DEVICE FOR DETECTING THE OPERATING STATE OF A MACHINE

• US 20140129192A1
• Filed: 10/08/2013
• Published: 05/08/2014
• Est. Priority Date: 11/05/2012
• Status: Active Grant

• Current Assignee: Deere & Company
• Original Assignee: Deere & Company
• Inventors: BLANK, SEBASTIAN, BECK, FOLKER, KNEIP, FRANK
• Granted Patent: US 10,318,609 B2
• Time in Patent Office: Days
• US Class Current: 703/2
• CPC Class Codes: A01B 76/00 Parts, details or accessories of agricultural machines or implements, not provided for in groups A01B51/00 - A01B75/00
• CPC Class Codes: 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
• CPC Class Codes: G07C 5/0825 using optical means
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A device for detecting the operating state of a machine comprises one or more sensors for making available in each case an output value relating to a current parameter of a component of the machine, and a processing unit which is connected to the sensors and is programmed to derive information about the operating state of machine using a Hidden Markov Model and on the basis of the measured values of the sensors and/or values derived therefrom. The processing unit can be supplied with a state transition matrix A, elements of an emission probability matrix B for the probability that an observation is conditioned by a certain state, and a vector π for describing an input state, in order to derive the operating states of the machine therefrom. The processing unit is programmed to derive elements of the emission probability matrix B from the measured values of the sensors.

Claims

1. A device for detecting an operating state of a machine, comprising:

at least one sensor for making available in each case an output value relating to a current parameter of a component of the machine; and

a processing unit connected to the at least one sensor, wherein said processing unit is configurable to derive information about the operating state of the machine using a Hidden Markov Model and based at least in part on at least one of;

at least one measured value of the at least one sensor or at least one value derived from the at least one sensor;

wherein the processing unit is further configurable to be supplied with a state transition matrix A, elements of an emission probability matrix B for the probability that an observation is conditioned by a certain state, and a vector for describing an input state, in order to derive at least one operating state of the machine therefrom, wherein the processing unit is further configurable to derive elements of the emission probability matrix B from the measured values of the at least one sensor.

2. The device according to claim 1, wherein the processing unit is further configurable to derive the elements of the emission probability matrix B from fuzzified measured values of the at least one sensor being fed to the Hidden Markov Model as an observation.

3. The device according to claim 1, wherein the processing unit is further configurable to derive the elements of the emission probability matrix B from measured values of a sensor state monitoring system for detecting a state of the at least one sensor or a state of a device for monitoring an operator.

8. The device according to claim 1, wherein the machine comprises an agricultural machine.

9. The device according to claim 1, wherein the device comprises an implement.

10. The device according to claim 1, wherein the derived operating state of the machine is displayable on a display panel of the machine.

11. The device according to claim 1, wherein at least one component of the machine is actuated based at least in part on the derived operating state of the machine.

12. The device according to claim 1, wherein at least one component of the device is actuated based at least in part on the derived operating state of the machine.

4. A device for detecting an operating state of a machine, comprising:

at least one sensor for making available in each case an output value relating to a current parameter of a component of the machine; and

a processing unit connected to the at least one sensor, wherein said processing unit is configurable to derive information about the operating state of the machine using a Hidden Markov Model and based at least in part on at least one of;

at least one measured value of the at least one sensor or at least one value derived from the at least one sensor;

wherein the processing unit is further configurable to be supplied with a state transition matrix A, elements of an emission probability matrix B for the probability that an observation is conditioned by a certain state, and a vector π

for describing an input state, in order to derive at least one operating state of the machine therefrom, wherein the processing unit is further configurable to;

determine a model for the respective operating mode of the machine based at least in part on measured values of at least one of;

the at least one sensor; and

a position-determining system; and

select at least one of the state transition matrix A and the vector π

, based at least in part on the determined model for the operating mode from a database in which different state transition matrices A and vectors π

for different operating modes of the machine are stored.

5. The device according to claim 4, wherein the processing unit is further configured to calculate elements of the state transition matrix A during operation.

6. A device for detecting an operating state of a machine, comprising:

at least one sensor for making available in each case an output value relating to a current parameter of a component of the machine; and

a processing unit connected to the at least one sensor, wherein said processing unit is configurable to derive information about the operating state of the machine using a Hidden Markov Model and based at least in part on at least one of;

at least one measured value of the at least one sensor or at least one value derived from the at least one sensor;

wherein the processing unit is further configurable to be supplied with a state transition matrix A. elements of an emission probability matrix B for the probability that an observation is conditioned by a certain state, and a vector π

for describing an input state, in order to derive at least one operating state of the machine therefrom, wherein the processing unit is further configurable to carry out a subsequent step for determining the operating state of the machine only if at least one of;

a different state transition matrix A and a different vector π

;

(i) has been selected since a previous step;

(ii) a sufficient data quantity for differentiating different operating states is available;

or

(iii) a change in the operating state is to be expected.

7. The device according to claim 6, wherein the processing unit is further configurable to determine the time of the subsequent step as a function of the diagonal elements of the state transition matrix A.