ANN-based estimation of time-dependent energy loss in lighting systems

Abstract The illuminance of a lighting system decreases over time both due to pollution on fixtures, lamps, and wall surfaces, and decreases and failures in the luminous flux of lighting components. Such decreases are not recognizable, as they occur slowly and continuously. Numerous studies have concluded that eyesight weakens due to incorrect lighting or decreases in luminous flux of lighting components over time. However, a sufficient and stable level of illuminance is obligatory for the establishment of healthy working environments. Following the installation of a lighting system, measurement of the illuminance distribution in that environment can become a tiring and time-consuming process. In this study, an artificial neural network (ANN) model is established as an alternative to these measurements and is trained to estimate the illuminance distribution in interior spaces. Thanks to an installed ANN model, real-time estimation of illuminance distribution in an environment was realized. With these estimated values, the mean illuminance in the environment was calculated, in turn allowing the depreciation multiplier of the system to be obtained. As a result, the percentage of energy in the system that was not transformed into light was determined, allowing either improvements or fundamental changes to be made to the system, thus preventing energy waste and light loss. Furthermore, ergonomic comfort conditions of the illuminated environment were kept at the desired level.