# US 2025/0190877 A1 · Processing data for 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 2025/0190877 A1
- Document ID: US20250190877A1
- Status: Published application
- Kind: A1
- Application number: 19/050,064
- Filed: 2025-02-10
- Published: 2025-06-12
- Earliest claimed: 2018-03-28
- Assignees: Fracta
- Applicants: Fracta
- Inventors: Daichi Yoshikawa; Matti Salomon Kakkori; Julio Daniel Buendia
- Web page: https://patentgrep.com/patent/US20250190877A1

## 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

A system receives and automatically transforms utility pipe attribute data and pipe break data. The missing and/or incorrect entries in the pipe attributes and/or break 5 data is automatically identified and correct values for these entries are is automatically imputed to generate improved datasets of the pipe attribute data and break data. The improved data can be used to build a model with machine learning. Predictions of future likelihood of failure for pipe sections in a network of pipes can be made based on the model. A national database can be created that is filled with environmental data that has been transformed, optimized, merged, and imputed. The national database can be used for many customers to save computational costs. The national database can be used to build the failure prediction model for utility companies thereby saving computational costs.

## Claims

### Claim 1

A method for improving pipe data relating to networks of underground pipes or carrying a fluid to consumers, the method comprising:
receiving by a computer system a set of pipe data that includes a plurality of pipe attributes for one or more of said networks of underground pipes;
identifying with the computer system one or more pipes in at least one of said networks for which one or more pipe attributes is missing or incorrect;
automatically generating imputed data for the one or more pipe attributes resulting in an improved set of pipe data; and
managing one or more aspects of one or more of said networks of underground pipes based on the improved set of pipe data.

### Claim 2 (depends on 1)

A method according to claim 1 where said automatically generating imputed data includes a geolocation transfer process that uses one or more sources selected from a group consisting of: GPS, address, and geocode.

### Claim 3 (depends on 2)

A method according to claim 2 wherein the set of pipe data includes pipe break data at least some of which includes locations for pipe breaks but not specific pipe sections for said breaks, and said geolocation transfer process assigns pipe sections to at least some of said pipe breaks that are not the closest pipe sections to the respective locations for the pipe breaks.

### Claim 4 (depends on 1)

A method according to claim 1 wherein said automatically generating imputed data includes using parcel data relating to a geographic position that corresponds to said one or more pipes.

### Claim 5 (depends on 1)

A method according to claim 1 wherein said one or more pipe attributes is missing or incorrect includes year of installation for a plurality of underground pipe sections, and said automatically generating imputed data includes correction and/or imputation of said missing or incorrect installation years for at least some of the underground pipe sections.

### Claim 6 (depends on 1)

A method according to claim 1 wherein said one or more pipe attributes is missing or incorrect pipe material for a plurality of underground pipe sections, and said automatically generating imputed data includes correction and/or imputation of said missing or incorrect pipe material for at least some of the underground pipe sections.

### Claim 7 (depends on 1)

A method according to claim 1 wherein said one or more pipe attributes is missing or incorrect pipe diameter for a plurality of underground pipe sections, and said automatically generating imputed data includes correction and/or imputation of said missing or incorrect pipe diameter for at least some of the underground pipe sections.

### Claim 8 (depends on 1)

A method according to claim 1 wherein said automatically generating imputed data includes uses machine learning to correct and/or impute for at least some of the missing or incorrect pipe attributes.

### Claim 9 (depends on 1)

A method according to claim 1 further comprising: predicting a likelihood of failure of one or more pipe sections based on said improved set of pipe data.

### Claim 10 (depends on 9)

A method according to claim 9 wherein said predicting is based at least in part on a model built with machine learning using at least some of said improved set of pipe data.

### Claim 11 (depends on 9)

A method according to claim 9 wherein said managing includes planning pipe section replacement jobs based at least in part on said predicted likelihood of failure of said one or more pipe sections.

### Claim 12 (depends on 1)

A method according to claim 1 wherein said imputed data includes imputed material and diameter data of one or more pipe sections, and the method further includes estimating cost of repair and replacement based on said imputed material and diameter data of one or more pipe sections.

### Claim 13

A system for improving pipe data relating to networks of underground pipes for carrying fluid to consumers, the system comprising:
a database that stores a set of pipe data that includes a plurality of pipe attributes for one or more of said networks of underground pipes; and
a processing system configured to identify one or more pipes in at least on of said networks for which one or more pipe attributes is missing or incorrect, generate imputed data for the one or more pipe attributes resulting in an improved set of pipe data, wherein one or more of aspects of one or more of said networks of underground pipes can be managed based at least in part on the improved set of pipe data.

### Claim 14 (depends on 13)

The system according to claim 13 further comprising a front end system that includes an uploader for receiving said set of pipe data from a customer who manages the one or more aspects of at least one of said networks of underground pipes, and a viewer that can display at least some of said improved set of pipe data which facilitates said management.

### Claim 15 (depends on 13)

The system according to claim 13 wherein the processing system is further configured to predict likelihood of pipe segments in the said networks leaking, and said one or more of aspects of one or more of said networks of underground pipes being managed includes replacing pipe sections based at least in part on said predicted likelihood of leaking.

### Claim 16 (depends on 15)

The system according to claim 15 wherein said processing system predicts the likelihood based at least in part on a model built with machine learning using at least some of said improved set of pipe data.

### Claim 17 (depends on 13)

The system according to claim 13 wherein the set of pipe data includes pipe break data at least some of which includes locations for pipe breaks but not specific pipe sections for said breaks, and the imputed data is generated using a geolocation transfer process configured to assign pipe sections to at least some of said pipe breaks that are not the closest pipe sections to the respective locations for the pipe breaks.

### Claim 18

A method of creating a standardized database containing environmental data, the method comprising:
accessing a first plurality of separate environmental raster form datasets; merging at least some of the first plurality of separate environmental raster
form datasets to generate a second plurality of larger environmental form datasets;
vectorizing at least some of second plurality of larger environmental form datasets to generate a third plurality of larger vector datasets;
merging at least some of the third plurality of larger vector datasets to form a merged vector dataset; and
imputing one or more missing attributes in the merged vector dataset to generate a standardized database.

### Claim 19 (depends on 18)

A method according to claim 18 wherein at least some of the first plurality of separate environmental raster datasets are not overlapping with each other or are not coextensive with each other.

### Claim 20 (depends on 18)

A method according to claim 18 wherein separate environmental raster form datasets include one or more types of data selected from a group consisting of soil properties, population, climate, elevation, slope and soil.

### Claim 21 (depends on 18)

A method according to claim 18 further comprising removing outlier data from said standardized database based on falling outside one or more predetermined limits.

### Claim 22 (depends on 18)

A method according to claim 18 wherein said standardized database includes one or more new environmental variables that were not included in the first plurality of separate environmental raster form datasets.

### Claim 23 (depends on 22)

A method according to claim 22 wherein the one or more new environmental variables include one or more selected from a group consisting of: soil density, population density, national slope, break density and proximity maps of shorelines, railways, subways, roads, rivers, creeks, streams, ponds and/or lakes.

### Claim 24 (depends on 18)

A method according to claim 18 wherein said first plurality of separate environmental raster form datasets includes zoning data and the method further comprises categorizing a portion of said zoning data.

### Claim 25 (depends on 18)

A method according to claim 18 further comprising approximating non-square-shaped data is to square-shaped data for more efficient integration into said database.

### Claim 26 (depends on 18)

A method according to claim 18 wherein said standardized database is used by a plurality of customers to provide computational cost savings to each of said customers compared to using a custom generated database.

### Claim 27 (depends on 18)

A method according to claim 18 further comprising predicting likelihood of pipe segments leaking in a network of underground pipes for carrying fluid to consumers based at least in part on said standardized database.

### Claim 28 (depends on 27)

A method according to claim 27 further comprising building a model using machine learning based at least in part on said standardized database, and wherein said predicting likelihood of pipe segments leaking is based on the model.
