CN112819217A - Method, system and storage medium for predicting main influence factors of mobile source pollution emission - Google Patents
Method, system and storage medium for predicting main influence factors of mobile source pollution emission Download PDFInfo
- Publication number
- CN112819217A CN112819217A CN202110110644.6A CN202110110644A CN112819217A CN 112819217 A CN112819217 A CN 112819217A CN 202110110644 A CN202110110644 A CN 202110110644A CN 112819217 A CN112819217 A CN 112819217A
- Authority
- CN
- China
- Prior art keywords
- data
- factors
- tail gas
- vehicle
- emission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000007689 inspection Methods 0.000 claims abstract description 23
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 8
- 231100000719 pollutant Toxicity 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012352 Spearman correlation analysis Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000001133 acceleration Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000010219 correlation analysis Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 239000000779 smoke Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000003197 catalytic effect Effects 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 239000000356 contaminant Substances 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 239000000446 fuel Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000003062 neural network model Methods 0.000 abstract description 4
- 239000007789 gas Substances 0.000 description 39
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000007637 random forest analysis Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention discloses a method, a system and a storage medium for predicting main influence factors of mobile source pollution emission, which take a motor vehicle as a research object and comprise the following steps: firstly, preprocessing collected annual inspection data and tail gas telemetering data of a vehicle; then, factors which do not have correlation with the concentrations of main components CO, HC and NO in the emission gas of the mobile source are eliminated by utilizing Spearman correlation analysis; determining key influence factors of all components by using a Lasso algorithm, and constructing a pollutant emission prediction model by using a neural network; finally, the effectiveness of the model for predicting the main components of the mobile source pollutant emission is verified on a test set. The model prediction result shows that the characteristic screening-based mobile source pollution emission data prediction neural network model has higher prediction precision, can reduce the mobile source pollution emission detection cost and provides a theoretical basis for relevant departments to make relevant policies.
Description
Technical Field
The invention relates to the technical field of environmental monitoring, in particular to a method and a system for predicting main influence factors of mobile source pollution emission and a storage medium.
Background
With the development of economy in China, the number of urban motor vehicles, airplanes and ships is increased continuously, and harmful gases emitted by the mobile sources cause damage to the health of people while the happiness of the whole people is improved. Therefore, a set of scientific and perfect analysis and prediction method is necessary to be established for the emission of harmful gases in the tail gas of the mobile source, so that relevant departments can efficiently control the emission of the tail gas of the mobile source.
In the actual exhaust detection work of the mobile source, the driving speed and the acceleration of the mobile source, the wind power and the wind direction of a measuring point, the ambient temperature, the humidity, the air pressure, the sunlight angle and the like have more or less influence on the measuring result, but the existing pollutant concentration prediction method only starts from pollutants, does not consider that the detection of the pollution emission of the mobile source is influenced by external factors, causes inaccurate and reliable estimation of the pollution emission of the mobile source, and causes difficulty in the targeted control of each component of the pollution emission of the mobile source for relevant departments.
Disclosure of Invention
The invention provides a method, a system and a storage medium for predicting main influence factors of mobile source pollution emission, and provides a method for predicting the main influence factors of the mobile source pollution emission based on feature selection and a neural network.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for predicting main influence factors of mobile source pollutant emission comprises the following steps:
(1) collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of an urban target road section;
(2) preprocessing the collected data;
(3) performing correlation analysis on main components in exhaust emission, namely CO, HC and NO, and external influence factors by using a Spearman coefficient on the preprocessed data;
(4) screening out main factors influencing respective emission concentrations of CO, HC and NO in the tail gas from the factors which are obtained in the step (3) and have correlation with each component in the tail gas emission by using a Lasso algorithm;
(5) and (4) according to the main factors influencing the emission concentration of each main component obtained in the step (4), establishing prediction models for CO, HC and NO respectively by adopting a BP neural network, and carrying out comparison and inspection on other prediction models.
Further, in the step (1), the process of extracting the motor vehicle exhaust telemetry data is as follows:
(11) data collected from the telemetry system includes: the device number is used for detecting vehicle passing time, license plate number, vehicle color, recognition confidence, vehicle running speed, acceleration, vehicle body length, CO measured concentration, HC measured concentration, NO measured concentration, smoke value, dynamic/static measurement, effective data, passing data, specific power, smoke value, wind speed, wind direction, air temperature, humidity and atmospheric pressure;
(12) the data obtained from the vehicle inspection includes: the number plate number, the maximum quality, the form of a transmission, the number of gears, the fuel specification, the type of a vehicle, the use property, the reference quality, the driving mode, the driving tire air pressure, the type of an engine, an engine manufacturer, the engine discharge capacity, whether a catalytic converter exists or not and an exhaust aftertreatment device.
Further, in the step (2), the motor vehicle exhaust telemetering data and the vehicle inspection data are preprocessed as follows: combining different characteristic attributes of the telemetering data and the vehicle inspection data records into a tail gas data record with more comprehensive information through the license plate number; and then, finding out missing values in the data segments for discarding, finding out abnormal values by using the boxcar graph for discarding, and deleting irrelevant attributes such as equipment numbers, detected vehicle passing time, license plate numbers, vehicle colors, recognition confidence degrees and the like. After the invalid attribute is deleted, 11 attributes of the residual reference mass, the running speed, the running acceleration, the specific power, the wind speed, the wind direction, the air temperature, the humidity, the atmospheric pressure, the vehicle body length and the service life are relevant external attributes researched by the invention.
Further, in the step (3), Spearman correlation analysis is performed among 11 external influence factors of each exhaust gas component, reference mass, running speed, running acceleration, specific power, wind speed, wind direction, air temperature, humidity, atmospheric pressure, vehicle body length and service life as follows:
(31) the formula for calculating the Spearman coefficient p of the tail gas components and influencing factors is as follows:
wherein x isiFor the ith sample value of the influencing factor,
is the mean value of the property, yiFor the ith sample value of the contaminant,
is the mean value thereof.
(32) The corresponding statistic p is then calculated using the Spearman coefficient p, the formula:
where n is the number of samples and p is the statistics of the influencing factors and emissions.
(33) The coefficient p is compared with t being 1.645(α being 0.05), and a value smaller than t indicates that there is no correlation between the corresponding attribute and the exhaust gas component.
Further, in the step (4), the step of screening the main factors by using the Lasso algorithm comprises the following steps:
(41) calculating coefficients related to the components of the exhaust gas by using the Lasso algorithm
The formula is as follows:
wherein lambda is a non-negative regularization parameter, y is a tail gas concentration value, and xjIs the value corresponding to the j-th attribute, betajIs a regression coefficient, and p is the number of attributes.
(42) And (4) screening out the attribute with the coefficient of 0 corresponding to the tail gas component, and deleting the attribute with the coefficient of 0 corresponding to the tail gas and the variable without correlation in the step (3).
Further, in the step (5), the model establishing and comparing steps are as follows:
(51) and (3) constructing a tail gas main component concentration prediction model, namely performing zero-mean normalization on the main factors of the components obtained in the step (4), taking the main factors as the input of a neural network, establishing a three-layer BP neural network, and performing data analysis according to the following steps of 8:1: the 1 is divided into a training set, a verification set and a test set, wherein the training set and the verification set are used for training the network, and the test set is used for measuring the prediction effect of the model.
On the other hand, the invention also discloses a system for predicting main influence factors of the mobile source pollution emission, which comprises the following units,
the data collection unit is used for collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of the urban target road section;
the data processing unit is used for preprocessing the collected data;
the correlation analysis unit is used for carrying out correlation analysis on the pre-processed data on specified components, namely CO, HC and NO, in exhaust emission and external influence factors by adopting a Spearman coefficient;
the factor screening unit is used for screening factors which influence the respective emission concentrations of the tail gas CO, HC and NO for the obtained factors which have correlation with the components in the tail gas emission by using a Lasso algorithm;
and the prediction unit is used for respectively establishing prediction models for CO, HC and NO by adopting a BP neural network according to the obtained specific factors influencing the emission concentration of each specific component and carrying out comparison and inspection with other prediction models.
The comparison with other prediction models operates as follows: the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the model provided by the invention are compared with a support vector regression prediction model (SVR) and a random forest prediction model (RandomForest) of the screened variables and a neural network prediction model (ANN) for screening related variables.
Compared with the prior art, the method has the advantages that: in the traditional tail gas prediction, the influence of data monitoring is not considered, and the prediction precision is low. According to the invention, each tail gas component is subjected to Spearman correlation analysis and Lasso characteristic screening to find out respective influence factors, so that a neural network model is established for prediction, and the stability and accuracy of the prediction result of the invention are better.
Compared with other methods, the method comprehensively considers the influence of external factors on detection, screens out main influence factors on different tail gas components, and then carries out prediction by modeling respectively, thereby effectively improving the prediction precision and providing a powerful scientific and technical basis for relevant departments to make relevant policies.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a Spearman coefficient for each exhaust gas component and influencing factor;
FIG. 3 is a chart of the Spearman coefficient based statistics of various exhaust gas constituents and influencing factors;
FIG. 4 is a three-layer BP neural network model;
FIG. 5 is a comparison of CO prediction models;
FIG. 6 is a comparison of HC prediction models;
FIG. 7 is a comparison of NO prediction models.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
As shown in fig. 1, the method for predicting the main influence factors of the mobile source pollutant emission described in this embodiment is specifically implemented as follows:
(1) collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of an urban target road section;
(11) data collected from the telemetry system includes: the device number is used for detecting vehicle passing time, license plate number, vehicle color, recognition confidence, vehicle running speed, acceleration, vehicle body length, CO measured concentration, HC measured concentration, NO measured concentration, smoke value, dynamic/static measurement, effective data, passing data, specific power, smoke value, wind speed, wind direction, air temperature, humidity and atmospheric pressure;
(12) the data obtained from the vehicle inspection includes: the number plate number, the maximum quality transmission form, the gear number, the fuel specification, the vehicle type, the use property, the reference quality, the driving mode, the driving tire pressure, the engine model, the engine manufacturing enterprise, the engine discharge capacity, whether a catalytic converter exists or not and an exhaust aftertreatment device.
(2) And preprocessing the collected data, which mainly comprises the fusion of tail gas remote measurement data and vehicle inspection data, tail gas data cleaning and abnormal value processing.
(21) Data fusion: combining different characteristic attributes of remote sensing monitoring tail gas data records with the same license plate number and vehicle annual inspection data records to form a tail gas data record with more comprehensive information;
(22) cleaning tail gas data: deleting invalid (the automobile public ratio is more than 20kW/t) tail gas data records, and deleting irrelevant attribute fields such as equipment numbers, detected vehicle passing time, license plate numbers, vehicle colors, recognition confidence and the like.
(23) Abnormal value processing: and judging whether the data is abnormal or not by using the box line graph, and discarding the abnormal value. The concrete implementation is as follows:
[1] respectively calculating the upper quartile (Q3) and the median (Q2) of the lower quartile (Q1) of each attribute;
[2] calculating the quartering distance IQR (Q3-Q1);
[3] and calculating the maximum value max which is Q3+1.5IQR, the minimum value min which is Q1-1.5IQR, and the value which is greater than max or less than min is the abnormal value of the attribute sample.
(3) Spearman correlation analysis of exhaust emission composition and influencing factors.
Based on step 2, the remaining factors relevant to the detection of motor vehicle exhaust: driving conditions (speed, acceleration), service life of the vehicle, wind speed, air temperature, reference mass, specific power, wind direction, humidity, atmospheric pressure, vehicle body length and the like. Judging whether each factor has correlation with the tail gas components by using Spearman correlation analysis;
by using
The Spearman coefficients for each factor and each emission component were obtained.
Where ρ is the Spearman coefficient, x, of a factor and emissionsiFor the ith sample value of the influencing factor,
is the mean value of the property, yiFor the ith sample value of the contaminant,
the data obtained are shown in FIG. 2.
Then use formula
Coefficients between the variables and the emission principal component are calculated.
Where n is the number of samples, here the number of samples is 3560, ρ is the Spearman coefficient for the contributors and emissions, and p is the statistic of the contributors and emissions. Here, the number of samples was 3560, and the p-value was as shown in FIG. 3.
The coefficient p is compared with t being 1.645(α being 0.05), and a value smaller than t indicates that there is no correlation between the corresponding attribute and the exhaust gas component, and is not studied. As can be seen from FIG. 3, the CO concentration has no statistical significance with respect to the vehicle length; HC concentration and reference mass, velocity, wind direction have no statistical significance; NO concentration and wind speed, temperature, barometric pressure have NO statistical significance
(4) In use mode
Coefficients having a correlation with each exhaust gas component are calculated.
Wherein lambda is a non-negative regularization parameter, y is a tail gas concentration value, and xjIs the value corresponding to the j-th attribute, betajIs a regression coefficient, and p is the number of attributes. The calculation results are shown in the following table.
| CO | HC | NO | |
| Service life | 0.010132 | 0.251103 | 0 |
| |
0 | 0 | 0.034444 |
| Speed of travel | -0.001522 | -0.01989 | -1.601211 |
| Acceleration of travel | 0.013481 | 0 | 0 |
| |
0 | 0 | 121.587871 |
| Specific power | 0.000559 | 0 | 0 |
| Wind speed | -0.011124 | 0.361842 | 13.063142 |
| Temperature of | 0.004769 | -0.09352 | 0 |
| Humidity | -0.000631 | 0.022117 | 0.408289 |
| Atmospheric pressure | -0.000049 | -0.001288 | 0.028648 |
| |
0 | 0.002636 | 0.096143 |
(5) And (4) according to the main factors influencing the emission concentration of each main component obtained in the step (4), establishing prediction models for CO, HC and NO respectively by adopting a BP neural network, and carrying out comparison and inspection on other prediction models.
(51) Prediction using BP neural network model
Based on the steps (3) and (4), deleting the attribute which has no correlation with each tail gas and the attribute with the weight coefficient of 0 calculated by the Lasso.
In the CO modeling, 8 attributes of service life, driving speed, driving acceleration, specific power, wind speed, temperature, humidity and atmospheric pressure are used as the influence factors of CO, and the concentration of CO is used as prediction output; in modeling HC, age will be used; 5 attributes of wind speed, temperature, humidity and atmospheric pressure are used as HC influence factors, and the concentration of HC is used as prediction output; in the modeling of NO, 6 attributes of reference mass, traveling speed, vehicle length, humidity, atmospheric pressure, and wind direction are used as influence factors of NO, and the concentration of NO is used as a prediction output.
The model adopts three layers of BP neural networks and utilizes a formula
Reuse of random searchTo find the most appropriate number of neurons and batch size, the learning rate was manually adjusted based on experience, with the Relu function as the activation function for each layer. Wherein N is the neuron number of the hidden layer, N and M are the neuron numbers of the input layer and the output layer respectively, and a belongs to [1,10 ]]The learning rate is adjusted based on experience.
The neural network adopts a Keras library based on TensorFlow to build a linear superposition model. After zero-mean normalization of the preprocessed data, the data set divides the data (3560 pieces) into a training data set (2848 pieces), a verification data set (356 pieces) and a test data set (356 pieces) according to the ratio of 8:1: 1.
Zero mean normalization: and finally obtaining data which has a mean value of 0 and a standard deviation of 1 and is subjected to standard normal distribution through centralization and standardization processing. The invention presses all attributes
Carrying out zero-mean normalization treatment:
where x is a sample value of a certain property, x*And u is the mean value of all sample data of the attribute, and sigma is the standard deviation of all sample data of the attribute.
The following table shows the parameters of each model
The prediction model provided by the invention is compared with other models for inspection
And finishing normalization processing, and finally outputting the prediction result of the model. And comparing two indexes of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the prediction result with Support Vector Regression (SVR), random forest (RandomForest) and neural network ANN without feature screening of the same input attribute.
FIG. 5, FIG. 6, and FIG. 7 are the CO prediction model comparison, HC prediction model comparison, and NO prediction model comparison, respectively, and in general, the absolute error and the root mean square error of the L-ANN model designed by the present invention are smaller than those of other prediction models, and the performance is the best; secondly, an SVR regression model is adopted, which is superior to other two models in most cases; the RandomForest regression model and the ANN model have the worst performance. Therefore, in the prediction of the pollutant emission components of various mobile sources, the prediction result of the L-ANN model has higher accuracy and stability.
On the other hand, the invention also discloses a system for predicting main influence factors of the mobile source pollution emission, which comprises the following units,
the data collection unit is used for collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of the urban target road section;
the data processing unit is used for preprocessing the collected data;
the correlation analysis unit is used for carrying out correlation analysis on the pre-processed data on specified components, namely CO, HC and NO, in exhaust emission and external influence factors by adopting a Spearman coefficient;
the factor screening unit is used for screening factors which influence the respective emission concentrations of the tail gas CO, HC and NO for the obtained factors which have correlation with the components in the tail gas emission by using a Lasso algorithm;
and the prediction unit is used for respectively establishing prediction models for CO, HC and NO by adopting a BP neural network according to the obtained specific factors influencing the emission concentration of each specific component and carrying out comparison and inspection with other prediction models.
In a third aspect, the present invention also discloses a computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the method as described above.
It is understood that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, the example and the beneficial effects of the related contents can refer to the corresponding parts in the method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for predicting main influence factors of mobile source pollution emission is characterized by comprising the following steps: comprises the following steps of (a) carrying out,
(1) collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of an urban target road section;
(2) preprocessing the collected data;
(3) performing correlation analysis on the pre-processed data on specified components in the exhaust emission, namely CO, HC and NO, and external influence factors by adopting a Spearman coefficient;
(4) screening out factors influencing respective emission concentrations of CO, HC and NO in the tail gas from the factors which are obtained in the step (3) and have correlation with each component in the tail gas emission by using a Lasso algorithm;
(5) and (4) according to the specific factors influencing the emission concentration of each specific component obtained in the step (4), establishing prediction models for CO, HC and NO respectively by adopting a BP neural network, and carrying out comparison and inspection with other prediction models.
2. The method of claim 1, wherein the method comprises: further, in the step (1), the process of extracting the motor vehicle exhaust telemetry data is as follows:
(11) data collected from the telemetry system includes: the device number is used for detecting vehicle passing time, license plate number, vehicle color, recognition confidence, vehicle running speed, acceleration, vehicle body length, CO measured concentration, HC measured concentration, NO measured concentration, smoke value, dynamic/static measurement, effective data, passing data, specific power, smoke value, wind speed, wind direction, air temperature, humidity and atmospheric pressure;
(12) the data obtained from the vehicle inspection includes: the number plate number, the maximum quality, the form of a transmission, the number of gears, the fuel specification, the type of a vehicle, the use property, the reference quality, the driving mode, the driving tire air pressure, the type of an engine, an engine manufacturer, the engine discharge capacity, whether a catalytic converter exists or not and an exhaust aftertreatment device.
3. The method of claim 1, wherein the method comprises: the step (2) comprises the following steps of preprocessing the motor vehicle tail gas telemetering data and the vehicle inspection data: combining different characteristic attributes of the telemetering data and the vehicle inspection data records into a new tail gas data record through the license plate number; then, finding out missing values in the data segments for discarding, then finding out abnormal values by using a boxcar graph for discarding, deleting irrelevant attributes such as equipment numbers, detecting vehicle passing time, license plate numbers, vehicle colors and identifying confidence;
after the invalid attribute is deleted, 11 attributes of the reference mass, the running speed, the running acceleration, the specific power, the wind speed, the wind direction, the air temperature, the humidity, the atmospheric pressure, the vehicle body length and the service life are left as relevant external attributes.
4. The method of claim 3, wherein the method comprises: in the step (3), Spearman correlation analysis is performed among 11 external influence factors including the components and the reference mass of each tail gas, the driving speed, the driving acceleration, the specific power, the wind speed, the wind direction, the air temperature, the humidity, the atmospheric pressure, the length of the vehicle body and the service life as follows:
(31) the formula for calculating the Spearman coefficient p of the tail gas components and influencing factors is as follows:
wherein x isiFor the ith sample value of the influencing factor,
is the mean value of the property, yiFor the ith sample value of the contaminant,
is the mean value thereof;
(32) the corresponding statistic p is then calculated using the Spearman coefficient p, the formula:
wherein n is the number of samples, and p is the statistic of influencing factors and emissions;
(33) the coefficient p is compared with t being 1.645 and α being 0.05), and a value smaller than t indicates that there is no correlation between the corresponding attribute and the exhaust gas component.
5. The method of claim 4, wherein the method comprises: in the step (4), the step of screening the main factors by using the Lasso algorithm comprises the following steps:
(41) calculating coefficients related to the components of the exhaust gas by using the Lasso algorithm
The formula is as follows:
wherein lambda is a non-negative regularization parameter, y is a tail gas concentration value, and xjIs the value corresponding to the j-th attribute, betajIs a regression coefficient, and p is the number of attributes;
(42) and (4) screening out the attribute with the coefficient of 0 corresponding to the tail gas component, and deleting the attribute with the coefficient of 0 corresponding to the tail gas and the variable without correlation in the step (3).
6. The method of claim 5, wherein the method comprises: in the step (5), the model establishing and comparing steps are as follows:
(51) constructing a prediction model of the concentration of the main components of the tail gas as follows:
and (4) after zero-mean normalization is carried out on the main factors of the components obtained in the step (4), the main factors are used as the input of a neural network, a three-layer BP neural network is established, and the data are calculated according to the following steps of 8:1: the 1 is divided into a training set, a verification set and a test set, wherein the training set and the verification set are used for training the network, and the test set is used for measuring the prediction effect of the model.
7. A system for predicting main influence factors of mobile source pollutant emission is characterized in that: comprises the following units of a first unit, a second unit,
the data collection unit is used for collecting motor vehicle tail gas remote measuring data and corresponding vehicle annual inspection data of the urban target road section;
the data processing unit is used for preprocessing the collected data;
the correlation analysis unit is used for carrying out correlation analysis on the pre-processed data on specified components, namely CO, HC and NO, in exhaust emission and external influence factors by adopting a Spearman coefficient;
the factor screening unit is used for screening factors which influence the respective emission concentrations of the tail gas CO, HC and NO for the obtained factors which have correlation with the components in the tail gas emission by using a Lasso algorithm;
and the prediction unit is used for respectively establishing prediction models for CO, HC and NO by adopting a BP neural network according to the obtained specific factors influencing the emission concentration of each specific component and carrying out comparison and inspection with other prediction models.
8. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110644.6A CN112819217A (en) | 2021-01-27 | 2021-01-27 | Method, system and storage medium for predicting main influence factors of mobile source pollution emission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110644.6A CN112819217A (en) | 2021-01-27 | 2021-01-27 | Method, system and storage medium for predicting main influence factors of mobile source pollution emission |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112819217A true CN112819217A (en) | 2021-05-18 |
Family
ID=75859665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110110644.6A Pending CN112819217A (en) | 2021-01-27 | 2021-01-27 | Method, system and storage medium for predicting main influence factors of mobile source pollution emission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819217A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421619A (en) * | 2021-07-20 | 2021-09-21 | 南京富岛信息工程有限公司 | Method for estimating carbon content of catalyst of continuous reforming device |
| CN113536601A (en) * | 2021-08-17 | 2021-10-22 | 南京富岛信息工程有限公司 | Method for improving carbon content estimation precision of catalyst of continuous reforming device |
| CN115422704A (en) * | 2022-07-19 | 2022-12-02 | 中山大学 | VOCs emission measuring and calculating method based on individual vehicle overall process travel behavior chain |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682699A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Vehicle exhaust emission characteristic analytic processing method based on clustering analysis |
| CN107300550A (en) * | 2017-06-21 | 2017-10-27 | 南京大学 | A kind of method based on BP neural network model prediction atmosphere heavy metal concentration |
| CN110826772A (en) * | 2019-10-15 | 2020-02-21 | 深圳市赛梅斯凯科技有限公司 | Vehicle exhaust emission prediction method, device, equipment and storage medium |
| CN110956310A (en) * | 2019-11-14 | 2020-04-03 | 佛山科学技术学院 | Fish feed feeding amount prediction method and system based on feature selection and support vector |
-
2021
- 2021-01-27 CN CN202110110644.6A patent/CN112819217A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682699A (en) * | 2016-12-31 | 2017-05-17 | 中国科学技术大学 | Vehicle exhaust emission characteristic analytic processing method based on clustering analysis |
| CN107300550A (en) * | 2017-06-21 | 2017-10-27 | 南京大学 | A kind of method based on BP neural network model prediction atmosphere heavy metal concentration |
| CN110826772A (en) * | 2019-10-15 | 2020-02-21 | 深圳市赛梅斯凯科技有限公司 | Vehicle exhaust emission prediction method, device, equipment and storage medium |
| CN110956310A (en) * | 2019-11-14 | 2020-04-03 | 佛山科学技术学院 | Fish feed feeding amount prediction method and system based on feature selection and support vector |
Non-Patent Citations (1)
| Title |
|---|
| 左付山等: "基于BP神经网络的汽油机尾气排放预测", 基于BP神经网络的汽油机尾气排放预测, vol. 41, no. 3, pages 307 - 313 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421619A (en) * | 2021-07-20 | 2021-09-21 | 南京富岛信息工程有限公司 | Method for estimating carbon content of catalyst of continuous reforming device |
| CN113421619B (en) * | 2021-07-20 | 2023-12-01 | 南京富岛信息工程有限公司 | Method for estimating carbon content of catalyst of continuous reforming device |
| CN113536601A (en) * | 2021-08-17 | 2021-10-22 | 南京富岛信息工程有限公司 | Method for improving carbon content estimation precision of catalyst of continuous reforming device |
| CN113536601B (en) * | 2021-08-17 | 2023-09-01 | 南京富岛信息工程有限公司 | Method for improving estimation accuracy of carbon content of catalyst of continuous reforming device |
| CN115422704A (en) * | 2022-07-19 | 2022-12-02 | 中山大学 | VOCs emission measuring and calculating method based on individual vehicle overall process travel behavior chain |
| CN115422704B (en) * | 2022-07-19 | 2024-04-05 | 中山大学 | VOCs emission measuring and calculating method based on individual vehicle whole-process travel behavior chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112819217A (en) | Method, system and storage medium for predicting main influence factors of mobile source pollution emission | |
| CN107577910B (en) | Vehicle exhaust concentration inversion method based on deep neural network | |
| CN110826772A (en) | Vehicle exhaust emission prediction method, device, equipment and storage medium | |
| CN108197731B (en) | Motor vehicle exhaust remote measurement and vehicle inspection result consistency method based on co-training | |
| CN111024898B (en) | Vehicle exhaust concentration standard exceeding judging method based on Catboost model | |
| Ma et al. | An evaluation of microscopic emission models for traffic pollution simulation using on-board measurement | |
| CN113435471A (en) | Deep feature clustering high-emission mobile source pollution identification method and system | |
| CN115829081B (en) | Urban traffic carbon emission prediction method based on support vector regression model | |
| CN110555570A (en) | Intelligent prediction method and device for gas concentration of mine limited space disaster | |
| Asher et al. | Economic and efficient hybrid vehicle fuel economy and emissions modeling using an artificial neural network | |
| CN116558834A (en) | PEMS emission analysis method, PEMS emission analysis device, PEMS emission analysis computer equipment and PEMS emission analysis storage medium | |
| CN113222211B (en) | Method and system for predicting pollutant emission factors of multi-region diesel vehicle | |
| CN115392116A (en) | Heavy diesel truck excess emission judgment method based on OBD data restoration | |
| Donateo et al. | Real time estimation of emissions in a diesel vehicle with neural networks | |
| CN111415008A (en) | Ship flow prediction method based on VMD-FOA-GRNN | |
| CN116992240B (en) | Vehicle emission remote evaluation method, device and storage medium | |
| CN115964905B (en) | Method and medium for constructing emission test working conditions of mountain roads in highland | |
| Xu et al. | Analysis and prediction of vehicle exhaust emission using ann | |
| CN112394040A (en) | Motor vehicle pollution discharge supervision system and method | |
| Kim et al. | Application of neural network model to vehicle emissions | |
| CN112991765B (en) | Method, terminal and storage medium for updating road high-emission source recognition model | |
| CN114282680A (en) | Vehicle exhaust emission prediction method and system based on machine learning algorithm | |
| CN115222145A (en) | Driving range prediction method and system based on new energy automobile operation big data | |
| CN114998075A (en) | Transportation carbon emission calculation method and system and storable medium | |
| CN114814092A (en) | IP index measuring method based on BP neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |