# US 2025/0156694 A1 · Predicting a maintenance status of a real-world device

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

- Number: US 2025/0156694 A1
- Document ID: US20250156694A1
- Status: Published application
- Kind: A1
- Application number: 18/946,546
- Filed: 2024-11-13
- Published: 2025-05-15
- Earliest claimed: 2023-11-13
- Assignees: Dassault Systemes
- Applicants: Dassault Systemes
- Inventors: Ali TLILI; Oumaima KHALED; Leonard KIENTZ
- Web page: https://patentgrep.com/patent/US20250156694A1

## CPC

- G06N 3/048: Activation functions
- 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)}
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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)

## Abstract

A computer-implemented method for predicting a maintenance status of a real-world device. The method comprises providing a dataset. The dataset includes data describing historical real-world maintenance events and properties of devices of a same type as the real-world device. The method further comprises training, based on the dataset, a neural network to predict parameters of a MCDA sorting model. The MCDA sorting model is configured to take as input at least one time measurement of maintenance-related physical and/or functional data of the real-world device and to output a prediction of a maintenance status of the real-world device.

## Claims

### Claim 1

A computer-implemented method for predicting a maintenance status of a real-world device, the method comprising:
obtaining a dataset including data describing historical real-world maintenance events and properties of devices of a same type as the real-world device; and
training, based on the dataset, a neural network to predict parameters of a MCDA sorting model, the MCDA sorting model being configured to take as input at least one time measurement of maintenance-related physical and/or functional data of the real-world device and to output a prediction of a maintenance status of the real-world device.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the MCDA sorting model is a NCS model.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the neural network is based on a sigmoid activation function for implementation of comparison rules in the MCDA sorting model, and at least one parameter of the MCDA sorting model is a sigmoid function implementing comparison rules.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the maintenance status is one of: normal operation, maintenance advised, and maintenance required.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, wherein the maintenance status is one of: normal operation, maintenance advised, and maintenance required.

### Claim 6

A computer-implemented method of applying a MCDA sorting model obtainable by predicting a maintenance status of a real-world device, the method comprising:
obtaining a dataset including data describing historical real-world maintenance events and properties of devices of a same type as the real-world device;
training, based on the dataset, a neural network to predict parameters of a MCDA sorting model, the MCDA sorting model being configured to take as input at least one time measurement of maintenance-related physical and/or functional data of the real-world device and to output a prediction of a maintenance status of the real-world device;
obtaining at least one time measurement of maintenance-related physical and/or functional data of the real-world device; and
applying the MCDA sorting model to the obtained at least one time measurement, thereby outputting a prediction of a maintenance status of the real-world device.

### Claim 7

A computer-implemented method of applying a MCDA sorting model configured to take as input time measurements of maintenance-related physical and/or functional data of a real-world device and to output a prediction of a maintenance status of the real-world device, at least one parameter of the MCDA sorting model being a sigmoid function implementing comparison rules, the method comprising:
obtaining at least one time measurement of maintenance-related physical and/or functional data of the real-world device; and
applying the MCDA sorting model to the obtained at least one time measurement, thereby outputting a prediction of a maintenance status of the real-world device.

### Claim 8 (depends on 6)

The computer-implemented method of claim 6, wherein the at least one time measurement consists in at least one real-time measurement.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein the MCDA sorting model is applied in real-time.

### Claim 10 (depends on 6)

The computer-implemented method of claim 6, wherein the at least one time measurement stems from at least one physical sensor of the device and/or attached to the device.

### Claim 11 (depends on 6)

The computer-implemented method of claim 6, further comprising:
comparing one or more predictions of the MCDA sorting model with one or more real-world maintenance statuses of the device; and
if the comparison results in a disparity, updating the MCDA sorting model based on the one or more real-world maintenance statuses of the device.

### Claim 12 (depends on 6)

The computer-implemented method of claim 6, further comprising:
performing maintenance of the device based on the prediction of the MCDA sorting model.

### Claim 13

A device comprising:
a non-transitory computer readable data storage medium having recorded thereon
a computer program having
instructions for predicting a maintenance status of a real-world device that when executed by a processor causes the processor to be configured to:
obtain a dataset including data describing historical real-world maintenance events and properties of devices of a same type as the real-world device; and
train, based on the dataset, a neural network to predict parameters of a MCDA sorting model, the MCDA sorting model being configured to take as input at least one time measurement of maintenance-related physical and/or functional data of the real-world device and to output a prediction of a maintenance status of the real-world device; and/or
instructions for applying the MCDA sorting model obtainable according to the predicting of the maintenance status of the real-world device that when executed by the processor causes the processor to being configured to:
obtain at least one time measurement of maintenance-related physical and/or functional data of the real-world device; and
apply the MCDA sorting model to the obtained at least one time measurement, thereby outputting a prediction of a maintenance status of the real-world device; and/or
instructions for applying the MCDA sorting model configured to take as input time measurements of maintenance-related physical and/or functional data of a real-world device and to output a prediction of a maintenance status of the real-world device, at least one parameter of the MCDA sorting model being a sigmoid function implementing comparison rule that when executed by the processor causes the processor to being configured to:
obtain at least one time measurement of maintenance-related physical and/or functional data of the real-world device; and
apply the MCDA sorting model to the obtained at least one time measurement, thereby outputting a prediction of a maintenance status of the real-world device; and/or
the MCDA sorting model obtainable by predicting the maintenance status of the real-world device; and/or
the MCDA sorting model configured to take as input time measurements of maintenance-related physical and/or functional data of the real-world device and to output the prediction of the maintenance status of the real-world device, at least one parameter of the MCDA sorting model being a sigmoid function implementing comparison rules.

### Claim 14 (depends on 13)

The device of claim 13, wherein the MCDA sorting model is a NCS model.

### Claim 15 (depends on 13)

The device of claim 13, wherein the neural network is based on a sigmoid activation function for implementation of comparison rules in the MCDA sorting model, and at least one parameter of the MCDA sorting model is a sigmoid function implementing comparison rules.

### Claim 16 (depends on 13)

The device of claim 13, wherein the maintenance status is one of: normal operation, maintenance advised, and maintenance required.

### Claim 17 (depends on 13)

The device of claim 13, further comprising the processor coupled to the non-transitory computer readable data storage medium.

### Claim 18 (depends on 14)

The device of claim 14, further comprising the processor coupled to the non-transitory computer readable data storage medium.

### Claim 19 (depends on 15)

The device of claim 15, further comprising the processor coupled to the non-transitory computer readable data storage medium.

### Claim 20 (depends on 16)

The device of claim 16, further comprising the processor coupled to the non-transitory computer readable data storage medium.
