Predictive Model of ACC Speed to Enhance Engine Operating Conditions

− The ACC feature when activated augments the engine performance in real-time. This article presents a novel methodology to predict the optimal adaptive cruise control set speed profile (ACCSSP) by considering all the effecting parameters. This paper investigates engine operating conditions (EOC) criteria to develop a predictive model of ACCSSP in real-time. We developed a deep learning (DL) model using the NARX method to predict engine operating point (EOP) mapping the vehicle-level vectors (VLV). We used real-world field data obtained from Cadillac test vehicles driven by activating the ACC feature for developing the DL model. We used a realistic set of assumptions to estimate the VLV for the future time steps for the range of allowable speed values and applied them at the input of the developed DL model to generate multiple sets of EOP’s. We imposed the defined EOC criteria on these EOPs, and the top three modes of speeds satisfying all the requirements are derived for each second. Thus, three eligible speed values are estimated for each second, and an additional criterion is defined to generate a unique ACCSSP for future time steps. Performance comparison between predicted and constant ACCSSPs indicates that the predictive model outperforms constant ACCSSP.


INTRODUCTION
The introduction of automobiles into the world inculcated innovation in many aspects of engineering, including design and manufacturing (Townsend and Calantone, 2014) [1]. Engineers worldwide continuously strive to develop cutting-edge technologies to augment the riders' comfort, traffic behaviour, enhance safety and fuel economy (Katzenbach, 2015) [2]. Among the many features integrated into the vehicle, the ACC system developed by reference (Labuhn and Chundrlik, 1995) played a vital role, affecting safety and EOC [3]. The intricate concept of an ACC system is to produce controlled acceleration without disengaging the cruise in the user-defined proximity and strictly follow the user command of set speed (Marsden et.al, 2001) [4]. Also, we could conclude from the existing literature (Mahdinia et.al, 2020) that activation of ACC results in lower IFCR [5]. Therefore, activating the ACC feature for traversing long trips would augment EOC.
However, identifying the optimal ACCSSP by considering the dynamic state of the vehicle for a definite coordinate on the terrain is an unsolved, challenging task for engineers. Researchers have performed the parametric optimisation of ACC output in the existing literature by analysing the realtime data of driver behaviour, traffic congestion, terrain data, and environmental factors.

PREDICTIVE MODEL for EOP
We adopted the commonly available DL methods, NARX and LSTM, to develop predictive models involving timesensitive data (Diaconescu, 2008) [25]. (Kolachalama et.al, 2021) , compared NARX and LSTM methods using the real-time test case (2019 Cadillac XT6) and proved that the NARX method outperforms the LSTM model [24]. Hence, in this research, a similar NARX DL model is used with default training options to predict EOP as shown in Table 4.

Figure 1. Predictive model -Inputs and Outputs [5]
As mentioned in the previous section, Figure 1  Hence, we defined the line segment conjoining the predicted and ideal EOP as the EOC vector, represented in Figure 2. The magnitude of the EOC vector represents the shown in Equation 1. In the 2D plane, there is no loss of generality in ignoring the parameter IES, as it is proportional to the vehicle speed. Therefore, lower ED represents increased EOC. The prediction of ACCSSP was categorised into four steps, as described in the following sections. ) and are assumed to be equal to the previous time step. (Table 8).

Prediction of outputs-DL Model
Step 2: We estimated the input sets for future time steps (1 second -[ ]) for the AVS range (e.g., [SL-10, SL]). Thus, we generated eleven sets of inputs, and fed them into the DL model, and predicted a corresponding eleven sets of outputs (EOP's). (Table 9) 4.3. Estimation of ACC Speed values-EOC Criteria.
Step 3: We applied the EOC criteria defined in section III for the eleven predicted EOP's ( Table 9). The top six performing speed values are selected for each EOC parameter, and hence, the top three modes of speeds (EVS) are calculated for each time step (Table 10). We incorporated a similar procedure for the next ten seconds, and ACC Matrix (3X10) was developed (Table 11).

Algorithm to predict ACCSSP
Step 4: Every second has three EVS, resulting in a maximum of 3 possible ACCSSP's for 10 seconds. The following conditions are defined to identify a unique ACCSSP inspired by the Dubin path traverse problem (La Valle, 2011) [32].

Assuming the ACCSSP at
is , if the EVS is either +1, , or -1, then the highest magnitude among the three is selected as .

2.
is chosen closer to (IAS). If this results in two values, then the higher value is considered as . 3. If the eligible speeds at are neither +1, , nor -1, then = .

Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 18 October 2021
Author A series of experiments are designed, analysed and evaluated on a real-time dataset to evaluate the performance of the proposed framework.

Dataset retrieval.
We conducted this research using three test vehicles, a 2019 Cadillac XT6, a 2020 Cadillac CT5, and a 2021 Cadillac CT4, obtained from GMC. A two-step procedure was employed to retrieve the data from the vehicle CAN bus (Li et.al, 2008) [33]. We connected the hardware neoVI to the vehicle and retrieved the data retrieval using the software Vehicle Spy. This tool records data in realtime (Gallardo, 2018) and allows the user to selectively retrieve the signal data required for analysis [34]. We performed the real-time test procedure by activating the ACC feature, and approximately 1E5 time-step snippet of data was collected for each vehicle at a frequency of 10Hz, assuming a no-slip (  The test cases are developed by driving the vehicles on selected road segments covering all the arterial, state ways, and freeways scenarios. Shown in Figure 4 are the paths traversed by the Cadillac test vehicles. The properties of the six datasets used for this analysis, including the input and output parameters of the DL model, are shown in Tables 1-3. Please find the details of the predictive model in the following sections.

Prediction of EOP
The properties of the NARX model and the test cases used for training are shown in Table 4. We developed individual training networks using the DL toolbox of MATLAB for the three vehicles' test data and the predicted EOPs, as shown in Figures 5-10. Each figure consists of three parts: IET (left), IES (middle), and IFCR (right). Furthermore, each plot compares the measured data (blue) with the predicted values (orange). We validated the performance of the NARX DL model prediction using traditional statistical techniques (RMSE, FOD, SNR) to compare the actual and predicted values of EOP, as reported in Table 5. We conclude that IES follows a smooth curve from Figures 5-10, whereas IFCR and IET oscillate.  (Table 11), and Step 4 is applied to the EVS, which results in eight ACCSSP's shown in Figure 11. Thus for = 70 MPH, the predicted ACCSSP is the row vector ([71, 71, 71, 71, 72, 72, 73, 73, 74, 74] MPH) plotted in Figure  13.   We adopted a similar procedure for ten seconds and predicted ACCSSP for IAS = 70 MPH, SL = 75 MPH, with a minimum of 71 MPH and a maximum of 73 MPH ( Figure  13). The predicted and constant ACCSSP profile (70 MPH) with corresponding inputs (section 4.1) were fed into the DL model to obtain two different EOP's vectors (section 4.2) for future time steps (10 s). We applied the EOC criteria for the two EOPs whose values are in Section A: We predicted the constant ACCSSP = 70 MPH to consume 379.095 1E-8 more fuel in 10 s compared with the predicted ACCSSP. The plots of engine performance parameters are shown in Figure 18, and the area under the curve has higher magnitudes by 1.2 (ETC) and 10.2 (ESC) for the predicted ACCSSP. Please find the smoothness measure for the conformance of the two EOP's in Table 13, and Adj/R squares have similar values (conformance~ 0), whereas RMSE/SSE have lower values for predicted ACCSSP for most cases. Section B: Table 12 depicts the performance of EOC parameters for all the test cases, and it is easy to see that in most cases, the predicted ACCSSP has reduced ED and IFCR. Hence the proposed approach in this article is novel and better suits enhancing EOC and lowering the trip time. In this manuscript, we developed a novel method to predict the ACCSSP, which optimises engine performance. We considered the vector EOP reflecting engine performance and used NARX DL modelling techniques to predict the EOP by mapping the VLV. We defined EOC criteria, which reflects optimal EOP in real-time. Therefore, a unique ACCSSP for the future time-steps was generated by utilising iterative methods and satisfying the EOC criteria. The computational results obtained were satisfactory, and thus, we observed augmented EOC for the predicted ACCSSP. This novel method could also trigger a new capability in ACC controllers to deviate from the user command of set speed and produce enhanced vehicle performance. We did not include many critical points, including traffic congestion, in the model. Future work would involve developing the model by including all the affecting parameters and performing extensive validation using multiple vehicle lines at various locations and periods.