SBIR-STTR Award

The objective of DoD SBIR 11.2 Solicitation Topic N112-159, Auxiliary System Sensor Fusion, is to develop methods and algorithms that allow sensor information from disparate auxiliary systems to be intelligently fused to provide enhanced situational awareness (SA). A proposal in response to the soliciation topic has been jointly prepared by Technical Documentation Incorporated (TDI), a wholly-owned small business based in King of Prussia, PA and the Center for Data Analytics and Biomedical Informatics, Computer and Information Sciences Department, Temple University based in Philadelphia, PA. The initial six-month period will involve receipt of software, data and documentation from the Government, which will define the notional system simulation of a reduced scale hardware implementation of a shipboard chilled water system and an electrical system. This software, data and documentation, in conjuction with the MATLAB, Simulink and Toolboxes software tool license to be purchased by TDI, will be used to build intelligent algorithms, for the fusion of data obtained from the simulated remote sensors. The intelligent algorithms will be based on proven techniques such as Bayesian belief networks, linear and nonlinear classifiers, Kalman filtering, and Dempster-Schafer. Other techniques may be investigated as they are identified and time and material resources permit.

Benefit:
Currently, Navy ships monitor sensors (temperature, current, pressure, etc) to determine Situational Awareness (SA) by sensing faults and/or events that can cause failures to onboard systems. These sensors individually provide data on the particular system to which they belong or are monitoring and cannot accurately predict the likely result of these potential failures on other systems. Similarly, no method exists to offer an accurate prediction in the case where there are large gaps in data, such as during a catastrophic event. Therefore, the current technology cannot aid the ships crew in determining all prudent corrective actions. An opportunity exists to develop a technology that will present an enhanced capability to predict the likely impact of sensor failure from one system to another, with large gaps in sensor data, and to accurately predict possible future impacts or failures. This will aid in fault detection and isolation, provide the user with an increased overall situational awareness and aid in determining any corrective actions. In addition, this will increase the Operational Availability (Ao), reduce the Total Ownership Cost (TOC) and improve safety of complex systems. These factors are largely driven by the reliability and maintainability of highly integrated equipment and by the cost of the systems and operator and maintenance personnel. Equipment reliability can be improved by increasing Mean Time Between Failure (MTBF) and maintainability can be improved by reducing Mean Time to Repair (MTTR). The TOC to the owners can be reduced by increasing Ao and reducing manpower cost. All of these factors are impacted by enhanced Situational Awareness (SA) and by reducing the number of support personnel required. A means to investigate how to achieve these results through modifications to existing systems hardware and software is proposed in this response to Navy Phase I SBIR Topic N112-159, Auxiliary Systems Sensor Fusion. Significant opportunities for commercialization, as discussed in greater detail in Section 6.0, exist with regard to both Department of Defense and private sector applications. For example, this technology could be integrated into the Navys Integrated Condition Assessment System (ICAS) to allow retrofit into existing shipboard systems. In the private sector, many industries have infrastructures that require the observation of multiple sensors that would also benefit from this technology. For example, Government (TVA) and commercially-owned and operated nuclear power plants use remote sensing and application software for fault detection and fault isolation, and condition-based maintenance, which is very similar to the ICAS software used on US Navy ships.

Keywords:
Intelligent Algorithms, Intelligent Algorithms, US Navy ships, Kalman Filtering, linear and nonlinear classifiers, and Dempster-Schafer, Bayesian Belief Networks, auxiliary systems sensors, data fusion

The objective of ONR SBIR Solicitation Topic N112-159, Auxiliary System Sensor Fusion, is to develop methods and algorithms that allow sensor information from disparate auxiliary systems to be intelligently fused to provide enhanced situational awareness. A Phase II proposal in response to the solicitation topic has been jointly prepared by Technical Documentation Incorporated (TDI), a wholly-owned small business based in King of Prussia, PA and the Center for Data Analytics and Biomedical Informatics, Computer and Information Sciences Department, Temple University based in Philadelphia, PA. The 18-month base period and the nine-month option period contract will involve continuation of the Phase I activity, including use of software, data and documentation from the Government, which defines the notional system simulation of a reduced scale hardware implementation of a shipboard chilled water system and an electrical system. This software, data and documentation, in conjunction with the MATLAB, Simulink and Toolboxes kits software tool license purchased by TDI, is being used to build intelligent algorithms, for the fusion of data obtained from the simulated remote sensors. The intelligent algorithms are based on proven techniques such as Bayesian belief networks, linear and nonlinear classifiers, Kalman filtering, and Dempster-Schafer. Other techniques may be investigated as they are identified and time and material resources permit.

Benefit:
Currently, Navy ships monitor sensors (temperature, current, pressure, etc) to determine Situational Awareness (SA) by sensing faults and/or events that can cause failures to onboard systems. These sensors individually provide data on the particular system to which they belong or are monitoring and cannot accurately predict the likely result of these potential failures on other systems. Similarly, no method exists to offer an accurate prediction in the case where there are large gaps in data, such as during a catastrophic event. Therefore, the current technology cannot aid the ships crew in determining all prudent corrective actions. An opportunity exists to develop a technology that will present an enhanced capability to predict the likely impact of sensor failure from one system to another, with large gaps in sensor data, and to accurately predict possible future impacts or failures. This will aid in fault detection and isolation, provide the user with an increased overall situational awareness and aid in determining any corrective actions. In addition, this will increase the Operational Availability (Ao), reduce the Total Ownership Cost (TOC) and improve safety of complex systems. These factors are largely driven by the reliability and maintainability of highly integrated equipment and by the cost of the systems and operator and maintenance personnel. Equipment reliability can be improved by increasing Mean Time Between Failure (MTBF) and maintainability can be improved by reducing Mean Time to Repair (MTTR). The TOC to the owners can be reduced by increasing Ao and reducing manpower cost. All of these factors are impacted by enhanced Situational Awareness and by reducing the number of support personnel required. A means to investigate how to achieve these results through modifications to existing systems hardware and software is proposed in this response to Navy Phase II SBIR Topic N112-159, Auxiliary Systems Sensor Fusion. Significant opportunities for commercialization exist with regard to both Department of Defense and private sector applications. For example, this technology could be integrated into the Navys Integrated Condition Assessment System (ICAS) to allow retrofit into existing shipboard systems. In the private sector, many industries have infrastructures that require the observation of multiple sensors that would also benefit from this technology. For example, Government (TVA) and commercially-owned and operated nuclear power plants use remote sensing and application software for fault detection and fault isolation, and condition-based maintenance, which is very similar to the ICAS software used on US Navy ships.

Keywords:
auxiliary systems sensors, and Dempster-Schafer, Intelligent Algorithms, Bayesian Belief Networks, US Navy ships, linear and nonlinear classifiers, Kalman Filtering, data fusion ---------- SHIELD uses a combination of AIS, radar, and camera data to perform vessel classification and anomalous traffic identification in the maritime domain. By leveraging machine learning algorithms, the system extracts important features from the data, such as vessel speed, direction, and size, and uses these features to classify and identify vessels. Furthermore, the system can also detect anomalous traffic patterns, such as unusual vessel movements or suspicious activity, which can be flagged for further investigation. Overall, the system can help improve situational awareness within busy ports and harbors, enabling quicker and more effective responses to potential security threats or emergency situations. It can also provide valuable insights into traffic patterns and vessel behavior, allowing for more efficient monitoring and management of maritime traffic. With its ability to integrate multiple data sources and employ advanced machine learning algorithms, the proposed system represents a significant step forward in the field of maritime traffic monitoring and management.

Benefit:
One of the primary benefits SHIELD provides is improved safety and security in ports and harbors. By utilizing real-time data from AIS, radar, and cameras, the system can help detect and identify potential security threats, such as suspicious vessels or unanticipated movements. This can help port authorities take preventive measures to avoid accidents or criminal activities, such as smuggling or terrorism. In addition, the system can provide valuable situational awareness to operators and help them respond quickly and effectively in case of emergencies. Another benefit of SHIELD, that applies to both Government and commercial customers, is improved efficiency in port operations. By providing accurate information on vessel locations, speeds, and directions, the system can help port operators optimize vessel traffic and reduce waiting times. This can help improve the overall throughput of the port and reduce congestion and delays, which can result in significant cost savings for businesses operating in the port. Furthermore, the system can be used to track and monitor cargo movement and help prevent theft or loss of cargo. Overall, the proposed system has significant potential to improve safety, security, and efficiency in port and harbor operations, making it an essential tool for port authorities and businesses operating in these areas.