# US 11,720,816 B2 · Predicting pipe failure > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,720,816 B2 - Document ID: US11720816B2 - Status: Granted - Kind: B2 - Application number: 16/365,466 - Filed: 2019-03-26 - Published: 2019-10-03 - Granted: 2023-08-08 - Earliest claimed: 2018-03-28 - Assignees: Fracta - Applicants: Fracta - Inventors: Daichi Yoshikawa; Takashi Kato - Web page: https://patentgrep.com/patent/US11720816B2 ## CPC - G06N 20/00: Machine learning - G01M 3/00: Investigating fluid-tightness of structures - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 30/00: Computer-aided design [CAD] - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/20: Ensemble learning - G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202) - G06Q 10/0631: Resource planning, allocation, distributing or scheduling for enterprises or organisations - G06Q 50/06: Energy or water supply - G06F 16/787: using geographical or spatial information, e.g. location - G06F 2113/14: Pipes - G06Q 10/00: Administration; Management - G06Q 10/06311: {Scheduling, planning or task assignment for a person or group} - G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders - G06Q 30/012: Providing warranty services - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract An improved solution accurately predicts of an underground pipe's likelihood of leaking. A data-driven approach uses a combination of information acquisition, classification, regression and/or machine learning. The replacement of underground pipes can be prioritized. Pipe data is inputted and processed. Potential features within the cleaned data is used in pipe life of failure prediction models. The importance of the potential features is ranked. The most important features are extracted and applied to a likelihood of failure model that is created based on historical data and machine learning. Future likelihood of failure for each pipe in the network of pipes can be predicted using the model. ## Claims ### Claim 1 A prioritized pipe replacement method, including for pipes that have never leaked, that incorporates predicting pipe leaks in a network of underground pipes for carrying a fluid consumers, including for pipes that have never leaked, the method comprising: receiving by a computer system a first set of variables potentially affecting leakage of the pipes, the first set of variables being at least 60 variables; wherein at least some of the variables of the first set include data pertaining to pipes which have never leaked; selecting automatically by the computer system a second set of variables being a subset of the first set of variables; building a mathematical model using machine learning based on the second set of variables; predicting likelihood of pipe segments leaking based on the model, including for pipes that never have leaked; and forming a graphical depiction of the pipes and of likelihood of failure thereof over a selected future time period of prioritization of pipe replacement jobs; and carrying out pipe replacement, including for pipes that have never leaked, consistent with and guided by said graphical depiction. ### Claim 2 (depends on 1) A method according to claim 1 wherein the selecting includes building an initial model based on the first set of variables and evaluating importance associated with each variable in the first set based said initial model. ### Claim 3 (depends on 2) A method according to claim 2 wherein the evaluating importance is based on evaluating a Gini coefficient or information gain coefficient. ### Claim 4 (depends on 1) A method according to claim 1 wherein at least some of the first set of variables are assigned to predetermined categories and selecting includes selecting no more than predetermined number of variables in each category to be included in the second set. ### Claim 5 (depends on 1) A method according to claim 1 wherein the number of variables in the first is at least 100. ### Claim 6 (depends on 5) A method according to claim 5 wherein the number of variables in the first set is at least 500. ### Claim 7 (depends on 1) A method according to claim 1 wherein the number of variables in the second set is less than 60. ### Claim 8 (depends on 7) A method according to claim 7 wherein the number of variables in the first set is at least 300 and the number of variables in the second set is less than 50. ### Claim 9 (depends on 1) A method according to claim 1 wherein a portion of the first set of variables are generated by geospatial analysis. ### Claim 10 (depends on 1) A method according to claim 1 wherein said network of pipes is for a first customer utility company and said building the model includes using data from a second customer utility company. ### Claim 11 (depends on 1) A method according to claim 1 wherein said building the model includes using data from an integrated national utility database. ### Claim 12 (depends on 1) A method according to claim 1 wherein said building the model is based at least in part on a plurality of models each being based on data from different time intervals. ### Claim 13 (depends on 1) A method according to claim 1 wherein said fluid is fresh water. ### Claim 14 (depends on 1) A method according to claim 1 wherein said fluid is selected from a group consisting of: waste water, recycle water, brackish water, storm water, sea water, drinking water, oil, natural gas, steam and compressed air. ### Claim 15 (depends on 1) A method according to claim 1 wherein said predicting includes predicting likelihood of pipe segments leaking over a future time interval wherein the prediction result is calibrated based in part on a number of breaks known to have occurred over a similar length prior time interval. ### Claim 16 (depends on 1) A method according to claim 1 wherein at least some of the first set of variables are assigned to predetermined categories and the method further comprises evaluating a normalized importance associated with each of the predetermined categories. ### Claim 17 (depends on 1) A method according to claim 1 wherein the predicting of pipes segments leaking is made for a greater number of years in the future than the number of years for which a leak history of pipes in the network is available. ### Claim 18 A system for prioritized pipe replacement, including of pipes that have never leaked, incorporating predicting pipe leaks including for pipes that have never leaked, in a network of underground pipes for carrying fluid to consumers, the system comprising: a database that stores a first set of variables relating to leakage of the pipes, the first set of variables being at least 60 variables; wherein at least some of the variables of the first set include data pertaining to pipes which have never leaked; and a processing system configured to automatically: select a second set of variables being a subset of the first set of variables; build a model using machine learning based on the second set of variables; predict likelihood of pipes segments leaking based on the model; form a graphical depiction of the pipes in said network and of likelihood of failure thereof over a selected future time period and of prioritization of pipe replacement jobs; and display said graphical depiction of pipes in said network and of likelihood of failure thereof over the selected future time and prioritization of pipe replacement jobs for carrying out pipe replacement, and prioritize the replacement of pipes, including of pipes that have never leaked, consistent with and guided by said graphical depiction. ### Claim 19 (depends on 18) A system according to claim 18 wherein the processing system selects the second set by building an initial model based on the first set of variables and evaluating importance associated with each variable in the first set based said initial model. ### Claim 20 (depends on 18) A system according to claim 18 wherein at least some of the first set of variables are assigned to predetermined categories and no more than predetermined number of variables in each category are selected to be included in the second set. ### Claim 21 (depends on 18) A system according to claim 18 wherein the number of variables in the first set is at least 500. ### Claim 22 (depends on 18) A system according to claim 18 wherein the number of variables in the second set is less than 50. ### Claim 23 (depends on 18) A system according to claim 18 wherein said fluid is selected from a group consisting of: fresh water, waste water, sea water, recycled water, brackish water, storm water, drinking water, steam, compressed air, oil and natural gas.