Intelligent identification management and control method and system for coal gas use safety risk based on machine vision, and storage medium

Through the intelligent identification and control system for gas use safety risks based on machine vision, the detection problems of existing technology in complex environments and the sensitivity of automatic shutoff valves are solved, and integrated learning of gas tank safety status and regional risk prediction are realized, improving the safety status of gas tanks Gas use safety.

CN118941755APending Publication Date: 2024-11-12NORTH CHINA UNIVERSITY OF TECHNOLOGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410961066.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing gas safety monitoring technology is difficult to meet the detection needs in complex environments such as dark cabinets, open-air or mobile shipping, and the complex design of automatic shutoff valves has problems such as power supply and sensitive aging of components, which is difficult to meet the actual safety of use.

Method used

Using a smart identification and control system for gas use safety risks based on machine vision, the pre-system module and safety assessment and early warning module are used to calculate the safety level of the gas tank by using picture acquisition and broken state machine learning algorithms, and the data is used. The storage and risk zoning warning module calculates the risk level of a specific area and conducts safety warnings.

Benefits of technology

It realizes integrated learning and determination of the safety status of gas tanks and regional safety risk prediction, provides differentiated safety warning decisions, is convenient to use, direct effect, and is not subject to environmental restrictions, improving the safety of gas use.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941755A_ABST
    Figure CN118941755A_ABST
Patent Text Reader

Abstract

The invention discloses a gas use safety risk intelligent identification management and control method and system based on machine vision and a storage medium. The technical key points are that a data acquisition and preprocessing front-end system module comprises a picture acquisition unit and a damage state machine learning algorithm module; the picture acquisition unit is used for acquiring appearance pictures of the gas tank; the damage state machine learning algorithm module reads a gas tank appearance picture obtained by the picture acquisition unit, and outputs tank body damage and pollution state parameters; and the safety evaluation and early warning module is used for calculating the safety level of the tank body according to the tank body damage and pollution state parameters output by the data acquisition and preprocessing front-end system module and carrying out risk early warning according to different levels. The intelligent identification management and control system can serve gas users and industry safety supervisors, and has the outstanding advantages of being convenient to use, direct in effect, free of environmental limitation and the like.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of risk management, and more specifically, to a method, system and storage medium for intelligently identifying and controlling gas use safety risks based on machine vision. Background Art

[0002] In recent years, gas safety has received a lot of attention, and technical solutions for related protection methods and devices have been released one after another, mainly focusing on two aspects:

[0003] The first is gas monitoring and supervision. For example, CN106292469A discloses a gas safety monitoring system based on the Internet of Things. The distance signal is detected by the distance detector, and the timing module calculates the ignition time. The distance signal and the ignition time are transmitted to the single-chip microcomputer. The single-chip microcomputer uploads the received data to the Internet of Things server. The Internet of Things server sends instructions to the single-chip microcomputer, thereby realizing the control of the gas electromagnetic switch.

[0004] The second is the improvement of the gas blocking device. For example, CN102734533B discloses an automatic electromagnetic rapid gas safety shut-off valve, including an electronic valve switch, on which a valve switch detection unit, a timer and a central controller are provided. The valve switch detection unit, the timer, the central controller and the electronic valve switch are connected in sequence, which can automatically shut off the gas at a fixed time, which is convenient and practical.

[0005] However, the existing technical solutions are all designed from the aspects of gas leak detection and physical protection devices, ignoring the fact that gas cylinders are often in dark cabinets, open air, and mobile transportation during daily use (especially in small restaurants and hotels). Leakage detection based on sensors and the Internet of Things often cannot meet environmental requirements, and is limited by sensor performance, etc., and the effect is difficult to meet the needs of safety supervision and has not been promoted and adopted.

[0006] In addition, the automatic shut-off valve involves complex designs such as detection units and electronic valves, and has limitations such as power supply, aging of component sensitivity, and easy damage during daily use, making it difficult to meet actual safety requirements.

[0007] Therefore, it is urgent to design safety protection auxiliary methods and equipment based on the actual situation of gas use, so that safety protection can be truly implemented. Summary of the invention

[0008] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art and to provide a method, system and storage medium for intelligent identification and control of gas use safety risks based on machine vision.

[0009] A gas use safety risk intelligent identification and control system based on machine vision, including: data collection and pre-processing front-end system module, safety assessment and early warning module;

[0010] The data acquisition and preprocessing front-end system module includes: a picture acquisition unit and a damage state machine learning algorithm module; the picture acquisition unit is used to collect gas tank appearance photos; the damage state machine learning algorithm module reads the gas tank appearance photos obtained by the picture acquisition unit and outputs tank damage and contamination state parameters;

[0011] Among them, the safety assessment and early warning module calculates the tank safety level based on the tank damage and contamination status parameters output by the data acquisition and preprocessing front-end system module and issues risk warnings according to different levels.

[0012] Furthermore, the machine vision-based intelligent identification and control system for gas use safety risks also includes: a data storage and risk zoning warning module;

[0013] The data storage and risk zoning warning module can store each gas tank image, recognition results and safety assessment;

[0014] The data storage and risk zoning warning module can calculate the risk level of a specific area based on the weighted superposition of the safety risk status of a single gas tank, and provide overall supervision warning.

[0015] Furthermore, the gas tank safety status evaluation and early warning classification model is divided into:

[0016] (1) Low risk: The damaged area of ​​the tank is ≤10%;

[0017] (2) General risk: The damaged area of ​​the tank is within the range of (10%, 30%);

[0018] (3) Higher risk: The damaged area of ​​the tank is within the range of [30%, 50%]

[0019] (4) High risk: The damaged area of ​​the tank is greater than 50%.

[0020] Furthermore, the risk level for a specific area is calculated as follows:

[0021] Risk level of a specific area = (number of tanks with major risks × 4 + number of tanks with relatively high risks × 3 + number of tanks with general risks × 2 + number of tanks with low risks × 1) / number of tanks with all risk ratings in the area.

[0022] A method for intelligently identifying and controlling gas use safety risks based on machine vision includes the following steps:

[0023] S1, collect photos of the appearance of the gas tank;

[0024] S2, reads the gas tank appearance photo obtained by S1 through the damage state machine learning algorithm module, and outputs the tank damage and contamination state parameters;

[0025] S3, calculates the tank safety level according to the state parameters obtained in S2 and issues risk warnings according to different levels.

[0026] A storage medium stores a program for executing the above method.

[0027] The advantages of this application are:

[0028] (1) This application proposes a gas use safety risk intelligent identification and control system based on machine vision. It can determine the safety status of the original gas tank through integrated learning of basic parameters such as its appearance damage status and service life without making any improvements to the original gas tank, and use an evaluation algorithm to analyze its regional safety risk level to make differentiated safety prediction and early warning decisions. It can serve gas users and industry safety regulators and has outstanding advantages such as easy use, direct effect, and no environmental restrictions.

[0029] (2) This application proposes a method for calculating the risk level of a specific area, namely: Risk level of a specific area = (number of tanks with major risks × 4 + number of tanks with relatively high risks × 3 + number of tanks with general risks × 2 + number of tanks with low risks × 1) / number of tanks with all risk ratings in the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present invention will be further described in detail below in conjunction with the embodiments in the accompanying drawings, but this does not constitute any limitation to the present invention.

[0031] Figure 1 It is a flowchart of the operation process of the intelligent identification and control system of this application. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Second, "one embodiment" or "an embodiment" as referred to herein refers to a particular feature, structure, or characteristic that may be included in at least one implementation of the present invention.

[0035] The phrase “in one embodiment” appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive of other embodiments.

[0036] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0037] Embodiment 1:

[0038] A gas use safety risk intelligent identification and control system based on machine vision, comprising:

[0039] (1) Data acquisition and preprocessing front module. Figure 1 As shown, the data acquisition and preprocessing front-end module includes: a front-end APP system, a gas tank damage picture library (no less than 1,000 pictures, and complete marking), a machine learning algorithm model (convolutional neural network) module, a daily information maintenance module, and an integrated learning module. Through the front-end system and the acquisition device (which can be installed on a smart phone with a camera function through the APP, or a dedicated law enforcement device), the camera (built-in calling function) is called to collect gas tank appearance photos or gas tank photos uploaded by users (at least 2 pictures of the tank body and 1 picture of the tank top that meet the clarity requirements are required); the image is optimized and enhanced through preprocessing technology to improve the subsequent recognition accuracy and efficiency; the collected entity photos are processed and the state is identified through the machine learning algorithm, and the tank damage and pollution state parameters can be output; in addition, the remaining time of the safe use period, the next maintenance time and other regulatory data content can also be input to realize the integrated learning and analysis of the safety status.

[0040] (2) Safety assessment and early warning module: Based on the tank safety status parameters identified by the "data acquisition and pre-processing front-end system device", the built-in gas tank use safety risk assessment model can automatically calculate the tank safety level and issue risk warnings based on different levels. If a gas tank is found to have safety hazards, the system will issue an alarm in time to remind relevant personnel to take necessary measures.

[0041] Table 1 Gas tank safety status evaluation and early warning classification model

[0042]

[0043] (3) Data storage and risk zoning warning module: The system will record each gas tank image, recognition results and safety assessment and store them in the database. These data can be used for subsequent statistical analysis and historical record query to facilitate safety trend analysis and troubleshooting. Based on the weighted superposition of the safety risk status of individual gas tanks, the risk level of a specific area can be calculated and an overall regulatory warning can be issued.

[0044] The risk level is calculated as follows:

[0045] Risk level of a specific area = (number of tanks with major risks × 4 + number of tanks with relatively high risks × 3 + number of tanks with general risks × 2 + number of tanks with low risks × 1) / number of tanks with all risk ratings in the area.

[0046] The above embodiments are preferred implementation modes of the present invention and are only used to facilitate the description of the present invention. They are not intended to limit the present invention in any form. Any person with ordinary knowledge in the relevant technical field, if they do not depart from the scope of the technical features of the present invention, can make equivalent embodiments by partial changes or modifications to the technical contents disclosed in the present invention, and they still fall within the scope of the technical features of the present invention without departing from the technical features of the present invention.

Claims

1. A gas use safety risk intelligent identification and control system based on machine vision, characterized in that: include: Data collection and pre-processing front-end system module, safety assessment and early warning module; The data acquisition and preprocessing front-end system module includes: a picture acquisition unit and a damage state machine learning algorithm module; the picture acquisition unit is used to collect gas tank appearance photos; the damage state machine learning algorithm module reads the gas tank appearance photos obtained by the picture acquisition unit and outputs tank damage and contamination state parameters; Among them, the safety assessment and early warning module calculates the tank safety level based on the tank damage and contamination status parameters output by the data acquisition and preprocessing front-end system module and issues risk warnings according to different levels.

2. According to claim 1, a gas use safety risk intelligent identification and control system based on machine vision is characterized in that: The machine vision-based gas use safety risk intelligent identification and control system also includes: a data storage and risk zoning early warning module; The data storage and risk zoning warning module can store each gas tank image, recognition results and safety assessment; The data storage and risk zoning warning module can calculate the risk level of a specific area based on the weighted superposition of the safety risk status of a single gas tank, and provide overall supervision warning.

3. According to claim 2, a gas use safety risk intelligent identification and control system based on machine vision is characterized in that: The gas tank safety status evaluation and early warning classification model is divided into: (1) Low risk: The damaged area of ​​the tank is ≤10%; (2) General risk: The damaged area of ​​the tank is within the range of (10%, 30%); (3) Higher risk: The damaged area of ​​the tank is within the range of [30%, 50%] (4) High risk: The damaged area of ​​the tank is greater than 50%.

4. According to claim 3, a gas use safety risk intelligent identification and control system based on machine vision is characterized in that: The risk level for a specific area is calculated as follows: Risk level of a specific area = (number of tanks with major risks × 4 + number of tanks with relatively high risks × 3 + number of tanks with general risks × 2 + number of tanks with low risks × 1) / number of tanks with all risk ratings in the area.

5. A method for intelligent identification and control of gas use safety risks based on machine vision, characterized in that: The steps include: S1, collect photos of the appearance of the gas tank; S2, reads the gas tank appearance photo obtained by S1 through the damage state machine learning algorithm module, and outputs the tank damage and contamination state parameters; S3, calculates the tank safety level according to the state parameters obtained in S2 and issues risk warnings according to different levels.

6. A storage medium, characterized in that: The storage medium stores a program for executing the method as claimed in claim 5.