Interactive alert

Abstract

The present disclosure provides a computer-implemented method of training a neural network for alarm resolution actions, a computer-implemented method, and a system. Industrial sites utilize process components or "tags" to perform, monitor, and control industrial processes. When an alarm occurs, it can be critical to quickly perform actions to optimally resolve the alarm. Providing an operator with a prioritized list of recommended actions for a particular alarm enables the user to quickly identify and take the recommended action to resolve the alarm. This recommendation can be determined by artificial intelligence, such as a trained neural network, analyzing the process components and their interrelationships associated with the alarm.

Description

Technical Field

[0001] The present invention generally relates to systems and methods for determining the root cause of alarms in complex environments, and more particularly to recommendations for interactively determining the root cause and being optimally determined to resolve the alarm. Background Technology

[0002] Complex environments, such as chemical manufacturing facilities, pharmaceutical plants, crude oil refineries, industrial kitchens, and power generation facilities, may have a large number of sensing components / sensors. These sensing components can monitor production (e.g., flow rate in pipelines, temperature or pressure in components), component operation (e.g., valve position, motor speed), and / or the surrounding environment, such as the detection of fire, smoke, leaks, vibration, etc. The sensing components / sensors are connected to the controller via a field network that supports communication between devices connected to that field network.

[0003] Alarms can indicate that the value of a specific sensor (or multiple sensors) is outside the normal operating range, but this information has limited use. The root cause of an alarm can be addressed by changing the settings of different components. For example, abnormal temperatures in a process may be caused by many other components (e.g., valves are incorrectly set or malfunctioning, there is blockage, contamination, the wrong raw material has been added, etc.). For many industrial processes, an alarm such as an abnormal temperature may be one of many alarms that could potentially provide a flood of information to the operator.

[0004] During an alarm state, processing may be suspended, resulting in unavailable output that requires complex reclamation efforts or indicates actual damage or the likelihood of damage. Knowing how to quickly resolve alarms is important for returning complex environments to normal operation and preventing escalation of problems. Summary of the Invention

[0005] Complex environments are typically used to perform one or more complex processes, such as producing chemicals or pharmaceuticals, refining crude oil, producing food, and generating electricity. Due to the large size, volume, and precision requirements of the processes they perform, complex environments can utilize hundreds or thousands of components dedicated to monitoring at least one part of the process and / or being controlled as part of at least one process. Many components are related, such as operating in parallel, serially, providing process inputs, and / or monitoring process outputs. These components are often referred to as “tags” and report current status or operational attributes. Components can be observable (e.g., reporting the temperature of a monitored portion of an industrial process) and / or controllable (e.g., valve position). Quickly determining how to resolve alarms triggered by one or more components is critical for maintaining the safe and efficient operation of complex environments.

[0006] The above and other needs are addressed through various embodiments and configurations of the present invention. The present invention can provide numerous advantages depending on the specific configuration. These and other advantages will be apparent from the disclosure of the invention contained herein.

[0007] In one embodiment, an alarm occurs and is presented in an alarm display (e.g., a device display, application window, etc.) to show the alarm and related facts associated with it, such as causal factors and / or correlation trends of one or more components. Recommended actions may be provided. Users can interact with the recommendations, such as being shown the underlying principles of the action, such as how other components (one of which is reporting an alarm) will be affected by the action. Users can query or automatically be shown historical alarms of the same or similar nature and actions taken in the past, along with their impact on other operational properties of that particular alarm and / or component. As a benefit, inexperienced operators can make informed decisions and handle alarms quickly and efficiently. Once a user performs an action, this is also saved so that it can be used for further analysis.

[0008] In another embodiment, the causal intelligence engine will read log files of events reported by the components and any associated alerts from the database. Analysis of the log files will reveal trends that can be determined to indicate whether an alert state was possible or unavoidable, and / or which previous actions successfully or unsuccessfully resolved a previous alert state.

[0009] In another embodiment, when an alarm occurs, alarm details are first collected. The causal intelligence engine then reads a time-series database (DB) to obtain details of all components or labels (the list of labels to be read will come from factory information). The alarm database is examined to obtain previously occurring alarms and other alarms that occurred during the same time period or that caused the alarm; for example, multiple alarms that occurred sequentially within a time period will be identified and analyzed. The engine then reads operator logs to see how the alarm was handled in the past. For example, if the same alarm occurred five times previously, and for each of those five alarms, the operator performed certain operator actions (e.g., changing label 1 or others) to resolve the alarm, the causal intelligence engine will analyze past operator actions. If the past operator actions (i.e., operation attributes) are the same (e.g., changing label 1 or others), then that operation attribute (i.e., changing label 1 or others) can be a "primary" operation attribute (with high importance) used to feed into training. Furthermore, changes in other parameters (e.g., label 2, label 3) (other operation attributes) caused by the change in the "primary" operation attribute (label 1) will also be used for training; these can be considered "minor" operation attributes. The engine will also obtain the results of this response from the time-series database (e.g., a decrease in label values). Based on this, the causal intelligence engine will pull out the trend of the relevant labels. The time-series database will be analyzed to understand the label trends, thus seeing how output depends on the label values. Based on the results of the time-series database analysis and past alarm responses, actions will be accurately recommended so that alarms can be handled without affecting output. Causal factors are obtained from the plant information database. Additionally, these details are learned from different systems / databases, and these details will be collected and effectively presented to the user on a single display screen. The user can then ask the engine more details or questions about the alarm. The engine will analyze the question and provide all relevant information. Based on this information, the user can make an informed decision.

[0010] For example, when an alarm occurs, the causal intelligence engine reads the values ​​of the tags associated with the alarm from the plant information database. The engine obtains the trends of the tags and displays them in the user interface; for example, tags 1, 7, 13, and 12. For tags with different values, the causal factors change in terms of value, percentage, status, etc. These values ​​are obtained from past alarms and plant information. A recommendation suggests increasing the setpoint values ​​for tags 12 and 24. This recommendation is created with the help of past data (e.g., operator logs, time-series databases, etc.) and current values.

[0011] As used herein, the term "industrial processing" refers to a process that may be one of several processes that utilize multiple, typically thousands, of components to perform and / or monitor the process. Industrial processes can be complex due to the number of steps, high precision, large amounts of input, and / or the complexity of the environment (such as the scale of the process). For example, a hydroelectric dam generates electricity with a simple process; however, generating electricity on a commercial scale requires careful coordination of many components. The components used in industrial processes are configured to report sensed states (e.g., temperature, pressure, motor speed, etc.) and / or be controllable (e.g., remotely control valves, motor speed, etc.).

[0012] In some aspects, the technology described herein relates to a computer implementation method for training a neural network for alarm solution actions, comprising: collecting a set of past operational attributes of an industrial process; applying one or more transformations to each of the past operational attributes in the set of past operational attributes of the industrial process, including: changing the degree of a first transformation among the one or more transformations; changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to omitted past operational attributes in the respective past operational attributes in the set of past operational attributes; and omitting at least one transformation among the one or more transformations applied to included past operational attributes in the respective past operational attributes to create a modified set of past operational attributes; creating a first training set, the first training set comprising the collected set of past operational attributes, the modified set of past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms; training the neural network in a first phase using the first training set; creating a second training set for a second phase of training, the second training set comprising the first training set and the set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and training the neural network in a second phase using the second training set.

[0013] In some aspects, the technology described herein relates to a computer-implemented method, further comprising: receiving an alarm associated with the industrial process, the alarm reporting an alarm status of at least one operational attribute of the industrial process; and in response to the alarm: providing a set of operational attributes of the industrial process and the alarm to the neural network to receive a recommended solution action from the neural network; presenting a marker of the recommended solution action and at least one action different from the recommended solution action on a graphical user interface (GUI); receiving a selected action, the selected action identifying one of the recommended solution action and the at least one action different from the recommended solution action; and modifying at least one processing component of the industrial process based on the selected action.

[0014] In some aspects, the technology described herein relates to a computer-implemented method in which: the recommended solution action is a plurality of priority-ordered recommended solution actions; presenting the recommendations on the GUI includes: presenting the plurality of priority-ordered recommended solution actions in priority order; receiving the selection action, the selection action identifying one of the plurality of priority-ordered recommended solution actions and at least one action different from the plurality of priority-ordered recommended solution actions; and modifying at least one processing component of the industrial process according to the selection action.

[0015] In some respects, the techniques described herein relate to a computer-implemented method in which the priority order is one or more of the following: faster alarm resolution, less waste generated by industrial processing, less risk of alarm escalation, and lower resource requirements.

[0016] In some respects, the techniques described herein relate to a computer-implemented method that further includes: monitoring the effect of the selected action on a set of operational attributes; and providing feedback to the neural network including the selected action and the effect.

[0017] In some respects, the techniques described herein relate to a computer-implemented method in which the set of operational attributes includes a set of one or more of the following parameters: readings from sensors, parameters of processing components used by the industrial process, and parameters of algorithms for operating one or more processing components used by the industrial process.

[0018] In some aspects, the technology described herein relates to a computer-implemented method comprising: collecting a set of operational attributes of an industrial process; analyzing the set of operational attributes to identify a subset of interdependent operational attributes; receiving an alarm from the industrial process; and in response to the alarm: identifying a subset of operational attributes associated with the alarm; identifying a first operational attribute in the subset of operational attributes associated with the alarm that triggered the alarm; identifying a second operational attribute interdependent with the first operational attribute; presenting a marker of the second operational attribute on a graphical user interface (GUI) and receiving modification input from the graphical user interface; and modifying the second operational attribute based on the modification input.

[0019] In some aspects, the technology described herein relates to a computer-implemented method in which: identifying a subset of operational attributes associated with the alarm includes: identifying a plurality of subsets of operational attributes associated with the alarm; identifying a first operational attribute that triggers the alarm from the subset of operational attributes associated with the alarm includes: identifying a set of first operational attributes that trigger the alarm from each subset of the plurality of operational attributes associated with the alarm; identifying a second operational attribute that is interdependent with the first operational attribute includes: identifying a second operational attribute that is interdependent with the set of the first operational attributes; and presenting a marker of the second operational attribute on a GUI and receiving modification input from the GUI includes: presenting a set of markers of the second operational attribute on the GUI and receiving modification input from the GUI.

[0020] In some respects, the techniques described herein relate to a computer implementation method, further comprising: prioritizing a set of second operation attributes to form a priority sorting list of the second operation attributes; and moving the marker of the highest priority operation attribute in the priority sorting list of the second operation attributes to the highest priority position closest to the GUI.

[0021] In some respects, the techniques described herein relate to a computer implementation method that further includes: moving, based on priority, the marker of the highest priority operation attribute in the set of second operation attributes to the highest priority position closest to the GUI.

[0022] In some respects, the techniques described herein relate to a computer implementation method in which the priority of the highest priority operational attribute is one or more of the following: faster alarm resolution, less waste generated by the industrial process, lower risk of alarm escalation, and lower resource requirements.

[0023] In some aspects, the techniques described herein relate to a computer-implemented method in which analyzing a set of operational attributes to identify subsets of interdependent operational attributes includes: collecting a set of past operational attributes of an industrial process; applying one or more transformations to each of the past operational attributes in the set of past operational attributes, including: changing the degree of a first transformation among the one or more transformations; changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to omitted past operational attributes in the set of past operational attributes; and omitting at least one transformation among one or more transformations applied to included past operational attributes in the set of past operational attributes to create a modified set of past operational attributes; creating a first training set comprising the collected set of past operational attributes, the modified set of past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms; training a neural network in a first phase using the first training set; creating a second training set for a second phase of training, the second training set comprising the first training set and a set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and training the neural network in a second phase using the second training set.

[0024] In some respects, the techniques described herein relate to a computer-implemented method in which the set of operational attributes includes a set of one or more of the following parameters: readings from sensors, parameters of processing components used by the industrial process, and parameters of algorithms for operating one or more processing components used by the industrial process.

[0025] In some aspects, the technology described herein relates to a system comprising: a database; and a processor coupled to a computer memory storing instructions for the processor to execute the instructions; and wherein the instructions cause the processor to perform: collecting a set of past operational attributes of an industrial process from the database; applying one or more transformations to each of the past operational attributes in the set of past operational attributes, including changing the degree of a first transformation in the one or more transformations, changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to omitted past operational attributes in the set of past operational attributes, and omitting the application of each past operational attribute in the set of past operational attributes. The process involves: 1) removing at least one transformation from one or more transformations of past operational attributes already included in the operational attributes to create a modified set of past operational attributes; 2) creating a first training set comprising a collected set of past operational attributes, the modified set of past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms; 3) training a neural network in a first phase using the first training set; 4) creating a second training set for a second phase of training, comprising the first training set and a set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and 5) training the neural network in a second phase using the second training set.

[0026] In some aspects, the technology described herein relates to a system further comprising: a network interface to a network; and a user device including the processor and a graphical user interface (GUI); and wherein the instructions further cause the processor to perform: receiving an alarm associated with the industrial process via the network, the alarm reporting an alarm status of at least one operational attribute of the industrial process; in response to the alarm: providing a set of operational attributes of the industrial process and the alarm to the neural network to receive a recommended solution action from the neural network; presenting a flag of the recommended solution action and at least one action different from the recommended solution action on the GUI; receiving a selected action that identifies the recommended solution action and at least one action different from the recommended solution action; and modifying at least one processing component of the industrial process based on the selected action.

[0027] In some aspects, the technology described herein relates to a system in which: the recommended solution action is a plurality of priority-ordered recommended solution actions; presenting the recommended solution actions on the GUI includes: presenting the plurality of priority-ordered recommended solution actions in priority order; receiving a selection action, the selection action identifying the recommended solution action and at least one action different from the recommended solution action, includes: receiving the selection action, the selection action identifying one of the plurality of priority-ordered recommended solution actions and at least one action different from the plurality of priority-ordered recommended solution actions; and modifying at least one processing component of the industrial process according to the selection action includes: modifying at least one processing component of the industrial process according to the selection action.

[0028] In some respects, the technology described herein relates to a system in which presenting the recommended solution actions on the GUI includes: presenting the plurality of priority-ordered recommended solution actions in the priority order, and further includes: moving the marker of the highest priority recommended solution action among the plurality of priority-ordered recommended solution actions to the highest priority position closest to the GUI.

[0029] In some respects, the technology described herein relates to a system in which the priority order is one or more of the following: faster alarm resolution, less waste generated by industrial processing, less risk of alarm escalation, and lower resource requirements.

[0030] In some respects, the technology described herein relates to a system in which the instructions further cause the processor to: monitor the effect of the selected action on a set of operational attributes; and provide feedback to the neural network including the selected action and the effect.

[0031] In some respects, the technology described herein relates to a system in which the set of operational attributes includes a set of one or more of the following parameters: readings from sensors, parameters of processing components used by the industrial process, and parameters of algorithms for operating one or more processing components used by the industrial process.

[0032] A system-on-a-chip (SoC) includes any one or more of the aspects described above or in the embodiments described herein.

[0033] One or more means for performing any one or more aspects of the embodiments described above or herein.

[0034] Any aspect in combination with any one or more other aspects.

[0035] Any one or more of the features disclosed herein.

[0036] Any one or more of the features substantially disclosed herein.

[0037] Any one or more of the features substantially disclosed herein combined with any one or more other features substantially disclosed herein.

[0038] Any one of the aspects / features / embodiments described herein, combined with any one or more other aspects / features / embodiments.

[0039] Use of any one or more of the aspects or features disclosed herein.

[0040] Any of the above aspects or aspects of the embodiments described herein, wherein the data storage device includes a non-transitory storage device, which may further include at least one of the following: on-chip memory within the processor, registers of the processor, on-board memory co-located on the processing board with the processor, processor-accessible memory via a bus, magnetic medium, optical medium, solid-state medium, input-output buffer, memory of input-output components communicating with the processor, network communication buffer, and networking components communicating with the processor via a network interface.

[0041] It should be understood that any feature described herein may be claimed in combination with any one or more other features described herein, regardless of whether those features are derived from the same described embodiments.

[0042] The phrases “at least one,” “one or more,” “or,” and “and / or” are open-ended expressions that function as both conjunctions and adversative words. For example, each of the expressions “at least one of A, B, and C,” “at least one of A, B, or C,” “one or more of A, B, and C,” “one or more of A, B, or C,” “A, B, and / or C,” and “A, B, or C” indicates: A alone, B alone, C alone, A and B together, A and C together, B and C together, or A, B, and C together.

[0043] The term "a" or "an" entity refers to one or more of the same entity. Therefore, the terms "a" (or "an"), "one or more," and "at least one" are used interchangeably herein. It should also be noted that the terms "comprising," "including," and "having" are used interchangeably.

[0044] As used herein, the term "automatic" and its variations refer to any process or operation that is typically sequential or semi-sequential and is performed without substantial human input. However, a process or operation can be automatic even if its execution uses substantial or non-substantial human input, provided that input is received before its execution. Human input is considered substantial if it influences how the process or operation will be performed. Human input that enables the execution of a process or operation is not considered "substantial."

[0045] The aspects of this disclosure may take the form of an embodiment that is entirely hardware, an embodiment that is entirely software (including firmware, resident software, microcode, etc.), or an embodiment that combines software and hardware aspects, all of which may be collectively referred to herein as a "circuit," "module," or "system." Any combination of one or more computer-readable media may be used. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium.

[0046] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any suitable combination thereof. More specific examples (not an exhaustive list) of computer-readable storage media will include the following: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the context of this document, a computer-readable storage medium can be any tangible, non-transitory medium that can contain or store a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0047] Computer-readable signal media may include, for example, propagated data signals in baseband or as part of a carrier wave, wherein the propagated data signals have computer-readable program code embodied therein. Such propagated signals may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. Computer-readable signal media may be any computer-readable medium that is not a computer-readable storage medium and may transmit, propagate, or transfer a program used by or in conjunction with an instruction execution system, apparatus, or device. Any suitable medium may be used to transmit program code embodied on a computer-readable medium, including, but not limited to, wireless, wired, fiber optic cable, RF, etc., or any suitable combination thereof.

[0048] As used herein, the terms “determine,” “calculate,” “operate,” and their variations are used interchangeably and include any type of method, process, mathematical operation, or technique.

[0049] The term "means" as used herein should be given its broadest possible interpretation. Therefore, claims containing the term "means" should cover all structures, materials, or actions described herein and all their equivalents. Furthermore, the structures, materials, or actions described herein and their equivalents should include all those described in the summary, description of drawings, detailed description, abstract, and claims themselves.

[0050] The foregoing is a simplified summary of the invention to provide an understanding of some aspects of the invention. This summary is neither a broad nor an exhaustive overview of the invention and its various embodiments. It is not intended to identify key or essential elements of the invention, nor to describe the scope of the invention, but rather to present selected inventive concepts in a simplified form as an introduction to the specific embodiments presented below. As will be understood, other embodiments of the invention are possible by utilizing one or more of the features set forth above or described in detail below, alone or in combination. Furthermore, while this disclosure is presented according to exemplary embodiments, it should be understood that various aspects of this disclosure can be claimed individually. Attached Figure Description

[0051] This disclosure is described in conjunction with the following figures: Figure 1 A system according to embodiments of the present disclosure is described; Figure 2 A system with alarm display according to an embodiment of the present disclosure is described; Figure 3 Processing according to embodiments of the present disclosure is described; and Figure 4 An apparatus for a system according to an embodiment of the present disclosure is described. Detailed Implementation

[0052] The following description provides only examples and is not intended to limit the scope, applicability, or configuration of the claims. Rather, it provides a description, enabling of those skilled in the art, for implementing the embodiments. It should be understood that various changes may be made to the function and arrangement of the elements without departing from the spirit and scope of the appended claims.

[0053] When sub-reference numerals are present in the accompanying drawings but no letter sub-reference numerals are used in the plural, any reference numerals included in the specification refer to any two or more elements having the same reference numeral. When such a reference numeral is in the singular form but does not identify a sub-reference numeral, it refers to one of the elements with the same number, and not to a limitation on a particular element among those referenced. Any explicit use to the contrary or provision of further identification or recognition herein shall prevail.

[0054] Exemplary systems and methods of this disclosure will also be described with respect to analysis software, modules, and associated analysis hardware. However, to avoid unnecessarily obscuring this disclosure, well-known structures, components, and devices are omitted in the following description, or may be shown in simplified form or otherwise summarized from the accompanying drawings.

[0055] For purposes of explanation, numerous details have been set forth in order to provide a thorough understanding of this disclosure. However, it should be understood that this disclosure may be practiced in various ways beyond the specific details set forth herein.

[0056] Figure 1 System 100 according to an embodiment of the present disclosure is illustrated. In one embodiment, system 100 illustrates components including, for example, processing component 102 interconnected via a network, computing components 106, 108, and 110, and data storage components (e.g., data storage device 108). It should be understood that in one embodiment, each of the illustrated components provides a single service. However, those skilled in the art will recognize that other topologies can be deployed without departing from the scope of the embodiments herein. For example, server 106 may be combined with data storage device 108, computer 110, and / or other computing or data storage components. In another embodiment, any computing component may be implemented as multiple computing components. In one embodiment, the illustrated component performs a single function; in other embodiments, one or more computing components may perform multiple functions, and / or one or more functions may be performed by multiple computing components including those as services (e.g., Software as a Service (SaaS)). In yet another embodiment, the connectivity topology may be the topology shown in system 100, or another topology without departing from the scope of the embodiments.

[0057] In one embodiment, the industrial site 104 includes multiple processing components 102. Each processing component 102 reports sensed information to a server 106, receives operational commands from the server 106, or both. Any two or more components 102 may be the same type of device or different types of devices.

[0058] The sensed information describes the operational attributes of the processes performed by industrial site 104. Operational attributes can be reported individually by server 106 or further processed into groups, trends, anomalies, alarms, etc. Operational attributes can be the current or desired state of one or more processing components 102 (e.g., an oven heated to a desired setpoint, fan speed settings, etc.). Processing components 102 perform and / or monitor one or more industrial processes at industrial site 104. In a further embodiment, at least one processing component 102 can monitor environmental conditions affecting the industrial processes (e.g., ambient temperature, load on the power grid, water level in a storage tank, etc.).

[0059] Computer 110 includes a display and can present information to a user (e.g., an operator at industrial site 104). Similarly, data storage device 108 can maintain logs of various operational attributes (e.g., events, states, etc.) and / or logs of processed operational attributes, such as grouping of various operational attributes, trends over time, settings, states, overrides, anomalies, alarms, etc.

[0060] In another embodiment, server 106 may perform artificial intelligence (AI), such as a neural network. The neural network is trained to identify alarms and their solutions. Recommendations provided by the neural network, such as those presented on computer 110 for a user to select or override, are used to resolve a current alarm triggered by at least one processing component 102. Additionally or alternatively, server 106 may automate alarm resolution actions, including changing operational attributes of one or more processing components 102.

[0061] Figure 2 A system 200 with an alarm display 202 according to an embodiment of the present disclosure is depicted. In one embodiment, the alarm display 202 is presented on a computer 110, which receives analysis (see reference) from a server 106. Figure 3 (To be described in more detail). As described above, computer 110 is implemented in various ways. In one embodiment, computer 110 is a standalone desktop or portable computer running an application that presents alarm display 202. In another embodiment, computer 110 may be implemented in conjunction with server 106. In yet another embodiment, computer 110 may be implemented in conjunction with one or more processing components 102, such as a control panel. Computer 110 may be located at an industrial site 104 or remotely located and communicate via networks such as the Internet, satellite links, cellular or wired telephone networks.

[0062] Alarm display 202 can be presented continuously, for example, indicating no alarms or "popping up" only when an alarm condition occurs. The content of the alarm display may include alarm condition 204 to indicate a problem, such as one or more processing components 102 operating or observing a state in the industrial process outside the normal range of operating parameter values. In one embodiment, alarm condition 204 is a clear description of a malfunction or undesirable condition in the industrial process (e.g., "tank overpressure"). Causal factor 206 provides details such as which processing component(s) 102 is associated with the alarm and its observed values ​​(e.g., "Label 37 - 13.9 bar", "Label 53 - 133% of normal value", etc.), and / or changes over time (e.g., "Label 21 - increased from 8.5 kV to 13.1 kV in the last 30 minutes"). Causal factor 206 can be retrieved from a database, such as one maintained by data storage device 108, indicating how values ​​reported from a particular processing component 102 would trigger a particular alarm. For example, an alarm can be indexed or otherwise identified such that when an "alarm X" occurs, computer 110 and / or server 106 retrieves a record from data storage device 108 that identifies a specific processing component 102 associated with the alarm and obtains values ​​from those specific processing components 102 for reporting.

[0063] In another embodiment, the alarm display 202 presents one or more recommended actions 210. Optionally, one or more recommended actions 210 may be presented (automatically or in response to receiving user input) along with corresponding recommendation details 212. Each recommended action 210 may provide a label of the recommended solution (e.g., “stop motor X”, “open valve Y”, “increase pump speed”) and / or more descriptive terms (e.g., “open the circuit breaker of motor X”, “open valve Y to 20%”, “increase pump speed to 30% of full speed”), and / or may be provided with descriptive details by recommendation details 212. Recommendations may be provided by an AI agent running on computer 110 or server 106 (see...). Figure 3(To be described in more detail) can be provided. The recommended actions 210 can be further prioritized such that recommended action 1 (210A) is moved to the position closest to the highest priority 208, which is closer to the next highest priority recommendation (i.e., recommended action 2 (210B)), and so on, up to recommended action n (210n). The content presented by the recommended actions 210 and the corresponding recommendation details 212 is embodied in various ways. In one embodiment, recommended action 210 describes a specific action (e.g., “turn off label 9”), which can be further described (automatically in response to user input) by the corresponding recommendation details 212 (e.g., “label 9 controls the supply of supplemental heat to tank 3”). As a further option, user-specified action 214 receives user input different from any of the presented recommended actions 210. User-specified action 214 can differ in time from one or more recommended actions 210 (e.g., “silent alarm for 30 minutes”), or initiate another action not provided by one or more recommended actions 210. In another embodiment, user-specified action 214 receives user input associated with recommended action 210. For example, user-specified action 214 could be "Please tell me why I gave recommended action 1 (210A)". After user-specified action 214, alarm display 202 can provide the reason for giving recommended action 1 (210A).

[0064] The content presented on the alarm display 202 can utilize various graphical user interface (GUI) elements. For example, a portion of the alarm display 202 presenting recommended actions 210A to 210n can be scrollable, have pages, etc. Similarly, the corresponding recommended details 212A-212n can be scrollable (e.g., left or right), pop up, display content in another window, etc. However, a top-priority recommended action (e.g., recommended action 1 (210A)) closest to the designated top-priority location 208 is provided to ensure that the optimal action can be quickly presented to the user, and optionally, the user can take this optimal action to resolve the alarm. The specific location of the top-priority location 208 is specified differently. For example, when presented as text, the location of the top-priority location 208 can be determined based on the operator's preferred written language; for example, when the operator's written language is read from left to right and then from top to bottom, the top-priority location 208 is placed in the upper left corner of the display, window, dialog box, etc. Similarly, when the operator's preferred written language is read from right to left and then from top to bottom, the top-priority location 208 can be located in the upper right corner of the display, window, dialog box, etc. In another embodiment, the alarm display 202 can be overlaid on a graphical representation of the industrial site 104 or one or more processing components 102. As a result, the top-priority location 208 can be the location closest to the image of a specific portion of the industrial site 104 or one or more processing components 102 associated with the alarm.

[0065] Recommended action 1 (210A) can be recommended because performing this action can affect the operational properties of the industrial process, thereby resolving the alarm most quickly. However, speed may not always be the primary objective in resolving an alarm. In other embodiments, recommended action 1 (210A) may be selected based on generating fewer scrap items, reducing the risk of alarm escalation, or resource costs. Similarly, the selection of any subsequent recommended actions 2 (210B) through n (210n) may be based on the speed of resolution and / or scrap, the risk of escalation, resource costs, etc.

[0066] In another embodiment, when the user selects user-specified action 214, alert display 202 can provide a list of options for processing components 102 to receive specific input for changing processing attributes of one or more processing components 102. Server 106 then signals the corresponding processing component 102 to implement the user's input. In a further embodiment, server 106 may utilize the input as feedback to the decision AI processing. As a result, any future identical or similar alerts will "decrease" the weight of the previously recommended action 210 and "increase" the weight of the recommended action associated with the user's input. In another embodiment, alerts, statuses, and user actions selected in user-specified action 214 of one or more processing components 102 are provided to AI processing for initial or subsequent training.

[0067] Figure 3 A process 300 according to embodiments of the present disclosure is described. In one embodiment, process 300 is a computer implementation method for training a neural network. As is known in the art, in one embodiment, the neural network self-configures individual layers of logical nodes having inputs and outputs. If the output is below a self-determined threshold level, the output is omitted (i.e., the input is within the inactive response portion of the scale, and no output is provided). If the self-determined threshold level is above the threshold, the output is provided (i.e., the input is within the active response portion of the scale, and an output is provided). A specific arrangement of active and inactive delineation is provided as one or more training steps. Multiple inputs entering a node generate a multidimensional plane (e.g., a hyperplane) to delineate combinations of active or inactive inputs. In another embodiment, process 300 includes a machine learning module. The machine learning module may use various machine learning algorithms, such as supervised machine learning, unsupervised machine learning, reinforcement machine learning, semi-supervised machine learning, self-supervised machine learning, multi-instance machine learning, inductive machine learning, deductive machine learning, and / or transductive machine learning, etc.

[0068] In one embodiment, process 300 begins, and in step 302, a set of past operational attributes of the industrial process is collected. Step 302 may collect past operational attributes from a database (e.g., a database maintained by data storage device 108) and / or other sources. Past operational attributes may include individual values ​​observed or reported by one or more processing components 102 during past executions of the industrial process. Next, step 304 applies one or more transformations to each past operational attribute, including: changing the degree of a first transformation among the one or more transformations, changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to an omitted past operational attribute, and omitting at least one transformation among one or more transformations applied to a included past operational attribute, thereby creating a modified set of past operational attributes. A past operational attribute contained in a past operational attribute is part of a set of past operational attributes. By applying one or more transformations to a past operational attribute contained in a past operational attribute, an "extended training set" can be obtained. This extended training set can substantially improve the training (accuracy) of the set of past operational attributes and address different scenarios in industrial processes and / or plants (e.g., process changes, plant changes, operator conditions, etc.).

[0069] Then, step 306 creates a first training set, which includes a collection of past operational attributes, a set of modifications to past operational attributes, and a set of extraneous operational attributes in the industrial process that are unrelated to previous alerts.

[0070] Step 308 trains the neural network in the first stage using the first training set, and then step 310 creates a second training set for the second stage of training. This second training set includes the first training set and a set of irrelevant operational attributes in the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms. In step 312, the neural network is trained in the second stage using the second training set. The set of irrelevant operational attributes may include operational attributes unrelated to alarms; specifically, the engine determines all operational attributes of the industrial process and identifies operational attributes that have changed due to alarms. The unchanged operational attributes of the industrial process will then be the set of irrelevant operational attributes.

[0071] Once trained, current operational attributes and / or alarms reported by one or more processing components 102 can be presented to the neural network, and the neural network returns one or more recommended actions, such as recommended action 210, to resolve the alarm. Additionally or alternatively, user-specified use of action 214 (and rejection of recommended action 210) can be provided to the neural network for training, retraining, or refining the recommended actions. As a benefit, the neural network is able to analyze operational attributes, such as discovering previously unknown interdependencies between two or more processing components 102 associated with an alarm. Once known, the alarm can be resolved by affecting the operational attributes of at least one of the two or more processing components.

[0072] Figure 4Device 402 in a system 400 according to an embodiment of the present disclosure is depicted. In one embodiment, server 106, computer 110, and / or one or more processing components 102 may be implemented, in whole or in part, as device 402 including various components and connections to other components and / or systems. Components are implemented in various ways and may include processor 404. As used herein, the term “processor” exclusively refers to an electronic hardware component including circuitry having connections (e.g., pin outputs) to and from the circuitry to transmit encoded electrical signals. Processor 404 may include programmable logic functions, such as programmable logic functions determined at least in part by accessing machine-readable instructions held in a non-transitory data storage device, which may be implemented as circuitry, on-chip read-only memory, computer memory 406, data storage device 408, etc., causing processor 404 to execute the steps of the instructions. Processor 404 may also be implemented as a single electronic microprocessor or multiprocessor device (e.g., multi-core) having circuitry, which may further include one or more control units, one or more input / output units, one or more arithmetic logic units, one or more registers, main memory, and / or other components that access information (e.g., data, instructions, etc.) received via bus 414, which executes instructions and, again, outputs data via bus 414. In other embodiments, processor 404 may include a shared processing device that may be utilized by other processing and / or processing owners in a processing array, such as within a system (e.g., blade, multiprocessor board, etc.) or a distributed processing system (e.g., a “cloud,” a field, etc.). It should be understood that processor 404 is a non-transitory computing device (e.g., an electronic machine including circuitry and connections for communication with other components and devices). Processor 404 may operate a virtual processor to, for example, process machine instructions that are not native to the processor (e.g., translating the VAX operating system and VAX machine instruction code set into Intel® 9xx chipset code so that VAX-specific applications can execute on a virtual VAX processor). However, as those skilled in the art will understand, such a virtual processor is an application executed by hardware, more specifically, by the underlying circuitry of the processor (e.g., processor 404) and other hardware. Processor 404 can be executed by a virtual processor, for example, when an application (i.e., a Pod) is orchestrated by Kubernetes. Virtual processors enable applications to appear as static and / or dedicated processors executing application instructions, while the underlying non-virtual processor is executing the instructions and can be dynamic and / or split across multiple processors.

[0073] In addition to the components of processor 404, device 402 may also utilize computer memory 406 and / or data storage device 408 to store accessible data, such as instructions, values, etc. Communication interface 410 facilitates communication with components, such as communicating with processor 404 via bus 414, and with components inaccessible via bus 414, and may be implemented as a network interface (e.g., Ethernet card, wireless network component, USB port, etc.). Communication interface 410 may be implemented as a network port, card, cable, or other configured hardware device. Additionally or alternatively, human input / output interface 412 connects to one or more interface components to present information (e.g., instructions, data, values, etc.) to and / or receive information (e.g., instructions, data, values, etc.) from humans and / or electronic devices. Examples of input / output devices 430 that can be connected to the input / output interface include, but are not limited to, keyboards, mice, trackballs, printers, displays, sensors, switches, repeaters, speakers, microphones, still and / or video cameras, etc. In another embodiment, the communication interface 410 may include or consist of a human input / output interface 412. The communication interface 410 may be configured to communicate directly with networking components or to utilize one or more networks, such as network 420 and / or network 424.

[0074] Network 420 may be a wired network (e.g., Ethernet), a wireless network (e.g., WiFi, Bluetooth, cellular, etc.), or a combination thereof, and enables device 402 to communicate with one or more networking components 422. In other embodiments, network 420 may be implemented wholly or partially as a telephone network (e.g., a public switched telephone network (PSTN), a private switched extension (PBX), a cellular telephone network, etc.).

[0075] Additionally or alternatively, one or more other networks may be utilized. For example, network 424 may represent a second network that facilitates communication with the components used by device 402. For example, network 424 may be an internal network of a business entity or other organization, whereby the components are more trusted (or at least more trusted) than networked component 422, which may connect to network 420, including potentially less trusted public networks (e.g., the Internet).

[0076] Components attached to network 424 may include computer memory 426, data storage device 428, one or more input / output devices 430, and / or other components accessible to processor 404. For example, computer memory 426 and / or data storage device 428 may completely supplement or replace computer memory 406 and / or data storage device 408, or supplement or replace it for a specific task or purpose. As another example, computer memory 426 and / or data storage device 428 may be an external data repository (e.g., a server farm, array, "cloud," etc.) and enable device 402 and / or other devices to access the data thereon. Similarly, processor 404 may access one or more input / output devices 430 directly, via network 424, via network 420 (not shown), or via network 424 and network 420, through human input / output interface 412 and / or via communication interface 410. Each of computer memory 406, data storage device 408, computer memory 426, and data storage device 428 includes a non-transitory data storage device.

[0077] It should be understood that computer-readable data can be sent, received, stored, processed, and presented by various components. It should also be understood that the components shown can control other components, whether shown herein or others. For example, an input / output device 430 may be a router, switch, port, or other communication component, such that a specific output of processor 404 enables (or disables) the input / output device 430 that may be associated with network 420 and / or network 424 to allow (or disallow) communication between two or more nodes on network 420 and / or network 424. Those skilled in the art will understand that other communication devices may be utilized, in addition to those described herein or as alternatives, without departing from the scope of the embodiments.

[0078] In the above description, the methods are described in a specific order for illustrative purposes. It should be understood that in alternative embodiments, these methods may be performed in a different order than described without departing from the scope of the embodiments. It should also be understood that the methods described above can be executed as an algorithm by a hardware component (e.g., circuitry) specifically built to perform one or more algorithms or portions thereof described herein. In another embodiment, the hardware component may include a general-purpose microprocessor (e.g., CPU, GPU) that is first converted into a dedicated microprocessor. The dedicated microprocessor then has coded signals loaded therein that enable the dedicated microprocessor to retain machine-readable instructions such that the microprocessor can read and execute a set of machine-readable instructions derived from the algorithms and / or other instructions described herein. The machine-readable instructions or portions thereof used to execute the algorithm are not unlimited but utilize a finite set of instructions known to the microprocessor. In one or more embodiments, machine-readable instructions may be encoded in the microprocessor as signals or values ​​in signal generation components through voltage in memory circuitry, configuration of switching circuitry, and / or by selective use of specific logic gates. Additionally or alternatively, machine-readable instructions may be microprocessor-accessible and encoded in a medium or device as magnetic fields, voltage values, charge values, reflective / non-reflective portions, and / or physical markings.

[0079] In another embodiment, the microprocessor also includes one or more of a single microprocessor, a multi-core processor, multiple microprocessors, a distributed processing system (e.g., an array, blade, server farm, "cloud," multi-purpose processor array, cluster, etc.), and / or may be located in the same location as a microprocessor performing other processing operations. Any one or more microprocessors may be integrated into a single processing device (e.g., a computer, server, blade, etc.), or may be wholly or partially located in discrete components and connected via communication links (e.g., a bus, network, backplane, etc., or more thereof).

[0080] Examples of general-purpose microprocessors may include a central processing unit (CPU) having data values ​​encoded in an instruction register (or other circuitry that maintains instructions) or data values ​​including storage locations that further include values ​​used as instructions. Storage locations may also include external storage locations to the CPU. Such external CPU components may be implemented as one or more of a field-programmable gate array (FPGA), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), random access memory (RAM), bus-accessible storage, network-accessible storage, etc.

[0081] These machine-executable instructions can be stored on one or more machine-readable media, such as CD-ROMs or other types of optical discs, floppy disks, ROMs, RAMs, EPROMs, EEPROMs, magnetic cards or optical cards, flash memory, or other types of machine-readable media suitable for storing electronic instructions. Alternatively, the method can be executed by a combination of hardware and software.

[0082] In another embodiment, the microprocessor may be a system or collection of processing hardware components, such as microprocessors on client devices and servers, a collection of devices having their respective microprocessors, or a shared processing service or remote processing service (e.g., a "cloud-based" microprocessor). A system of microprocessors may include task-specific allocation of processing tasks and / or shared processing tasks or distributed processing tasks. In yet another embodiment, the microprocessor may execute software to provide services to emulate a different microprocessor or multiple microprocessors. As a result, a first microprocessor, composed of a first set of hardware components, can virtually provide the services of a second microprocessor, whereby hardware associated with the first microprocessor can operate using the instruction set associated with the second microprocessor.

[0083] While machine-executable instructions may be stored and executed locally on a particular machine (e.g., a personal computer, a mobile computing device, a laptop computer, etc.), it should be understood that the storage of data and / or instructions and / or the execution of at least a portion of the instructions may be provided via a connection to a remote data storage and / or processing device or collection of devices (often referred to as the “cloud”), which may include public, private, dedicated, shared and / or other service providers, computing services and / or “server farms”.

[0084] Examples of microprocessors described herein may include, but are not limited to, at least one of the following: Qualcomm® Snapdragon® 800 and 801, Qualcomm® Snapdragon® 610 and 615 with 4G LTE integration and 64-bit computing, Apple® A7 microprocessor with 64-bit architecture, Apple® M7 motion microprocessor, Samsung® Exynos® series, Intel® Core™ series microprocessors, Intel® Xeon® series microprocessors, Intel® Atom™ series microprocessors, Intel (Intel) Itanium® series microprocessors, Intel® Core® i5-4670K and i7-4770K 22nm Haswell, Intel® Core® i5-3570K 22nm Ivy Bridge, AMD® FX™ series microprocessors, AMD® FX-4300, FX-6300 and FX-8350 32nm Vishera, AMD® Kaveri microprocessor, Texas Instruments® Jacinto The C6000™ automotive infotainment microprocessor, Texas Instruments® OMAP™ automotive-grade mobile microprocessor, ARM® Cortex™-M microprocessor, ARM® Cortex-A and ARM926EJ-S™ microprocessor, and other industry-equivalent microprocessors can perform computing functions using any known or future-developed standards, instruction sets, libraries, and / or architectures.

[0085] Any of the steps, functions, and operations discussed in this article can be performed continuously and automatically.

[0086] Exemplary systems and methods of the present invention have been described in conjunction with communication systems and components and methods for monitoring, enhancing, and modifying communications and messages. However, to avoid unnecessarily obscuring the invention, many known structures and devices have been omitted from the foregoing description. Such omissions should not be construed as limiting the scope of the claimed invention. Specific details have been set forth to provide an understanding of the invention. However, it should be understood that the invention can be practiced in various ways beyond the specific details set forth herein.

[0087] Furthermore, while the exemplary embodiments illustrated herein show various components of the system assembled together, some components of the system may be located remotely, in a distant part of a distributed network such as a LAN and / or the Internet, or within a dedicated system. Therefore, it should be understood that components of the system, or portions thereof (e.g., microprocessors, memory / storage devices, interfaces, etc.), may be combined into one or more devices, such as a server, multiple servers, a computer, a computing device, a terminal, a “cloud”, or other distributed processing, or configured on specific nodes of a distributed network such as analog and / or digital telecommunications networks, packet-switched networks, or circuit-switched networks. In another embodiment, components may be physically or logically distributed across multiple components (e.g., a microprocessor may include a first microprocessor on one component and a second microprocessor on another component, each of the first and second microprocessors performing a shared task and / or a portion of an assigned task). As can be understood from the foregoing description, for computational efficiency reasons, components of the system may be arranged anywhere within a distributed network of components without affecting the operation of the system. For example, various components may be located in switches or gateways such as PBXs and media servers, in one or more communication devices, in one or more users' premises, or some combination thereof. Similarly, one or more functional parts of the system may be distributed among one or more telecommunications devices and associated computing devices.

[0088] Furthermore, it should be understood that the various links connecting the elements can be wired links or wireless links, or any combination thereof, or any other known or later-developed element capable of providing data to and / or transmitting data from the connected elements. These wired or wireless links can also be secure links and capable of transmitting encrypted information. The transmission medium used as the link can be, for example, any suitable carrier for electrical signals, including coaxial cables, copper wires, and optical fibers, and can take the form of sound waves or light waves, such as those generated during radio wave and infrared data communication.

[0089] Furthermore, although flowcharts have been discussed and illustrated with respect to specific event sequences, it should be understood that changes, additions, and omissions to the sequence can occur without substantially affecting the operation of the invention.

[0090] Many variations and modifications of the invention can be used. Some features of the invention may be provided without others.

[0091] In another embodiment, the systems and methods of the present invention may be implemented in combination with a dedicated computer, a programmable microprocessor or microcontroller and peripheral integrated circuit elements, an ASIC or other integrated circuit, a digital signal microprocessor, hardwired electronic or logic circuitry (e.g., discrete component circuitry), a programmable logic device or gate array (e.g., PLD, PLA, FPGA, PAL), a dedicated computer, any similar device, etc. Generally, any device or apparatus capable of implementing the methods described herein can be used to implement various aspects of the present invention. Exemplary hardware that can be used with the present invention includes computers, handheld devices, telephones (e.g., cellular, internet-enabled, digital, analog, hybrid, etc. telephones), and other hardware known in the art. Some of these devices include microprocessors (e.g., single or multiple microprocessors), memory, non-volatile storage devices, input devices, and output devices. Furthermore, alternative software implementations, including but not limited to distributed processing or component / object distributed processing, parallel processing, or virtual machine processing, may also be constructed to implement the methods described herein as provided by one or more processing components.

[0092] In another embodiment, the disclosed method can be readily implemented using object-oriented software or an object-oriented software development environment that provides portable source code usable on various computer or workstation platforms. Alternatively, the disclosed system can be implemented, partially or entirely, in hardware using standard logic circuitry or VLSI designs. Whether to implement the system according to the invention using software or hardware depends on the system's speed and / or efficiency requirements, specific functions, and the specific software or hardware system or microprocessor or microcomputer system used.

[0093] In yet another embodiment, the disclosed method can be implemented in part in software, which can be stored on a storage medium and executed on a programmed general-purpose computer, special-purpose computer, microprocessor, etc., in cooperation with a controller and memory. In these cases, the system and method of the present invention can be implemented as a program embedded in a personal computer, such as an applet, JAVA®, or CGI script; as a resource residing on a server or computer workstation; or as routines embedded in a dedicated measurement system, system component, etc. The system can also be implemented by physically incorporating the system and / or method into a software and / or hardware system.

[0094] The software embodiments described herein are executed or stored by one or more microprocessors for subsequent execution and are executed as executable code. This executable code is selected to execute instructions including those of a particular embodiment. The instructions to be executed are a constrained set of instructions selected from a discrete set of native instructions understood by the microprocessor and are committed to microprocessor-accessible memory prior to execution. In another embodiment, the human-readable "source code" software is first converted into system software to include a platform-specific instruction set (e.g., computer, microprocessor, database, etc.) selected from the platform's native instruction set.

[0095] Although this invention describes the components and functions implemented in embodiments with reference to specific standards and protocols, the invention is not limited to these standards and protocols. Other similar standards and protocols not mentioned herein exist and are considered to be included in this invention. Furthermore, the standards and protocols mentioned herein, as well as other similar standards and protocols not mentioned herein, are periodically replaced by faster or more efficient equivalents having substantially the same functionality. These replacement standards and protocols having the same functionality are considered to be equivalents included in this invention.

[0096] In various embodiments, configurations, and aspects, the present invention includes components, methods, processes, systems, and / or apparatuses substantially as depicted and described herein, including various embodiments, sub-combinations, and subsets thereof. Those skilled in the art will understand how to make and use the invention upon understanding this disclosure. In various embodiments, configurations, and aspects, the present invention includes providing devices and processes in the absence of items not depicted and / or described herein or in its various embodiments, configurations, or aspects, including providing devices and processes in the absence of items that may have already been used in prior devices or processes, for example, for improving performance, ease of implementation, and / or reducing implementation costs.

[0097] The foregoing discussion of the invention is provided for illustrative and descriptive purposes. The foregoing is not intended to limit the invention to the one or more forms disclosed herein. For example, in the foregoing detailed description, various features of the invention have been grouped together in one or more embodiments, configurations, or aspects to facilitate a smooth disclosure. Features of embodiments, configurations, or aspects of the invention may be combined in alternative embodiments, configurations, or aspects other than those discussed above. This method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the appended claims, the inventive aspect lies in having fewer features than all of the features of a single foregoing disclosed embodiment, configuration, or aspect. Accordingly, the following claims are thus incorporated into this Detailed Description section, wherein each claim is independently a separate preferred embodiment of the invention.

[0098] Furthermore, although the description of the invention has included descriptions of one or more embodiments, configurations, or aspects, as well as certain variations and modifications, other variations, combinations, and modifications are within the scope of the invention upon understanding this disclosure, for example, as may be possible within the skill and knowledge of those skilled in the art. Rights are sought that include alternative embodiments, configurations, or aspects within the permissible scope, including claimed alternatives, interchangeable, and / or equivalent structures, functions, scopes, or steps, whether or not such alternatives, interchangeable, and / or equivalent structures, functions, scopes, or steps are disclosed herein, and no patentable subject matter is intended to be publicly contributed.

Claims

1. A computer implementation method for training a neural network for alarm solution actions, comprising: Collect a set of past operational attributes of industrial processes; Applying one or more transformations to each of the past operating attributes in the set of past operating attributes of the industrial process includes: changing the degree of a first transformation in the one or more transformations, changing the order of one or more transformations applied to two or more past operating attributes, including applying a second transformation to an omitted past operating attribute in the set of past operating attributes, and omitting at least one transformation in one or more transformations applied to included past operating attributes in the respective past operating attributes, to create a modified set of past operating attributes. Create a first training set, which includes a set of collected past operational attributes, a set of modifications to the past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms. The neural network is trained in the first phase using the first training set; A second training set is created for the second phase of training. The second training set includes the first training set and a set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and The neural network is trained in the second phase using the second training set.

2. The computer implementation method according to claim 1 further includes: Receive an alarm associated with the industrial process, the alarm reporting the alarm status of at least one operational attribute of the industrial process; as well as In response to the aforementioned alert: The set of operational attributes of the industrial process and the alarm are provided to the neural network to receive recommended solution actions from the neural network; The graphical user interface displays a marker for the recommended solution action and at least one action that differs from the recommended solution action. Receive a selection action, the selection action identifying one of the recommended solution action and at least one action that is different from the recommended solution action; as well as Based on the selected action, at least one processing component of the industrial process is modified.

3. The computer implementation method according to claim 2, wherein: The recommended solution action consists of multiple recommended solution actions ordered by priority; Presenting recommendations on the graphical user interface includes: presenting the multiple priority-sorted recommended solutions in order of priority. Receive the selection action, the selection action identifying one of the plurality of priority-ordered recommended solution actions and at least one action different from the plurality of priority-ordered recommended solution actions; and Based on the selected action, at least one processing component of the industrial process is modified.

4. The computer implementation method according to claim 3, wherein, The priority order is one or more of the following: faster alarm resolution, less waste generated by the industrial process, less risk of alarm escalation, and lower resource requirements.

5. The computer implementation method according to claim 3 further includes: Monitor the impact of the selected action on the set of operation attributes; as well as Feedback, including the selected action and the effect, is provided to the neural network.

6. The computer implementation method according to claim 1, wherein, The set of past operating attributes includes a set of one or more of the following parameters: readings from sensors, parameters of the processing components used by the industrial process, and parameters of the algorithm used to operate one or more processing components used by the industrial process.

7. A computer implementation method, comprising: A collection of operational attributes for industrial processing; Analyze the set of operational attributes to identify subsets of interdependent operational attributes; Receive an alarm from the industrial process; as well as In response to the aforementioned alert: Identify a subset of operational attributes associated with the alarm; Identify the first operational attribute that triggers the alarm from the subset of operational attributes associated with the alarm; Identify a second operational attribute that is interdependent with the first operational attribute; The second operation attribute is displayed on the graphical user interface, and modification input is received from the graphical user interface; as well as Modify the second operation attribute based on the modified input.

8. The computer implementation method according to claim 7, wherein: Identifying a subset of operational attributes associated with the alarm includes: identifying multiple subsets of operational attributes associated with the alarm; Identifying the first operational attribute that triggers the alarm from a subset of operational attributes associated with the alarm includes: identifying a set of first operational attributes that trigger the alarm from each subset of the plurality of operational attribute subsets associated with the alarm; Identifying the second operational attribute that is interdependent with the first operational attribute includes: identifying the second operational attribute that is interdependent with the set of the first operational attributes; and Presenting the markers of the second operation attribute on the graphical user interface and receiving modification input from the graphical user interface includes: presenting a set of markers of the second operation attribute on the graphical user interface and receiving the modification input from the graphical user interface.

9. The computer implementation method according to claim 8 further includes: The set of the second operation attributes is sorted by priority to form a priority sorting list of the second operation attributes; as well as Move the marker of the highest priority operation attribute in the priority sorting list of the second operation attributes to the highest priority position closest to the graphical user interface.

10. The computer implementation method according to claim 8, further comprising: Based on priority, the marker of the highest priority operation attribute in the set of second operation attributes is moved to the highest priority position closest to the graphical user interface.

11. The computer implementation method according to claim 10, wherein, The highest priority operation attribute is prioritized by one or more of the following: faster alarm resolution, less waste generated by the industrial process, lower risk of alarm escalation, and lower resource requirements.

12. The computer implementation method according to claim 7, wherein, Analyzing the set of operational attributes to identify subsets of interdependent operational attributes includes: Collect a set of past operational attributes of industrial processes; Applying one or more transformations to each of the past operational attributes in the set of past operational attributes includes: changing the degree of a first transformation in the one or more transformations, changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to an omitted past operational attribute in the set of past operational attributes, and omitting at least one transformation in the one or more transformations applied to included past operational attributes in the set of past operational attributes, to create a modified set of past operational attributes. Create a first training set, which includes a set of collected past operational attributes, a set of modifications to the past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms. The neural network is trained in the first phase using the first training set; A second training set is created for the second phase of training. The second training set includes the first training set and a set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and The neural network is trained in the second phase using the second training set.

13. The computer implementation method according to claim 7, wherein, The set of operational attributes includes a set of one or more of the following parameters: readings from sensors, parameters of the processing components used by the industrial process, and parameters of the algorithm used to operate one or more processing components used by the industrial process.

14. A system comprising: database; as well as A processor coupled to a computer memory, the computer memory storing instructions for the processor to execute the instructions; as well as The instructions cause the processor to execute: Collect a set of past operational attributes of industrial processes from the database; Applying one or more transformations to each of the past operational attributes in the set of past operational attributes includes: changing the degree of a first transformation in the one or more transformations, changing the order of one or more transformations applied to two or more past operational attributes, including applying a second transformation to an omitted past operational attribute in the set of past operational attributes, and omitting at least one transformation in one or more transformations applied to included past operational attributes in the set of past operational attributes, to create a modified set of past operational attributes; Create a first training set, which includes a set of collected past operational attributes, a set of modifications to the past operational attributes, and a set of irrelevant operational attributes of the industrial process that are unrelated to previous alarms. The neural network is trained in the first phase using the first training set; A second training set is created for the second phase of training. The second training set includes the first training set and a set of irrelevant operational attributes of the industrial process that are unrelated to any previous alarms, wherein the set of irrelevant operational attributes was incorrectly identified as influencing previous alarms; and The neural network is trained in the second phase using the second training set.

15. The system of claim 14, further comprising: The network interface to the network; as well as User equipment, which includes the processor and the graphical user interface; as well as The instructions also cause the processor to execute: The alarm associated with the industrial process is received via the network, and the alarm reports the alarm status of at least one operational attribute of the industrial process; In response to the aforementioned alert: The set of operational attributes of the industrial process and the alarm are provided to the neural network to receive recommended solution actions from the neural network; The graphical user interface displays a marker for the recommended solution action and at least one action that differs from the recommended solution action. Receive a selection action, the selection action identifying one of the recommended solution action and at least one action that is different from the recommended solution action; as well as Based on the selected action, at least one processing component of the industrial process is modified.

16. The system according to claim 15, wherein: The recommended solution action consists of multiple recommended solution actions ordered by priority; Presenting the recommended solution action on the graphical user interface includes: presenting the multiple priority-sorted recommended solution actions in priority order; Receiving a selection action, wherein the selection action identifies one of the recommended solution action and at least one action different from the recommended solution action, includes: receiving the selection action, wherein the selection action identifies one of the plurality of priority-ordered recommended solution actions and at least one action different from the plurality of priority-ordered recommended solution actions; and Modifying at least one processing component of the industrial process according to the selected action includes: modifying the at least one processing component of the industrial process according to the selected action.

17. The system according to claim 16, wherein, Presenting the recommended solution action on the graphical user interface includes: presenting the plurality of priority-sorted recommended solution actions in the priority order, and further includes: moving the marker of the highest priority recommended solution action among the plurality of priority-sorted recommended solution actions to the highest priority position closest to the graphical user interface.

18. The system according to claim 16, wherein, The priority order is one or more of the following: faster alarm resolution, less waste generated by industrial processing, lower risk of alarm escalation, and lower resource requirements.

19. The system according to claim 16, wherein, The instruction also causes the processor to execute: Monitor the impact of the selected action on the set of operation attributes; and Feedback, including the selected action and the effect, is provided to the neural network.

20. The system according to claim 15, wherein, The set of operational attributes includes a set of one or more of the following parameters: sensor readings, parameters of the processing components used by the industrial process, and parameters of the algorithm used to operate one or more processing components used by the industrial process.

Images