Evaluation of Digital Power Control Algorithms for Automotive LED Headlights using TMS320F28035 Microcontroller

Abstract: Digital power management solutions offer some distinct advantages over theiranalog counterparts and are increasingly being employed by power electronics designersthese days. The post-implementation flexibility of digital solutions is oneof the major advantages. Increasing demands on functionalities like communication,remote fault monitoring and configurability have also fueled this transitionfrom analog to digital control. The possibility of implementing non-linear controlalgorithms is a major advantage of these solutions. Highly integrated analogcomponents, like analog to digital converters and comparators in modern microcontrollers,have enabled designers to decrease on-board component count andcomplexity. Digital power management solutions have limitations in performancewhen compared to analog designs, but rapid performance improvements in microcontrollers(MCUs) certainly create a bright future for digital power management.

In this project we have investigated a digital power control implementationfor switch mode DC-DC converters. The application under consideration is LEDbasedautomotive headlights. LEDs (light emitting diodes) have gained footholdin many lighting applications due to the decrease in cost per lumen. The automotiveindustry has previously employed LEDs in a number of lighting application,like back and interior lighting, and now consider a potential use in headlights.Moreover we wanted to prove the capabilities of the TMS320F28035 MCU that isdesigned for real-time control applications. The combination of two new avenuesof digital power management and LED headlights has raised a few challenges thathave been solved in this project.

First, the characteristic behavior of LEDs is different from conventional incandescentbulbs. LEDs are controlled by maintaining a constant current throughthem rather than applying a constant voltage. Switch mode power stages intendedto control LEDs inherently operate in voltage mode. Considerable modelingand implementation efforts are required to handle both these contrasting behaviors.Secondly, discrete-time models are required for MCU implementation.Existing control theory predominantly employs continuous-time models. Thesecontinuous-time models are required to be converted to discrete-time models tomake use of existing models for digital implementation. Discrete-time modelsthat are developed from scratch requires considerable effort. Third, existing testsetupsused for analog designs can not be directly used for digital designs. Considerableanalysis is required for these modifications.

The first step in the design flow is modeling; we have to model convertersfor controlling current through LEDs. Two solutions are proposed: First, existingcontinuous-time voltage mode models for converters are used and modifiedto control LEDs. Later some further modifications are made to convert them todiscrete time. Second, a new non-linear and discrete-time model is proposed forcontrolling LED current using inductor current feedback.

Later, the developed model is implemented on TMS320F28035. This MCUcontains two heterogeneous processor cores. A pre-implementation analysis iscarried out to allocate hardware resources and system bandwidth to different softwaretasks. The control loop is implemented on a so-called control-law accelerator,as it is optimized for this purpose, while useful features like graphicaluser interface and diagnostics are implemented on C28x CPU. The initial bandwidthallocation to different software tasks is verified by doing measurementsand re-allocation. The initial implementation of different software components isalso optimized to enhance performance based on this post-implementation systemanalysis.

Lastly, the implemented control algorithms are verified by performing frequencyresponse measurements. Modifications are made to existing test-setups tosuit them to needs of digital power control. Open loop and closed loop measurementsare performed under different operating conditions. These measurementsare compared with results from the model and used to lay down our final analysis.Recursive design approach is used at each design phase. Moreover previousdesign phases are revisited whenever necessary to optimize the implementation.