MACSEA Improving Navy Ship Reliability

Military Sealift Command – A Large, Civilian-Operated Navy Fleet Operator

Military Sealift Command (MSC), as part of the U.S. Navy, provides strategic sealift and ocean transportation for U.S. military forces. Its mission is to provide ocean transportation of equipment, fuel, supplies, and ammunition to sustain U.S. forces worldwide during peacetime and in war. MSC operates more than 120 ships worldwide on a day-to-day basis, all crewed by civilian mariners.

As the United States continues to reduce the size of its military presence overseas, our military's readiness and rapid response capabilities depend increasingly on MSC. It is a matter of national priority that MSC ships be available at a moment’s notice and performs reliably when called upon. MSC operates ships that provide combat logistics support to U.S. Navy ships at sea; special mission support to U.S. government agencies; pre-positioning of U.S. military supplies and equipment at sea; and ocean transportation of DOD cargo in both peacetime and war. Recent crises have reinforced MSC’s vital role as a major contributor in the execution of U.S. national strategy.

The Need for Low Asset Costs and High Reliability

The Navy places strong emphasis on reducing the total ownership cost of its assets throughout their life cycle. Studies indicate that manning and maintenance related costs consume the largest part of the operations and support budget and continue to grow most rapidly. Cost reduction efforts are therefore focused on reducing manning levels and implementing Condition-Based Maintenance (CBM) on future Navy ships.

The cost benefits of CBM strategies for machinery health monitoring have been clearly established in many industries, however, an effective CBM program can’t be implemented without expense. Machinery condition must be measured via sensor instrumentation and assessed using special analytical methods, which often require special expertise. Specific CBM work tasks must be diligently performed and can generate significant crew workload requirements. With the trend towards reduced manning, there simply are not enough people to gather and analyze performance data on the multitude of machinery and equipment found aboard Navy ships. This situation has caused a needs gap within the Navy maintenance community.

Advanced Technology for Automating Fleet-wide CBM – Now and in the Future

Existing shipboard machinery automation systems are primarily designed for safety and protection. They also provide large amounts of data for equipment health monitoring; however, transforming massive amounts of data into actionable information for effective CBM remains an arduous task. The situation will be amplified on future all-electric Navy ships, as distributed, integrated power systems will include orders of magnitude more sensors than today’s ships, creating increasingly complex maintenance requirements. Machinery performance monitoring and health assessment are areas where the exploitation of software agent technology will yield substantial near-term economic benefits to the Navy. Software agents can be used to clone human intelligence, perform human-like reasoning, and interact with human clients. Agents can perform tedious, repetitive, time-consuming, and analytically complex tasks more accurately and reliably than people.

Software agents can serve as expert assistants in monitoring, troubleshooting, and predicting failures in complex machinery processes in support of drastic manning reductions on future ships. Imparting intelligent processing functions into software agents will allow the Navy to leverage valuable knowledge across a geographically distributed ship fleet. Agents can be distributed when and where needed to enhance fleet operations, performance, and readiness. Their intelligence can be upgraded remotely. The human-agent team can provide higher levels of platform readiness/reliability at far less cost than that of the equivalent human resource required to perform the same work.

MACSEA Ltd. in Stonington, Connecticut has developed a software product called DEXTER™ that allows its customers to build and deploy machinery health monitoring software agents. The agents are designed to automate the majority of the data gathering and analytics associated with CBM. The software agents are deployed in machinery data networks and perform their work unobtrusively in the background, alerting maintenance and operations personnel when an equipment problem has been detected or predicted to occur in the near future. This allows expeditious isolation and repairing of existing problems and, through predictive analytics, the avoidance of future problems that could impact machinery reliability.

MSC has been one of the early adopters of MACSEA’s intelligent software agent technology to support cost-effective CBM with minimally manned ships. DEXTER agents have been customized and deployed aboard MSC vessels for several years, primarily for diesel and gas turbine engine health monitoring.

Intelligent Software Agents for Condition-Based Maintenance

Intelligent software agents automate the bulk of the work necessary to continuously monitor machinery health. They autonomously perform complex information processing tasks to identify impending failures and accurately predict remaining useful equipment life. Software agents can be deployed to automatically monitor and analyze hundreds of thousands of data points, while being integrated into existing automation system environments at relatively low cost.

Figure 1 illustrates the division of labor between software agents and humans for typical equipment health monitoring tasks. The six main CBM processes include data acquisition, equipment performance analysis, condition assessment, fault diagnosis and isolation, problem verification, and maintenance/repair action. As shown in figure 1, the agents automate the majority of these processes, reducing the human’s role to fault verification and corrective action. Furthermore, these human activities only become necessary after a problem has been identified by an agent, resulting in very significant savings in manpower required for CBM implementation. DEXTER agents can be created for any type of machinery systems for which sensor measurements are available. This technology allows companies that have already invested in plant automation systems and process control software to further leverage these investments with advanced agent-based analytics.

Diagnostic Agents

Diagnostic agents perform real-time assessment of existing alarm conditions. Their automatic fault diagnostics provide troubleshooting assistance to maintenance personnel, directing them to the most likely problems causing the alarms. The agents will reduce troubleshooting time and help restore normal operations as quickly as possible, minimizing the cost of any process disruption. All diagnostic events are logged, allowing a management review of equipment reliability over any operating time interval. A distinguishing feature of diagnostic agents is their real-time assessment of behavioral anomalies of plant machinery. The probabilistic assessment of equipment faults can be particularly useful to new maintenance personnel that may be unfamiliar with plant operations. Their job performance and, in turn, plant reliability, stands to benefit from the knowledge and experience of the team of experts used to develop the diagnostic knowledgebase.


Prognostic AgentsHistory

During World War II, four separate government agencies controlled sea transportation. In 1949, the Military Sea Transportation Service, renamed Military Sealift Command in 1970, became the single managing agency for the Department of Defense's ocean transportation needs. The command assumed responsibility for providing sealift and ocean transportation for all military services as well as for other government agencies.

Only nine months after it's creation, MSC, then named MSTS, responded to the challenge of the Korean War. On July 6, 1950, only eleven days after the initial invasion of South Korea by communist North Korean troops, MSTS deployed the 24th infantry division for duty in Japan to Pusan, South Korea. In addition to transporting troops and combat equipment to and from Korea, command ships supplied U.S. bases and Distant Early Warning line construction sites and supported U.S. nation building efforts in from Europe and Africa to the Far East.

The 1960s brought the conflict in Southeast Asia. From 1965 to 1969 MSC moved almost 54 million tons of combat equipment and supplies and almost 8 million long tons of fuel to Vietnam. The Vietnam era also marked the last use of MSC troop ships. Now, most U.S. troops move primarily by air.

Through the 1970s and 1980s MSC provided the Department of Defense with ocean transportation as part of U.S. determent efforts during the Cold War years.

During the first Persian Gulf War, consisting of Operation Desert Shield and Operation Desert Storm, MSC distinguished itself as the largest source of defense transportation of any nation involved. Command resources were tasked to deliver more than 12 million tons of wheeled and tracked vehicles, helicopters, ammunition, dry cargo, fuel and other supplies and equipment during the war. At the high point of the war, more than 230 government-owned and chartered ships delivering the largest part of the international arsenal that soundly defeated Iraqi aggression.

MSC was also involved in the second Persian Gulf War, Operation Iraqi Freedom, delivering 61 million square feet of cargo and 1.1 billion gallons of fuel by the end of the first year.

Command Relationships

Military Sealift Command is one of three component commands reporting to the joint service U.S. Transportation Command, known as USTRANSCOM. Headquartered at Scott Air Force Base, Ill., USTRANSCOM is under the command of a four-star flag officer and is responsible for the coordination of all common-user Department of Defense air, land and sea transportation worldwide. Common-user ships carry cargo for more than one military service.

In addition to MSC, two other Department of Defense transportation component commands, the U.S. Army's Surface Deployment and Distribution Command and the U.S. Air Force's Air Mobility Command, also fall under the command of USTRANSCOM.


Today, Military Sealift Command has more than 10,800 employees worldwide, approximately 80 percent of which serve at sea. MSC is the largest employer of merchant mariners in the United States. Approximately 5,100 employees are federal civil service, 660 are military personnel; and another 4,600 are employed by MSC contractors.

Transition to War

The transition from peace to war calls for a steady progression of increased levels of sealift ships and personnel to meet contingency requirements. The progression begins with prepositioning sealift.

MSC's prepositioning ships are loaded with combat equipment for U.S. Army, Marine Corps, Air Force and Navy, as well as fuel for the Defense Logistics Agency. The ships are stationed in strategic areas around the world, close to potential contingency areas.

In wartime, prepositioning ships are usually the first ships to respond. In wartime and during other contingencies, the Sealift force can expand dramatically to move the massive amounts of heavy armored combat equipment and other war-fighter supplies from U.S. bases to the theater of operation. MSC first looks to the commercial market to charter suitable U.S.- flagged tonnage. If more tonnage is needed, foreign-flagged ships may be used. MSC may also activate government-owned surge sealift ships, normally kept in reduced operating status. In the event of a full mobilization, more than 1,000 ships and 30,000 people would be employed in sealift missions ashore and afloat.

Ship Programs Military Sealift Command is organized around four programs:

  • Naval Fleet Auxiliary Force or NFAF
  • Special Mission
  • Prepositioning
  • Sealift

  • Navy-Maritime Relationship

    The Voluntary Intermodal Sealift Agreement, or VISA, a partnership between the U.S. government and the maritime industry, was introduced in the mid-1990s to provide joint planning and assured access to commercial shipping at pre-agreed rates during a national emergency. The agreement makes it possible for the U.S. Department of Defense to use the ships and shore-based transportation systems of ocean shipping companies in time of war. In return, the companies receive a subsidy from the federal government or are awarded peacetime defense cargo movement contracts. Thus, the companies and their assets become an integral part of military contingency planning.

    Naval Reserves

    MSC has access to 1,000 selected reservists in MSC reserve units across the US. When mobilized, these reservists quickly take charge of establishing MSC port offices to assist with sealift operations wherever needed.


    MSC's worldwide operations are financed through two working capital funds. The Navy Working Capital Fund is used by MSC to support Navy fleet commanders and other Department of Defense entities. The Transportation Working Capital Fund is used to support sealift services.

    Working capital funds are reimbursed by direct appropriations or by funds transferred into the working capital fund by various MSC customers. MSC receives no direct funding appropriations to support command operations; rather, MSC customers transfer funding for any service they request from MSC into the appropriate working capital fund, and MSC draws funds from the fund to pay for command operations.

    Unlike private industry, working capital funds are budgeted to break even, not make a profit. The cost of MSC operations in 2004 exceeds $3 billion.

    Looking Ahead

    As the United States continues to draw down the size of its land-based military presence overseas, sealift will be an enduring mission. Our military's readiness and rapid response capabilities will depend increasingly on maintaining a presence "Forward…From the Sea."

    Military Sealift Command, with its wide array of ocean transportation resources and its highly trained personnel, performs vital missions around the clock and around the globe. MSC delivers!

    Neural Network Based Diagnostic Reasoning

    During the past several decades, scientists developed computer models of biological neural networks that can learn and perform brain-like functions. These models, referred to as artificial neural networks, are able to learn from examples and are particularly useful for certain tasks, such as pattern recognition. DEXTER agents use neural networks for their diagnostic and prognostic reasoning about machinery faults. The software agent’s neural network automatically learns to associate patterns of alarm conditions with the machinery faults.Missed diagnostic calls and false calls translate directly into added maintenance costs, either from unexpected machinery failures or unnecessary maintenance activities. The robustness of a diagnostic system therefore directly impacts maintenance expenditures, as well as equipment reliability. DEXTER’s neural networks are tolerant of noisy or incomplete input patterns, making their diagnostics more robust than those developed from logic or rule-based approaches. Even if one or more symptoms are missing, DEXTER still identifies the most probable faults based on all available evidence. Reliable Hardware for Harsh Environments

    The diagnostic system that monitors the reliability of the machinery has to be extremely reliable itself. A typical shipboard environment is about as harsh as it gets on a computer system that needs to run continuously for extended periods of time. Corrosion, high vibration, low quality power, frequent power interruptions, high temperature, dust and dirt are some of the factors that can destroy most electronic equipment. While the DEXTER agent server computer isn’t subject to crashing ocean waves, it is subject to all of the other aforementioned factors. MACSEA thoroughly investigated commercial industrial grade computing platforms over ten years ago and selected the Advantech IPC 6806 series computer to host its shipboard diagnostic software. As it turned out, it was the right choice, as this workhorse has performed extremely reliably on over 40 ship installations made over a ten year period. “The Advantech IPC computers have worked reliably on some ships for over ten years without a problem” reports Robin Osmer, MACSEA field service technical manager. “The locations where we install them aren’t the best for computer equipment, which is, in most cases, a small enclosed area inside a control console. Even with poor air flow and high temperatures, these computers just keep on working.”

    Figure 3 illustrates a typical shipboard configuration for deploying DEXTER machinery diagnostics. The DEXTER Server (IPC 6806) interfaces directly with existing machinery alarm monitoring and control systems through a serial or Ethernet connection. This allows real-time machinery performance data to be acquired, archived, and analyzed by the diagnostic software agents. The DEXTER Server is also connected to the ship’s high-speed, fiber optic LAN, which serves as the ship’s data highway. Diagnostic workstations running DEXTER client software are distributed throughout the ship and allow engineers real-time access to plant data and diagnostic agent results. By transmitting real-time machinery performance data across the LAN, DEXTER provides a very convenient and inexpensive means for the engineers to keep a close watch on the machinery plant from the comfort of their staterooms, which are typically several decks away from the control room. When an abnormal event occurs in the middle of the night, they can check it out a few steps away on their workstation, instead of having to walk down several flights of stairs to the control room.

    Prognostic Agents

    Prognostic agents predict machinery problems at their earliest stage of development. Developing equipment problems can often be discovered by degrading performance trends in historical data. Prognostic agents automatically perform statistical trending analysis to detect abnormal machinery performance trends. These agents are important tools for maintenance personnel to implement effective Condition-Based Maintenance (CBM). The predictions of future machinery faults include estimated time to failure, and as such, can help determine when maintenance should be carried out. By predicting machinery problems before they occur, unexpected breakdowns can be avoided. In the absence of significant trends, equipment overhaul periods may be rationally extended, thereby eliminating unnecessary maintenance work. The ability to predict future maintenance requirements improves maintenance planning, cost management, and plant reliability. Maintenance and repair decisions can be tied to actual plant operating conditions based on the severity of degrading trends and predicted plant problems.

    ADAM Modules –Low Cost Solution for Enhanced Gas Turbine Monitoring

    On one particular class of DEXTER-installed ships, the MSC engineers wanted to enhance their monitoring of the main gas turbine engines by measuring the inlet air filter differential pressure. Inlet air has a large impact on gas turbine performance, but for some reason, this particular parameter was not instrumented during ship construction as part of the normal automation system. After receiving a high cost estimate from the control system vendor, MACSEA was approached to suggest a solution. A simple design comprised of an ADAM 4017 8-channel analog input module, small power supply, and enclosure box was subsequently installed and tested aboard the USNS Supply. The ADAM 4017 signals were fed directly into the DEXTER Server for display and analysis. This simple, low-cost solution using the ADAM modules is currently being installed on three additional MSC gas turbine ships.

    Advantech Corporation, eAutomation Group – Founded in 1983, the eAutomation Group of Advantech Corporation is a pioneer in eAutomation technology; combining connectivity, flexibility and ruggedness with today's most reliable PC-based automation technologies. Product offerings include: Open HMI platforms, Industrial Ethernet, Automation Controllers and Software, Fanless Box PCs, Distributed I/O Modules, Plug-in I/O and Industrial Communication for a wide array of industries.

    With the combined talent of more than 2,700 people, Advantech operates an extensive support, sales and marketing network in 17 countries and 28 major cities to deliver fast time-to-market services to our worldwide customers. Today Advantech offers over 700 products and solutions, adding approximately 30 new products each year. US operations for the eAutomation Group are based in Cincinnati, OH (800-205-7940). Advantech Corporation, eAutomation Group, 1320 Kemper Meadow Drive, Suite 500, Cincinnati, OH 45240. Website for Advantech customers in North America: . Email:

    MACSEA Ltd. – Founded in 1982, MACSEA Ltd. is one of the first companies to offer commercial software specifically designed to build and deploy intelligent software agents for automated machinery and process health assessment. Over a decade of research involving artificial neural network models for diagnostic pattern recognition, control, and machine learning has resulted in some of the most advanced agent-based technology on the market for real-time machinery diagnostics and prognostics. Software agent deployment is a rapidly expanding field, as companies realize the potential of software agents to increase profits, improve machinery reliability, and enhance the availability of critical equipment and processes. MACSEA‘s offices: 163 Water Street, Stonington, CT 06378. MACSEA Website: Email: