To detect the stress of steel structures and members using the existing magnetism, a magnetic stress sensing system integrating a magnetic flux induction coil, a magnetic flux measurement device, a loaded device, and data acquisition software was developed. The magnetic coupling test research was carried out for different grades of structural building and bridge steel specimens to establish the magnetic stress flux mathematical model, and the fitting equation of the magnetic flux changes with the positions of different sections of specimens was analyzed. Furthermore, a practical formula for stress detection was obtained through the experiments. Meanwhile, on these bases, the typical steel truss structure model of a Bailey beam was designed and manufactured under different working conditions, nondestructive online stress testing was carried out, and the stress of the model structure and its members was measured by strain and magnetic flux tests to obtain the curves of the test results for the stress–strain and magnetic stress flux, respectively. The results of these two methods are in good agreement with each other. The stress of the steel truss model structure was analyzed and calculated using the finite element method. The results agreed well with the experimental results from the magnetic stress sensing system—the maximum error was about 5%, which meets the requirements of engineering applications.

Traditional leakage prediction models for long-distance pipelines have limitations in effectively synchronizing spatial and temporal features of leakage signals, leading to data processing that heavily relies on manual experience and exhibits insufficient generalization capabilities. This paper introduces a novel leakage detection and localization algorithm for oil and gas pipelines, integrating wavelet denoising with a Long Short-Term Memory (LSTM)-Transformer model. The proposed algorithm utilizes pressure sensors to collect real-time pipeline pressure data and applies wavelet denoising to eliminate noise from the pressure signals. By combining LSTM’s temporal feature extraction with the Transformer’s self-attention mechanism, we construct a short-term average pressure gradient-average instantaneous flow network model. This model continuously predicts pipeline flow based on real-time pressure gradient inputs, monitors deviations between actual and predicted flow, and employs a pressure curve distance algorithm to accurately determine the leakage location. Experimental results from the Jilin-Changchun long-distance oil pipeline demonstrate that the model possesses superior leakage warning and localization capabilities. Specifically, the leakage prediction accuracy reaches 99.995%, with a leakage location error margin below 2.5%. Additionally, the model can detect leaks exceeding 0.6% of the main pipeline flow without generating false alarms during operation.

With the aim of determining the influence of the fluid–structure coupling dynamic effect of the oil and gas transmission medium and pipeline on the seismic response, an oil pipeline supported by a cable-stayed spanning structure was taken as the study object. Kinetic equations taking into account the action of oil and gas medium were studied, and a finite element model structure considering the additional-mass method and the fluid–structure coupling effect were established separately. In addition, the mechanism of the oil–gas–pipeline coupling action on the seismic response of pipeline structure was analyzed, and the results were obtained. The results show that the pipeline has a minimal seismic response at the abutment location, the seismic response gradually increases along the abutment to the main tower, and the seismic response reach is maximized at about one-fifth of the bridge platform. The seismic response of the oil and gas pipeline model structure using the additional-mass method is generally more significant than that based on the fluid–solid coupled dynamic model; moreover, the maximum displacement response differs by about 24%, and the maximum acceleration response differs by approximately 30%, indicating that the oil and gas medium has a certain viscoelastic damping effect on the seismic response of the oil pipeline, which provides a reference for the seismic response calculation theory and analysis method of cable-stayed spanning oil pipelines.