An intelligent control method for a commercial vehicle automatic transmission based on the VCU architecture

Abstract

The present invention relates to an intelligent control method for a commercial vehicle automatic transmission based on a VCU architecture, including a rule-based control mode. According to the vehicle operation conditions, road conditions, and the driver's intention, the operation mode of the vehicle AMT transmission is determined according to the optimal principle. The VCU performs intelligent switching control on the shift laws of the transmission economy and power performance. In the case of light load, or small road gradient, or when the throttle opening is less than or equal to the preset threshold in the uphill working condition, the economic mode is selected. In the case of heavy load, large gradient, and throttle opening greater than the preset value in the uphill working condition, the power mode is selected. Intelligent switching control is performed on the shift laws of the transmission economy and power performance to ensure that the engine operates in an appropriate speed range, and improve the climbing power performance on the premise of ensuring economy. At the same time, through this multi-level throttle Map switching control method, the VCU enhances the driver's perception of the vehicle fuel economy and power performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of automatic transmissions, and relates to an intelligent control method for a commercial vehicle automatic transmission based on a VCU architecture. Background Art

[0002] With the rapid development of automotive electronic control technology, traditional manual transmissions can no longer meet the needs of users for advanced automotive technology products. In view of the complex driving conditions and harsh environment of commercial vehicles, most vehicle manufacturers choose to develop AMT transmissions with high cost performance, energy saving and fuel efficiency to adapt to different road conditions and meet the economic and dynamic requirements of customers. Intelligent switching of throttle Maps with different characteristics is performed according to the real-time state of the vehicle, road conditions and driver's intentions (throttle, engine speed, vehicle load, etc.), the operating mode of the vehicle transmission is judged, and the target operating mode of the automatic transmission (AMT) is decided through the vehicle controller (VCU). The transmission controller (TCU) receives and executes the E / P mode switching request (economic mode E, power mode P) sent by the VCU to meet the driver's requirements for vehicle fuel economy, power performance, etc. The existing intelligent control schemes for commercial vehicle automatic transmissions are as follows:

[0003] 1. Multi-stage throttle switching control scheme for commercial vehicles:

[0004] 1) Commercial vehicles control the switching of different throttle Maps by configuring a power-saving switch, and the driver operates the switch manually, but there are problems such as low utilization rate of user manual control;

[0005] 2) Commercial vehicles based on the VCU architecture are only equipped with a set of throttle Maps, without distinguishing the vehicle operating state and driving intention, and the best fuel economy and power performance of the whole vehicle cannot be achieved;

[0006] 2. Automatic transmission operating mode switching control scheme:

[0007] 1) The E / P switching of the commercial vehicle AMT automatic transmission is manually operated by the driver, and there are problems such as user complaints about insufficient climbing power caused by mode non-switching and low utilization rate of manual control;

[0008] 2) The commercial vehicle AMT automatic transmission recognizes the upcoming ramp in advance according to the electronic map module (e-Horizon) installed in the whole vehicle, and the controller decides to automatically switch the economic mode of the transmission to the power mode through an algorithm to meet the climbing power requirement. However, this method requires the installation of an electronic map module, resulting in a high cost; there is still no low-cost control technology for automatic switching control based on vehicle state, driver intention and road conditions. Summary of the Invention

[0009] The present invention provides an intelligent switching control method for the operating mode of a commercial vehicle automatic transmission. According to the current vehicle state, road conditions, and driver intention, intelligent switching control is performed on the vehicle throttle Map and the shift laws of the economy and power performance of the transmission, ensuring that the engine operates within a suitable speed range and improving power performance on the premise of ensuring economy; the control method of the present invention is integrated in the VCU without increasing the vehicle cost.

[0010] The present invention is implemented by adopting the following technical solutions:

[0011] An intelligent control method for a commercial vehicle automatic transmission, the intelligent control method includes a rule-based control mode, and the rule-based control mode makes a throttle Map switch and a decision on the transmission operating mode according to the current vehicle state, the current vehicle load condition, the road slope condition, and the driver intention. The VCU performs intelligent switching control on the shift laws of the economy and power performance of the transmission, and at the same time, the VCU controls and switches the throttle Map according to the current gear; the VCU makes a decision on the operating mode and controls the switch according to the current road slope grading state and the throttle pedal opening state; ensuring that the engine works in the economic speed range as much as possible and always operates in the high-efficiency working condition of the engine, and improving power performance on the premise of ensuring economy.

[0012] As a further description of the present invention:

[0013] In the case of light load, or small road slope, or when the throttle opening is less than or equal to the preset threshold in the uphill working condition, the economic mode is selected and sent to the transmission TCU; in the case where the three conditions of heavy load, large slope, and throttle opening greater than the preset threshold are simultaneously satisfied in the uphill working condition, the power mode is selected and sent to the transmission TCU; the transmission TCU selects the economic shift law to shift gears according to the E mode status signal sent by the VCU; the transmission TCU selects the power shift law to shift gears according to the P mode status signal sent by the VCU;

[0014] Preferably, in the case of light load, or flat road, or gentle uphill and the throttle opening is less than or equal to the throttle opening set for the gentle slope, or steep uphill and the throttle opening is less than or equal to the throttle opening set for the steep slope, the economic mode is selected and sent to the transmission TCU; in the case where the three conditions of heavy load and gentle slope and the throttle opening is greater than the throttle opening set for the gentle slope, or heavy load and steep slope and the throttle opening is greater than the throttle opening of the steep slope are simultaneously satisfied, the power mode is selected and sent to the transmission TCU.

[0015] As a further description of the present invention:

[0016] Set different throttle thresholds APP for steep slopes and gentle slopes, where the throttle threshold for the steep slope is APP1 and the throttle threshold for the gentle slope is APP2;

[0017] Since the power demand for climbing gentle slopes is small, when it is heavy load, gentle slope and the throttle opening is greater than APP2, switch to the power mode; when it is heavy load, gentle slope and the throttle opening is less than or equal to APP2, switch to the economy mode;

[0018] Since the power demand for climbing steep slopes is large, when it is heavy load, steep slope and the throttle opening is greater than APP1, switch to the power mode; when it is heavy load, steep slope and the throttle opening is less than or equal to APP1, switch to the economy mode;

[0019] Set the throttle threshold APP1 for steep slopes to 45% and the throttle threshold APP2 for gentle slopes to 65%.

[0020] As a further description of the present invention: The VCU controls and switches the throttle Map according to the current gear, including:

[0021] On the premise of judging the driving intention through the VCU, select different throttle MAPs according to the operating conditions of different gears. When the gear state is 1, switch to throttle Map1; when the gear state is 2, switch to throttle Map2; when the gear state is 3, switch to throttle Map3, taking into account both power performance and economy, and improving the driving performance of the whole vehicle;

[0022] Through big data statistical analysis of the gear distribution of the currently running vehicles, divide the gear intervals according to different transmission models: the gear state 1 is the low gear area, the gear state 2 is the middle gear area, and the gear state 3 is the high gear area;

[0023] Throttle Map state division: Map1 is for the power performance of starting and climbing mountains in the low gear area; Map2 is for climbing at high speed in the middle gear area, taking into account power performance on the premise of economy; Map3 is for high-speed cruising conditions in the high gear area, meeting economy.

[0024] As a further description of the present invention:

[0025] When the actual gear of the transmission is higher than the low gear area threshold, switch from the throttle MAP state 1 in the low gear area to the throttle MAP state 2 in the middle gear area, and perform smooth processing on torque control;

[0026] When the actual gear of the transmission is higher than the middle gear area threshold, switch from the throttle MAP state 2 in the middle gear area to the throttle MAP state 3 in the high gear area, and perform smooth processing on torque control;

[0027] When the actual gear of the transmission is lower than the middle gear area threshold, switch from the throttle MAP state 2 in the middle gear area to the throttle MAP state 1 in the low gear area, and perform smooth processing on torque control;

[0028] When the actual gear of the transmission is lower than the high gear area threshold, switch from the throttle MAP state 3 in the high gear area to the throttle MAP state 2 in the middle gear area, and perform smooth processing on torque control.

[0029] As a further description of the present invention:

[0030] The VCU makes decisions on and switches the operating mode based on the current road slope classification status and the throttle pedal opening status, including: making decisions on and switching the transmission operating mode according to the current vehicle load condition, the current road slope classification status, and the throttle pedal opening status;

[0031] Road slope classification status division:

[0032] Road slope status 1: flat road; Road slope status 2: gentle slope; Road slope status 3: steep slope;

[0033] Principle of road slope classification status judgment and jump:

[0034] When the slope is greater than S1 and remains greater than the time threshold, it jumps from road slope status 1 to road slope status 2;

[0035] When the slope is less than or equal to S1 and remains greater than the time threshold, it jumps from road slope status 2 to road slope status 1;

[0036] When the slope is greater than S2 and remains greater than the time threshold, it jumps from road slope status 2 to road slope status 3;

[0037] When the slope is less than or equal to S2 and remains greater than the time threshold, it jumps from road slope status 3 to road slope status 2;

[0038] When the slope is greater than S2 and remains greater than the time threshold, it jumps from road slope status 1 to road slope status 3;

[0039] Throttle opening status setting:

[0040] Throttle opening status 1 is greater than the throttle opening APP2 under a gentle slope;

[0041] Throttle opening status 2 is less than or equal to the throttle opening APP2 under a gentle slope;

[0042] Throttle opening status 3 is greater than the throttle opening APP1 under a steep slope;

[0043] Throttle opening status 4 is less than or equal to the throttle opening APP1 under a steep slope;

[0044] Among them, S1 is 3%, S2 is 7%, and the slope unit is percentage; less than S1 is a flat road, greater than S2 is a steep slope, and between S1 - S2 is a gentle slope.

[0045] As a further description of the present invention: The intelligent control method is characterized in that it specifically includes the following steps:

[0046] After the intelligent E / P shift of the transmission is activated, the default is the economy mode E, which continuously judges the vehicle load threshold, road gradient threshold, and accelerator pedal opening threshold in real time;

[0047] The judgment conditions for the transmission operation mode to switch from the economy mode E to the power mode P are as follows:

[0048] 1) When the vehicle load is greater than the set threshold m, the vehicle stays in road gradient state 2 for longer than the set time threshold, and the accelerator opening state 1 lasts for longer than the set time threshold, after all three conditions are met simultaneously, the transmission operation mode switches from the economy mode E to the power mode P;

[0049] 2) When the vehicle load is greater than the set threshold m, the vehicle stays in road gradient state 3 for longer than the set time threshold, and the accelerator opening state 3 lasts for longer than the set time threshold, after all three conditions are met simultaneously, the transmission operation mode switches from the economy mode E to the power mode P;

[0050] The judgment conditions for the transmission operation mode to switch from the power mode P to the economy mode E are as follows:

[0051] 1) When the vehicle load is less than or equal to the set threshold m, it switches from the power mode P to the economy mode E;

[0052] 2) When the vehicle load is greater than the set threshold m and the vehicle stays in road gradient state 1 for longer than the set time threshold, it switches from the power mode P to the economy mode E;

[0053] 3) When the vehicle load is greater than the set threshold m, the vehicle stays in road gradient state 2 for longer than the set time threshold, and the accelerator opening state 2 lasts for longer than the set time threshold, it switches from the power mode P to the economy mode E;

[0054] 4) When the vehicle load is greater than the set threshold m, the vehicle stays in road gradient state 3 for longer than the set time threshold, and the accelerator opening state 4 lasts for longer than the set time threshold, it switches from the power mode P to the economy mode E.

[0055] As a further illustration of the present invention:

[0056] The intelligent control method further includes a control mode based on an artificial intelligence algorithm. Each time the vehicle is powered on and started, it first enters the rule-based control mode, and automatically switches to the control mode based on the artificial intelligence algorithm after the vehicle has accumulated 200 kilometers of driving after startup;

[0057] The control mode based on the artificial intelligence algorithm identifies the driving style according to the past vehicle operation data, conducts data clustering analysis based on the vehicle operation data, samples and formulates a driving cycle according to the driving conditions, classifies the road type and driving behavior of the vehicle operation. The road type is identified by the distribution of vehicle speed, slope, and gear operation. The feature vectors extracted from the driving behavior include the maximum vehicle speed, average vehicle speed, maximum lateral acceleration, and maximum acceleration pedal change rate information, which are standardized. Three driving style models of aggressive, general, and mild are obtained through the classification tree classification algorithm training. The aggressive driving style model is correspondingly switched to the power mode, and the general or mild driving style model is switched to the economic mode.

[0058] As a further description of the present invention:

[0059] The control mode based on the artificial intelligence algorithm specifically includes the following steps:

[0060] S1, sample making:

[0061] First, a data collection route covering different road grades such as urban, highway, national road, mountain area, and hilly area is formulated as a driving cycle sample, and the idling, accelerating, decelerating, and uniform speed distributions and ratios of the driving cycle sample are set, and the road type is identified by the distribution of vehicle speed, slope, and gear operation;

[0062] Secondly, drivers are selected. Drivers with three styles of aggressive, mild, and general are selected, and the driving data of these drivers on the formulated driving cycle sample is collected. The driving data is subjected to data cleaning and data slicing processing. After the data processing is completed, the driving behavior of the drivers within the driving cycle sample is comprehensively scored;

[0063] S2, feature engineering:

[0064] First, the mean, variance, maximum and minimum mathematical features of the samples in different scenarios are extracted as basic features, and the basic features are standardized. In terms of feature selection, first, the low-variance features extracted are deleted. Secondly, through the two-sample t-test, features with large differences in different comprehensive driving styles are selected. Finally, redundant features are deleted through correlation analysis; the collected driving data is made into multiple separate small samples for the convenience of the clustering analysis in step S3;

[0065] S3, clustering analysis:

[0066] The driving style recognition problem is regarded as an unsupervised learning problem. First, the collected driving data is analyzed offline, and the K-means clustering method without PCA is used for clustering analysis of the sample data. The clustering result is used as a sample label, and the corresponding driving style label is added according to the specific result;

[0067] S4, classification algorithm development:

[0068] After adding labels to the samples through clustering analysis, the labeled samples are used to train the classification algorithm. A generalized linear classifier that uses a support vector machine to classify data in a supervised learning manner is selected. Features related to vehicle speed, longitudinal and lateral accelerations, acceleration, and acceleration pedal change rate are input into the classification algorithm. The algorithm training is implemented through an m-file script. The distance from a sample point to near overclocking operation can itself reflect the radical degree of the sample point. The driving style is no longer simply divided into three isolated categories of radical, mild, and normal, but a linear scoring of the radical degree. The distance from a radical sample to the radical hyperplane is higher than that of a normal sample, and the distance from a normal sample to the radical hyperplane is higher than that of a mild sample. After the algorithm training is completed, the trained algorithm is integrated into Simulink through the matlab function module to achieve the model development of the algorithm. After the model is built, C++ code is generated for the model through Embedded Coder, and a driving style recognition APP is made. The driving style APP finally calculates and outputs three labels: radical, mild, and normal for the driving style.

[0069] As a further description of the present invention: Preferably, in step S1,

[0070] The data cleaning includes smoothing noise, outlier detection, and missing value handling to ensure data quality. The smoothing of noise removes high-frequency noise through simple moving window averaging and low-pass filtering. The outlier detection sets a threshold based on vehicle physical knowledge and combines the data of multiple sensors to judge rationality. The missing value handling is divided into small-segment missing and large-segment missing. For small-segment missing, linear interpolation or forward filling is used, and for large-segment missing, the affected time period is directly removed.

[0071] Different slicing rules are designed for different scenarios. There are three methods for data slicing. The first method uses a fixed time window as a segment, which is suitable for steady-state analysis. The second method is event-driven, where rules for sudden acceleration, sudden braking, and sharp turning events are defined, and 5 seconds of data before and after the event are extracted. The vehicle speed is relatively high and changes less during high-speed driving, while there are frequent starts and stops, sudden accelerations, and sudden brakings during driving on national roads. The third method is driving state segmentation, which is based on the idle, acceleration, deceleration, and constant-speed states set by the driving cycle and is segmented based on the state change points.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] 1) The intelligent switching control method for the operating mode of the commercial vehicle automatic transmission of the present invention includes a rule-based control mode. The rule-based control mode identifies and predicts the driver's intention based on the current vehicle state, road conditions, and past vehicle data, and performs intelligent switching control on the vehicle throttle Map and the shift laws of the transmission for economy and power, ensuring that the engine works as much as possible in the economic speed range and always operates in the high-efficiency working condition of the engine, and improving the power performance on the premise of ensuring economy.

[0074] 2) The intelligent switching control method for the operating mode of the commercial vehicle automatic transmission of the present invention further includes a control mode based on artificial intelligence algorithms. Each time the vehicle is powered on and started, it first enters the rule-based control mode, and automatically switches to the control mode based on artificial intelligence algorithms after the vehicle has accumulated 200 kilometers of driving after startup; the control mode based on artificial intelligence algorithms is that after the driving style recognition APP uses the vehicle operation data to complete learning, the APP issues a driving style label. The aggressive driving style label corresponds to the power mode P, and the general and gentle driving style labels are switched to the economy mode E to realize the adaptive control of the transmission operation mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 is the intelligent switching control architecture diagram of the transmission based on VCU of the present invention (rule-based control mode);

[0076] Figure 2 is the schematic diagram of multi-stage throttle switching control based on the gear range;

[0077] Figure 3 is the schematic diagram of the road slope grading state judgment and jump of the present invention;

[0078] Figure 4 is the intelligent E / P mode switching working flow chart of the present invention;

[0079] Figure 5 is the development flow chart of the driving style recognition algorithm in the control mode based on artificial intelligence algorithms of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0080] In order to enable those skilled in the art of the present technology to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0081] Abbreviation and Definition of Key Terms:

[0082] VCU: Vehicle Control Unit; TCU: Transmission Control Unit; ECU: Engine Control Unit;

[0083] The throttle MAP, namely the pedal map, also known as the throttle pedal characteristic, is a corresponding curve among the pedal depth, engine speed, and engine power.

[0084] Embodiment 1

[0085] An intelligent control method for a commercial vehicle automatic transmission according to the present invention, the intelligent control method includes a rule-based control mode, such as Figure 1 As shown in the transmission intelligent switching control architecture diagram based on VCU (rule-based control mode), the vehicle control unit VCU selects different throttle Maps in real time according to the vehicle operating conditions (real-time acquisition of engine speed, throttle opening, automatic / manual transmission mode status, vehicle load, transmission gear status, etc.), road conditions, and the driver's intention, and determines the operating mode of the vehicle AMT transmission according to the optimal principle.

[0086] According to the current vehicle state, road slope condition, and driver intention, perform throttle Map switching and transmission operating mode decision-making; the VCU performs intelligent switching control on the shift laws of the automatic transmission economy and power modes. At the same time, the VCU controls and switches different throttle Maps according to the current gear; the VCU makes decisions and control switches on the operating mode according to the current road slope grading state and throttle pedal opening state; ensure that the engine works as much as possible in the economic speed range and always operates in the high-efficiency working condition of the engine, and improve the power performance on the premise of ensuring economy. The engine speed is a reference quantity used to judge whether the vehicle starts, and the economic speed range of the engine can be controlled at 1000 - 1700 rpm.

[0087] Judge according to the vehicle weight, road slope, and throttle opening. The VCU performs intelligent switching control on the shift laws of the transmission economy and power modes. In the case of light load, or small road slope, or throttle opening less than the preset value, select the economic mode and send it to the TCU. Select the power mode and send it to the TCU when the three conditions of heavy load, large slope, and throttle opening greater than the preset value are simultaneously satisfied to ensure the power performance of the vehicle. The transmission TCU selects the economic shift law for shifting according to the E mode status signal sent by the VCU; the transmission TCU selects the power shift law for shifting according to the P mode status signal sent by the VCU.

[0088] By performing throttle Map switching and transmission operating mode decision-making on the current vehicle state and driver intention, parameters such as the road slope threshold S, vehicle load threshold m, and throttle opening threshold APP for E / P mode switching need to be finely calibrated according to the vehicle to meet the requirements of different market segments for vehicle performance.

[0089] As shown in Figure 2 the multi - stage throttle switching control schematic diagram based on gear ranges:

[0090] By statistically analyzing the gear distribution of currently running vehicles through big data, dividing the gear ranges according to different transmission models, it is set that: gear state 1 is the low - gear range, gear state 2 is the medium - gear range, and gear state 3 is the high - gear range.

[0091] Throttle Map state setting: Throttle Map 1 is for the low - gear range to handle the power performance during starting and climbing in mountainous areas; Throttle Map 2 is for the medium - gear range to handle high - speed climbing, taking into account power performance on the premise of economy; Throttle Map 3 is for the high - gear range to handle high - speed cruising conditions and meet economy.

[0092] When the actual gear of the transmission is higher than the low - gear range threshold, it jumps from the throttle MAP state 1 in the low - gear range to the throttle MAP state 2 in the medium - gear range;

[0093] When the actual gear of the transmission is higher than the medium - gear range threshold, it jumps from the throttle MAP state 2 in the medium - gear range to the throttle MAP state 3 in the high - gear range;

[0094] When the actual gear of the transmission is lower than the medium - gear range threshold, it jumps from the throttle MAP state 2 in the medium - gear range to the throttle MAP state 1 in the low - gear range;

[0095] When the actual gear of the transmission is lower than the high - gear range threshold, it jumps from the throttle MAP state 3 in the high - gear range to the throttle MAP state 2 in the medium - gear range.

[0096] Based on the premise that the VCU of the present invention judges the driving intention, different throttle MAPs are selected according to the operating conditions of different gears. Throttle Map 1 is switched for gear state 1, Throttle Map 2 is switched for gear state 2, and Throttle Map 3 is switched for gear state 3, taking into account both power performance and economy, and improving the driving performance of the whole vehicle.

[0097] As shown in Figure 3 the schematic diagram of the road slope grading state judgment and jump of the present invention:

[0098] Road slope state 1: flat road;

[0099] Road slope state 2: gentle slope;

[0100] Road slope state 3: steep slope.

[0101] Principle of road slope grading state judgment and jump:

[0102] When the slope is greater than S1 and remains greater than the time threshold, it jumps from road slope state 1 to road slope state 2;

[0103] When the slope is less than or equal to S1 and remains greater than the time threshold, it jumps from road slope state 2 to road slope state 1;

[0104] When the slope is greater than S2 and remains greater than the time threshold, it jumps from road slope state 2 to road slope state 3;

[0105] When the slope is less than or equal to S2 and remains greater than the time threshold, it jumps from road slope state 3 to road slope state 2;

[0106] When the slope is greater than S2 and remains greater than the time threshold, it jumps from road slope state 1 to road slope state 3.

[0107] Throttle opening state setting:

[0108] Throttle opening state 1 is greater than the throttle opening APP2 under gentle slope;

[0109] Throttle opening state 2 is less than or equal to the throttle opening APP2 under gentle slope;

[0110] Throttle opening state 3 is greater than the throttle opening APP1 under steep slope;

[0111] Throttle opening state 4 is less than or equal to the throttle opening APP1 under steep slope.

[0112] The rule-based control method defaults to the economic mode E, and it continuously judges the vehicle load threshold, road slope threshold, and throttle pedal opening threshold.

[0113] The judgment conditions for the transmission operation mode to switch from the economic mode E to the power mode P are as follows:

[0114] 1) When the vehicle load is greater than the set threshold m, the vehicle stays in road slope state 2 for more than the set time threshold, and the throttle opening state 1 stays for more than the set time threshold, after all three conditions are met simultaneously, the transmission operation mode switches from the economic mode E to the power mode P;

[0115] 2) When the vehicle load is greater than the set threshold m, the vehicle stays in road slope state 3 for more than the set time threshold, and the throttle opening state 3 stays for more than the set time threshold, after all three conditions are met simultaneously, the transmission operation mode switches from the economic mode E to the power mode P.

[0116] Throttle opening state 1 is greater than the throttle opening APP2 under gentle slope;

[0117] Throttle opening state 3 is greater than the throttle opening APP1 under steep slope;

[0118] Throttle opening state 4 is less than or equal to the throttle opening APP1 under steep slope.

[0119] The judgment conditions for the transmission operation mode to switch from the power mode P to the economy mode E are as follows:

[0120] 1) When the vehicle load is less than or equal to the set threshold m, switch from the power mode P to the economy mode E;

[0121] 2) When the vehicle load is greater than the set threshold m and the holding time in the road slope state 1 is greater than the set time threshold, switch from the power mode P to the economy mode E;

[0122] 3) When the vehicle load is greater than the set threshold m, the holding time in the road slope state 2 is greater than the set time threshold, and the holding time in the throttle opening state 2 is greater than the set time threshold, switch from the power mode P to the economy mode E;

[0123] 4) When the vehicle load is greater than the set threshold m, the holding time in the road slope state 3 is greater than the set time threshold, and the holding time in the throttle opening state 4 is greater than the set time threshold, switch from the power mode P to the economy mode E.

[0124] Embodiment 2

[0125] An intelligent control method for a commercial vehicle automatic transmission according to the present invention includes a rule-based control mode and an artificial intelligence algorithm-based control mode. Each time the vehicle is powered on and started, it first enters the rule-based control mode, and automatically switches to the artificial intelligence algorithm-based control mode after the vehicle has accumulated 200 kilometers of driving after startup; The intelligent switching control flowchart of the commercial vehicle automatic transmission operation mode of the present invention is as Figure 4 shown. State machine A is the rule-based control mode, and state machine B is the artificial intelligence algorithm-based control mode. After the transmission EP intelligent switching is activated, when the vehicle has accumulated 200 kilometers of driving after startup, the artificial intelligence algorithm-based control mode intervenes, and the control of state machine A is switched to state machine B, realizing automatic control.

[0126] The control method based on the artificial intelligence algorithm is that after the driving style recognition APP learns using the vehicle operation data, the APP issues a driving style label. The aggressive driving style label corresponds to switching to the power mode P, and the general and gentle driving style labels are switched to the economy mode E, realizing the adaptive control of the gearbox operation mode.

[0127] An intelligent control method for a commercial vehicle automatic transmission according to the present invention,

[0128] Figure 5 is the development process of the driving style recognition algorithm in the control mode based on the artificial intelligence algorithm of the present invention. The driving style is recognized according to the past vehicle operation data, and a real-time driving style recognition algorithm based on machine learning is developed. Data clustering analysis is carried out based on the vehicle operation data. The main implementation methods are as follows:

[0129] S1, Data collection:

[0130] First, formulate a data collection route covering different road grades such as urban roads, highways, national roads, mountainous areas, and hilly areas as a driving cycle (acceleration ratio, deceleration ratio, constant speed ratio, idling ratio), and identify the road type through the distribution of vehicle speed, slope, and gear operation.

[0131] Secondly, select drivers. Choose drivers with three styles: aggressive, mild, and average. Collect the driving data of these drivers on the formulated driving cycle, and perform data cleaning and data slicing. The data differences in different driving scenarios will correspondingly adjust the data cleaning and slicing.

[0132] Data cleaning processes noise, anomalies, and missing values to ensure data quality. Smooth noise is removed by simple moving window averaging and low-pass filtering to remove high-frequency noise. Anomaly detection sets thresholds based on vehicle physical knowledge and combines data from multiple sensors to judge reasonableness; missing value processing is divided into small-segment and large-segment missing values. Small-segment missing values are filled using linear interpolation or forward filling, and large-segment missing values directly remove the affected time periods.

[0133] Design different slicing rules for different scenarios. There are three methods for data slicing. The first is to use a fixed time window as a segment. For example, every 30 seconds of high-speed driving is a segment, which is suitable for steady-state analysis. The segment for national road driving can be shortened to 20 seconds; the second is event-driven. Define rules for events such as hard acceleration, hard braking, and sharp turns, and extract 5 seconds of data before and after the event; the vehicle speed is relatively high and changes less during high-speed driving, while during national road driving, there are frequent starts and stops, and more hard accelerations and hard brakings. The third is driving state segmentation. Based on the idling, accelerating, decelerating, and constant speed states set by the driving cycle, segment based on state change points, such as from acceleration to constant speed.

[0134] After data processing, comprehensively score the driver's driving behavior within this driving cycle. Set a basic score according to the distribution of acceleration, braking, turning, lane changing, steady-state driving, idling, and unreasonable use of air conditioning in the driving data, and then multiply by the corresponding weight coefficients according to the occurrence frequency and other factors to obtain a comprehensive score. This comprehensive score is an important basis for the selection of the subsequent clustering algorithm;

[0135] S2, Feature engineering:

[0136] First, extract the mathematical features such as the mean, variance, maximum, and minimum of the samples in different scenarios as basic features. To avoid the influence between different quantities, standardize the features. In terms of feature selection, first delete the low-variance features extracted, and secondly, through the two-sample t-test, select the features with large differences in different comprehensive driving styles. Finally, delete the redundant features through correlation analysis. Through the above series of operations, the collected data are made into multiple separate small samples for clustering analysis.

[0137] S3. Clustering analysis:

[0138] Since the aggressiveness of driving style is a difficult-to-objectively evaluate, it basically relies on subjective experience to add labels. However, the workload of adding labels to big data is huge, and the accuracy of adding labels is difficult to evaluate. Therefore, first regard the driving style recognition problem as an unsupervised learning problem, collect a large amount of driving data, perform offline analysis on the data, and use a clustering algorithm to perform clustering analysis on the sample data, and add corresponding labels according to the specific results, which can greatly reduce the workload of algorithm development. Here, the K-means clustering method without PCA is used for clustering, and the clustering result is used as a sample label.

[0139] Currently, the common clustering algorithms mainly include K-means clustering, Gaussian mixture clustering, hierarchical clustering, density clustering, and spectral clustering. The patent mainly focuses on K-means clustering and Gaussian mixture clustering. Through the analysis of the clustering results, it is found that the results obtained by the two methods are close. Due to the large amount of data, the K-means clustering method without PCA has a faster convergence speed and higher timeliness.

[0140] S4. Classification algorithm development: Due to the influence of external conditions, it is difficult for a driver to maintain a fixed driving style throughout the entire driving cycle. Therefore, it is impossible to classify the driving style of the driver throughout the entire driving cycle as aggressive, normal, or mild with 100% certainty. After adding labels to the samples through cluster analysis, the labeled samples are used to train the classification algorithm. Here, a support vector machine, a generalized linear classifier that classifies data according to the supervised learning method, is selected. Relevant features such as vehicle speed, longitudinal and lateral acceleration, acceleration, and acceleration pedal change rate are input into the classification algorithm. The algorithm training can be achieved by using an m-file script. The distance of a sample point to a near-overclock operation can itself reflect the degree of aggressiveness of the sample point. The driving style is no longer three isolated categories (aggressive, mild, normal), but a linear scoring of the degree of aggressiveness. The distance of an aggressive sample to the aggressive hyperplane is higher than that of a normal sample, and the distance of a normal sample to the aggressive hyperplane is higher than that of a mild sample. After the algorithm training is completed, the trained algorithm is integrated into Simulink through the matlab function module to achieve the model development of the algorithm. After the model is built, the model is generated into C++ code through Embedded Coder to produce a driving style recognition APP. The driving style APP finally calculates and outputs the driving style label (aggressive, mild, normal).

[0141] The above description is only an example display of the embodiments of the present invention and does not impose any formal restrictions on the present invention. The protection scope of the present invention is subject to the claims and is not limited by the above specific embodiments. Any simple modification, equivalent change, or modification based on the technical essence of the present invention to the above embodiments belongs to the protection scope of the present invention.

Claims

1. A commercial vehicle automatic transmission intelligent control method based on VCU architecture, characterized by: The intelligent control method includes a rule-based control mode, which performs throttle map switching and transmission operation mode decision-making according to the current vehicle state, the current vehicle load, the road slope and the driver's intention. The VCU intelligently switches and controls the transmission economy and power mode shifting rules, and at the same time, the VCU controls and switches the throttle map according to the current gear position; the VCU makes decisions and controls the switching of the operation mode according to the current road slope classification state and the accelerator pedal opening state; ensures that the engine works in the economic speed range as much as possible, always runs in the engine's high-efficiency working condition, and improves the power under the premise of ensuring economy; The specific steps include: After the transmission E / P intelligent switching is activated, the default is economic mode E, which determines the vehicle load threshold, road slope threshold, and accelerator pedal opening threshold in real time; The conditions for switching the transmission operating mode from the economic mode E to the power mode P are as follows: 1) When the vehicle load is greater than the set threshold m, the time maintained in the road slope state 2 is greater than the set time threshold, and the time maintained in the throttle opening state 1 is greater than the set time threshold, the transmission operation mode is switched from the economic mode E to the power mode P when the three conditions are met at the same time; 2) When the vehicle load is greater than the set threshold m, the time maintained in the road slope state 3 is greater than the set time threshold, and the time maintained in the throttle opening state 3 is greater than the set time threshold, the transmission operation mode is switched from the economic mode E to the power mode P; The conditions for switching the transmission operating mode from power mode P to economy mode E are as follows: 1) When the vehicle load is less than or equal to the set threshold m, the power mode P is switched to the economic mode E; 2) When the vehicle load is greater than the set threshold m and the time maintained in the road slope state 1 is greater than the set time threshold, the power mode P is switched to the economic mode E; 3) When the vehicle load is greater than the set threshold m, the time maintained in the road slope state 2 is greater than the set time threshold, and the time maintained in the throttle opening state 2 is greater than the set time threshold, the power mode P is switched to the economic mode E; 4) When the vehicle load is greater than the set threshold m, the time maintained in the road slope state 3 is greater than the set time threshold, and the time maintained in the throttle opening state 4 is greater than the set time threshold, the power mode P is switched to the economic mode E; Road slope classification status: Road slope state 1: flat road; Road slope state 2: gentle slope; Road slope state 3: steep slope; The slope is divided into S1 and S2. The slope less than S1 is a flat road, the slope greater than S2 is a steep slope, and the slope between S1 and S2 is a gentle slope. Set different throttle thresholds APP for steep slopes and gentle slopes, where the throttle threshold for steep slopes is APP1 and the throttle threshold for gentle slopes is APP2; Throttle opening state setting: The throttle opening state 1 is greater than the throttle opening APP2 on a gentle slope; Throttle opening state 2 is less than or equal to throttle opening APP2 on a gentle slope; The throttle opening state 3 is greater than the throttle opening APP1 under the steep slope; The throttle opening state 4 is less than or equal to the throttle opening APP1 on a steep slope.

2. The intelligent control method for commercial vehicle automatic transmission according to claim 1, characterized in that: S1 is 3%, S2 is 7%, and the slope unit is percentage.

3. The intelligent control method for commercial vehicle automatic transmission according to claim 1, characterized in that: The throttle threshold APP1 for the steep slope is set to 45%, and the throttle threshold APP2 for the gentle slope is set to 65%.

4. The intelligent control method for commercial vehicle automatic transmission according to claim 1, characterized in that: The VCU controls the throttle map according to the current gear position, including: Based on the premise of judging the driving intention through VCU, different throttle MAPs are selected according to the operating conditions of different gears. Gear state 1 switches to throttle Map1, gear state 2 switches to throttle Map2, and gear state 3 switches to throttle Map3, taking into account both power and economy, and improving the driving performance of the whole vehicle; Through big data statistics and analysis of the gear distribution of currently running vehicles, the gear ranges are divided according to different gearbox models: gear state 1 is the low gear area, gear state 2 is the middle gear area, and gear state 3 is the high gear area; Throttle Map status division: Map1 is the low gear area to cope with starting and mountain climbing; Map2 is the middle gear area to cope with high-speed climbing, taking into account both power and economy; Map3 is the high gear area to cope with high-speed cruising conditions to meet economy.

5. The intelligent control method for commercial vehicle automatic transmission according to claim 4, characterized in that: When the actual gear position of the transmission is higher than the low gear threshold, the throttle MAP state 1 in the low gear is switched to the throttle MAP state 2 in the middle gear, and the torque control is smoothed; When the actual gear position of the transmission is higher than the threshold of the middle gear area, the throttle MAP state 2 in the middle gear area is switched to the throttle MAP state 3 in the high gear area, and the torque control is smoothed; When the actual gear position of the transmission is lower than the threshold of the middle gear area, the throttle MAP state 2 in the middle gear area is switched to the throttle MAP state 1 in the low gear area, and the torque control is smoothed; When the actual gear position of the transmission is lower than the high gear threshold, the throttle MAP state 3 in the high gear is switched to the throttle MAP state 2 in the middle gear, and the torque control is smoothed.

6. The intelligent control method for commercial vehicle automatic transmission according to claim 1, characterized in that: The VCU makes a decision and controls the switching of the operation mode according to the current road slope classification state and the accelerator pedal opening state, including: making a decision and controlling the switching of the transmission operation mode according to the current vehicle load, the current road slope classification state and the accelerator pedal opening state; Road slope classification status judgment jump principle: When the slope is greater than S1 and remains greater than the time threshold, the road slope state 1 jumps to the road slope state 2; When the slope is less than or equal to S1 and remains greater than the time threshold, the road slope state 2 is changed to the road slope state 1; When the slope is greater than S2 and remains greater than the time threshold, the road slope state 2 is changed to the road slope state 3; When the slope is less than or equal to S2 and remains greater than the time threshold, the road slope state 3 is changed to the road slope state 2; When the slope is greater than S2 and remains greater than the time threshold, the road slope state 1 jumps to the road slope state 3.

7. The intelligent control method for commercial vehicle automatic transmission according to claim 1, characterized in that: The intelligent control method also includes a control mode based on an artificial intelligence algorithm, where each time the vehicle is powered on and started, it first enters a rule-based control mode, and automatically switches to a control mode based on an artificial intelligence algorithm after the vehicle has accumulated 200 kilometers of driving after starting; The control mode based on the artificial intelligence algorithm identifies the driving style according to the past vehicle operation data, performs data cluster analysis based on the vehicle operation data, clusters and samples the driving conditions and formulates the driving cycle, classifies the road type and driving behavior of the vehicle, identifies the road type through the distribution of vehicle speed, slope, and gear operation, extracts the characteristic vector of the driving behavior including the maximum vehicle speed, average vehicle speed, maximum lateral acceleration, and maximum acceleration pedal change rate information, performs standardization processing, and obtains three driving style models of aggressive, general, and mild through training of the classification tree classification algorithm. The aggressive driving style model is switched to the power mode, and the general or mild driving style model is switched to the economy mode.

8. The intelligent control method for commercial vehicle automatic transmission according to claim 7, characterized in that: The control mode based on artificial intelligence algorithm specifically includes the following steps: S1, sample preparation: First, a data collection route covering different road levels such as cities, highways, national roads, mountainous areas, and hills is formulated as a driving cycle sample, and the idling, acceleration, deceleration, and uniform speed distribution and proportion of the driving cycle sample are set, and the road type is identified through the distribution of vehicle speed, slope, and gear operation; The second step is driver selection. Drivers with three driving styles, namely, aggressive, moderate and general, are selected. The driving data of these drivers on the specified driving cycle samples are collected. The driving data are cleaned and sliced. After the data processing is completed, the driving behaviors of the drivers in the driving cycle samples are comprehensively scored. S2, feature engineering: First, the mean, variance, and maximum mathematical features of samples in different scenarios are extracted as basic features, and the basic features are standardized. In terms of feature selection, the extracted low-variance features are first deleted. Secondly, the two-sample t-test is used to select features with large differences in different comprehensive driving styles. Finally, redundant features are deleted through correlation analysis. The collected driving data is made into multiple separate small samples to facilitate cluster analysis in step S3. S3, cluster analysis: The driving style recognition problem is regarded as an unsupervised learning problem. First, the collected driving data is analyzed offline. The sample data is clustered using the K-means clustering method without PCA. The clustering result is used as a sample label, and the corresponding driving style label is added according to the specific result. S4, classification algorithm development: After adding labels to the samples through cluster analysis, the labeled samples are used to train the classification algorithm. The generalized linear classifier that supports vector machines to classify data in a supervised learning manner is selected. The vehicle speed, lateral and longitudinal acceleration, acceleration, and accelerator pedal change rate related features are input into the classification algorithm. The algorithm training is implemented by using m-file scripts. The distance from the sample point to the near-overclocking operation can itself reflect the aggressiveness of the sample point. The driving style is no longer divided into three isolated categories: aggressive, mild, and general, but a linear score for the degree of aggressiveness. The distance from the aggressive sample to the aggressive hyperplane is higher than that of the general sample, and the distance from the general sample to the aggressive hyperplane is higher than that of the mild sample. After the algorithm training is completed, the trained algorithm is integrated into Simulink through the matlab function module to realize the modeling development of the algorithm. After the model is built, the model is generated into C++ code through Embedded Coder to make a driving style recognition APP. The driving style APP finally calculates and outputs three labels of driving style: aggressive, mild, and general.

9. The intelligent control method for commercial vehicle automatic transmission according to claim 8, characterized in that: In step S1, The data cleaning includes noise smoothing, outlier detection and missing value processing to ensure data quality; noise smoothing removes high-frequency noise through simple sliding window averaging and low-pass filtering, outlier detection sets thresholds based on vehicle physics knowledge and judges rationality based on multiple sensor data; missing value processing is divided into small segment missing and large segment missing, small segment missing uses linear interpolation or forward filling, large segment missing directly removes the affected time period; Different slicing rules are designed for different scenarios. There are three methods for data slicing. The first method takes a fixed time window as a segment, which is suitable for steady-state analysis. The second method is event-driven, which defines rules for sudden acceleration, sudden braking, and sharp turns, and extracts 5 seconds of data before and after the event. The speed of high-speed driving is higher and changes less, while when driving on national highways, the vehicle starts and stops frequently, and there are more sudden accelerations and sudden braking. The third method is driving state segmentation, which is based on the idle, acceleration, deceleration, and constant speed states set in the driving cycle, and is segmented based on state change points.

Images