Examples of data science utilization in the construction and social infrastructure sector! Case study on improving inspection efficiency.
We will introduce a case study of improvement in abnormal detection of overhead wires using deep learning. At Tokyo Electric Power Grid, the inspection and maintenance of overhead wires involved humans visually identifying abnormalities from aerial footage. The visual inspection process required the aerial video to be played back at one-tenth speed for manual checking, which was very costly and also had issues with accuracy due to potential oversights leading to missed detections. To address this, a model was developed using deep learning to determine abnormalities and normal conditions from image data. By quantifying and visualizing the "abnormality" of the overhead wires, AI was able to identify areas that required human visual confirmation, thereby achieving a reduction in the costs associated with visual inspections.
Inquire About This Product
basic information
【Case Overview】 ■Industry: Social Infrastructure ■Business: Operations and Maintenance ■Challenge: Improvement of Inspection Efficiency ■Analytics and AI Solution - Developed a deep learning model to determine anomalies/normalcy from image data - Input captured image data to quantify/visualize the degree of abnormality in overhead wires and create reports - By inspecting only the locations with high abnormality scores, significantly reduced the labor involved in visual inspections 【Effects】 ■Reduction in costs of visual confirmation ■Initially aimed for a 50% reduction in inspection work time, with a goal of 80% reduction by 2021, progressing in stages *For more details, please refer to the PDF document or feel free to contact us.
Price range
Delivery Time
Applications/Examples of results
For more details, please refer to the PDF document or feel free to contact us.
Company information
We provide comprehensive support for our customers' DX promotion and data utilization. Our support includes analysis by data scientists and engineers from academic backgrounds, assistance with product utilization, and the establishment of data science organizations within our customers' companies, tailored to meet their needs. Please feel free to contact us if you have any requests.