Ultrasound serves as an alternative to traditional communication methods in environments with considerable electromagnetic shielding and interference. Ultrasonic-guided waves, such as Lamb waves, demonstrate advantageous transmission properties in plate-like structures, allowing for long-distance propagation with minimal energy loss. This article introduces a noncontact data transmission technique using air-coupled leaky Lamb waves. Ultrasound signals are emitted and collected by airborne ultrasound transducers. Wave conversion and the dispersion interference of Lamb waves contribute to nonlinear effects in air-coupled leaky Lamb wave communication. To address the nonlinear interference present in the received signal, the receiver uses a deep neural network for effective signal decoding. Transmission experiments in real-world conditions were performed on a plate-like structure using a pitch-catch configuration, evaluating three modulation techniques: amplitude-shift keying, frequency-shift keying, and binary phase-shift keying (BPSK). Among these methods, BPSK exhibited the most effective anti-interference performance. The actual communication system platform successfully achieved a data transmission rate of 50 kbps, with a bit error rate recorded at less than 0.2$\%$.

Plate structures are widely adopted in many industries and instruments. Guided ultrasonic wave communication has unique advantages, as it can transmit over long distances in plates unaffected by electromagnetic interference. This is particularly beneficial in scenarios where electromagnetic waves are shielded or severely influenced, and where wired communication is difficult to deploy. Meanwhile, the main challenges in air-coupled guided ultrasonic wave communication are wave conversion and multimodal nonlinear interference. Motivated by these issues, this paper proposes an air-coupled Lamb waves based non-contact communication system, which uses deep neural networks to decode received signals and address nonlinear interference during wave propagation. Additionally, to address the issue of increased bit error rates (BER) caused by transmission channel variations, a strategy (Adaptive-BPSK) combining a feedback mechanism and binary phase-shift keying (BPSK) is proposed, enhancing communication stability and robustness. It is noteworthy that traditional cross-correlation methods cannot effectively decode in this system, but deep neural network based decoding can achieve a BER of 0.19%.

Travel time estimation plays a core role in intelligent traffic systems, as people or smart vehicles can choose a better travel route in advance, while local authorities can make urban traffic planning based on it. The paper proposes a dual traffic network topology coupled with improved delay models to estimate travel time in urban traffic system. The structure of the system is demonstrated by the dual traffic network (DTN) topology. It hires nodes to representjoint points of links and intersections; it also has two kinds of edges-links and turning cases of intersections. The BPR model is improved by concerning the influence of pedestrians and the lane width, and the HCM model is improved by adding travel time at intersections and considering three different turning cases to match with the DTN topology. The proposed methodology is evaluated by a comparison and an experiment in Changzhou, China. The error is greatly reduced, even though the degree of saturation exceeds 0.72. This proposed estimation methodology can improve the estimation accuracy significantly, especially in high degree of saturation cases.

In this paper, the main form of energy consumption of typical compressed air system is introduced, to analyze basic potentials of energy saving. Then the current situation of energy saving in compressed air systems is also given. Four major energy saving measures according to present problems of energy saving in compressed air systems and prospects of energy saving of air system are proposed.

Energy-saving of compressed air system was very important for the sustainable development of enterprises, which could be achieved though fast and accurate load forecasting. In this paper, according to the distribution rules and characteristics of 24 hours compressed air supply, the 24h compressed air flow demand model was firstly built with least square support vector machine (LSSVM). In order to avoid the long time consumption for determining the model parameters in the traditional cross validation method, Bayesian evidence framework was selected to train the parameters, and then identified and optimized them. Meanwhile, Nyström low- rank approximation decomposition algorithm was used to accelerate kernel matrix decomposition process. Though the experimental verification with real industrial data, the modeling time of LSSVM within Bayesian evidence framework is reduced to 1/20 compared with traditional cross-validation method; in the contrast with Practical Swarm Optimization (PSO), the modeling time is reduced to 80%, and the prediction accuracy can increase 14.3%, proving this method quite suitable for fast and accurate forecasting for large flow compressed air load.