CN114740774B - Behavior analysis control system for safe operation of fume hood - Google Patents
Behavior analysis control system for safe operation of fume hood Download PDFInfo
- Publication number
- CN114740774B CN114740774B CN202210363737.4A CN202210363737A CN114740774B CN 114740774 B CN114740774 B CN 114740774B CN 202210363737 A CN202210363737 A CN 202210363737A CN 114740774 B CN114740774 B CN 114740774B
- Authority
- CN
- China
- Prior art keywords
- risk
- safety
- fume hood
- data
- unit
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25257—Microcontroller
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a behavior analysis control system for safe operation of a fume hood, which comprises: the system comprises a control layer, an execution layer, a communication layer and a far-end control layer; the control layer is respectively connected with the execution layer and the communication layer, and the communication layer is connected with the remote control layer; the control system can realize behavior analysis based on safe operation of the fume hood, alarm and linkage of relevant equipment of the fume hood are carried out according to the behavior analysis, and safety risks in the experimental operation process of scientific research personnel are reduced.
Description
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a behavior analysis control system for safe operation of a fume hood.
Background
At present, according to the requirements of experimental processes, scientific research personnel need to use a ventilation cabinet to carry out toxic and harmful high-risk experimental operations in the experimental process, and the frequency of safety accidents caused by improper operations is high, so that the personal safety and occupational health of the personnel are greatly influenced.
However, the existing control systems are a ventilation control system and a window action control system, and no control system can perform centralized control on risk operation prejudgment, alarming and linkage in a ventilation cabinet; the existing monitoring technology is face recognition and GMP workshop operation recognition technology, and there is no recognition technology aiming at operation safety risks of experimental technology and scientific research personnel. And scientific research units mostly adopt an artificial routine inspection mode, the labor cost is high, real-time inspection and risk identification cannot be carried out, and the practical situation is not met. Meanwhile, a safe risk database for operation of the fume hood is not available, scientific research units do not have data and images for science popularization education, the science popularization difficulty is higher, the effect is poor,
accordingly, to overcome the above problems, the present invention provides a behavior analysis control system for safe operation of a hood.
Disclosure of Invention
The invention provides a behavior analysis control system for safe operation of a fume hood, which is used for realizing behavior analysis based on safe operation of the fume hood, and carrying out alarm and linkage of relevant equipment of the fume hood according to the behavior analysis control system, so that safety risks in the experimental operation process of scientific research personnel are reduced.
A behavioral analysis control system for safe operation of a fumehood, comprising:
the system comprises a control layer, an execution layer, a communication layer and a far-end control layer;
the control layer is respectively connected with the execution layer and the communication layer, and the communication layer is connected with the remote control layer;
the control layer comprises a controller and a human-computer interface, wherein the controller is used for sending an action instruction to the execution layer and collecting feedback data of the execution layer, and the human-computer interface is used for displaying data parameters and an operation state of the controller;
the execution layer is used for receiving the action instruction of the controller, completing the operation action based on the action instruction and simultaneously sending feedback data to the controller based on the operation result;
the communication layer is used for reading the data parameters and the running state of the controller and uploading the data parameters and the running state to the remote control layer;
and the remote control layer is used for monitoring the data parameters and the running state of the controller based on the Internet and carrying out reverse control on the controller based on a preset authority.
Preferably, the behavior analysis control system for safe operation of the fume hood, the controller includes:
the monitoring module is used for controlling the monitoring system to monitor the experiment operation performed in the fume hood in real time; the high-speed switching value module is used for opening one or more of a window motion system, a VAV control system, a gas fire extinguishing system, an alarm system and an exhaust fan set control system to work when a safety accident happens in an experiment in the fume hood; the analog quantity module is used for analyzing and positioning safety accidents when the safety accidents happen in the experiment in the fume hood, and controlling the VAV control system or the window motion system according to the analysis result and the positioning result; the communication module is used for transmitting the data parameters and the running state in the controller; and the big data module is used for carrying out risk early warning analysis and learning risk identification on the monitored content.
Preferably, the behavioral analysis control system for safe operation of the fume hood comprises the following execution layers:
the window motion system is used for controlling the ventilating hood window to move; the VAV control system is used for adjusting the air volume; a gas fire extinguishing system for performing a fire extinguishing operation when a fire occurs in the fume hood; the monitoring system is used for monitoring the experiment operation in the fume hood; the alarm system is used for carrying out alarm operation when a safety accident occurs in the fume hood; and the exhaust unit control system is used for regulating and controlling the ventilation speed of the fume hood.
Preferably, the behavior analysis control system for safe operation of the fume hood comprises a communication layer and a remote control layer, wherein the communication layer comprises a mobile end and an integrated management platform end.
Preferably, the behavior analysis control system for safe operation of the fume hood comprises the big data module:
the early warning analysis unit is used for carrying out early warning analysis on ventilation safety operation based on a first preset algorithm, and comprises the following specific steps:
step 1: acquiring risk behaviors during ventilation safety operation, analyzing the risk behaviors and determining a dynamic risk data set;
step 2: at the said movementSelecting initialized k samples as initial clustering centers alpha in the state risk data set, wherein alpha is alpha 1 ,α 2 ,...,α k ；
And step 3: computing each sample x in the dynamic risk dataset m Distances to the k initial cluster centers, and based on the calculation results, every sample x m Classifying the cluster centers with the minimum distance into the risk categories corresponding to the cluster centers;
and 4, step 4: recalculating the clustering centers in each risk category based on the assignment result and according to the following formula;
wherein, a j A cluster center represented in the jth risk category; c. C i An ith cluster center represented in the jth risk category; x represents dynamic risk data in the jth risk category;
and 5: acquiring a target termination condition, and repeating the steps 2-4 until the target termination condition is reached;
step 6: and finishing early warning analysis on the risk behaviors based on the calculation result.
Preferably, the behavior analysis control system for safe operation of the fume hood further includes:
the risk behavior identification unit is used for learning risk behaviors in safety operation of the fume hood based on a second preset algorithm, and the risk behavior identification unit specifically comprises the following steps:
s101: obtaining network neurons of a preset convolutional network, and determining the state y of a first network neuron based on the output result of the network neurons h ＝[y 1 ,y 2 ,...,y n ] T Wherein h is ∈ [1, n ]]；y 1 Representing a first neuron in a convolutional neural network; y is 2 Representing a second neuron in the convolutional network; y is n Representing the nth neuron in the convolutional network; n represents the number of network neurons of the convolutional neural network; t represents transposition;
s102: obtaining an initial state y of the convolutional neural network 0 ＝[y 1 (0),y 2 (0),...,y n (0)] T Wherein, y 0 Representing the initial state of said convolutional neural network, y 1 (0) Representing a first initial neuron in the convolutional neural network; y is 2 (0) Representing a second initial neuron in said convolutional neural network; y is n (0) Representing an nth initial neuron in the convolutional neural network;
setting the initial state of the convolutional neural network in the convolutional neural network, and determining the learning state change rule of each neuron in the convolutional neural network according to the following formula based on the setting result;
wherein, y k Representing the second network neuron state; n represents the number of network neurons of the convolutional neural network; h represents the current network neuron, k represents the current network neuron after learning, and h and k correspond one to one; w is a hk Representing the state y of a neuron from a first network h To a second network neuron state y k Learning factors for learning, and the value range is (0.99, 1.01); t is k Indicating a transition state value during learning;
s104: and finishing learning the risk behaviors in the safety operation of the fume hood based on the learning state change rule and the learning result.
Preferably, the monitoring module includes:
the video image acquisition unit is used for acquiring a video image for carrying out experiment operation in the fume hood based on a preset video image acquisition device;
the video image processing unit is used for extracting a previous frame video image and a current frame video image of the video image, and simultaneously respectively acquiring a first image code of the previous frame video image and a second image code of the current frame video image;
the video image processing unit is further configured to perform fusion processing on the first image code and the second image code, and determine the target image code;
the pixel information determining unit is used for performing two-dimensional orthogonal transformation on the target image code to determine pixel information of the video image;
the video image processing unit is further configured to calculate pixel point information of the video image according to a preset mode, and determine a background image and a foreground image of the video image;
the image reading unit is used for performing first reading on the background image, determining a working environment in which the fume hood works, and performing data description on the working environment to generate working environment data;
the risk content confirmation unit is used for carrying out first matching on the working environment data in a preset risk database and determining first predicted risk content;
the image reading unit is further used for performing second reading on the foreground image, extracting an operator in the foreground image, tracking the operator and determining the action behavior of the operator;
the attitude data analysis unit is used for determining attitude data of the operator based on the action behavior of the operator, inputting the attitude data into a preset operation action model for analysis, and estimating a target operation experiment performed by the operator according to an output result;
the risk content confirming unit is further configured to determine experimental data of the target operation experiment, input the experimental data into the preset risk database for second matching, and determine second predicted risk content;
a safety monitoring condition generating unit, configured to set a safety monitoring condition according to the first predicted risk content and the second predicted risk content;
and the monitoring unit is used for carrying out safety monitoring on a target operation experiment based on the safety monitoring condition, generating an alarm instruction when the operator violates the safety monitoring condition, and transmitting the alarm instruction to the execution layer for carrying out alarm operation.
Preferably, as shown in fig. 3, the monitoring module further includes:
the initial state confirmation unit is used for acquiring initial data parameters of the controller and determining the initial state of the controller according to the initial data parameters;
the interval setting unit is used for setting a change interval of the data parameters according to the safety criterion of experimental operation and the initial data parameters corresponding to the initial state of the controller, and determining the safe change interval of the data parameters;
the operation state reading unit is used for reading the operation state, determining operation data parameters corresponding to the operation state and simultaneously recording the operation data parameters in real time;
the safety prediction unit is used for acquiring real-time change values of the initial data parameters and the operation data parameters, comparing the real-time change values with the data parameter safety change interval, and predicting the safety of experimental operation in the fume hood according to the comparison result;
when the real-time change value is within the data parameter safety change interval, judging that no safety accident occurs in the experimental operation in the fume hood;
when the real-time change value is equal to a critical threshold value of the data parameter safety change interval, judging that a safety accident is about to occur in the experimental operation in the fume hood;
and when the real-time change value is not in the data parameter safety change interval, judging that a safety accident occurs in the experimental operation in the fume hood.
Preferably, the behavior analysis control system for safe operation of the fume hood further includes:
the first alarm subunit is used for generating a first early warning instruction based on the real-time change value when a safety accident is about to happen in the experimental operation in the fume hood, and controlling an alarm system to perform a first alarm operation based on the first early warning instruction;
and the second alarm subunit is used for generating a second early warning instruction based on the real-time change value when a safety accident happens to the experimental operation in the fume hood, and controlling an alarm system to perform a second alarm operation based on the second early warning instruction.
Preferably, the behavior analysis control system for safe operation of the fume hood, the remote control layer, includes:
the information acquisition unit is used for acquiring the authority information of the preset authority and the control instruction information for the controller to perform reverse control when the controller is performed with reverse control based on the preset authority;
the association node confirmation unit is used for acquiring communication association nodes of a communication layer and the remote control layer and determining a communication gateway label in the communication association nodes;
the request generating unit is used for generating an instruction transmission request according to the authority information, the control instruction information and the communication gateway label and sending the instruction transmission request to the communication layer;
the verification unit is used for receiving the instruction transmission request based on the communication layer, reading the instruction transmission request and determining an instruction verification code;
the verification unit is further used for performing matching verification on the instruction verification code in a preset verification text, and when the matching verification is passed, the control instruction information is sent to the controller through the communication layer based on the instruction transmission request.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a structural diagram of a behavior analysis control system for safe operation of a fume hood according to an embodiment of the present invention;
FIG. 2 is a diagram of a system architecture in accordance with an embodiment of the present invention;
fig. 3 is a diagram of a monitoring module structure in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1:
the embodiment provides a behavior analysis control system for safe operation of a fume hood, as shown in fig. 1-2, including:
the system comprises a control layer, an execution layer, a communication layer and a far-end control layer;
the control layer is respectively connected with the execution layer and the communication layer, and the communication layer is connected with the remote control layer;
the control layer comprises a controller and a human-computer interface, wherein the controller is used for sending an action instruction to the execution layer and collecting feedback data of the execution layer, and the human-computer interface is used for displaying data parameters and an operation state of the controller;
the execution layer is used for receiving the action instruction of the controller, completing the operation action based on the action instruction and simultaneously sending feedback data to the controller based on the operation result;
the communication layer is used for reading the data parameters and the running state of the controller and uploading the data parameters and the running state to the remote control layer;
and the remote control layer is used for monitoring the data parameters and the running state of the controller based on the Internet and carrying out reverse control on the controller based on a preset authority.
In this embodiment, the control layer is connected with the execution layer through a wired signal, the control layer is connected with the communication layer through a MODBUS, and the communication layer is connected with the remote control layer through an ethernet/5G.
In this embodiment, the data parameter may be set in advance when the system is in normal operation, and the operation state may be an operation state determined by monitoring the experiment operation performed in the fume hood.
In the embodiment, the controller stores an operating program and an intelligent analysis strategy for the embedded controller, sends an action instruction to the execution layer and collects feedback data of the execution layer. And receiving an operation instruction of an upper computer, wherein the upper computer can be an operation instruction for carrying out reverse control on the controller by a remote control layer, and a human-machine interface (HMI) displays system data parameters and an operation state.
The working principle of the technical scheme is as follows: the operation experiment of the fume hood is monitored, when a safety accident happens, an action instruction is generated based on a controller in a control layer, the action instruction is sent to an execution layer to be executed, then the execution result of the execution layer is fed back to the control layer, data display is carried out through a human-computer interface, and data parameters and the operation state in the controller are transmitted to a remote control layer to be monitored based on the internet according to a communication layer.
The beneficial effects of the above technical scheme are: the control system can realize behavior analysis based on safe operation of the fume hood, alarm and linkage of relevant equipment of the fume hood are carried out according to the behavior analysis, and safety risks in the experimental operation process of scientific research personnel are reduced.
Example 2:
on the basis of embodiment 1, this embodiment provides a behavior analysis control system for safe operation of a fume hood, where the controller includes:
the monitoring module is used for controlling the monitoring system to monitor the experiment operation performed in the fume hood in real time; the high-speed switching value module is used for opening one or more of a window motion system, a VAV control system, a gas fire extinguishing system, an alarm system and an exhaust fan set control system to work when a safety accident happens in an experiment in the fume hood; the analog quantity module is used for analyzing and positioning safety accidents when the safety accidents happen to the experiments in the fume hood, and controlling the VAV control system or the window motion system according to the analysis result and the positioning result; the communication module is used for transmitting the data parameters and the running state in the controller; and the big data module is used for carrying out risk early warning analysis and learning risk identification on the monitored content.
In this embodiment, the VAV control system is a variable air volume control system for controlling the air volume.
In this embodiment, the analog module includes:
the sensor confirming unit is used for confirming a sensor group in the fume hood when a fire disaster happens in the fume hood, and the distance between each sensor in the sensor group and a fire source is equal;
the first calculation unit is used for calculating the distance from the fire source to the sensor;
wherein lg (-) represents a base-10 logarithm; d represents the distance of the fire source to the sensor; δ represents the total number of sensors in the fume hood; τ represents the current sensor; t represents the temperature value of the fire source; t is i Representing the temperature value sensed by the ith sensor; k represents a constant, and the value of k is 32.4; c represents the propagation speed of the infrared waves sent by the sensor in the air, and generally takes the value of 3 x 10 8 m/s; λ represents the wavelength of infrared waves;
the target sensor acquisition unit is used for randomly selecting one sensor from the sensor group as a target sensor at the central point A of the sensor group, and the position point of the target sensor is B;
the second calculation unit is used for calculating an included angle between the direction of a line segment AB where the central point A of the sensor group and the position point of the target sensor are located and the direction of the fire source based on the distance from the fire source to the sensor;
wherein theta represents an included angle between the line segment AB direction and the fire source direction; t is ε Representing a temperature value sensed by the target sensor;
and the position confirmation unit is used for determining the specific position of the fire source in the fume hood based on the distance from the fire source to the sensor and the included angle between the line segment AB direction and the fire source direction.
The beneficial effects of the above technical scheme are: the system is controlled and monitored through a monitoring module, a high-speed switching value module, an analog quantity module, a communication module and a big data module in the controller, traceability of safety monitoring alarm data is facilitated, meanwhile, the control system integrates the big data module, a database can be formed according to dynamic data of risk behavior analysis, and the database is iterated and intelligent criteria are optimized through a machine learning algorithm and a behavior analysis prediction model algorithm.
Example 3:
on the basis of embodiment 1, this embodiment provides a behavior analysis control system for safe operation of a fume hood, where the execution layer includes:
the window motion system is used for controlling the ventilating hood window to move; the VAV control system is used for adjusting the air volume; a gas fire extinguishing system for performing a fire extinguishing operation when a fire occurs in the fume hood; the monitoring system is used for monitoring the experiment operation in the fume hood; the alarm system is used for carrying out alarm operation when a safety accident occurs in the fume hood; and the exhaust unit control system is used for regulating and controlling the ventilation speed of the ventilation cabinet.
The beneficial effects of the above technical scheme are: through the accurate execution of the execution layer, the personal safety of operators can be effectively guaranteed.
Example 4:
on the basis of embodiment 1, this embodiment provides a behavior analysis control system for safe operation of a fume hood, where the communication layer includes a communication module, and the remote control layer includes a mobile terminal and an integrated management platform terminal.
The beneficial effects of the above technical scheme are: information interaction between the remote control layer and the control layer can be realized based on the communication layer, so that the monitoring control efficiency of safe operation of the fume hood is improved.
Example 5:
on the basis of embodiment 2, this embodiment provides a behavior analysis control system for safe operation of a fume hood, and the big data module includes:
the early warning analysis unit is used for carrying out early warning analysis on ventilation safety operation based on a first preset algorithm, and comprises the following specific steps:
step 1: acquiring risk behaviors during ventilation safety operation, analyzing the risk behaviors and determining a dynamic risk data set;
and 2, step: selecting initialized k samples as initial cluster centers alpha in the dynamic risk data set, and alpha is alpha 1 ,α 2 ,...,α k ；
And step 3: computing each sample x in the dynamic risk dataset m Distances to the k initial cluster centers, and based on the calculation results, every sample x m Classifying the cluster centers with the minimum distance into the risk categories corresponding to the cluster centers;
and 4, step 4: recalculating the clustering centers in each risk category based on the assignment result and according to the following formula;
wherein, a j A cluster center represented in the jth risk category; c. C i Is indicated in the j windThe ith cluster center in the risk category; x represents dynamic risk data in the jth risk category;
and 5: acquiring a target termination condition, and repeating the steps 2-4 until the target termination condition is reached;
step 6: and finishing early warning analysis on the risk behaviors based on the calculation result.
In this embodiment, the first predetermined algorithm may be a K-means behavior analysis algorithm.
In this embodiment, the target termination condition may be a condition that is set in advance by a human and is used to terminate the algorithm.
In this embodiment, initialization may be based on setting sample data in advance that represents risk and sample data that is not at risk while operating in the fume hood.
The beneficial effects of the above technical scheme are: the database can be iterated through a K-means behavior analysis algorithm, and the accurate classification of the operation behaviors of the experiment operation is realized.
Example 6:
on the basis of embodiment 2, this embodiment provides a behavior analysis control system for safe operation of a fume hood, and the big data module further includes:
the risk behavior identification unit is used for learning risk behaviors in safety operation of the fume hood based on a second preset algorithm, and the risk behavior identification unit specifically comprises the following steps:
s101: obtaining network neurons of a preset convolutional network, and determining the state y of a first network neuron based on the output result of the network neurons h ＝[y 1 ,y 2 ,...,y n ] T Wherein h is ∈ [1, n ]]；y 1 Representing a first neuron in a convolutional neural network; y is 2 Representing a second neuron in the convolutional network; y is n Representing the nth neuron in the convolutional network; n represents the number of network neurons of the convolutional neural network; t represents transposition;
s102: obtaining an initial state y of the convolutional neural network 0 ＝[y 1 (0),y 2 (0),...,y n (0)] T Wherein, y 0 Representing the initial state of said convolutional neural network, y 1 (0) Representing a first initial neuron in the convolutional neural network; y is 2 (0) Representing a second initial neuron in said convolutional neural network; y is n (0) Representing an nth initial neuron in the convolutional neural network;
setting the initial state of the convolutional neural network in the convolutional neural network, and determining the learning state change rule of each neuron in the convolutional neural network according to the following formula based on the setting result;
wherein, y k Representing the second network neuron state; n represents the number of network neurons of the convolutional neural network; h represents the current network neuron, k represents the current network neuron after learning, and h and k correspond one to one; w is a hk Representing state y of neurons from the first network h To a second network neuron state y k Learning factors for learning, and the value range is (0.99, 1.01); t is a unit of k Indicating a transition state value during learning;
s104: and finishing learning the risk behaviors in safety operation in the fume hood based on the learning state change rule and the learning result.
In this embodiment, when each neuron in the convolutional neural network is no longer changed, the output state of the neuron is:
wherein t represents an output time; x (t) represents the output state of the neuron.
In this embodiment, the first network neuron state may be a network neuron state determined without learning in the convolutional network.
In this embodiment, the second network neuron state may be a network neuron state determined after learning in a convolutional network.
In this embodiment, the second preset algorithm may be a Hopfield machine learning algorithm.
The beneficial effects of the above technical scheme are: the method and the device improve the identification precision of the risk behaviors in the operation behaviors and can optimize the intelligent judgment of the risk behaviors.
Example 7:
on the basis of embodiment 2, this embodiment provides a behavior analysis control system for safe operation of a fume hood, and the monitoring module includes:
the video image acquisition unit is used for acquiring a video image for carrying out experiment operation in the fume hood based on a preset video image acquisition device;
the video image processing unit is used for extracting a previous frame video image and a current frame video image of the video image, and simultaneously respectively acquiring a first image code of the previous frame video image and a second image code of the current frame video image;
the video image processing unit is further configured to perform fusion processing on the first image code and the second image code to determine the target image code;
the pixel point information determining unit is used for performing two-dimensional orthogonal transformation on the target image code to determine pixel point information of the video image;
the video image processing unit is further configured to calculate pixel point information of the video image according to a preset mode, and determine a background image and a foreground image of the video image;
the image reading unit is used for performing first reading on the background image, determining a working environment in which the fume hood works, and performing data description on the working environment to generate working environment data;
the risk content confirmation unit is used for carrying out first matching on the working environment data in a preset risk database and determining first predicted risk content;
the image reading unit is further used for performing second reading on the foreground image, extracting an operator in the foreground image, tracking the operator and determining the action behavior of the operator;
the attitude data analysis unit is used for determining attitude data of the operator based on the action behavior of the operator, inputting the attitude data into a preset operation action model for analysis, and estimating a target operation experiment performed by the operator according to an output result;
the risk content confirming unit is further configured to determine experimental data of the target operation experiment, input the experimental data into the preset risk database for second matching, and determine second predicted risk content;
a safety monitoring condition generating unit, configured to set a safety monitoring condition according to the first predicted risk content and the second predicted risk content;
and the monitoring unit is used for carrying out safety monitoring on a target operation experiment based on the safety monitoring condition, generating an alarm instruction when the operator violates the safety monitoring condition, and transmitting the alarm instruction to the execution layer for carrying out alarm operation.
In this embodiment, the preset video image capturing device may be, for example, a camera or the like.
In this embodiment, the first image encoding may be an image encoding of a previous frame video image, and the second image encoding may be an image encoding of a current frame video image.
In this embodiment, the target image code may be a target image code determined after the first image code and the second image code are fused, and is used to accurately obtain the image code, thereby facilitating extraction of pixel point information of the video image.
In this embodiment, the preset manner may be a binarization operation, and is used to extract a background image and a foreground image of the video image.
In this embodiment, the first reading is used to read the background image, so as to determine the working environment of the fume hood, wherein the working environment may be, for example, whether there is an open fire or not in the experiment operation.
In this embodiment, the preset risk database may be set, obtained by continuously optimizing learning through a K-means behavior analysis algorithm and a Hopfield machine learning algorithm, and includes various experiments and data such as risks in the experiments.
In this embodiment, the first matching is to match the working environment data in a preset risk database, and the second matching is to match the experimental data in the preset risk database.
In this embodiment, the first predicted risk context is, for example, when there is an open flame in the work environment.
In this embodiment, the second predicted risk content may be, for example, that the operation process of the operator will not cause open fire or leakage of harmful gas.
In this embodiment, the attitude data may be an operation action of the operator.
In this embodiment, the safety monitoring condition may be a condition determined according to the first predicted risk content and the second predicted risk content, and is used as a condition for monitoring the target operation experiment, and when the safety monitoring condition is violated, it is determined that the target operation experiment may have a risk.
The beneficial effects of the above technical scheme are: the foreground image and the background image of the video image are determined according to the video image, and the foreground image and the background image are analyzed, so that the target operation experiment and the experiment environment of the target operation experiment can be accurately determined, the safety monitoring condition can be determined according to the first risk prediction content and the second risk prediction content, the monitoring accuracy and the monitoring efficiency are greatly improved, and the risk can be effectively avoided.
Example 8:
on the basis of embodiment 2, this embodiment provides a behavior analysis control system for safe operation of a fume hood, as shown in fig. 3, the monitoring module further includes:
the initial state confirmation unit is used for acquiring initial data parameters of the controller and determining the initial state of the controller according to the initial data parameters;
the interval setting unit is used for setting a change interval of the data parameters according to the safety criterion of experimental operation and the initial data parameters corresponding to the initial state of the controller, and determining the safe change interval of the data parameters;
the operation state reading unit is used for reading the operation state, determining operation data parameters corresponding to the operation state and simultaneously recording the operation data parameters in real time;
the safety prediction unit is used for acquiring real-time change values of the initial data parameters and the operation data parameters, comparing the real-time change values with the data parameter safety change interval, and predicting the safety of experimental operation in the fume hood according to the comparison result;
when the real-time change value is within the data parameter safety change interval, judging that no safety accident occurs in the experimental operation in the fume hood;
when the real-time change value is equal to a critical threshold value of the data parameter safety change interval, judging that a safety accident is about to occur in the experimental operation in the fume hood;
and when the real-time change value is not in the data parameter safety change interval, judging that the safety accident occurs to the experimental operation in the fume hood.
In this embodiment, the initial data parameters are set in advance by the system and are set on the basis that the fume hood monitored by the system is safe.
In this embodiment, the safety criterion of the experimental operation may be an experimental operation specification process of an experimenter in the fume hood, which is an operation process that does not cause a safety accident.
In this embodiment, the safe variation interval of the data parameter may be the maximum interval in which the initial parameter can be varied within the safe range.
In this embodiment, the operation data parameter will change continuously with the progress of the experiment, and therefore the real-time change value is the change value between the operation data parameter and the initial state parameter, which is the real-time change value.
In this embodiment, the critical threshold is a maximum value of a data parameter variation interval, and a value range of the data parameter variation interval is greater than or greater than zero and less than or equal to the critical threshold.
The beneficial effects of the above technical scheme are: through the record tracking of the operation parameters, the safety of experiment operation in the fume hood can be found in time, and therefore the monitoring sensitivity is improved.
Example 9:
on the basis of embodiment 8, this embodiment provides a behavior analysis control system for safe operation of a fume hood, and the safety prediction unit further includes:
the first alarm subunit is used for generating a first early warning instruction based on the real-time change value when a safety accident is about to occur in the experimental operation in the fume hood, and controlling an alarm system to perform a first alarm operation based on the first early warning instruction;
and the second alarm subunit is used for generating a second early warning instruction based on the real-time change value when a safety accident happens to the experimental operation in the fume hood, and controlling an alarm system to perform a second alarm operation based on the second early warning instruction.
In the embodiment, the first early warning instruction or the second early warning instruction is generated through the real-time change value, so that the first warning operation or the second warning operation can be triggered accurately.
In this embodiment, the first alarm operation may be, for example, sending an alarm short message to the control layer or the remote control layer through the communication layer.
In this embodiment, the second warning operation may be one or more of sound, vibration, and light.
The beneficial effects of the above technical scheme are: through first alarm operation or second alarm operation, be favorable to in time discovering that the experiment operation can take place the incident to when being favorable to taking place danger in the fume chamber, save the remediation time.
Example 10:
on the basis of embodiment 1, this embodiment provides a behavior analysis control system for safe operation of a fume hood, where the remote control layer includes:
the information acquisition unit is used for acquiring the authority information of the preset authority and the control instruction information for the controller to perform reverse control when the controller is performed with reverse control based on the preset authority;
the association node confirmation unit is used for acquiring communication association nodes of a communication layer and the remote control layer and determining a communication gateway label in the communication association nodes;
the request generating unit is used for generating an instruction transmission request according to the authority information, the control instruction information and the communication gateway label and sending the instruction transmission request to the communication layer;
the verification unit is used for receiving the instruction transmission request based on the communication layer, reading the instruction transmission request and determining an instruction verification code;
the verification unit is further used for performing matching verification on the instruction verification code in a preset verification text, and when the matching verification is passed, the control instruction information is sent to the controller through the communication layer based on the instruction transmission request.
In this embodiment, the control instruction information may be automatically generated by the remote control layer through user operation.
In this embodiment, the associated node may be a communication data node when the communication layer performs data transmission with the remote control layer.
In this embodiment, the tag of the communication gateway may be a tag corresponding to a communication gateway in the communication layer and the remote control layer, and may be represented by binary data to accurately generate the command transfer request.
In this embodiment, the instruction verification code is used to verify the instruction delivery request in order to protect the security of the system data.
The beneficial effects of the above technical scheme are: the command transmission request is generated and verified through the communication layer, so that the safety of the system is maintained, and when the command transmission request passes the verification, the control command information is transmitted to the controller, so that the data can be safely and accurately reversely operated.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A behavioral analysis control system for safe operation of a fumehood, comprising:
the system comprises a control layer, an execution layer, a communication layer and a far-end control layer;
the control layer is respectively connected with the execution layer and the communication layer, and the communication layer is connected with the remote control layer;
the control layer comprises a controller and a human-computer interface, wherein the controller is used for sending an action instruction to the execution layer and collecting feedback data of the execution layer, and the human-computer interface is used for displaying data parameters and an operation state of the controller;
the execution layer is used for receiving the action instruction of the controller, completing the operation action based on the action instruction and sending feedback data to the controller based on the operation result;
the communication layer is used for reading the data parameters and the running state of the controller and uploading the data parameters and the running state to the remote control layer;
the remote control layer is used for monitoring data parameters and running states of the controller based on the Internet and performing reverse control on the controller based on preset authority;
the controller includes:
the monitoring module is used for controlling the monitoring system to monitor the experiment operation performed in the fume hood in real time; the high-speed switching value module is used for opening one or more of a window motion system, a VAV control system, a gas fire extinguishing system, an alarm system and an exhaust fan set control system to work when a safety accident happens in an experiment in the fume hood; the analog quantity module is used for analyzing and positioning safety accidents when the safety accidents happen to the experiments in the fume hood, and controlling the VAV control system or the window motion system according to the analysis result and the positioning result; the communication module is used for transmitting the data parameters and the running state in the controller; the big data module is used for carrying out risk early warning analysis and learning risk identification on the monitored content;
the monitoring module comprises:
the video image acquisition unit is used for acquiring a video image for carrying out experiment operation in the fume hood based on a preset video image acquisition device;
the video image processing unit is used for extracting a previous frame video image and a current frame video image of the video image, and simultaneously respectively acquiring a first image code of the previous frame video image and a second image code of the current frame video image;
the video image processing unit is further configured to perform fusion processing on the first image code and the second image code to determine a target image code;
the pixel information determining unit is used for performing two-dimensional orthogonal transformation on the target image code to determine pixel information of the video image;
the video image processing unit is further configured to calculate pixel point information of the video image according to a preset mode, and determine a background image and a foreground image of the video image;
the image reading unit is used for performing first reading on the background image, determining a working environment in which the fume hood works, and performing data description on the working environment to generate working environment data;
the risk content confirmation unit is used for carrying out first matching on the working environment data in a preset risk database and determining first predicted risk content;
the image reading unit is further used for performing second reading on the foreground image, extracting an operator in the foreground image, tracking the operator and determining the action behavior of the operator;
the attitude data analysis unit is used for determining attitude data of the operator based on the action behavior of the operator, inputting the attitude data into a preset operation action model for analysis, and estimating a target operation experiment performed by the operator according to an output result;
the risk content confirming unit is further configured to determine experimental data of the target operation experiment, input the experimental data into the preset risk database for second matching, and determine second predicted risk content;
a safety monitoring condition generating unit, configured to set a safety monitoring condition according to the first predicted risk content and the second predicted risk content;
and the monitoring unit is used for carrying out safety monitoring on a target operation experiment based on the safety monitoring condition, generating an alarm instruction when the operator violates the safety monitoring condition, and transmitting the alarm instruction to the execution layer for carrying out alarm operation.
2. A behavioral analysis control system according to claim 1, characterized in that said executive layer comprises:
the window motion system is used for controlling the ventilating hood window to move; the VAV control system is used for adjusting air volume; a gas fire extinguishing system for performing a fire extinguishing operation when a fire occurs in the fume hood; the monitoring system is used for monitoring the experiment operation in the fume hood; the alarm system is used for carrying out alarm operation when a safety accident occurs in the fume hood; and the exhaust unit control system is used for regulating and controlling the ventilation speed of the ventilation cabinet.
3. A behavioral analysis control system according to claim 1, characterized in that the communication layer comprises a communication module, and the remote control layer comprises a mobile terminal and an integrated management platform terminal.
4. A behavioral analysis control system according to claim 1, characterized in that said big data module comprises:
the early warning analysis unit is used for carrying out early warning analysis on ventilation safety operation based on a first preset algorithm, and comprises the following specific steps:
step 1: acquiring risk behaviors during ventilation safety operation, analyzing the risk behaviors and determining a dynamic risk data set;
step 2: selecting initialized k samples in the dynamic risk dataset as initial cluster centers alpha, and alpha ═ alpha 1 ,α 2 ,...,α k ；
And step 3: computing each sample x in the dynamic risk dataset m Distances to k initial cluster centers and based on the calculation, every sample x m Classifying the cluster centers with the minimum distance into the risk categories corresponding to the cluster centers;
and 4, step 4: recalculating the clustering centers in each risk category based on the assignment result and according to the following formula;
wherein, a j A cluster center represented in the jth risk category; c. C i An ith cluster center represented in the jth risk category; x represents dynamic risk data in the jth risk category;
and 5: acquiring a target termination condition, and repeating the steps 2-4 until the target termination condition is reached;
and 6: and finishing early warning analysis on the risk behaviors based on the calculation result.
5. A behavioral analysis control system according to claim 1, characterized in that said big data module further comprises:
the risk behavior identification unit is used for learning risk behaviors in safety operation of the fume hood based on a second preset algorithm, and the risk behavior identification unit specifically comprises the following steps:
s101: acquiring network neurons of a preset convolutional network, and determining a first network neuron state y based on an output result of the network neurons h ＝[y 1 ,y 2 ,...,y n ] T Wherein h is ∈ [1, n ]]；y 1 Representing a first neuron in a convolutional neural network; y is 2 Representing a second neuron in the convolutional network; y is n Representing the nth neuron in the convolutional network; n represents the number of network neurons of the convolutional neural network; t represents transposition;
s102: obtaining an initial state y of the convolutional neural network 0 ＝[y 1 (0),y 2 (0),...,y n (0)] T Wherein, y 0 Representing the initial state of said convolutional neural network, y 1 (0) Representing a first initial neuron in the convolutional neural network; y is 2 (0) Representing a second initial neuron in said convolutional neural network; y is n (0) Representing an nth initial neuron in the convolutional neural network;
setting the initial state of the convolutional neural network in the convolutional neural network, and determining the learning state change rule of each neuron in the convolutional neural network according to the following formula based on the setting result;
y k ＝f(net h )，h＝1,2,3...,n；
wherein n represents the number of network neurons of the convolutional neural network; y is k Representing the first network neuron state y h Acquiring the state of a second network neuron after learning; f (net) h ) Is an activation function; net h A convolutional neural network formed for the network neurons;
s103: calculating the first network neuron state y according to the following formula h Learning results of learning in a convolutional neural network;
wherein, y k Representing the second network neuron state; n represents the number of network neurons of the convolutional neural network; h represents the current network neuron, k represents the current network neuron after learning, and h and k correspond one to one; w is a hk Representing the state y of a neuron from a first network h To a second network neuron state y k Learning factors for learning, and the value range is (0.99, 1.01); t is k A transition state value indicating a transition in the learning process;
s104: and finishing learning the risk behaviors in the safety operation of the fume hood based on the learning state change rule and the learning result.
6. A fume hood safety operating behavioral analysis control system according to claim 1, wherein the monitoring module further comprises:
the initial state confirmation unit is used for acquiring initial data parameters of the controller and determining the initial state of the controller according to the initial data parameters;
the interval setting unit is used for setting a change interval of the data parameters according to the safety criterion of experimental operation and the initial data parameters corresponding to the initial state of the controller, and determining the safe change interval of the data parameters;
the operation state reading unit is used for reading the operation state, determining operation data parameters corresponding to the operation state and simultaneously recording the operation data parameters in real time;
the safety prediction unit is used for acquiring real-time change values of the initial data parameters and the operating data parameters, comparing the real-time change values with the data parameter safety change interval, and predicting the safety of experimental operation in the fume hood according to the comparison result;
when the real-time change value is within the data parameter safety change interval, judging that no safety accident occurs in the experimental operation in the fume hood;
when the real-time change value is equal to a critical threshold value of the data parameter safety change interval, judging that a safety accident is about to occur in the experimental operation in the fume hood;
and when the real-time change value is not in the data parameter safety change interval, judging that the safety accident occurs to the experimental operation in the fume hood.
7. A behavioral analysis control system according to claim 6, characterized in that the safety prediction unit further comprises:
the first alarm subunit is used for generating a first early warning instruction based on the real-time change value when a safety accident is about to occur in the experimental operation in the fume hood, and controlling an alarm system to perform a first alarm operation based on the first early warning instruction;
and the second alarm subunit is used for generating a second early warning instruction based on the real-time change value when a safety accident happens to the experimental operation in the fume hood, and controlling an alarm system to perform a second alarm operation based on the second early warning instruction.
8. A behavioral analysis control system according to claim 1 for safe operation of a fumehood, wherein said remote control layer comprises:
the information acquisition unit is used for acquiring the authority information of the preset authority and the control instruction information for the controller to perform reverse control when the controller is performed with reverse control based on the preset authority;
the association node confirmation unit is used for acquiring communication association nodes of a communication layer and the remote control layer and determining a communication gateway label in the communication association nodes;
the request generating unit is used for generating an instruction transmission request according to the authority information, the control instruction information and the communication gateway label and sending the instruction transmission request to the communication layer;
the verification unit is used for receiving the instruction transmission request based on the communication layer, reading the instruction transmission request and determining an instruction verification code;
the verification unit is further used for performing matching verification on the instruction verification code in a preset verification text, and when the matching verification is passed, the control instruction information is sent to the controller through the communication layer based on the instruction transmission request.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210363737.4A CN114740774B (en) | 2022-04-07 | 2022-04-07 | Behavior analysis control system for safe operation of fume hood |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210363737.4A CN114740774B (en) | 2022-04-07 | 2022-04-07 | Behavior analysis control system for safe operation of fume hood |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114740774A CN114740774A (en) | 2022-07-12 |
| CN114740774B true CN114740774B (en) | 2022-09-27 |
Family
ID=82280119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210363737.4A Active CN114740774B (en) | 2022-04-07 | 2022-04-07 | Behavior analysis control system for safe operation of fume hood |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114740774B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218689B (en) * | 2013-04-23 | 2017-09-22 | 湖南工学院 | The analysis method for reliability and device of operator's state estimation |
| CN108510194B (en) * | 2018-03-30 | 2022-11-29 | 平安科技（深圳）有限公司 | Wind control model training method, risk identification method, device, equipment and medium |
| CN108876600B (en) * | 2018-08-20 | 2023-09-05 | 平安科技（深圳）有限公司 | Early warning information pushing method, device, computer equipment and medium |
| CN109165840B (en) * | 2018-08-20 | 2022-06-21 | 平安科技（深圳）有限公司 | Risk prediction processing method, risk prediction processing device, computer equipment and medium |
| CN109447048B (en) * | 2018-12-25 | 2020-12-25 | 苏州闪驰数控系统集成有限公司 | Artificial intelligence early warning system |
| CN110308689A (en) * | 2019-05-22 | 2019-10-08 | 浙江工业大学 | A kind of remote monitoring intelligent vent cabinet safety management system |
| WO2022022368A1 (en) * | 2020-07-28 | 2022-02-03 | 宁波环视信息科技有限公司 | Deep-learning-based apparatus and method for monitoring behavioral norms in jail |
-
2022
- 2022-04-07 CN CN202210363737.4A patent/CN114740774B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114740774A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109980781B (en) | Intelligent monitoring system of transformer substation | |
| CN111622735B (en) | Environment-friendly drilling machine automatic control and monitoring system and method based on Internet of things | |
| JP6900918B2 (en) | Learning device and learning method | |
| EP4018399A1 (en) | Modeling human behavior in work environments using neural networks | |
| KR20210010184A (en) | Appartus and method for abnormal situation detection | |
| Cruz‐Ramírez et al. | Vision‐based hierarchical recognition for dismantling robot applied to interior renewal of buildings | |
| CN115663999A (en) | Transformer substation online intelligent inspection system and method based on big data and deep learning | |
| CN110597165B (en) | Steel piling monitoring system and steel piling monitoring method | |
| CN114740774B (en) | Behavior analysis control system for safe operation of fume hood | |
| KR20210050889A (en) | Method and system for updating cctv-control system | |
| CN113554364A (en) | Disaster emergency management method, device, equipment and computer storage medium | |
| US11276285B2 (en) | Artificial intelligence based motion detection | |
| Chala et al. | The Use of Neural Networks for the Technological Objects Recognition Tasks in Computer-Integrated Manufacturing | |
| CN117572863A (en) | Path optimization method and system for substation robot | |
| CN115958609B (en) | Instruction data safety early warning method based on intelligent robot automatic control system | |
| CN115861364B (en) | Site personnel management and control method and system based on AI identification | |
| KR102619200B1 (en) | Method and computer program for creating a neural network model that automatically controls environmental facilities based on artificial intelligence | |
| CN116541689A (en) | Multi-mode data acquisition and labeling method, device and computer equipment | |
| CN115063921A (en) | Construction site intelligent gate system and construction method | |
| KR102153360B1 (en) | Context aware system of robot based on cloud computing and processing method thereof | |
| CN114756026B (en) | Inspection control system for experimental environment safety inspection | |
| Yin et al. | Method for detection of unsafe actions in power field based on edge computing architecture | |
| US20200202178A1 (en) | Automatic visual data generation for object training and evaluation | |
| CN115797878B (en) | Equipment operation safety detection method and system based on image processing and related equipment | |
| Lika et al. | Lightweight Deep Learning for Object Detection on Mobile Device |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Behavior Analysis Control System for Safe Operation of Fume hood Effective date of registration: 20230615 Granted publication date: 20220927 Pledgee: Agricultural Bank of China Limited Qingdao Branch Business Department Pledgor: Qingdao wobers Intelligent Experimental Technology Co.,Ltd. Registration number: Y2023980044130 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |