Design And Implementation Of Vehicle Body Health Data Detection System

Information networking has penetrated into every aspect of people's working lives,and it has formed a perfect collision with the rapid development of the modern automobile industry.Of course,whether it is the owner or various companies on the health of the body It is more and more concerned that some vehicle body health data analysis not only presents the body's own health status for a period of time,but these conclusions are not only instructive for owners and even related companies such as insurance companies and second-hand car market leaders.In the presence of this demand,the system integrates client presentation,data transmission,data analysis,health status and prediction into one,with maneuvering times,vehicle age,number of days used,lighting conditions,engine speed and killing thick driving.Based on the six factors of speed,it creates a practical vehicle body health detection system for users.This system uses the OBD interface to collect real-time vehicle body data,transmit it to a smartphone for processing and calculation,and then displays it to the user with a smart phone.The research project mainly did the following work:First of all,the collected data is transmitted from the PC side to the client side using the currently very convenient Bluetooth transmission technology.And save it on the client.In this way,vehicle body data can be processed on the mobile phone side,and can also be added,deleted,or the like.Second,using the KNN algorithm and 2? criteria to classify the body health data.The KNN algorithm is used to determine whether the car body is in a normal state.In the determination of the KNN value,an Android parallel operation is used to improve the calculation efficiency,and the results of the three consecutive votes are consistent,and the final classification result is determined.The normal car body is further graded by the six health levels classified by the 2? criteria.This is a very detailed level for the health of the car body.Finally,according to the classification of multiple state of the vehicle body,a linear regression prediction model and a grey prediction model are compared to select a prediction method that is more suitable for the system—a method combining the linear regression prediction and the grey prediction algorithm.If the univariate linear regression algorithm's significance coefficient R is greater than 0.7,it means that the variables are highly significant and can be predicted by one-way linear regression.Otherwise,the gray prediction method is used to predict the future health of the vehicle body,and how long it takes to reach an anomaly Status,thus reminding the user even if sent for inspection.This not only saves the cost of hardware equipment,but also provides the user with an overall data trend to maintain the vehicle body.