Contextualized engine for industrial data

By extracting and aggregating sensor data from industrial facilities, generating operational data and processing it using a contextualized engine, the problem of monitoring and optimization complexity in industrial batch processing is solved, fast and accurate data analysis and decision support are achieved, and industrial performance and efficiency of the facility.

CN119013633APending Publication Date: 2024-11-22OPTIMISTIK
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202380033906.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-04-16
Filing Date
2023-03-22
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art is difficult to provide global processing methods in industrial batch processing, resulting in complex and time-consuming monitoring, control and optimization processing, and lack of effective industrial tools to simplify and facilitate the processing of sensor data and monitoring, control and optimization of devices.

Method used

By extracting state data from the operation stage and generating traceability data, aggregating state data and traceability data to generate operation data, using a contextualized engine to process sensor data in a standardized manner, simplifying the monitoring, control and optimization of sensor data, and The upstream and downstream operation data are linked to genealogy data to realize data merging and analysis.

Benefits of technology

Reduces the time, effort and cost required to improve the performance of industrial facilities, provides accurate real-time and offline data analysis, enables the necessary industrial decisions to be made within a reasonable time, and improves the monitoring, control and optimization capabilities of industrial processing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119013633A_ABST
    Figure CN119013633A_ABST
Patent Text Reader

Abstract

The invention relates to a method for processing data items from plant sensors for monitoring at least one item of plant devices, said method comprising the steps of:-extracting sensor data items relating to a phase of an operation performed within a plant; -generating a traceability data item relating to the location of a stage in the operational process within the plant; -aggregating the sensor data items and the traceability data items to generate operational data specific to the operations in the process.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a method for processing sensor data from a plant in order to ensure optimization by controlling its devices.

[0002] The invention enables the creation of a contextualization engine for industrial production process data for monitoring, controlling and optimizing these processes and associated devices. Background Art

[0003] The management of industrial production processes requires the processing of a large amount of data from various sensors. These sensors provide information about a large number of parameters, providing information about the status of various devices operating in different stages and / or conditions. The same device can operate with different parameters depending on a given operating stage within a given operation of the entire production process.

[0004] Knowledge of the exact course of the treatment is key to monitoring, controlling and optimizing the plant.

[0005] In the process industry, especially in batch processing, this is a major obstacle to utilizing sensor data beyond simple monitoring.

[0006] In this type of process, the finished product is obtained after a series of tasks rather than continuously. Batch control in industry is used in many fields: food, chemicals, pharmaceuticals, cosmetics, biotechnology, brewing, crop protection, detergents, enzymes, paints, metallurgy, materials, etc. In all these fields, it is necessary to finely and constantly control the mixture and dosage of the various reagents involved in the production process of the final product, as well as the conditions under which this production process is carried out.

[0007] For manufacturers, mastery of batch process control is a guarantee of quality and productivity. However, these processes must comply with strict traceability rules as well as quality and regulatory controls.

[0008] Industries using batch control often require different products to be manufactured from the same plant configuration: for example, a certain amount of white paint followed by the same amount of black paint for the same can, which may or may not involve allowing time for changeover and / or cleaning. Plants are therefore used for a variety of operations which themselves may involve different phases.

[0009] Batch processing therefore enables us to achieve a high degree of flexibility in production and even reduce the design time for new products. However, this requires strict process monitoring and full traceability of the batches produced.

[0010] Various approaches have been proposed to meet this monitoring need.

[0011] Most are based on tracking the time series of sensor data using data models to describe production operations. These solutions visualize sensor time curves where the start and end correspond to the start and end of the corresponding operation.

[0012] However, these solutions have many disadvantages. They do not provide a global approach to the process. Data is acquired by sensors and only as a function of time. This makes it difficult and time consuming to gain a comprehensive understanding of the process and the problems that may arise when anomalies are detected. This makes monitoring, controlling and optimizing the process extremely complex (if not impossible under certain conditions).

[0013] Therefore, there is a need for improved processing of sensor data from industrial plants to ensure optimization through equipment control. In particular, there is a need for an industrial tool to simplify and facilitate the monitoring, control and optimization of processes and equipment associated with such facilities.

[0014] The present invention falls within this framework. Summary of the invention

[0015] According to a first aspect, the invention relates to a method for processing sensor data of an industrial installation for controlling at least one device of the installation, the method comprising the following steps:

[0016] - extracting status data relating to the phases of operations performed within said industrial plant,

[0017] - generating traceability data relating to the position of said stage in the operational flow within said plant,

[0018] - aggregating the state data and the traceability data to generate operational data specific to the operation in the process.

[0019] The method according to the first aspect enables sensor data from a production process to be contextualized in a standardized way according to production monitoring (traceability and genealogy) to simplify and facilitate monitoring, control and optimization of the process and associated equipment.

[0020] This approach reduces the time, effort and cost required to improve the performance of industrial facilities as they exist in, for example, factories. It also accelerates the analysis of real-time and offline data to identify the root causes of process inefficiencies.

[0021] Embodiments of the present invention provide an industrial process engineering tool. Embodiments enable monitoring, control and optimization of the behavior of industrial processes in a practical manner. Thus, their improvement can be guided with sufficient accuracy and at a reasonable time and cost.

[0022] Thus, embodiments of the present invention provide an industrial tool that is currently lacking in factory development. Purely intelligent processing of sensor data is not possible. In fact, it is not possible to perform the calculations required to achieve sufficiently accurate and significant results to enable the necessary industrial decisions to be made within an industrially reasonable time.

[0023] For example, generation of operational data involves applying a time window relative to the phase of the operation.

[0024] For example, the generation of operational data comprises the location of data relating to the phase of the operation.

[0025] According to an embodiment, the operating data are sent to a control module of said at least one device.

[0026] The method according to the first aspect may further comprise the following steps:

[0027] - generating genealogical data related to the sequencing of said operational processes within said factory,

[0028] - Aggregating said operational and genealogical data.

[0029] For example, generation of genealogy data involves creating links between one or more downstream operations that use products from one or more upstream operations in processes implemented within the plant regarding their data.

[0030] For example, by applying a function representing the link, the family tree data may be used to determine data for one or more downstream operations from data associated with one or more upstream operations.

[0031] According to an embodiment, the operation performed within the plant is an upstream operation, the results of which are used by a plurality of downstream operations, and wherein the generated operational data specific to the upstream operation is used to generate operational data specific to the downstream operation.

[0032] According to an embodiment, the operation performed within the plant is a downstream operation that uses results from a plurality of upstream operations, and wherein generating the operational data specific to the downstream operation comprises applying a function for merging the operational data specific to the upstream operations.

[0033] According to an embodiment, the aggregation of operations and genealogical data is stored in a data structure comprising:

[0034] - a first data set describing the operations of said operational procedure,

[0035] - a second data set describing means of said installation for implementing said operations of said operating procedure and associated with said sensors of said installation,

[0036] - a third data set comprising said aggregation of said data.

[0037] For example, for each operation of the process, the first data set includes a subset of data describing the operational phase of the operation.

[0038] For example, for each operation of the process, the third data set includes a family tree type for indicating the ordering links between the operations of the operational process.

[0039] According to an embodiment, the aggregation of the operations and genealogy data is sent to a control module of the at least one device.

[0040] According to an embodiment, the state data comprises at least one of data from sensors of the plant and values ​​of state variables of devices of the plant.

[0041] According to a second aspect, the invention relates to an apparatus for implementing the method according to the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Other features and advantages of the invention will become apparent from the following detailed description given by way of non-limiting example and from the accompanying drawings, which include the following:

[0043] [ Figure 1 ] shows an environment in which an implementation scheme is implemented,

[0044] [ Figure 2 ] shows the data structure used to describe the production process,

[0045] [ Figure 3 ] shows a data structure used to describe operations in a production process,

[0046] [ Figure 4 ] shows a family tree data structure according to an embodiment,

[0047] [ Figure 5 ] shows a data fusion module according to an embodiment,

[0048] [ Figure 6 ] shows a first type of family tree according to an embodiment,

[0049] [ Figure 7 ] shows a second type of family tree according to an embodiment,

[0050] [ Figure 8 ] is a view of processing steps according to an embodiment,

[0051] [ Fig. 9 ] schematically shows a device according to an embodiment,

[0052] [ Fig.10 ] schematically illustrates a method according to an embodiment implemented in a food production facility. DETAILED DESCRIPTION

[0053] As will become apparent from the detailed description, embodiments of the present invention enable data from sensors associated with equipment in a plant to be contextualized.

[0054] This contextualization may be based, for example, on the state of the facility in which the sensors are present at a given moment.

[0055] Contextualization can be achieved by enabling data “traceability”, for example, by unit operating cycle, operation, production phase, etc.

[0056] This contextualization can also be achieved by associating data with a “genealogy.” This means propagating the information from sensors throughout the production process and its constituent stages.

[0057] This makes it possible to give context to the information provided by the sensors based on the way the process is running or has run. In this way, the correct information can be established to enable monitoring, control and optimization of production.

[0058] Data processed in this way can be used to combine the spatial context of a facility (where the equipment is) and the temporal aspects (when specific operations or phases occur).

[0059] In this way, the process according to various embodiments enables the aggregation of sensor data by combining it with the context of the industrial process, which is necessary for monitoring, controlling and optimizing the process in question.

[0060] Figure 1 An example of a contextualization engine is shown. The contextualization engine 100 processes data from various sensors on devices in a factory 101 that implements a production process. The engine 100 receives data via a real-time interface 102, which connects the data to an automated process control system 103. It also receives data directly input by an operator via a human-machine interface 104.

[0061] For example, the data received from the interface 104 are data useful for process control. The automated process control system 103 is, for example, of the SNCC type (“Système Numérique de The system 103 may be a PLC (an acronym for Programmable Logic Controller) for example. This type of system is a programmable logic controller designed to control industrial processes using sequential processing. It generates computerized commands based on sensor data and sends them to actuators in the plant.

[0062] The contextualization engine 100 also communicates with the control system 105 of the plant 101. The system uses the processes of the contextualization engine to monitor, control, analyze and / or optimize the processes implemented by the plant.

[0063] The contextualization engine is handled by various modules. Module 106 is a traceability and genealogy generator. As described below, it enables tracking of the state data of the plant from the perspective of the progress of the various stages of the processing implemented by the plant. The state data may include sensor data and / or state variable values ​​from the plant devices. These state variable values ​​may, for example, come from the 103 automatic control system. The state variables may give an indication of the operating stage in which a plant device is located. Module 106 generates traceability and genealogy information from the data received via interface 102 to feed module 107.

[0064] The contextualization engine also includes a module 107 for monitoring production within the plant based on data received from the interface 104 and the module 106. The data from this module 107 is then processed by a data fusion module 109 which aggregates it with sensor data received and processed by the module 108 connected to the interface 102.

[0065] The contextual engine is based on Figure 2 The data structure shown.

[0066] The purpose of this data structure is to reproduce and digitally represent the production process implemented by the factory 101. It provides a standardized, detailed description of the process and the data attached to it.

[0067] The processes implemented by the plant 101 are described by data sets 200 that respectively describe operations (OP#1...N) 201, 202,..., 203 of the operational processes. These operations are implemented with the help of various devices (EQUIP#1...P...Q) 205,..., 206,..., 207 described by the data sets. Each of these devices is associated with a corresponding sensor (SNSR) 208,..., 209,..., 210, so that status information (e.g., temperature, pressure or other physical parameters) can be obtained from these devices.

[0068] according to Figure 3 The data structure 300 shown describes each operation. An operation (OP) has a unique operation reference (REF) 301, which enables it to be uniquely identified. It is also described by a set of traceability data 302, 303, ..., 304 describing the successive stages of the operation (PHS#1...R). Each stage is described with the help of data including data 305, 306, 307 representing the corresponding starting point (STRT) and data 308, 309, 310 representing the end (END). Each stage is also associated with data 311, 312, 313 indicating the location (LOC) of the device that implements it. Finally, the described operation can also be described with the help of other data 314 (DAT) stored in a structure provided for this purpose.

[0069] The process is also described with the aid of so-called "genealogy" data (GNLGY) 204, which links the sensor data from the various devices according to the operational flow during which the sensor data was acquired. The operational flow is described by data 201, 202, ..., 203. Figure 4 The genealogy data 204 is described in more detail.

[0070] The figure shows data (GNLGY) 400 linking a data set (UPSTR) 401 representing an upstream operation and a data set (DWNSTR) 403 representing a downstream operation. Each data set includes corresponding upstream data (404, 404) and downstream data (405, 406) describing an operation in a process implemented by the factory. Genealogy type (TYP) data 402 indicates the type of link between operations, such as whether a downstream operation is linked to several upstream operations (or vice versa - type 1->N or N->1), or whether several upstream operations are linked to several downstream operations (type N->N).

[0071] Some of the data described above (particularly traceability and genealogy data) is generated by the traceability and genealogy generator. This module takes as input data from the automated driving system. In particular, the generator takes as input data representing the state of a device. For example, given a device (or set of devices), it may take as input the phase it is in at a given moment.

[0072] The above data structure enables the data fusion module to combine data at two levels. First, the module merges the traceability data with the sensor data to build a data signature of the operation. Second, the module merges the traceability data with the data associated with the operation.

[0073] At the first level, Figure 5 As shown, a data fusion module (FSN) 109 combines the traceability data (e.g., the start of a phase, the end of a phase, the location of a phase in a device) with the sensor data to generate operation-related data items. Figure 2 data structure.

[0074] First, in step 500, the data fusion module 109 selects the sensors 208 attached to the device 205 at the locations corresponding to the relevant phase 302. Second, for these sensors, it selects in step 501 a time window consisting of the start and end of the phase in question, as given by modules 305 and 308. Third, in step 502, it aggregates the sensor data in this window using the transformation function (f).

[0075] The calculations performed by the data fusion module can be performed on the fly (each time data attached to an operation is requested) to ensure that the data is always up to date. It can also be a stored pre-calculation with rules for triggering calculation updates to enable a large number of queries to be launched for use when a large number of operations require it.

[0076] At the second level, data from one or more upstream operations is propagated to one or more downstream operations. The propagation process depends on the type of family tree involved.

[0077] Figure 6 A 1->N family tree is shown. The result of an upstream operation represented by upstream operation data 600 is used by a downstream operation represented by downstream operation data 601. In the case shown, an upstream operation 602 is followed by two downstream operations 603 and 604. The data 605 of operation 602 is propagated as is and reused as data 606 and 607 of operations 603 and 604 themselves, respectively. For example, a product A with feature X and value Y is produced in operation 602. The value Y of feature X is retrieved using downstream operations 603 and 604 of the product from the upstream operation.

[0078] Figure 7 N->N or N->1 family tree is shown. The result of the upstream operation represented by the upstream operation data 700 is used by the downstream operation represented by the downstream operation data 701. In this case, processing is performed to generate data 702, 703 associated with downstream operations 704, 705, because several upstream operation data 706, 707, 708, 709 are needed to construct each of them. Thus, for example, product A with feature X of value Y is produced in upstream operations 708, 709. Downstream operation 704 or 705 uses products from these different upstream operations. In order to obtain the Y value of feature X of this downstream operation, function f is applied to the Y value of feature X of the upstream batch by data fusion module 710. For example, this is a weighted sum. These values ​​can be weighted by the quality of the products used in the various upstream operations. Of course, other functions or processing can be envisioned depending on the processing implemented.

[0079] In view of the foregoing, it is apparent that the methods implemented enable industrial personnel to be provided with a problem of managing the data collected within their plants so that they can optimize the processes they implement. These embodiments provide standardized data structures for describing production operations and stages, and thus standardize the way genealogy and traceability (i.e., production tracking) data are constructed. The generation of traceability and genealogy data enables the data structure to be fed in an expected form, and thus adapts to the form in which these data are available in an automatic control system. The described data fusion enables operation-related data to be generated by combining production monitoring data with sensor data. In particular, the data fusion enables sensor data to be combined with traceability data to systematically obtain aggregate information at the scale of the operation stage. Due to the genealogy, it also enables data from one or more upstream operations to be combined with one or more downstream operations.

[0080] refer to Figure 8 Summarizing the steps of the method according to an embodiment, Figure 8 It is a flowchart of the steps.

[0081] In step 800, data from the automatic process control system controlling the plant are sent. In parallel, in step 801, other complementary data related to the facility may also be sent by other information systems. For example, data sent by an operator via a human-machine interface, as already described.

[0082] The contextualization engine implementing the method receives this data in a collection step 802, which is then routed to various engine modules for processing.

[0083] In step 803, data related to the genealogy of sensor data is extracted and stored in step 805. Then, in step 808, this data is used to create genealogy data according to the above structure to link upstream and downstream operational data.

[0084] In parallel, in step 804, data related to the traceability of the sensor data are extracted and stored in step 806. This data is then used to generate traceability data according to the above structure in step 809, making it possible to describe the successive phases of the operation from which the data originate (starting point and end point, location of the phase according to the device used, etc.).

[0085] The sensor data itself is also extracted in step 807 and stored in step 810 .

[0086] As described above, traceability data is aggregated with sensor data in step 811. Aggregation of these data is then used to generate operational data specific to the implemented operation in step 813. This generation is based on the operational data extracted in step 812 from previously collected data.

[0087] Finally, the genealogy data and operational data are aggregated to be sent to the plant control module in step 814. In this way, the control module has all the information it needs to optimally control the plant. In addition to the raw sensor data, the control module also has a means of knowing exactly the context in which they are collected.

[0088] The method according to an embodiment can be implemented in different ways. It can be implemented by a computer connected to the plant. For example, the method according to an embodiment can be implemented as part of a so-called "on prem" solution. It can also be implemented on a remote computer remotely connected to the facility. In this way, the processing according to an embodiment can be implemented within the framework of a so-called "SaaS" solution (acronym for "Software as a Service").

[0089] Fig. 9 900 is a block diagram of a system for implementing one or more embodiments of the present invention. The above systems or servers may have the same structure.

[0090] System 900 includes a communication bus connected thereto:

[0091] - a processing unit 901, such as a microprocessor, referred to as a CPU;

[0092] - 902 RAM unit for storing executable code of a process according to one embodiment of the invention, and registers suitable for storing variables and parameters required for implementing a process according to other embodiments, the memory capacity of which can be expanded by, for example, an optional RAM connected to an expansion port;

[0093] - a storage unit 903, called ROM, for storing a computer program designed to implement the invention;

[0094] - A network interface unit 904 connected to a communication network through which digital data to be processed is sent or received. The network interface 904 may be a single network interface, or may consist of a set of different network interfaces (e.g., wired and wireless interfaces, or different types of wired or wireless interfaces). Data is written to the network interface for sending or read from the network interface for receiving under the control of a software application running in the CPU 901;

[0095] - Graphical user interface unit 905 for receiving user input or displaying information to the user;

[0096] -906HD-class hard disk;

[0097] -907 I / O module, which is used to receive / send data from / to external systems such as video sources or displays.

[0098] The executable code may be stored in read-only memory 903, on hard disk 906, or on a removable digital medium such as a disk. In a variant, the executable program code may be received via network interface 904 over a communication network to be stored in one of the storage devices of communication system 900, such as hard disk 906, before execution.

[0099] The central processing unit 901 is adapted to control and direct the execution of instructions or parts of software code of a program according to an embodiment of the invention, which instructions are stored in one of the above-mentioned storage devices. For example, after power-on, the processing unit 901 is capable of executing instructions related to software applications from the main RAM 902 after these instructions have been loaded from the ROM program 903 or the hard disk (HD) 906. When executed by the CPU 901, such a software application results in the execution of method steps according to an embodiment.

[0100] To illustrate the implementation of the process according to the embodiment in the factory, Fig.10 An example of a factory is shown in FIG.

[0101] The factory includes a set (COMPNT) 1001 of tanks 1002 to 1009 of ingredients (C#1, ..., #8). Each tank contains an ingredient used in the manufacturing process of a product within the factory. For example, the final product is a cake, and the tanks contain ingredients for the cake, such as milk, sugar, flour, eggs, oil, yeast, almonds, and fruit.

[0102] The factory also includes various frames (BLK#1, ..., #5) using various components of the equipment (EQUIP) 1010, 1012, 1015, 1019, 1022. For example, frame 1010 includes a single device 1011 for sourdough culture. Frame 1012 includes two devices 1013, 1014 for kneading dough and resting dough, respectively. Frame 1015 includes three units 1016, 1017, 1018, for example, for molding, baking and cooling, respectively. Frame 1019 includes two devices 1020, 1021 for demoulding and inspecting cakes. Finally, frame 1022 includes a device 1023 for packaging cakes.

[0103] For example, ingredients C#1 to C#3 are supplied to a yeast dough culture device 1011, and ingredients C#2 to C#8 are supplied to a kneading device 1013. The output from the 1011 devices is a yeast dough, which is also supplied to a kneading device that produces cake dough. The dough is supplied to a device 1014 for standing. The standing dough is then supplied to a device 1016 to mold cakes, which are then supplied to a device 1017 to bake. Once baked, the cakes are supplied to a device 1018 for cooling. Then they are demoulded in a device 1020. Quality control is performed in a device 1021. Once unqualified cakes have been filtered, they are packaged in a device 1023 for transport to their distribution locations.

[0104] In the following, the baking step in the device 1017 will be particularly considered. The implementation of the contextualization engine can refer to the above description, especially Figure 8 Flowchart shown.

[0105] Assume that the installation includes two ovens, each equipped with a sensor measuring the temperature inside the oven and a sensor measuring the humidity inside the oven. Each oven is also equipped with an automatic control system that can send back at any given moment the state of the oven (baking, waiting) and the batch number of the dough used for the product being baked.

[0106] It is also assumed that dough quality data (dry matter, viscosity) are collected for each batch of dough used.

[0107] Implementing the processing described above in this plant enables the following operations to be performed.

[0108] First, data from various sensors, status information from both ovens and information about the batch number of dough used are collected. The sensor data are stored. This corresponds to steps 802 and 807 already described above.

[0109] Then, traceability data is generated based on the oven state information. This corresponds to step 809 described above. In this example, each time the oven state changes from "waiting" to "ignition", a new operation comprising a single stage is created using the date and time of the start of the stage and the date and time of the transition. A unique operation number is then generated, for example, in the format YYYY-MM-DD-XXX (where YYYY is the year, MM is the month, DD is the day, and XXX is a serial number that is reset to 0 at the beginning of each production day). The stage end date and time determined later corresponds to the date and time when the transition from the "ignition" to the "waiting" state is established. The position assigned to the stage is a reference to the oven whose state data is used to create the operation. This traceability creation process is performed in parallel on the data from the two ovens. The collection, extraction and storage of data for this creation correspond to steps 802, 804 and 806.

[0110] Again as described above with respect to steps 803, 805, 808, 1->N family tree information is generated by associating the batch number of the used slurry (upstream) with the operation number that just processed the slurry (downstream).

[0111] For example, according to step 811 already described, a first traceability merge operation is used to calculate a temperature-derived indicator for each baking operation. For the operation in question, a temperature sensor corresponding to the oven specified at the location is selected. Then, according to step 812, data from this sensor within the time window between the start and end of the phase as described in the operation is selected. According to step 813, an aggregation operation is then performed on these data. In this example, three different indicators can be calculated: average temperature, minimum temperature, and maximum temperature. All three results are stored for this operation to be used at a later date.

[0112] To complete the data related to the baking operation, a family tree merge operation is performed according to step 814. The quality data (dry matter, viscosity) corresponding to the batch number of the slurry used in the cooking operation is retrieved and stored in the cooking operation.

[0113] At the end of this process, for each baking operation, a unique operation number of the form YYYY-MM-DD-XXX, a phase with start date / time and end date / time and five data items are available: average temperature, minimum temperature, maximum temperature, viscosity of the dough used, dry matter of the dough used.

[0114] For each baking operation, the family tree data gives the batch number of the dough used (upstream), the family tree type: 1->N and the unique baking operation number of the form YYYY-MM-DD-XXX in which the dough was used.

[0115] All of this data is used to control the system, which determines the settings for regulating the oven's temperature.

[0116] The present invention is described and illustrated with reference to the accompanying drawings in this detailed description. However, the present invention is not limited to the embodiments shown. Other variations, embodiments and feature combinations can be inferred and implemented by those skilled in the art by reading this specification and the accompanying drawings.

[0117] To meet specific needs, modifications or changes may be applied by a person skilled in the art.

[0118] In the claims, the term "comprising" does not exclude other elements or steps. The various features presented and / or claimed may be advantageously combined. Their presence in the description or in different dependent claims does not exclude the possibility of combining them. The reference signs should not be understood as limiting the scope of the invention.

Claims

1. A method for processing status data of an industrial facility (101), the method being used to control at least one device of the facility, wherein: The state data comprises at least one of data from sensors of the facility and values ​​of state variables of devices of the facility, and the method comprises the following steps: - extracting (802) status data relating to the phases (302, 303, 304) of the operation (300) performed in said plant, - generating (809) traceability data relating to the position of said stage in the operational flow within said plant, - aggregating (811) the state data and the traceability data to generate (813) operational data specific to the operation in the process.

2. The method according to claim 1, wherein: The generation of the operational data comprises applying a time window associated with the phase of the operation.

3. A method according to any one of the preceding claims, wherein: The generation of the operational data includes the location of data related to the phase of the operation.

4. A method according to any one of the preceding claims, wherein: The operational data is sent to a control module of the at least one device.

5. The method according to any one of the preceding claims, further comprising the steps of: - generating (808) genealogical data relating to the sequencing of said operations in said operational flow within said factory, - Aggregating (814) the operations and family tree data.

6. The method according to claim 5, wherein: The generation of the genealogy data includes creating links between one or more downstream operations that use products from one or more upstream operations in the processes implemented within the plant related to data thereof.

7. The method according to claim 6, wherein: The family tree data enables data for one or more downstream operations to be determined from data related to one or more upstream operations by applying a function representing the link.

8. The method according to claim 7, wherein: The operation performed within the plant is an upstream operation, the results of which are used by a plurality of downstream operations, and wherein the generated operational data specific to the upstream operation is used to generate operational data specific to the downstream operation.

9. The method according to claim 7, wherein: The operation performed within the plant is a downstream operation that uses results from multiple upstream operations, and wherein generating the operational data specific to the downstream operation includes applying a function for merging the operational data specific to the upstream operations.

10. The method according to any one of claims 5 to 9, wherein: The aggregation of the operations and genealogy data is stored in a data structure, the data structure comprising: - a first data set describing the operations of said operational procedure, - a second data set describing said means of said installation for implementing said operations of said operating procedure and associated with said sensors of said installation, - a third data set comprising said aggregation of said data.

11. The method according to claim 10, wherein: For each operation of the process, the first data set includes a subset of data describing an operational phase of the operation.

12. The method according to claim 10, wherein: The third data set includes, for each operation of the process, a family tree type indicating an ordered link between the operations of the operational process.

13. The method according to any one of claims 5 to 12, wherein: The aggregation of the operations and genealogy data is sent to a control module of the at least one device.

14. A device (900) comprising a processing unit (901) configured to implement the steps of the process according to any one of the preceding claims.