An automobile spark plug aging detection and early warning system based on data analysis

Abstract

The present invention discloses an automobile spark plug aging detection and early warning system based on data analysis, which specifically relates to the field of automobile spark plug monitoring technology, and includes: a data acquisition module for collecting working parameter data of automobile spark plugs, a data processing module for processing and analyzing the collected data, a model establishment module for establishing a prediction model based on the collected working parameter data of automobile spark plugs, a parameter prediction module for predicting the future working parameters of the spark plugs based on the collected working parameter data of automobile spark plugs and the model prediction results, and a system interaction module for interacting with users. The present invention designs the functions of a model selection module, a parameter selection module, and a model training module, so that the system can train multiple different machine learning models, and fuse the prediction results of these models through a model fusion module to obtain a final prediction result, thereby improving the accuracy of the model.

Description

Technical Field

[0001] The invention relates to the technical field of automobile spark plug monitoring, and in particular to an automobile spark plug aging detection and early warning system based on data analysis. Background Art

[0002] Automobile spark plug aging detection and early warning refers to predicting the possibility of spark plug aging by analyzing automobile spark plug usage data, and issuing early warning signals before the spark plug ages, reminding car owners to replace the spark plugs in time to avoid engine failures and safety problems caused by spark plug aging. Usually, professional spark plug testing instruments are used to detect whether the voltage of the spark plug is normal and whether the spark plug is aged. However, such a method requires users to maintain the vehicle themselves during actual use, and the use of professional instruments for detection is limited by time and space, and it is impossible to monitor the working status of the spark plug in real time, and problems may not be discovered in time. This makes it impossible for users to understand the status of the spark plug in real time while driving, thereby increasing travel risks. Therefore, the practicality of such monitoring methods in actual use is reduced. Therefore, we propose an automobile spark plug aging detection and early warning system based on data analysis. Summary of the invention

[0003] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an automobile spark plug aging detection and early warning system based on data analysis.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] A car spark plug aging detection and early warning system based on data analysis, comprising: a data acquisition module for collecting working parameter data of car spark plugs, a data processing module for processing and analyzing the collected data, a model building module for building a prediction model based on the collected working parameter data of car spark plugs, a parameter prediction module for predicting the future working parameters of spark plugs based on the collected working parameter data of car spark plugs and the model prediction results, a system interaction module and a parsable module for interacting with users, the data acquisition module comprising a sensor interface module for connecting and communicating with sensors on cars and acquiring data collected by sensors, a data storage module for storing collected data in a database for subsequent data processing and analysis, and a data transmission module for transmitting and processing collected data, the data processing module comprising a data cleaning module for performing operations such as denoising, deduplication, and processing missing values ​​on collected data, and a data processing module for extracting useful features from the cleaned data The model building module includes a data set partitioning module for dividing the processed data set into a training set, a validation set and a test set, a selection training module for selecting a suitable machine learning algorithm or deep learning model and performing model training and optimization on the training set, and a model evaluation module for evaluating the trained model on the validation set and the test set. The parameter prediction module includes a threshold setting module for setting a prediction result threshold, a prediction output module for presenting the results predicted by the model to the user in a visual and easy-to-understand manner, and a data warning module for sending warning information to the car owner when the prediction result reaches the warning threshold. The system interaction module includes a user input module for binding user personal information according to information entered by the user into the system, a warning storage module for sending the warning information in the data warning module to the user while performing warning backup, and a data warning module for sending warning information to the user.

[0006] The present invention is further configured as follows: the selection and training module includes a model selection module for selecting a suitable algorithm or model, a parameter selection module for selecting parameters for the selected algorithm or model, a model training module for training using preprocessed data and the selected model, a model fusion module for fusing and tuning multiple models, an interpretable analysis module for interpreting and analyzing the prediction results of the model, a system monitoring module for monitoring and managing the entire system, a user feedback module for collecting user feedback and suggestions, and an exception handling module for detecting and handling any abnormal situations during data processing and analysis.

[0007] The present invention is further configured as follows: the sensor interface module transmits the collected data to the data storage module and stores the data for subsequent data processing and analysis; the data transmission module retrieves the data in the data storage module and distributes the data to other modules for processing; the data transmission module transmits the collected raw data to the data cleaning module and cleans and pre-processes the raw data.

[0008] The present invention is further configured as follows: the feature extraction module extracts useful features from the cleaned data from the data cleaning module, the data analysis module extracts these useful features from the original data according to the feature extraction module for model training and prediction, the data set division module receives the data that completes the data analysis in the data analysis module and divides it into a training set, a validation set and a test set, the selection training module needs to select a suitable model and algorithm according to the output of the data set division module, and perform training and optimization, the model evaluation module needs to evaluate the performance and generalization ability of the model according to the output of the selection training module, and judge the quality of the model according to the evaluation result, and the threshold setting module can set the optimal threshold based on the comprehensive model evaluation module and the actual situation in order to better judge the prediction result of the model.

[0009] The present invention is further configured as follows: the prediction output module can help users timely understand the aging status of automobile spark plugs according to the threshold setting module and the amount of actual working value; the warning storage module records the data of actual values ​​exceeding the threshold value received from the data warning module and feeds back the warning information to the user through the output user module; the data warning module can help users timely discover abnormal situations and perform warning processing according to the prediction output module to better ensure the safety and stability of the automobile; the output user module converts the prediction results of spark plug aging obtained by the data warning module through analysis and processing of the data of automobile spark plugs into an easy-to-understand form and conveys it to the user; the user input module transmits the information bound to the user to the system so as to convey the warning information to the user for warning.

[0010] The present invention is further configured as follows: the model selection module can select the optimal parameter combination in the machine learning model according to the parameter selection module based on different model evaluation indicators in the model selection module to train the machine learning model to establish a prediction model; the model training module trains multiple different machine learning models and passes the prediction results of these models to the model fusion module for fusion to obtain the final prediction result; the parseable module analyzes the result after the model fusion module fuses the prediction results of multiple models to find out the causes of model prediction errors and put forward improvement suggestions.

[0011] The present invention is further configured as follows: the parameter selection module proposes improvement suggestions and parameter adjustment suggestions to select more appropriate model parameters after analyzing the prediction results of the model according to the analyzable module; the system monitoring module proposes improvement suggestions and system optimization suggestions to optimize and adjust the system after analyzing the prediction results of the model according to the analyzable module; the function of the exception handling module is to handle the exception in time when the system monitoring module detects the exception; the system monitoring module feeds back the system data to the user feedback module in real time so as to provide feedback to the user.

[0012] The beneficial effects of the present invention are:

[0013] Through the functions of the model selection module, parameter selection module and model training module, the system of the present invention can train multiple different machine learning models, and fuse the prediction results of these models through the model fusion module to obtain the final prediction result, thereby improving the accuracy of the model.

[0014] At the same time, the parameter selection module analyzes the prediction results of the model based on the analyzable module and proposes improvement suggestions and parameter adjustment suggestions to select more appropriate model parameters. The system monitoring module analyzes the prediction results of the model based on the analyzable module and proposes improvement suggestions and system optimization suggestions to optimize and adjust the system. The role of the exception handling module is to handle the exception in time when the system monitoring module detects the exception. The system monitoring module feeds back the system data to the user feedback module in real time so as to provide feedback to the user. Through the collaborative relationship between these modules, the accuracy and reliability of the entire system can be improved, thereby better realizing the detection and early warning of automobile spark plug aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the system in the present invention.

[0016] Figure 2 This is a partial system diagram of the selection training module in the present invention. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0018] Example 1

[0019] like Figure 1-2As shown, a car spark plug aging detection and early warning system based on data analysis includes: a data acquisition module for collecting working parameter data of car spark plugs, a data processing module for processing and analyzing the collected data, a model building module for building a prediction model according to the collected working parameter data of car spark plugs, a parameter prediction module for predicting the future working parameters of spark plugs based on the collected working parameter data of car spark plugs and the model prediction results, a system interaction module and a parsable module for interacting with users, the data acquisition module includes a sensor interface module for connecting and communicating with sensors on cars and acquiring data collected by sensors, a data storage module for storing collected data in a database for subsequent data processing and analysis, and a data transmission module for transmitting and processing collected data, the data processing module includes a data cleaning module for performing operations such as denoising, deduplication, and processing missing values ​​on collected data, a feature extraction module for extracting useful features from the cleaned data, and a data analysis module for analyzing the extracted features;

[0020] The model building module includes a data set partitioning module for partitioning the processed data set into a training set, a validation set and a test set, a selection training module for selecting a suitable machine learning algorithm or deep learning model and performing model training and optimization on the training set, and a model evaluation module for evaluating the trained model on the validation set and the test set. The parameter prediction module includes a threshold setting module for setting a prediction result threshold, a prediction output module for presenting the model prediction result to the user in a visual and easy-to-understand manner, and a data warning module for sending warning information to the car owner when the prediction result reaches the warning threshold. The system interaction module includes a user input module for binding user personal information according to the information entered by the user into the system, a warning storage module for sending the warning information in the data warning module to the user while performing warning backup, and a data warning module for sending warning information to the user.

[0021] The selection and training module includes a model selection module for selecting a suitable algorithm or model, a parameter selection module for selecting parameters for the selected algorithm or model, a model training module for training using preprocessed data and the selected model, a model fusion module for fusing and tuning multiple models, an interpretable analysis module for interpreting and analyzing the prediction results of the model, a system monitoring module for monitoring and managing the entire system, a user feedback module for collecting user feedback and suggestions, and an exception handling module for detecting and handling any abnormal situations during data processing and analysis. The sensor interface module transmits the collected data to the data storage module and stores the data for subsequent data processing and analysis;

[0022] The data transmission module retrieves the data from the data storage module and distributes the data to other modules for processing. The data transmission module transmits the collected raw data to the data cleaning module and cleans and preprocesses the raw data. The feature extraction module extracts useful features from the cleaned data in the data cleaning module. The data analysis module extracts these useful features from the raw data according to the feature extraction module for model training and prediction. The data set partitioning module receives the data analyzed in the data analysis module and partitions it into training set, validation set and test set. The selection training module needs to select the appropriate model and algorithm according to the output of the data set partitioning module, and perform training and optimization. The model evaluation module needs to evaluate the performance and generalization ability of the model according to the output of the selection training module. , and judge the quality of the model according to the evaluation result. The threshold setting module can set the best threshold based on the comprehensive model evaluation module and the actual situation to better judge the prediction result of the model. The prediction output module can help users timely understand the aging of automobile spark plugs according to the threshold setting module and the amount of the actual working value. The early warning storage module records the data of the actual value exceeding the threshold received from the data early warning module and feeds back the early warning information to the user through the output user module. The data early warning module can help users timely discover abnormal situations and perform early warning processing according to the prediction output module to better ensure the safety and stability of the car. The output user module converts the prediction result of spark plug aging obtained by the data early warning module through analysis and processing of the data of the automobile spark plug into an easy-to-understand form and conveys it to the user;

[0023] The user input module transmits the information bound by the user to the system so as to pass the warning information to the user for warning. The model selection module can select the optimal parameter combination in the machine learning model according to the parameter selection module based on different model evaluation indicators in the model selection module to train the machine learning model to establish a prediction model. The model training module trains multiple different machine learning models and passes the prediction results of these models to the model fusion module for fusion to obtain the final prediction result. The analyzable module analyzes the result after the prediction results of multiple models are fused by the model fusion module to find out the cause of the model prediction error and put forward improvement suggestions;

[0024] The parameter selection module analyzes the prediction results of the model based on the parseable module and proposes improvement suggestions and parameter adjustment suggestions to select more appropriate model parameters. The system monitoring module analyzes the prediction results of the model based on the parseable module and proposes improvement suggestions and system optimization suggestions to optimize and adjust the system. The function of the exception handling module is to handle the exception in time when the system monitoring module detects the exception. The system monitoring module feeds back the system data to the user feedback module in real time so as to provide feedback to the user.

[0025] In the above embodiment, by collecting the working parameter data of the automobile spark plug, the data is cleaned and feature extracted by the data processing module, and then the prediction model is obtained through model training and evaluation in the model building module. The parameter prediction module uses the prediction model and the collected working parameter data of the automobile spark plug to predict the future working parameters of the spark plug, and sends a warning message to the car owner when the prediction result reaches the warning threshold. The system interaction module is responsible for interacting with the user, including the user input module, the warning storage module and the data warning module. At the same time, the cooperation of the modules such as the training module, the model fusion module, the analyzable module, the system monitoring module, the exception handling module and the user feedback module can improve the accuracy and reliability of the whole system. The system can help car owners to timely discover the aging of the automobile spark plug and ensure the safety and stability of the car.

[0026] The function of the exception handling module is to handle the exception in time when the system monitoring module detects the exception. The function of the parameter selection module is to select the best model parameters to improve the accuracy and reliability of the model. In practical applications, if the exception handling module does not respond to the exception in time, it may cause the parameter selection module to select the wrong model parameters, thereby affecting the accuracy and reliability of the entire system.

[0027] Among them, the role of the exception handling module is to handle the exception in time when the system monitoring module detects an exception. The role of the user feedback module is to collect the user's feedback information and pass it to the system monitoring module. If the exception handling module does not respond to the exception in time, it may cause the system to fail or the wrong prediction result, thereby causing dissatisfaction and complaints from the user. Therefore, the working relationship between the exception handling module and the user feedback module is also very important. The exception handling module should respond to the exception in time and notify the user feedback module in time so that the user feedback module can collect the user's feedback information in time and pass it to the system monitoring module, so as to adjust the system parameters in time and improve the accuracy and reliability of the system.

[0028] Working principle: When the present invention is used, the data acquisition module first collects the working parameter data of the automobile spark plug and stores it in the database. Then, the data processing module performs operations such as denoising, deduplication, and processing missing values ​​on the collected data, and extracts useful features from it. Next, the model building module divides the processed data set into a training set, a validation set, and a test set, and selects a suitable machine learning algorithm or deep learning model for model training and optimization. The parameter prediction module uses the prediction model and the collected working parameter data of the automobile spark plug to predict the future working parameters of the spark plug, and sends a warning message to the owner when the prediction result reaches the warning threshold. The system interaction module is responsible for interacting with the user, including a user input module, a warning storage module, and a data warning module. At the same time, the cooperation of modules such as the training module, the model fusion module, the analyzable module, the system monitoring module, the exception handling module, and the user feedback module can improve the accuracy and reliability of the entire system. The system can help car owners to detect the aging of automobile spark plugs in time and ensure the safety and stability of the car.

[0029] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An automobile spark plug aging detection and early warning system based on data analysis, characterized in that: include: A data acquisition module for collecting working parameter data of automobile spark plugs, a data processing module for processing and analyzing the collected data, a model building module for establishing a prediction model based on the collected working parameter data of automobile spark plugs, a parameter prediction module for predicting the future working parameters of spark plugs using the collected working parameter data of automobile spark plugs and model prediction results, a system interaction module and a parsable module for interacting with users, the data acquisition module includes a sensor interface module for connecting and communicating with sensors on the car and acquiring data collected by the sensors, a data storage module for storing the collected data in a database for subsequent data processing and analysis, and a data transmission module for transmitting and processing the collected data, the data processing module includes a data cleaning module for denoising, deduplicating, and processing missing value operations on the collected data, a feature extraction module for extracting useful features from the cleaned data, and a feature extraction module for extracting useful features from the extracted data. The model building module includes a data analysis module for analyzing the features, the model building module includes a data set division module for dividing the processed data set into a training set, a validation set and a test set, a selection training module for selecting a suitable machine learning algorithm or deep learning model and performing model training and optimization on the training set, and a model evaluation module for evaluating the trained model on the validation set and the test set. The parameter prediction module includes a threshold setting module for setting a prediction result threshold, a prediction output module for presenting the results predicted by the model to the user in a visual and easy-to-understand manner, and a data warning module for sending warning information to the car owner when the prediction result reaches the warning threshold. The system interaction module includes a user input module for binding user personal information according to the information entered by the user into the system, a warning storage module for sending the warning information in the data warning module to the user while performing warning backup, and a data warning module for the data warning module to send warning information to the user The selection and training module includes a model selection module for selecting a suitable algorithm or model, a parameter selection module for selecting parameters for the selected algorithm or model, a model training module for training using preprocessed data and the selected model, a model fusion module for fusing and tuning multiple models, an interpretable analysis module for interpreting and analyzing the prediction results of the model, a system monitoring module for monitoring and managing the entire system, a user feedback module for collecting user feedback and suggestions, and an exception handling module for detecting and handling any abnormal situations during data processing and analysis; The sensor interface module transmits the collected data to the data storage module and stores the data for subsequent data processing and analysis. The data transmission module retrieves the data in the data storage module and distributes the data to other modules for processing. The data transmission module transmits the collected raw data to the data cleaning module and cleans and pre-processes the raw data. The feature extraction module extracts useful features from the cleaned data in the data cleaning module, and the data analysis module extracts these useful features from the original data according to the feature extraction module for model training and prediction. The data set division module receives the data analyzed in the data analysis module and divides it into a training set, a validation set and a test set. The selection training module needs to select a suitable model and algorithm according to the output of the data set division module, and perform training and optimization. The model evaluation module needs to evaluate the performance and generalization ability of the model according to the output of the selection training module, and judge the quality of the model according to the evaluation results. The threshold setting module can set the best threshold based on the comprehensive model evaluation module and the actual situation to better judge the prediction results of the model; The prediction output module can help users to timely understand the aging of automobile spark plugs according to the threshold setting module and the amount of actual working value. The warning storage module records the data of actual value exceeding the threshold value received from the data warning module and feeds back the warning information to the user through the output user module. The data warning module can help users to timely find abnormal conditions and perform warning processing according to the prediction output module to better ensure the safety and stability of the automobile. The output user module converts the prediction result of spark plug aging obtained by the data warning module through analysis and processing of automobile spark plug data into an easy-to-understand form and conveys it to the user. The user input module transmits the information bound by the user to the system so as to pass the warning information to the user for warning. The model selection module can select the optimal parameter combination in the machine learning model according to the different model evaluation indicators in the model selection module, and the model training module can train the machine learning model to establish a prediction model according to the parameter selection module. The model training module trains multiple different machine learning models and passes the prediction results of these models to the model fusion module for fusion to obtain the final prediction result. The analyzable module will analyze the results of the fusion of the prediction results of multiple models by the model fusion module to find out the reasons for the model prediction errors and put forward improvement suggestions. The parameter selection module analyzes the prediction results of the model based on the parseable module and proposes improvement suggestions and parameter adjustment suggestions to select more appropriate model parameters. The system monitoring module analyzes the prediction results of the model based on the parseable module and proposes improvement suggestions and system optimization suggestions to optimize and adjust the system. The function of the exception handling module is to handle the exception in time when the system monitoring module detects the exception. The system monitoring module feeds back the system data to the user feedback module in real time so as to provide feedback to the user.

Images