Method for characterization of rock strata in drilling operations

• US 6,490,527 B1
• Filed: 07/11/2000
• Issued: 12/03/2002
• Est. Priority Date: 07/13/1999
• Status: Expired due to Fees

• Current Assignee: United States Department Of Health And Human Services (Government of the United States of America)
• Original Assignee: United States Department Of Health And Human Services (Government of the United States of America)
• Inventors: Utt, Walter K.
• Primary Examiner(s): McElheny, Jr., Donald E.
• Application Number:
  US09/613,963
• Time in Patent Office: 875 Days
• Field of Search: 702/9, 700/174, 700/175, 700/177, 175/50, 73/81, 73/82, 731/520.3, 324/338, 324/339
• US Class Current: 702/9
• CPC Class Codes: E21B 2200/22 Fuzzy logic, artificial intelligence, neural networks or the like
• CPC Class Codes: E21B 47/00 Survey of boreholes or wells monitoring pressure or flow of drilling fluid E21B21/08
• CPC Class Codes: E21C 39/00 Devices for testing in situ the hardness or other properties of minerals, e.g. for giving information as to the selection of suitable mining tools
• CPC Class Codes: E21F 17/185 Rock-pressure control devices with or without alarm devices; Alarm devices in case of roof subsidence props with load-measuring devices E21D15/46
• CPC Class Codes: G01V 9/00 Prospecting or detecting by methods not provided for in groups G01V1/00 - G01V8/00

Abstract

A method and system for determining the relative strength and classification of rock strata in near real-time during drilling operations is provided for use in underground mines. Neural network technology is used to classify mine roof strata in terms of, for example, relative strength or strength index as the roof bolt hole is being drilled (i.e., in near real-time). Measurements taken while a layer of the rock strata is being drilled are used to compute the specific energy input and convert these data to suitably scaled features. A neural network is then used to classify the strength of the layer. The neural network can be trained using data of known rock strata classifications prior to using it to classify new measurements. The present system allows for detection of unsafe conditions within the rock strata being drilled, and allows appropriate warnings to be issued in near real-time so that appropriate actions can be taken.

Claims

1. A method for determining and analyzing, in near real-time, the relative strength of rock strata during drilling operations in an underground mine, said method comprising

(1) collecting data from a plurality of sensors monitoring a rock drill during roof bolt drilling operations;

(2) converting the data to computer readable input data using transducers coupled with the plurality of sensors in near real-time;

(3) analyzing the computer readable input data in near real-time using a neural network analyzer to determine relative strength and classification of the rock strata encountered by the rock drill in near real-time during drilling operations.

2. The method as defined in claim 1, wherein the collected data from the rock drill includes torque, rotation rates, thrust, penetration rates, or depth of drill tip.

3. The method as defined in claim 2, wherein the collected data are used to determine specific energy of drilling, and wherein the specific energy of drilling and at least one other collected data from the rock drill are employed in the neural network analyzer.

4. The method as defined in claim 3, wherein the other collected data is penetration rates.

5. The method as defined in claim 4, wherein near real-time is one second or less.

6. The method as defined in claim 5, further comprising, if the analyzing indicates an unsafe condition, activating an alarm warning workers operating the drill.

7. A method for determining and analyzing, in near real-time, the relative strength of rock strata during drilling operations, said method comprising

(1) collecting data from a plurality of sensors monitoring a rock drill during drilling operations;

(2) converting the data to computer readable input data using transducers coupled with the plurality of sensors in near real-time;

(3) analyzing the computer readable input data in near real-time using a neural network analyzer to determine relative strength and classification of the rock strata encountered by the rock drill; and

(4) providing an output signal detailing the relative strength and classification of the rock strata encountered by the rock drill in near real-time during drilling operations.

8. The method as defined in claim 7, wherein the collected data from the rock drill includes torque, rotation rates, thrust, penetration rates, or depth of drill tip.

9. The method as defined in claim 8, wherein the collected data are used to determine specific energy of drilling, and wherein the specific energy of drilling and at least one other collected data from the rock drill are employed in the neural network analyzer.

10. The method as defined in claim 9, where the other collected data are penetration rates.

11. The method as defined in claim 10, wherein near real-time is one second or less.

12. The method as defined in claim 11, further comprising, if the output signal indicates an unsafe condition, activating an alarm.

13. A system for determining and analyzing, in near real-time, the relative strength of rock strata during drilling operations in an underground mine, said system comprising

(1) a plurality of sensors for monitoring and collecting a plurality of subsets of data from a rock drill, wherein the plurality of the subsets of data correspond to layers of rock encountered by the rock drill during roof bolt drilling operations;

(2) transducers coupled with the plurality of sensors to convert the subsets of data from the rock drill to computer readable data in near real-time;

(3) a computer system to accept and analyze the computer readable data in near real-time using a neural network analyzer to determine relative strength and classification of the rock strata encountered by the rock drill; and

(4) an output device proximate the rock drill and coupled to the computer system to provide an output signal detailing the relative strength and classification of the rock strata encountered by the rock drill in near real-time.

14. The system as defined in claim 13, wherein the collected subsets of data from the rock drill includes torque, rotation rates, thrust, penetration rates, or depth of drill tip.

15. The system as defined in claim 14, wherein the collected subsets of data are used to determine specific energy of drilling, and wherein the specific energy of drilling and at least one other collected subset of data from the rock drill are employed in the neural network analyzer.

16. The system as defined in claim 15, where the other collected subset of data are penetration rates.

17. The system as defined in claim 16, wherein near real-time is one second or less.

18. The system as defined in claim 17, further comprising an alarm that is activated if the output signal indicates an unsafe or hazardous condition.

19. A method for presenting stability data for rock strata during mining operations via a plurality of sensory monitoring the mining operations and a trained neural network, the method comprising:

collecting data from the plurality of sensors monitoring the mining operations, the data comprising stability measurements for one or more rock strata;

transmitting the data to the trained neural network;

receiving a signal from the trained neural network; and

during the mining operations, providing an output signal based on the signal from the trained neural network.

20. The method of claim 19 wherein the output signal is presented in near real-time during the mining operations.

21. The method of claim 19 wherein the output signal is presented proximate the mining operations.