# US 2018/0025558 A1 · Detection and reconstruction of sensor faults

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

- Number: US 2018/0025558 A1
- Document ID: US20180025558A1
- Status: Published application
- Kind: A1
- Application number: 15/214,162
- Filed: 2016-07-19
- Published: 2018-01-25
- Earliest claimed: 2016-07-19
- Assignees: GM Global Technology Operations LLC; University of Waterloo
- Applicants: GM Global Technology Operations LLC
- Inventors: SHIH-KEN CHEN; NIKOLAI K. MOSHCHUK; BAKHTIAR B. LITKOUHI; REZA ZARRINGHALAM; AMIR KHAJEPOUR; WILLIAM MELEK
- Web page: https://patentgrep.com/patent/US20180025558A1

## CPC

- G07C 5/0808: {Diagnosing performance data (testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005)}
- B60W 50/00: Details of control systems for road vehicle drive control not related to the control of a particular sub-unit {, e.g. process diagnostic or vehicle driver interfaces}
- B60W 50/0205: {Diagnosing or detecting failures; Failure detection models}
- B60W 50/029: Adapting to failures or work around with other constraints, e.g. circumvention by avoiding use of failed parts
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- B60W 2050/0025: {Transfer function weighting factor}
- B60W 2050/0215: {Sensor drifts or sensor failures}
- B60W 2050/0292: {Fail-safe or redundant systems, e.g. limp-home or backup systems}
- B60W 2520/105: Longitudinal acceleration
- B60W 2520/125: Lateral acceleration
- B60W 2520/14: Yaw
- B60W 2540/18: Steering angle
- G05B 2219/37537: Virtual sensor
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- 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

Methods and systems are provided for detecting faults in a sensor and reconstructing an output signal without use of the faulty sensor. In one embodiment, a method includes: receiving, by a processor, sensor data indicating a measured value from a first sensor; receiving, by a processor, sensor data indicating measured values from a plurality of other sensors; computing, by a processor, virtual values based on a vehicle model and the sensor data from the plurality of other sensors; computing, by a processor, a residual difference between the measured value from the first sensor and the virtual values; detecting, by a processor, whether a fault exists in the first sensor based on the residual difference; and when a fault in the sensor is detected, generating, by a processor, a control value based on the virtual values instead of the measured value.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving, by a processor, sensor data indicating a measured value from a first sensor;
receiving, by a processor, sensor data indicating measured values from a plurality of other sensors;
computing, by a processor, virtual values based on a vehicle model and the sensor data from the plurality of other sensors;
computing, by a processor, a residual difference between the measured value from the first sensor and the virtual values;
detecting, by a processor, whether a fault exists in the first sensor based on the residual difference; and
when a fault in the sensor is detected, generating, by a processor, a control value based on the virtual values instead of the measured value.

### Claim 2 (depends on 1)

The method of claim 1, wherein the detecting whether a fault exists comprises comparing the residual difference with an adaptive fault threshold.

### Claim 3 (depends on 2)

The method of claim 2, wherein the comparing the residual difference with the adaptive fault threshold comprises detecting if the residual difference exceeds the adaptive threshold for a predetermined time period.

### Claim 4 (depends on 3)

The method of claim 3, wherein the adaptive fault threshold is computed using at least one of a driving condition and a dynamic region.

### Claim 5 (depends on 1)

The method of claim 1, wherein generating the control value is based on a computed weighted virtual value.

### Claim 6 (depends on 1)

The method of claim 1, wherein the generating the control value is based on an average of a plurality of computed virtual values.

### Claim 7 (depends on 1)

The method of claim 1, wherein the first sensor is a lateral acceleration sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a longitudinal acceleration sensor, and a yaw rate sensor.

### Claim 8 (depends on 1)

The method of claim 1, wherein the first sensor is a yaw rate sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a lateral acceleration sensor, and a longitudinal acceleration sensor.

### Claim 9 (depends on 1)

The method of claim 1, wherein the first sensor is a longitudinal acceleration sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a lateral acceleration sensor, and a yaw rate sensor.

### Claim 10

A system, comprising:
a non-transitory computer readable medium comprising:
a first module that receives, by a processor, sensor data indicating a measured value from a first sensor, that receives, by a processor, sensor data indicating measured values from a plurality of other sensors, and that computes, by a processor, virtual values based on a vehicle model and the sensor data from the plurality of other sensors;
a second module that computes, by a processor, a residual difference between the measured value from the first sensor and the virtual values;
a third module that detects, by a processor, whether a fault exists in the first sensor based on the residual difference, and when a fault in the sensor is detected,
generating, by a processor, a control value based on the virtual values instead of the measured value.

### Claim 11 (depends on 10)

The system of claim 10, wherein the third module detects whether the fault exists by comparing the residual difference with an adaptive fault threshold.

### Claim 12 (depends on 11)

The system of claim 11, wherein the third module compares the residual difference with the adaptive fault threshold by detecting if the residual difference exceeds the adaptive threshold for a predetermined time period.

### Claim 13 (depends on 10)

The system of claim 10, wherein the adaptive fault threshold is computed using at least one of a driving condition and a dynamic region.

### Claim 14 (depends on 10)

The system of claim 10, wherein the third module generates the control value based on a computed weighted virtual value.

### Claim 15 (depends on 10)

The system of claim 10, wherein the third module generates the control value based on an average of a plurality of computed virtual values.

### Claim 16 (depends on 10)

The system of claim 10, wherein the first sensor is a lateral acceleration sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a longitudinal acceleration sensor, and a yaw rate sensor.

### Claim 17 (depends on 10)

The system of claim 10, wherein the first sensor is a yaw rate sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a lateral acceleration sensor, and a longitudinal acceleration sensor.

### Claim 18 (depends on 10)

The system of claim 10, wherein the first sensor is a longitudinal acceleration sensor, and wherein the plurality of other sensors includes a steering angle sensor, an angular velocity sensor, a lateral acceleration sensor, and a yaw rate sensor.