System and method for automated wet material management

Abstract

An automated wet stock management system can include a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility, and a wet stock management server communicatively coupled to the plurality of sensors. The wet stock management server can process the fuel data to detect whether the fuel data satisfies an anomaly indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wet stock management server. In some embodiments, the wet stock management server can generate a workflow for assisting a user of the fuel storage facility to resolve the operational issue. In some embodiments, the wet stock management server can assign a risk category to the anomaly and electronically transmit an alert to the user characterizing the operational issue.

Description

[0001] Cross Reference to Related Applications

[0002] This application claims priority to U.S. Patent Application No. 16 / 506,614, filed July 9, 2019, entitled “Systems and Methods for Automated Wetstock Management,” the entirety of which is incorporated herein by reference. TECHNICAL FIELD

[0003] Systems and methods for automated management of wetstock are provided. BACKGROUND

[0004] Wetstock management is a fundamental function in the day-to-day operations of a fuel storage facility. Generally, wetstock management can involve monitoring fuel inventory at a fuel storage facility using a variety of measurement devices such as automatic tank gauges (ATGs), fuel leak detection sensors, magnetostrictive probes, and the like, evaluating the measurements to detect anomalies and, often, unsafe events affecting the fuel inventory (e.g., fuel loss, fuel excess, tank defects, operational problems, etc.), and taking corrective action when necessary.

[0005] Conventionally, wetstock measurements can be evaluated manually by a storage facility operator. The operator can be responsible for monitoring the measurements in order to identify anomalies and respond appropriately. However, the practice of relying on human manual monitoring of large volumes of sensor data can be error-prone, potentially leading to failure to detect and resolve problems at an early stage. In the context of wetstock management, such failures can have catastrophic consequences, such as environmental pollution, loss of revenue, damage to reputation, and public health risks. SUMMARY

[0006] Methods and devices for automated wetstock management are provided. In one example embodiment, one or more of a plurality of sensors disposed in a fuel storage facility can sense fuel data characterizing one or more aspects of the fuel storage facility. A wetstock management server communicatively coupled to the plurality of sensors can process the fuel data to detect whether the fuel data satisfies an anomaly indicative of an operational problem of the fuel storage facility based on one or more predefined rules or models stored in the wetstock management server.

[0007] In certain example embodiments, upon detecting the anomaly, the wetstock management server can identify the operational problem of the fuel storage facility based on the anomaly. The wetstock management server can then automatically generate a workflow comprising a series of steps to assist one or more users of the fuel storage facility in resolving the identified operational problem. Further, a device communicatively coupled to the wetstock management server can display a visual feature of the workflow using a display unit of the device.

[0008] In certain example embodiments, when the anomaly is detected, the wet stock management server can assign a risk category of a plurality of predefined risk categories to the anomaly based on one or more anomaly criteria associated with each of the plurality of predefined risk categories. Based on the identified risk category, the wet stock management server can automatically select one or more electronic communication channels and electronically transmit an alert characterizing the operational issue to one or more users via the one or more selected electronic communication channels. BRIEF DESCRIPTION OF DRAWINGS

[0009] Embodiments herein can be better understood with reference to the following description in conjunction with the accompanying drawings, in which like reference numerals indicate identical or functionally similar elements, wherein:

[0010] Figure 1 is a flowchart illustrating an example overview of an automated wet stock management system;

[0011] Figure 2 is an example user interface implemented by the automated wet stock management system of Figure 1 ; and

[0012] Figure 3 is a flowchart illustrating an example simplified procedure implemented by the automated wet stock management system of Figure 1 .

[0013] It should be understood that the foregoing drawings are not necessarily to scale, presenting a somewhat simplified representation of various preferred features illustrative of the basic principles of the disclosure. The specific design features of the disclosure, including, for example, specific dimensions, orientations, locations, and shapes, will be determined in part by the particular intended application and use environment. DETAILED DESCRIPTION

[0014] Wet stock management can involve monitoring fuel inventory at a fuel storage facility using fuel data sensors, evaluating the measurement data to detect anomalies affecting the fuel inventory, and performing corrective actions if necessary. The sensors can measure fuel data characterizing myriad possible aspects of the fuel storage facility. For example, fuel losses due to leaks, theft, delivery shortfalls, or the like can be detected and damage to storage equipment can be identified. By applying, for example, artificial intelligence and / or machine learning techniques to automate these processes in an “intelligent” manner, as described below, wet stock management can be performed more efficiently, economically, and safely.

[0015] Embodiments of methods and systems for automated wet stock management are discussed below.

[0016] Figure 1One embodiment of an exemplary automated wet stock management system is shown. The automated wet stock management system ("wet stock system") 100 can use automated processing, artificial intelligence, and / or machine learning techniques to provide an automated, alert-driven wet stock management service to dynamically create workflows for the purpose of resolving issues that arise in a given fuel storage facility. In some embodiments, the operations of the wet stock system 100 can be performed by a remote, cloud-based wet stock management server (not shown) that is configured to perform one or more of the operations described below. The wet stock system 100 can collect electronic fuel data characterizing one or more aspects of a fuel storage facility from a plurality of sources, including but not limited to the fuel stored in the facility, storage equipment (e.g., tanks), monitoring equipment, etc., such as, for example, automated tank gauges (ATGs), point-of-sale equipment, forecourt controllers, back office systems, fuel dispensers, and the like, as well as manually submitted fuel data (e.g., through a wet stock management computer application, a web site, etc.). The wet stock system 100 can automatically process the collected data through various algorithms, machine learning, and / or artificial intelligence to create alerts and / or anomalies.

[0017] Further, the wet stock system 100 can apply a risk classification to the dynamically created diagnostic workflows. The wet stock system 100 can evaluate incoming data when an anomaly is raised, validate the anomaly to filter out any invalid anomalies, classify the anomaly based on risk, identify the most likely fault and the probability of the fault, and notify a user (e.g., a fuel storage facility operator or administrator, a fuel merchant, etc.) in a bespoke manner. In addition to anomaly-specific faults, the wet stock system 100 can utilize individual anomalies to generate a consolidated risk versus probability model and solution. Finally, the wet stock system 100 can track and record resolved issues. The data can be used as training data in a machine learning context to enable the wet stock system 100 to learn from previous diagnostics and diagnose similar situations more effectively in the future.

[0018] According to some embodiments, as shown in Figure 1 The wet stock system 100 can be configured to embody support components 110 and analysis components 120, each of which is comprised of a plurality of individual elements. However, the wet stock system 100 is not limited to this configuration. The support components 110 of the wet stock system 100 can include components necessary to enable the analysis models, implemented by the analysis components 120, to function and be serviced. The analysis components 120 of the wet stock system 100 can include components through which the collected fuel data is processed and analyzed. It should be understood that the support and analysis components 110 and 120 are not limited to the configurations shown in FIG. 1. Figure 1The configuration shown in the figures and described below is an example configuration. Other configurations can be used consistent with the scope of the present claims as defined herein.

[0019] In operation, the wetstock system 100 can execute the individual units of the support and analysis components 110 and 120 in a particular order, such as the order depicted in the figures. However, Figure 1 the order of the units shown in the figures is provided for exemplary purposes only, and operation of the wetstock system 100 is not limited thereto. Thus, the units of the support and analysis components 110 and 120 can be executed in any suitable order, respectively, as would be understood by one of ordinary skill in the art consistent with the scope of the present claims as defined herein. Figure 1

[0020] Referring now to Figure 1 , the support component 110 can initialize the wetstock system 100 by executing units that support or enable operation of the analysis component 120, thereby automatically processing and analyzing collected fuel data. Initially, for example, an onboarding unit 111 can be executed, whereby features required to initialize an organization, site, wetstock details, and the like are performed. Similarly, a user and system management unit 112 can be executed, whereby features required to initialize one or more users (e.g., fuel storage facility operators or administrators, fuel merchants, etc.) of the wetstock system 100 are performed. For example, one or more registered users of the wetstock system 100 can be loaded, one or more user preferences can be imported, user permissions can be set, and the like. Further, features required to initialize the wetstock system 100 itself can be performed. For example, security settings associated with the wetstock system 100, site groups, and the like can be initialized. Depending on the configuration, the user and system management unit 112 can initialize user and system settings using operational data stored in local or remote memory (not shown) that characterizes one or more aspects of previous operation of the wetstock system 100. In the absence of such operational data, the user and system management unit 112 can initialize user and system settings according to a default configuration.

[0021] ​Once the support component 110 initializes the wet stock system 100 by executing the units that support or enable the operation of the analysis component 120, the units of the analysis component 120 can be executed. First, for example, the data processing unit 121, which includes both import and export of data, can be executed. In detail, the data processing unit 121 can begin by collecting fuel data characterizing one or more aspects of the fuel storage facility from a variety of devices such as sensors or other measurement tools. These devices can include, for example, ATGs, fuel leak detection sensors, magnetostrictive probes, point-of-sale devices, forecourt controllers, back office systems, fuel dispensers, and the like. In addition, users of the wet stock system 100 can manually submit data to be processed. All of the input data can be combined and exported for automated assessment using predefined algorithms (122) of the wet stock system 100.

[0022] The algorithm unit 122 can then be executed, whereby the fuel data collected in the data processing unit 121 is input to one or more predefined models and / or rules of the wet stock system 100. The algorithms of the wet stock system 100 can include any models and / or rules for processing the collected fuel data to generate one or more anomalies (123) if said one or more anomalies are present. The algorithms can be used to assess the collected input data for any number of purposes such as analyzing fuel loss, flow, delivery volume, and the like, in order to alert users of any problems occurring in the fuel storage facility. Such algorithms can include, but are not limited to, anomaly detection (e.g., detecting the presence of a value outside of a computed or preconfigured normal range of values during a given time slice), trend analysis (e.g., detecting a trend of a value moving toward a range deemed unacceptable), cross-value correlation (e.g., detecting a trend of a change in a value based on a value of another variable or an external event), and the like. To this end, the input data can be analyzed in a variety of ways such as computing a maximum or minimum value over a given time slice, computing an average, mean, or median value over a given time slice, computing a standard deviation over a given time slice, and the like. For example, an average value in a given time slice (e.g., week, month, quarter, year, etc.) can be compared to a corresponding average value associated with a past time slice to detect an anomaly. In some embodiments, multiple algorithms can be combined to create a new algorithm. The output data generated by executing these algorithms can be used to identify anomalies, escalate risks, and / or applied to further algorithms.

[0023] Next, the anomaly and service unit 123 can be executed, whereby anomalies generated by processing the collected fuel data via the above-described algorithms can be communicated to the user. For the purposes of the present disclosure, an anomaly can refer to any data outputted via the algorithm unit 122 that has a value outside of a predefined normal or safe range or threshold. For example, a fuel leak can cause a sudden drop in the fuel tank level. If the ATG detects that the level is less than a predefined minimum tank level threshold, there can be an anomaly indicating a fuel leak. A wide range of services can be provided to the user based on the generated anomalies, including, for example, predictive maintenance of equipment that is about to fail, regulatory report generation and communication to the appropriate standard bodies, authority notification when product theft is detected, predictive delivery of product based on trends, supplier notification of incorrect delivery of product (e.g., insufficient delivery, incorrect product, etc.), automatic shut down of fuel pumps due to detected issues (e.g., leaks, mechanical pump issues, etc.), and the like.

[0024] Next, the risk escalation unit 124 can be executed, whereby risk categories can be assigned to the anomalies generated by the algorithm unit 122 and the anomaly and service unit 123 based on a variety of factors. The risk assignment can be used to determine whether to escalate the anomaly, and the degree to which the anomaly is escalated. Further, the risk classification can allow the user to assign rules to specific risk categories that are specific to their needs. In certain instances, when an anomaly in the input data is detected and an anomaly is generated in the above-described manner, the machine learning based system can examine the actions taken to resolve the anomalous situation in real-time as the anomalous situation occurs, such as a fuel leak. Thus, when the anomaly reoccurs, the response time can be compared to both the configured service level agreement and past resolutions to determine whether the correct resources were applied and whether the fuel leak was given the appropriate attention. Further, when a new anomaly in the fuel data is detected and an anomaly is generated that can exacerbate the situation, the machine learning techniques can use past resolutions as training data to change the resources assigned or invoke an automated reaction to the new higher or lower risk. Examples of these reactions can be shutting down equipment, notifying authorities, notifying more experienced personnel, and the like.

[0025] Next, a workflow unit 125 can be executed whereby a workflow comprising a series of steps for assisting a user in resolving the identified operational problem can be generated in real-time based on the identified anomaly and the risk category assigned thereto. The workflow can depend on the threat and severity of the problem, take into account the field device, and provide end-to-end support to the user in resolving the operational problem in the most appropriate and efficient manner. For example, when the operational problem is a fuel leak, the workflow can include steps aimed at correcting or preventing the fuel leak from worsening. The workflow can be provided to the user in a manner determined from the generated anomaly and the risk level assigned thereto. In some embodiments, a device (e.g., a computing device such as a computer, mobile device, tablet device, etc.) coupled to a wet material management server (not shown) responsible for executing the analysis component 120 can display visual features of the workflow via a display unit of the device, enabling the user to read and follow the displayed workflow steps.

[0026] Next, a notification unit 126 can be executed whereby a notification or alert characterizing the operational problem can be generated, each of which are used interchangeably herein, and can be sent to the user through various possible communication channels or mechanisms. The notification can be generated to take into account the specific message and channel of communication used depending on the type of alert. Multiple different users can be notified at once, which can vary depending on the time of day. Furthermore, the notification can be created and transmitted in a manner determined based on the assigned risk category, such that the user is alerted of the field device problem only when certain rules and / or risks are violated.

[0027] Upon resolution of the operational problem, e.g., the detected fuel leak has been eliminated, a data reevaluation unit 127, resolution and learning unit 128, and tool unit 113 can be executed, completing the analysis component 120 and support component 110 for the particular anomaly. In response to the problem resolution, the assigned risk category can be de-escalated, but fuel data can still be collected and monitored to ensure that the anomaly does not recur. Furthermore, the wet material system 100 can keep a record for ongoing improvements thereto, such as validation of the workflow and training of the model. In this regard, machine learning techniques can be applied to train the rules, thresholds, and / or settings using available information (e.g., collected fuel data, generated anomalies, workflows, notifications, etc.) as input. As a result, the workflows and notifications provided by the wet material system 100 in response to anomalies can be improved throughout the operational life of the system.

[0028] As an illustrative example, assume a fuel storage facility is equipped with a tank overflow alarm that activates when an ATG coupled to a fuel tank detects a particular inventory level volume. A fuel data collection device (not shown), such as an Internet of Things (IoT) device, located on-site can collect ATG data and transmit the collected data to a remotely located wetstock management server (not shown) configured to perform operations of the wetstock system 100. In particular, the wetstock management server can execute the aforementioned units of the analysis component 120 including the data processing unit 121 to collect ATG data from the fuel data collection device in conjunction with other on-site device measured fuel data and / or manually entered data, the algorithm unit 122 to process the collected data according to one or more predefined rules and / or models, the anomaly and service unit 123 to determine whether an anomaly exists, such as a fuel tank level outside of a safety range, the risk escalation unit 124 to assign a risk category to the detected anomaly, and the workflow unit 125 to generate a workflow that provides end-to-end support for a user to resolve the issue causing the anomaly.

[0029] The wetstock management server can further execute the notification unit 126 to determine a notification action dependent on user-specific and tank-specific settings. In some cases, multiple risk categories can be created, where each risk category corresponds to one or more predefined anomaly criteria. Each risk category can also correspond to one or more electronic communication channels through which a notification is delivered, such as an automated phone call, a short message service (SMS) message (text message), an email, a push notification to a wetstock management application, and the like. As the urgency of a risk category increases, more communication channels can be selected to transmit a notification. A risk category from among the multiple possible risk categories can be assigned to an anomaly based on the anomaly criterion(s) associated with each risk category. To illustrate, an example set of risk categories and corresponding criteria and communication channels are provided in Table 1 below.

[0030] [Table 1]

[0031] Risk category type Abnormal criteria Communication channel Has equalled or exceeded nominal capacity Phone call; SMS; email; push notification Safety working capacity (SWC) has been breached by more than 100 litres SMS; push notification SWC has been breached by less than 100 litres Push notification SWC has not been breached No alarm

[0032] Based on the risk category of the generated anomaly, a notification describing the operational issue can be generated and electronically transmitted via the corresponding electronic communication channel(s). The notification can include any available data characterizing the nature of the issue. As the risk of the operational issue, such as the severity of a fuel leak, increases, the number of communication channels through which a notification is transmitted also increases. The date and time of the detected operational issue can determine one or more users of the notification.

[0033] The notified user(s) can then log into the application of the wet material system 100 and review a workflow generated by the wet material management server for the anomaly that will guide them to resolve the issue (e.g., a fuel leak). The workflow can include recommendations such as checking a particular location, e.g., an interceptor, a forecourt sensor, etc., for signs of a fuel spill, contacting a relevant authority or response team, and the like. After the issue has been resolved, the wet material system 100 can keep a record for learning purposes so that in the event of future inventory readings at the same elevation, the risk of such an issue is known and can be resolved more efficiently.

[0034] The wet material system 100 can implement a wet material management computer application having a user interface through which a user can interact with the wet material system 100 by viewing workflows, receiving notifications (e.g., push notifications), and the like. In this regard, Figure 2 is an example user interface implemented by the wet material system 100. The user interface 200 can include a variety of interactive elements designed to inform a user of information characterizing one or more aspects of a fuel storage facility provided by the wet material system 100. For example, the user interface 200 can include a test point selection portion 210 in which a user can select a test point (e.g., test point 1) of a fuel storage facility and a particular tank (e.g., tank 1) of the selected point. The test point selection portion 210 can also include selectable elements (e.g., buttons, drop-down menus, test input fields, etc.) that enable a user to quickly select a current point, receive a confidence prediction (as described below), and / or reset all input data collected by the wet material system 100.

[0035] Additionally, the user interface 200 can include a fuel data portion 220 that displays information based on collected fuel data characterizing one or more aspects of a fuel storage facility. For example, the fuel data portion 220 can include status indicators for sensors, alarms, and the like within a fuel storage facility. Moreover, the fuel data portion 220 can include visual indicators of both active and inactive anomalies automatically determined by the wet material system 100 based on collected fuel data. As shown in Figure 2 For example, the fuel data object 221 can indicate an inactive anomaly, while the fuel data object 222 can indicate an active anomaly. As such, the wet material system 100 is not limited to identifying only a single anomaly at a time, but can identify multiple anomalies in certain situations.

[0036] In some embodiments, the wet stock system 100 can combine multiple anomalies indicated by the fuel data objects 221 and 222 in order to predict the most likely cause of the anomaly. In this regard, the user interface 200 can include a confidence prediction section 230 in which one or more possible faults are provided in order of probability calculated using the wet stock system 100 analysis described above. As Figure 2 For example, as shown in the middle, a line issue can be predicted as the most likely fault or cause of the current anomaly. Based on the predicted most likely fault, the wet stock system 100 can generate a workflow in the manner described above that can be displayed to the user through the user interface 200. In some embodiments, the user can select a particular predicted cause of the anomaly and the workflow can be generated based on the selected cause.

[0037] Figure 3 is a flowchart illustrating an example simplified procedure implemented by the wet stock system 100. The procedure 300 can begin at step 305 and continue to step 310, where, as described in greater detail below, the wet stock system 100 can perform automated wet stock management to enable resolution of an anomaly identified during operation of a fuel storage facility.

[0038] At step 305, one or more of a plurality of sensors (e.g., ATG, fuel leak detection sensors, magnetostrictive probes, point-of-sale devices, forecourt controllers, back office systems, fuel dispensers, etc.) disposed in a fuel storage facility can sense fuel data of the fuel storage facility. The fuel data can include any type of measurement data characterizing one or more aspects of the fuel storage facility, including, for example, fuel tank levels, water content, leak detection, flow readings, device status, and the like.

[0039] At step 310, a wet stock management server communicatively coupled to the plurality of sensors can collect the acquired fuel data via the data processing unit 121 and process the fuel data via the algorithm unit 122 and the anomaly and service unit 123 to detect whether the fuel data satisfies an anomaly indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wet stock management server. The wet stock management server can be a remote server, i.e., a cloud-based server, located outside of the fuel storage facility. In some embodiments, the measured fuel data can be collected by a fuel data collection device (not shown), such as an IoT device, located on-site, and the fuel data collection device can transmit the collected data to the wet stock management server for processing.

[0040] Upon detecting that the collected fuel data satisfies an anomaly, the procedure 300 can proceed towards one or more outputs, including generating and displaying a work flow (steps 315 to 325) and identifying a risk category and transmitting an alert via a selected communication channel (steps 330 to 340). In some embodiments, only one of the outputs can be performed. In other embodiments, two outputs or any combination thereof can be performed.

[0041] At step 315, an operational issue of the fuel storage facility can be identified based on the anomaly. For example, if the anomaly stems from a sudden drop in the fuel tank level, the operational issue can be identified as a loss or leak of fuel.

[0042] At step 320, a work flow can be generated via the work flow unit 125 for assisting a user of the fuel storage facility in resolving the operational issue identified in step 315. The work flow can include a series of steps that provide end-to-end support to the user to resolve the operational issue in the most appropriate and efficient manner. The work flow can be dynamically generated, i.e., generated in real-time, while taking into account the on-site equipment and the severity of the issue.

[0043] At step 325, a device communicatively coupled to the wet stock management server can display a visual feature of the work flow, such as a list of the work flow steps. For example, a device such as a computer, a mobile device, a tablet computer, or the like can include a display unit configured to display the visual feature of the work flow. In some embodiments, the user can interact with the device, for example, by indicating via the device that a work flow step has been completed, that additional assistance is needed, or the like.

[0044] Meanwhile, at step 330, a risk category out of a plurality of predefined risk categories can be assigned to the anomaly via the risk escalation unit 124. Identifying the risk category can be performed based on one or more anomaly criteria associated with each of the plurality of predefined risk categories. For example, as shown in Table 1, a criterion pertaining to an amount of fuel exceeding a predefined maximum limit can correspond to each risk category. The anomaly detected in step 310 can be compared to the anomaly criteria to assign an appropriate risk category to the anomaly.

[0045] At step 335, one or more electronic communication channels out of a plurality of predefined electronic communication channels can be selected for transmitting an alert to a user characterizing the operational issue. Again with reference to Table 1, each predefined risk category can correspond to a specific set of electronic communication channels. Accordingly, the one or more electronic communication channels can be selected based on the assigned risk category.

[0046] At step 340, an alert or notification characterizing the operational problem can be electronically transmitted to the user via the notification unit 126 using the one or more electronic communication channels selected in step 335. The number of users receiving the alert can depend on the level of urgency associated with the assigned risk category and the date and time at which the anomaly was detected. Furthermore, the alert can be created and transmitted such that the user is only alerted of the on-site equipment problem when certain rules and / or risks are breached.

[0047] The program 300 can continue throughout the operation of the fuel storage facility. The techniques by which the steps of the program 300 can be performed are described in detail above, as are ancillary programs and anomaly criteria.

[0048] It should be noted that, Figure 3 The steps shown in FIG. 3 are merely examples for illustration and can include or exclude certain other steps as desired. Furthermore, while a particular order of steps is shown, this order is merely illustrative, and any suitable arrangement of steps can be utilized without departing from the scope of the embodiments herein. Still further, the steps shown can be modified in any suitable manner according to the scope of the present claims.

[0049] Accordingly, the automated wet material management system discussed herein can combine all known alerts and data points, on-site equipment and infrastructure details into a model to provide the most likely on-site failure for the user based on risk, likelihood, real-life probability, and equipment on-site. By applying artificial intelligence and machine learning techniques to the wet material management program, wet material management can be performed more efficiently, thereby saving costs and improving safety.

[0050] It should be understood that the terms used herein are for the purpose of describing particular embodiments and are not intended to be limiting of the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" "comprising," "includes" or "including" when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of one or more of the associated listed items. The term "coupled" means the physical relationship between two components, whereby the components are directly connected to each other or indirectly connected via one or more intermediate components.

[0051] As used throughout the specification and claims, approximate language can be used to modify any permissible variation without altering its associated essential function in quantitative representation. Therefore, values ​​modified by one or more terms such as “about,” “approximately,” and “substantially” are not limited to the specified precise values. In at least some cases, approximate language may correspond to the precision of the instrument used to measure the value. Scope limitations may be combined and / or interchanged herein and throughout the specification and claims, and unless otherwise specified by context or language, such scopes are identified and include all subscopes contained therein.

[0052] Furthermore, it should be understood that one or more of the above methods or aspects thereof can be performed by at least one control unit. The term "control unit" can refer to a hardware device including a memory and a processor. The memory is configured to store program instructions, and the processor is specifically programmed to execute the program instructions to perform one or more of the above processes. As described herein, a control unit can control a unit, module, part, device, or such operation. Moreover, it should be understood, as those skilled in the art will appreciate, that the above methods can be performed by a device, such as a wet material management server, including a control unit in conjunction with one or more other components.

[0053] The foregoing description has been directed to embodiments of the present disclosure. However, it is clear that other changes and modifications can be made to the described embodiments to obtain some or all of their advantages. Therefore, this description is to be understood as illustrative only and is not intended to otherwise limit the scope of the embodiments herein. Accordingly, the appended claims are intended to cover all such changes and modifications that fall within the true spirit and scope of the embodiments herein.

Claims

1. A method for automated wet stock management, comprising: sensing, using one or more of a plurality of sensors disposed in a fuel storage facility, fuel data characterizing one or more aspects of the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect, based on one or more predefined rules or models stored in the wet stock management server, whether the fuel data satisfies a plurality of anomalies indicative of an operational issue of the fuel storage facility; and in response to detecting that the fuel data satisfies the plurality of anomalies: identifying, by the wet stock management server, a plurality of predicted causes of the operational issue of the fuel storage facility based on the plurality of anomalies, generating, by the wet stock management server, a workflow comprising a series of steps for assisting one or more users of the fuel storage facility in resolving the identified operational issue, the generated workflow based on a user selection received by the wet stock management server indicative of a predicted cause from the identified plurality of predicted causes, causing, by the wet stock management server, a device communicatively coupled to the wet stock management server to display, using a display unit of the device, a visual feature of the workflow, storing, by the wet stock management server, the fuel data in a storage unit, and training, by the wet stock management server, a machine learning algorithm using the fuel data, the machine learning algorithm operable to accept a given dataset as input and assign a risk category from a plurality of predefined risk categories to an anomaly as output.

2. The method of claim 1, wherein, detecting whether the fuel data satisfies the plurality of anomalies comprises: obtaining a current fuel level based on the fuel data; and determining whether the current fuel level exceeds a predefined capacity of a fuel tank.

3. The method of claim 1, wherein, the visual feature comprises analysis information of the fuel data and one or more recommended actions for resolving the operational issue.

4. The method of claim 1, further comprising: storing, by the wet stock management server, the fuel data in a storage unit; and training, by the wet stock management server, a machine learning algorithm using the fuel data and data characterizing the operational issue of the fuel storage facility, the machine learning algorithm operable to accept a given dataset as input and identify an operational issue of the fuel storage facility as output.

5. The method of claim 1, wherein, the fuel data comprises measurements obtained by two or more of the plurality of sensors.

6. The method of claim 1, further comprising: determining, by the wet stock management server, whether the fuel data satisfies any of a plurality of predefined anomalies, respectively; and in response to determining that one or more of the plurality of predefined anomalies are satisfied, identifying, by the wet stock management server, an operational issue of the fuel storage facility based on the one or more predefined anomalies that are satisfied.

7. The method of claim 1, further comprising: generating, by the wet stock management server, a probability associated with each of a plurality of possible operational issues; and identifying, by the wet stock management server, an operational issue of the fuel storage facility based on a possible operational issue from the plurality of possible operational issues associated with a highest generated probability.

8. The method of claim 1, further comprising: causing, by the wet stock management server, the device to display, via the display unit, a visual feature of the one or more predefined anomalies that are satisfied.

9. The method of claim 8, wherein, the visual feature comprises an indication of whether the one or more predefined anomalies that are satisfied are active or inactive.

10. A system for automated wet stock management, comprising: a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility; a wet stock management server communicatively coupled to the plurality of sensors, the wet stock management server configured to: process the fuel data to detect, based on one or more predefined rules or models stored in the wet stock management server, that the fuel data satisfies a plurality of anomalies indicative of an operational issue of the fuel storage facility, identify a plurality of predicted causes of the operational issue of the fuel storage facility based on the plurality of anomalies, generate a workflow comprising a series of steps for assisting one or more users of the fuel storage facility in resolving the identified operational issue, the generated workflow based on a user selection received by the wet stock management server indicative of a predicted cause from the identified plurality of predicted causes, store the fuel data in a storage unit, and train a machine learning algorithm using the fuel data, the machine learning algorithm operable to accept a given data set as input and assign a risk category from a plurality of predefined risk categories to an anomaly as output; and a device communicatively coupled to the wet stock management server, the device comprising a display unit, wherein the wet stock management server is configured to cause the device to display, via the display unit, a visual feature of the workflow.

11. A method for automated wet stock management, comprising: sensing, using one or more of a plurality of sensors disposed in a fuel storage facility, fuel data characterizing one or more aspects of the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect, based on one or more predefined rules or models stored in the wet stock management server, that the fuel data satisfies a plurality of anomalies indicative of an operational issue of the fuel storage facility; and in response to detecting that the fuel data satisfies the plurality of anomalies: identifying a plurality of predicted causes of the operational issue, generating, by the wet stock server, a workflow comprising a series of steps for assisting one or more users of the fuel storage facility in resolving the identified operational issue, the generated workflow based on a user selection received by the wet stock management server indicative of a predicted cause from the identified plurality of predicted causes, assigning, by the wet stock management server, a risk category from a plurality of predefined risk categories to the anomaly based on one or more anomaly criteria associated with each of the plurality of predefined risk categories, selecting, by the wet stock management server, a first number of a plurality of predefined electronic communication channels when the assigned risk category is a first category, selecting, by the wet stock management server, a second number of the plurality of predefined electronic communication channels when the assigned risk category is a second category associated with a risk higher than a risk associated with the first category, the second number greater than the first number, selecting, by the wet stock management server, one or more electronic communication channels from the plurality of predefined electronic communication channels based on the assigned risk category, and electronically transmitting, by the wet stock management server, an alert characterizing the operational issue to the one or more users via the one or more selected electronic communication channels.

12. The method of claim 11, wherein assigning the risk category to the anomaly comprises: obtaining, by the wet material management server, a current fuel level based on the fuel data; calculating, by the wet material management server, a difference between the current fuel level and a predefined capacity of the fuel tank; and assigning, by the wet material management server, a risk category to the anomaly based on the calculated difference.

13. The method of claim 11, wherein, The plurality of predefined electronic communication channels includes two or more of an email, a short message service (SMS), a push notification through a device application, an automated phone call.

14. The method of claim 11, wherein the selection of the one or more electronic communication channels comprises: selecting, by the wet material management server, a first number of the plurality of predefined electronic communication channels when the assigned risk category is a first category; and selecting, by the wet material management server, a second number of the plurality of predefined electronic communication channels when the assigned risk category is a second category associated with a risk higher than a risk associated with the first category, the second number being greater than the first number.

15. The method of claim 11, further comprising: selecting, by the wet material management server, one or more users to receive an alert characterizing the operational issue based on a current date and time.

16. The method of claim 11, further comprising: electronically providing, by the wet material management server, a workflow to the one or more users. The electronic provision of the workflow comprises:

17. The method of claim 16, wherein, causing, by the wet material management server, a device communicatively coupled to the wet material management server to display, using a display unit of the device, a visual feature of the workflow.

18. The method of claim 11, further comprising: storing, by the wet material management server, the fuel data in a storage unit; and training, by the wet material management server, a machine learning algorithm using the fuel data, the machine learning algorithm operable to accept a given dataset as input and assign a risk category of a plurality of predefined risk categories to an anomaly as output.

19. The method of claim 11, further comprising: determining, by the wet material management server, whether the fuel data no longer satisfies a plurality of anomalies; and electronically transmitting, by the wet material management server, a message to the one or more users indicating that at least one of the plurality of anomalies is no longer satisfied when at least one of the plurality of anomalies is no longer satisfied.

20. A system for automated wet material management, comprising: a plurality of sensors disposed in a fuel storage facility, the plurality of sensors configured to sense fuel data characterizing one or more aspects of the fuel storage facility; a wet material management server communicatively coupled to the plurality of sensors, the wet material management server configured to: process the fuel data to detect whether the fuel data satisfies a plurality of anomalies indicative of an operational issue of the fuel storage facility based on one or more predefined rules or models stored in the wet material management server, assign a risk category of a plurality of predefined risk categories to the plurality of anomalies based on one or more anomaly criteria associated with each of the plurality of predefined risk categories, select, by the wet material management server, a first number of the plurality of predefined electronic communication channels when the assigned risk category is a first category, ​ when the assigned risk category is a second category associated with a risk higher than the risk associated with the first category, a second number of the plurality of predefined electronic communication channels is selected by the wetted material management server, the second number being greater than the first number, the plurality of predicted causes of the operational issue being identified, a workflow comprising a series of steps is generated by the wetted material management server for assisting one or more users of the fuel storage facility in resolving the identified operational issue, the generated workflow being based on a user selection received by the wetted material management server, the user selection indicating a predicted cause from the plurality of predicted causes identified, and when the assigned risk category is the first category, an alert characterizing the operational issue is electronically transmitted to the one or more users via a first number of the plurality of predefined electronic communication channels, and when the assigned risk category is the second category, the alert characterizing the operational issue is electronically transmitted to the one or more users via a second number of the plurality of predefined electronic communication channels.

Images