Assessment of performance and dependability in embedded control systems: Methodology and case study

Abstract

Distributed and embedded control systems play an increasing role in modern safety-critical systems, and there is a pressing need to investigate the impact of different design decisions on system performance and safety integrity. In this paper, a methodology for the measurement and estimation of such attributes is presented. The methodology integrates statistical fault-injection testing with the application of on-line, model-based performance monitoring of the embedded control system under test. The methodology is particularly suited to late-phase system testing in which "hardwarein-the-loop" (HIL) simulation techniques are employed. The methodology is illustrated in an extended case study, in which the performance and dependability of eight possible designs for an automotive control system are compared. It is concluded that the methodology is a useful adjunct to the available testing and analysis techniques for such systems.

Bandwidth-efficient burst error tolerance in TDMA-based CAN networks

“…This is thought to increase the predictability and overall reliability of the network, along with several other benefits (see, for example, [2][3] [4][7] [8]). A potential drawback with most existing time-triggered CAN implementations lies in the enforcement of single-shot message transmissions [19] [20].…”

“…Although the benefits of TDMA-based systems are numerous and have been well discussed in the literature (e.g. [2][3] [4][7] [8]), this form of media access control is also known to have several drawbacks, most notably in terms of message transmission reliability [5][14] [19]. The principal focus of the paper is upon systems implemented using the Controller Area Network (CAN) protocol [1], although the techniques readily extend to other TDMA-based industrial communication networks.…”

A Microcontroller-Based Adaptive Model Predictive Control Platform for Process Control Applications

“…This in effect reduces the latency of data transfers to negligible levels and allows for high-speed sampling rates and high capacity payload transfers of multiple simulation signals simultaneously between the ARM7 microcontroller and the computer. HIL testing has been employed in various domains, such as the aerospace industry [21], automotive applications [23], power electronics and control [24], and marine applications [25]. As discussed, the real-time HIL test-bed introduced in [20] has been employed in this paper.…”

“…HIL testing is used to lower total costs, shorten development cycles, and improve functional performance of real-time and embedded control systems. It is also an extremely useful experimental tool for exploring system behaviors in a fully controlled and generally safe environment [23]. The overall concept of HIL is that the system under test (implemented at least partially by real hardware/software) is connected through data-acquisition devices to a secondary computer, which is used to simulate the behavior of the target environment [23].…”

“…HIL simulation provides an effective technique for designing and testing of real-time and embedded control systems [20][21][22][23][24][25]. HIL testing is used to lower total costs, shorten development cycles, and improve functional performance of real-time and embedded control systems.…”