Method and system for providing simulation model generation in a cloud computing environment

Abstract

A method and system for providing simulation model generation in a cloud computing environment (100) is disclosed. The method includes receiving a request of a user device (128A-N) for generating a simulation model. The request includes asset information associated with assets (122, 124A-N and 126) in a plant environment (106). Further, the method includes generating the simulation model associated with the assets (122, 124A-N and 126) based on the received asset information and pre-stored asset information in a cloud database (116). The method also includes validating the simulation model associated with the assets (122, 124A-N and 126) based on real-time asset information received from the plant environment (106). Further, the method includes outputting the simulation model associated with the assets (122, 124A-N and 126) on a user interface of the user device (128A-N).

Description

Technical Field

[0001] The present invention relates to cloud computing systems, and more particularly, to a method and system for providing simulation model generation in a cloud computing environment. Background Art

[0002] For example, in process industry environments, simulation models with real-time capabilities are preferably used in operator training systems (OTS) or in systems for virtual commissioning (VIBM). Simulation content and models are key elements for any given simulation software. Typically, simulation model development is done manually in simulation software by extracting information and behavior of field devices and converting the behavior into mathematical models. In addition, all simulation models are maintained locally by the simulation software as a batch library. Some key use cases for simulation software are the development, testing, and maintenance of simulation models for various field devices (such as motors, valves, pumps, transmitters, hydraulic devices, etc.). For any simulation software, the manual implementation and testing of locally stored simulation models leads to different problems. Several issues are highlighted below.

[0003] The development of simulation models is costly and time-consuming. All detailed characteristics and behavior data of field devices should be collected from asset profiles, and finally, simulation experts must manually develop the data. Therefore, the development cost is huge.

[0004] The availability of simulation models is another crucial issue in today's dynamically growing business landscape. Simulation model development and testing consume increasing amounts of time, and the models developed are often manufacturer-specific. However, existing simulation software falls short of expectations in meeting market demands.

[0005] Several methods currently exist for generating simulation models. These methods can be used with any available simulation software and plant engineering data. However, these methods require expert user intervention to create simulation objects. In one method, the components controlled by a programmable logic controller (PLC) have unique identifiers, so a list of components is retrieved from the PLC program. Component relationships are also extracted from the PLC program, as references exist in the PLC code between connected components. Thus, the topology of the controlled system is incorporated into the PLC program. The control logic includes a structured approach, so the relationships between variables and objects are transformed into the language of the simulation software. However, this approach relies on data available in the production database and PLC code. Another approach discloses a set of workflows and user roles for an automated model generation mechanism. However, this approach requires simulation expertise.

[0006] US 2004 / 230404 A1 relates to a method for simulating a process involving discrete events or tasks with multiple available resources. A model application communicates with a database and is configured to receive a command from a user, retrieve one of a plurality of models and a corresponding plurality of one or more entity, task, and resource parameters in response to the user command, receive input data corresponding to attributes of the one or more entity, task, and resource parameters from a commercial database system, and generate a simulation model based on the selected commercial database system and the input data. However, US 2004 / 230404 A1 fails to teach validation of the generated simulation model and outputting the generated simulation model only when the validation result is successful.

[0007] In view of the above, there is a need for an improved method and system for providing simulation model generation in a cloud computing environment. Summary of the Invention

[0008] Therefore, an object of the present invention is to provide a method and system for providing simulation model generation in a cloud computing environment.

[0009] The objectives of the present invention are achieved by a method for providing simulation model generation in a cloud computing environment. The method includes: receiving a request for generating a simulation model from a user device. The request includes asset information associated with an asset in a factory environment. The asset information includes asset profile data, which includes asset configuration information, asset physical block information, test data sets, asset alarms, etc. In an embodiment, the assets include servers, robots, switches, automation devices, programmable logic controllers (PLCs), human-machine interfaces (HMIs), input-output modules, motors, valves, pumps, actuators, sensors, and other industrial equipment (one or more). In an embodiment, each asset in the factory environment is associated with a profile (referred to as an asset profile file). The asset profile file includes asset configuration information, asset specification information, asset faults, asset alarms, etc. The asset profile file is shared along with the request from the user device.

[0010] The method includes generating a simulation model associated with the asset based on the received asset information and pre-stored asset information in a cloud database.

[0011] The pre-stored asset information corresponds to a last received version of asset information associated with an asset in a factory environment. The pre-stored asset information may correspond to one or more pre-stored simulation models associated with the asset, one or more pre-stored asset parameters, historical asset information, and a sample data set for the asset.

[0012] The method includes identifying a simulation model associated with an asset based on real-time asset information received from a plant environment. In an embodiment, the real-time asset information is received from the plant environment via a cloud agent located at the plant environment. In an embodiment, the real-time asset information is received from one or more assets in the plant environment, wherein the one or more assets are capable of transmitting asset information directly to a cloud computing system.

[0013] Further, the method includes outputting the simulation model associated with the asset on a user interface of a user device.

[0014] In a preferred embodiment, the method includes storing the simulation model associated with the asset in a cloud database.

[0015] In another preferred embodiment, in generating the simulation model associated with the asset based on the received asset information and the pre-stored asset information, the method includes determining behavior of the asset using one or more asset parameters associated with the asset in the plant environment. The one or more asset parameters include asset characteristics, asset location, asset behavior trends, asset tag information, and / or asset faults. The behavior of the asset indicates physical behavior of the asset in the form of equations or relationships between different asset parameters.

[0016] Further, the method includes generating a plurality of test data associated with the behavior of the asset. The test data can be utilized with the asset information as a time series dataset or can be utilized without the asset information as a time series dataset. However, the test data can be generated on the fly based on minimum and maximum limits of the asset parameters.

[0017] Further, the method includes obtaining a mathematical model associated with the asset based on the test data and the determined behavior of the asset. The mathematical model of the asset includes mathematical equations depicting the behavior of the asset. In this preferred embodiment, in obtaining the mathematical model associated with the asset based on the test data and the determined behavior of the asset, the method includes identifying minimum and maximum range values for each asset parameter using the asset information. The minimum and maximum range values refer to threshold values defined by a manufacturer of the asset. The minimum and maximum values of the asset parameters help define the test data sequence in case the test data sequence is not available in the asset profile. Further, the minimum and maximum values of all the asset parameters help in obtaining the initial mathematical equations of the physical behavior of the asset. In an embodiment, the minimum and maximum values are a range of process values of the asset. For example, current and voltage values of a motor have minimum and maximum range values for startup and breakdown of the motor. Based on the requirement of speed / rotation of the motor, a particular motor has this minimum and maximum range of current and voltage values.

[0018] In addition, the method includes: generating a polynomial graph for each asset parameter that affects the behavior of the asset. In addition, the method includes: obtaining a relationship matrix for the generated polynomial graph. The relationship matrix indicates the behavior of the asset for each asset parameter. In an embodiment, the relationship matrix is ​​obtained using given inputs in an asset profile test data set. Based on the coefficients of the obtained mathematical equation (or model as referred to in this document), a matching mathematical model is searched in a database. The best possible match of the obtained mathematical equation is determined. If the best possible match of the obtained mathematical equation does not exist, the obtained mathematical equation itself is regarded as a basic version of the mathematical model and is further scheduled for confirmation based on received real-time asset information. In addition, the method includes: obtaining a mathematical model associated with the asset based on the relationship matrix.

[0019] Additionally, the method includes generating a simulation model for the asset based on the obtained mathematical model associated with the asset.

[0020] In another preferred embodiment, in confirming a simulation model associated with an asset based on real-time asset information received from a factory environment, the method includes: receiving the real-time asset information associated with the asset from the factory environment via a cloud agent. Furthermore, the method includes confirming the simulation model associated with the asset based on the real-time asset information and predefined rules.

[0021] In another preferred embodiment, the method includes analyzing a validation result of a simulation model associated with the asset. Furthermore, the method includes generating an error log file associated with the simulation model if the validation result is unsuccessful. Furthermore, the method includes displaying the error log file associated with the simulation model on a user interface of a user device.

[0022] In another preferred embodiment, the method includes analyzing asset information associated with an asset in a factory environment. The method also includes determining whether a pre-stored simulation model exists in a cloud database based on the analyzed asset information. Furthermore, if the pre-stored simulation model does not exist in the cloud database, retrieving a similar simulation model stored in the cloud database. Furthermore, the method includes generating a simulation model template associated with the asset based on the retrieved similar simulation model and historical asset information stored in the cloud database.

[0023] In a preferred embodiment, the method includes: detecting one or more anomalies associated with an asset in a factory environment using a cloud agent. The method includes: receiving a notification message from a user device. The notification message includes the one or more detected anomalies associated with the asset.

[0024] In another preferred embodiment, the method includes providing a price for each stored simulation model based on the asset information. In an embodiment, each simulation model is associated with a pricing model and a user rating.

[0025] The objects of the present invention are also achieved by a simulation model generation system. The simulation model generation system includes one or more processors and a memory coupled to the processors. The memory includes a simulation model generation module stored in the form of machine-readable instructions executable by the processors. The simulation model generation system module is configured to perform the method described above.

[0026] The object of the present invention is also achieved by a cloud computing system, comprising a server and a cloud platform, wherein the cloud platform comprises a simulation model generation system stored therein in the form of machine-readable instructions executable by the server. The simulation model generation system is configured to perform the method described above.

[0027] The objectives of the present invention are also achieved through a cloud computing environment. The cloud computing environment includes a cloud computing system and a factory environment. The factory environment includes one or more assets and a cloud agent capable of transmitting asset information associated with the one or more assets to the cloud computing system. The cloud computing environment also includes at least one user device communicatively coupled to the cloud computing system and the factory environment.

[0028] The objects of the present invention are also achieved by a computer program product having machine-readable instructions stored therein, which, when executed by one or more servers, cause the one or more servers to perform the method steps as described above.

[0029] The present invention also achieves the objectives of the present invention by a user device comprising one or more processors and a memory coupled to the processors. The memory includes an asset data processing module stored in the form of machine-readable instructions executable by the processors. The asset data processing module is configured to perform the method described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The above and other features of the present invention will now be described with reference to the accompanying drawings of the present invention.The illustrated embodiments are intended to illustrate, not to limit, the present invention.

[0031] The invention is further described below with reference to the embodiments shown in the accompanying drawings, in which:

[0032] Figure 1 is a schematic representation of a cloud computing environment capable of providing simulation model generation according to an embodiment of the present invention;

[0033] Figure 2 A simulation model generation system (such as, Figure 1 A block diagram of a simulation model generation system shown in FIG;

[0034] Figure 3 It is a simulation model generation module (such as, Figure 1 and Figure 2 , a block diagram of a simulation model generation module shown in FIG;

[0035] Figure 4 is a process flow diagram illustrating an exemplary method for providing simulation model generation in a cloud computing environment according to an embodiment of the present invention;

[0036] Figure 5 is a user device capable of implementing an embodiment of the present invention (such as, Figure 1 A block diagram of a user device shown in FIG;

[0037] Figure 6 is a process flow diagram illustrating an exemplary method for providing simulation model generation in a cloud computing environment according to another embodiment of the present invention;

[0038] Figure 7A -B is a screenshot of an exemplary graphical user interface for providing simulation model generation according to an embodiment of the present invention; and

[0039] Figure 8A -E is a graphical representation illustrating a method of deriving a mathematical model associated with an asset based on test data and determined asset behavior according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] Various embodiments are described with reference to the accompanying drawings, wherein like reference numerals are used to refer to like elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodiments. It may be apparent that such embodiments may be practiced without these specific details.

[0041] Figure 1 is a schematic representation of a cloud computing environment 100 capable of providing simulation model generation according to an embodiment of the present invention. In particular, Figure 1Depicted is a cloud computing system 102 capable of delivering cloud applications for managing a factory environment 106, which includes one or more assets 122, 124A-B, and 126. As used herein, a "cloud computing environment" refers to a processing environment that includes configurable computing physical and logical resources (e.g., networks, servers, storage, applications, services, etc.) and data distributed across a cloud platform. Cloud computing environment 100 provides on-demand network access to a shared pool of configurable computing physical and logical resources.

[0042] The cloud computing system 102 is connected to a cloud broker 120 in a factory environment 106 via a network 104 (e.g., the Internet). The one or more assets 122, 124A-B, and 126 may include servers, robots, switches, automation devices, programmable logic controllers (PLCs), human-machine interfaces (HMIs), input-output modules, motors, valves, pumps, actuators, sensors, and other industrial equipment (s). In an exemplary embodiment, asset 122 may be a PLC and assets 124A-N may be input-output modules or controllers. Asset 126 may be a field device. The cloud computing system 102 may be a public cloud, a private cloud, and / or a hybrid cloud configured to provide dedicated cloud services to its users. Although Figure 1 The cloud computing system 102 is shown connected to one factory environment 106 via a cloud proxy 120 , but those skilled in the art will appreciate that the cloud computing system 102 can be connected to several factory environments 106 located at different locations via the network 104 .

[0043] In addition, the cloud computing system 102 is connected to user devices 128A-N via the network 104. User devices 128A-N are capable of accessing the cloud computing system 102 to automatically generate simulation models. In an embodiment, the user devices 128A-N include engineering systems capable of running industrial automation applications. User devices 128A-N can be laptops, desktop computers, tablet computers, smartphones, etc. User devices 128A-N are capable of accessing cloud applications (e.g., enabling users to generate simulation models based on user requirements) via a web browser. In addition, users are provided with a quick option to download simulation models from the cloud platform 108 directly into their simulation software running on the user devices 128A-N. Furthermore, user devices 128A-N can install plug-ins for accessing simulation models on the cloud computing system 102 via different simulation software running on the user devices 128A-N.

[0044] The cloud computing system 102 includes a cloud platform 108, a simulation generation system 110, a server 112 including hardware resources and an operating system (OS), a network interface 114, a database 116, and an application programming interface (API) 118. The network interface 114 enables communication between the cloud computing system 102, the factory environment 106, and user devices (one or more) 128A-N. Figure 1 The cloud computing system 102 (not shown) may allow engineers on one or more user devices 128A-N to access simulation models stored in the cloud computing system 102 and perform one or more actions on the simulation models as the same instance. Server 112 may include one or more servers on which an operating system is installed. Server 112 may include: one or more processors; one or more storage devices, such as memory units, for storing data and machine-readable instructions, such as applications and application programming interfaces (APIs) 118; and other peripherals required to provide cloud computing functionality. Cloud platform 108 is a platform that can implement functions such as data reception, data processing, data rendering, and data communication using the hardware resources and operating system of server 112, and deliver the aforementioned cloud services using application programming interfaces 118 deployed on server 112. Cloud platform 108 may include a combination of specialized hardware and software built on the hardware and operating system.

[0045] The cloud agent 120 is used to send runtime asset information to the cloud computing system 102. In addition, the cloud agent 120 is configured to detect one or more anomalies associated with the assets 122, 124A-N, and 126 in the factory environment 106. In addition, the cloud agent is configured to send notification messages to the cloud computing system 102 and the user devices 128A-N. The notification messages include the one or more detected anomalies associated with the assets.

[0046] Cloud database 116 stores information related to plant environment 106 and user device(s) 128A-N. Cloud database 116 is, for example, a Structured Query Language (SQL) data warehouse or a NoSQL (NoSQL) data warehouse. Cloud database 116 is configured as a cloud-based database implemented in cloud computing environment 100, where computing resources are delivered as a service on cloud platform 108. According to another embodiment of the present invention, cloud database 116 is a location on a file system directly accessible by simulation model generation system 110. Database 116 is configured to store asset information, asset parameters, simulation models, error logs, validation results, anomalies associated with assets 122, 124A-N, and 126, mathematical models, relationship matrices, behavioral trends, polynomial graphs, pricing models, user ratings for each simulation model, and the like. Cloud database 116 also maintains simulation model versions.

[0047] Figure 2is a simulation model generation system 110 (such as, Figure 1 The simulation model shown in Figure 1 generates a block diagram of the system). Figure 2 , the simulation model generation system 110 includes a processor(s) 202 , an accessible memory 204 , a communication interface 206 , an input unit 208 , an output unit 210 , and a bus 212 .

[0048] As used herein, processor(s) 202 represent any type of computing circuitry, such as, but not limited to, a microprocessor unit, a microcontroller, a complex instruction set computing microprocessor unit, a reduced instruction set computing microprocessor unit, a very long instruction word microprocessor unit, an explicitly parallel instruction computing microprocessor unit, a graphics processing unit, a digital signal processing unit, or any other type of processing circuitry. Processor(s) 202 may also include an embedded controller, such as a general-purpose or programmable logic device or array, an application-specific integrated circuit, a single-chip computer, or the like.

[0049] The memory 204 may be a non-transitory volatile memory or a non-volatile memory. The memory 204 may be coupled for communication with the processor(s) 202, such as as a computer-readable storage medium. The processor(s) 202 may execute machine-readable instructions and / or source code stored in the memory 204. Various machine-readable instructions may be stored in and accessed from the memory 204. The memory 204 may include any suitable element for storing data and machine-readable instructions, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, a hard drive, a removable media drive for processing compact disks, digital video disks, floppy disks, magnetic tape cassettes, memory cards, and the like. In this embodiment, the memory 204 includes a simulation model generation module 214 stored in the form of machine-readable instructions on any of the aforementioned storage media, and may be in communication with and executed by the processor(s) 202.

[0050] When executed by the processor(s) 202, the simulation model generation module 214 causes the processor(s) 202 to provide simulation model generation in the cloud computing environment 100. In one embodiment, the simulation model generation module 214 causes the processor(s) 202 to receive a request from a user device 128A-N to generate a simulation model. The request includes asset information associated with an asset (such as 122, 124A-B, 126) in the factory environment 106. The asset information includes asset profile data, including asset configuration information, asset physical block information, test data sets, asset alarms, etc. Upon receiving the request, the simulation model generation module 214 causes the processor(s) 202 to generate a simulation model associated with the asset (122, 124A-B, 126) based on the received asset information and pre-stored asset information. The pre-stored asset information is stored in the database 116.

[0051] In an embodiment, a simulation model associated with an asset in the plant environment 106 is generated by determining the behavior of the asset using one or more asset parameters associated with the asset. The one or more asset parameters may include asset characteristics, asset location, asset behavior trends, asset tag information, and / or asset faults. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to generate a plurality of test data associated with the asset's behavior. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to derive a mathematical model associated with the asset based on the test data and the determined asset behavior. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to generate a simulation model for the asset based on the derived mathematical model associated with the asset.

[0052] In one aspect of the embodiment, a mathematical model associated with the asset is obtained by using the asset information to identify the minimum and maximum range values ​​for each asset parameter. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to generate a polynomial graph for each asset parameter that affects the behavior of the asset. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to obtain a relationship matrix for the generated polynomial graph. The relationship matrix indicates the behavior of the asset for each asset parameter. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to obtain a mathematical model associated with the asset based on the relationship matrix.

[0053] Additionally, the simulation model generation module 214 causes the processor(s) 202 to identify a simulation model associated with the asset based on the real-time asset information received from the factory environment 106. In an embodiment, the simulation model associated with the asset is identified by receiving the real-time asset information associated with the asset from the factory environment 106 via the cloud agent 120. Additionally, the simulation model generation module 214 causes the processor(s) 202 to identify a simulation model associated with the asset based on the real-time asset information and predefined rules.

[0054] Additionally, the simulation model generation module 214 causes the processor(s) 202 to output the simulation model associated with the asset on a user interface of the user device 128A-N.

[0055] The simulation model generation module 214 causes the processor(s) 202 to store the simulation model associated with the asset in the cloud database 116 .

[0056] In addition, the simulation model generation module 214 causes the processor(s) 202 to analyze the results of the validation of the simulation model associated with the asset. In addition, the simulation model generation module 214 causes the processor(s) 202 to generate an error log file associated with the simulation model if the validation result is unsuccessful. In addition, the simulation model generation module 214 causes the processor(s) 202 to display the error log file associated with the simulation model on a user interface of the user device (128A-N).

[0057] The simulation model generation module 214 causes the processor(s) 202 to analyze asset information associated with the assets in the plant environment 106. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to determine whether a pre-stored simulation model exists in the cloud database 116 based on the analyzed asset information. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to retrieve a similar simulation model stored in the cloud database 116 if the pre-stored simulation model does not exist in the cloud database 116. Furthermore, the simulation model generation module 214 causes the processor(s) 202 to generate a simulation model template associated with the assets 122, 124A-N, and 126 based on the retrieved similar simulation model and the historical asset information stored in the cloud database 116.

[0058] The simulation model generation module 214 causes the processor(s) 202 to detect one or more anomalies associated with assets in the plant environment 106 using the cloud agent 120 and receive notification messages from the user devices 128A-N. The notification messages include the detected one or more anomalies associated with the assets.

[0059] The simulation model generation module 214 causes the processor(s) 202 to provide a price for each stored simulation model based on the asset information.

[0060] The communication interface 206 is configured to establish a communication session between the one or more user devices 128A-N and the cloud computing system 102. The communication interface 206 allows the one or more engineering applications running on the user devices 128A-N to import / import simulation models into the cloud computing system 102. In an embodiment, the communication interface 206 interacts with an interface on the user devices 128A-N to allow engineers to access simulation models and perform one or more actions on the simulation models stored in the cloud computing system 102.

[0061] Input unit 208 may include an input device capable of receiving one or more input signals (such as user commands for processing the simulation model): a keyboard, a touch-sensitive display, a camera (such as a camera that receives gesture-based input), etc. Furthermore, output unit 210 may be a display unit for displaying a graphical user interface that visualizes the simulation model associated with the asset and also displays an error log associated with each set of actions performed on the simulation model. Bus 212 serves as an interconnection between processor 202, memory 204, input unit 208, and output unit 210.

[0062] Those skilled in the art will appreciate that for a particular implementation, Figure 2 The hardware depicted in the present disclosure may vary. For example, other peripheral devices such as optical drives, local area networks (LANs), wide area networks (WANs), wireless (e.g., Wi-Fi) adapters, graphics adapters, disk controllers, and input / output (I / O) adapters may be used in addition to or in place of the depicted hardware. The depicted examples are provided for purposes of explanation only and are not intended to imply architectural limitations with respect to the present disclosure.

[0063] Those skilled in the art will appreciate that, for the sake of simplicity and clarity, not all structures and operations of all data processing systems suitable for use with the present disclosure are depicted or described herein. Instead, cloud computing system 102 is depicted and described only to the extent that it is unique to the present disclosure or necessary to understand the present disclosure. The remainder of the construction and operation of cloud computing system 102 may conform to any of the various current implementations and practices known in the art.

[0064] Figure 3 is a simulation model generation module 214 (such as, Figure 1 and Figure 2The simulation model generation module 214 includes a data importer module 302, an automatic model generation module 304, a model validation module 306, a model repository 308, a model designer module 310, and an output module 312.

[0065] The data importer module 302 is configured to receive a request from a user device 128A-N to generate a simulation model. The request includes asset information associated with an asset in the factory environment 106. The asset information includes asset profile data, which includes asset configuration information, asset physical block information, test data sets, asset alarms, etc. In addition, the data importer module 302 is configured to detect one or more anomalies associated with the asset in the factory environment 106 using the cloud agent 120 and receive a notification message from the user device 128A-N. The notification message includes the one or more detected anomalies associated with the asset.

[0066] The automatic model generation module 304 is configured to generate a simulation model associated with the asset based on the received asset information and pre-stored asset information in the cloud database 116. In an embodiment, the automatic model generation module 304 first determines the behavior of the asset using one or more asset parameters associated with the asset in the plant environment 106. In an exemplary embodiment, equations describing the behavior of the motion of the major moving parts in a pressure reducing valve are obtained as follows. This example illustrates how to extract one of various valve behaviors from an imported asset profile file. The following second-order ordinary differential equation is formulated to simulate the motion of the valve disc. This example represents one of the behaviors of a pressure reducing valve. Similarly, different equations can be formulated for different behaviors.

[0067] mx + Cx^ + Fs = Ff -Fg + fc

[0068] where m is the mass of the moving part including the disk, disk holder, and rod, x is the acceleration of the disk part along the moving direction, c is the damping coefficient, x^ is the velocity of the disk part, Fs is the spring force acting on the disk and is equal to k(x0 + x(t)), Ff is the flow force acting on the disk part, Fg represents the weight of the disk, and fc is the Coulomb friction.

[0069] In addition, the automatic model generation module 304 generates a plurality of test data associated with the behavior of the asset. In addition, the automatic model generation module 304 obtains a mathematical model associated with the asset based on the test data and the determined asset behavior. To obtain the mathematical model, the automatic model generation module 304 uses the asset information to identify the minimum and maximum range values ​​for each asset parameter. In an exemplary embodiment, a mathematical model is obtained for a DC motor. The motor torque varies with speed. When unloaded, you have maximum speed and zero torque. The load increases the mechanical resistance. The motor begins to consume more current to overcome this resistance, and the speed decreases. The speed, torque, power, and efficiency of the motor are not constant values. Typically, the manufacturer provides the following data as shown in Table 1:

[0070]

[0071] Table 1.

[0072] Based on the above information, the following asset parameters are calculated:

[0073] no=no-load speed

[0074] Io=no-load current

[0075] MH = stall torque

[0076] R=terminal resistance.

[0077] Based on the asset parameters calculated above, minimum and maximum value ranges as well as default values ​​for all parameters are identified.

[0078] In addition, the automatic model generation module 304 generates a polynomial graph for each asset parameter that affects the behavior of the asset. Considering the above example, polynomial graphs are generated for current versus torque and speed versus torque. Table 2 below provides exemplary data points for each of speed, current, torque, power, and efficiency. Figure 8A Plot the resulting graph of one such polynomial.

[0079] Torque speed Current power efficiency (oz-in) (rpm) （A） (watt) （%） 0.025 11, 247.65 0.024 0.208 0.1 0.05 10,786.30 0.048 0.399 71.87

[0080] Table 2.

[0081] In addition, the automatic model generation module 304 obtains a relationship matrix for the generated polynomial graph. The relationship matrix indicates the behavior of the asset for each asset parameter. In the same example as above, the relationships governing the behavior of the asset (e.g., in this case, the motor) are obtained from the physical laws and characteristics of the motor in various situations. The asset data processing modules 130A-N in the user devices 128A-N are configured to obtain the physical laws and characteristics from the asset profile. However, in some cases, not all characteristics may be detectable. In this scenario, the cloud database 116 also has a predefined set of characteristics (historical dataset) for various types of assets, which further assists the automatic model generation module 304 in programmatically obtaining similar matching characteristics associated with the asset.

[0082] Furthermore, the automatic model generation module 304 obtains a mathematical model associated with the asset based on the relationship matrix. In an exemplary embodiment, the mathematical model associated with the motor is obtained based on the relationship matrix between asset parameters associated with the motor (such as current, torque, speed, power, and efficiency). For example, the polynomial equation is obtained by observing the trends in a polynomial graph. In this example, mathematical models for the motor's torque versus speed, torque versus current, torque versus power, and torque versus efficiency are obtained. These mathematical models are obtained by evaluating the motor's speed, current consumption, and efficiency as a function of the motor's torque. These mathematical models are obtained and solved to generate a simulation model.

[0083] Additionally, the automatic model generation module 304 generates a simulation model for the asset based on the obtained mathematical model associated with the asset.

[0084] In an alternative embodiment, the automatic model generation module 304 is configured to analyze asset information associated with assets in the plant environment 106. Based on the analyzed asset information, the automatic model generation module 304 is configured to determine whether a pre-stored simulation model exists in the cloud database 116. Additionally, the automatic model generation module 304 is configured to, if a pre-stored simulation model exists in the cloud database 116, generate a simulation model template associated with the asset based on the pre-stored simulation model and historical asset information stored on the cloud database 116. In an exemplary embodiment, if it is determined that an exact matching simulation model requested by a user of the user device 128A-N does not exist in the model data repository 308, the automatic model generation module 304 generates a simulation model template associated with the asset based on the closest matching simulation model stored in the model data repository 308 and the historical asset information stored on the cloud database 116.

[0085] The model validation module 306 is configured to validate the simulation model associated with the asset based on real-time asset information received from the factory environment 106. Specifically, the model validation module 306 receives real-time asset information associated with the asset from the factory environment 106 via the cloud agent 120. Furthermore, the model validation module 306 validates the simulation model associated with the asset based on the real-time asset information and predefined rules. Furthermore, the model validation module 306 analyzes the validation results of the simulation model associated with the asset. If the validation result is successful, the generated model is output via the output module 312. If the validation result is unsuccessful, an error log file associated with the simulation model is generated and displayed on the user interface of the user device 128A-N.

[0086] Model repository 308 is a database configured to store simulation models associated with assets. Each simulation model is stored along with a user's rating for the model and an associated price. In an exemplary embodiment, if a user clicks the Model Repository button, a search box is provided. For example, if a user enters "reversible motor" in the search box and clicks the Search button, all reversible motors available in a model repository (such as model repository 308) are provided, along with their prices and ratings. If no mathematical model exists in model repository 308, an option is provided to generate a model by uploading an asset profile.

[0087] The model designer module 310 is configured to allow users of the user devices 128A-N to design a simulation model based on user requirements using a component type editor interface (a graphical user interface for manually designing a simulation model). In addition, the model designer module 310 is configured to compile and publish the simulation model.

[0088] The output module 312 is configured to output the simulation model associated with the asset on a user interface of the user device 128A-N.

[0089] Figure 4 1 is a process flow diagram illustrating an exemplary method 400 for providing simulation model generation in a cloud computing environment 100 according to an embodiment of the present invention. At step 402, a request for generating a simulation model is received from a user device 128A-N. The request includes asset information associated with an asset in the factory environment 106. At step 404, a simulation model associated with the asset is generated based on the received asset information and pre-stored asset information in the cloud database 116. At step 406, the simulation model associated with the asset is confirmed based on real-time asset information received from the factory environment 106. At step 408, the simulation model associated with the asset is output on a user interface of the user device 128A-N.

[0090] Figure 5 is a user device 500 (such as, Figure 1 In an embodiment, the user device 500 is similar to Figure 1 The user devices 128A-N are shown in FIG. Figure 5 , user device 500 includes processor(s) 502 , accessible memory 504 , storage unit 506 , communication interface 512 , input-output unit 514 , network interface 516 , and bus 518 .

[0091] As used herein, processor(s) 502 represent any type of computing circuitry, such as, but not limited to, a microprocessor unit, a microcontroller, a complex instruction set computing microprocessor unit, a reduced instruction set computing microprocessor unit, a very long instruction word microprocessor unit, an explicitly parallel instruction computing microprocessor unit, a graphics processing unit, a digital signal processing unit, or any other type of processing circuitry. Processor(s) 502 may also include an embedded controller, such as a general-purpose or programmable logic device or array, an application-specific integrated circuit, a single-chip computer, or the like.

[0092] Memory 504 may be a non-transitory volatile memory or a non-volatile memory. Memory 504 may be coupled for communication with processor(s) 502, such as as a computer-readable storage medium. Processor(s) 502 may execute machine-readable instructions and / or source code stored in memory 504. Various machine-readable instructions may be stored in and accessed from memory 504. Memory 504 may include any suitable element for storing data and machine-readable instructions, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, a hard drive, a removable media drive for processing compact disks, digital video disks, floppy disks, magnetic tape cassettes, memory cards, and the like. In this embodiment, memory 504 includes an asset data processing module 508 stored in the form of machine-readable instructions on any of the aforementioned storage media, and may be in communication with and executed by processor(s) 502.

[0093] The asset data processing module 508 is configured to detect keywords in the asset profile file based on user input / requests. This generates filtered asset information. This filtered asset information is shared with the cloud computing system 102 to generate simulation models associated with the asset(s). The filtered asset information is shared in a specific data file format (such as, for example, JSON). Table 3 below depicts exemplary filtered asset information associated with a flow meter obtained from the flow meter profile file.

[0094] index Parameter name Data Type access Notes EDD 16 Block Object DS 32 read Constant block information 17 Current Mode Unsigned read 18 IM Tag function Visible string Read and write Mapping to PID 22 Target mode Unsigned Read and write Expected device model 23 OrderID Visiblestring(20) read xxx 24 Softwareversion Visiblestring(20) read Xxx4 25 Hardwareversion Visiblestring(20) read Xxx3 26 VendorID unsigned read Xxx2 27 Device ID Visiblestring(20) read Xxx1 28 IM serial number Visiblestring(20) read Xx12 29 Diagnosis octectstring read W12 31 IM tag location Visiblestring(20) R, w Xx122 32 IM revision counter unsigned read 123 33 IM profile ID unsigned read 124 34 IM profile specific type unsigned read xxx

[0095] Table 3.

[0096] In an embodiment, the filtered asset information is sent to the cloud computing system 102 via the wireless network 104 .

[0097] User device 500 also includes a graphical user interface (GUI) 510 configured to display one or more simulation models associated with assets in plant environment 106. GUI 510 also enables a user to search for simulation models stored in cloud database 116 and also design simulation models using a component type editor user interface.

[0098] The storage unit 506 is configured to store asset profile files associated with one or more assets in the factory environment 106 .

[0099] The communication interface 512 is configured to establish a communication session between the one or more user devices 128A-N and the cloud computing system 102. The communication interface 206 allows the one or more engineering applications running on the user devices 128A-N to import / import simulation models into the cloud computing system 102. In an embodiment, the communication interface 206 interacts with the interface port 510 on the user devices 128A-N to allow engineers to access simulation models and perform one or more actions on the simulation models stored in the cloud computing system 102. The network interface 516 helps manage network communications between the user devices 128A-N and the cloud computing system 102.

[0100] Input / output unit 514 may include an input device capable of receiving one or more input signals (such as user commands for processing the simulation model): a keyboard, a touch-sensitive display, a camera (such as a camera that receives gesture-based input), etc. Furthermore, input / output unit 514 may be a display unit for displaying the simulation model associated with the asset, and may also display an error log associated with each set of actions performed on the simulation model. Bus 518 serves as an interconnection between processor 502, memory 504, and input / output unit 508.

[0101] Those skilled in the art will appreciate that for a particular implementation, Figure 5 The hardware depicted in the present disclosure may vary. For example, other peripheral devices such as optical drives, local area networks (LANs), wide area networks (WANs), wireless (e.g., Wi-Fi) adapters, graphics adapters, disk controllers, and input / output (I / O) adapters may be used in addition to or in place of the depicted hardware. The depicted examples are provided for purposes of explanation only and are not intended to imply architectural limitations with respect to the present disclosure.

[0102] Those skilled in the art will appreciate that, for the sake of simplicity and clarity, not all structures and operations of all data processing systems suitable for use with the present disclosure are depicted or described herein. Instead, user device 500 is depicted and described only to the extent that it is unique to the present disclosure or required to understand the present disclosure. The remainder of the configuration and operation of user device 500 may conform to any of the various current implementations and practices known in the art.

[0103] Figure 6 is a process flow diagram illustrating an exemplary method 600 for providing simulation model generation in the cloud computing environment 100 according to another embodiment of the present invention. At step 602, a user at a user device 128A-N requests the generation of a simulation model associated with an asset in the plant environment 106. This is accomplished by the user searching for simulation models using a basic keyword set on the GUI 510. The asset data processing module 508 processes the request, generates filtered asset information associated with the asset for which the simulation model is to be generated, and transmits the filtered asset information and the request to the cloud computing system 102. Once the request is received, at step 604, a mathematical model associated with the asset is obtained based on the asset information. Specifically, the mathematical model is obtained based on test data associated with the behavior of the asset.

[0104] At step 606, a determination is made based on the obtained mathematical model whether the requested simulation model already exists in the cloud database 116. If the requested simulation model already exists in the cloud database 116, then at step 608, such simulation model is retrieved and outputted on the user interface of the user device 128A-N. Alternatively, if the requested simulation model does not exist in the cloud database 116, then at step 610, a further determination is made as to whether the requested simulation model can be automatically generated based on the filtered asset information and pre-stored asset information in the cloud database 116. If the requested simulation model can be automatically generated based on the filtered asset information and pre-stored asset information in the cloud database 116, then at step 612, the requested simulation model is generated based on the filtered asset information and pre-stored asset information in the cloud database 116. Furthermore, at step 614, the generated simulation model is validated based on real-time asset information received from the factory environment 106 via the cloud agent 120. Furthermore, at step 616, the validated simulation model is analyzed, optimized, and reconfigured to ensure that the simulation model is accurate. At step 618 , the simulation model is output on the user interface 510 of the user device 128A-N.

[0105] Alternatively, if it is determined that the requested simulation model cannot be automatically generated based on the filtered asset information and pre-stored asset information in cloud database 116, then, at step 620, a simulation model template associated with the asset is generated based on similar simulation models stored in cloud database 116 and historical asset information stored in cloud database 116. At step 622, the simulation model template is validated based on the predefined rules and the real-time asset information. At step 624, a further determination is made as to whether validation of the simulation model template was successful. If validation of the simulation model template was successful, then at step 628, the simulation model template is stored in cloud database 116 and simultaneously displayed on the user interface of user device 128A-N. If validation of the simulation model template was unsuccessful, then at step 626, an error log for the simulation model template is displayed on the user interface of user device 128A-N.

[0106] Figure 7A -B is a screenshot of an exemplary graphical user interface for providing simulation model generation according to an embodiment of the present invention. Figure 7A , a web-based user interface 700a at a user device 128A-N is depicted. The web-based user interface 700a allows a user at the user device 128A-N to import / export simulation models, search for simulation models already stored in the cloud database 116, design, compile, and publish simulation models based on asset information obtained from an asset profile file, and also determine the status of validation of a simulation model. Figure 7B , the graphical user interface 700b includes a search field 702b for enabling a user to search for and select simulation models in the online cloud database 116. In addition, the graphical user interface 700b includes price and rating tag field information associated with each selected simulation model.

[0107] Figure 8A -E is a graphical representation illustrating a method for obtaining a mathematical model associated with an asset based on test data and determined asset behavior according to an embodiment of the present invention. Figure 8A In FIG, a polynomial graph 800a generated from an imported sample data set points associated with an asset is depicted. The polynomial graph depicts the behavioral trends of asset parameters such as torque, current, power, speed, and efficiency. Figure 8B In , a polynomial graph of the speed and torque values ​​of the motor is plotted. Using this graph 800b, a relationship matrix between speed and torque is obtained and from this the mathematical model for the asset is calculated. Similarly, in Figure 8C In FIG, the torque and current values ​​of the motor are plotted. Using this graph 800c, the relationship matrix between torque and current is obtained, and the mathematical model for the asset is calculated from it. In addition, in Figure 8DIn , the power and torque values ​​of the motor are plotted. Using this graph 800d, the relationship matrix between torque and power is obtained and from this the mathematical model for the asset is calculated. Similarly, in Figure 8E , the efficiency and torque of the motor are plotted. Using this graph 800e, a relationship matrix between torque and efficiency is obtained and from this the mathematical model for the asset is calculated.

[0108] The present invention can take the form of a computer program product comprising program modules accessible from a computer-usable or computer-readable medium storing program code for use by or in conjunction with one or more computers, processors, or instruction execution systems. For the purposes of this description, a computer-usable or computer-readable medium can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or apparatus or device), or any of these and their own propagation media (when a signal carrier wave is not included in the definition of a physical computer-readable medium), including semiconductor or solid-state memory, magnetic tape, removable computer diskettes, random access memory (RAM), read-only memory (ROM), rigid magnetic disks, and optical disks (such as compact disk read-only memory (CD-ROM), compact disk read / write, and DVD). As will be appreciated by those skilled in the art, the processors and program code used to implement each aspect of the technology can be centralized or decentralized (or a combination thereof).

[0109] Although the present invention has been described in detail with reference to certain embodiments, it should be understood that the present invention is not limited to those embodiments. In view of this disclosure, it will be apparent to those skilled in the art that many modifications and variations will exist without departing from the scope of the various embodiments of the present invention, as described herein. The scope of the present invention is therefore indicated by the following claims, rather than by the preceding description. All changes, modifications, and variations that fall within the meaning and scope of the equivalents of the claims will be deemed to be within their scope. All advantageous embodiments claimed for protection in the method claims may also be applied to system / device claims.

Claims

1. A method for providing simulation model generation in a cloud computing environment, comprising: A request for generating a simulation model is received by a processor (202) from a user device, wherein The request includes asset information associated with an asset in the factory environment, and The asset in question is industrial equipment in a factory environment; Generating, by the processor (202), a simulation model of the asset based on the received asset information and pre-stored asset information in the cloud database (116), wherein generating the simulation model associated with the asset (122, 124A-N, and 126) based on the received asset information and the pre-stored asset information includes: determining, by a processor (202), a behavior of an asset (122, 124A-N, and 126) using one or more asset parameters associated with the asset in the plant environment (106); generating, by a processor (202), a plurality of test data associated with behavior of the assets (122, 124A-N, and 126); A mathematical model associated with the assets (122, 124A-N, and 126) is obtained based on the test data and the determined behavior of the assets (122, 124A-N, and 126) by the following steps: Using the asset information, identify minimum and maximum range values ​​for each asset parameter; generating a polynomial graph of each asset parameter that affects the behavior of the asset (122, 124A-N, and 126); obtaining a relationship matrix of the generated polynomial graph, wherein the relationship matrix indicates the behavior of the asset (122, 124A-N, and 126) for each asset parameter; and obtaining a mathematical model associated with the assets (122, 124A-N, and 126) based on the relationship matrix; and generating a simulation model for the asset (122, 124A-N, and 126) based on the obtained mathematical model associated with the asset (122, 124A-N, and 126); receiving, by a processor (202) via a cloud agent (120), real-time asset information associated with assets (122, 124A-N, and 126) from a plant environment (106); identifying, by a processor (202), simulation models associated with assets (122, 124A-N, and 126) based on real-time asset information received from a plant environment (106); If the result of the validation of the simulation model is successful, the simulation model associated with the asset (122, 124A-N, and 126) is outputted by the processor (202) on a user interface of the user device (128A-N); and If the result of the validation of the simulation model is unsuccessful, the processor (202) outputs a plurality of error log files of the simulation model.

2. The method (400) of claim 1, further comprising: Simulation models associated with assets (122, 124A-N, and 126) are stored in a cloud database (116).

3. The method (400) of claim 1, wherein the one or more asset parameters include asset characteristics, asset location, asset behavior trends, asset tag information, and / or asset faults.

4. The method (400) of claim 1, wherein validating the simulation model associated with the asset (122, 124A-N, and 126) based on real-time asset information received from the plant environment (106) comprises: A simulation model associated with the asset (122, 124A-N, and 126) is identified based on real-time asset information and predefined rules.

5. The method (400) according to any one of claims 1 to 4, further comprising: analyzing results of validation of simulation models associated with assets (122, 124A-N, and 126); and If the result of the confirmation is unsuccessful, the plurality of error log files associated with the simulation model are generated.

6. The method (400) according to any one of claims 1 to 4, further comprising: analyzing asset information associated with assets (122, 124A-N, and 126) in a plant environment (106); determining whether a pre-stored simulation model exists in a cloud database (116) based on the analyzed asset information; If the pre-stored simulation model does not exist in the cloud database (116), retrieving a similar simulation model stored in the cloud database (116); and A simulation model template associated with the asset (122, 124A-N, and 126) is generated based on the retrieved similar simulation models and historical asset information stored on the cloud database (116).

7. The method (400) according to any one of claims 1 to 4, comprising: detecting, using a cloud agent (120), one or more anomalies associated with assets (122, 124A-N, and 126) in a factory environment (106); and A notification message is received from a user device (128A-N), wherein the notification message includes one or more detected anomalies associated with an asset (122, 124A-N, and 126).

8. The method according to any one of claims 1 to 4, further comprising: Provides a price for each stored simulation model based on asset information.

9. A simulation model generation system (110), comprising: one or more processors (202); and A memory (204) coupled to the one or more processors (202), wherein the memory (204) includes a simulation model generation module (214) stored in the form of machine-readable instructions executable by the one or more processors (202), wherein the simulation model generation module (214) is capable of performing the method of any one of claims 1-8.

10. A cloud computing system (102), comprising: Server (112); and A cloud platform (108) comprising a simulation model generation system (110) stored therein in the form of machine-readable instructions and executable by the server (112), wherein the simulation model generation system (110) is configured to perform the method according to any one of claims 1 to 8.

11. A cloud computing environment (100), comprising: The cloud computing system (102) as claimed in claim 10; a plant environment (106) comprising one or more assets (122, 124A-N, and 126) and a cloud agent (120) capable of transmitting asset information associated with the one or more assets (122, 124A-N, and 126) to a cloud computing system (102); and At least one user device (128A-N) is communicatively coupled to the cloud computing system (102) and the factory environment (106) via the network (104).

12. A computer program product comprising machine-readable instructions stored therein, which, when executed by one or more servers (112), cause the one or more servers (112) to perform the method of any one of claims 1-8.

Images