A ppb-Level Ammonia Detection System Based on TD-FD(HHT)–CNN-TL Deep Learning Model

The recent exponential growth in the utilization of the amino fertilizer has resulted in the significant release of ammonia ( $\text {NH}_{{3}}$ ) during its hydrolysis, causing serious safety risks or environmental pollution, thereby accurate $\text {NH}_{{3}}$ detection is imperative under this condition. In this article, a novel dual-branch time-domain (TD)–frequency-domain (FD) Hilbert-Huang transform (HHT)–convolutional neural network (CNN)–transfer learning (TL) deep learning model combined with tunable diode laser absorption spectroscopy (TDLAS) is proposed to detect ammonia, where (FD) branch information obtained by HHT are extracted through 2-D CNN and TD branch features are extracted by the corresponding 1D-CNN. Subsequently, this dual-branch deep learning model is initially trained by plenty of simulation datasets, and then the pretrained model parameters are further fine-tuned by TL with finite experimental datasets. The final test results show that the system provides reliable $\text {NH}_{{3}}$ detection with an average absolute error of 0.76 ppm and achieves the minimum detection limit of 0.03 ppm via the Allan variance analysis. Hence, it can be concluded that the system holds significant potential for $\text {NH}_{{3}}$ detection applications, and the proposed model introduces an innovative idea for designing neural networks in subsequent spectral signal analysis.

I. Introduction

Ammonia (NH3) is a toxic volatile nitrogen compound with an irritating odor that serves a crucial function in amino fertilizer production, including urea and ammonium nitrate. According to the Food and Agriculture Organization of the United Nations, food demands of the growing human population have recently caused an exponential increase in global fertilizer utilization, among which the amino fertilizer may release massive NH3 during its hydrolysis in soil [1], [2]. Nevertheless, exposure to high levels of NH₃ poses severe health risks to both humans and animals. As recommended by the American Conference of Governmental Industrial Hygienists (ACGIHs), the long-term exposure limit value (TLV-TWA) for NH₃ concentrations in air is 25 ppm [3]. In addition, the excessive emission of NH₃ can result in soil acidification, water eutrophication, and the formation of particulate matter in the atmosphere [4], [5]. Therefore, accurate NH₃ detection is essential for protecting human health and the environment.