The water electrolysis based on Polymeric Electrolyte Membrane technology (E-PEM) is an interesting solution for efficient carbon-free hydrogen production. By the end of the 21st century, the contribution of hydrogen will continue to achieve significant rate in the energy mix. As there have been advances of efficient end-use technologies, hydrogen could even become the main energy carrier. Regarding diagnosis purposes, Empirical Model Decomposition (EMD) method has proven to be a versatile and efficient tool to analyze non-stationary signals and extract features from them. As a starting point of its decomposition, oscillations are considered, at a local level, as the sum of a specified number of high and low frequency contributions called Intrinsic Mode Functions (IMFs). IMFs represent the natural oscillatory mode embedded in the signal and work as the basis functions, which makes EMD a self-adaptive method. fig.1 shows the decomposition of the E-PEM current into a finite set of intrinsic mode functions. This study presents a non-intrusive tool designed to fulfill on-line diagnosis requirements. Indeed, the proposed method does not require any excitation signal or stabilization period as Electrochemical Impedance Spectroscopy-based approaches. Therefore, the electrolyzer remains continuously available, even while the diagnosis is being performed. Besides, it only requires measurement of current and has a low computational costs, which are significant economic and technical advantages. Here, EMD has been used to study the anode flow rate dynamics. Several experiments have been conducted and experimental results have demonstrated the effectiveness of the proposed diagnosis tool and its advantages compared to other methods.