# US 10,311,657 B2 · System and method for identifying machine work cycle phases

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

- Number: US 10,311,657 B2
- Document ID: US10311657B2
- Status: Granted
- Kind: B2
- Application number: 15/381,775
- Filed: 2016-12-16
- Published: 2018-06-21
- Granted: 2019-06-04
- Earliest claimed: 2016-12-16
- Assignees: Caterpillar Inc.
- Applicants: Caterpillar Inc.
- Inventors: Darryl V. Collins
- Web page: https://patentgrep.com/patent/US10311657B2

## CPC

- G07C 5/08: Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- E02F 9/2054: {Fleet management}
- E02F 9/261: {Surveying the work-site to be treated}
- E02F 9/264: {Sensors and their calibration for indicating the position of the work tool}
- E02F 3/842: {using electromagnetic, optical or photoelectric beams, e.g. laser beams}
- G05D 1/0278: {using satellite positioning signals, e.g. GPS}
- G05D 1/12: Target-seeking control
- 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
- E02F: DREDGING; SOIL-SHIFTING (winning peat E21C49/00)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES

## Abstract

A system is disclosed for monitoring work cycles on a worksite including a truck and a loading machine. The system includes a communications interface, memory storing instructions, and a processing unit configured to execute the instructions. The processing unit receives, via the communications interface, location information and acceleration information for the truck and location information for the loading machine. The processing unit determines a distance between the truck and the loading machine based on the location information. The processing unit determines a phase of a work cycle of the truck based on the determined distance between the truck and the loading machine and on the acceleration information for the truck.

## Claims

### Claim 1

A system for monitoring work cycles on a worksite including a truck and a loading machine, the system comprising:
a communications interface;
memory storing instructions;
an accelerometer on the truck;
a GPS device or other location device on each of the truck and the loading machine; and
a processing unit configured to execute the instructions to:
receive, via a data link connected to the communications interface, a signal from the GPS device or other location device on the truck and a signal from the accelerometer on the truck indicative of location information and acceleration information, respectively, for the truck and a signal from the GPS device or other location device on the loading machine indicative of location information for the loading machine;
determine a distance between the truck and the loading machine based on a difference between the location information for the truck and the location information for the loading machine; and
determine a phase of a work cycle of the truck based on the determined distance between the truck and the loading machine and on the acceleration information for the truck.

### Claim 2 (depends on 1)

The system of claim 1, wherein the acceleration information includes at least a magnitude of acceleration of the truck in the vertical direction measured by the accelerometer on the truck.

### Claim 3 (depends on 1)

The system of claim 1, further including at least one of a gyroscope or a magnetometer on the truck, wherein the processing unit is further configured to execute the instructions to:
receive, via the datalink connected to the communications interface, a signal from at least one of the gyroscope or the magnetometer, respectively, indicative of at least one of rotation information or magnetic field information, respectively, for the truck; and
determine the phase of the work cycle based further on the at least one of the rotation information or the magnetic field information.

### Claim 4 (depends on 3)

The system of claim 3, wherein the rotation information includes a magnitude of rotation measured by the gyroscope on the truck, and the magnetic field information includes a magnitude of a magnetic field measured by the magnetometer on the truck.

### Claim 5 (depends on 1)

The system of claim 1, wherein the work cycle includes at least one of a loading phase, a traveling full phase, a dumping phase, or a traveling empty phase.

### Claim 6 (depends on 1)

The system of claim 1, wherein, to determine the phase of the work cycle, the processing unit is configured to execute the instructions to provide the determined distance between the truck and the loading machine and the acceleration information for the truck as input to a learning model.

### Claim 7 (depends on 6)

The system of claim 6, wherein the model is a Hidden Markov Model.

### Claim 8 (depends on 6)

The system of claim 6, wherein the processing unit is further configured to train the learning model using the determined distance between the truck and the loading machine and the acceleration information for the truck as input to a learning model.

### Claim 9

A method for monitoring work cycles on a worksite including a truck and a loading machine, the truck including an accelerometer, and each of the truck and the loading machine including a GPS device or other location device, the method comprising:
receiving, at a processing unit via a datalink connected to a communications interface a signal from the GPS device or other location device on the truck and a signal from the accelerometer on the truck indicative of location information and acceleration information, respectively, for the truck and a signal from the GPS device or other location device on the loading machine indicative of location information for the loading machine;
determining, using the processing unit, a distance between the truck and the loading machine based on a difference between the location information for the truck and the location information for the loading machine; and
determining, using the processing unit, a phase of a work cycle of the truck based on the determined distance between the truck and the loading machine and on the acceleration information for the truck.

### Claim 10 (depends on 9)

The method of claim 9, wherein the acceleration information includes at least a magnitude of acceleration of the truck in the vertical direction measured by an accelerometer on the truck.

### Claim 11 (depends on 9)

The method of claim 9, wherein the truck further includes at least one of a gyroscope or a magnetometer, the method further comprising:
receiving via the datalink connected to the communications interface a signal from at least one of the gyroscope or the magnetometer, respectively, indicative of at least one of rotation information or magnetic field information, respectively, associated with the truck; and
determining the phase of the work cycle based further on the at least one of the rotation information or the magnetic field information.

### Claim 12 (depends on 11)

The method of claim 11, wherein the rotation information includes a magnitude of rotation measured by the gyroscope on the truck, and the magnetic field information includes a magnitude of a magnetic field measured by the magnetometer on the truck.

### Claim 13 (depends on 9)

The method of claim 9, wherein the work cycle includes at least one of a loading phase, a traveling full phase, a dumping phase, or a traveling empty phase.

### Claim 14 (depends on 9)

The method of claim 9, wherein determining the phase of the work cycle includes providing the determined distance between the truck and the loading machine and the acceleration information for the truck as input to a learning model.

### Claim 15 (depends on 14)

The method of claim 14, wherein the model is a Hidden Markov Model.

### Claim 16 (depends on 14)

The method of claim 14, further comprising training the learning model using the determined distance between the truck and the loading machine and the acceleration information for the truck as input to the learning model.

### Claim 17

A system for monitoring work cycles on a worksite including a truck and a loading machine, the system comprising:
a communications interface;
memory storing instructions;
an accelerometer on the truck;
a GPS device or other location device on each of the truck and the loading machine; and
a processing unit configured to execute the instructions to:
receive, via a data link connected to the communications interface, a signal from the GPS device or other location device on the truck and a signal from the accelerometer on the loading machine indicative of location information and acceleration information, respectively, for the loading machine and a signal from the GPS device or other location device on the truck indicative of location information for the truck;
determine a distance between the loading machine and the truck based on a difference between the location information for the loading machine and the location information for the truck; and
determine a phase of a work cycle of the loading machine based on the determined distance between the loading machine and the truck and on the acceleration information for the loading machine.

### Claim 18 (depends on 17)

The system of claim 17, wherein the acceleration information includes at least a magnitude of acceleration of the loading machine in the vertical direction measured by an accelerometer on the loading machine.

### Claim 19 (depends on 17)

The system of claim 17, wherein the work cycle includes at least one of a digging phase, a swinging full phase, a dumping phase, or a swinging empty phase.

### Claim 20 (depends on 17)

The system of claim 17, wherein, to determine the phase of the work cycle, the processing unit is configured to execute the instructions to provide the determined distance between the loading machine and the truck and the acceleration information for the loading machine as input to a learning model.
