Control-oriented hybrid model of a small-scale refrigerated truck chamber

Refrigerated last-mile transport of goods has faced rapidly growing importance in recent years. Although hardware components underwent comprehensive improvements to fulfill increased efficiency demands, little was done regarding control strategies. Simple algorithms or restricted consideration of system parts for control design harshly limit attainable economic and ecological flexibilities provided by state-of-the-art hardware. Sophisticated model-based control schemes constitute a promising remedy but lack detailed and computationally reasonable models of the overall cooling application. This article introduces an appropriate dynamic, low-order model to overcome this issue. The mathematical description relies on first principles, features lumped parameters, and comprises temperature evolution and electrical power consumption, allowing for the assessment of system efficiency. Besides the explicit consideration of door openings, incorporating thermal capacities of the insulation walls and the cooling unit's secondary storage loop stands out. Component's switching behavior is embedded in the chosen discrete hybrid automaton modeling approach, for which 18.4 h of real-world measurement data drive parameterization and validation. An overall fit to validation data of 86.2% and 88.7% for the most significant temperature quantity and total power consumption illustrates the model's high performance and practicality for control applications, soft-sensors, and fault detection.