# US 11,898,704 B2 · Methods and Internet of Things systems for smart gas pipeline life prediction based on safety

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,898,704 B2
- Document ID: US11898704B2
- Status: Granted
- Kind: B2
- Application number: 18/062,555
- Filed: 2022-12-06
- Published: 2023-03-30
- Granted: 2024-02-13
- Earliest claimed: 2022-10-14
- Assignees: Chengdu Qinchuan Iot Technology Co., Ltd.
- Applicants: Chengdu Qinchuan Iot Technology Co., Ltd.
- Inventors: Zehua Shao; Haitang Xiang; Lei Zhang; Yong Li; Yongzeng Liang
- Web page: https://patentgrep.com/patent/US11898704B2

## CPC

- F17D 5/005: {of gas pipelines, e.g. alarm}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- F16L 55/32: being self-contained
- F17D 5/02: Preventing, monitoring, or locating loss
- F17D 5/06: using electric or acoustic means
- G05B 13/048: {using a predictor}
- G05B 19/042: using digital processors (G05B19/05 takes precedence)
- G05B 19/4155: characterised by program execution, i.e. part program or machine function execution, e.g. selection of a program
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G05B 23/0283: {Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] (preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06)}
- G05D 1/0221: {involving a learning process}
- G06F 11/3447: {Performance evaluation by modeling}
- G06F 11/3452: {Performance evaluation by statistical analysis}
- G06N 3/02: Neural networks
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/049: Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
- G06N 3/08: Learning methods
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/025: Extracting rules from data
- G06N 5/04: Inference or reasoning models
- G06N 5/046: Forward inferencing; Production systems
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G16Y 10/35: Utilities, e.g. electricity, gas or water
- G16Y 40/50: Safety; Security of things, users, data or systems
- F16L 2101/30: Inspecting, measuring or testing
- F16L 2201/30: Detecting leaks
- G06F 2113/08: Fluids
- G06F 2201/86: Event-based monitoring
- Y02P 90/30: Computing systems specially adapted for manufacturing
- F17D: PIPE-LINE SYSTEMS; PIPE-LINES (pumps or compressors F04; fluid dynamics F15D; valves or the like F16K; pipes, laying pipes, supports, joints, branches, repairing, work on the entire line, accessories F16L; steam traps or the like F16T; fluid-pressure electric cables H01B9/06)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- F16L: PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16Y: INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

The present disclosure provides a method for smart gas pipeline life prediction based on safety. The method includes: obtaining the operation information of the target gas pipeline section within the first time period; determining, based on operation information, the first performance parameter of the target gas pipeline section of at least one moment within the first time period, the first performance parameter including at least the transport performance of the target gas pipeline section within the first time period; determining, based on the first performance parameter of at least one moment, the first performance parameter sequence of the target gas pipeline section within the first time period, the first performance parameter sequence being the sequence obtained by arranging the first performance parameters of at least one moment in chronological order; and determining, based on the first performance parameter sequence, the remaining life of the target gas pipeline section.

## Claims

### Claim 1

A method for smart gas pipeline life prediction, wherein the method is implemented by a smart gas pipeline network device management sub-platform, the method comprising:
obtaining operation information of a target gas pipeline section within a first time period through a smart gas data center;
determining, based on the operation information, a first performance parameter of the target gas pipeline section of at least one moment within the first time period, wherein the first performance parameter at least includes transportation performance of the target gas pipeline section within the first time period;
determining, based on the first performance parameter of at least one moment, a first performance parameter sequence of the target gas pipeline section within the first time period, wherein the first performance parameter sequence is a sequence obtained by arranging the first performance parameter of at least one moment in a chronological order; and
determining, based on the first performance parameter sequence, a remaining life of the target gas pipeline section, including
predicting, based on the first performance parameter sequence, a second performance parameter sequence of the target gas pipeline section within a second time period, wherein the second performance parameter sequence includes performance parameter of at least one future moment; and
determining, based on the first performance parameter sequence or the second performance parameter sequence, the remaining life of the target gas pipeline section;
wherein the predicting, based on the first performance parameter sequence, a second performance parameter sequence of the target gas pipeline section within a second time period includes:
determining, based on the first performance parameter sequence, the second performance parameter sequence of the target gas pipeline section within the second time period through a performance parameter prediction model, wherein the performance parameter prediction model is a time series prediction model, an input of the performance parameter prediction model includes the first performance parameter sequence and an environmental feature sequence, the environmental feature sequence includes a plurality of environmental features arranged in chronological order, the performance parameter prediction model includes a first prediction layer and a second prediction layer, an input of the first prediction layer includes the first performance parameter sequence, an output of the first prediction layer includes second performance parameter sequence before correction, an input of the second prediction layer includes the second performance parameter sequence before correction, a confidence level, the first performance parameter sequence, and the environmental feature sequence, an output of the second prediction layer includes the second performance parameter sequence, wherein the confidence level is related to a number of performance parameters in the second performance parameter sequence before correction and a complexity of a gas pipeline map.

### Claim 2 (depends on 1)

The method of claim 1, wherein the method further comprises:
sending the remaining life of the target gas pipeline section to the smart gas data center, wherein the smart gas data center is used to send the remaining life of the target gas pipeline section to a smart gas service platform, and the smart gas service platform is used to send the remaining life of the target gas pipeline section to a smart gas user platform, and the smart gas user platform is used for a user to query the remaining life of the target gas pipeline section.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first performance parameter also includes pipeline integrity of the target gas pipeline section within the first time period, and the determining, based on the operation information, a first performance parameter of the target gas pipeline section of at least one moment within the first time period comprises:
obtaining an image of the target gas pipeline section through a crawling robot; and
determining, based on the image, the pipeline integrity of the target gas pipeline section through an image recognition model, wherein the image recognition model is a machine learning model.

### Claim 4 (depends on 1)

The method of claim 1, wherein the determining, based on the operation information, a first performance parameter of the target gas pipeline section of at least one moment within the first time period comprises:
determining the gas pipeline map corresponding to the target gas pipeline section through the smart gas data center, wherein the gas pipeline map is a map of a connection relationship of multiple gas pipeline sections within a preset range of the target gas pipeline section; and
determining, based on the gas pipeline map, the transportation performance of the target gas pipeline section within the first time period by a transportation performance determination model, wherein the transportation performance determination model is a graph neural network model.

### Claim 5 (depends on 1)

The method of claim 1, wherein predicting, based on the first performance parameter sequence, a second performance parameter sequence of the target gas pipeline section within the second time period comprises:
obtaining multiple performance degradation models;
for each of the multiple performance degradation models, determining a goodness of fit between the first performance parameter sequence and each performance degradation model;
determining, based on the goodness of fit between the first performance parameter sequence and each performance degradation model, a target performance degradation model from the multiple performance degradation models; and
determining, based on the target performance degradation model, the second performance parameter sequence.

### Claim 6 (depends on 1)

A non-transitory computer-readable storage medium, wherein the storage medium stores computer instructions, when the computer reads the computer instructions in the storage medium, the computer executes the method of claim 1.

### Claim 7

An Internet of Things system for smart gas pipeline life prediction, wherein the system comprises a smart gas safety management platform, the smart gas safety management platform includes a smart gas pipeline network device management sub-platform and a smart gas data center, and the smart gas pipeline network device management sub- platform is configured to:
obtain operation information of a target gas pipeline section within a first time period through the smart gas data center;
determine, based on the operation information, a first performance parameter of the target gas pipeline section of at least one moment within the first time period, wherein the first performance parameter at least includes transportation performance of the target gas pipeline section within the first time period;
determine, based on the first performance parameter of at least one moment, a first performance parameter sequence of the target gas pipeline section within the first time period, wherein the first performance parameter sequence is a sequence obtained by arranging the first performance parameter of at least one moment in a chronological order; and
determine, based on the first performance parameter sequence, a remaining life of the target gas pipeline section;
wherein the smart gas pipeline network device management sub-platform is further configured to:
predict, based on the first performance parameter sequence, a second performance parameter sequence of the target gas pipeline section within a second time period, wherein the second performance parameter sequence includes performance parameter of at least one future moment; and
determine, based on the first performance parameter sequence or the second performance parameter sequence, the remaining life of the target gas pipeline section;
wherein the smart gas pipeline network device management sub-platform is further configured to:
determine, based on the first performance parameter sequence, the second performance parameter sequence of the target gas pipeline section within the second time period through a performance parameter prediction model, wherein the performance parameter prediction model is a time series prediction model, an input of the performance parameter prediction model includes the first performance parameter sequence and an environmental feature sequence, the environmental feature sequence includes a plurality of environmental features arranged in chronological order, the performance parameter prediction model includes a first prediction layer and a second prediction layer, an input of the first prediction layer includes the first performance parameter sequence, an output of the first prediction layer includes second performance parameter sequence before correction, an input of the second prediction layer includes the second performance parameter sequence before correction, a confidence level, the first performance parameter sequence, and the environmental feature sequence, an output of the second prediction layer includes the second performance parameter sequence, wherein the confidence level is related to a number of performance parameters in the second performance parameter sequence before correction and a complexity of a gas pipeline map.