In areas where livestock are bred, there is a demand for accurate, real-time, and stable monitoring of ammonia concentration in the breeding environment. However, existing electronic nose systems have slow response times and limited detection accuracy. In this study, we introduce a novel solution: the bionic chamber construction of the electronic nose is optimized, and the sensor response data in the chamber are analyzed using an intelligent algorithm. We analyze the structure of the biomimetic chamber and the surface airflow of the sensor array to determine the sensing units of the system. The system employs an electronic nose to detect ammonia and ethanol gases in a circulating airflow within a closed box. The captured signals are processed, followed by the application of classification and regression models for data prediction. Our results suggest that the system, leveraging the biomimetic chamber, offers rapid gas detection response times. A high classification prediction accuracy, with a determination coefficient R² value of 0.99 for single-output regression and over 0.98 for multi-output regression predictions, is achieved by incorporating a backpropagation (BP) neural network algorithm. These outcomes demonstrate the effectiveness of the electronic nose, based on an optimized bionic chamber combined with a BP neural network algorithm, in accurately detecting ammonia emitted during livestock excreta fermentation, satisfying the ammonia detection requirements of breeding farms.

Deep neural networks have been widely applied for gas concentration estimation in low-cost gas sensor arrays; however, their dependency on sample distribution remains a significant challenge. Current research indicates that deep learning models are susceptible to sample imbalance, where their predictive accuracy is strongly influenced by the number of available samples. In sensor arrays used for monitoring indoor and outdoor harmful gas emissions, most response values remain within a normal range, while only a limited number exhibit high response values. Addressing this imbalance typically requires assigning weights to different classes or pruning datasets; however, the cross-sensitivity of sensors and the limited availability of datasets complicate this approach. In this study, we investigated the impact of sample imbalance on model performance and proposed a simulated sensor generative adversarial network (SSGAN) to generate synthetic sensor response values alongside their corresponding gas concentrations. A multiple-sensor generator was designed to produce sensor array response values paired with gas concentrations, while discriminators ensured that generated samples closely resembled real instances without being identical. Furthermore, a customized generative loss function was developed to optimize the training of the SSGAN. To validate our approach, experiments were conducted on the UCI Machine Air Quality dataset using a traditional convolutional neural network (CNN), a backpropagation neural network (BPNN), and a custom-designed attention block. The results demonstrated that SSGAN effectively reduced the average absolute error of the three target models by 4.45%, 12.06%, and 3.08%, respectively.

Ultrasonic wind speed measurements performed in complex flow fields face challenges related to low signal-to-noise ratio (SNR) and non-stationary waveform distortion. In this study, we aim to address this issue by proposing a measurement system that employs a polyvinylidene fluoride (PVDF) piezoelectric film ultrasonic transducer integrated with a microphone (MIC). In addition, a signal processing framework is proposed based on the joint optimization of variational mode decomposition (VMD) and an extended Kalman filter (EKF) and integrating cross-correlation interpolation. By leveraging the low Q-factor and wide bandwidth characteristics of the PVDF, the system achieved omnidirectional transmission and high-fidelity reception within a compact structural design. The experimental results demonstrated that the proposed VMD-reference signal-assisted EKF method enhanced the SNR by approximately 26% and reduced the wind speed measurement error by approximately 35% compared with the conventional EKF. The proposed system exhibited superior robustness and measurement linearity across a wide wind speed range of 0–60 m/s. The proposed scheme significantly enhances the accuracy and environmental adaptability of ultrasonic wind speed measurements and provides an essential theoretical basis and engineering reference for the development of precision instruments in fields such as meteorological monitoring and wind energy assessment.

To address the limitations of conventional discrete ammonia-monitoring schemes, this study proposes a closed-loop sensing–inference architecture that integrates a distributed chemical-sensing network with a physics-informed neural network (PINN) to achieve high-fidelity three-dimensional dynamic reconstruction of gas diffusion in confined environments. A distributed sensor array based on a PPy/Graphene/WO₃ ternary nanocomposite provides real-time wireless monitoring and reliable observational data streams owing to its sub-ppm detection limit and high signal-to-noise ratio. Fick’s second law of diffusion and Neumann no-flux boundary conditions are embedded in a mesh-free PINN, and rolling horizon data assimilation (RHDA) is introduced to dynamically fine-tune the network weights with high-frequency real-time observations, thereby establishing a real-time closed-loop correction between theoretical inference and the monitored environment. The proposed method achieves accurate three-dimensional concentration-field reconstruction under steady-state conditions, markedly suppresses errors and maintains robustness under unknown abrupt concentration disturbances, and mitigates the temporal divergence of conventional data-driven models during long-term purely physical extrapolation without data support. Thus, the framework combines hardware sensitivity, computational efficiency, and macroscopic physical generalization.