An online monitoring method for poor quality fuel of diesel engine based on Internet of Vehicles big data

Abstract

The present invention proposes an online monitoring method for inferior fuel of a diesel engine based on big data of the Internet of Vehicles, the method comprising: step 1: cleaning the raw data collected by the Internet of Vehicles, and removing the abnormal values in the raw data measured during the actual driving process of the vehicle; step 2: judging the starting point of diesel engine refueling; step 3: taking each refueling moment as the starting point, establishing a diesel engine operating condition data set; step 4: using the exhaust pressure P1 at the DPF inlet, the exhaust pressure P2 at the DPF outlet, and the exhaust flow rate Q at the inlet to calculate the DPF flow resistance R; step 5: using the exhaust temperature T at the DPF outlet to calculate the DPF flow resistance R; step 6: using the exhaust temperature T at the DPF outlet to calculate the DPF flow resistance R; step 7: using the exhaust temperature T at the DPF outlet to calculate the DPF flow resistance R; step 8: using the exhaust temperature T at the DPF outlet to calculate the DPF flow resistance R; step 9: using the exhaust temperature T at the out and the exhaust gas temperature at the DPF inlet T in The ratio of is used to estimate the ash index A in DPF r Step 6: Determine whether the diesel engine is filled with inferior fuel by measuring the ash index in the DPF during the active regeneration of the DPF and the maximum exhaust temperature at the DPF outlet.

Description

Technical Field

[0001] The present invention relates to an online monitoring method for inferior fuel of a diesel engine based on Internet of Vehicles big data, and belongs to the field of diesel engine operating status and health level detection. Background Art

[0002] Fuels of different qualities have significant differences in their physical and chemical properties, technical indicators, and characteristic parameters. The general characteristics of inferior fuels are high sulfur, high ash content, high additives, high viscosity, high freezing point, high asphalt content, and low cetane number. If inferior fuels are used, they will have serious effects on diesel engines, including: (1) increased corrosion and wear of cylinder and piston components; (2) high residual carbon content, excessive carbon deposits during combustion, affecting the combustion effect of the engine, and excessively high combustion temperature, leading to carbon deposits on the injectors and piston ring seizure; (3) high sulfur content in diesel, which damages the quality of the engine oil, causing the oil to reduce its performance prematurely and making the engine of the diesel generator set not well lubricated; (4) the low calorific value of diesel during combustion does not reach the specified value; the fuel consumption rate is higher than the rated engine power and the engine cannot reach the rated power, which directly leads to a decrease in diesel engine power.

[0003] Existing online detection methods mostly use empirical formulas to determine whether a diesel engine is filled with inferior fuel based on data such as diesel engine fuel consumption, mileage, operating conditions (speed, torque), exhaust temperature, etc. The existing methods have a long detection cycle and large errors in the detection results.

[0004] Therefore, it is of great significance to explore the beneficial value of the big data of the Internet of Vehicles, use the historical data of the DPF (Diesel Particulate Filter) regeneration process and the time series data of vehicle operation, and build a method that can determine whether the diesel engine is filled with inferior fuel based on the ash content in the DPF and the maximum temperature during regeneration. Summary of the invention

[0005] The invention discloses an online monitoring method for inferior fuel of a diesel engine based on big data of the Internet of Vehicles, which aims to solve the problem that the existing technology cannot judge whether a diesel engine is filled with inferior fuel based on big data of the Internet of Vehicles.

[0006] The technical solution of the present invention is: a method for online monitoring of inferior fuel of a diesel engine based on big data of Internet of Vehicles, the method comprising:

[0007] Step 1: Clean the raw data collected by the Internet of Vehicles and remove abnormal values ​​from the raw data measured during the actual driving of the vehicle. The raw data is the vehicle data uploaded to the cloud during the driving of the vehicle;

[0008] Step 2: Determine the diesel engine refueling starting point;

[0009] Step 3: Taking each refueling time as the starting point, establish a diesel engine operating condition data set;

[0010] Step 4: Collect the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet of the diesel engine through the exhaust pressure sensor; collect the exhaust flow Q at the DPF inlet of the diesel engine through the exhaust flow sensor; calculate the DPF flow resistance R using the exhaust pressure P1 at the DPF inlet, the exhaust pressure P2 at the DPF outlet, and the exhaust flow Q at the inlet; record the highest DPF flow resistance R of each active regeneration process of the DPF;

[0011] Step 5: Collect the exhaust temperature T at the DPF inlet of the diesel engine through the exhaust temperature sensor in and the exhaust temperature at the DPF outlet T out ; Use the exhaust temperature T at the DPF outlet out and the exhaust gas temperature at the DPF inlet T in The ratio of is used to estimate the ash index A in DPF r ;

[0012] Step 6: Determine whether the diesel engine is filled with inferior fuel by measuring the ash index in the DPF during the DPF active regeneration process and the maximum exhaust temperature at the DPF outlet.

[0013] Furthermore, the diesel engine refueling starting point is determined in step 2, specifically: the diesel engine refueling starting point is determined based on the liquid level data collected by the liquid level sensor in the diesel engine tank and the vehicle speed data collected by the vehicle speed sensor.

[0014] Furthermore, in step 1, the raw data collected by the Internet of Vehicles is cleaned, specifically including:

[0015] Step S1-1: Eliminate unreasonable data, including abnormal values, missing values, and values ​​that do not conform to the mechanism range;

[0016] Step S1-2: Select key measurement points in each frame of raw data acquired by the CAN bus as original measurement points for constructing a zero ash state;

[0017] Step S1-3: Eliminate sensor occupancy data such as 255, 65536, etc.; Eliminate the exhaust temperature T at the DPF inlet in and the exhaust temperature at the DPF outlet T out Abnormal interval data; eliminate the interval data with abnormal exhaust flow at the DPF inlet of the diesel engine; eliminate the frames with missing values ​​in all key measurement points.

[0018] Furthermore, the values ​​that do not conform to the mechanism range include data with a vehicle speed higher than 225 km / h and an engine speed higher than 5000 rpm; the key measurement points include vehicle speed, diesel engine speed, exhaust gas temperature T at the DPF inlet, in , diesel engine tank level, diesel engine exhaust flow rate Q at DPF inlet, DPF inlet exhaust pressure P1, DPF outlet exhaust pressure P2, DPF inlet exhaust temperature T in , exhaust gas temperature at DPF outlet T out .

[0019] Furthermore, the diesel engine operating condition data set in step 3 includes: vehicle speed, diesel engine speed, exhaust gas temperature T at the DPF inlet in , diesel engine tank level, diesel engine exhaust flow rate Q at DPF inlet, DPF inlet exhaust pressure P1, DPF outlet exhaust pressure P2, DPF inlet exhaust temperature T in , exhaust gas temperature at DPF outlet T out .

[0020] Furthermore, the calculation method of the DPF flow resistance R in step 4 includes:

[0021] Step S4-1: using the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet to calculate the DPF pressure difference ΔP=P1-P2;

[0022] Step S4-2: The DPF pressure difference ΔP is regarded as the voltage across the DPF, and the exhaust flow rate Q at the DPF inlet is regarded as the current flowing through the DPF. The DPF flow resistance R is obtained by the ratio ΔP / Q of the DPF pressure difference ΔP and the exhaust flow rate Q at the DPF inlet.

[0023] Furthermore, the ash index A in the DPF in step 5 is r The calculation methods include:

[0024] Step S5-1: Based on the historical data collected by the Internet of Vehicles, obtain n sets of DPF flow resistance sequence data corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time, and calculate the highest flow resistance data sequence {R 1 ,R 2 …,R n}, calculate the average value of the maximum flow resistance Among them, n depends on the operating conditions of the diesel engine and the external environment during the two refueling periods;

[0025] Step S5-2: Based on the historical data collected by the Internet of Vehicles, obtain n groups of DPF inlet exhaust gas temperatures T corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time inand the exhaust temperature at the DPF outlet T out Data sequence, calculate the highest DPF outlet exhaust temperature of n DPF active regeneration processes and its corresponding exhaust temperature at the DPF inlet

[0026] Step S5-3: Using the mean normalization method, the highest flow resistance R of n DPF active regeneration processes between two refueling times is calculated. max and the average value of the maximum flow resistance R m Calculate the ash index A in the DPF during each active regeneration process r Correction value M = 1-0.3×(R max -R m );

[0027] Step S5-4: DPF ash index during the i-th active regeneration between two refuelings

[0028] Furthermore, in step 6, determining whether the diesel engine is filled with inferior fuel specifically includes:

[0029] Step S6-1: The highest flow resistance R of the last active regeneration process of the diesel engine before refueling max0 and the historical average maximum flow resistance R before the last active regeneration process of the diesel engine before refueling m0 Calculate the ash index in the DPF during the last active regeneration process before refueling

[0030] Step S6-2: The maximum flow resistance R of the first active regeneration process after the diesel engine is refueled max1 and the historical average maximum flow resistance R before the first active regeneration process of the diesel engine after refueling m1 Calculate the ash index in the DPF during the first active regeneration process after refueling

[0031] Step S6-3: Based on the historical data collected by the Internet of Vehicles, obtain the data sequence of the highest outlet exhaust temperature of the DPF during the n DPF active regeneration processes between the current refueling time and the last refueling time Calculate the historical average maximum exhaust temperature at the DPF outlet The maximum exhaust temperature at the DPF outlet during the last active regeneration process before refueling

[0032] Step S6-4: Calculate and obtain the maximum exhaust temperature at the outlet of the DPF during the last active regeneration process of the diesel engine before refueling. The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the last active regeneration process of the diesel engine before refueling

[0033] Step S6-5: The maximum exhaust temperature at the outlet of the DPF during the first active regeneration process after the diesel engine is refueled The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the first active regeneration process of the diesel engine after refueling

[0034] Step S6-6: The ratio of the DPF ash index before and after the refueling of the diesel engine And the ratio of the maximum exhaust temperature change at the DPF outlet As a characterization parameter of the ash index change rate; when and It is determined that the diesel engine is filled with inferior fuel.

[0035] Furthermore, the ash index threshold is 1.1, the maximum exhaust temperature change threshold is 2, when and It is determined that the diesel engine is filled with inferior fuel.

[0036] Beneficial effects of the present invention:

[0037] The present invention can determine whether the diesel engine is filled with inferior fuel according to the ash index of the diesel engine DPF and the maximum exhaust temperature at the DPF outlet during the active regeneration process fed back online by the Internet of Vehicles. The present invention taps the beneficial value of the big data of the Internet of Vehicles, uses the historical data of the DPF regeneration process and the time series data of the vehicle operation, and quantifies the ash index in the DPF and the maximum exhaust temperature at the DPF outlet during the active regeneration process with the help of big data analysis to determine whether the diesel engine is filled with inferior fuel, reduce unnecessary damage to the engine caused by inferior fuel, save fuel consumption, and is of great significance to energy conservation and emission reduction and extending the service life of the diesel engine. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Attached Figure 1 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0039] The present invention provides a method for online monitoring of inferior fuel of a diesel engine based on Internet of Vehicles big data, the method comprising the following steps:

[0040] Step 1: Clean the raw data collected by the Internet of Vehicles and remove abnormal values ​​from the raw data measured during the actual driving of the vehicle. The raw data is the vehicle data uploaded to the cloud during the driving of the vehicle;

[0041] Step 2: Determine the diesel engine refueling starting point based on the liquid level data collected by the liquid level sensor in the diesel engine tank and the vehicle speed data collected by the vehicle speed sensor;

[0042] Step 3: Taking each refueling time as the starting point, establish a diesel engine operating condition data set;

[0043] Step 4: Collect the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet of the diesel engine through the exhaust pressure sensor; collect the exhaust flow Q at the DPF inlet of the diesel engine through the exhaust flow sensor; calculate the DPF flow resistance R using the exhaust pressure P1 at the DPF inlet, the exhaust pressure P2 at the DPF outlet, and the exhaust flow Q at the inlet; record the highest DPF flow resistance R of each active regeneration process of the DPF;

[0044] Step 5: Collect the exhaust temperature T at the DPF inlet of the diesel engine through the exhaust temperature sensor in and the exhaust temperature at the DPF outlet T out ; Use the exhaust temperature T at the DPF outlet out and the exhaust gas temperature at the DPF inlet T in The ratio of is used to estimate the ash index A in DPF r ;

[0045] Step 6: Ash index A in the DPF during active DPF regeneration r and the maximum exhaust temperature at the DPF outlet to determine whether the diesel engine is filled with inferior fuel.

[0046] In the above steps, the raw data collected by the Internet of Vehicles is cleaned in step 1, which specifically includes the following steps:

[0047] Step S1-1: Eliminate unreasonable data, which includes abnormal values, missing values, and values ​​that do not conform to the mechanism range; the values ​​that do not conform to the mechanism range specifically include data with a vehicle speed higher than 225 km / h and an engine speed higher than 5000 rpm;

[0048] Step S1-2: Select each frame of raw data acquired by the CAN bus, the sampling rate is preferably 1 frame / second, and the key measurement points in each frame of raw data are used as the original measurement points when constructing the zero ash state. The key measurement points include vehicle speed (km / h), diesel engine speed (rpm), exhaust temperature T at the DPF inlet, and the exhaust gas temperature T at the DPF inlet. in(℃), diesel engine tank level (L), diesel engine exhaust flow rate Q at DPF inlet (L / min), exhaust pressure P1 at DPF inlet (kPa), exhaust pressure P2 at DPF outlet (kPa), exhaust temperature T at DPF inlet in (℃), exhaust temperature at DPF outlet T out (℃);

[0049] Step S1-3: Eliminate sensor occupancy data such as 255, 65536, etc.; Eliminate the exhaust temperature T at the DPF inlet in , exhaust temperature at DPF outlet T out The obviously abnormal interval data; the obviously abnormal interval data of the exhaust flow Q at the inlet of the diesel engine DPF are eliminated; the frames containing missing values ​​in all key measurement points are eliminated.

[0050] In step S1-2, the diesel engine speed is less than 500 rpm or greater than 6000 rpm, and the exhaust gas temperature T at the DPF inlet is in In the estimated temperature range T in ≥50℃, and the exhaust temperature at the DPF outlet is T out In the estimated temperature range T in ≤1000℃.

[0051] The diesel engine operating condition data set in step 3 includes: vehicle speed (km / h), diesel engine speed (rpm), exhaust gas temperature T at the DPF inlet in (℃), diesel engine tank level (L), diesel engine exhaust flow rate Q at DPF inlet (L / min), exhaust pressure P1 at DPF inlet (kPa), exhaust pressure P2 at DPF outlet (kPa), exhaust temperature T at DPF inlet in (℃), exhaust temperature at DPF outlet T out (℃); The data in the above diesel engine operating condition data set are collected from the CAN bus, with each refueling moment as the sampling starting point and the sampling frequency being 1 frame / second.

[0052] The method for calculating the DPF flow resistance R in step 4 comprises the following steps:

[0053] Step S4-1: using the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet to calculate the DPF pressure difference ΔP=P1-P2;

[0054] Step S4-2: The DPF pressure difference ΔP is regarded as the voltage across the DPF, and the exhaust flow rate Q at the DPF inlet is regarded as the current flowing through the DPF. The DPF flow resistance R is obtained by the ratio ΔP / Q of the DPF pressure difference ΔP and the exhaust flow rate Q at the DPF inlet.

[0055] The ash index A in the DPF in step 5 r The calculation method includes the following steps:

[0056] Step S5-1: Based on the historical data collected by the Internet of Vehicles, obtain n sets of DPF flow resistance sequence data corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time, and calculate the highest flow resistance data sequence {R 1 ,R 2 …,R n}, calculate the average value of the maximum flow resistance Among them, n depends on the operating conditions of the diesel engine and the external environment during the two refueling periods, and its recommended value is n≥5;

[0057] Step S5-2: Based on the historical data collected by the Internet of Vehicles, obtain n groups of DPF inlet exhaust gas temperatures T corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time in (℃) and the exhaust temperature at the DPF outlet T out (℃) data sequence, calculate the highest DPF outlet exhaust temperature of n DPF active regeneration processes (℃) and its corresponding exhaust gas temperature at the DPF inlet (℃);

[0058] Step S5-3: Using the mean normalization method, the highest flow resistance R of n DPF active regeneration processes between two refueling times is calculated. max and the average value of the maximum flow resistance R m Calculate the ash index A in the DPF during each active regeneration process r Correction value M = 1-0.3×(R max -R m );

[0059] Step S5-4: DPF ash index during the i-th active regeneration between two refuelings

[0060] The specific method for determining whether the diesel engine is filled with inferior fuel in step 6 comprises the following steps:

[0061] Step S6-1: Using the mean normalization method, the highest flow resistance R of the last active regeneration process of the diesel engine before refueling is calculated. max0 and the historical average maximum flow resistance R before the last active regeneration process of the diesel engine before refueling m0 Calculate the ash index in the DPF during the last active regeneration process before refueling The historical average maximum flow resistance refers to the same vehicle, extracting the maximum flow resistance from each DPF active regeneration stage in history, and averaging the set based on the maximum flow resistance;

[0062] Step S6-2: Using the mean normalization method, the maximum flow resistance R of the first active regeneration process of the diesel engine after refueling is calculated. max1 and the historical average maximum flow resistance R before the first active regeneration process of the diesel engine after refueling m1 Calculate the ash index in the DPF during the first active regeneration process after refueling The historical average maximum flow resistance refers to the same vehicle, extracting the maximum flow resistance from each DPF active regeneration stage in history, and averaging the set based on the maximum flow resistance;

[0063] Step S6-3: Based on the historical data collected by the Internet of Vehicles, obtain the data sequence of the highest outlet exhaust temperature of the DPF during the n DPF active regeneration processes between the current refueling time and the last refueling time Calculate the historical average maximum exhaust temperature at the DPF outlet The maximum exhaust temperature at the DPF outlet during the last active regeneration process before refueling

[0064] Step S6-4: Calculate and obtain the maximum exhaust temperature at the outlet of the DPF during the last active regeneration process of the diesel engine before refueling. The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the last active regeneration process of the diesel engine before refueling

[0065] Step S6-5: The maximum exhaust temperature at the outlet of the DPF during the first active regeneration process after the diesel engine is refueled The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the first active regeneration process of the diesel engine after refueling

[0066] Step S6-6: Since the content of inferior components in the fuel (such as sulfur content, etc.) is positively correlated with the ash content in the DPF, and the ash content is positively correlated with the maximum temperature at the DPF outlet during active regeneration, the ratio of the DPF ash index before and after refueling of the diesel engine is calculated. And the ratio of the maximum exhaust temperature change at the DPF outlet As the characterization parameter of the ash index change rate; through calibration, when and When , it indicates that the ash index change rate exceeds the normal threshold, so it is determined that the diesel engine is filled with low-quality fuel; the ash index threshold is preferably 1.1, and the maximum exhaust temperature change threshold is preferably 2, that is, preferably: when and When , it indicates that the ash index change rate exceeds the normal threshold, so it is determined that the diesel engine is filled with inferior fuel; further, the more diesel engine models are calibrated, the more accurate the ash index threshold and the maximum exhaust temperature change threshold are; in actual application, the ash index threshold and the maximum exhaust temperature change threshold can be dynamically optimized according to the number of diesel engine models and quantity / units applied by the current method, that is, the richer the big data volume, the more accurate the ash index threshold and the maximum exhaust temperature change threshold are.

Claims

1. A method for online monitoring of low-quality diesel fuel based on Internet of Vehicles big data. Its characteristics are include: Step 1: Clean the raw data collected by the Internet of Vehicles and remove abnormal values ​​from the raw data measured during the actual driving of the vehicle. The raw data is the vehicle data uploaded to the cloud during the driving of the vehicle; Step 2: Determine the diesel engine refueling starting point; Step 3: Taking each refueling time as the starting point, establish a diesel engine operating condition data set; Step 4: Collect the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet of the diesel engine through the exhaust pressure sensor; collect the exhaust flow Q at the DPF inlet of the diesel engine through the exhaust flow sensor; calculate the DPF flow resistance R using the exhaust pressure P1 at the DPF inlet, the exhaust pressure P2 at the DPF outlet, and the exhaust flow Q at the inlet; record the highest DPF flow resistance R of each active regeneration process of the DPF; Step 5: Collect the exhaust temperature T at the DPF inlet of the diesel engine through the exhaust temperature sensor in and the exhaust temperature at the DPF outlet T out ; Use the exhaust temperature T at the DPF outlet out and the exhaust gas temperature at the DPF inlet T in The ratio of is used to estimate the ash index A in DPF r ; Step 6: Determine whether the diesel engine is filled with inferior fuel by measuring the ash index in the DPF during the DPF active regeneration process and the maximum exhaust temperature at the DPF outlet; The ash index A in the DPF in step 5 r The calculation methods include: Step S5-1: Based on the historical data collected by the Internet of Vehicles, obtain n sets of DPF flow resistance sequence data corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time, and calculate the highest flow resistance data sequence {R 1 ,R 2 …,R n }, calculate the average value of the maximum flow resistance Among them, n depends on the operating conditions of the diesel engine and the external environment during the two refueling periods; Step S5-2: Based on the historical data collected by the Internet of Vehicles, obtain n groups of DPF inlet exhaust gas temperatures T corresponding to n DPF active regeneration processes between the current refueling time and the last refueling time in and the exhaust temperature at the DPF outlet T out Data sequence, calculate the highest DPF outlet exhaust temperature of n DPF active regeneration processes and its corresponding exhaust temperature at the DPF inlet Step S5-3: Using the mean normalization method, the highest flow resistance R of n DPF active regeneration processes between two refueling times is calculated. max and the average value of the maximum flow resistance R m Calculate the ash index A in the DPF during each active regeneration process r Correction value M = 1-0.3×(R max -R m ); Step S5-4: DPF ash index during the i-th active regeneration between two refuelings 2. According to claim 1, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are Determining the diesel engine refueling starting point in the step 2 is specifically: determining the diesel engine refueling starting point according to the liquid level data collected by the liquid level sensor in the diesel engine tank and the vehicle speed data collected by the vehicle speed sensor.

3. According to claim 1, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are In step 1, the raw data collected by the Internet of Vehicles is cleaned, specifically including: Step S1-1: Eliminate unreasonable data, including abnormal values, missing values, and values ​​that do not conform to the mechanism range; Step S1-2: Select key measurement points in each frame of raw data acquired by the CAN bus as original measurement points for constructing a zero ash state; Step S1-3: Eliminate sensor occupancy data such as 255, 65536, etc.; Eliminate the exhaust temperature T at the DPF inlet in and the exhaust temperature at the DPF outlet T out Abnormal interval data; eliminate the interval data with abnormal exhaust flow at the DPF inlet of the diesel engine; eliminate the frames with missing values ​​in all key measurement points.

4. According to claim 3, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are The values ​​that do not conform to the mechanism range include data with a vehicle speed higher than 225 km / h and an engine speed higher than 5000 rpm; the key measurement points include vehicle speed, diesel engine speed, diesel engine tank level, exhaust flow Q at the diesel engine DPF inlet, exhaust pressure P1 at the DPF inlet, exhaust pressure P2 at the DPF outlet, exhaust temperature T at the DPF inlet in , exhaust gas temperature at DPF outlet T out .

5. According to claim 1, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are The diesel engine operating condition data set in step 3 includes: vehicle speed, diesel engine speed, diesel engine fuel tank level, exhaust flow Q at the diesel engine DPF inlet, exhaust pressure P1 at the DPF inlet, exhaust pressure P2 at the DPF outlet, exhaust temperature T at the DPF inlet in , exhaust gas temperature at DPF outlet T out .

6. According to claim 1, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are The calculation method of the DPF flow resistance R in step 4 includes: Step S4-1: using the exhaust pressure P1 at the DPF inlet and the exhaust pressure P2 at the DPF outlet to calculate the DPF pressure difference ΔP=P1-P2; Step S4-2: The DPF pressure difference ΔP is regarded as the voltage across the DPF, and the exhaust flow rate Q at the DPF inlet is regarded as the current flowing through the DPF. The DPF flow resistance R is obtained by the ratio ΔP / Q of the DPF pressure difference ΔP and the exhaust flow rate Q at the DPF inlet.

7. According to claim 1, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are Determining whether the diesel engine is filled with inferior fuel in step 6 specifically includes: Step S6-1: The highest flow resistance R of the last active regeneration process of the diesel engine before refueling max0 and the historical average maximum flow resistance R before the last active regeneration process of the diesel engine before refueling m0 Calculate the ash index in the DPF during the last active regeneration process before refueling Step S6-2: The maximum flow resistance R of the first active regeneration process after the diesel engine is refueled max1 and the historical average maximum flow resistance R before the first active regeneration process of the diesel engine after refueling m1 Calculate the ash index in the DPF during the first active regeneration process after refueling Step S6-3: Based on the historical data collected by the Internet of Vehicles, obtain the data sequence of the highest outlet exhaust temperature of the DPF during the n DPF active regeneration processes between the current refueling time and the last refueling time Calculate the historical average maximum exhaust temperature at the DPF outlet The maximum exhaust temperature at the DPF outlet during the last active regeneration process before refueling Step S6-4: Calculate and obtain the maximum exhaust temperature at the outlet of the DPF during the last active regeneration process of the diesel engine before refueling. The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the last active regeneration process of the diesel engine before refueling Step S6-5: The maximum exhaust temperature at the outlet of the DPF during the first active regeneration process after the diesel engine is refueled The average maximum exhaust temperature T at the DPF outlet between this refueling time and the last refueling time m , calculate the maximum exhaust temperature change value at the DPF outlet during the first active regeneration process of the diesel engine after refueling Step S6-6: The ratio of the DPF ash index before and after the refueling of the diesel engine And the ratio of the maximum exhaust temperature change at the DPF outlet As a characterization parameter of the ash index change rate; Ash index threshold and When the maximum exhaust temperature changes to a threshold value, it is determined that the diesel engine is filled with inferior fuel.

8. According to claim 7, a method for online monitoring of low-quality fuel of a diesel engine based on big data of Internet of Vehicles, Its characteristics are The ash index threshold is 1.1, and the maximum exhaust temperature change threshold is 2. and It is determined that the diesel engine is filled with inferior fuel.

Images