Sensor-based automobile exhaust networking analysis system

Abstract

The invention relates to the technical field of automobile exhaust pollution, in particular to a sensor-based automobile exhaust networking analysis system, which comprises a data acquisition module, a data processing and fusion module, an analysis and prediction module, an intelligent decision module, a data storage module and a user interaction module, the data processing and fusion module is used for processing the received pollutant component data, the data storage module is used for storing the pollutant component data, the analysis and prediction module is used for analyzing the pollutant component data in real time and predicting the tail gas emission trend, and the intelligent decision module is used for generating optimized vehicle operation parameters and providing maintenance suggestions. And the user interaction module provides a visual interaction interface and displays the tail gas emission data, the analysis result and the decision suggestion of the vehicle in real time. According to the automobile exhaust monitoring system, the technical problems existing in an existing automobile exhaust monitoring system are effectively solved, and the accuracy and reliability of data are remarkably improved.

Description

Technical Field

[0001] The invention relates to the technical field of automobile exhaust pollution, and in particular to a sensor-based automobile exhaust networking analysis system. Background Art

[0002] As global environmental problems become increasingly serious, reducing automobile exhaust emissions has become a focus of attention for governments and automakers. Automobile exhaust contains a variety of pollutants, such as oxygen, nitrogen oxides, hydrocarbons, particulate matter and carbon dioxide, which have caused serious harm to the atmospheric environment and human health. To this end, countries have introduced strict exhaust emission standards, requiring automakers to use advanced technologies and means to monitor and control exhaust emission levels in real time to reduce pollutant emissions. Modern cars are equipped with a variety of sensors to collect pollutant composition data in the exhaust system, and process and analyze data through on-board computers to optimize engine operating parameters and reduce pollutant emissions. However, traditional automobile exhaust monitoring systems still face many challenges in data collection, processing and analysis, and are in urgent need of further improvement and enhancement.

[0003] The existing automobile exhaust monitoring system has the following main technical problems: First, the data collection accuracy is insufficient. Although modern cars are equipped with a variety of sensors, the accuracy and reliability of the sensors are often limited by environmental factors and the performance of the sensors themselves, resulting in noise and errors in the collected data, affecting the accuracy of subsequent analysis and prediction. Secondly, the data processing and fusion capabilities are limited. Traditional data processing methods are difficult to effectively clean, filter and fuse multi-source data, resulting in insufficient data integrity and consistency, which affects the reliability of the analysis results. In addition, the existing system lacks effective real-time optimization and maintenance recommendation functions, making it difficult to dynamically adjust vehicle operating parameters based on real-time data and optimize exhaust emission levels. At the same time, there is a lack of timely diagnosis and maintenance recommendations for vehicle faults, which cannot guarantee the normal operation of the vehicle and environmental protection. Summary of the invention

[0004] Based on the above purpose, the present invention provides a sensor-based automobile exhaust network analysis system.

[0005] The sensor-based automobile exhaust network analysis system includes a data acquisition module, a data processing and fusion module, an analysis and prediction module, an intelligent decision-making module, a data storage module and a user interaction module, among which;

[0006] The data acquisition module includes a plurality of sensors for collecting pollutant component data in automobile exhaust in real time;

[0007] The data processing and fusion module includes a data preprocessing unit and a multi-source data fusion unit. The data preprocessing unit is used to clean, filter and format the received pollutant composition data. The multi-source data fusion unit is used to fuse the data from different sensors to improve the integrity and reliability of the data.

[0008] The data storage module is used to store processed and fused pollutant composition data, supports data encryption and authority control, and ensures data security;

[0009] The analysis and prediction module uses machine learning algorithms to perform real-time analysis of pollutant composition data and predict tail gas emission trends;

[0010] The intelligent decision-making module generates decision suggestions based on the results of the analysis and prediction module, including optimizing vehicle operating parameters and providing maintenance suggestions;

[0011] The user interaction module provides a visual interactive interface to display vehicle exhaust emission data, analysis results and decision suggestions in real time.

[0012] Optionally, the plurality of sensors include an oxygen sensor, a nitrogen oxide sensor, a hydrocarbon sensor, a particulate matter sensor and a carbon dioxide sensor, wherein;

[0013] The oxygen sensor is used to detect the concentration of oxygen in the exhaust gas;

[0014] The nitrogen oxide sensor is used to detect the nitrogen oxide content in the exhaust gas;

[0015] The hydrocarbon sensor is used to detect the hydrocarbon content in the exhaust gas;

[0016] The particle sensor is used to detect the particle content in the exhaust gas;

[0017] The carbon dioxide sensor is used to detect the carbon dioxide content in the exhaust gas.

[0018] Optionally, the data preprocessing unit specifically includes:

[0019] Data cleaning: Detect missing values ​​in the received pollutant composition data, fill them using the mean filling method, and delete outliers in the data;

[0020] Data filtering: Use moving average filtering to filter noise from data;

[0021] Data formatting: Converting data from different sensors into a unified format.

[0022] Optionally, the multi-source data fusion unit specifically includes:

[0023] Standardization processing: standardize the data of multiple sensors to make them have the same dimension and range;

[0024] Data fusion: Use the Kalman filter algorithm to fuse the standardized multi-source data.

[0025] Optionally, the data storage module specifically includes:

[0026] Distributed database technology: The data storage module uses a distributed database to store and manage the processed and analyzed pollutant composition data in a distributed manner;

[0027] Data encryption: Static encryption of data stored in the database to protect the security of data on the storage medium. During data transmission, data is dynamically encrypted.

[0028] Permission control: Define different user roles and permission levels, such as administrator, data analyst, ordinary user, etc., and assign corresponding access rights and operation permissions based on user roles.

[0029] Optionally, the analysis and prediction module specifically includes:

[0030] Data extraction: Extracting historical pollutant composition data stored in distributed databases, including oxygen, nitrogen oxides, hydrocarbons, particulate matter, and carbon dioxide concentrations;

[0031] Feature extraction: Extract time features, such as hours, days, months, quarters, etc., to capture the periodicity and trend in the time series, and the concentration characteristics of different pollutants;

[0032] Data splitting: Divide the data into training set, validation set and test set;

[0033] Model selection and training: Use the long short-term memory network algorithm to build a model, use the training set to train the model, and verify it on the validation set;

[0034] Model prediction and evaluation: Use the trained model to predict the test set data, output the exhaust emission trend for a period of time in the future, and use the mean square error, root mean square error and determination coefficient to evaluate the prediction performance of the model.

[0035] Optionally, the optimizing vehicle operating parameters includes:

[0036] Acquisition of analysis and prediction results: Acquisition of exhaust emission trends and related data output by the analysis and prediction module, including changes in pollutant concentrations;

[0037] Determine optimization goals: According to the exhaust emission trend and pollutant concentration changes, determine the optimization goals, such as reducing the emission of specific pollutants (such as NOx, CO2), improving fuel efficiency, etc.;

[0038] Operation parameter adjustment strategy: According to the optimization target, formulate the adjustment strategy of vehicle operation parameters, including engine speed, fuel injection amount and ignition time, and realize parameter adjustment through control algorithm;

[0039] Real-time optimization: Real-time monitoring of vehicle operating status and emission data, and continuous adjustment of operating parameters based on control algorithms.

[0040] Optionally, providing maintenance suggestions includes:

[0041] Data acquisition: obtain exhaust emission trends and related data output by the analysis and prediction module;

[0042] Fault diagnosis: Based on the analysis and prediction results, fault diagnosis and maintenance recommendations are made using predefined rule sets;

[0043] Generate maintenance suggestions: Generate maintenance suggestions based on fault diagnosis results, such as replacing air filters, cleaning fuel injection systems, checking and repairing exhaust systems, etc.;

[0044] Maintenance suggestion notification: Maintenance suggestions are notified to the vehicle owner or maintenance personnel through the user interaction module.

[0045] Optionally, the user interaction module includes:

[0046] Real-time data display: Real-time display of pollutant composition data in exhaust gas, using line charts, bar charts or dashboards to show real-time concentration changes of pollutants;

[0047] Analysis result display: Based on the results of the analysis and prediction module, the exhaust emission trend forecast is displayed, such as the pollutant concentration change trend in the future;

[0048] Decision suggestion display: Based on the results of the intelligent decision-making module, it displays optimization suggestions for vehicle operating parameters, such as adjusting engine speed, fuel injection amount, ignition timing, etc. Based on the fault diagnosis results, it displays maintenance suggestions, such as replacing the air filter, cleaning the fuel injection system, checking the exhaust system, etc.;

[0049] Notifications and reminders: Send notifications and reminders to vehicle owners or maintenance personnel based on real-time data and decision-making recommendations, such as regular maintenance reminders, abnormal situation reminders, etc.

[0050] Beneficial effects of the present invention:

[0051] The present invention realizes high-precision collection and processing of pollutant component data in automobile exhaust through the coordinated work of the data acquisition module, the data processing and fusion module, and the analysis and prediction module. Specifically, the data processing and fusion module eliminates noise and outliers in the data through data cleaning, filtering and formatting, ensuring the accuracy and consistency of the data. At the same time, the multi-source data fusion unit adopts the Kalman filter algorithm to fuse the data of different sensors, thereby improving the integrity and reliability of the data. In this way, the analysis and prediction module can perform real-time analysis and prediction based on high-quality data, and provide accurate exhaust emission trend prediction results.

[0052] In the present invention, the intelligent decision module generates specific strategies for optimizing vehicle operating parameters and providing maintenance suggestions based on the results of the analysis and prediction modules. By real-time monitoring of the vehicle's operating status and emission data, the control algorithm is used to continuously adjust key parameters such as engine speed, fuel injection amount, and ignition time to minimize pollutant emissions and maximize fuel efficiency. At the same time, the intelligent decision module diagnoses possible faults of the vehicle, generates maintenance suggestions, and notifies the owner or maintenance personnel through the user interaction module to ensure the normal operation and timely maintenance of the vehicle.

[0053] In the present invention, the data storage module adopts distributed database technology to achieve efficient storage, management and rapid access to large-scale data. The efficiency and response speed of the system when processing large amounts of data are guaranteed. At the same time, the data storage module supports data encryption and authority control, and uses the AES algorithm to encrypt static data to ensure the security of data during storage and transmission. In addition, the user interaction module provides an intuitive visual interface to display the vehicle's exhaust emission data, analysis results and decision-making suggestions in real time. Users can easily understand and manage the vehicle's operating status, thereby improving the system's practicality and user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A schematic diagram of a system flow of an embodiment of the present invention;

[0056] Figure 2 The figure is a flow chart of the data processing and fusion module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0058] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0059] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0060] like Figure 1-Figure 2 As shown, the sensor-based automobile exhaust network analysis system includes a data acquisition module, a data processing and fusion module, an analysis and prediction module, an intelligent decision-making module, a data storage module and a user interaction module, wherein;

[0061] The data acquisition module includes multiple sensors for collecting real-time data on pollutant components in automobile exhaust;

[0062] The data processing and fusion module includes a data preprocessing unit and a multi-source data fusion unit. The data preprocessing unit is used to clean, filter and format the received pollutant composition data, and the multi-source data fusion unit is used to fuse the data from different sensors to improve the integrity and reliability of the data.

[0063] The data storage module is used to store processed and integrated pollutant composition data, supporting data encryption and permission control to ensure data security;

[0064] The analysis and prediction module uses machine learning algorithms to conduct real-time analysis of pollutant composition data and predict exhaust emission trends;

[0065] The intelligent decision-making module generates decision suggestions based on the results of the analysis and prediction modules, including optimizing vehicle operating parameters and providing maintenance suggestions;

[0066] The user interaction module provides a visual interactive interface to display the vehicle's exhaust emission data, analysis results and decision-making recommendations in real time.

[0067] The plurality of sensors include an oxygen sensor, a nitrogen oxide sensor, a hydrocarbon sensor, a particulate matter sensor, and a carbon dioxide sensor, wherein;

[0068] The oxygen sensor is used to detect the concentration of oxygen in the exhaust gas;

[0069] The nitrogen oxide sensor is used to detect the nitrogen oxide content in the exhaust gas;

[0070] The hydrocarbon sensor is used to detect the hydrocarbon content in the exhaust gas;

[0071] The particle sensor is used to detect the particle content in the exhaust gas;

[0072] The carbon dioxide sensor is used to detect the carbon dioxide content in the exhaust gas;

[0073] Multiple sensors are installed near the vehicle exhaust pipe to ensure that the sensors can directly contact and sense the exhaust gas. The data acquisition module can collect pollutant composition data in automobile exhaust in real time and accurately, and provide a reliable data basis for subsequent data processing, analysis and decision-making.

[0074] The data preprocessing unit specifically includes:

[0075] Data cleaning: Detect missing values ​​in the received pollutant composition data, fill them using the mean filling method, and delete outliers in the data;

[0076] Mean imputation is calculated as:

[0077] Among them, x 填补 is the value after filling, n is the total number of samples, x i is the i-th sample value;

[0078] The Z-Score statistical method is used to detect outliers in the data, calculated as:

[0079] Among them, Z is the Z-Score, x is the sample value, μ is the sample mean, σ is the sample standard deviation, and if |Z|>3, it is considered an outlier;

[0080] Data filtering: Use moving average filtering to filter the data for noise, expressed as:

[0081]

[0082] Among them, y t is the smoothed data, x t-i is the original data at the ti-th moment, k is the filter window size;

[0083] Data formatting: converting data from different sensors into a unified format for subsequent processing and analysis;

[0084] Convert ppm to mg / m according to the sensor data unit and standard unit 3 , expressed as:

[0085] Among them, 24.45 is a constant used for unit conversion at standard temperature and pressure;

[0086] The linear interpolation method is used to unify the timestamp. The linear interpolation method generates a new data point by linear interpolation between known data points to ensure that all sensor data have a unified timestamp, which is helpful for the synchronization and fusion of multi-source data and ensures the consistency and accuracy of subsequent data processing and analysis. The linear interpolation method is calculated as:

[0087]

[0088] Among them, y(t) is the interpolated data, y(t1) and y(t2) are the data at time points t1 and t2 respectively;

[0089] The data preprocessing unit can effectively clean, filter and format the received pollutant composition data to ensure the accuracy, completeness and consistency of the data, and provide a high-quality data foundation for subsequent data fusion and analysis.

[0090] The multi-source data fusion unit specifically includes:

[0091] Standardization processing: standardize the data of multiple sensors to make them have the same dimension and range;

[0092] The normalization formula is: Among them, x is the sample value, the measurement value from the sensor, μ is the sample mean, σ is the sample standard deviation, and x' is the standardized data value;

[0093] Data fusion: Use the Kalman filter algorithm to fuse the standardized multi-source data, combine the measurement results of each sensor and the prior estimation, and obtain the optimal state estimation. The Kalman filter fusion steps are as follows:

[0094] (1) State prediction: Use the state transition equation to predict the state and error covariance at the next moment, expressed as:

[0095]

[0096] P k|k-1 =AP k-1|k-1 A T +Q;

[0097] (2) Update step: Update the state estimate and error covariance according to the current measurement value, expressed as:

[0098] K k =P k|k-1 H T (HP k|k-1 H T +R) -1 ;

[0099]

[0100] P k|k =(IK k H)P k|k-1 ;

[0101] in, is the predicted state vector, is the updated state vector, P k|k-1 and P k|k are the covariance matrices of prediction and update, respectively, K k is the Kalman gain, z k is the measured value, A is the state transfer matrix, B is the control input matrix, u k is the control input vector, H is the measurement matrix, Q and R are the process and measurement noise covariance matrices, respectively, and I is the identity matrix;

[0102] Kalman filter fusion can effectively process dynamic data from multiple sensors and improve the accuracy and reliability of data.

[0103] The data storage module specifically includes:

[0104] Distributed database technology: The data storage module uses a distributed database (such as Apache Cassandra, Hadoop HDFS or MongoDB) to distribute and manage the processed and analyzed pollutant composition data;

[0105] Distributed databases store data in pieces on multiple nodes, increasing storage capacity and access speed while also having high availability and fault tolerance.

[0106] Use the index mechanism of distributed database to improve the speed of data query and access;

[0107] The query optimizer of the distributed database selects the optimal query path and execution plan based on the data distribution and query mode to improve query performance;

[0108] Data encryption: Static encryption of data stored in the database to protect the security of data on the storage medium;

[0109] Use Advanced Encryption Standard (AES) for data encryption to ensure the confidentiality of pollutant composition data;

[0110] The data encryption process includes:

[0111] (1) Generate key: Generate data encryption key using encryption algorithm;

[0112] (2) Data encryption: Use the generated key to encrypt the pollutant composition data;

[0113] (3) Storing encrypted data: storing the encrypted pollutant composition data in a database;

[0114] During data transmission, data is dynamically encrypted to prevent data leakage during network transmission. Transport layer security protocol (TLS / SSL) is used to encrypt data transmission to ensure the security of data during network transmission.

[0115] Permission control: define different user roles and permission levels, such as administrator, data analyst, ordinary user, etc. Each role has different permissions and can access and operate different data and functions. According to the user role, the corresponding access rights and operation rights are assigned. The permissions include reading, writing, deleting, modifying and other operations of data, ensuring that different roles can only perform operations within the authorized scope.

[0116] The analysis and prediction module specifically includes:

[0117] Data extraction: Extracting historical pollutant composition data stored in distributed databases, including oxygen, nitrogen oxides, hydrocarbons, particulate matter, and carbon dioxide concentrations;

[0118] Feature extraction: Extract time features, such as hours, days, months, quarters, etc., to capture the periodicity and trend in the time series, and the concentration characteristics of different pollutants;

[0119] Data splitting: Divide the data into training set, validation set and test set;

[0120] Model selection and training: Use the long short-term memory network algorithm to build a model, use the training set to train the model, and verify it on the validation set. The specific steps are as follows:

[0121] (1) Establishment of long short-term memory network model:

[0122] Input layer: sets the shape of the input data (time steps, number of features);

[0123] LSTM layer: Add one or more long short-term memory network layers to capture long-term and short-term dependencies in time series;

[0124] Output layer: Add a fully connected layer to map the output of the long short-term memory network layer to the predicted value;

[0125] (2) Hyperparameter setting:

[0126] Time step: Select an appropriate time step (such as 5, 10, 20) to indicate the length of the time series input each time;

[0127] Number of hidden units: the number of hidden units in the LSTM network layer (e.g. 50, 100);

[0128] Learning rate: the learning rate of the optimizer (such as 0.001);

[0129] Batch size: the number of samples for each training (e.g. 32, 64);

[0130] (3) Model training:

[0131] Use the training set to train the model and validate it on the validation set to prevent overfitting;

[0132] The training process consists of multiple iterations, each of which adjusts the model parameters to minimize the prediction error;

[0133] Model prediction and evaluation: Use the trained model to predict the test set data, output the exhaust emission trend for a period of time in the future, and use the mean square error, root mean square error and determination coefficient to evaluate the prediction performance of the model;

[0134] The mean square error is calculated as:

[0135] Where n is the total number of samples, y i is the actual value of the ith sample, is the predicted value of the i-th sample;

[0136] The root mean square error is calculated as:

[0137] Where n is the total number of samples, y i is the actual value of the ith sample, is the predicted value of the i-th sample;

[0138] The coefficient of determination was calculated as:

[0139] Where n is the total number of samples, y i is the actual value of the ith sample, is the predicted value of the ith sample, is the average of the actual values, calculated as

[0140] The analysis and prediction module can perform real-time analysis on the processed data based on the long short-term memory network algorithm, predict exhaust emission trends, and improve the decision-making support capabilities of the system.

[0141] Optimizing vehicle operating parameters includes:

[0142] Acquisition of analysis and prediction results: Acquisition of exhaust emission trends and related data output by the analysis and prediction module, including changes in pollutant concentrations;

[0143] Determine optimization goals: According to the exhaust emission trend and pollutant concentration changes, determine the optimization goals, such as reducing the emission of specific pollutants (such as NOx, CO2), improving fuel efficiency, etc.;

[0144] Operation parameter adjustment strategy: According to the optimization target, formulate the adjustment strategy of vehicle operation parameters, including engine speed, fuel injection amount and ignition time, and realize parameter adjustment through control algorithm;

[0145] The PID control algorithm is used to achieve parameter adjustment, and the calculation is:

[0146]

[0147] Among them, u(t) is the control output, e(t) is the error (the difference between the actual value and the target value), K p ,K i , K d are proportional, integral and differential coefficients respectively;

[0148] Real-time optimization: Real-time monitoring of vehicle operating status and emission data, and continuous adjustment of operating parameters based on control algorithms.

[0149] Maintenance recommendations include:

[0150] Data acquisition: obtain exhaust emission trends and related data output by the analysis and prediction module;

[0151] Fault diagnosis: Based on the analysis and prediction results, fault diagnosis and maintenance recommendations are made using predefined rule sets;

[0152] Example ruleset:

[0153] If the analysis and prediction module shows that the oxygen concentration in the exhaust gas is abnormal, and the oxygen sensor signal fluctuates frequently or remains unchanged for a long time, it is recommended to check and replace the oxygen sensor;

[0154] If the prediction results show that the fuel efficiency is significantly reduced and the fuel injection amount is unstable, it is recommended to clean or replace the fuel injector;

[0155] Generate maintenance suggestions: Generate maintenance suggestions based on fault diagnosis results, such as replacing air filters, cleaning fuel injection systems, checking and repairing exhaust systems, etc.;

[0156] Maintenance suggestion notification: through the user interaction module, the maintenance suggestion is notified to the owner or maintenance personnel;

[0157] The intelligent decision-making module generates specific strategies for optimizing vehicle operating parameters and maintenance recommendations by analyzing the results of the prediction module. By adjusting operating parameters in real time and performing maintenance in a timely manner, it can effectively reduce pollutant emissions and improve vehicle operating efficiency and reliability.

[0158] The user interaction module includes:

[0159] Real-time data display: Real-time display of pollutant composition data in exhaust gas, using line charts, bar charts or dashboards to show real-time concentration changes of pollutants;

[0160] Analysis result display: Based on the results of the analysis and prediction module, the tail gas emission trend forecast is displayed, such as the pollutant concentration change trend in the future, and the predicted trend of different pollutants is displayed in the form of line charts, trend charts, etc.;

[0161] Decision suggestion display: Based on the results of the intelligent decision-making module, it displays optimization suggestions for vehicle operating parameters, such as adjusting engine speed, fuel injection amount, ignition timing, etc. Based on the fault diagnosis results, it displays maintenance suggestions, such as replacing the air filter, cleaning the fuel injection system, checking the exhaust system, etc.;

[0162] Notifications and reminders: Send notifications and reminders to vehicle owners or maintenance personnel based on real-time data and decision-making suggestions, such as regular maintenance reminders, abnormal situation reminders, etc.

[0163] The user interaction module provides an intuitive visual interactive interface through which users can understand the operating status of the system and take corresponding maintenance measures based on the system's recommendations, effectively reducing pollutant emissions and improving vehicle operating efficiency and reliability.

[0164] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0165] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A sensor-based automobile exhaust network analysis system, characterized in that: It includes data acquisition module, data processing and fusion module, data storage module, analysis and prediction module, intelligent decision-making module and user interaction module, among which; The data acquisition module includes a plurality of sensors for collecting pollutant component data in automobile exhaust in real time; The data processing and fusion module includes a data preprocessing unit and a multi-source data fusion unit. The data preprocessing unit is used to clean, filter and format the received pollutant composition data, and the multi-source data fusion unit is used to fuse the data from different sensors. The data storage module is used to store processed and fused pollutant composition data, and supports data encryption and authority control; The analysis and prediction module uses machine learning algorithms to perform real-time analysis of pollutant composition data and predict tail gas emission trends; The intelligent decision-making module generates decision suggestions based on the results of the analysis and prediction module, including optimizing vehicle operating parameters and providing maintenance suggestions; The user interaction module provides a visual interactive interface to display vehicle exhaust emission data, analysis results and decision suggestions in real time.

2. The sensor-based automobile exhaust network analysis system according to claim 1 is characterized in that: The plurality of sensors include an oxygen sensor, a nitrogen oxide sensor, a hydrocarbon sensor, a particulate matter sensor, and a carbon dioxide sensor, wherein; The oxygen sensor is used to detect the concentration of oxygen in the exhaust gas; The nitrogen oxide sensor is used to detect the nitrogen oxide content in the exhaust gas; The hydrocarbon sensor is used to detect the hydrocarbon content in the exhaust gas; The particle sensor is used to detect the particle content in the exhaust gas; The carbon dioxide sensor is used to detect the carbon dioxide content in the exhaust gas.

3. The sensor-based automobile exhaust network analysis system according to claim 1 is characterized in that: The data preprocessing unit specifically includes: Data cleaning: Detect missing values ​​in the received pollutant composition data, fill them using the mean filling method, and delete outliers in the data; Data filtering: Use moving average filtering to filter noise from data; Data formatting: Converting data from different sensors into a unified format.

4. The sensor-based automobile exhaust network analysis system according to claim 1 is characterized in that: The multi-source data fusion unit specifically includes: Standardization processing: standardize the data of multiple sensors to make them have the same dimension and range; Data fusion: Use the Kalman filter algorithm to fuse the standardized multi-source data.

5. The sensor-based automobile exhaust network analysis system according to claim 1 is characterized in that: The data storage module specifically includes: Distributed database technology: The data storage module uses a distributed database to store and manage the processed and analyzed pollutant composition data in a distributed manner; Data encryption: Static encryption of data stored in the database to protect the security of data on the storage medium. During data transmission, data is dynamically encrypted. Permission control: define different user roles and permission levels, and assign corresponding access rights and operation permissions based on user roles.

6. The sensor-based automobile exhaust network analysis system according to claim 5 is characterized in that: The analysis and prediction module specifically includes: Data extraction: Extracting historical pollutant composition data stored in distributed databases, including oxygen, nitrogen oxides, hydrocarbons, particulate matter, and carbon dioxide concentrations; Feature extraction: extract time features and concentration features of different pollutants; Data splitting: Divide the data into training set, validation set and test set; Model selection and training: Use the long short-term memory network algorithm to build a model, use the training set to train the model, and verify it on the validation set; Model prediction and evaluation: Use the trained model to predict the test set data, output the exhaust emission trend for a period of time in the future, and use the mean square error, root mean square error and determination coefficient to evaluate the prediction performance of the model.

7. The sensor-based automobile exhaust network analysis system according to claim 6 is characterized in that: The optimized vehicle operating parameters include: Acquisition of analysis and prediction results: Acquisition of exhaust emission trends and related data output by the analysis and prediction module, including changes in pollutant concentrations; Determine the optimization target: Determine the optimization target based on the exhaust emission trend and pollutant concentration changes; Operation parameter adjustment strategy: According to the optimization target, formulate the adjustment strategy of vehicle operation parameters, including engine speed, fuel injection amount and ignition time, and realize parameter adjustment through control algorithm; Real-time optimization: Real-time monitoring of vehicle operating status and emission data, and continuous adjustment of operating parameters based on control algorithms.

8. The sensor-based automobile exhaust network analysis system according to claim 7 is characterized in that: The maintenance recommendations provided include: Data acquisition: obtain exhaust emission trends and related data output by the analysis and prediction module; Fault diagnosis: Based on the analysis and prediction results, fault diagnosis and maintenance recommendations are made using predefined rule sets; Generate maintenance suggestions: Generate maintenance suggestions based on fault diagnosis results; Maintenance suggestion notification: Maintenance suggestions are notified to the vehicle owner or maintenance personnel through the user interaction module.

9. The sensor-based automobile exhaust network analysis system according to claim 8, characterized in that: The user interaction module comprises: Real-time data display: Real-time display of pollutant composition data in exhaust gas, using line charts, bar charts or dashboards to show real-time concentration changes of pollutants; Analysis result display: Based on the results of the analysis and prediction modules, the exhaust emission trend forecast is displayed; Decision suggestion display: Based on the results of the intelligent decision-making module, it displays optimization suggestions for vehicle operating parameters, and based on the fault diagnosis results, it displays maintenance suggestions; Notifications and reminders: Send notifications and reminders to vehicle owners or maintenance personnel based on real-time data and decision suggestions.

Images