SYSTEM AND METHOD FOR OPTIMIZING FUEL USE IN A MARINE VESSEL

Abstract

A marine vessel advisory system can be configured to calculate and provide operational information showing fuel savings based on adjustments to the vessel's speed and / or heading. In one mode, the advisory system can operate in real time to gather information on operational and / or environmental conditions, which is then used to calculate alternative vessel operating performance that will save fuel and reduce emissions. The calculations may include simulation, machine learning, and / or artificial intelligence to determine a vessel speed and / or heading that will reduce fuel consumption. The advisory system can display the calculated information to the operator, who can then choose to switch to the alternative operating parameters (e.g., slower speed).In one mode, the advisory system can interact directly with a marine vessel system and automatically cause the marine vessel system to adjust operating parameters based on calculated operating parameters that save fuel and reduce emissions.

Description

SYSTEM AND METHOD FOR OPTIMIZING THE USE OF FUEL IN A MARINE VESSEL Cross-reference to related application This application claims priority to the pending U.S. provisional patent application Serial No. 62 / 878,270 filed July 24, 2019, the entire contents of which are incorporated by reference. Background of the invention Vessels, such as cargo vessels, drilling vessels, underwater vessels (such as ROVs), research vessels, or any other maritime vessel, have many mechanical and electrical systems and subsystems (e.g., engines, electrical systems, mechanical systems, electromechanical systems, hydraulic systems, communications systems, sensors, etc.) (hereafter, vessel system) that are used to control and operate the vessels. Operators of these vessels rely on the vessel system and subsystems to remain in good working order to minimize vessel downtime. The vessel system has operating parameters within which the vessel system operates properly.However, as a result of normal vessel wear and tear over time, the vessel system must be maintained to prevent a potential catastrophic failure that could disable or impair the vessel's operation. In most cases, the vessel system has many sensors used to detect various operating parameters (e.g., pressures, temperatures, forces, etc.) of the vessel system. The sensors generate sensor signals that are typically available to operators through one or more user interfaces at the vessel's helm in one form or another. For example, if an operating parameter crosses a threshold level detected by a sensor, the sensor signals are used to trigger a notification in the form of an audible and / or visual indicator to the operator.One problem is that a vessel system can have hundreds or thousands of parameters or variables, resulting in an operator typically managing operations in a reactive mode when indicators show signs of trouble (e.g., sensor signals indicating overheating, pressure changes, fluid leaks, power decreases, etc.). Due to the overwhelming number of variables and the limited number of available indicators that can be displayed on a user interface, an operator's ability to monitor every indicator to track the operations of each system is not possible.Furthermore, the nominal levels of a vessel's system's variables can be difficult for operators to track, and environmental conditions, such as outside temperature, water temperature, tidal conditions, etc., can affect variables in ways that an operator may not be able to track, leaving them unidentified and unaddressed until an imminent or actual failure occurs. As such, there is a need for a more proactive system that can help an operator manage the monitoring of each of the systems. / 1 / Qbn / zznz / q / YiAi Maritime vessels consume large amounts of fuel and produce significant emissions when in operation. Logistics management of maritime vessels, such as ferries and transport vehicles, includes the management of maritime vessels before, during, and after transportation. Management may include planning, transportation, monitoring collision avoidance, following rules of procedure, fuel conservation, generating transportation reports when delayed, and so on. As is understood in the art, the fuel efficiency of maritime vessels is important because maritime vessels consume a lot of fuel due to the use of large-capacity engines, and such fuel consumption is costly and has a high environmental impact.Even if electric motors are used now or in the future, conserving energy by traveling efficiently is necessary to save money, reduce electricity usage, and increase the productivity of the vessel and crew. As part of the logistics management of maritime vessels, such as ferries and cargo ships, berthing is an important area where docking can be difficult due to the size of the vessels, the challenges of viewing the docks directly from the bridge, environmental conditions such as wind and water current, and so on. Multiple crew members are often needed to assist in viewing and guiding the vessel during berthing. Cameras that look alongside, behind, and / or in front of a vessel can be used to assist the crew or captain in the berthing process by adding viewing capability. Despite having cameras, berthing processes are generally performed manually, with many of the same challenges as berthing without cameras. Brief description of the invention Managed transportation of a maritime vessel can be achieved by optimizing the transportation operation of the maritime vessel. By optimizing the transportation operation, a number of different tools can be provided to vessel operators utilizing a maritime vessel. The maritime vessel can be configured to receive a destination location and a time by which the cargo is to arrive at the destination location, and calculate the navigation points through which the maritime vessel should travel to the destination location. One such tool can be an advisory system that can be configured to include a simulator. In one embodiment, the simulator can be configured to perform route planning, which can include setting different speeds for a route to determine fuel usage, and route planning based on environmental conditions (e.g., wind and current).In one embodiment, the advisory system may include a simulator tool that simulates the route with different vessel parameters and speeds to determine fuel usage. In one embodiment, a desired fuel usage may be input into the advisory / planning system to determine the time, route, start or end time, etc. In one embodiment, maximum fuel efficiency may be determined at speeds that allow the vessel to travel through the navigation points to establish a departure time and arrive at the destination location at the destination time. Additionally, or alternatively, the advisory system may include a machine learning module that learns from the past performance of the maritime vessel and helps / 1 / Qbn / zznz / q / YiAi identify optimal operating parameters to reduce fuel consumption.Artificial intelligence can be used to recognize operational and / or environmental conditions (e.g., water current, wind speed and direction) to help determine the optimal speed of the maritime vessel to save fuel during part or all of the vessel's voyage. A Conditional Online Risk Advisory System (CORBAS) (advisory system) may provide monitoring and notifications and alerts to a user regarding abnormalities in a vessel system, including engines, electrical systems, mechanical systems, electromechanical systems, hydraulic systems, communications systems, sensors, etc., (ship system) of a vessel where the advisory system operates, or another vessel system, to provide proactive and efficient operation of a vessel system. The advisory system may also provide optimizations to reduce costs and increase uptime. The advisory system utilizes a machine learning system, as the system can learn from the user to gain more insights over time.Using machine learning, the advisory system can maintain monitoring of the vessel system, but limit (i) false positive and false negative notifications and (ii) alarms and verification communications with the user or operator. In one embodiment, the advisory system may be configured to (i) continuously monitor vessel system variables, (ii) provide automatic and rapid warning in case of approaching limits of the system of variables, (iii) report information about the status, trends and health of the vessel system, (iv) present statistics of the vessel system, (v) provide indicators and / or directives (e.g., green (nominal), yellow (warning) and red (alarm)) for operations, (vi) calculate dependencies between variables, and / or (vii) become more knowledgeable or more intelligent based on human interaction.Such human interactions may include requesting that an operator confirm the correlation between variables and relevance, which will allow the advisory system to learn which variables are related to a time and are relevant to reduce human interaction thereafter, and provide appropriate notifications and guidance in response to the identification of the same or similar conditions leading to the interaction. An embodiment of an advisory system for operating a vessel may include at least one system configured to operate the vessel. Multiple sensors may be configured to detect variables of the systems, where the variables may be representative of the functional parameters of at least one system. A processor may be in communication with the systems and the sensors, and configured to identify a change in the values ​​of a first variable over a period of time. In response to determining the change in the values ​​of the first variable, the first variable may be correlated with a second variable that has a change in values ​​over at least a portion of the time period. A notification may be generated that includes the first and second variables and a change in their values ​​to allow an operator to indicate whether the first and second variables should be correlated with each other.In response to receiving an indication from the operator that the first and second variables should be correlated with each other, an indicator may be stored that the first and second variables are correlated with each other. Otherwise, an indicator may be stored that the first and second variables are uncorrelated with each other. Subsequently, in response to identifying a change in the values ​​of the first and second variables, a determination may be made as to whether an indicator exists that is indicative of the first and second variables being correlated with each other, and if so, an alert may be generated to the operator of the changing values ​​of the first and second variables. Otherwise, an alert may not be generated to the operator of the change in the values ​​of the first and second variables. An embodiment of a vessel operation process may include sensing variables of a system, where the variables may be representative of functional parameters of the system. A change in the values ​​of a first variable over a period of time may be identified. In response to determining the change in the values ​​of the first variable, the first variable may be correlated with a second variable that has a change in values ​​over at least a portion of the time period. A notification including the first and second variables and the change in their values ​​may be generated to allow an operator to indicate whether the first and second variables should be correlated with each other. In response to receiving an indication from the operator that the first and second variables should be correlated with each other, an indicator indicative that the first and second variables are correlated with each other may be stored.Otherwise, an indicator that the first and second variables are not correlated with each other may be stored. Subsequently, in response to identifying a change in the values ​​of the first and second variables, it may be determined whether an indicator exists that indicates that the first and second variables are correlated with each other, and if so, the operator may be notified of the changing values ​​of the first and second variables. Otherwise, a warning to the operator of the change in the values ​​of the first and second variables may not be generated. As a result, false positive and false negative notifications of vessel system status to an operator may be reduced. An embodiment of a vessel operation process may include identifying a first trend change in sampled values ​​over a first time period of a variable, where the variable may be representative of a functional parameter of the vessel. In response to determining the first trend change in the sampled values ​​of the variable, a notification may be generated that includes an indication of the first trend change in the sampled values ​​of the variable. The notification that includes the indication of the first trend change in the sampled values ​​of the variable may be communicated to an operator. The communication may be performed in any manner, such as by displaying on a user interface of an operator console, as described previously in this document.In response to receiving an indication from the operator as to whether the first trend change in the sampled values ​​of the variable is normal, a first indicator as to the first trend change in the sampled values ​​of the variable may be stored for future use. Otherwise, in response to receiving an indication from the operator that the first trend change in the sampled values ​​of the variable is not normal, a second indicator as to the first trend change in the sampled values ​​of the variable not being normal may be stored for future use. Brief description of the drawings Illustrative embodiments of the present invention are described in detail below with reference to the accompanying drawing figures, which are incorporated herein by reference, and in which: Figure 1 is an image of a maritime vessel including a vessel system used to control and operate the maritime vessel; Figure 2 is a schematic of an illustrative vessel system; Figure 3 is an illustrative user interface placed on a bridge of a maritime vessel through which a vessel system may be interconnected; Figure 4 is a block diagram of an illustrative vessel system in communication with an advisory system used to monitor vessel system variables and provide notifications and alerts to an operator via a user interface; Figures 5A and 5B are a high-level flow diagram of an illustrative advisory system process including components and processes that interact with a user to determine whether correlated variables of a vessel system are dependent and / or relevant; Figure 6 is an illustrative common deviation curve that may be used by an advisory system to help monitor changes in a parameter or combination of parameters of a vessel system to operate a vessel; Figure 7 is a graph showing an illustrative variable with an upward trend in temperature over time together with established warning levels that can be used as indicators for an operator by an advisory system; Figure 8 is an illustration of a high-level illustrative design of a user interface that may be used by an operator in leveraging a vessel system; Figures 9A and 9B is an illustration of an illustrative checklist or status indicator user interface of a vessel system for operating a vessel; Figure 10 is an illustration of an illustrative chart showing the temperature dependencies of a generator of a ship system for operating a ship; Figure 11 is a flow diagram of an illustrative advisory process to support a vessel operator; Figure 12 is a flow diagram of another illustrative advisory process to support a vessel operator; Figure 13 is an illustration of an illustrative waterway in which a vessel may travel and perform real-time reconnaissance on the fuel consumption of a vessel while traveling from point A to point B; Figure 14 is a block diagram of an illustrative vessel system in communication with an improved advisory system compared to the advisory system; / 1 / Qbn / zznz / q / YiAi Figures 15A and 15B are two graphs showing a power versus ground speed curve and a power versus ground speed curve; Figure 16 is an illustrative user interface that produces data representative of the vessel's current speed and fuel savings as a function of a change in speed in kilometers per hour (knots), reduced emissions (e.g., NOx and COz), and an amount of fuel savings over a certain number of kilometers (nautical miles) (e.g., 185.2 km (100 Nm)); Figure 17 is a graph of a portion of the power curve versus ground speed; Figures 18A to 18D are a user interface illustrating a series of operating parameters of a vessel control and propulsion system for driving the seagoing vessel; Figures 19A and 19B is a user interface showing illustrative operating parameters of the maritime vessel; Figure 20 is a graph showing illustrative total fuel by vessel operating mode; Figure 21 is a fuel consumption report that includes a trip summary and recommendations and savings; Figure 22 is a graph showing (i) the actual speed over the ground and fuel rate curves and (ii) the recommended speed over the ground and fuel rate curves; Figure 23 is a graph showing active generators and propulsion devices (e.g., propellers and generators); Figure 24 is a flow diagram of an illustrative simulation run by an advisory system to determine more efficient fuel consumption for a maritime vessel; Detailed description of the invention Maritime vessels, such as the maritime vessel 100 shown in Figure 1, are used for shipping goods, people, and equipment around the world. Maritime vessels operate in many different environmental conditions, including weather, temperature, and water temperature. The environment can have an impact on the operation of vessels, as well as the systems and components used to operate and control them. Maritime vessels have vessel systems made up of electrical, mechanical, electromechanical, hydraulic, pneumatic, and other systems and components used to operate and control them. An illustrative vessel system 200 is shown in Figure 2. In managing a vessel in which the vessel system is employed, an operator may interact with the vessel system 200 through user interfaces 200a to 200n, such as those shown in more detail in Figure 3, which are typically located on a bridge or control center of a vessel. The vessel system 200 is shown to include a variety of subsystems and components, including a propulsion unit including propulsion motor elements 204a to 204n (collectively 204) and thrusters 206a to 206n (collectively 206).The thrusters 206 may include (i) conventional propellers that may be driven / 1 / Qbn / zznz / q / YiAi by power plants (e.g., diesel engines) 208a to 208n (collectively 208) and (ii) electrically controlled thrusters (e.g., tunnel thrusters) that are driven by electrical equipment that may convert power from a main shaft extending from the power plant 208 that drives the propulsion unit 206. The vessel system 200 may further include dynamic positioning controllers 210a to 210n (collectively 210) that may be configured to semi-automatically or automatically operate the power plants 208. The dynamic positioning controllers 210 may be used to control the direction of the vessel by applying a certain amount of power to control the thrust of each of the power plants and / or the propulsion unit 206. The dynamic positioning controllers 210 may also be configured to control the angle of one or more rudders (not shown) of the vessel to further assist in maneuvering the vessel, as desired by the operator interacting with the user interfaces 202.For example, the operator may adjust the position of a joystick 212 (e.g., forward-left, forward-right, reverse-left, reverse-right) to cause any speed and direction of the power plants 208, propulsion unit 206, and / or rudders to be adjusted to cause the vessel to follow an operator command. Alternatively, the user interface 200 may be programmed to automatically steer the vessel to a particular coordinate, such as a global positioning system (GPS) coordinate. The vessel system 200 may further include sensors 214a to 214n (collectively 214). The sensors 214 may be environmental sensors configured to detect environmental parameters (e.g., wind, current, temperature, atmospheric pressure, etc.) and operational sensors to detect operational parameters (e.g., voltage, current, vibration, direction, equipment and / or fluid temperature, fluid pressure, rotational speed, etc.). By monitoring the various environmental and operational parameters, the vessel system 200, which may include an advisory system that can be configured to self-monitor and self-diagnose the subsystems and components of the maritime vessel and the vessel system 200 to provide the operator with information to help prevent a catastrophic failure of the maritime vessel, as described later herein. With respect to Figure 3, an illustration is shown of an exemplary bridge 300 of a vessel system including user interfaces 302a to 302n (collectively 302). One or more of the user interfaces 302 may be used to display notifications generated by an advisory system running by a computer system within the bridge 300 or elsewhere. The visual notifications may be in the form of text, graphics, a pop-up window, or other graphical user interface element that may be brought to the attention of an operator of the user interfaces 302. In one embodiment, an audible notification may also be generated in conjunction with the visual notification.In addition to causing a visual and / or audible notification to be generated and presented on one or more of the user interfaces 302, a notification (e.g., text message, email, instant message, or otherwise) may be communicated to a mobile electronic device (e.g., mobile phone, handheld controller with user interface, etc.) to notify an operator in the event that the operator is not currently located on the bridge 300. / 1 / Qbn / zznz / q / YiAi General Architecture A monitoring or advisory system is a hardware / software system configured to monitor subsystems of a maritime vessel (or other vehicle, such as an aircraft), determine and / or identify problems or potential problems with subsystems and components, and attempt to correlate variables that may be indicative of problems or potential problems with the subsystems and components. The advisory system can be used to create notifications with warnings, alarms, predictions, and optimizations for a vessel's vessel system. In accordance with the principles described herein, a secure and trusted relationship can be created between a human operator or user and the advisory system. If the advisory system cannot calculate reliable reports for the user, the advisory system will lose its integrity and value to a vessel operator.One feature that provides success for an advisory system as provided herein is the ability to learn from the user, which makes the advisory system more educated over time, thus being able to advise an operator when the relevance of importance is determined and ignore situations that are deemed irrelevant or not significant enough (e.g., false positives and false negatives) for the operator to attend to.

[0027] Referring to Figure 4, a block diagram of an illustrative vessel system 400 is shown in communication with an advisory system 402 that is used to monitor vessel system variables and provide notifications and alerts to an operator via a user interface 404. The vessel system 400 may collect and communicate variables 406 collected by sensors that are configured to collect operational data from systems and subsystems (e.g., see Figure 2) comprising the vessel system 400. The variables 406 (i.e., values ​​collected from the sensors or derived from values ​​collected from the sensors) of the vessel system 400 are communicated to user interfaces 404 for display (see, e.g., Figure 3) in conjunction with an advisory system 402 that may process the variables 406 to monitor the variables 406 and determine possible correlations. In one embodiment, variables 406 may include one or both of environmental parameters and operational parameters of the maritime vessel as detected by vessel system 400, and advisory system 402 may use variables 406 to determine whether a problem has or may be developing along with possible underlying causes of the problem.For example, if the vessel's speed does not match the speed at which the operator has commanded, the advisory system 402 may correlate that a fuel pump sensor may detect that a fuel pump is not pumping an anticipated amount of fuel, a wind sensor may detect that a headwind speed is higher than anticipated by a controller, a current sensor may detect that a water current speed is higher than anticipated by the controller, an electrical current sensor may detect that a quantity, or a combination of the parameters may correlate with each other. The advisory system 402 may include a processor comprised of one or more / 1 / Qbn / zznz / q / YiAi processors, memory, an input / output (I / O) unit configured to communicate over a local area network (e.g., with a ship system computer) or a broadband area network (e.g., satellite network, internet, etc.). In one embodiment, the advisory system 402 may communicate correlation confirmation requests 408 to user interfaces for a human operator to provide feedback or confirmation 410 as to whether the identified correlations of the parameters or variables 406 in the correlation confirmation requests 408 are related and / or relevant.That is, if the advisory system 402 is unsure that two or more variables 406 are correlated with each other and a notification or alert 412 is determined to be due to a fault or potential fault, then the advisory system 402 may communicate one or more correlation confirmation requests 408 to the user interfaces 404 so that an operator may assist the advisory system 402, which is a machine learning system, in learning which variables are relevant and / or related to each other. Over time, the advisory system 402 may learn to substantially reduce or eliminate the need to send correlation confirmation requests 408 to the operator. The user interfaces may be the same as or different from the user interfaces used to directly interact with the vessel system.For example, user interfaces with which the advisory system may interact may be mobile devices, web pages, emails, SMS messages, or any other user interface that allows the user to provide feedback to the advisory system. With respect to Figures 5A and 5B, a high-level schematic of an illustrative advisory process 500 that may be executed in an advisory system is shown. The process 500 may be configured to receive a data input point 502 from a sensor, such as an environmental sensor or an operational sensor, and provide the data input point 502 to an outlier rejection filter 504 for processing. The outlier rejection filter 504 may be configured to determine if the data input point 502 is outside a common range of a parameter or variable whose data input point 502 is defined. In step 506, it may be determined whether the data input point 502 should be accepted. Otherwise, in step 508, the data input point 502 may be marked as rejected so that the data input point 502 is not used for any data processing.In one embodiment, a determination may be made to determine whether repeated unacceptable data entry points are being determined to notify an operator of the existence of a potential problem with a sensor. If it is determined in step 506 that the data entry point should be accepted as a result of not being filtered by the outlier rejection filter 504, the process 500 may continue to step 510, where the data entry point 502 may be marked as accepted. It should be understood that the data entry point 502 may simply be accepted or not accepted without actually creating and assigning a flag to the data entry point 502. The process may continue at step 512, where it may be determined whether data entry point 502 should complete one of a predefined time series of accepted data. Otherwise, the process may continue to step 514, where data entry point 502 may be stored in a database. Otherwise, in step 516, data entry point 502 may be used / 1 / Qbn / zznz / q / YiAi to calculate the mean, standard deviation, confidence intervals, low and high warning thresholds, intercept, and slope for a time series, etc. The database may be configured to store variable data and correlation data. In step 518, it may be determined whether the rate of change and / or slope is too rapid. Otherwise, in step 520, the mean, standard deviation, confidence intervals, low and high thresholds, intercept, and slope may be flagged as normal.Otherwise, in step 522, dependencies and correlations with other variables can be checked or determined. In step 524, it may be determined whether any other variables explain the behavior described by the statistics calculated in step 516. In either case, the advisory system may notify and ask the operator whether the behavior described by the statistics is normal or typical, and whether any dependencies between the variables can be used to describe the behavior. As described above, behavior (e.g., diesel engine temperature tending to rise) may be identified before it occurs using correlated variables or parameters that are measured by sensors. The operator may be able to provide an answer to the question as to whether the behavior is normal and / or whether one or more variables correlate with the behavior. In general, a variable should be correlated if it is outside of common levels or specifications.In one embodiment, if a value of one or more variables or parameters is above or below a maximum or minimum specification, then the variables may be considered for correlation, and if they are potentially related to the variable potentially causing the behavior, the variables may be provided to the operator, such as operator 528, for confirmation. Operator 528 may be provided with two options for answering the question of whether the behavior is normal and / or whether one or more variables correlate with the behavior. If so, then process 500 may continue to step 530, where the rate of change limit may be updated. A mean, standard deviation, confidence intervals, low and high warning thresholds, intercept, and slope may be flagged as normal and stored in the database in step 514. Alternatively, in step 532, the mean, standard deviation, confidence intervals, low and high warning thresholds, intercepts, and slope may be flagged as abnormal and stored in the database in step 514. In another aspect of process 500, a coefficient of determination between two variables may be calculated in step 534. In step 536, a determination is made as to whether a value of the coefficient of determination between the two variables is above a certain percentage, such as 40%. It should be understood that other threshold percentages may be used. Otherwise, the process returns to step 534. If so, in step 538, a notification and query may be made to an operator 540 as to whether a valid dependency exists between the two variables that are determined to be correlated. Operator 540 may be the same as operator 528. Operator 540 may be provided with two options that allow operator 540 to make one of two decisions, including (i) that the variables are not dependent on each other in step 542, and (ii) that the variables are dependent on each other in step 544.The decision as to whether the variables are confirmed to be correlated may be stored in the database in step 514. / I 7Qbn / 77n7 / q / YIAI In general, the process 500 may provide for communication with operators to verify dependencies or correlations along with the relevance of variables to the behaviors of the vessel system or components thereof. The advisory system process 500 may be executed by a computer system on a vessel that is part of a vessel system, on a separate system (e.g., server or other computer system) on the vessel, or located remotely from the vessel, such as in the cloud or within a facility of a vessel operator or a third party, such as the developer of the advisory system. It should be understood that the advisory system process 500 is illustrative and that a wide variety of alternative configurations and processes may be utilized. False warnings and alarms are reduced or eliminated using the advisory system provided in this document. By using the 504 outlier rejection filter, spikes in data collected on a vessel can be effectively eliminated. By removing spikes from collected data, not only are false notifications reduced or eliminated, but data collection for calculating nominal values ​​can also be improved. Nominal values ​​contain an expected value for a monitored variable with upper and lower warning levels. An example of such a monitored variable is the voltage of a 12-volt battery, where the voltage may vary between 11 and 13 volts. As is understood in the art, a range between 11 and 13 volts may depend on an operating state. The same battery may also have absolute upper and lower alarm limits, which are typically set by the battery manufacturer. In this case, the lower and upper alarm limits could be 10 and 14 volts, respectively. Nominal values ​​can be calculated and based on collected data, which are assumed to operate under normal conditions for a defined period. The assumption of operating under normal conditions is reasonable, as the initial data collection can occur shortly after a supplier and regulatory body have approved the equipment and vessel for operation. In one embodiment, a minimum of one hour can be used to collect data to determine the initial nominal values ​​to be calculated. Other durations can be used to collect data to establish nominal values ​​that are used for different systems and subsystems of the vessel system. A reasonable question might be: How can we know that the monitored variable will be nominal in the hours, days, and weeks that follow an initial period (e.g., one hour) of data collection? The answer to this question lies in the use of machine learning in interacting with the human operator 528 and 540. In one embodiment, utilizing regression methods to predict the future of variables, the advisory system can predict when a variable will reach upper and lower warning and alarm thresholds. When the advisory system detects the threshold crossing, the advisory system can first check for any correlation with other variables, such as geolocation, sea temperature, and others. It should be understood that there may be hundreds or thousands of variable correlation determinations that can be made from a vessel system and the environment in which the vessel operates. The advisory system can then notify the human operator or user for confirmation on the variable's behavior. The human decision can be fed back to the advisory system, so that the advisory system can adjust its actions the next time the same or similar situation arises. By enabling human interaction, the advisory system can learn and remember how a human would handle a given situation (for example, whether a particular correlation between detected signals is relevant), leading to a more intelligent monitoring and advisory system that can create reliable and trustworthy notifications and reports for the operator. Over time, the advisory system can suggest optimizations to the client for more cost-effective and less time-consuming vessel operations. The advisory system may utilize modern advances in Global Navigation Satellite System (GNSS) receivers and Global Positioning System (GPS) receivers, including accuracy, reliability, and quality calculations based on guidance documentation from the International Marine Contractors Association (IMCA) and the International Association of Oil and Gas Producers (OGP). The use of advanced positioning receivers allows the advisory system to use accuracy to correlate positioning with certain other variables or parameters, as described later in this document. For example, the advisory system can utilize some or all of the data available from modern GNSS receivers and correlate the data with solar interference, GNSS receiver configuration, changes in constellations based on geolocation and time and date, and other external interference to provide proactive measures and ensure safe operations across the fleet (in the case where the vessel is part of a fleet of vessels). For example, as a vessel approaches an oil platform, the advisory system can continuously monitor the data for accuracy, reliability, and quality. It can detect blocking of correction satellites, multipath issues, or any other negative trend in quality measurements. If the advisory system has previously detected one of the previous scenarios, it can predict whether that scenario will occur again.This way, the advisory system can proactively notify and advise other vessels approaching the same oil platform if the advisory system detects a similar scenario. Detailed functionality Each collected data variable can be processed by the 504 outlier rejection filter to remove spikes and outliers, ensuring a better basis for calculating nominal values. Spikes and outliers negatively affect nominal values ​​and cause false warnings and alarms if not eliminated. An outlier filter 504 based on the median absolute deviation can provide a shape / 1 / Qbn / zznz / q / YiAi χ — — y* w γ. *avgxstd—_Jz¿=iO¿— xavg^ The standard deviation for the variable can be used to calculate the upper and lower warning thresholds. In statistics, for a normally distributed data set, there is a rule called the 68-95-99.7 rule that correlates with the 1-sigma, 2-sigma, and 3-sigma standard deviations used to measure the percentage of values ​​that fall within a band around the mean, as shown in Figure 6. For example, given a sampling rate of 1 Hz (i.e., one sample per second), and using 3 standard deviations to calculate the lower and upper warning thresholds, 99.7% of all samples fall within the band. After one day, 86,400 samples are collected, of which 2,592 are outside the band, which would equate to an average warning every 3 seconds, which is too frequent for a vessel's operation. Using 4.5 or 5 standard deviations instead provides a warning on average every 2 or 20 days, respectively, which is a much more practical time interval to receive warnings for a vessel system that is sampled every second. The upper and lower warning thresholds can be calculated using the following equations: Upper warning threshold = xavg+k-xstd Lower warning threshold = xavg—.k-xstd, where the chosen multiplier k may be adjustable to allow an operator to make the warning thresholds narrower or wider. In one embodiment, A k = 5 may be set as the default for all variables. In one embodiment, k may be set so that the thresholds fall within the upper and lower alarm thresholds, which may be set by a manufacturer of a system or subsystem of a vessel system providing variables being monitored. The upper and lower threshold for the 95% confidence interval can be calculated using the following equations: Upper confidence threshold = xavg+ 1.96 Lower confidence threshold = xavg-1.96 Predictions A prediction of where a variable will be located in the future can be used in the advisory system, as predictions allow for an understanding of when the variable might reach upper or lower warning and alarm thresholds. This prediction system, used by the advisory system, allows a vessel operator to be proactively notified when the vessel system / 1 / Qbn / zznz / q / YiAi being monitored might present a problem. There are many methods for predicting the future, including linear and nonlinear regression methods, but for simplicity, the advisory system provided in this paper may initially focus on a linear alternative, which is based on fitting an available data set to the following linear equation: x¡ = a + β·ίί„ where t¡ is the time for the current sample i, a is the intercept, and β is the rate of change for the variable x¡, βγ a can be calculated with the following equations: Σ / Λ'ί- <<^0 θ' — Xavy—β ' tavg. where xavg is the average of all measurements in the available data set, and tavg is the average of all time samples in the available data set. The linear equation can be used to calculate when the variable being used for prediction will potentially collide with different thresholds (e.g., notification and alert thresholds). Although most systems and subsystems are nonlinear in nature, systems can be linearized through modeling over a sufficiently small time step. The different thresholds can be set based on manufacturing-specified thresholds, recommended thresholds, or other thresholds. The advisory system can include more advanced regression methods and may also include mathematical models, where available, including nonlinear mathematical models. In an alternative embodiment, a mathematical model of the variables can be used, and predictions of when the variables may cross a threshold can be made by running the mathematical model. The rate of change or slope of a variable can also be monitored with high and low thresholds, since the normal behavior of the variable may have an upper and lower limit on how quickly the variable can change. To determine the upper and lower thresholds, knowledge about the variable or parameter, whether from a manufacturer or otherwise (e.g., testing, adjustment of variations based on system or component specifications, actual operating performance, historical performance, etc.), can be used. Limits may be set and / or modified by a user or vessel operator. Additionally, or alternatively, limits may be set by a developer of the advisory system. Limits may be set by the limits of system, subsystem, and / or component manufacturers (e.g., mechanical structures, electrical components, etc.). The advisory system can use machine learning to help establish various upper and lower limits. The advisory system can run a continuous correlation analysis with other variables, up to and including all other vessel system variables or variables external to the vessel system, such as geolocation, sea temperature, time and date, etc., to understand the dependencies between vessel system variables. / 1 / Qbn / zznz / q / YiAi For example, if the advisory system detects that a generator's temperature is changing too rapidly, the advisory system may first check for strong correlations with other variables before sending a notification to an operator. In this generator temperature change notification, the advisory system may ask the human operator or user whether the behavior (e.g., the generator temperature change optionally correlated with another variable) is normal or not. If the behavior is indicated as normal by the human operator, then the advisory system may be configured not to contact the user with a notification the next time. Instead, the advisory system may send a warning or alarm notification the next time the same situation arises.In one embodiment, the advisory system may be configured to allow the operator to dismiss the notification for the first time, but allow the advisory system to alert the operator in the future if the same situation arises, thereby allowing the user to be aware of possible correlations that may exist and that may have been previously unknown to the operator. / 1 / Qbn / zznz / q / YiAi Correlations and dependencies The advisory system can be configured to continuously identify new dependencies between variables. Each time the advisory system identifies a potential correlation between two or more variables, the advisory system can notify the human operator for confirmation of whether or not a real dependency exists between the variables identified with the potential correlation. The advisory system can then recall (i.e., store) the operator's decision for future analysis. As an example, two variables, x and y, can be tracked. Based on the collected data sets or variables, X = {xi,x¿, ...,xn} and Y = {yi, y2, ...,Yn}, the coefficient of determination, or R2, can be calculated using the following equation (assuming a linear model for the relationship between the variables): where, ---- V* iV xy = 77 Σί=i xíVí The coefficient of determination, R2, typically ranges between 0 and 1, where 0 indicates a 0% correlation between the variables, while 1 indicates a 100% correlation between the two variables. The advisory system may send a notification to the human user when a particular correlation limit or threshold (e.g., 40%) is crossed by the coefficient of determination to obtain confirmation from the user as to whether or not a valid correlation exists between the vessel system variables. A 40% correlation limit has been found to be an acceptable level of interaction with an operator, but a higher or lower correlation limit may be used. It should also be understood that the correlation limit may vary for different variables, especially those that may have a catastrophic impact on the vessel (e.g., oil pump pressure, ballast pressure, engine temperature, etc.). One of the reasons the advisory system cannot validate its own findings, based on the R2 value, is due to the risk of confirming a false correlation. Since the coefficient of determination is based on a linear model, false correlations can occur due to the nature of some data sets. A human eye can quickly validate whether or not a true correlation exists between the two variables. In response to the user validating whether or not a correlation exists between the two variables in step 538, the advisory system may store the decision in the database in step 514 to recall the decision in the future in order to advise (e.g., notify or alert) or not inform the operator if the same or a similar correlation exists between the two variables and qualifies for notification. Over time, the advisory system may ask the operator about new dependencies less frequently since most of the dependencies have been pre-mapped by the advisory system. The advisory system may map most of the dependencies based on a linear regression model, but the advisory system may use nonlinear regression or other mathematical models to calculate R2 values ​​for the remaining dependencies. As part of the advisory system, correlations can monitor potential dependencies between internal vessel system variables on the vessel and external variables, such as geolocation, sea temperature, air temperature, current, waves (e.g., wave size, wave frequency), time, season, wind, and humidity. These environmental, location-based, and time-dependent variables can be correlated with internal vessel variables, allowing for the impact of environmental parameters on operational parameters. For example, when a vessel is operating in the North Sea, the temperatures of most of the vessel's internal variables are expected to be lower compared to a vessel operating in warmer waters, such as the Gulf of Mexico. Similarly, understanding the behavior of internal variables based on the time of year (season) or other environmental conditions could reveal previously unconsidered optimizations. Presentation With respect to Figure 7, a graph is shown depicting an illustrative variable curve 700 with an upward trend in temperature over time along with set upper and lower warning levels 702 and alert levels 704 that can be used to generate and communicate indicators or messages to an operator via an advisory system. The graph shows measurements of variables that the advisory system collects periodically (e.g., daily) or aperiodically (e.g., in response to an event), and plots the measurements against warning and critical levels 702 and 704 of the variable. In the case of a bearing temperature as shown in Figure 7, for example, the temperature can be traced to be trending upward. The temperature trend can be correlated with other variables, in order to potentially determine a cause and effect relationship. As shown later in Figure 7, a current measurement or today's measurement 706 shows how the variable bearing temperature curve 700 is trending over time. A linear projection curve 708 shows that if the current trend of the curve 700 remains the same, then the warning level 702 is predicted to be reached in 28 days with a certainty of 73% at point 710 and the critical level 704 is predicted to be reached in 53 days with a certainty level of 58% at point 712. For example, the prediction may be provided to the operator so that they may attempt to prevent either level 702 or 704 from being reached by correcting (e.g., repairing) a subsystem. With respect to Figure 8, a screenshot of an illustrative user interface 800 of an advisory system showing or listing subsystems 802a to 802n (collectively 802) that are part of a vessel system along with associated status indicators 804a to 804d (collectively 804). Two subsystems, propulsor control system (TCS) 802b and integrated bridge system (IBS) 802c, are indicated as nominal, and two subsystems, dynamic positioning system (DPS) 802a and mechanical system (MES) 802d, are indicated as having imminent action due or overdue by displaying indicators 804a and 804d in a different format and / or color (e.g., red) than the indicators 804b and 804c associated with subsystems 802b and 802c (e.g., green) that were determined to be operationally nominal.It should be understood that alternative formats and / or colors may be used to indicate that a subsystem, component, and / or variable is or has reached a warning level as compared to a subsystem, component, and / or variable that is or has reached a critical level. The mechanical subsystem 802d is shown to be expanded in a hierarchical format to display the subsystems or components (bearings, switchboard, generators) 806a to 806c of the mechanical system. An identifier 808a associated with the bearings 806a indicates that a problem with the mechanical subsystem 802d is with the bearings 806b. A user may select (e.g., click) on the bearings 806a, and further detail about a specific location of the bearings 806a may be displayed with text and / or graphics that have crossed through the warning and / or alarm levels. In one embodiment, a user interface, such as user interface 800 shown in Figure 8, that provides information to an operator may use colors to notify and / or alert users of problems that may be trending toward a problem or are actually a problem. A green (nominal) level may provide a status check, trend analysis, and other statistics about a system or subsystem in question. The advisory system does not act upon a green level, as a green (nominal) level is considered normal system behavior or operating conditions. It should be understood that alternative configurations of the notification and user interface may be used to provide the same or similar functionality as that provided herein. In one embodiment, a yellow (warning) level may be used to inform the operator of a trend change that could portend a future violation of the warning and alarm levels. If the advisory system has not previously experienced a trend change, the advisory system may request confirmation from the operator (e.g., via email, text, website, embedded system, dashboard in an onboard control system, advisory system user interface, etc.) as to whether the trend change is normal or not. The request to the operator allows the advisory system to eliminate false warnings and alarms in the future. In one embodiment, the operator may be provided with the following information at a yellow level: (i) Dependencies detected with other variables; (II) When the system was last used; (iii) Evolution of the data; and (iv) How long it will take before a warning or alarm threshold is breached. In one embodiment, a red level (alarm) alert reports an imminent or current failure along with details about statistical and system rules. A prohibition notice may be issued to the operator in an alert level event. Presumably, a yellow level advisory notification will precede a red level advisory notification, but in the event that a yellow level advisory notification does not occur due to an unforeseen failure or is somehow missed by an operator, for example, the red alert or warning may provide an alert message along with the ability for the operator to respond to the relevance of the correlation of multiple variables. With respect to Figures 9A and 9B, an illustration is shown of an exemplary status indicator and panel user interface 900 of a vessel system for operating a vessel. The status indicator and panel user interface 900 may include one or more lists of various systems and subsystems 902a to 902n (collectively 902) that are color-coded, including green for online, blue for offline, and red for in alarm, to indicate to an operator whether or not there are anticipated problems with the vessel system. The checklist may be configured to expand hierarchically so that the operator may drill down to see specifically which variable associated with which system or subsystem may be trending toward or currently in a notification or alert state. It should be understood that a wide range of user interface designs may be used to provide status information to the operator.The presentation of the ship systems can be configured for and / or by an end user, as desired. The user interface 900 may also include more conventional panel elements, including one or more sensor lists 904a and 904b (collectively 904), which may include digital GPS sensors, scanners, heading compass, voltage sensors, gyroscope sensors, or others. A navigation mode list 906 may also be displayed on the user interface 900. It should be understood that (i) / 1 / Qbn / zznz / q / YiAi lists 902, 904, and 906, (ii) items in the lists 902, 904, and 906, and (iii) formats of the lists and the user interface 900 are illustrative, and that any other lists, parameters or variables, and formats may be used in accordance with the principles described herein. Regarding Figure 10, a graph, in this case a pie chart, shows illustrative variables that describe how dependencies and correlations can be illustrated on a vessel system website. As shown, the primary variable is the generator temperature, and the dependency variables, which are environmental parameters or variables, are sea temperature, geolocation, and time of day. In this example, the time of day variable has the strongest dependency or correlation, as the generator operates more during the day compared to the night. It should be noted that the graph is intended to illustrate the dependencies of non-vessel system variables and is not based on operational correlations. Data points and variables / parameters A vessel system may have dozens, hundreds, or thousands of variables or data input points that can be monitored by the advisory system. The lists below are not exhaustive and may be updated as additional data input points become available through detection in a vessel system. It should be understood that the list of variables may be different for different vessel systems. As shown, eight main groups of systems and / or subsystems can be presented for data entry points or variables of a ship's system on a ship. Additional and / or alternative ship system systems or subsystems can also be presented. • Dynamic Positioning Systems (DPS) • Integrated Bridge Systems (IBS) • Thruster Control Systems (TCS) • Sensor Systems (SES) • Mechanical Systems (MES) • Power Supply Systems (POS) • Computing and Network Systems (CNS) • External Factors (EXF) / 1 / Qbn / zznz / q / YiAi Dynamic Positioning Systems (DPS) The following subgroups can be monitored for DPS: • DP Checklists o Custom List 1 for Accepted Operation o Custom List 2 for Accepted Operation oio Custom List N for Accepted Operation • DP Class o Use of Position Reference System (PRS) according to class. o Use of the sensor system according to the class. o Use of the propellant according to the class. or Power according to class. • DP Performance or Lost Position or Lost Heading or • DP Computers or Control Computers Control Computer 1 (CC1) Control Computer 2 (CC2) * Control Computer 3 (CC3) or Operating System Operating System 21 (OS21) Operating System 22 (OS22) Operating System NM (OSNM) or Thruster Indicator Diagrams Throttle Indicator 1 (TCI) Diagram Thruster 2 (TC2) Gauge Diagram Thruster N Indicator Diagram (TCN) • DP Network or Network A (NET A) or Network B (NET B) • Customer Checklists or Customer List 1 or Customer List 2 or Customer List N / 1 / Qbn / zznz / q / YiAi Integrated Bridge Systems (IBS) The following subgroups can be monitored for IBS: • Ballast tanks or Ballast tank 1 or Ballast tank 2 or Ballast tank N • Warping tanks or Warping tank 1 or Warping tank 2 or Warping tank N • Fuel tank or Fuel tank 1 Pressure Level or Fuel Tank 2 EITHER : o Fuel Tank N • Fire and leak gas detection systems o Fire and leak gas detection system 1 Fire warnings Gas or Fire and Gas Leak Detection System 2 oio Fire and Gas Leak Detection System N • Fire Extinguishing Systems or Fire Extinguishing System 1 Bombs Valves Engines or Fire Extinguishing System 2 oio Fire Extinguishing System N • Non-Critical Systems or Weatherproof Doors or Heating, Ventilation and Air Conditioning / I 7Qbn / 77n7 / q / YIAI Sensor Systems (SES) The following subgroups can be monitored for SES: • Global Reference Systems or Global Reference System 1 / GNSS Receiver 1 / DGNSS Receiver 1 / ... Position Speed General system error / Quality factor or Global Reference System 2 / GNSS receiver 2 / DGNSS receiver 2 / ... oio Global Reference System N / GNSS Receiver N / DGNSS Receiver N / ... or C-Nav 1 GNSS Receiver Position Speed Precision indication Indication of reliability RAIM Test F Test W General System Error / Quality Factor or C-Nav 2 GNSS Receiver EITHER : o C-Nav N GNSS Receiver • Local Reference Systems o Local Reference System 1 / Cyscan 1 / Radascan 1 / Origin 1 / ... Position / Range and Bearing General system error or Local Reference System 2 / Cyscan 2 / Radascan 2 / Origin 2 / ... oio Local Reference System N / Cyscan N / Radascan N / Origin N / ... • North-seeking systems or North-seeking system 1 / Gyrocompass 1 / AHRS 1 / INS / AHRS 1 / ... Course Heading speed / Rate of turn General system error or North Seeking System 2 / Gyrocompass 2 / AHRS 2 / INS / AHRS 2 / ... oio North Seeking System N / Gyro Compass N / AHRS N / INS / AHRS N / ... • Motion Sensor Systems / 1 / Qbn / zznz / q / YiAi or Motion Sensor System 1 / VRU 1 / MRU 1 / INS 1 / Slope 1 / ... Warp Pitching General system error or Motion sensor system 2 / VRU 2 / MRU 2 / INS 2 / Pending 2 / ... oio Motion Sensor System N / VRL) N / MRU N / INS N / Pending N / ... / 1 / Qbn / zznz / q / YiAi Thruster Control Systems (TCS) The following subgroups can be monitored for TCS: • Thrusters o Thruster 1 o Thruster 2 o ; o Propeller N • Variable Frequency Drives o Variable Frequency Drive 1 (VFD1) o Variable Frequency Drive 2 (VFD2) o ; or Variable Frequency Drive N (VFDN) Pumps or Steering pump 1 or Steering pump 2 or Steering pump N Computers or Propulsion System Control Computers Thruster Control System Control Computer 1 (TCSCC1) Thruster Control System Control Computer 2 (TCSCC2) Thruster Control System Control Computer 3 (TCSCC3) or Operating System Operating System 21 (OS21) Operating System 22 (OS22) Operating System 23 (OS23) Operating System 31 (OS31) or Gateways Gate 1 (GW1) Gate 2 (GW2) Gate N (GWN) or Thruster Indicator Diagrams Propeller gauge diagrams Thruster 2 (TC2) Gauge Diagram Propellant Indicator Diagram N (TCN) / 1 / Qbn / zznz / q / YiAi Mechanical Systems (MES) The following subgroups can be monitored for MES: • Propellers or 1 RPM Propeller Winding temperatures Bearing temperatures Bearing vibration Internal vibration of the gear or Propeller 2 oio Propeller N • Engines and driving elements or Main engines Main Engine 1 • Bearing Monitoring (BeCOMS) • Combustion Pressure Monitoring (BeCOMS / Pressure Sensor) • Oil Splash and Oil Mist Monitoring (SiCOMS / OCom) • Combustion Temperature • Lube Oil Condition Sensor (Conductivity) • Lube Oil Temperature • Cooling Water Temperature . RPM • Load Main engine 2 Main Engine N or Diesel Electric Engines Diesel Electric Engine 1 • Bearing Monitoring (BeCOMS) • Combustion Pressure Monitoring (BeCOMS / Pressure Sensor) • Oil Splash and Oil Mist Monitoring (SiCOMS / OCom) • Combustion Temperature • Lube Oil Condition Sensor (Conductivity) • Lube Oil Temperature • Cooling Water Temperature . RPM • Load Diesel electric engine 2 Diesel Electric Engine N or Electric Motor Electric Motor 1 • Bearing Vibration • Bearing Temperature • Heater On or Off • Winding Temperature . RPM • Load Electric motor 2 Electric motor N • Bearings o Bearings 1 Temperature Vibration o Bearings 2 oio Bearings N / 1 / Qbn / zznz / q / YiAi • Valves o Valve 4 Ultrasound Position or Valve 2 or ; or N Valve Bombs or Bomb 1 Bearing vibration Bearing temperature Pressure Flow or Pump 2 O o Pump N • Gearboxes o Gearbox 1 Bearing vibration Bearing temperature Gear vibration Lubricating oil quality / Conductivity Lubricating oil temperature or Gearbox 2 EITHER : o Gearbox N • Cranes o Crane 1 Hydraulic pumps Hydraulic filters Hydraulic valves Hydraulic tank Hydraulic motors Gears Encoders Electric Motors Electric Heaters Pressure / 1 / Qbn / zznz / q / YiAi Speed Load or Crane 2 or Crane N • Axis lines or Axis line 1 Bearing vibration Alignment vibration Bearing temperature Torsional shaft vibration Power Fuel consumption Strain gauge or axis line 2 EITHER : o Axis line N • Winches o Winch 1 Hydraulic motor Hydraulic valves Hydraulic pressure Gears Encoders RPM Encoder or Winch 2 O i o Winch N • Hydraulic elements o Hydraulic element 1 Pumps • Pump 1 or Bearing Vibration or Bearing Temperature or Pressure or Calculated Flow or Flowmeter / 1 / Qbn / zznz / q / YiAi or Pump Angle Transducer or Calculated Hydraulic Power or LS Pressure Transmitter or Oil Temperature • Pump 2 • • N-Bomb Valves • Valve 4 or Input Signal or Position Feedback or Calculated Valve Response • Valve 2 • • N Valve Filters • Filter 1 or Delta Pressure / Switch for High Pressure Filters or Delta Pressure / Switch for Return Filters or Delta Pressure / Switch for Drain Filters • Filter 2 • • Filter N Oil Tanks • Oil Tank 1 o Level o Temperature o Particle Count o Relative Humidity • Oil Tank 2 • • Oil tank N Motors • Motor 1 o Bearing vibration o Bearing temperature o Oil pressure / 1 / Qbn / zznz / q / YiAi o Oil flow o Oil temperature o Motor angle o Calculated hydraulic power o LS pressure • Motor 2 / 1 / Qbn / zznz / q / YiAi • Motor N o Hydraulic element 2 oio Hydraulic element N Power Supply Systems (POS) The following subgroups can be monitored for POS: • Generators or Generator 1 RPM Frequency Circuit breaker Bearing temperature Bearing vibration Vibrations Bearings Oil pressure Air Pressure or Generator 2 EITHER : o Generator N • Variable Frequency Drives o Variable Frequency Drive 1 (VFD1) o Variable Frequency Drive 2 (VFD2) O io Variable Frequency Drive N (VFDN) • Switchboards or Switchboard 1 (SWBD1) Frequency Circuit Breaker or Switchboard 2 (SWBD2) or ; o Switchboard N (SWBDN) ​​• Grounding Systems • High Voltage Systems • Low Voltage Systems • Universal Power Supplies o Universal Power Supply 1 o Universal Power Supply 2 oio Universal Power Supply N • Batteries o Battery 1 o Battery 2 EITHER : o Battery N / 1 / Qbn / zznz / q / YiAi Computing and Network Systems (CNS) Using the Simple Network Management Protocol (SNMP) and an optional private SNMP service, complete network and computer monitoring is possible. The private SNMP service can be installed on selected equipment to collect status information from network equipment and intelligent switches. Every control computer (CC), operating system (OS), and intelligent switch across an entire control network can be monitored, thus providing complete monitoring of a vessel system. The following subgroups can be monitored for CNS: • Control Computers and Operating Systems or DP Control Computer 1 (DPCC1) * System • Uptime • Date • Description • Contact • Name • Location Storage and Memory • Size • Used CPU • Non-Idle Time for Each Core Network • IP Address • MAC Address • Unicast or Packets In or Packets Out • Non-Unicast Packets or Packets In or Packets Out • Operational Interface Status • Dropped and Error Packets Software • Names • CPU Usage • Memory Usage or DP Control Computer 2 (DPCC2) or DP Control Computer 3 (DPCC3) or TCS Control Computer 1 (TCSCC1) or TCS Control Computer 2 (TCSCC2) or TCS Control Computer 3 (TCSCC3) or Operating System 1 (OS21) or Operating System 2 (OS21) O í o Operating System N (OS21) • Smart Switches o Smart Switch 1 System • Uptime • Date • Description • Contact • Name / 1 / Qbn / zznz / q / YiAi • Location Network • IP Address • MAC Address • Unicast or Packets In or Packets Out • Non-Unicast Packets or Packets In or Packets Out • Interface Status • Dropped Packets • Error Packets • Power over Ethernet (PoE) Status or Smart Switch 2 oio Smart Switch N / 1 / Qbn / zznz / q / YiAi External factors (EXF) The following variables can be monitored for EXF: • Time and date • Geolocation • Air humidity • Air and sea temperature • Wind, waves and currents • Weather and climate • Solar flares Referring to Figure 11, a flowchart of an illustrative advisory process 1100 of an advisory system for supporting a vessel operator is shown. The process 1100 may begin in step 1102, where multiple variables of a vessel system may be sensed. The system may be any system or subsystem on the vessel capable of being sensed by a sensor. In one embodiment, the sensing may be of an environmental parameter, such as water or air temperature. Alternatively, the sensing may be of any operational parameter, such as temperature, pressure, electrical current or voltage, or other variable or parameters of a vessel system. In step 1104, it may be determined whether a first variable correlates with a second variable. In step 1106, an operator may confirm that the first and second variables correlate.In step 1108, an indicator denoting that the first and second variables are correlated in response to the operator confirms the same for future use. Process 1100 operates as a machine learning process that includes human training of the advisory system by a human operator who instinctively knows whether particular variables correlate with each other or not. Over time, process 1100 learns which variables correlate with each other, such that the amount of human operator support or interaction with the vessel system monitoring can be decreased, and a reduction in false positives and false negatives reported to the operator occurs. More specifically, one embodiment of a vessel operation process may include sensing variables of a system, where the variables may be representative of functional parameters of the system. A change in the values ​​of a first variable over a period of time may be identified. In response to determining the change in the values ​​of the first variable, the first variable may be correlated with a second variable that has a change in values ​​over at least a portion of the time period. A notification including the first and second variables and a change in their values ​​may be generated for an operator to indicate whether the first and second variables should be correlated with each other. In response to receiving an indication from the operator that the first and second variables should be correlated with each other, an indicator indicative that the first and second variables are correlated with each other may be stored.Otherwise, an indicator that the first and second variables are uncorrelated may be stored. Subsequently, in response to identifying a change in the values ​​of the first and second variables, it may be determined whether an indicator exists that indicates the first and second variables are correlated with each other, and if so, an alert may be generated to the operator of the changing values ​​of the first and second variables. Otherwise, an alert may not be generated to the operator of the change in the values ​​of the first and second variables. The process may further include (i) sampling values ​​of the first variable over a nominal value sampling time period, (ii) sampling values ​​of the second variable over the nominal value sampling time period, and (iii) establishing a set of nominal values ​​for each of the first and second variables. In one embodiment, the process may further include establishing a notification threshold level at which a notification will be sent to the operator of the variable crossing the threshold level. The process may further include calculating a prediction of whether the first variable will cross the reporting threshold level. In one embodiment, the process may calculate when the first variable will cross the threshold level. Calculating a prediction may include a regression calculation. The calculation may include running a model of the first variable. Correlating the first variable with a second variable may include correlating the first variable with an environmental parameter. Correlating the first variable with a second variable may include correlating the first variable with another variable detected on the vessel. Identifying the change in the values ​​of the first and second variables may include / 1 / Qbn / zznz / q / YiAi determining whether the change in the values ​​of the first and second variables changed in the same or similar pattern as the previous change, to which the operator indicated that the first and second variables were correlated with each other. The process may further include running an outlier rejection filter to filter out outliers of the first and second variables. The process may further include correlating the first variable with all other variables to identify the second variable. Identifying the change in the values ​​of the first variable may include identifying that the change in values ​​is outside of a standard deviation threshold level. In one embodiment, another system may be used to collect information (e.g., correlated variables) produced on independent vessels. The collected information may be onshore on a communications network and used to perform correlations on information collected across a fleet of vessels, thereby producing fleet-level correlations (e.g., failures occurring at water temperatures below a certain temperature). The onshore system may operate in the same or similar manner as the vessel system in terms of confirming with a user whether the correlations between different variables identified by the onshore system are indeed related and relevant. If so, then the onshore system may continue to monitor and report future situations that are the same or similar (mathematically calculated).Otherwise, the ground system can continue monitoring but avoid reporting situations that are the same or similar. Referring to Figure 12, a flow diagram of an illustrative advisory process 1200 of an advisory system for supporting a vessel operator is shown. The process 1200 may begin in step 1202, where one or more variables of a vessel system may be sensed. The system may be any system or subsystem on the vessel capable of being sensed by a sensor. The sensing may be of any operating parameter, such as temperature, pressure, electrical current or voltage, or other variable or parameters of a vessel system. Additionally, or alternatively, the sensing may be of an environmental parameter, such as water or air temperature. In step 1204, it may be determined whether the behavior of a variable is normal (e.g., within defined normal operating levels). In step 1206, an operator may confirm whether the behavior (e.g., trend) of the variable is normal.In step 1208, an indicator indicating whether the variable is normal or abnormal may be stored for future use. Process 1200 operates as a machine learning process that includes human training of the advisory system by a human operator who instinctively knows whether particular variables, and optionally related variables, are operating normally or not. Over time, process 1200 learns whether variables are operating normally or not, such that the amount of human operator support or interaction with the vessel system monitoring may be decreased, and a reduction in false positive and false negative reporting to the operator occurs.Process 1200 may also allow a human operator to provide feedback to the system regarding information about dependencies on other variables that might exist to assist the vessel system's machine learning to better determine the operation of the vessel system. / 1 / Qbn / zznz / q / YiAi An embodiment of a method of operating a vessel may include identifying a first trend change in sampled values ​​over a first time period of a variable, where the variable may be representative of a functional parameter of the vessel. In response to determining the first trend change in the sampled values ​​of the variable, a notification may be generated that includes an indication of the first trend change in the sampled values ​​of the variable. The notification that includes the indication of the first trend change in the sampled values ​​of the variable may be communicated to an operator. The communication may be performed in any manner, such as by displaying on a user interface of an operator console, as described previously in this document.In response to receiving an indication from the operator as to whether the first trend change in the sampled values ​​of the variable is normal, a first indicator of the first trend change in the sampled values ​​of the variable may be stored for future use. Otherwise, in response to receiving an indication from the operator that the first trend change in the sampled values ​​of the variable is not normal, a second indicator of the first trend change in the sampled values ​​of the variable not being normal may be stored for future use. Furthermore, in response to identifying a second trend change in the sampled values ​​of the variable over a second period of time, a determination may be made as to whether the first or second indicator exists that indicates that the first trend change in the sampled values ​​is normal or abnormal, and if the second indicator exists, a warning may be generated for the operator of the second trend change in the sampled values ​​of the variable. Otherwise, if the first indicator exists, no warning may be generated for the operator of the second trend change in the sampled values ​​of the variable. Identifying a first trend change in the sampled values ​​of a variable may include calculating a linear trend line based on the sampled values. The process may also include calculating the amount of time the variable will cross a threshold value if the linear trend line continues until a first reporting threshold level is reached. Although the vessel system and processes described herein generally refer to maritime vessels, it should be understood that the systems and processes may apply to non-maritime vessels. For example, rather than a vessel, the system may be any other vehicle (e.g., airplanes, trains, automobiles, etc.) or non-vehicle (e.g., manufacturing facility) that has systems and subsystems that utilize a monitoring system. Use of the machine learning advisory system in any other environment may provide the same or similar capability to monitor multiple variables and correlate variables over time to help ensure that operators can more efficiently track changes that may result in notifications and warnings that may occur, thereby reducing downtime or catastrophic events. / 1 / Qbn / zznz / q / YiAi Fuel knowledge and optimization system Maritime vessel operators are generally concerned about fuel usage due to the cost and efficiency of maritime vessel operations. The speed of the maritime vessel represents an important factor in fuel usage. Maritime vessel propulsion systems typically have a speed or speed range at which fuel usage is maximized. With respect to Figure 13, an illustration is shown of an illustrative waterway in which a vessel may travel and gain real-time insight into a vessel's fuel consumption while traveling from point A to point B. As shown, the seagoing vessel departing from point A may utilize a number of different schedules to travel from point A to point B. The different schedules, such as schedules A, B, C1, and C2, may have various parameters, including, but not limited to, speed, heading, and waypoints or route. The schedules may be calculated and presented to an operator of the seagoing vessel so that the operator is aware of the various options. In one embodiment, the schedules may be produced by simple calculations that estimate different speeds (e.g., varying speeds by 3,704 km / h (2 knots)) along the same route to determine fuel usage.If the advisory or planning system has operational and / or environmental data (e.g., wind speed, wind direction, water current speed, water current direction, etc.), then the calculations can be more accurate. In one embodiment, the calculations can be performed as part of a simulation running in real time so that the operator can stay abreast of speed and / or other operational information (e.g., route) that can save or optimize fuel use. As shown, program A has one most direct route between point A and point B, program B has a second most direct route, and programs C1 and C2 have the third most direct route, but they travel at different speeds.Wind speed and direction and water current may have an impact on the route, vessel speed, or otherwise, and may be constantly updated and used by the vessel's advisory system, as described later in this document. Referring to Figure 14, a block diagram of an illustrative vessel system 1400 is shown in communication with an enhanced advisory system 1402 as compared to the advisory system 402 of Figure 4. The advisory system 1402 includes a planning system that may incorporate various additional intelligences, such as a simulator, machine learning (e.g., learning trajectory system), and / or artificial intelligence engine (e.g., neural network, convolutional neural network, etc.). The planning system may utilize any or all of the engines to assist in generating fuel consumption awareness information for a vessel operator in real time.For example, vessel system 1400 may collect and communicate variables 1406 collected by sensors that are configured to collect operational data from systems and subsystems (see, e.g., FIG. 2 ) comprising vessel system 1400. The variables 1406 (i.e., values ​​collected from the sensors or derived from values ​​collected from the sensors) of vessel system 1400 may be communicated to user interfaces 404 for display (see, e.g., FIG. 3 ) in conjunction with advisory system 1402 that may process variables 1406 to monitor variables 1406, determine potential correlations, and generate knowledge information that may be presented to a user and / or automatically utilized by the vessel system to control operation of the maritime vessel (e.g., in a fuel optimization mode). In one embodiment, with a focus on the planning system aspect of the advisory system 1402, the variables 1406 may include one or both of environmental parameters (e.g., wind speed, wind direction, current speed, current direction, potentially both locally and along the path of the maritime vessel) and operational parameters (e.g., propulsion system type, propulsion vs. fuel usage curve, vessel loading, etc.) of the maritime vessel as detected by the vessel system 1400, and the advisory system 1402 may utilize the variables 1406 to determine optimal and / or optional speed vs. fuel usage information, alternate course information, etc. The advisory system 1402 may provide the vessel operator and / or vessel system 1400 with real-time information regarding speed and / or path options that may help reduce the vessel's total fuel consumption along part or all of the path between a point A (starting or current location) and a point B (destination location). In one embodiment, the advisory system 1402 may be configured to provide the operator with a departure time to satisfy a desired time of arrival (ETA) that has a speed that optimizes fuel consumption. In one embodiment, the planning system may provide the operator with consequences (e.g., total fuel consumption and estimated time of arrival) for increasing or decreasing the vessel's speed in increments / decrements of 3704 km / h (2 knots) or other increment / decrement, from a starting or current vessel speed.In real time, the collected variables 1406 may update the advisory system 1402 so that the planning system may update its various functions to update fuel usage projections. In one embodiment, the advisory system 1402 may operate a simulation utilizing the real-time measurements of environmental factors (e.g., water current vectors, wind speed vectors, etc.) along different potential vessel routes from the vessel's current locations to determine which path or route may provide the greatest fuel efficiency and duration between the vessel's current location and the destination location. The advisory system 1402 may include a processor comprised of one or more processors, memory, and an input / output (I / O) unit configured to communicate via a local area network (e.g., with a vessel system computer) or a broadband area network (e.g., satellite network, Internet, etc.). In one embodiment, the advisory system 1402 may communicate advisory information 1408 to user interfaces for a human operator to provide adjustment parameters 1410 to potentially adjust parameters being used by the planning system of the advisory system 1402. That is, the operator may interact with the planning system as potential operating parameters or circumstances for the maritime vessel and / or the operator change (e.g., changes in point B).For example, if a simulation is used, simulation parameters such as weighting, bias, or otherwise, / 1 / Qbn / zznz / q / YiAi may be adjusted by an operator. In one embodiment, the simulation may use a Monte Carlo method to adjust one or more variables to determine a most efficient combination of variables. The simulation may use current and / or anticipated operating and environmental conditions based on measured and / or predicted conditions (e.g., wind, rain, water current, etc.). In one embodiment, the simulation may use hysteresis (e.g., waiting 30 minutes for any future course adjustments after a previous course adjustment) to prevent the simulation from introducing or causing excessive course adjustments. Alternatively, the simulation may be continuous and update potential course adjustments in real-time or near-real-time. Over time, the advisory system 1402 may learn to produce more fuel-efficient operation of the maritime vessel based on past performance under possibly similar environmental conditions. For example, the planning system may utilize adaptive path learning so that the vessel's path can be as direct as possible (e.g., avoiding wider turns, if possible, along a river or along an ocean voyage). If artificial intelligence is included in the planning system, the current and / or future environment and / or operating parameters of the vessel may be recognized by a neural network and taken into account in route planning (e.g., heading, speed, etc.) if the planning system utilizes artificial intelligence to optimize fuel usage.Such optimized fuel usage may become more accurate over time, such that fuel awareness information 1412 may be communicated to user interfaces 1404 for display. With respect to Figures 15A and 15B, two graphs 1500a and 1500b are shown showing a power over ground speed curve 1502a and a power over ground speed curve 1502b. These two curves may be used to determine fuel efficiency based on the current speed of the vessel. Data for the curves may be collected by the vessel system 1400, as described above (see also Figure 4). With respect to Figure 16, an illustrative user interface 1600 is shown that produces data representative of the vessel's current speed and fuel savings as a function of a speed change in kilometers per hour (knots), reduced emissions (e.g., NOx and CO2), and an amount of fuel savings over a certain number of kilometers (nautical miles) (e.g., 185.2 km (100 Nm)). Other information may be presented, such as estimated time of arrival, trim recommendation, draft recommendation, and any number of other operating parameters. As described above, operating parameters that result in improved fuel efficiency may be determined using simulation, machine learning, and artificial intelligence (e.g., neural network).The simulation, machine learning, and / or artificial intelligence system may be identical on different maritime vessels, but because each maritime vessel may be handled differently due to the structure and / or operating parameters of the propulsion systems, for example, the performance of the simulation, machine learning, and / or artificial intelligence system may result in different projections and determinations than other maritime vessels that may be operating in the same or similar environmental conditions and in the same locations and routes between the current and destination locations. With respect to Figure 17, a graph of a portion of the power-over-ground-speed curve 1502a is shown. As an example, the system may automatically calculate the distance the vessel will travel to a platform. When a vessel is currently operating at 10 knots (18.52 km / h), software, such as the advisory system planning system 1402 of Figure 14, may provide the operator with an estimated fuel consumption and ETA based on 10 knots (18.52 km / h) (see Figure 16). The software may also provide the user with estimated information as to how much more fuel (e.g., in percentage and liters (gallons)) the vessel will use by increasing the vessel's speed by 2 knots (3.704 km / h). The system may also display an estimate of how much faster the vessel will arrive at the destination (by providing the new ETA and the decrease in time in hours / days).In addition to these operating parameters, the system can provide the user with information on how much fuel the vessel will save (in percentage and liters (gallons)) by reducing the speed by 3,704 km / h (2 knots), but also how much longer the vessel's voyage will take (by providing the new ETA and the increment in hours / days). From the user interface (provided by the software), the operator can increase or decrease the vessel's speed based on information provided by the software. The user can also activate the new speed setpoint using an actuator, such as an analog button (e.g., a physical button, a physical switch, etc.) or a digital button (e.g., a software button in a graphical user interface), which can be actuated (e.g., pressed or selected) to actively instruct an autopilot to transition to the new speed setpoint. With respect to Figures 18A through 18D, a user interface 1800 is shown illustrating a variety of operating parameters of a vessel's propulsion and control system for driving the maritime vessel. A user may have the ability to view the parameters of the vessel's propulsion system. In one embodiment, the advisory system 1402 of Figure 14 running a simulation may vary any of the operating parameters of the propulsion system to determine fuel efficiency. As described above, a Monte Carlo method or other simulation technique may be used to vary the operating parameters. Using machine learning, an analysis may be performed on how to adjust the operating parameters that have the highest probability of success to result in fuel usage optimization. With respect to Figures 19A and 19B, a user interface 1900 is shown displaying illustrative operating parameters of the maritime vessel. As with the user interface 1800 of Figure 18, the advisory system 1402 of Figure 14 may vary any of the operating parameters, such as heading, specific propulsors (e.g., electric propulsors) that are most fuel-efficient, to determine optimal fuel usage. In one embodiment, the user interfaces 1800 and 1900 may allow an operator to set one or more operating parameters and allow the others to be varied by the simulator or other tool of the advisory system 1402. / 1 / Qbn / zznz / q / YiAi Referring to Figure 20, a 2000 chart is shown showing illustrative total fuel by vessel operating mode. Chart 2000 includes a number of operational parameters (e.g., total fuel consumed (liters (gallons))), but any number of additional operating parameters may be included. Referring to Figure 21, a fuel consumption report 2100 is shown, including a trip summary and recommendations and savings. The trip summary may display several operating parameters: start time, end time, trip duration, average ground speed, average fuel rate, and fuel usage. Recommendations and savings may include recommended ground speed, optimal fuel rate, percentage and liters (gallons) of fuel savings, and emissions savings. It should be understood that any number of additional and / or alternative operating parameters may be included. With respect to Figure 22, charts 2200 show (i) the actual ground speed and fuel rate curves 2202a and 2202b and show (ii) the recommended ground speed and fuel rate curves 2204a and 2204b. The recommended ground speed and fuel rate curves 1404a and 1404b show that the fuel rate 1404b is essentially constant at 235.5 l / h (62.2 gal / h). Depending on environmental conditions (e.g., strong winds and currents), the fuel rate may vary. For example, machine learning may be used to determine burning more fuel and / or an alternate path during one segment of a voyage to overcome a water current so that a vessel may use a downstream current during a later segment of the voyage to reduce overall fuel consumption during the voyage.Other environmental factors and / or operating parameters may be used by the machine learning, artificial intelligence and / or simulation system. With respect to Figure 23, a graph 2300 is shown with usage curves for active generators and propulsion devices (e.g., propellers and generators). It has been shown that the use of active generators includes two, while active propulsion varies from four to two and back again, meaning that less fuel can be used during the time in which fewer propulsion devices are used, while still providing sufficient propulsion for the duration of a voyage. The decision to use more or fewer propulsion devices can be based on the simulation results, as described above.That is, if a simulation determines that a certain course is advantageous over other potential courses for fuel-saving purposes that involved turning propulsion devices, then the simulation can incorporate a variety of different configurations that allow the system to use or disable different operating parameters during the simulation. For example, the number and type of propulsion systems can be manually and / or automatically turned on and off by the simulation to, for example, determine the most efficient way to operate the vessel for fuel efficiency. Referring to Figure 24, a flowchart 2400 of an illustrative simulation run by an advisory system for determining more efficient fuel consumption for a maritime vessel is shown. The simulation flowchart 2400 may begin in step 2402. In step 2404, a starting point A and an ending point B of a vessel's trajectory may be established. The starting point A may be set based on the current coordinates of the maritime vessel. In step 2406, vessel parameters and fuel consumption may be calculated at different operating speeds. In one embodiment, the different speeds may be set in increments of 3,704 km / h (2 knots) per hour. Alternatively, other increments may be used.Alternatively, instead of using constant speeds, variable or dynamic speeds can be set based on the environmental conditions that exist or are expected to exist when the maritime vessel is impacted by environmental conditions. Machine learning and / or artificial intelligence can be used to calculate vessel parameters and fuel consumption. For example, artificial intelligence can be used to recognize previous weather and / or water conditions and determine the optimal speed settings, headings, or other operating parameters that maximize fuel efficiency for those recognized environmental conditions.In one embodiment, for example, a dynamic simulation operating in real time may be used to continuously update and generate new operating parameters (e.g., propulsion speed, number of propulsion systems used, type of propulsion systems used, etc.) that maximize fuel efficiency may be used based on continuously updated environmental parameters. An embodiment of a system for navigating a maritime vessel may include a user interface that allows a user to enter a destination location on a waterway to which cargo from the maritime vessel is to be delivered. A processor may be in communication with propulsion controllers configured to control propulsion devices on a vessel, and be configured to receive the destination location from the user interface, receive a time when the cargo to be transported by the maritime vessel must arrive at the destination location, calculate waypoints through which the maritime vessel must travel to the destination location, and cause the propulsion controllers to generate propulsion commands to cause the maritime vessel to follow the calculated waypoints. The processor, when calculating navigation commands, can be further configured to receive measured environmental forces along a route between a vessel location and the destination location, and calculate updated navigation points based on the environmental forces. The processor can be further configured to calculate a departure time by which the vessel must depart to ensure arrival at the destination time. The departure time can be the latest time by which the vessel must depart to be able to reach the destination location at the arrival time. The departure time can be an optimal departure time that minimizes fuel consumption of the propulsion engines.The processor may further be configured to run a simulation using measured environmental forces along a route between a current location of the vessel and the destination location and, in response to running the simulation, cause the simulation results to be indicative of projected fuel usage along the current route and display an alternate route. The processor may be further configured to determine that an earliest arrival time is after the time by which the cargo is to arrive at the destination location, and to generate a report indicative of the determined late arrival based on the determined arrival time. In generating the report, the processor may be configured to automatically generate the report in response to determining that the earliest arrival time is after the time by which the cargo is to arrive at the destination location. The processor may be further configured to generate the report before or during transportation of the cargo to the destination location. The report may be further configured to automatically communicate the report (e.g., to a ground location, such as the destination location). The above method descriptions and process flow diagrams are provided merely as illustrative examples and are not intended to require or imply that the steps in the various embodiments must be performed in the order presented. As one skilled in the art will appreciate, the steps in the above embodiments may be performed in any order. Words such as "then," "next," and so on, are not intended to limit the order of the steps; these words are used simply to guide the reader through the description of the methods. Although process flow diagrams may describe operations as sequential, many of the operations may be performed in parallel or simultaneously. Furthermore, the order of operations may be rearranged. A process may correspond to a method, function, procedure, subroutine, subprogram, and so on.When a process corresponds to a function, its termination may correspond to a return of the function to the requesting function or to the main function. The various illustrative logic blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different manners for each particular application, but such implementation decisions should not be construed as causing a departure from the scope of the present invention. The embodiments implemented in computer software may be implemented in software, firmware, middleware, microcode, hardware description languages, or any combination thereof. A machine-executable code segment or instruction may represent a procedure, function, subprogram, program, routine, subroutine, module, software package, class, or any combination of instructions, data structures, or program instructions. A code segment may be coupled to and / or communicate with another code segment or hardware circuit by transmitting and / or receiving information, data, arguments, parameters, or memory contents. The information, arguments, parameters, data, etc., may be transferred, forwarded, or transmitted through any suitable means, including memory sharing, message passing, token passing, network transmission, etc. The actual software code or specialized control hardware used to implement these / 1 / Qbn / zznz / q / YiAi systems and methods is not limiting of the invention. Therefore, the operation and behavior of the systems and methods are described without reference to the specific software code, it being understood that control software and hardware may be designed to implement the systems and methods based on the disclosure herein. When implemented in software, functions may be stored as one or more instructions or code on a non-transitory computer-readable or processor-readable storage medium. The steps of a method or algorithm disclosed herein may be incorporated into a processor-executable software module that may reside on a computer-readable or processor-readable storage medium. A non-transitory computer-readable or processor-readable medium includes both computer storage media and tangible storage media that facilitates the transfer of a computer program from one location to another. A non-transitory processor-readable storage medium may be any available medium that can be accessed by a computer.By way of example, and not limitation, such non-transitory processor-readable media may comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other tangible storage medium that can be used to store the desired program code in the form of instructions or data structures and which can be accessed by a computer or processor. Disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, some of which reproduce data magnetically and others reproduce data optically with lasers. Combinations of the foregoing shall also be included within the scope of computer-readable media.Furthermore, the operations of a method or algorithm may reside as one or any combination or set of codes and / or instructions on a non-transitory processor-readable medium and / or computer-readable medium, which may be incorporated into a computer program product. The foregoing description is of a preferred embodiment for implementing the invention, and the scope of the invention should not necessarily be limited by this description. The scope of the present invention is defined instead by the following claims.

Claims

1. A method for optimizing fuel consumption of a maritime vessel, the method comprising: measuring operating parameters of the maritime vessel, the operating parameters including current vessel speed and fuel consumption; calculating projected fuel consumption based on a vessel speed of the maritime vessel different from the current vessel speed; displaying the projected fuel consumption and the different vessel speed associated with the projected fuel consumption; and enabling an operator to cause the maritime vessel to selectively change the current vessel speed to the different vessel speed.

2. The method according to claim 1, wherein calculating the projected fuel consumption includes running a simulation that models the maritime vessel and applies the different vessel speed to determine fuel consumption along a trajectory toward a destination location from a departure location.

3. The method according to claim 1, wherein running a simulation includes running a simulation using the current coordinates as a starting location.

4. The method according to claim 3, wherein the simulation execution includes the simulation execution in real time, and the actual operating parameters of the maritime vessel are used in the simulation to calculate the projected fuel consumption.

5. The method according to claim 4, wherein the execution of the simulation includes the execution of the simulation using the ambient conditions to determine the projected fuel consumption.

6. The method according to claim 5, wherein the execution of the simulation includes the execution of the simulation using environmental conditions along the route between the departure location and the destination location to determine the projected fuel consumption.

7. The method according to claim 1, wherein the calculation of the projected fuel consumption includes the use of a machine learning software module that uses the historical performance of the operating parameters of maritime vessels when calculating the projected fuel consumption.

8. The method according to claim 1, wherein the calculation of the projected fuel consumption includes the use of artificial intelligence to identify the operating parameters of the vessel and / or the environmental conditions to determine the speed of the different vessels.

9. The method of claim 1, wherein allowing an operator to cause the seagoing vessel to selectively change the current vessel speed to the different vessel speed includes providing an actuator for the operator to select to change the vessel speed from the current vessel speed to the different vessel speed. / 1 / Qbn / zznz / q / YiAi determined arrival.

18. The system of claim 17, wherein the processor, in generating the report, is configured to automatically generate the report in response to determining that the earliest arrival time is after the time by which the cargo is to arrive at the destination.

19. The system of claim 18, wherein the processor is configured to generate the report before or during transportation of the cargo to the destination. 20.The system according to claim 19, wherein the processor is configured to automatically communicate the report.

Images