soot, dust, etc.) out of the laboratory through a vent line.
However, in the air exhaust process, the blower of the fume hood may break down, or the pipeline breaks, so that the air cannot be effectively exhausted out of the laboratory, the air exhaust effect is affected, and the harm is caused to the experimenters. Therefore, how to effectively detect whether the ventilation of the laboratory is abnormal is extremely important.
The foregoing description is provided for general background information and is not admitted to be prior art.
Disclosure of Invention
The invention aims to provide a laboratory ventilation abnormity detection method and system capable of detecting whether a ventilation pipeline is abnormal.
The invention provides a laboratory ventilation abnormity detection method, which comprises the steps of S1, S2 and S3, wherein the step S1 is to collect real-time wind speed data in a ventilation pipeline in real time; step S2 is to collect the real-time wind speed data, and construct an anomaly recognition model from a plurality of wind speed data over a period of time; step S3 is to detect the real-time wind speed data by a mathematical statistic method according to the abnormality recognition model and determine whether the ventilation duct is abnormal.
Further, in step S1, multiple sets of real-time wind speed data are collected simultaneously in the ventilation duct.
Further, the step S2 includes S21 and S22, the step S21 is to build a time sliding window model for the real-time wind speed data, and the step S22 is to build the abnormality recognition model for a plurality of sliding window data in the time sliding window model.
Further, the step S21 includes steps S211 and S212, the step S211 is to form the real-time wind speed data into sequence data according to the collection time, the step S212 is to maintain a window with a constant size for the sequence data, store the latest data, when new data comes, the oldest data will expire, the window will store the latest data and remove the oldest data, and form the time sliding window model.
Further, the step S22 includes steps S221 and S222, where the step S221 is to filter out median med in the sliding window data, and the step S222 is to construct the anomaly identification model by using the lazida criterion and using med ± 3 σ as an interval, where σ is a standard deviation in the sliding window data.
Further, in the step S1, multiple sets of real-time wind speed data are collected simultaneously in the ventilation duct; the step S3 includes steps S31 and S32, the step S31 is to determine whether the real-time wind speed data is abnormal according to the abnormality recognition model by using the mathematical statistics method, the step S32 is executed when the abnormality occurs, and the step S32 is to determine that the ventilation duct is abnormal when more than half of the plurality of sets of real-time wind speed data are abnormal.
Further, in the step S31, the method for determining whether the real-time wind speed data is abnormal is that if any data in the sliding window data is not within the med ± 3 σ interval, it is determined that the real-time wind speed data is abnormal.
Further, in the step S31, the method for determining whether the real-time wind speed data is abnormal is that two adjacent data in the sliding window data are equal, and it is determined that the real-time wind speed data is abnormal.
The invention also provides a laboratory ventilation abnormity detection system which comprises a plurality of wind speed sensors, a sensing network and a background server and is used for realizing the laboratory ventilation abnormity detection method.
Further, the background server is used for sending alarm information when the ventilation pipeline is abnormal.
The laboratory ventilation abnormity detection method and the laboratory ventilation abnormity detection system provided by the invention utilize a mathematical statistics method to establish an abnormity identification model to detect the ventilation condition of the laboratory, and the method is simple and easy to implement. And time sequence data is processed through a sliding window model, and a plurality of groups of detection data are simultaneously analyzed, so that errors caused by individual reasons generated by too small data quantity or damage of a single data acquisition point are avoided. If the abnormity is detected, the abnormity information is pushed in time, the danger caused by the ventilation fault is avoided, and the safety of the laboratory is improved.
Drawings
FIG. 1 is a schematic diagram of a laboratory ventilation anomaly detection method according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a laboratory ventilation anomaly detection system according to an embodiment of the present invention;
fig. 3 is a schematic distribution diagram of data of a sliding window in the laboratory ventilation anomaly detection method shown in fig. 1.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1 to 3, a method for detecting abnormal ventilation in a laboratory according to an embodiment of the present invention includes the following steps:
s1: collecting real-time wind speed data in the ventilation pipeline 10 in real time;
s2: collecting real-time wind speed data, and constructing a plurality of wind speed data in a period of time into an abnormal recognition model;
s3: and detecting real-time wind speed data by using a mathematical statistical method according to the abnormality identification model and judging whether the ventilation duct 10 is abnormal or not.
Referring to fig. 1, in step S1, wind speed data collection points are disposed at multiple positions in the ventilation duct 10, so as to avoid the influence of data deviation on the detection result caused by instrument damage and the like at a single data collection point. In other embodiments, the positions of the specific wind speed data acquisition points can be adjusted according to actual conditions, but the number of the wind speed data acquisition points is as large as possible, so that the deviation caused by too small data quantity is avoided.
Step S2 includes S21: respectively establishing a time sliding window model and S22 for a plurality of groups of real-time wind speed data: and constructing an abnormal recognition model for the sliding window data in the time sliding window model. Step S21 includes S211: forming the real-time wind speed data into sequence data according to the acquisition time; s212: maintaining a window with constant size for the sequence data, storing a plurality of latest data, wherein when new data arrives, the oldest data is expired, and the window stores the latest data and removes the oldest data to form a time sliding window model. For example, the window size is k, the latest k data are saved, and the current window data are assumed to be
When new data is present
When the data arrives and is normal data, the window changes, and the data in the window is updated to be normal data
The subsequent data is analogized.
Step S22 includes S221: screening out median med in the sliding window data; s222: and constructing the anomaly identification model by adopting a Laplace criterion and using med +/-3 sigma as an interval. The general control chart method is based on the average value X of the control chart, but X is easily affected by extreme values and anomalies tend to appear as extreme values, so the control chart is built by using the median med of the data set. For example
As sensor node SjData sets within a T period.
In other embodiments, if the number of window data k is large enough, the sliding window data can be regarded as approximately normal distribution, and the situation can be madeBy mean value
The Laviand criterion is applied for the midline.
The lazida standard has intervals med ± c σ of 68%, 95%, and 99.7%, where c ═ 1,2,3 }. In the interval formed by med ± 3 σ, the probability that the measured value does not belong to this interval is 0.3%. As shown in fig. 3, the model consists of three lines: the centerline (ML, Middle line), which is the median of the sensor node data set, and the upper Control line (UCL, UpperControl Limit) and Lower Control line (LCL, Lower Control Limit). By sigmamedRepresenting the standard deviation of the sensor node data set. In specific use, in order to make the data more approximate to a normal distribution and avoid errors, the value of the window data k should be increased as much as possible.
ML＝med (2)
UCL＝med+3σmed(3)
LCL＝med-3σmed(4)
Step S3 includes S31 and S32, and step S31 is performed by determining whether there is an abnormality in the real-time wind speed data according to the abnormality recognition model using a mathematical statistics method, and performing S32 when the abnormality occurs. In step S31, the method for determining whether the real-time wind speed data is abnormal is to determine that the real-time wind speed data is abnormal if any of the sliding window data is not within the interval. I.e. if
If equation (5) is not satisfied, the wind speed data is abnormal data:
wherein ucl and lcl are the upper and lower limits of the control chart model interval respectively,
sampled at time i when
And (5) updating the data of the window.
Meanwhile, in step S31, if two adjacent data in the sliding window data are equal, it is also determined that the real-time wind speed data is abnormal. Since when a wind speed sensor fails, it is possible to produce the same readings in successive sampling instants, i.e.
In step S32, when more than half of the real-time wind speed data sets are abnormal, it is determined that the ventilation duct 10 is abnormal.
The method provided by the embodiment detects the ventilation condition of the laboratory by using mathematical statistics, processes time sequence data through the sliding window model, and constructs the abnormality recognition model. And a plurality of groups of detection data are simultaneously analyzed, so that errors caused by individual reasons generated by too small data quantity or damage of a single data acquisition point are avoided.
Referring to fig. 2, the present embodiment further provides a laboratory ventilation anomaly detection system 20, which includes a plurality of wind speed sensors 21, a sensor network 22 and a background server 23, and is used to implement the laboratory ventilation anomaly detection method. The wind speed sensor 21 is disposed in the ventilation duct 10, and the wind speed sensor 21 is connected to the background server 23 through the sensing network 22, so as to send the collected real-time wind speed data to the background server 23 through the sensing network 22. The background server 23 is configured to construct an anomaly identification model to detect the real-time wind speed data and determine whether the ventilation duct 10 is anomalous, and send alarm information when it is determined that the ventilation duct 10 is anomalous.
The method and the system for detecting the ventilation abnormity of the laboratory utilize a mathematical statistics method to establish an abnormity identification model to detect the ventilation condition of the laboratory, and the method is simple and easy to implement. And time sequence data is processed through a sliding window model, and a plurality of groups of detection data are simultaneously analyzed, so that errors caused by individual reasons generated by too small data quantity or damage of a single data acquisition point are avoided. If the abnormity is detected, the abnormity information is pushed in time, the danger caused by the ventilation fault is avoided, and the safety of the laboratory is improved.
In the drawings, the size and relative sizes of layers and regions may be exaggerated for clarity. It will be understood that when an element such as a layer, region or substrate is referred to as being "formed on," "disposed on" or "located on" another element, it can be directly on the other element or intervening elements may also be present. In contrast, when an element is referred to as being "directly formed on" or "directly disposed on" another element, there are no intervening elements present.
In this document, unless expressly stated or limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms can be understood in a specific case to those of ordinary skill in the art.
As used herein, the meaning of "a plurality" or "a plurality" is two or more unless otherwise specified.
As used herein, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, including not only those elements listed, but also other elements not expressly listed.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A laboratory ventilation abnormity detection method is characterized by comprising the steps of S1, S2 and S3, wherein the step S1 is to collect real-time wind speed data in a ventilation pipeline in real time; step S2 is to collect the real-time wind speed data, and construct an anomaly recognition model from a plurality of wind speed data over a period of time; step S3 is to detect the real-time wind speed data by a mathematical statistic method according to the abnormality recognition model and determine whether the ventilation duct is abnormal.
2. The method for detecting laboratory ventilation abnormality according to claim 1, characterized in that said step S1 is to collect multiple sets of real-time wind speed data simultaneously in said ventilation duct.
3. The method of detecting laboratory ventilation abnormality according to claim 1, wherein said step S2 includes steps S21 and S22, said step S21 is to build a time sliding window model for said real-time wind speed data, and said step S22 is to build said abnormality recognition model for a plurality of sliding window data in said time sliding window model.
4. The method for detecting laboratory ventilation abnormality according to claim 3, wherein said step S21 includes steps S211 and S212, said step S211 forms sequence data by said real-time wind speed data according to the collection time, said step S212 maintains a window of constant size for said sequence data, stores the latest plurality of data, when new data comes, the oldest data will expire, the window will store the latest data and remove the oldest data, forming said time-sliding window model.
5. The laboratory ventilation anomaly detection method according to claim 3, wherein said step S22 includes steps S221 and S222, said step S221 is to screen out median med in said sliding window data, said step S222 is to construct said anomaly identification model using Laplace' S criterion in the interval med ± 3 σ, where σ is the standard deviation in said sliding window data.
6. The method for detecting laboratory ventilation abnormality according to claim 5, wherein said step S1 is to collect multiple sets of real-time wind speed data simultaneously in said ventilation duct; the step S3 includes steps S31 and S32, the step S31 is to determine whether the real-time wind speed data is abnormal according to the abnormality recognition model by using the mathematical statistics method, the step S32 is executed when the abnormality occurs, and the step S32 is to determine that the ventilation duct is abnormal when more than half of the plurality of sets of real-time wind speed data are abnormal.
7. The method for detecting laboratory ventilation abnormality according to claim 6, wherein said step S31 of determining whether or not said real-time wind speed data is abnormal is performed by determining that said real-time wind speed data is abnormal if any of said sliding window data is not within the med ± 3 σ interval.
8. The method for detecting abnormality in laboratory ventilation according to claim 6, wherein said step S31 of determining whether or not said real-time wind speed data is abnormal is performed by determining that said real-time wind speed data is abnormal if two adjacent data in said sliding window data are equal to each other.
9. A laboratory ventilation anomaly detection system is characterized by comprising a plurality of wind speed sensors, a sensing network and a background server and used for realizing the laboratory ventilation anomaly detection method according to any one of claims 1 to 8, wherein the wind speed sensors are deployed in a ventilation pipeline, the wind speed sensors are connected with the background server through the sensing network and used for sending acquired real-time wind speed data to the background server through the sensing network, and the background server is used for constructing an anomaly identification model to detect the real-time wind speed data and judge whether the ventilation pipeline is anomalous or not.
10. The laboratory ventilation anomaly detection system according to claim 9, wherein said background server is configured to send an alarm message when an anomaly occurs in said ventilation duct.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010093761.1ACN111256943A (en) | 2020-02-14 | 2020-02-14 | Laboratory ventilation abnormity detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010093761.1ACN111256943A (en) | 2020-02-14 | 2020-02-14 | Laboratory ventilation abnormity detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111256943Atrue CN111256943A (en) | 2020-06-09 |
Family
ID=70954487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010093761.1APendingCN111256943A (en) | 2020-02-14 | 2020-02-14 | Laboratory ventilation abnormity detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111256943A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033316A (en)* | 2021-03-01 | 2021-06-25 | 湖南长海现代实验室设备有限公司 | Device and method for detecting and controlling show window state of fume hood |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103631681A (en)* | 2013-12-10 | 2014-03-12 | 国家电网公司 | Method for online restoring abnormal data of wind power plant |
| CN207457270U (en)* | 2017-11-10 | 2018-06-05 | 上海汇检菁英科技股份有限公司 | A kind of vent cabinet wind speed monitoring system |
| CN108302329A (en)* | 2018-01-25 | 2018-07-20 | 福建双环能源科技股份有限公司 | A kind of dew point data exception detection method |
| CN109521726A (en)* | 2018-12-19 | 2019-03-26 | 广州九诺实业有限公司 | Laboratory ventilation robot control system(RCS) |
| US20190187680A1 (en)* | 2016-05-09 | 2019-06-20 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection in an industrial environment with haptic feedback and control of data storage and bandwidth |
| CN110542189A (en)* | 2019-08-20 | 2019-12-06 | 北京戴纳实验科技有限公司 | Laboratory ventilation system and method thereof |
- 2020
- 2020-02-14CNCN202010093761.1Apatent/CN111256943A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103631681A (en)* | 2013-12-10 | 2014-03-12 | 国家电网公司 | Method for online restoring abnormal data of wind power plant |
| US20190187680A1 (en)* | 2016-05-09 | 2019-06-20 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection in an industrial environment with haptic feedback and control of data storage and bandwidth |
| CN207457270U (en)* | 2017-11-10 | 2018-06-05 | 上海汇检菁英科技股份有限公司 | A kind of vent cabinet wind speed monitoring system |
| CN108302329A (en)* | 2018-01-25 | 2018-07-20 | 福建双环能源科技股份有限公司 | A kind of dew point data exception detection method |
| CN109521726A (en)* | 2018-12-19 | 2019-03-26 | 广州九诺实业有限公司 | Laboratory ventilation robot control system(RCS) |
| CN110542189A (en)* | 2019-08-20 | 2019-12-06 | 北京戴纳实验科技有限公司 | Laboratory ventilation system and method thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033316A (en)* | 2021-03-01 | 2021-06-25 | 湖南长海现代实验室设备有限公司 | Device and method for detecting and controlling show window state of fume hood |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116975378B (en) | Equipment environment monitoring method and system based on big data | |
| JP6703613B2 (en) | Anomaly detection in data stream | |
| US20210389290A1 (en) | Intelligent Monitoring and Analysis Method for Air Pollution and Device Thereof | |
| CN108289088B (en) | Abnormal traffic detection system and method based on business model | |
| KR101323074B1 (en) | Intelligence network anomaly detection using a type ⅱ fuzzy neural network | |
| CN104363106B (en) | A kind of communicating for power information fault pre-alarming analysis method based on big data technology | |
| JP2018533897A5 (en) | ||
| CN116992391B (en) | Hard carbon process environment-friendly monitoring data acquisition and processing method | |
| CN118130729A (en) | Carbon emission monitoring system and method based on CEMS | |
| CN117540229B (en) | Atmospheric environment monitoring method based on clustering algorithm | |
| CN111256943A (en) | Laboratory ventilation abnormity detection method and system | |
| CN118427046A (en) | An analysis and monitoring system and method based on computer data | |
| Iturbe et al. | On the feasibility of distinguishing between process disturbances and intrusions in process control systems using multivariate statistical process control | |
| CN113655189A (en) | Automatic monitoring data analysis and judgment system for pollution source | |
| CN118250201A (en) | Intranet flow detection method and system based on artificial intelligence | |
| CN113917093A (en) | Air quality monitoring system based on wireless network | |
| CN119602984A (en) | A network intrusion detection method based on machine learning | |
| JP2008193538A (en) | Network attack monitoring device and attack trail management device | |
| CN117176229A (en) | Satellite Internet Intrusion Detection and Defense Algorithm | |
| CN119251990B (en) | Unmanned aerial vehicle environment monitoring and disaster early warning system and method | |
| CN119316217A (en) | A method and device for security situation awareness, monitoring and early warning of ore terminal production network | |
| CN117433978B (en) | Monitoring and early warning method and system of dust remover for transmission | |
| CN112037106A (en) | Data anomaly analysis method based on characteristic cross correlation and probability density | |
| CN118074955A (en) | Subway communication safety detection method and system based on artificial intelligence | |
| CN117938512A (en) | A security situation awareness system based on industrial control network traffic |
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:20200609 | |
| RJ01 | Rejection of invention patent application after publication |