The present disclosure relates to a data driven system and method to determine the state and operating mode of a facility in a particular event context.
Facilities, such as industrial plants, refineries, manufacturing plants, pulp and paper plants, steel mills, and office buildings and other buildings can have many states and modes. The facility state refers to the overall state of a facility or a unit in the facility. For an industrial plant, the four generally accepted states of a plant are maintenance, startup, shutdown, and normal operation. During the maintenance, startup, and shutdown states, initial conditions and process parameter values can differ significantly from the normal operation state. The operating mode of the plant is the combined activity of plant units and assets for a period of time to achieve a specified production output. For example, in a petro-chemical refinery plant, the type and quality of the crude oil that is input into the plant will determine the amounts and qualities of the different products that can be refined from the crude oil, such as kerosene, diesel, and gasoline. Consequently, plant states and operating modes are affected by the product that the plant is producing, operational constraints, process constraints, the state of non-automated parameters, the plant load, equipment maintenance, equipment failure, process upsets, and environmental conditions.
There are times when plant stability is most at risk, since these times can be the most difficult to control and anticipate. These times are normally considered to be the maintenance, startup, and shutdown states or events. These are the three most common types of events that occur, that do not fit in with the normal plant operations, and that directly affect the stability of the plant and the safe operations of equipment and processes. In current plant operations, unit/asset performance monitoring and key performance indicators (KPI) do not contain data driven and/or readily consumable information to determine and identify the cause of events, and to diagnose plant state and operating mode.
In the following description, reference is made to the accompanying drawings that form a part hereof, and in which is shown by way of illustration specific embodiments which may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention, and it is to be understood that other embodiments may be utilized and that structural, electrical, and optical changes may be made without departing from the scope of the present invention. The following description of example embodiments is, therefore, not to be taken in a limited sense, and the scope of the present invention is defined by the appended claims.
To address these situations, one or more embodiments are directed to a system and method to identify unique states and operating modes of an industrial plant or other facility during operation of the plant or facility. More specifically, an embodiment describes the implementation and validation of a self-configuring, self-updating, machine learning-based artificial intelligence algorithm to determine a plant state and operating mode by detecting when the relation between manipulated parameters changes. Data that are available in a plant's digital control system are used and therefore no human input is required.
The ability to determine the state and operating mode of a plant in a real-time or close to real-time fashion can be put to use in several different manners to improve the operations of a plant. First, the response of an operator to an event or an abnormal condition in the plant will vary based on the state of the plant and operating mode of the plant at the time the event occurred. Therefore, knowing both the state and mode aids the operator in responding to a plant event. Second, an operator has several process variables (PVs) and key performance indicators (KPIs) trending on his or her control room computer screen that are related to the tag (or tags) in an alarm. Knowing the current plant state and mode will assist an operator in responding to these trends and alarms. Third, an operator uses these trends to determine the response required to manage such an alarm event. Therefore, knowing the current state and mode of a plant will help highlight the behavior and/or reaction of an operator during normal operation, start-ups, trips, and emergency shutdowns.
Additionally, to enable the next level of improvement in industrial plant performance, one or more embodiments include automated methods to perform the following. First, an embodiment can predict lead indications of abnormal events (e.g., process stress). The embodiment that deals with these abnormal events is robust (e.g., increased strength of protection and control systems). Second, the embodiment can estimate future values of key performance indicators (KPIs) to enable the corrective actions that should be taken to address the problem(s). Third, the embodiment can provide real-time guidance to operators to ensure optimal operation of the plant and/or to ensure appropriate responses to events. Fourth, the embodiment can provide an assessment of the on-the-job competency of an operator. Such assessments can then be used to develop and/or improve operator training sessions.
These embodiments include a component to estimate the plant state and plant operating mode. A reason for the need to accurately and on a real-time basis to determine the plant state and plant operating mode is because acceptable performance in one state or operation mode may not be acceptable in another state or operating mode. The correct determination, in a real-time or near real-time basis, of plant state and operating mode therefore assists in predicting lead indications of abnormal events, estimating future values of KPIs, providing real-time guidance to operators, and evaluating operator on-the-job performance.
The conditions that lead to and/or cause changes or variances of the plant state and plant operating mode are as follows. The type of product that is being produced by the plant influences the plant state and operating mode. A plant unit or plant asset may be configured distinctly for different product types. For example, if the two different products are kerosene and diesel fuel, patterns of time series process variable data for temperatures and pressures in a distillate column will be different when the plant operations are in the different modes. Additionally, these changes can be sensed when there is a changeover from one product to another product. Consequently, these different product types can be reflected in on-line or off-line analyzer measurements of the feed input used to make the product and the actual product output itself. The plant state and operating mode can also change when the plant is going through a maintenance period, a startup period (cold or hot), and a planned or unplanned shutdown. A plant unit or plant asset may be configured distinctly for different plant loads, that is, different product throughputs (e.g. 50% or 90% of total capacity). These different plant loads are reflected in process variable data of feed/input flow tag values. Environmental conditions around the plant may be distinct and may affect the plant state and plant operating mode. For example, in a food processing plant, there are more likely than not different cooling needs in the summer months versus in the winter months. Such differences can be reflected in process variable data related to utility flow rate. Also, various process constraints may exist at a plant, which could affect the plant state and/or plant mode. For example, a constraint could be that a particular unit or asset is not available. As another example, a catalyst could have become degraded, and the plant process would then have to be run at higher temperatures. Lastly, there are various non-automated parameters in a plant such as hand valves and manual lockouts of units/assets, and the status of these non-automated parameters can affect the plant state and plant mode.
In response to the need to be able to accurately determine on a real-time or near real-time basis a plant state and plant mode of an industrial plant, one or more embodiments invoke a self-configuring, self-updating, machine-learning based artificial intelligence algorithm to determine plant state and plant operating mode (when the plant is in a normal operating state) by detecting the relationship between manipulated parameter changes. An embodiment processes and integrates multiple data sources to learn about the plant states and plant modes.
The integration of the multiple data sources in
The process of using event data 312 to identify the plant state and mode is further illustrated in
In a similar fashion,
As noted above, an embodiment first determines in a real-time or near real-time the state of an industrial plant, and then, if the plant is in a normal operating state, determines the operating mode of the plant. Knowing the plant state and operating mode allows an operator to determine if a current event (as indicated by a process variable for example) is of concern or not. Before addressing the details of the embodiment, the different possible plant states are discussed in further detail.
Normal plant operation is the state of a plant in which an operator maintains the operating variables/parameters within defined operating limits. The plant processes should run at steady state conditions. Significant deviations from the normal operation lead to an upset condition. The normal operation of a plant has two sub-states—normal and off normal. The normal state is detected by analyzing if process variable (PVs) values of all parameters are within the operating range without any alarm events. The normal state has two further sub-states —optimized operation and non-optimized operation. Optimized operation is detected by analyzing if the PVs have minimal deviations from defined set points (SPs). Non-optimized operation is detected by analyzing if the PVs deviate from the SPs, but the PVs do not cross any alarm limits. The off normal state includes alarm events, which are detected by analyzing if PVs have deviated from the alarm limit values.
Major shutdowns in industrial plants typically happen infrequently (every year or two). However, when such shutdowns occur, they normally take several days to complete. In general, these shutdowns have two objectives. First, to repair problems identified during previous major shutdowns, and second, to inspect parts of the plant not accessible during operation in order to identify problems that will be repaired during future planned shutdowns. There are generally two types of shutdowns—normal shutdowns and emergency shutdowns. A normal shutdown is part of a plant safeguarding system and its purpose is to minimize the frequency and consequences of excursions outside the facility operating envelope. Possible causes of a normal shutdown include composition changes in the feed (e.g., feed stock changes, products requirement variations), process limitations (e.g., limitations of exchangers, vessels, columns, and other equipment to meet process demands), maintenance activities (e.g., regeneration/activation of catalysts, management of delta pressure or heat transfer issues through furnaces/exchangers, maloperation of compressors, pumps, and columns), and management of parameter issues that degrade products. An emergency shutdown is part of a plant safeguarding system and its purpose is to keep the plant processes within design limits and to prevent the escalation of abnormal conditions into a major hazardous event. The possible causes of an emergency shutdown include equipment failure, process upsets/trips, process/operational constraints like pipeline choking, flooding/weeping in columns, runaway conditions, over pressurization, and process control issues.
A plant startup is identified as the time between a shutdown and normal operation. A plant startup has two sub-categories—cold startup and hot startup. In a cold startup, variables such as casing temperatures, shaft temperatures, and bearing temperatures of equipment are at ambient temperature and there is zero (0%) holdup in the sumps, vessels, and other similar equipment. A cold startup is normally followed when equipment, such as a turbine, is in stop/standby condition for more than a certain amount of time, such as 20 hours. In hot startup, the variables such as casing temperature, shaft temperature, and bearing temperature are not equal to ambient temperature, and holdups in the sumps, vessels, and other equipment are more than 0%.
Typical causes for entering an unplanned maintenance state include failure to replace worn out parts, lack of lubrication, and other issues. Information indicating the maintenance state is captured in condition monitoring alarms, maintenance override switch (MOS) activation events, red-tags identifications (tagged equipment that is taken out of service), and flows across plant equipment.
As previously noted, when it is determined that the plant is in a normal operating state, then an embodiment can determine not only the current operating mode of the plant, but whether an event in the plant is cause for concern. This determination of whether there is a need for concern is based on a machine learning (ML)/artificial intelligence (AI) algorithm that was trained with historical plant data (to learn the relationships among all related events/data/equipment) and the instant event, and the use of the trained ML/AI algorithm to make a decision on the need/cause for concern in view of a plant event. In an embodiment, the ML/AI algorithm involves a clustering method.
Plant operating mode varies based several factors. These factors include the type of product that is being produced, the current load of the plant, the environmental conditions under which the plant is currently operating, any operational constraints, and the states of any non-automated parameters. An embodiment determines that a plant unit/asset is in a different operating mode when the values of key variables move into another steady state, or when correlation between parameters changes (as learned by the training of the ML/AI algorithm). During normal plant operation, all alarm events require a response from the operator to return to normal operating range. However, an operator may face different scenarios like the flooding of events (i.e., multiple events or alarms occurring at the same time), operational constraints (which would prevent the operator from responding to an alarm/event in the most effective manner), and flow tag trends. To respond to events optimally, it is necessary to be able to distinguish among such scenarios. Operating mode identification provides the context for an event, i.e. the operating mode within which a given event occurs. Simply put, to enable accurate fault detection it is necessary to accurately detect the plant unit/asset operating mode because a fault in one operation mode may not be a fault in another operating mode. The method to determine the operating mode in an embodiment is discussed in connection with
There are several unique and novel features to one or more embodiments of the present disclosure. First, an embodiment can automatically identify plant critical tags that impact the state of the plant. That is, given an event on a single or group of process variables (PVs), there are specific related PVs that need to be examined to determine the plant state and operating mode at the time of an event. These related PVs were learned from the ML/AI algorithm that was trained on plant historical data. This embodiment can auto-identify and process the principle data components related to a candidate tag using configuration data and graphics data (HMI).
Second, an embodiment can identify in real-time the operating mode of a plant. As noted previously, the embodiment uses historical plant data to machine-learn plant operating modes, and then uses the machine-learned models to process real time data from the plant and determine the operating mode of the plant. Additionally, the database containing learned operating modes (models) is updated when new operating modes are identified through the learning process and these new modes are confirmed by an operator. The features of this embodiment can assist and guide an operator in the real time operation of the plant.
Third, an embodiment enables plant process optimization in real-time by identifying and evaluating deviations from steady state values to determine the durations when the plant is not in optimal operating modes and further identifying the factors causing the operation to deviate. This information will enable the operator to adjust parameters to further optimize the process. Once again, this is further aided by the trained models that identify, in real-time, the plant state and the plant operating mode.
Fourth, as mentioned above, an embodiment enables additional systems for industrial plant monitoring that results in the next level of improvement in plant performance. For example, the embodiment can predict lead indications of abnormal events and improve the robustness of dealing with these abnormal events. Future values of key performance indicators (KPIs) can be estimated to enable corrective actions to be taken. On-the-job competency of the operator can be assessed to enable training interventions. Real-time guidance can be provided to operators to ensure optimal operations.
Referring first to
Further in the data preparation stages of operations 505, 506, and 507, history data for each tag are analyzed to determine the distribution and density of data values. The percentage of the data in each range is calculated. The ranges where most of the data are present are assumed to be the steady state ranges. It is noted that these may or may not be contiguous ranges.
At 510, the plant state and plant operating modes of the industrial plant are determined using the data from operations 505, 506, and 507. Operation 510 involves the determination whether the plant is in a state of normal operation 520, planned maintenance 530, planned startup 540, or shutdown mode 550. The process for determining normal operating mode begins at operation 520, and includes the determination of the context 521 of an event, such as a process alarm 313. At 522, the trends of the event and their relations to related process value flow tags are analyzed. As indicated at 522A, these flow tags are assigned to particular plant assests. Flow tags that may be related to the flow tags at 522A are considered at 522B. At 523, standing previous alarms are considered. For example, if an upstream alarm is standing (i.e., it has not be solved and reset), then the eventual addressing of the problem that caused the standing alarm may also address the current alarm 521 at issue. At 524, the steady state value of the process variable with which the alarm is associated is determined. The extent of the deviation from the steady state process value can assist in determining the seriousness of the alarm. At 525, related tags are analyzed, once again to assist in determining the event context. At 526, the statuses of other operator tags can be considered. Finally, at 527, other operational constraints are considered. For example, a particular plant unit may currently be out of service. This may involve analyzing historical data for all tags and calculating pertient ranges (527A).
At 530, the system is trained to identify that the plant is in a planned maintenance state. It can be determined that a plant is in a planned maintenance state at 531 by noticing maintenance override switch (MOS) activation, and at 532 by determining that a particular piece of equipment or plant unit has been red tagged (i.e., a red tag has been attached to the equipment indicating that it is not in proper working order).
Operation 540 details a determination that a plant is in a planned startup state. As noted in
Operation 550 and its related operations determine that the state of the plant is a shutdown state. At 560, it can be determined that the shutdown is a planned shutdown, and at 570, it can be determined that the shutdown is an emergency shutdown. First addressing a planned shutdown 560, all process value flow tags are analyzed at 561. At 562, all standing alarms during the duration of the planned shutdown are analyzed. The standing alarms may provide information on the reasons for the planned shutdown. Similarly, at 563, rotating equipment alarms are analyzed during the duration of the planned shutdown. Finally, at 564, the controller operations are analyzed in connection with the planned shutdown.
As indicated at 570, an emergency shutdown is handled automatically by the plant system. Historically, such emergency shutdowns could be handled either automatically by the plant system or manually by an operator (for example, when the operator observes that a process value is out of the safe operating range). Similarly, in an embodiment, an emergency shutdown can be handled automatically or by operator intervention. An advantage of an embodiment however is that the emergency shutdown decision is more robust because of the training and learning of the system. As indicated at 571, an emergency shutdown can be triggered by process upsets and/or process trips, or as indicated at 572, by the detection of equipment failure. During an emergency shutdown, all process value flow tags are recorded and analyzed at 573. Like the case for a planned shutdown 560, all standing alarms during the duration of the emergency shutdown are analyzed at 574, and at 575, any rotating equipment alarms are analyzed during the duration of the emergency shutdown. Finally, at 576, the statuses of all safety solenoid values are analyzed.
This process of the determination of the plant state illustrated in
If at 620 all KPI variable values are in the proper operating ranges and all KPI variable values are not less then the process variable lower limits, then the process checks at 630 if the plant is in a normal operating state. If the controller operations of the plant are all in the normal range (631), and if the statuses of all rotating equipment is on (632), and all safety solenoid tags are opened (633), and the number of standing alarms are less than a threshold (e.g., less than the ASM standard) (634), then at 630 it is determined that the plant is in a normal operating state 635.
If the plant is not in a normal operating state at 630, 635, then the system checks at 640 to determine if the plant is in a shutdown state 645. This is executed by determining if MOSs are enabled (641), if particular plant units have been red tagged (642), and if flow tag values across the plant equipment are equal to zero (643). If one or more of operation 641, 642, and 643 are not true, then it is determined that the plant is in a shutdown state at 645. If all operations 641, 642, and 643 are true, beginning at 650, the system determines if the plant is in a shutdown state 674 or a maintenance state 672. Specifically, at 655, an inquiry is made if the amount of time that a particular piece of equipment has been red tagged can be determined. If that determination cannot be made, then at 656 equipment switchover times are identified in order to derive the maintenance time duration (i.e., the red tag time duration). If that determination can be made at 655, that at 657, the equipment that switched over during the red tag duration time is identified (i.e., the amount of time that the equipment was red tagged). In either event, after operations 656 and 657, at 660, the maintenance override switches (MOS) that are enabled during the duration of the red tag event are identified (i.e., the time that the tag was in the red zone). At 665, the MOS enabled switches are linked to equipment where the switchover occurred, and at 670, if there is a large number of plant assets in a plant unit in maintenance, then the plant unit is in a shutdown state at 674. If not, then the plant unit is in maintenance mode at 672.
In an embodiment, the data are engineered prior to further processing. For example, as indicated at 706A, the facility data are engineered by dividing the facility data into subsets. These subsets can be based on certain environmental conditions, certain facility load conditions (e.g., the facility is operating at 80% of capacity), and certain time windows. Additionally, as indicated at 706B, the facility data can be normalized, cleaned (e.g., by removing outliers), and by filling in missing data (e.g., by interpolation).
At 710, the facility data are grouped into clusters. While clustering is used in one embodiment, other forms of machine learning could also be used. Each of the clusters relates to a particular facility state and a particular facility operating mode. Further, each of the clusters includes descriptors that relate to the particular facility state and the particular facility operating mode. For example, descriptors can include process variable values, process variable ranges, HVAC set points, and temperature ranges. The result of the clustering is a plurality of clusters relating to different facility states and facility operating modes. At 715, the clusters are used to determine the current state and current operating mode of the facility. For example, as indicated at 716A, currently facility data are accessed, and at 716B, the current facility data are compared to the clusters. At 716C, clusters that are similar to the current facility data are identified. This identification can be executed by, for example, identifying clusters whose data are within a certain percentage of the current facility data, for example within 10%. In other embodiments, other numerical analysis techniques can be used to identify similar clusters. As indicated at 716D, this identification of similar clusters generates a subset of clusters. Then, at 716E, the state and operating mode of the facility can be determined by the identified similar clusters. As noted at 717, the state and mode of a facility can be based on such factors as the type of product being manufactured by an industrial plant, planned maintenance of the plant, the operating load of the plant, an environmental condition, a process constraint, and a state of a non-automated parameter.
As noted above, in an embodiment, the states of a facility can be a normal state, a startup state, a shutdown state, and a maintenance state. When the facility is in a normal operating state, then at 720, it is determined if an event, such as an alarm or a change in a facility process, is an abnormality. At 725, if the event is an abnormality, a signal is transmitted to an operator or a computer display device reporting the abnormality. In addition to determining if an event is an abnormality at 720, the system can further execute other operations when the facility is in a normal state of operations. For example, as indicated at 721, the system can use the clusters to estimate future values of key performance indicators (KPIs). Like in connection with a determination of an abnormality, the determination of future values of the KPIs can provide real-time guidance to an operator of the facility (e.g., advising operator to shut down plant, decrease flow rate of an ingredient, etc.), and can further be used to evaluate on-the-job actions of the operator (e.g., determining if and/or how closely an operator followed advice, and/or the outcome of the operator following of the advice).
When it is determined that the facility is in a normal operating state (720), then at 722A, the system can use the clusters to determine whether the facility is in a steady state and/or optimal operating mode. For example, the system could have learned from the clusters that when certain KPIs and/or process variables are within a certain percentage of their set points, then the facility is in a steady state and/or optimal operating mode. Conversely, at 722B, if the facility is not in a steady state or optimal operating mode, then an analysis using the clusters can identify one or more factors that may be causing the facility to not be in a steady state or operating in an optimal operating mode.
In addition to determining whether an alarm is a cause for concern based on the current state and operating mode of a facility (as learned from machine learning of historical data), the system can execute several other functions based on the machine learning. For example, at 730, the system can use the clusters to determine whether the facility is going through a change in the state or the mode of the facility. In an embodiment, this can be executed by examining values of key process indicators (KPIs) in the clusters. Additionally, correlation changes among the facility data can be examined. At 731, the system can transmit a signal to an operator or a computer display device reporting the change in the state or the mode.
The system can also determine a relationships among facility data based on the machine learning. For example, an examination of facility data that are directly related to an event and facility data that are indirectly related to the event. Specifically, at 735, facility data in the clusters that are directly related to an event are examined. An example of directly related data is pressure data in a holding tank that resulted in a high pressure alarm. Then, at 736, facility data in the clusters that are indirectly related to the event are examined. An example of indirectly related data is a flow rate in a pipe that feeds the holding tank. At 737, the system determines a course of action in response to the event based on this examination of the direct and indirect facility data. Then at 738, the system transmits a signal to an operator or a computer display device indicating the course of action.
While the system can be initially trained with historical facility data, the system can be retrained as more current data become available. Specifically, as indicated at 740, the clusters can be regenerated when new operating modes of the facility are identified. At 741, the regenerated clusters are used to determine (once again, when the facility is in a normal state), whether an event in the facility comprises an abnormality. Lastly, at 742, a signal is transmitted to an operator or a computer display device indicating the abnormality.
In addition to determining that a facility is in a normal state, the system can also determine if the facility is currently in other states and/or when other states should be initiated. For example, the system can use the clusters to determine when to commence a normal shutdown (750), when to commence an emergency shutdown (755), and whether a detected startup is a cold startup or a hot startup (760). After each of these, a signal is transmitted to an operator or a computer display device conveying the information (751, 756,761).
The example computer system 800 includes a processor 802 (e.g., a central processing unit (CPU), a graphics processing unit (GPU) or both), a main memory 801 and a static memory 806, which communicate with each other via a bus 808. The computer system 800 may further include a display unit 810. The computer system 800 may additionally include a storage device 816 (e.g., drive unit), a signal generation device 818 (e.g., a speaker), a network interface device 820, and one or more sensors 828, such as a global positioning system sensor, compass, accelerometer, or other sensor.
The drive unit 816 includes a machine-readable medium 822 on which is stored one or more sets of instructions and data structures (e.g., software 824) embodying or utilized by any one or more of the methodologies or functions described herein. The software 824 may also reside, completely or at least partially, within the main memory 801 and/or within the processor 802 during execution thereof by the computer system 800, the main memory 801 and the processor 802 also constituting machine-readable media.
While the machine-readable medium 822 is illustrated in an example embodiment to be a single medium, the term “machine-readable medium” may include a single medium or multiple media (e.g., a centralized or distributed database, and/or associated caches and servers) that store the one or more instructions. The term “machine-readable medium” shall also be taken to include any tangible medium that is capable of storing, encoding or carrying instructions for execution by the machine and that cause the machine to perform any one or more of the methodologies of the present invention, or that is capable of storing, encoding or carrying data structures utilized by or associated with such instructions. The term “machine-readable medium” shall accordingly be taken to include, but not be limited to, solid-state memories, and optical and magnetic media. Specific examples of machine-readable media include non-volatile memory, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.
The software 824 may further be transmitted or received over a communications network 826 using a transmission medium via the network interface device 820 utilizing any one of a number of well-known transfer protocols (e.g., HTTP). Examples of communication networks include a local area network (“LAN”), a wide area network (“WAN”), the Internet, mobile telephone networks, Plain Old Telephone (POTS) networks, and wireless data networks (e.g., Wi-Fi® and WiMax® networks). The term “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding or carrying instructions for execution by the machine, and includes digital or analog communications signals or other intangible medium to facilitate communication of such software.
It should be understood that there exist implementations of other variations and modifications of the invention and its various aspects, as may be readily apparent, for example, to those of ordinary skill in the art, and that the invention is not limited by specific embodiments described herein. Features and embodiments described above may be combined with each other in different combinations. It is therefore contemplated to cover any and all modifications, variations, combinations or equivalents that fall within the scope of the present invention.
The Abstract is provided to comply with 37 C.F.R. § 1.72(b) and will allow the reader to quickly ascertain the nature and gist of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.
In the foregoing description of the embodiments, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting that the claimed embodiments have more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus the following claims are hereby incorporated into the Description of the Embodiments, with each claim standing on its own as a separate example embodiment.
Number | Date | Country | Kind |
---|---|---|---|
202041022669 | May 2020 | IN | national |