Monitoring operator condition using sensor data
Systems and methods for monitoring an operator of an asset are described herein. The method includes receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments. The method can also include training a machine learning model to recognize one or more operator conditions based on the received training data and receiving sensor data from a plurality of sensors associated with the asset or the operator. The method can further include determining an operator condition of the operator based on the received sensor data and the machine learning model and taking one or more actions in response to the determined operator condition.
1. A method for monitoring an operator of an asset, the method comprising:
receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments;
training a machine learning model to recognize one or more operator conditions and asset statuses based on the received training data;
receiving, from at least one asset sensor, asset data that indicates an operating status of the asset;
receiving, from at least one biometric sensor, biometric data associated with the operator;
determining, by the machine learning model, an operator condition of the operator has reached an impairment threshold based on the biometric data;
identifying, by the machine learning model, at least one risk parameter in a current operation of the asset based on the operating status of the asset; and
in response to determining the operator condition has reached the impairment threshold and the at least one risk parameter, sending, to the asset, a command that remotely shuts down operation of the asset.
2. The method of claim 1 , wherein the training sensor data further comprises one or more known sensor readings associated with a particular performance impairment.
3. The method of claim 1 , wherein the different performance impairments are simulated using a biomechanical model operating a simulated version of the asset.
4. The method of claim 1 , wherein the training data further comprises historical data from known incidents, the known incidents including a known operator condition and one or more known sensor readings.
5. The method of claim 1 , further comprising:
collecting data on a performance impact or a safety impact of the operator condition; and
estimating a financial impact of performing a task with the asset while the operator is affected by the operator condition based on the collected data, and
taking one or more actions based on the financial impact of performing the task while the operator is affected by the operator condition.
6. The method of claim 5 , wherein the collected data is collected using a simulation of the received sensor data.
7. The method of claim 5 , wherein the one or more actions includes initiating a safety measure for the asset, providing a recommendation to the operator of the asset, assess a quality of training of the operator, ensure compliance with one or more reporting requirements, quantify a productivity loss of the operator, and recommend a countermeasure to the operator condition.
8. A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a process for monitoring an operator of an asset, the process comprising:
receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments;
training a machine learning model to recognize one or more operator conditions and asset statuses based on the received training data;
receiving, from at least one asset sensor, asset data that indicates an operating status of the asset;
receiving, from at least one biometric sensor, biometric data associated with the operator;
determining, by the machine learning model, an operator condition of the operator has reached an impairment threshold based on the biometric data;
identifying, by the machine learning model, at least one risk parameter in a current operation of the asset based on the operating status of the asset; and
in response to determining the operator condition has reached the impairment threshold and the at least one risk parameter, sending, to the asset, a command that remotely shuts down operation of the asset.
9. The non-transitory computer-readable medium of claim 8 , wherein the training sensor data further comprises one or more known sensor readings associated with a particular performance impairment.
10. The non-transitory computer-readable medium of claim 8 , wherein the different performance impairments are simulated using a biomechanical model operating a simulated version of the asset.
11. The non-transitory computer-readable medium of claim 8 , wherein the training data further comprises historical data from known incidents, the known incidents including a known operator condition and one or more known sensor readings.
12. The non-transitory computer-readable medium of claim 8 , the process further comprising:
collecting data on a performance impact or a safety impact of the operator condition;
estimating a financial impact of performing a task with the asset while the operator is affected by the operator condition based on the collected data, and
taking one or more actions based on the financial impact of performing the task while the operator is affected by the operator condition.
13. The non-transitory computer-readable medium of claim 12 , wherein the collected data is collected using a simulation of the received sensor data.
14. The non-transitory computer-readable medium of claim 12 , wherein the one or more actions includes initiating a safety measure for the asset, providing a recommendation to the operator of the asset, assess a quality of training of the operator, ensure compliance with one or more reporting requirements, quantify a productivity loss of the operator, and recommend a countermeasure to the operator condition.
15. A computing device for monitoring an operator of an asset, the computing device comprising:
one or more processors; and
a memory comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform a process, the process comprising:
receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments;
training a machine learning model to recognize one or more operator conditions and asset statuses based on the received training data;
receiving, from at least one asset sensor, asset data that indicates an operating status of the asset;
receiving, from at least one biometric sensor, biometric data associated with the operator;
determining, by the machine learning model, an operator condition of the operator has reached an impairment threshold based on the biometric data;
identifying, by the machine learning model, at least one risk parameter in a current operation of the asset based on the operating status of the asset; and
in response to determining the operator condition has reached the impairment threshold and the at least one risk parameter, sending, to the asset, a command that remotely shuts down operation of the asset.
16. The computing device of claim 15 , wherein the different performance impairments are simulated using a biomechanical model operating a simulated version of the asset.
17. The computing device of claim 15 , wherein the training data further comprises historical data from known incidents, the known incidents including a known operator condition and one or more known sensor readings.
18. The computing device of claim 15 , the process further comprising:
collecting data on a performance impact or a safety impact of the operator condition; and
estimating a financial impact of performing a task with the asset while the operator is affected by the operator condition based on the collected data, and
taking one or more actions based on the financial impact of performing the task while the operator is affected by the operator condition.
19. The computing device of claim 18 , wherein the collected data is collected using a simulation of the received sensor data.
20. The computing device of claim 18 , wherein the one or more actions includes initiating a safety measure for the asset, providing a recommendation to the operator of the asset, assess a quality of training of the operator, ensure compliance with one or more reporting requirements, quantify a productivity loss of the operator, and recommend a countermeasure to the operator condition.