Temperature and strain measurement using artificial neural networks

To ensure the reliable and stable operation of the power communication network, comprehensive monitoring of the physical parameters of the OPGW optical cable is imperative. This includes tracking strain, temperature, and attenuation in real-time to promptly identify faults, preempt potential risks, and conduct precise performance assessments. This study employs the Brillouin scattering distributed optical fiber sensing system to continuously monitor the temperature and strain of the OPGW optical cable. Leveraging deep learning techniques, specifically the ANN algorithm, offers a departure from conventional methods reliant on curve fitting and solving complex equations. By eliminating the need for such processes, this approach markedly enhances the accuracy of temperature and strain measurements compared to traditional methods.