Method for detecting standardized operation of locomotive steward based on artificial intelligence
An artificial intelligence and flight attendant technology, applied in the field of multi-source heterogeneous fusion analysis and detection, can solve the problems of inability to accurately locate the standardized operations of flight attendants, difficulty in achieving high coverage of locomotive traffic data analysis, etc., and achieve high theoretical research value and practical application value , Ease of practical application, and the effect of increasing operation and maintenance costs
Pending Publication Date: 2022-04-15
CHINA NAT SOFTWARE & SERVICE
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] At present, in the face of the above massive data, diverse data sources, and different data forms, manual analysis and automatic analysis of a single data source cannot accurately determine whether the flight attendants have completed standardized operations in different scenarios, and cannot efficiently convert multi-dimensional driving data into flight attendant job evaluation. Standards, it is difficult to meet the requirements of high coverage and high accuracy for locomotive traffic data analysis
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] In order to further understand the present invention, the technical solutions of the present invention will be further described below in combination with actual use cases and accompanying drawings.
[0033] This case is to verify the technical effectiveness of this method based on the train operation data of the XX workshop of the XX Locomotive Depot of China Railway XX Bureau Group Co., Ltd. The LKJ data used are shown in Table 1, and the standardization item of the judged flight attendant is the hand ratio signal.
[0034] The detailed implementation plan is as follows:
[0035] 1) The flight attendant dumps the video files in the driver's room and the video files of the road conditions before and after the train to the video analysis system through the U disk, and the video analysis module first performs video data preprocessing.
[0036] 2) Based on the FTP protocol, the LKJ source file is obtained through a third-party interface. The LKJ data module decodes the L...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a locomotive steward standardized operation detection method based on artificial intelligence. The method comprises the following steps: 1) acquiring an indoor video file of a locomotive cab and road condition video files in front of and behind the locomotive, and acquiring an LKJ source file; (2) the LKJ data module decodes the LKJ source file to obtain LKJ data; 3) an OSD data module extracts OSD data and a corresponding video position from the video file obtained in the step 1); 4) the item point analysis module retrieves the LKJ data to generate a hand ratio signal item point, and inquires and intercepts an indoor video clip and a road condition video clip in a time interval corresponding to the record according to the time of the record; and 5) performing comprehensive identification on the indoor video clip and the road condition video clip by a hand ratio signal action identification model, and judging whether a corresponding standardized operation behavior exists or not. According to the invention, the recognition accuracy and recognition efficiency of the standardized operation of the locomotive crew are improved.
Description
technical field [0001] The invention relates to the field of computer science and the field of traffic management of railway locomotive crew members, in particular to an artificial intelligence-based multi-source heterogeneous fusion analysis and detection method for standardized operations of railway locomotive crew members. Background technique [0002] Traffic safety has always been the top priority and untouchable red line of the national railway maintenance system. Among them, the locomotive crew (commonly known as the train driver) is the first person responsible for ensuring traffic safety and the last pass. Its value multiplies the quality of operation, which is related to the overall safety production situation of the entire railway maintenance system and has a huge social impact. At this stage, according to relevant regulations, locomotive crew members must strictly implement the "Operational Standards for Locomotive Crew One-time Trip", and all locomotives attach...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04N17/02H04N17/04H04N17/06
Inventor 张子良靳钊乔实
Owner CHINA NAT SOFTWARE & SERVICE