Method and system for judging compliance of hydrogenation process based on artificial intelligence recognition

Abstract

The present disclosure provides a method and system for judging the compliance of a hydrogenation process based on artificial intelligence recognition, wherein the method includes: collecting the behavioral actions of staff members through an AI camera, using a posture learning algorithm to identify the behavioral actions, and forming behavioral action data; reading the behavioral action data through a semantic analysis algorithm, and converting the behavioral action data into digital feature data; synthesizing the multi-frame information contained in each action in the digital feature data through a big data analysis framework to obtain the single action information data corresponding to the action, and storing the single action information data corresponding to all actions in a database; querying the single action information data stored in the database through a background service, judging compliance based on a preset hydrogenation process template, and obtaining a compliance judgment result. The present disclosure can realize the real-time collection of the behavioral actions of manual operations, realize the process guidance of the hydrogenation process and the detection of illegal actions, and provide multiple security guarantees for hydrogenation stations.

Description

Technical Field

[0001] This document relates to the field of artificial intelligence, and in particular to a method and system for determining the compliance of a hydrogenation process based on artificial intelligence identification. Background Art

[0002] Hydrogen refueling stations serve as hubs connecting upstream hydrogen production and downstream users in the industry, providing hydrogen for fuel cell vehicles. However, the nature of hydrogen itself determines its dangerousness, and hydrogen-related accidents at home and abroad have proved that the danger is difficult to completely eliminate. Therefore, it is necessary to attach great importance to the compliance judgment of the hydrogen refueling process to avoid safety problems.

[0003] Among related technologies, hydrogen refueling stations adopt traditional management methods, which have defects such as simple functional equipment and low degree of integration. Full-process digital management is a new trend in the development of the new energy industry, which provides new systems, equipment, technologies and management ideas. However, it is limited by the design of traditional hardware, making it impossible to use digital means to supervise whether the hydrogen refueling process is compliant.

[0004] Based on the above analysis of the development status of this technology field, the existing technology lacks the use of intelligent digital means to judge the compliance of the hydrogenation process. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for judging the compliance of a hydrogenation process based on artificial intelligence recognition, aiming to solve the above-mentioned problems in the prior art.

[0006] According to a first aspect of an embodiment of the present disclosure, a method for determining compliance of a hydrogenation process based on artificial intelligence identification is provided, comprising:

[0007] The AI ​​camera is used to collect the staff's behavior and actions, and the posture learning algorithm is used to identify the behavior and actions to form behavior and action data;

[0008] Read behavioral action data through semantic analysis algorithms and convert the behavioral action data into digital feature data;

[0009] The multi-frame information of each action in the digital feature data is synthesized through a big data analysis framework to obtain the single action information data corresponding to the action, and the single action information data corresponding to all actions are stored in the database;

[0010] The single action information data stored in the database is queried through the background service, and compliance is determined based on the preset hydrogenation process template to obtain the compliance judgment result.

[0011] According to a second aspect of an embodiment of the present disclosure, a hydrogenation process compliance judgment system based on artificial intelligence recognition is provided, comprising:

[0012] A data collection module is used to collect the behavior of workers through AI cameras, identify the behavior using a posture learning algorithm, and generate behavior data;

[0013] A feature processing module is used to read the behavior action data through a semantic analysis algorithm and convert the behavior action data into digital feature data;

[0014] The multi-frame merging module is used to synthesize the multi-frame information contained in each action in the digital feature data through the big data analysis framework, obtain the single action information data corresponding to the action, and store the single action information data corresponding to all actions in the database;

[0015] The compliance judgment module is used to query the single action information data stored in the database through the background service, judge whether it is compliant according to the internal hydrogenation process template, and obtain the compliance judgment result.

[0016] The technical solution provided by the embodiment of the present invention includes the following beneficial effects: it can realize real-time collection of manual operation behaviors, predict and warn of real-time accident hazards and take necessary intervention measures, realize process guidance of hydrogenation process and detection of illegal actions, and provide multiple safety guarantees for hydrogenation stations.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a flow chart of a method for determining compliance of a hydrogenation process based on artificial intelligence recognition according to an embodiment of the present invention;

[0020] Figure 2 Schematic diagram of the steps of a method for determining compliance of a hydrogenation process according to an embodiment of the present invention;

[0021] Figure 3 2 is a schematic diagram of a hydrogenation process compliance judgment system based on artificial intelligence recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0023] Technical terminology

[0024] NLP semantic analysis algorithm: studies language issues in human-computer interaction. According to the difficulty of technical implementation, it is divided into three types: simple matching, fuzzy matching, and paragraph comprehension.

[0025] Spark parallel framework: a general-purpose big data analytics engine with high performance, ease of use, and universality.

[0026] Redis database: A remote dictionary service, an open source, network-friendly, in-memory and persistent log-based, key-value database written in ANSI C, and providing APIs in multiple languages.

[0027] Method Example

[0028] According to an embodiment of the present invention, a method for judging the compliance of a hydrogenation process based on artificial intelligence recognition is provided. Figure 1 This is a flow chart of a method for determining compliance of a hydrogenation process based on artificial intelligence recognition according to an embodiment of the present invention. Figure 1 As shown, the method for determining compliance of a hydrogenation process based on artificial intelligence recognition according to an embodiment of the present invention specifically includes:

[0029] In step S110, the AI ​​camera captures the worker's actions and uses a gesture learning algorithm to identify them, generating action data. Specifically, this involves capturing every frame of the worker's actions from the moment they begin operating the hydrogen refueling machine to the moment they complete the refueling process, including gestures and movements, and identifying them using a gesture learning algorithm trained on OpenPose.

[0030] In step S120, the behavior action data is read through the semantic analysis algorithm and converted into digital feature data in json format, that is, the behavior action data is classified and labeled to facilitate the algorithm to perform model training and prediction. The semantic analysis algorithm adopts the BERT model in NLP.

[0031] In step S130, the multi-frame information of each action in the digital feature data is synthesized through the big data analysis framework to obtain the single action information data corresponding to the action, and the single action information data corresponding to all actions are stored in the database. Specifically, it includes:

[0032] Multi-frame information is synthesized through custom templates, that is, digital feature data is analyzed, processed and classified through custom templates to obtain single action information data, and the single action information data is stored in the database in json format. The big data analysis framework adopts the Spark parallel framework, and the database adopts Redis. Among them, the custom template uses the posture learning algorithm to identify the standard hydrogenation action, and the angle information and distance information in the behavioral action data are formed.

[0033] In step S140, the single action information data stored in the database is queried through the background service, and compliance is determined according to the preset hydrogenation process template to obtain a compliance judgment result. Step S140 is implemented through an algorithm. Specifically, it includes:

[0034] The algorithm compares the angles and similarities of the limbs in the hydrogenation process template with the single action information data. If the difference is within 5%, the action is considered a match. If an action is not executed, that is, no single action information data matching the action in the hydrogenation process template is generated, the process is considered to be missing. If the order of the single action information data contained in different actions is inconsistent with the order in the hydrogenation process template, it is considered a process jump violation. The backend service uses Java.

[0035] The standard hydrogenation actions in the hydrogenation process template are: step 1, touch the electrostatic column; step 2, take the electrostatic clamp and clamp it to the vehicle; step 3, operate the hydrogenation machine control panel; step 4, take the hydrogenation gun and insert it into the hydrogenation vehicle; step 5, after hydrogenation is completed, touch the electrostatic column or hydrogenation machine; step 6, unplug the hydrogenation gun; step 7, remove the electrostatic clamp and put it back into the electrostatic box.

[0036] The method further includes: collating single action information data and compliance judgment results after the hydrogenation is completed, and generating a data report.

[0037] To sum up, in response to the existing problems, this paper invented a method for judging the compliance of the hydrogenation process based on artificial intelligence recognition. It uses AI cameras to collect and process a large number of manual operation actions in real time, and merges the multiple frames of information corresponding to each action into a single action information book data to improve processing efficiency. It judges compliance based on the internal hydrogenation process template, realizes the process guidance of the hydrogenation process and the detection of illegal actions, and provides multiple safety guarantees for hydrogenation stations.

[0038] Figure 2 Schematic diagram of the steps of the method for determining compliance of the hydrogenation process according to an embodiment of the present invention. Figure 2As shown, the complete steps of the method for determining the compliance of the hydrogenation process are demonstrated.

[0039] System Example

[0040] According to an embodiment of the present invention, a hydrogenation process compliance judgment system based on artificial intelligence recognition is provided. Figure 3 Schematic diagram of a hydrogenation process compliance judgment system based on artificial intelligence recognition according to an embodiment of the present invention. Figure 3 As shown, the hydrogenation process compliance judgment system based on artificial intelligence recognition according to an embodiment of the present invention specifically includes:

[0041] The data acquisition module 30 is used to capture the worker's actions using an AI camera, identify them using a gesture learning algorithm, and generate action data. Specifically, it collects every frame of the worker's actions from the moment they begin operating the hydrogenation equipment to the moment they complete the hydrogenation process, and identifies them using a gesture learning algorithm trained on OpenPose.

[0042] The feature processing module 32 is used to read the behavior action data through a semantic analysis algorithm and convert the behavior action data into digital feature data. The semantic analysis algorithm adopts the BERT model in NLP.

[0043] The multi-frame merging module 34 is used to synthesize the multi-frame information contained in each action in the digital feature data using a big data analysis framework, obtain the single action information data corresponding to the action, and store the single action information data corresponding to all actions in a database. Specifically, it is used to synthesize multi-frame information using a custom template. The big data analysis framework uses the Spark parallel framework and the database uses Redis.

[0044] The compliance judgment module 36 is used to query the single action information data stored in the database through the background service, judge whether it is compliant according to the internal hydrogenation process template, and obtain the compliance judgment result. Specifically used for:

[0045] If an action is not executed, meaning no matching single action information data is generated for that action in the hydrogenation process template, a process violation is identified. If the order in which the single action information data for different actions appears is inconsistent with the order in the hydrogenation process template, a process jump violation is identified. The backend service uses Java.

[0046] The system further comprises:

[0047] The data report module 38 is used to organize the single action information data and judgment results after the hydrogenation is completed and generate a data report.

[0048] To sum up, in response to the existing problems, this paper invented a hydrogenation process compliance judgment system based on artificial intelligence recognition. It uses AI cameras to collect and process a large number of manual operation behaviors in real time, and merges the multiple frames of information corresponding to each action into a single action information book data to improve processing efficiency. It judges compliance based on the internal hydrogenation process template, realizes the process guidance of the hydrogenation process and detection of illegal actions, and provides multiple safety guarantees for hydrogenation stations.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for judging the compliance of a hydrogenation process based on artificial intelligence recognition, characterized in that: include: The AI ​​camera is used to collect the staff's behavior and actions, and the posture learning algorithm is used to identify the behavior and actions to form behavior and action data; Reading the behavior action data through a semantic analysis algorithm and converting the behavior action data into digital feature data; synthesizing multiple frames of information contained in each action in the digital feature data through a big data analysis framework to obtain single action information data corresponding to the action, and storing the single action information data corresponding to all actions in a database; The single action information data stored in the database is queried through a background service, and compliance is determined according to a preset hydrogenation process template to obtain a compliance determination result.

2. The method according to claim 1, characterized in that The method further includes: collating the single action information data and the compliance judgment result after the hydrogenation is completed, and generating a data report.

3. The method according to claim 1, characterized in that The collecting of the worker's behavior and actions by the AI ​​camera specifically includes: collecting each frame of all actions from the time the worker starts operating the hydrogenation equipment to the end of hydrogenation.

4. The method according to claim 1, wherein The semantic analysis algorithm adopts the BERT model in NLP, the big data analysis framework adopts the Spark parallel framework, the database adopts Redis, and the background service adopts Java.

5. The method according to claim 1, wherein The synthesizing of the multi-frame information contained in each action in the digital feature data through a big data analysis framework specifically includes: synthesizing the multi-frame information through a custom template.

6. The method according to claim 1, characterized in that The determination of compliance based on the preset hydrogenation process template includes: When an action is not executed, that is, the single action information data that matches the action in the hydrogenation process template is not generated, it is determined that the process lacks a violation; when the order in which the single action information data contained in different actions appears is inconsistent with the order of the hydrogenation process template, it is determined that the process jumps in violation.

7. A hydrogenation process compliance judgment system based on artificial intelligence recognition, characterized in that: include: A data collection module is used to collect the behavior of workers through AI cameras, identify the behavior using a posture learning algorithm, and generate behavior data; A feature processing module, configured to read the behavior action data through a semantic analysis algorithm and convert the behavior action data into digital feature data; A multi-frame merging module is used to synthesize the multi-frame information contained in each action in the digital feature data through a big data analysis framework to obtain the single action information data corresponding to the action, and store the single action information data corresponding to all actions in a database; The compliance judgment module is used to query the single action information data stored in the database through the background service, judge whether it is compliant according to the internal hydrogenation process template, and obtain a compliance judgment result.

8. The system according to claim 7, characterized in that The system further comprises: The data report module is used to organize the single action information data and the judgment results after the hydrogenation is completed and generate a data report.

9. The system according to claim 7, wherein: The semantic analysis algorithm adopts the BERT model in NLP, the big data analysis framework adopts the Spark parallel framework, the database adopts Redis, and the background service adopts Java.

10. The system according to claim 7, wherein: The data acquisition module is specifically used to: collect each frame of all actions from the beginning of the operator's operation of the hydrogenation equipment to the end of hydrogenation; The multi-frame merging module is specifically used to: synthesize the multi-frame information through a custom template; The compliance judgment module is specifically used to: when an action is not executed, that is, the single action information data that matches the action in the hydrogenation process template is not generated, it is judged that the process lacks a violation; when the order in which the single action information data contained in different actions appears is inconsistent with the order of the hydrogenation process template, it is judged as a process jump violation.

Images