Aging infrastructure is a threatening issue throughout the world. Long exposure to oxygen and moisture causes premature corrosion of reinforced concrete structures leading to the collapse of the structures. As a consequence, real-time monitoring of civil structures for rust becomes critical in avoiding mishaps. Muon scattering tomography is a non-destructive, non-invasive technique which has shown impressive results in 3D imaging of civil structures. This paper explores the application of advanced machine learning techniques in identifying a rusted reinforced concrete rebar using muon scattering tomography. To achieve this, we have simulated the performance of an imaging prototype setup, designed to carry out muon scattering tomography, to precisely measure the rust percentage in a rusted rebar. We have produced a 2D image based on the projected 3D scattering vertices of the muons and used the scattering vertex density and average deviation angle per pixel as the distinguishing parameter for the analysis. A filtering algorithm, namely the Pattern Recognition Method, has been employed to eliminate background noise. Since this problem boils down to whether or not the material being analyzed is rust, i.e., a classification problem, we have adopted the well-known machine learning algorithm Support Vector Machine to identify rust in the rusted reinforced cement concrete structure. It was observed that the trained model could easily identify 30% of rust in the structure with a nominal exposure of 30 days within a small error range of 7.3%.
The CMS detector, including its muon system, has been operating at the CERN LHC in increasingly challenging conditions for about 15 years. The muon detector was designed to provide excellent triggering and track reconstruction for muons produced in proton–proton collisons at an instantaneous luminosity ( $$\mathcal {L}$$ ) of $$1 \times 10^{34}$$ cm $$^{-2}$$ s $$^{-1}$$ . During the Run 2 data-taking period (2015–2018), the LHC achieved an instantaneous luminosity of twice its design value, resulting in larger background rates and making the efficient detection of muons more difficult. While some backgrounds result from natural radioactivity, cosmic rays, and interactions of the circulating protons with residual gas in the beam pipe, the dominant source of background hits in the muon system arises from proton–proton interactions themselves. Charged hadrons leaving the calorimeters produce energy deposits in the muon chambers. In addition, high-energy particles interacting in the hadron calorimeter and forward shielding elements generate thermal neutrons, which leak out of the calorimeter and shielding structures, filling the CMS cavern. We describe the method used to measure the background rates in the various muon subsystems. These rates, in conjunction with simulations, can be used to estimate the expected backgrounds in the High-Luminosity LHC. This machine will run for at least 10 years starting in 2029 reaching an instantaneous luminosity of $$\mathcal {L} = 5 \times \text {10}^\text {34}\,\text {cm}^\text {-2}\,\text {s}^\text {-1}$$ and increasing ultimately to $$\mathcal {L} = 7.5 \times \text {10}^\text {34}\,\text {cm}^\text {-2}\,\text {s}^\text {-1}$$ . These background estimates have been a key ingredient for the planning and design of the muon detector upgrade.