Systems and methods for monitoring industrial plant equipment - Patents.com

Abstract

A monitoring system for monitoring industrial plant equipment is provided. The system comprises a first layer (100) having a plurality of sensors (110-150) configured to detect parameters of equipment (20, 30) of the industrial plant (1). The system also comprises a second layer (200) configured to implement process control based on data from the first layer (100) and an interface (600) coupled to the first and / or second layer (100, 200) configured to receive data from the first and / or second layers (100, 200) and to pre-process the received data. The interface (600) comprises an analyzer (610) configured to add metadata to data from the plurality of sensors (110-150). The interface (600) is configured to analyze the received data and output the processed data to a data sink (530). The interface is configured to allow only one-way data communication to the data sink (530).

Description

[Technical field]

[0001] FIELD OF THEINVENTION The present invention relates to a system and method for monitoring industrial plant equipment. [Background technology]

[0002] 2. Background of the Invention Industrial process plants, such as chemical production, are highly security-sensitive production environments. Industrial plants, such as chemical plants, usually include multiple assets for producing products. Such plants have multiple sensors distributed for data collection as well as monitoring or control purposes. Thus, production, such as chemical production, results in huge amounts of data. Therefore, there is great interest in applying new techniques in cloud computing and big data analytics. However, unlike other manufacturing industries, process industries are subject to very high security standards. For this reason, computing infrastructures are usually compartmentalized with highly restrictive access to monitoring and control systems. Therefore, latency and availability considerations are against simply migrating current embedded control systems to cloud computing systems or data analytics systems, etc. Thus, the challenge is to bridge the gap between highly proprietary industrial manufacturing systems and cloud technologies. Summary of the Invention [Means for solving the problem]

[0003] Summary of the Invention It is an object of the present invention to provide a monitoring system and method for monitoring industrial plant equipment, which allows data from the industrial plant to be analysed in a more flexible way.

[0004] According to one aspect of the present invention, a monitoring system for monitoring an industrial plant equipment is provided. The system comprises a first layer having a plurality of sensors configured to detect parameters of the equipment of the industrial plant. The system further comprises a second layer configured to implement a process control system based on data from the first layer. The system also comprises an interface coupled to the first and / or second layer configured to receive data from the first and / or second layer and to pre-process the received data. The interface comprises an analyzer configured to add metadata to the data from the plurality of sensors. The interface is configured to analyze the received data and output the processed data to a data sink, such as a central data sink. The interface is configured to allow only one-way data communication to the data sink. Providing an interface to the system for monitoring the industrial plant equipment enables secure extraction and monitoring of data from the industrial plant equipment. The data sink may be implemented as a cloud-based data sink, such as a cloud-based service.

[0005] In particular, the analyzer of the interface may be configured to analyze data received as incoming data and output the analyzed data, optionally including added metadata, as processed data to a data sink via one-way data communication.

[0006] According to one embodiment of the present invention, the interface comprises an analyzer configured to analyze the received data and add metadata, a data buffer, a key performance indicator KPI calculator configured to determine at least one key performance indicator based on the data in the buffer, and an upload selector configured to select data from the received data to be transferred to the data sink.

[0007] The KPI calculator allows to determine key performance indicators that can be transferred to the data sink. It is thus possible to significantly reduce the amount of data that needs to be transferred to the data sink without losing much information from the data. This also results in a significant reduction in the amount of traffic between the interface, which can be implemented as a cloud service, and the data sink.

[0008] According to a further embodiment of the invention, the metadata comprises time information (in particular timestamp or time shift information) and / or information about the respective sensor which detected the data.

[0009] If the metadata includes time information, it is also possible in a system for monitoring industrial plant equipment to compare data from different industrial plant equipment or from different sensors in or for the industrial plant equipment. Due to the sensor related metadata (sensor ID, sensor type, etc.), different types of sensors can be analyzed even if they are distributed across different industrial plants or different subdivisions of an industrial plant.

[0010] According to a further embodiment of the invention, the second layer comprises a condition monitoring system and / or a machine protection system. The interface is configured to analyze data from the condition monitoring system and / or the machine protection system, add metadata to output data, process the data to reduce the amount of data if necessary, and output the processed data to a data sink. In particular, the output data may be data output by the condition monitoring system and / or the machine protection system. In particular, the processed data may be output data, optionally provided together with metadata, if indicated by the analysis.

[0011] According to a further aspect of the invention, there is provided a method for monitoring an industrial plant equipment by a monitoring system comprising a plurality of sensors for detecting parameters of the equipment of the industrial plant in a first layer. In a second layer of the monitoring system, a process control system base is implemented based on data from the first layer. In an interface, data is received from the first and / or second layers and the received data is pre-processed. In an analyzer in the interface, metadata is added to the data from the plurality of sensors. The received data is analyzed in the interface and the processed data is output to a data sink. The interface is configured to allow only one-way data communication to the data sink.

[0012] According to one aspect of the invention, a computer program for monitoring a product processing apparatus, the computer program comprising code means for causing the system to carry out the method described above, when the program is executed on a computer controlling the system.

[0013] According to one embodiment of the present invention, a system for monitoring industrial plant equipment is provided. The system comprises a first layer having a number of sensors measuring parameters of components of the industrial plant. The system also comprises a second layer related to a process control system of the industrial plant. Data from the sensors in the industrial plant are extracted and provided together with metadata such as time information (such as a timestamp) and / or information about the sensors (such as name, type, ID). The data and optionally the metadata are pre-processed to reduce the amount of data, if necessary. The data is then transferred to a cloud service where it can be analyzed or further processed. In other words, existing data in the industrial plant is reused for analytical purposes.

[0014] According to one embodiment of the present invention, a method is provided for pre-processing or preparing data for subsequent processing outside of the first and second layers of the automation architecture. In particular, data from various sensors across a plant can be harmonized (with respect to time codes or time information and other metadata) and collected in a location, such as a central location in the cloud, for further in-depth analysis.

[0015] According to an aspect of the present invention, an industrial plant may comprise a control system for controlling the operation of elements of the industrial plant. The industrial plant comprises a number of sensors for monitoring equipment of the industrial plant. The industrial plant may also comprise a condition monitoring system CMS, a machine protection system MPS, and / or a process information management system PIMS. The monitoring system may use or share hardware of the control system of the industrial plant. It should be noted, however, that the monitoring system may only receive data from the control system (such as data from sensors, condition monitoring system, machine protection system, and / or process information management system). The monitoring system according to an embodiment of the present invention cannot and is not permitted to transmit data to sensors or other systems of the control system. Furthermore, the monitoring system cannot and is not permitted to affect the operation of the control system. The monitoring system according to an embodiment of the present invention simply uses data from sensors, condition monitoring system CMS, machine protection system MPS, process information management system PIMS for monitoring purposes. Thus, the respective data may first be used for the control of the industrial plant and then also reused for monitoring purposes.

[0016] Although the monitoring system may share hardware with the control system, the operation of the monitoring system does not interact with or affect the industrial plant's control system.

[0017] According to an embodiment of the present invention, the equipment monitored by the sensor may be a rotating machine such as a motor, a centrifuge, or the equipment may be a reciprocating pump, a compressor, etc. The equipment may also be a fractionation or distillation column, a chemical reactor, and / or a laboratory device. The equipment may also be a process plant, a flare stack, a combustion chamber, a filling plant, a packaging plant, or a dryer.

[0018] The control system of an industrial plant may be implemented as a pyramid according to the automation pyramid or the NAMUR pyramid.

[0019] The interface may be implemented as an edge unit (e.g., placed at the edge of the system to reduce data traffic with a data sink in the cloud) or may share the hardware resources of an edge unit.

[0020] Edge computing, performed for example by Internet of Things IoT edge units, refers to distributed computing power located in the vicinity of data sources. Thus, instead of locating computing power exclusively in the cloud, multiple edge units can be provided in or near industrial plants. This is advantageous as it can reduce the required bandwidth towards the cloud and also reduce processing latency.

[0021] It is to be understood that the above-mentioned aspects, in particular the monitoring system of claim 1, the method of claim 9 and the computer program of claim 10, have similar and / or identical preferred embodiments, in particular as defined in the dependent claims.

[0022] It shall also be understood that a preferred embodiment of the invention may also be any combination with the dependent claims or the respective independent claims of the above embodiments.

[0023] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter. [Brief description of the drawings]

[0024] [Figure 1] FIG. 1 is a schematic diagram illustrating a system for monitoring an industrial plant. [Diagram 2] FIG. 2 is a schematic diagram of a portion of the system of FIG. 1. [Diagram 3] FIG. 2 illustrates a portion of the first and second layers of the system of FIG. 1. [Figure 4] FIG. 2 is a schematic block diagram of an interface according to an embodiment of the present invention; [Figure 5A] 1 is a graph showing unshifted raw data of a sensor. [Figure 5B] 1 is a graph showing shifted raw data. [Figure 6] 1 is a graph showing raw data. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0025] Detailed Description of the Embodiments In an industrial plant (e.g., a chemical process plant), a large number of devices are typically used to produce a desired product, the parameters of which must be sensed and the devices are controlled by a control system based on the sensed parameters.

[0026] For example, industrial production of chemical processes usually starts with an upstream product, which is used to generate further downstream products. The value chain production through various intermediate products to the final product is highly constrained and based on separate infrastructures. This is a disadvantage for the introduction of new technologies such as the Internet of Things loT, cloud computing, and big data analytics. Process industries are subject to very high standards, especially with regard to availability and security. Therefore, the computing infrastructure is usually unidirectional and isolated, with highly constrained access to the monitoring and control systems of the chemical plants. In general, chemical production plants are built in an isolated manner with different layers within the enterprise architecture to achieve functional separation between operational technology and information technology solutions. These layers are described in the automation pyramid or the NAMUR pyramid.

[0027] The industrial plant may be embodied as a chemical plant, a chemical processing plant, or a chemical product processing plant.

[0028] FIG. 1 is a schematic diagram illustrating a system for monitoring an industrial plant. A first layer 100 is related to a physical process in the plant 100. In the first layer 100, a number of sensors 110, 120 are arranged to measure or determine various parameters of the equipment 20, 30 in the plant. Furthermore, the first layer 100 may be related to intelligent devices for sensing and manipulating the physical process, for example via process sensors, analyzers, and actuators. A second layer 200 is related to a process control system for the industrial plant 100 or a part of the industrial plant 100. The second layer 200 may comprise a number of processing units, such as a condition monitoring system CMS 210, a machine protection system MPS 220, and / or an analysis unit 230 that may perform analysis operations. The condition monitoring system CMS 210, the machine protection system MPS 220, and / or the analysis unit 230 use data from the sensors 110, 120 of the first layer 100 as inputs for performing their respective functions or processing operations. The analytics unit 230 may be implemented as an Internet of Things device, which may include analytics components, Internet of Things IoT edge units, and containers. Thus, the second layer 200 is used to supervise, monitor, and control the physical processes in the industrial plant. Real-time control and software, process information management systems PIMS, human machine interfaces HMI, supervisory and data acquisition SCADA software may also be part of the second layer 200.

[0029] The third layer 300 relates to operational control systems, i.e. manufacturing operational systems for managing the production workflow to produce the desired product. Here, a process information management system PIMS 330 may be provided. Furthermore, a condition monitoring system 320 and / or a further analysis unit 310 may be provided. The analysis unit 310 may be implemented as an Internet of Things edge device and may comprise an analysis component, an Internet of Things IoT edge unit, and a container. Furthermore, batch management, manufacturing execution / operations management systems (MES / MOMS), laboratory, maintenance and plant performance management systems, data historians and related middleware may be further components of the third layer 300. The time frame for control and monitoring may be shifts, hours, minutes, seconds.

[0030] The fourth layer 400 relates to business logistics systems for managing the business related activities of the manufacturing operation. Enterprise Resource Planning ERP is the primary system and may establish the basic plant production schedule, material usage, shipment, inventory layers. Time frames may be months, weeks, days, shifts.

[0031] The fifth layer 500 relates to cloud services 500. The cloud services 500 may comprise one or more data sinks 530, which may be implemented as cloud servers or cloud services. The data sink 530 may be a central data sink or multiple distributed or mirrored data sinks.

[0032] Optionally, a monitoring system according to an embodiment of the invention may share or reuse parts of a control system without affecting the control system.

[0033] The above layers may implement strict one-way communication protocols that do not allow data inflow to the first layer 100. In addition to such an automation structure or architecture, an external company network or the corporate external Internet may be provided, but is not coupled to the first, second and third layers due to security considerations. In this context, the challenge is to leverage the advantages of cloud computing and big data while still ensuring the established advantages of the existing architecture, namely high availability and reliability of the lower layer systems (first layer 100) and cybersecurity.

[0034] According to one embodiment of the present invention, an interface 600 is provided, which can operate independently from the processing units 210, 220, 230 in the second layer 200 and allows data (output data) from the sensors 110, 120 or the processing units 210, 220, 230 in the second or third layer 300 to be used for analytical purposes. This data is not used by the monitoring system to control or influence the operation of the existing automation architecture (first, second, third and fourth layers 100-400). The improved interface 600 is provided for extracting data and parameters from the devices 20, 30 of an industrial plant, processing the data as required and outputting the data to a data sink 530, which may be implemented in the fourth layer 400 or the fifth layer 500. The interface 600 only allows one-way communication from the sensors to the data sink 530.

[0035] According to an embodiment of the present invention, the interface 600 may use or share existing hardware or services in the second layer 200 or the third layer 300 of the control system (i.e., the automation system) to perform its operations. The interface 600 may be used to extract data from various sensors sensing parameters from various types of devices 20, 30 and / or from various processing units in the second or third layers 200, 300, and store the data in the data sink 530. However, before the data can be stored in the data sink 530, the data must be analyzed, pre-processed, and / or possibly harmonized (e.g., with respect to their time information). The functionality and operation of the interface 600 is independent of the operation of the automation architecture.

[0036] The core process system provides process or asset specific data of an industrial plant, e.g., a chemical plant contextualizes the process or asset specific data of the chemical plant. Further, the plant specific data of the (chemical) plant may be provided to the fifth layer via interface 600. Here, plant specific data may refer to contextualized process or asset specific data. The process or asset specific data may include values, qualities, times, units of measure, asset identifiers.

[0037] Through contextualization, further context can be added, such as plant identifier, plant type, reliability indicators, or alarm limits of the plant. In a further step, the technical asset structure of one or more plants or sites and other asset management (e.g., asset networks) and even application context (e.g., model identifiers, third party exchanges) can be added.

[0038] The fifth layer 500 may be a computing or cloud environment that provides virtualized computing resources, such as data storage and computing power. Plant-specific data from one or more chemical plants may be provided to an external service. Such data may be provided in real time or on demand. Furthermore, data transfer to and / or from external services may be performed in real time or on demand. The fifth layer 500 may be used to store, contextualize, or aggregate plant-specific data from two or more chemical plants and / or to store historical data from two or more chemical plants. In this way, data storage may be externalized, the required on-premise storage capacity may be reduced, and historical transfer may be made redundant. The fifth layer 500 may comprise a data sink 530.

[0039] Additionally, the interface 600 and / or the fifth layer 500 may be configured to exchange data with third party management systems, e.g., via integration of third party external processing layers, enable visualization of data, enable computing process workflows, enable data calculations, enable application program interface APIs to access data, enable metadata for data storage, transfer, and calculations, provide an interactive plant data work environment for users, e.g., operators, and verify and improve data quality.

[0040] The fifth layer 500 may be configured as a centralized cloud computing platform. The fifth layer 500 may be configured as a manufacturing data workspace with full data integration across multiple plants, including transport and streaming of manufacturing data history, collection of all data from all edge components. In this way, full contextualization of all lower layer contexts may be integrated within and on the fifth layer 500 for multiple plants. In this way, the fifth layer 500 may be further configured to run cloud-native apps, connect with external PaaS and Saas tenants, integrate machine learning with manufacturing data and processes, deploy training tests, and / or visualize data, access and orchestrate apps.

[0041] The above system architecture allows for a bottom-up contextualization concept, where all information available on the lower layers may already be added as attributes to the data, so that the context of the lower layers is not lost. Here, the first layer 100 as the lowest context layer may contain measurements and data that are contextualized with respect to the parameters on which the measurements were performed. The second or third layers 200, 300 may be further contextualized by further adding tags related to the individual chemical plants.

[0042] The contextualization concept may cover at least two basic types of context. One type may be a functional location in a production environment with multiple chemical plants. This may cover information about what and where this data point represents inside the production environment. Examples are association with a functional location, attributes for which physical asset the data was collected, etc. This context may be beneficially used for later applications to explain which data is available for which plants and assets.

[0043] FIG. 2 is a schematic diagram of a part of the system of FIG. 1. In FIG. 2, a number of sensors 110, 120 belonging to the first layer 100 and a number of processing units 210, 220, 230, 240 from the second layer 200 are shown. The sensors 110, 120 output measurement data, which are input to input / output units (IO cards) 211, 221, 231 of the CMS unit 210, the MPS unit 220 or the analysis unit 230, respectively. The IO units 211, 221, 231 can add metadata to the measurement data from the sensors 110, 120. This metadata can include time information, such as a timestamp. The time information, for example in the form of a timestamp, can be received from a Network Time Protocol NTP server 800. The measurement data together with their metadata can be processed in the units of the second layer 200. The outputs of these units 210-230 can be forwarded to an interface 600. Here, the data may be analyzed, pre-processed, and / or harmonised before the data is forwarded to a data sink 530 in the fourth layer 400 or the fifth layer 500. The interface 600 may share processing resources of, for example, the analysis units 230 or 310. Alternatively, the interface 600 may have dedicated resources. The interface 600 may have a digital output 601 and / or an analog output 602 towards the data sink 530.

[0044] The metadata includes time information from a timestamp generator, which may generate timestamps using the Network Time Protocol NTP from an NTP server 800.

[0045] FIG. 3 shows a part of the first and second layers of the system of FIG. 1. Here, sensors 130-150 are provided to measure parameters of equipment in an industrial plant. Data from the sensor 150 is forwarded to a data splitter 151. An output of the data splitter 151 is forwarded to a machine protection system MPS unit 220, which uses the data to perform machine protection actions. An output of the data splitter 151 is forwarded to an IO unit 211, where optionally a timestamp may be introduced as metadata. An output of the sensor 140 is received by the IO unit 241. The interface 600 may for example be implemented as an industrial PC IPC, which may be coupled to the IO unit 241 and / or the IO unit 211 and may add metadata (in the form of a timestamp). The IPC 600 may be coupled to a timestamp generator 800 (like an NTP server) to generate a timestamp and introduce it as metadata. The interface 600 may for example share processing resources of the analysis unit 230.

[0046] The units of the first, second and third layers 100, 200, 300 are data sources and may be a Machine Protection System (MPS), a Condition Monitoring System (CMS) or an industrial PC. In addition, the output of a sensor (via an I / O unit) may be a data source. Furthermore, a Process Information Management System (PIMS) or a Laboratory Information Management System (LIMS) may also be a data source.

[0047] Fig. 4 shows a schematic block diagram of an interface according to an embodiment of the present invention. The interface 600 may receive output data from the processing units 210, 220, 230, from the second level 200 or from the sensors 110-150 in the first level 100. The interface 600 optionally comprises a data converter 605, an analyzer 610, a (ring) buffer 620, a key performance indicator KPI calculator 650, an upload selector 630 and an uploader 640. The analyzer 610 is provided to analyze the data from the input sources 210, 220, 230 and add metadata if necessary. The metadata 10 may be time information such as a timestamp. The time information may also relate to a time shift, i.e. a shift in timing information of the received data. This may be necessary if the respective data is to be compared or analyzed against other data. The received and possibly analyzed data may be stored in the (ring) buffer 620. If the amount of data from a particular source is too large, the KPI calculator 650 may calculate key performance indicators KPIs based on the data in the buffer 620. The KPI calculator 650 may forward the KPIs (e.g., instead of the entire data from a particular source) to the data sink 530. If the amount of data is not too large, the upload selector may select the data to be uploaded to the data sink 530. This data may be uploaded by the uploader 640.

[0048] The sensors 110-150 may be high frequency HF sensors, such as temperature sensors, pressure sensors, current sensors, position sensors, vibration sensors, and the like.

[0049] The interface 600 may be implemented or integrated in the analyzers 230 and / or 310. That is, the interface may share processing hardware with the units 230, 310. The interface may receive data from the first layer 100 (sensors 110-150), from the second layer (CMS 210, MPS 220) and / or from the third layer 300 (CMS 320, PIMS 330). It should be noted that the interface 600 may receive data only from within the first layer, second layer or third layer and not from external sources. The interface 600 may receive raw data (sensor data) as input from sensors and / or from processing units 210, 220, 230, 240 in the second layer 200. Depending on the processing units 210-240, the interface 600 may also only receive key performance indicators KPIs. The protocol of the data may be a proprietary protocol. Data can be received as analog or digital signals (Modbus, OPC-UA).

[0050] The interface 600 may analyze the incoming data. If the amount of data from one of the data sources is too large, the amount of data must be reduced, for example by determining key performance indicators, and the KPIs must be forwarded to the data sink 530 together with metadata instead of the raw data.

[0051] In the data sink 530, the input data may be analyzed using, for example, big data techniques.

[0052] The sensors 110-150 can be high frequency HF sensors, such as temperature sensors, pressure sensors, current sensors, position sensors, vibration sensors, or optical sensors (such as video cameras, bars, optical fibers, etc.).

[0053] Figure 5A shows a graph representing unshifted raw data, and Figure 5B shows a graph with shifted raw data. The signal in Figure 5A relates to a high frequency raw data signal of a machine element (such as a rotating machine) over time.

[0054] FIG. 5B shows another type of raw data signal of the same machine over time. Figure 6 shows a graph representing the raw data, where the signals have been shifted based on the timestamp or time-shift information in the metadata and combined on the same time axis.

[0055] A single unit device or system may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Procedures such as analyzing data and adding metadata to data performed by one or more units or devices can be performed by any other number of units, devices, systems. These procedures may be implemented as program code means of a computer program and / or as dedicated hardware. The computer program product may be distributed by storage / media on any suitable medium, such as an optical storage medium or a solid medium supplied together with or as part of other hardware, but also in other forms, such as via the Internet or other wired or wireless telecommunication systems.

[0056] Any reference signs in the claims shall not be construed as limiting the scope. [Explanation of symbols]

[0057] List of References 10 Metadata 20 equipment 30 equipment 100 1st Layer 110 Sensors 120 Sensors 130 Sensors 140 Sensors 150 Sensors 151 Data Splitter 200 Second Layer 210 Condition Monitoring System CMS 211 Input / Output Unit (IO Card) 220 Machine Protection System 221 Input / Output Unit (IO Card) 230 Analysis Units 231 Input / Output Unit (IO Card) 240 Processing Unit 241 units 300 Third Layer 310 Analysis Unit 320 Condition Monitoring System CMS 330 Process Information Management System 400 The Fourth Layer 500 5th Layer 530 Data Sink 600 Interface 601 Digital Output 602 Analog Output 605 Data Converter 610 Server 620 Buffer 630 Upload Selector 640 Uploader 650 Calculator 800 Servers CMS Condition Monitoring System ERP Enterprise Resource Planning IPC Industrial PC KPI Key Performance Indicator MPS Machine Protection System NTP Network Time Protocol PIMS Process Information Management System

Claims

1. A monitoring system for monitoring an industrial plant device (20, 30), comprising: a first layer (100) having a number of sensors (110-150) configured to detect parameters of devices (20, 30) of an industrial plant (1); a second layer (200) configured to implement a process control system based on data from the first layer (100); an interface (600) coupled to the first and / or second layers (100, 200) configured to receive data from the first and / or second layers (100, 200) and to pre-process the received data; Equipped with the interface (600) comprises an analyzer (610) configured to analyze the data from the first and / or second layers (100, 200) and to add metadata to the data from the plurality of sensors (110-150); the interface (600) is configured to analyze the received data and output the processed data to a data sink (530); the interface (600) is configured to permit only one-way data communication to the data sink (530); A monitoring system for monitoring an industrial plant device (20, 30).

2. the interface (600) further comprises a data buffer (620), a key performance indicator calculator (650) configured to determine at least one key performance indicator based on the data in the buffer (620), and an upload selector (630) configured to select data from the received data to be transferred to the data sink (530), 2. A monitoring system for monitoring an industrial plant device according to claim 1.

3. the metadata (10) including time information and / or information about the sensor that detected the data; A monitoring system for monitoring an industrial plant apparatus according to claim 1 or 2.

4. The time information includes a time stamp or time shift information. A monitoring system for monitoring an industrial plant device according to claim 3.

5. the second layer (200) comprises a condition monitoring system (210) and / or a machine protection system (220); the interface (600) is configured to analyze the data from the condition monitoring system (210) and / or the machine protection system (220), add metadata to their output data, process the data to reduce the amount of data if necessary, and output the processed data to the data sink (530). A monitoring system for monitoring an industrial plant apparatus according to any one of claims 1 to 4.

6. The interface (600) is implemented as an Internet of Things edge unit. A monitoring system for monitoring an industrial plant apparatus according to any one of claims 1 to 5.

7. the interface (600) is configured to perform a time shift on the data from the first layer (100) based on time shift information in the metadata to harmonize the data with data from other sensors. A monitoring system for monitoring an industrial plant apparatus according to any one of claims 4 to 6.

8. 1. An industrial plant comprising: At least one industrial plant device (20, 30); a control system having a first layer (100) having a plurality of sensors (110-150) configured to detect parameters of the industrial plant equipment (20, 30) and a second layer configured to implement a process control system based on data from the first layer (100); A monitoring system for monitoring an industrial plant installation (20, 30) according to any one of claims 1 to 7; An industrial plant comprising:

9. A method for monitoring devices (20, 30) of an industrial plant by a monitoring system comprising a first layer (100) having a number of sensors (110-150) for detecting parameters of the devices (20, 30) in the industrial plant, a second layer (200) in which a process control system is implemented based on data from the first layer (100), and an interface (600) coupled to the first and / or second processing layers (100, 200), comprising: receiving data from the first and / or second layers (100, 200) via the interface (600); pre-processing the data received by said interface (600); adding metadata to the data from the plurality of sensors by an analyzer (610) in the interface (600); analyzing the received data by the interface (600) and outputting the processed data to a data sink (530); The method includes the steps of: the interface (600) permits only one-way data communication to the data sink (530); method.

10. A computer program for monitoring industrial plant equipment, comprising code means for causing a monitoring system according to any one of claims 1 to 7 to carry out the method according to claim 9, when said program is run on a monitoring system.

Images