Kurita Water Industries has been granted a patent for an improved method to predict the likelihood of leaks in underground pipes. The method uses data-driven techniques such as classification, regression, and machine learning to prioritize pipe replacement. By inputting and processing pipe data, potential features are identified and ranked for their importance. These features are then used to create a model that predicts the likelihood of failure for each pipe in the network. The method also includes graphical depictions of pipe failure likelihood over time to guide pipe replacement decisions. GlobalData’s report on Kurita Water Industries gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
According to GlobalData’s company profile on Kurita Water Industries, Reverse osmosis and nano-filtration was a key innovation area identified from patents. Kurita Water Industries's grant share as of September 2023 was 20%. Grant share is based on the ratio of number of grants to total number of patents.
The patent is granted for a method of prioritizing pipe replacement based on predicting pipe leaks in underground pipes
A recently granted patent (Publication Number: US11720816B2) describes a prioritized pipe replacement method that incorporates predicting pipe leaks in an underground network of pipes. The method involves receiving a set of variables that potentially affect pipe leakage, selecting a subset of these variables, and building a mathematical model using machine learning. This model is then used to predict the likelihood of pipe segments leaking, even for pipes that have never leaked before. A graphical depiction of the pipes and their likelihood of failure over a selected future time period is formed, which guides the prioritization of pipe replacement jobs. The method also includes carrying out pipe replacement, including for pipes that have never leaked, based on this graphical depiction.
The patent also mentions additional details about the method. It states that the selection of variables involves building an initial model based on the full set of variables and evaluating the importance associated with each variable. This evaluation can be based on metrics such as the Gini coefficient or information gain coefficient. The method may also assign variables to predetermined categories and select a limited number of variables from each category for inclusion in the subset.
The patent highlights the use of a large number of variables, with the first set containing at least 60 variables and potentially exceeding 500 variables. However, the second set, which is used for building the model, consists of less than 60 variables and potentially less than 50 variables. The method may also involve generating a portion of the variables through geospatial analysis.
Furthermore, the patent mentions the use of data from different sources, such as other utility companies or an integrated national utility database, for building the model. The method can also incorporate historical data on pipe breaks to calibrate the prediction results. The fluid carried by the pipes can be various types, including fresh water, waste water, sea water, recycled water, brackish water, storm water, drinking water, steam, compressed air, oil, and natural gas.
In addition to the method, the patent describes a system for prioritized pipe replacement. This system includes a database for storing the variables related to pipe leakage and a processing system that automatically selects variables, builds a model, predicts likelihood of pipe segments leaking, forms a graphical depiction, and displays it for guiding pipe replacement prioritization.
Overall, this patent presents a method and system that utilize machine learning and a large number of variables to predict pipe leaks and prioritize pipe replacement, even for pipes that have never leaked before.
To know more about GlobalData’s detailed insights on Kurita Water Industries, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
