Systems and methods for automated wet stock management
The automated wetstock management system addresses manual monitoring inefficiencies by using sensors and AI to detect fuel anomalies, assign risks, and automate corrective actions, enhancing operational efficiency and safety.
Patent Information
- Application Number
- JP2022500942
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2019-07-09
- Filing Date
- 2020-06-22
- Publication Date
- 2024-11-13
- Estimated Expiration
- 2040-06-22
AI Technical Summary
Traditional wetstock management relies heavily on manual monitoring by operators, which is error-prone and often fails to detect anomalies early, leading to potential environmental pollution, financial loss, and health risks.
An automated wetstock management system using sensors, a wet stock management server, and AI/machine learning to analyze fuel data, identify exceptions, assign risk categories, and generate workflows for corrective actions.
Enhances the efficiency and safety of fuel storage management by promptly detecting and addressing operational issues, reducing risks and costs through automated anomaly detection and response.
Smart Images

Figure 0007582626000002 
Figure 0007582626000003 
Figure 0007582626000004
Abstract
Description
Content of disclosure
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. patent application Ser. No. 16 / 506,614, entitled "Systems and Methods for Automated Wetstock Management," filed July 9, 2019, which is incorporated by reference in its entirety.
[0002] [Field] SUMMARY OF THE DISCLOSURE Systems and methods for automated wetstock management are provided.
[0003] 〔background〕 Wet stock management is an essential function in the day-to-day operation of a fuel storage facility. Typically, wet stock management may involve monitoring fuel stocks at a fuel storage facility using a variety of measurement devices such as automatic tank gauges (ATGs), fuel leak detection sensors, magnetostrictive probes, etc., evaluating the measurements to detect abnormal and often unsafe events affecting the fuel stocks (e.g., fuel loss, fuel overfill, tank defects, operational problems, etc.), and implementing corrective actions as necessary.
[0004] Traditionally, wet stock measurements may be manually assessed by storage facility operators. The operators may be responsible for monitoring the measurements to identify anomalies and respond appropriately. However, the practice of relying on humans to manually monitor large amounts of sensor data is prone to error and may not detect and resolve problems at an early stage. Such failures can have catastrophic consequences in the context of wet stock management, including environmental contamination, lost revenue, damaged reputations, and public health risks.
[0005] 〔overview〕 Methods and devices are provided for automated wet stock management. In one exemplary embodiment, one or more of a plurality of sensors disposed at a fuel storage facility can 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 can process the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem with the fuel storage facility based on one or more predefined rules or models stored at the wet stock management server.
[0006] In certain exemplary embodiments, the wetstock management server can identify an operational problem with the fuel storage facility based on the exception when the exception is detected. The wetstock management server can then automatically generate a workflow including 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 characterization of the workflow using a display unit of the device.
[0007] In certain exemplary embodiments, the wet stock management server can assign a risk category of a plurality of predefined risk categories to the exception when the exception is detected based on one or more exception 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 problem to one or more users via the one or more selected electronic communication channels.
[0008] The embodiments herein may be better understood by reference to the following description in conjunction with the accompanying drawings, in which like reference numbers indicate identical or functionally similar elements. [Brief description of the drawings]
[0009] [Figure 1] 1 is a flow chart illustrating an example overview of an automated wet stock management system. [Diagram 2] 2 is an exemplary user interface implemented by the automated wet stock management system of FIG. 1. [Diagram 3] 2 is a flow chart illustrating an exemplary simplified procedure implemented by the automated wet stock management system of FIG. 1.
[0010] It should be understood that the above-described drawings are not necessarily to scale, but rather depict somewhat simplified representations of various preferred features illustrating the underlying principles of the present disclosure. The particular design features of the present disclosure, including, for example, specific dimensions, orientations, locations, and shapes, are determined in part by the particular intended application and environment of use.
[0011] Detailed Description Wet stock management can include the use of fuel data sensors to monitor fuel reserves at a fuel storage facility, evaluating the measured data to detect anomalies affecting the fuel reserves, and taking corrective action as necessary. The sensors can measure fuel data that characterize myriad possible aspects of the fuel storage facility. For example, fuel losses due to leaks, theft, under-delivery, etc. can be detected, and damage to the storage equipment can be identified. By automating these processes in a "smart" manner, for example, applying artificial intelligence and / or machine learning techniques as described below, wet stock management can be made more efficient, economical, and safe.
[0012] Embodiments of methods and systems for automated wet stock management are discussed herein below.
[0013] FIG. 1 illustrates one embodiment of an exemplary automated wet stock management system. The automated wet stock management system ("wet stock system") 100 can use automated processing, artificial intelligence, and / or machine learning technologies to provide automated, alert-driven wet stock management services and dynamically create workflows for the purpose of resolving issues that arise at 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) configured to perform one or more operations described below. The wet stock system 100 can collect electronic fuel data characterizing one or more aspects of a fuel storage facility, including, but not limited to, fuel stored at the facility, storage equipment (e.g., tanks), monitoring equipment, etc., from multiple sources, such as, for example, automatic tank gauges (ATGs), point-of-sale devices, fueling station controllers, back-office systems, fuel dispensers, etc., as well as manually submitted fuel data (e.g., through a wet stock management computer application, website, 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 exceptions.
[0014] Additionally, the wetstock system 100 can apply risk classification to the dynamically created diagnostic workflow. When an exception occurs, the wetstock system 100 can evaluate the incoming data, validate the exception to filter out any invalid exceptions, classify the exception based on risk, identify the most likely faults and the probability of said faults, and notify the user (e.g., fuel storage facility operator or manager, fuel supplier, etc.) in a custom manner. In addition to the faults specific to the exception, the wetstock system 100 can utilize the individual exceptions to generate a consolidated risk-versus-probability model and solution. Finally, resolved issues can be tracked and logged by the wetstock system 100. This data can be used as training data in a machine learning context to enable the wetstock system 100 to learn from previous diagnoses and more effectively diagnose similar conditions in the future.
[0015] According to some embodiments, as shown in FIG. 1, the wetstock system 100 may be configured to embody a support component 110 and an analysis component 120, each of which is comprised of a number of separate elements. However, the wetstock system 100 is not limited to such a configuration. The support component 110 of the wetstock system 100 may include components necessary to enable the analytical model implemented by the analysis component 120 to function and be serviced. The analysis component 120 of the wetstock system 100 may include components depending on which collected fuel data is to be processed and analyzed. It is understood that the support component 110 and the analysis component 120 are not limited to the configuration shown in FIG. 1 and described below, but may be reconfigured and / or rearranged in any suitable manner as would be understood by one of ordinary skill in the art, consistent with the scope of the claims defined herein.
[0016] In operation, the wetstock system 100 may execute the individual units of the support component 110 and the analytical component 120 in a particular order, such as the order shown in Figure 1. However, the ordering of the units shown in Figure 1 is provided merely for demonstration purposes, and the operation of the wetstock system 100 is not so limited. Thus, the units of each of the support component 110 and the analytical component 120 may be executed in any suitable order, as understood by one of ordinary skill in the art, consistent with the claims defined herein.
[0017] Referring now to FIG. 1 , the support component 110 may initialize the wetstock system 100 by executing units that support or enable the operation of the analysis component 120, whereby collected fuel data is automatically processed and analyzed. First, for example, an onboarding unit 111 may be executed, which may perform functions necessary to initialize the structure, site, wetstock details, etc. Similarly, a user and system management unit 112 may be executed, which may perform functions necessary to initialize one or more users of the wetstock system 100 (e.g., a fuel storage facility operator or manager, a fuel supplier, etc.). For example, one or more registered users of the wetstock system 100 may be loaded, one or more user preferences may be imported, user permissions may be set, etc. Additionally, functions necessary to initialize the wetstock system 100 itself may be performed. For example, security settings, site groups, etc. associated with the wetstock system 100 may be initialized. The user and system management unit 112 may initialize user and system settings using operational data stored in a local or remote memory (not shown), depending on the configuration, to characterize one or more aspects of the previous operation of the wetstock system 100. If said operational data does not exist, the user and system management unit 112 can initialize the user and system settings according to default settings.
[0018] Once the support component 110 has initialized the wet stock system 100 by executing units that support or enable the operation of the analysis component 120, the units of the analysis component 120 can be executed. First, the data processing unit 121, which includes, for example, both importing and exporting data, can be executed. In particular, the data processing unit 121 can begin by collecting fuel data that characterizes one or more aspects of the fuel storage facility from a wide range 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, fueling station controllers, back-office systems, fuel dispensers, and the like. Additionally, a user of the wet stock system 100 can manually submit data to be processed. All entered data can be combined and exported for automatic evaluation using predefined algorithms (122) of the wet stock system 100.
[0019] An algorithm unit 122 may then be executed, whereby the collected fuel data in the data processing unit 121 is input into one or more predefined models and / or rules of the wetstock system 100. The algorithms of the wetstock system 100 may include any models and / or rules for processing the collected fuel data to generate one or more exceptions (123) if said one or more exceptions exist. The algorithms may be used to evaluate the collected input data for a myriad of purposes, such as analysis of fuel losses, flow rates, delivery yields, etc., to alert a user to any problems occurring within the fuel storage facility. Such algorithms may include, but are not limited to, anomaly detection (e.g., detecting the presence of values outside of a calculated or pre-set normal range for values during a given time slice), trend analysis (e.g., detecting a trend of values moving towards a range considered unacceptable), cross-value correlation (e.g., detecting a trend of values changing based on the value of another variable or an external event), etc. For these purposes, the input data may be analyzed in various ways, such as calculating a maximum or minimum value over a given time slice, calculating an average, mean, or median value over a given time slice, calculating a standard deviation over a given time slice, etc. For example, an average value within a given time slice (e.g., a week, month, quarter, year, etc.) may be compared to corresponding average values associated with past time slices to detect anomalies. In some embodiments, multiple algorithms may be combined to create new algorithms. Output data generated by the execution of these algorithms may be used to identify exceptions, escalate risks, and / or apply to further algorithms.
[0020] An exception and service unit 123 may then be executed, which may deliver to a user exceptions generated through processing of the collected fuel data through the algorithms described above. For purposes of this disclosure, an exception may refer to any data outputted through the algorithm unit 122 having a value that is outside of a predefined normal or safe range or threshold. For example, a fuel leak may cause a sudden drop in fuel tank level. An exception indicating a fuel leak may exist if the ATG detects that the level is below a predefined minimum tank level threshold. A wide range of services may be provided to the user based on the generated exceptions, including, for example, predictive maintenance of impending defective equipment, generation and distribution of regulatory reports to appropriate standards bodies, notification of authorities if product theft is detected, predictive delivery of products based on trends, vendor notification of product misdelivery (e.g., improper delivery, wrong product, etc.), automatic shutdown of fuel pump due to detected issues (e.g., leaks, mechanical pump issues, etc.), etc.
[0021] Next, a risk escalation unit 124 may be executed, which may assign risk categories to the exceptions generated through the algorithm unit 122 and the exception and service unit 123 based on various factors. The risk assignment may be used to determine whether and to what extent the exception should be escalated. Furthermore, the risk classification allows users to assign rules to specific risk categories that are specific to their needs. In some cases, when an anomaly in the input data is detected and an exception is generated in the manner described above, the machine learning based system may inspect the actions taken to address the abnormal condition, such as a fuel leak, in real time as it occurs. Thus, when an exception reoccurs, the response time may be compared to both the configured service level agreement and past solutions to determine whether the correct resources have been applied and the fuel leak has been given proper attention. Furthermore, when a new anomaly in the fuel data is detected and an exception is generated that may worsen the condition, the machine learning technique may use past solutions as training data to change the allocated resources or launch an automatic reaction to the new high or low risk. Examples of these reactions may be shutting down the device, notifying authorities, notifying more experienced personnel, etc.
[0022] Next, the workflow unit 125 may be executed, whereby a workflow including a sequence of steps to assist the user in resolving the identified operational problem may be generated in real time based on the identified exception and its assigned risk category. The workflow may provide end-to-end guidance for the user to most appropriately and efficiently resolve the operational problem, depending on the threat and severity of the problem, and taking into account the on-site equipment. For example, if the operational problem is a fuel leak, the workflow may include steps intended to correct or prevent the fuel leak from worsening. The workflow may be provided to the user in a manner determined according to the generated exception and the level of risk assigned thereto. In some embodiments, a device (e.g., a computing device such as a computer, a mobile device, a tablet device, etc.) coupled to the wet stock management server (not shown) responsible for executing elements of the analysis component 120 may display a visual characterization of the workflow via a display unit of the device, allowing the user to read and follow the displayed workflow steps.
[0023] A notification unit 126 may then be executed, which may generate notifications or alerts, each of which is used interchangeably herein, characterizing the operational problem and send them to users through various possible communication channels or mechanisms. Notifications may be generated to use specific messages and communication channels depending on the type of alert. Different users may be notified at times that may differ based on the time of day. Notifications may also be created and sent in a manner determined based on assigned risk categories, such that users are only alerted to on-site equipment issues when specific rules and / or risks are violated.
[0024] When an operational issue is resolved, e.g., a detected fuel leak is eliminated, the data reevaluation unit 127, the resolution and learning unit 128, and the tools unit 113 may be executed, thereby completing the analysis component 120 and the support component 110 for the particular exception. The assigned risk category may be phased out in response to the issue resolution, while the fuel data may still be collected and monitored to ensure that the exception no longer occurs. Additionally, the wet stock system 100 may maintain records for its continuous improvement, such as validating workflows and training models. In this regard, machine learning techniques may be applied to train rules, thresholds, and / or settings using available information (e.g., collected fuel data, generated exceptions, workflows, notifications, etc.) as input. As a result, the workflows and notifications provided through the wet stock system 100 in response to exceptions may be improved throughout the operational life of the system.
[0025] As an illustrative example, a fuel storage facility may be equipped with a tank overfill alarm that is activated when an ATG coupled to a fuel tank detects a particular stock level volume. A fuel data collection device (not shown), such as an Internet of Things (IoT) device located on-site, may collect ATG data and transmit the collected data to a remotely located wet stock management server (not shown) configured to perform the operations of the wet stock system 100. In particular, the wet stock management server may execute the aforementioned units of the analysis component 120, including a data processing unit 121 that collects the ATG data from the fuel data collection device in conjunction with fuel data measured by other on-site devices and / or manually entered data, an algorithm unit 122 that processes the collected data according to one or more predefined rules and / or models, an exception and service unit 123 that determines whether an exception exists, e.g., a fuel tank level outside a safe range, a risk escalation unit 124 that assigns a risk category to the detected exception, and a workflow unit 125 that generates a workflow that provides end-to-end support for a user to resolve the problem causing the exception.
[0026] The wet stock management server may further execute a notification unit 126 to determine notification actions contingent on user-specific and tank-specific settings. In some cases, multiple risk categories may be created, each corresponding to one or more predefined exception criteria. Each risk category may also correspond to one or more electronic communication channels through which notifications are delivered, such as an automated phone call, a short message service (SMS) message (text message), email, push notification to the wet stock management application, etc. As risk categories become more urgent, more communication channels may be selected for sending notifications. A risk category from among multiple possible risk categories may be assigned to an exception based on the exception criteria associated with each risk category. For illustrative purposes, an example set of risk categories and corresponding criteria and communication channels is shown in Table 1 below.
[0027] [Table 1]
[0028] Based on the risk category of the generated exception, a notification describing the operational problem can be generated and sent electronically via a corresponding electronic communication channel. The notification can include any available data that characterizes the nature of the problem. As the risk of the operational problem, e.g., the severity of a fuel leak, increases, the number of communication channels over which the notification is sent also increases. The date and time of the detected operational problem can determine which user or users are notified.
[0029] The notified user can then log onto the wetstock system 100 application and review the workflow generated by the wetstock management server about the exception that will guide the user to resolving the problem (e.g., fuel leak). The workflow may include recommendations such as checking specific locations, e.g., interceptors, fueling station sensors, etc., for signs of a fuel spill, contacting the appropriate authorities or response teams, etc. After the problem is resolved, the wetstock system 100 can maintain a record for learning purposes, and if future stock readings are the same high, the risk of such a problem is already known and can be addressed more efficiently.
[0030] The wet stock system 100 may implement a wet stock management computer application with a user interface that allows a user to interact with the wet stock system 100 by viewing workflows, receiving notifications (e.g., push notifications), and the like. In this regard, FIG. 2 is an exemplary user interface implemented by the wet stock system 100. The user interface 200 may include various interactive elements intended to inform the user of information that characterizes one or more aspects of the fuel storage facility provided by the wet stock system 100. For example, the user interface 200 may include a test site selection section 210, in which a user may select a test site for the fuel storage facility (e.g., Test Site 1), as well as a particular tank (e.g., Tank 1) at the selected site. The test site selection section 210 may also include selectable elements (e.g., buttons, drop-down menus, test input bars, and the like) that allow the user to quickly select a current site, receive a confidence prediction (described below), and / or reset all input data collected by the wet stock system 100.
[0031] Additionally, the user interface 200 may include a fuel data section 220 that displays information based on the collected fuel data that characterizes one or more aspects of the fuel storage facility. For example, the fuel data section 220 may include status indicators of sensors, alarms, etc. within the fuel storage facility. Additionally, the fuel data section 220 may include visual indicators of both active and inactive exceptions, as automatically determined by the wetstock system 100 based on the collected fuel data. As shown in FIG. 2, the fuel data object 221 may indicate an inactive exception, and the fuel data object 222 may indicate an active exception. Thus, the wetstock system 100 is not limited to recognizing only a single exception at a time, but may recognize multiple exceptions under certain circumstances.
[0032] In some embodiments, the wet stock system 100 can combine multiple exceptions, as indicated by the fuel data objects 221 and 222, to predict the most likely cause of the exception. 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 analysis of the wet stock system 100 described above. For example, as shown in FIG. 2, a line problem can be predicted as the most likely fault or cause of the current exception. Based on the predicted most likely fault, the wet stock system 100 can generate a workflow in the manner described above, which can be displayed to the user through the user interface 200. In some embodiments, the user can select a particular predicted cause of the exception, and a workflow can be generated based on the selected cause.
[0033] 3 is a flow chart illustrating an exemplary simplified procedure implemented by the wetstock system 100. The procedure 300 may begin at step 305 and proceed to step 310, where the wetstock system 100 may perform automated wetstock management to enable resolution of exceptions identified during operation of the fuel storage facility, as described in further detail below.
[0034] In step 305, one or more of a plurality of sensors (e.g., ATGs, fuel leak detection sensors, magnetostrictive probes, point-of-sale devices, fueling station controllers, back office systems, fuel dispensers, etc.) located at the fuel storage facility may sense fuel data for the fuel storage facility. The fuel data may include any type of measurement data that characterizes one or more aspects of the fuel storage facility, including, for example, fuel tank levels, water content, leak detection, flow readings, equipment status, etc.
[0035] In step 310, the wet stock management server communicatively coupled to the multiple sensors can collect the acquired fuel data via the data processing unit 121, process the fuel data, and detect whether the fuel data meets an exception indicating an operational problem of the fuel storage facility based on one or more predefined rules or models stored in the wet stock management server via the algorithm unit 122 and the exception and service unit 123. The wet stock management server can be a remote, i.e., cloud-based, server located outside 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, which can transmit the collected data to the wet stock management server for processing.
[0036] Upon detecting that the collected fuel data meets an exception, the procedure 300 may proceed toward one or more outputs, including generating and displaying a workflow (steps 315-325), as well as identifying a risk category and sending an alert via a selected communication channel (steps 330-340). In some embodiments, only one of the outputs may be performed. In other embodiments, both outputs or any combination thereof may be performed.
[0037] An operational problem with the fuel storage facility may be identified based on the exception in step 315. For example, if the exception results from a sudden drop in fuel tank level, the operational problem may be identified as a fuel loss or fuel leak.
[0038] In step 320, a workflow may be generated via the workflow unit 125 to assist the fuel storage facility user in resolving the operational problem identified in step 315. The workflow may include a series of steps that provide end-to-end guidance for the user to most appropriately and efficiently resolve the operational problem. The workflow may be generated dynamically, i.e., in real-time, taking into account the on-site equipment and the criticality of the problem.
[0039] At step 325, a device communicatively coupled to the wet stock management server can display a visual characterization of the workflow, such as a list of workflow steps. The device, e.g., a computer, a mobile device, a tablet, etc., can include a display unit configured to display the visual characterization of the workflow. In some embodiments, a user can interact with the device, e.g., by indicating through the device that a workflow step is completed, that additional assistance is needed, etc.
[0040] Meanwhile, in step 330, a risk category of the plurality of predefined risk categories may be assigned to the exception via the risk escalation unit 124. The identification of the risk category may be based on one or more exception criteria associated with each of the plurality of predefined risk categories. For example, as shown in Table 1, a criterion regarding the amount of fuel exceeding a predefined maximum limit may correspond to each risk category. The exception detected in step 310 may be compared to the exception criteria to assign an appropriate risk category to the exception.
[0041] In step 335, one or more of the plurality of predefined electronic communication channels may be selected for sending an alert to the user characterizing the operational problem. Referring again to Table 1, each of the predefined risk categories may correspond to a particular set of electronic communication channels. Thus, one or more electronic communication channels may be selected based on the assigned risk category.
[0042] In step 340, an alert or notification characterizing the operational problem may be sent electronically to users via notification unit 126 using one or more electronic communication channels selected in step 335. The number of users receiving the alert may depend on the urgency associated with the assigned risk category and the date and time the exception was detected. Alerts may also be created and sent such that users are only alerted to on-site equipment problems when certain rules and / or risks are violated.
[0043] Procedure 300 may continue throughout the operation of the fuel storage facility. Techniques by which the steps of procedure 300 may be implemented, as well as auxiliary procedures and exception criteria, are described in detail above.
[0044] It should be noted that the steps shown in Figure 3 are merely illustrative examples, and that certain other steps may be included or excluded as desired. Additionally, while a particular order of steps is shown, this ordering is merely exemplary, and any suitable sequence of steps may be utilized without departing from the scope of the embodiments herein. Additionally, the illustrated steps may be modified in any suitable manner in accordance with the scope of the present invention.
[0045] Thus, an automated wet stock management system as discussed herein can combine and model all known alarms and data points, site equipment, and infrastructure details to provide the user with the most likely on-site failures based on both risk, likelihood, actual probability, and on-site equipment. By applying artificial intelligence and machine learning techniques to wet stock management procedures, wet stock management can be made more efficient, thereby saving costs and improving safety.
[0046] It is to be understood that the terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural unless the context clearly dictates otherwise. It will be further understood that the terms "comprises", "includes" or variations thereof, as used herein, specify the presence of the 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" refers to a physical relationship between two components, whereby the components are directly connected to each other or indirectly connected through one or more intermediate components.
[0047] Approximating language as used herein throughout the specification and claims may be applied to modify any quantitative expression that may be permissibly varied without resulting in a change in the relevant basic function. Thus, values modified by one or more terms such as "about," "approximately," "substantially," etc. are not limited to the exact value specified. In at least some instances, the approximating language may correspond to the precision of an instrument for measuring the value. Here, and throughout the specification and claims, range limitations may be combined and / or interchanged, and such ranges are specified and include all subranges contained therein, unless otherwise indicated by context or wording.
[0048] It is further understood that the above method or one or more of its aspects may be performed by at least one control unit. The term "control unit" may 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 processes described above. The control unit may control the operation of units, modules, components, devices, etc., as described herein. It is further understood that the above method may be performed by an apparatus, such as a wet stock management server, that includes a control unit along with one or more other components, as will be understood by those skilled in the art.
[0049] The foregoing description is directed to the embodiments of the present disclosure. However, it will be apparent that other variations and modifications may be made to the described embodiments, with the attainment of some or all of their advantages. This description is therefore taken by way of example only, and is not intended to otherwise limit the scope of the embodiments herein. It is therefore the object of the appended claims to cover all such variations and modifications as come within the true spirit and scope of the embodiments herein.
[0050] [Embodiment] (1) A method for automated wet stock management, comprising: sensing fuel data characterizing one or more aspects of the fuel storage facility with one or more of a plurality of sensors disposed at the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; in response to detecting that the fuel data satisfies the exception, identifying, by the wet stock management server, the operational problem at the fuel storage facility based on the exception; 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 problems; 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 characterization of the workflow; A method comprising: (2) detecting whether the fuel data satisfies the exception, obtaining a current fuel level based on the fuel data; determining whether the current fuel level exceeds a predefined capacity of a fuel tank; 2. The method of embodiment 1, comprising: (3) The method of claim 1, wherein the visual characterization includes analysis information of the fuel data and one or more recommended actions for resolving the operational problem. (4) storing the fuel data in a storage unit by the wet stock management server; and training, by the wet stock management server, a machine learning algorithm with the fuel data and data characterizing the operational problem of the fuel storage facility, the machine learning algorithm operable to accept a given data set as an input and identify the operational problem of the fuel storage facility as an output; 2. The method of embodiment 1, further comprising: (5) The method of claim 1, wherein the fuel data includes measurements obtained by two or more of the plurality of sensors.
[0051] (6) determining, by the wet stock management server, whether the fuel data satisfies any of a plurality of predefined exceptions; and in response to determining that one or more of the plurality of predefined exceptions have been met, identifying, by the wet stock management server, the operational problem of the fuel storage facility based on the one or more predefined exceptions being met; 2. The method of embodiment 1, further comprising: (7) determining, by the wet stock management server, a plurality of potential operational problems at the fuel storage facility based on the one or more predefined exceptions being satisfied; and generating, by the wet stock management server, a probability associated with each of the plurality of potential operational problems; identifying the potential operational problem of the fuel storage facility based on the potential operational problem of the plurality of potential operational problems associated with a highest probability generated by the wet stock management server; 7. The method of embodiment 6, further comprising: (8) The method of embodiment 6, further comprising causing the wet stock management server to cause the device to display, via the display unit, a visual characterization of the one or more predefined exceptions that have been met. (9) The method of claim 8, wherein the visual characterization includes an indication of whether the one or more predefined exceptions that have been satisfied are active or inactive. (10) A system for automated wet stock management comprising: a plurality of sensors disposed at a fuel storage facility 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, processing the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; identifying the operational problem at the fuel storage facility based on the exception; generating a workflow comprising a series of steps to assist one or more users of the fuel storage facility in resolving the identified operational problem; A wet stock management server configured as follows: A device communicatively coupled to the wet stock management server, the device including a display unit; Including, The wet stock management server is configured to cause the device to display a visual characterization of the workflow via the display unit.
[0052] (11) A method for automated wet stock management, comprising: sensing fuel data characterizing one or more aspects of the fuel storage facility with one or more of a plurality of sensors disposed at the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; in response to detecting that the fuel data satisfies the exception, assigning, by the wet stock management server, a risk category among a plurality of predefined risk categories to the exception based on one or more exception criteria associated with each of the plurality of predefined risk categories; selecting, by the wet stock management server, one or more electronic communication channels of a plurality of predefined electronic communication channels based on the assigned risk category; electronically transmitting, by the wet stock management server, an alert characterizing the operational problem to one or more users via the one or more selected electronic communication channels; A method comprising: (12) The assignment of such risk categories to such exceptions is obtaining, by the wet stock management server, a current fuel level based on the fuel data; calculating, by the wet stock management server, a difference between the current fuel level and a predefined capacity of a fuel tank; assigning, by the wet stock management server, the risk category to the exception based on the calculated difference; 12. The method of embodiment 11, comprising: (13) The method of embodiment 11, wherein the plurality of predefined electronic communication channels include two or more of email, short message service (SMS), push notification via a device application, and automated telephone call. (14) Selecting the one or more electronic communication channels comprises: selecting, by the wet stock management server, a first number of the plurality of predefined electronic communication channels if 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 greater than the first number if the assigned risk category is a second category associated with a higher risk than the risk associated with the first category; 12. The method of embodiment 11, comprising: (15) The method of claim 11, further comprising selecting, by the wet stock management server, the one or more users to receive the alert characterizing the operational problem based on a current date and time.
[0053] (16) generating, by the wet stock management server, a workflow comprising a series of steps for assisting the one or more users in resolving operational issues associated with the exception; and providing, by the wet stock management server, the workflow electronically to the one or more users; 12. The method of embodiment 11, further comprising: (17) Providing the workflow electronically includes: 17. The method of claim 16, further comprising causing a device communicatively coupled to the wet stock management server to display a visual characterization of the workflow using a display unit of the device. (18) storing the fuel data in a storage unit by the wet stock management server; training, by the wet stock management server, a machine learning algorithm with the fuel data, the machine learning algorithm operable to accept a given data set as an input and assign a risk category of the plurality of predefined risk categories to the exception as an output; 12. The method of embodiment 11, further comprising: (19) determining, by the wet stock management server, whether the fuel data no longer satisfies the exception; and when the exception is no longer satisfied, electronically transmitting, by the wet stock management server, a message to the one or more users indicating that the exception is no longer satisfied; 12. The method of embodiment 11, further comprising: (20) A system for automated wet stock management comprising: a plurality of sensors disposed at a fuel storage facility 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, processing the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored at the wet stock management server; assigning a risk category of a plurality of predefined risk categories to the exception based on one or more exception criteria associated with each of the plurality of predefined risk categories; selecting one or more electronic communication channels from a plurality of predefined electronic communication channels based on the assigned risk category; electronically transmitting an alert characterizing the operational problem to one or more users via the one or more selected electronic communication channels. A wet stock management server configured as follows: Including, the system.
Claims
1. 1. A method for automated wet stock management comprising: sensing fuel data characterizing one or more aspects of the fuel storage facility with one or more of a plurality of sensors disposed at the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; in response to detecting that the fuel data satisfies the exception, identifying, by the wet stock management server, the operational problem at the fuel storage facility based on the exception; 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 problems; 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 characterization of the workflow; storing the fuel data in a storage unit by the wet stock management server; training, by the wet stock management server, a machine learning algorithm with the fuel data and data characterizing the operational problem of the fuel storage facility, the machine learning algorithm operable to accept a given data set as an input and identify the operational problem of the fuel storage facility as an output; A method comprising:
2. Detecting whether the fuel data satisfies the exception includes: obtaining a current fuel level based on the fuel data; determining whether the current fuel level exceeds a predefined capacity of a fuel tank; The method of claim 1 , comprising:
3. The method of claim 1 , wherein the visual characterization includes an analysis of the fuel data and one or more recommended actions to resolve the operational problem.
4. The method of claim 1 , wherein the fuel data includes measurements obtained by two or more of the plurality of sensors.
5. determining, by the wet stock management server, whether the fuel data satisfies any of a plurality of predefined exceptions, respectively; in response to determining that one or more of the plurality of predefined exceptions have been met, identifying, by the wet stock management server, the operational problem of the fuel storage facility based on the one or more predefined exceptions being met; The method of claim 1 further comprising:
6. determining, by the wet stock management server, a plurality of possible operational problems of the fuel storage facility based on the one or more predefined exceptions being satisfied; generating, by the wet stock management server, a probability associated with each of the plurality of potential operational problems; identifying the potential operational problem of the fuel storage facility based on the potential operational problem of the plurality of potential operational problems associated with a highest probability generated by the wet stock management server; The method of claim 5 further comprising:
7. 6. The method of claim 5, further comprising causing the wet stock management server to cause the device to display, via the display unit, a visual characterization of the one or more predefined exceptions that have been met.
8. The method of claim 7 , wherein the visual characterization includes an indication of whether the one or more predefined exceptions that have been satisfied are active or inactive.
9. 1. A system for automated wet stock management, comprising: a plurality of sensors disposed at a fuel storage facility 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, processing the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; identifying the operational problem at the fuel storage facility based on the exception; generating a workflow comprising a series of steps to assist one or more users of the fuel storage facility in resolving the identified operational problem; A wet stock management server configured as follows: A device communicatively coupled to the wet stock management server, the device including a display unit; Including, the wet stock management server causes the device to display a visual characterization of the workflow via the display unit; storing the fuel data in a storage unit; training a machine learning algorithm with the fuel data and data characterizing the operational problem of the fuel storage facility, the machine learning algorithm configured to accept a given data set as an input and to be operable to identify the operational problem of the fuel storage facility as an output; system.
10. 1. A method for automated wet stock management comprising: sensing fuel data characterizing one or more aspects of the fuel storage facility with one or more of a plurality of sensors disposed at the fuel storage facility; processing, by a wet stock management server communicatively coupled to the plurality of sensors, the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored on the wet stock management server; in response to detecting that the fuel data satisfies the exception, assigning, by the wet stock management server, a risk category among a plurality of predefined risk categories to the exception based on one or more exception 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 if 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 greater than the first number if the assigned risk category is a second category associated with a higher risk than the risk associated with the first category; and electronically transmitting, by the wet stock management server, an alert characterizing the operational problem to one or more users via the first number or the second number of multiple electronic communication channels.
11. Assigning the risk category to the exception comprises: obtaining, by the wet stock management server, a current fuel level based on the fuel data; calculating, by the wet stock management server, a difference between the current fuel level and a predefined capacity of a fuel tank; assigning, by the wet stock management server, the risk category to the exception based on the calculated difference; The method of claim 10, comprising:
12. The method of claim 10 , wherein the plurality of predefined electronic communication channels includes two or more of the following: email, short message service (SMS), push notification via a device application, and automated phone call.
13. The method of claim 10, further comprising selecting, by the wet stock management server, the one or more users to receive the alert characterizing the operational problem based on a current date and time.
14. generating, by the wet stock management server, a workflow comprising a series of steps for assisting the one or more users in resolving an operational problem associated with the exception; providing, by the wet stock management server, the workflow electronically to the one or more users; The method of claim 10 further comprising:
15. providing the workflow electronically, 15. The method of claim 14, comprising causing, by the wet stock management server, a device communicatively coupled to the wet stock management server to display a visual characterization of the workflow using a display unit of the device.
16. storing the fuel data in a storage unit by the wet stock management server; training, by the wet stock management server, a machine learning algorithm with the fuel data, the machine learning algorithm operable to accept a given data set as an input and assign a risk category of the plurality of predefined risk categories to the exception as an output; The method of claim 10 further comprising:
17. determining, by the wetstock management server, whether the fuel data no longer satisfies the exception; when the exception is no longer satisfied, electronically transmitting, by the wet stock management server, a message to the one or more users indicating that the exception is no longer satisfied; The method of claim 10 further comprising:
18. 1. A system for automated wet stock management, comprising: a plurality of sensors disposed at a fuel storage facility 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, processing the fuel data to detect whether the fuel data satisfies an exception indicative of an operational problem at the fuel storage facility based on one or more predefined rules or models stored at the wet stock management server; assigning a risk category of a plurality of predefined risk categories to the exception based on one or more exception criteria associated with each of the plurality of predefined risk categories; selecting a first number of a plurality of predefined electronic communication channels if the assigned risk category is a first category; selecting a second number of the plurality of predefined electronic communication channels, greater than the first number, if the assigned risk category is a second category associated with a higher risk than the risk associated with the first category; electronically transmitting an alert characterizing the operational problem to one or more users via the first number or the second number of multiple electronic communication channels. A wet stock management server configured as follows: Including, system.
Citation Information
Patent Citations
Plant monitoring system
JP2003150245A
Method, System and Components for Operating a Fuel Distribution System with Unmanned Self-Service Gasoline Stations
US20100023162A1
System, method and apparatus for monitoring fluid storage and dispensing systems
US20110040503A1
Fuel Dispensing Environment Component Health Monitoring
US20150346163A1
Artificial intelligence based service control and home monitoring
US20190027018A1
