Leaky containers are a key issue for beverage and food manufacturers, as this affects the quality and shelf life of the products. Acoustic inline measuring systems are already available for leak testing, but they are not suitable for continuous use in harsh industrial environments. Contamination leads to clogging of the microphone protection cap and thus to measurement errors or even failure of the microphone. Undetected measurement errors can lead to consumers receiving inferior products and the manufacturer's reputation suffers. If the microphone fails completely, there is a loss of production because the microphone has to be sent in. The aim of the project is to develop a sound sensor system based on acoustic resonance analysis for inline quality testing that is particularly suitable for harsh industrial conditions. The development of an AI-based self-monitoring function for the sensor system is particularly challenging. This should detect measurement errors intelligently and independently and provide recommendations for action.