Welding spot quality analysis system and method based on big data mathematical statistics
A technology of mathematical statistics and solder joint quality, applied in electrical digital data processing, special data processing applications, digital data information retrieval, etc. explanatory effect
Pending Publication Date: 2021-10-29
DONGFENG MOTOR GRP
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
figure 1 The abnormal fluctuation (unsmooth) of the marked welding area resistance versus time curve indicates that "spatter" phenomenon has occurred in the current welding process. The larger the fluctuation jump, the more serious the "spatter" phenomenon, which leads to poor solder joints quality and higher energy consumption
[0005] In the existing technical solutions, the judgment of the state of the solder joints is mainly through the installation of corresponding devices and sensors, online collection of solder joint data and photos of solder joint splash gestures, and research on energy consumption; in this method, it is necessary to install corresponding devices and Sensors, and online collection of solder joint data and solder joint spatter attitude information, transmitted to the computer through the CAN line, the method is complex
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
[0020] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0021] The data that the present invention needs statistical analysis is the welding process data (half a year, 500G) of the welding robot that has accumulated a large amount of automatic real-time collections, and the sampling period of solder joint data is 1ms, and about 400 solder joint records of each solder joint file, statistical analysis of data Massive, to avoid sample differences caused by factors such as time and location, resulting in model instability, this is the first step in statistical analysis of big data. In the process of basic data integration, Numpy's efficient processing capabilities for N-dimensional arrays are more used to deal with the differences, high dimensions, and sparseness of data sources, find the heterogeneity and commonality of data, and reduce dimensionality and denoise. In the subsequent data proce...
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 welding spot quality analysis system and method based on big data mathematical statistics, which take intelligently manufactured welding spot big data as a research object, carry out mathematical statistics on massive welding spot dynamic resistance and related data, carry out statistical analysis on the welding spot dynamic resistance performance, and provide a set of complete welding spot dynamic resistance performance statistical analysis method and process is provided; then welding spot quality abnormity information is obtained through dynamic resistance discretization, outlier and skewness / kurtosis abnormity analysis, welding spot real objects and spot check results are combined, welding spot abnormity reasons are analyzed together with field welding process experts, and good interpretability can be obtained. In order to further quickly find quality defect problems, search main factors influencing quality abnormity and realize predictive maintenance of quality inspection, process and the like, the purposes of increasing efficiency, saving energy and reducing cost are achieved.
Description
technical field [0001] The invention relates to the technical field of auto parts manufacturing, in particular to a solder joint quality analysis system and method based on big data mathematical statistics. Background technique [0002] Welding is a common process in modern machinery manufacturing industry, and it is widely used in automobile manufacturing. The welding process uses a welding torch as a tool to connect two or more metal materials of the same or different types into one body in the form of solder joints. The quality of the solder joints has a great impact on the overall quality of the car. With the deepening of intelligent manufacturing, big data technology and artificial intelligence can be used to make welding data generate greater value. For example, it can quickly find quality defects, find out the main factors affecting quality abnormalities, and realize predictive maintenance such as quality inspection and process, so as to achieve the purpose of increa...
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): G06F16/2458G06F17/18
CPCG06F16/2462G06F17/18Y02D10/00Y02P90/30
Inventor 王秋来史建鹏洪伟孙震汤泽波
Owner DONGFENG MOTOR GRP