Method for generating implementation protocols for executing standard operating procedures in industrial plants
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ABB (SCHWEIZ) AG
- Filing Date
- 2022-01-11
- Publication Date
- 2026-06-30
Smart Images
Figure CN116848478B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to standard operating procedures (SOPs) that are not fully automated in industrial plants. Background Technology
[0002] For many safety-critical industrial plants, especially chemical plants, certain tasks must be performed according to Standard Operating Procedures (SOPs). These SOPs are designed to ensure the safe and reliable operation of the plant. For example, an SOP may specify exactly what needs to be done to start up the plant, shut down the plant, or perform maintenance work on the plant or any part thereof. These and other tasks requiring authorized SOPs are often not fully automated; instead, they require one or more human workers to carry out the SOPs. SOPs are often part of plant operation certification or other plant operating licenses, making compliance with SOPs crucial.
[0003] EP 1 413 937 A1 discloses a control system for controlling devices and / or processes based on finite state machines. The information available to the operator is enhanced by a graphical representation of the finite state machine on a display. The graphical representation includes at least two states and at least one permissible transition between these two states.
[0004] Purpose of the invention
[0005] The purpose of this invention is to implement Standard Operating Procedures (SOPs) in industrial plants with computer assistance, even if such implementation is not entirely automated.
[0006] This objective is achieved by a first computer-implemented method for generating an implementation protocol for at least one Standard Operating Procedure (SOP) according to the first independent claim, and by a second computer-implemented method for coordinating the implementation of the SOP using the thus-generated implementation protocol. Further advantageous embodiments are described in detail in the corresponding dependent claims. Summary of the Invention
[0007] The present invention provides a method for generating and / or expanding a computer implementation of an implementation protocol for at least one standard operating procedure (SOP) in an industrial plant.
[0008] In this document, the term "agreement" should not be interpreted as limiting the meaning to the idea that this is the only way to implement a Standard Operating Procedure (SOP) and everything must be done exactly according to the agreement. Instead, the instructions in the agreement can allow for a degree of flexibility, such as "close all valves leading to a specific container" without specifying the order in which the valves should be closed. Furthermore, there may be multiple different ways to implement an SOP. From a reliability perspective, this may be more desirable. If the only way forward assumes that a certain piece of equipment is available, and that equipment fails, then this is a single point of failure, and the implementation of the SOP cannot continue. However, if there are alternative methods that can achieve the same result using other equipment, then there is no longer a single point of failure.
[0009] In other words, as in the context of "communication protocol," the term "protocol" should not be construed as restrictive. Rather, the meaning of the term "protocol" in the context of this invention is very similar to that of the term "scheme," namely, a sequence of instructions that allows a specific objective to be achieved. Incidentally, the term "implementation protocol" is a well-known term in the English language used to describe in detail how a criminal is sentenced to death.
[0010] This method begins with at least one Standard Operating Procedure (SOP) from the provided plant. An SOP comprises multiple steps. In this document, the term "step" should not be construed as limiting the meaning to a single sequence of steps from the beginning to the end of the SOP. Rather, one or more steps in an SOP may be optional, and at any point during the implementation of the SOP, selection may be made between two or more alternative steps.
[0011] In the course of this method, measurement data acquired during multiple implementations of at least one Standard Operating Procedure (SOP) is provided. This measurement data indicates actions performed in the plant that modify the state and / or behavior of the plant or any part thereof in order to implement the SOP.
[0012] Examples of this type of measurement data include:
[0013] • Log data indicating that at least one instruction for modifying the behavior of the plant or any part thereof has been entered into the plant's distributed control system;
[0014] • Measurement data is delivered by field equipment directly related to at least one industrial process implemented in the plant; and
[0015] • Monitor data to indicate the location and / or behavior of at least one worker involved in implementing the SOP.
[0016] For each step of the SOP, a subset of the measurement data is determined based on the measurement data. This subset indicates the actions performed to implement that specific step of the SOP. In other words, the measurement data can be segmented according to the steps of the SOP to which they belong, and measurement data that is completely irrelevant to the implementation of the SOP can be ignored.
[0017] A subset of measurement data determined for each step of the Standard Operating Procedure (SOP) is aggregated into at least one instruction for that specific step of the SOP. This instruction is part of the sought protocol for the overall implementation of the SOP. Specifically, the measurement data can be aggregated via actions represented by the measurement data, and these actions can link the measurement data to one or more instructions. For example, an instruction may relate to the execution of one or more actions. Conversely, given one or more actions, it can be looked up, for example, in a predetermined correspondence where one or more instructions need to be executed in order to perform the one or more actions.
[0018] The inventors have discovered that while Standard Operating Procedures (SOPs) are highly relevant to factory operations, they are typically specified at a very abstract level in the early stages of a factory's development. Therefore, they do not always incorporate subsequent adjustments or knowledge from personnel with extensive experience in that particular factory. Much of this knowledge is difficult to put into writing. Consequently, it often exists only in the minds of the workers implementing the SOPs. Furthermore, the abstract specifications of SOPs require a degree of interpretation.
[0019] For example, if the SOP specifies to open a valve "slowly," it doesn't specify whether the opening should be performed at a constant, slow speed, or whether the opening should begin extremely slowly and then accelerate rapidly. Furthermore, each worker may have a different understanding of the specific speed referred to as "slow."
[0020] Furthermore, the new or revised protocols for implementing SOPs contain richer details that are particularly helpful for newcomers to the plant who are inexperienced with it. For example, if workers who were previously documented to be going to a specific location within the plant for implementing a particular step of an SOP always ended up there, the protocol for implementing the SOP (which might have previously only referred to a piece of equipment by its name or by related terms such as "the leftmost pump") will now include the specific location on the plant floor that won't be mistaken for anything else. In contrast, the related term "the leftmost pump" might lead a newcomer entering the building from the back door instead of the front door to the wrong place.
[0021] This invention does not aim to improve the SOP itself. The SOP is considered given. In the course of the method, a plan is extracted from the operator's actions to facilitate the implementation of the given SOP. That is, knowledge for performing the SOP that might only exist in the operator's mind can now be made available in written form to everyone else.
[0022] SOPs can also refer to technical locations that are difficult to find, such as labels indicating specific locations. For example, the location indicated on a label might require at least a novice worker to translate it into its physical location in the plant using piping and instrumentation charts. However, experienced workers, after being there multiple times, will remember the physical location and will not need to consult the charts again.
[0023] For example, log data can be obtained from the plant's historical records, which capture plant operations and sensor values in an audit trail. For instance, log data may specifically indicate one or more of the following:
[0024] • Setting up new setpoints for lower-level controllers in the factory;
[0025] • The opening or closing of at least one valve in the plant;
[0026] • The start-up or shutdown of at least one piece of equipment in the factory; and
[0027] • Commands to modify the state or behavior of any other actuators of the plant or any part thereof.
[0028] Monitoring data indicating the location and / or behavior of at least one worker involved in implementing the SOP may include, for example, one or more of the following:
[0029] • At least one video stream showing at least one worker involved in implementing the SOP and / or filming using a camera worn by that worker;
[0030] • Data indicating the direction of gaze of at least one worker involved in implementing the SOP;
[0031] • Radio or audio recordings of the voice of at least one worker involved in implementing the SOP; and
[0032] • The interaction between at least one worker involved in implementing the SOP and the human-machine interface of the plant's distributed control system, such as cursor movement and menu selection.
[0033] For example, factory floors can be monitored via video surveillance to track workers' movements within the factory. Worker locations can also be obtained from video streams captured using cameras worn by workers. The latter, along with the direction of the worker's gaze, can also be used to monitor what the worker is actually focusing on.
[0034] Radio or audio recordings of a worker's voice can provide information about which communications between that worker and other workers in the factory are necessary for implementing standard operating procedures (SOPs). For example, if an SOP for maintaining a piece of equipment mandates disconnecting the equipment from the power supply and ensuring it is not reconnected, this might require communication with the central control room via two-way radio to disconnect the power and mark and lock the corresponding switch.
[0035] Interactions between workers and human-machine interfaces (HMIs) can generate information about what information the worker is looking for within that interface. For example, a Standard Operating Procedure (SOP) might specify that the temperature and / or pressure inside a container must be verified before it can be opened. Interactions with the HMI can then expand the specifications within the SOP with information from which the required information can be found.
[0036] Determining the corresponding actions for "each specific step of executing the SOP" means that for each step of a given SOP, it is determined which manual actions are performed for that specific step. Therefore, the manual operations and the measurement data indicating these manual operations are grouped according to the steps of the given SOP. Thus, the process remains governed by the original SOP, which has neither been modified nor rejected.
[0037] In a particularly advantageous embodiment, determining a subset of measurement data related to the steps of the SOP includes filtering portions of the measurement data that relate to one or more of the following:
[0038] • Time slot, in which the SOP steps are performed;
[0039] • Equipment, related to the steps for implementing SOPs;
[0040] • Location within the factory, related to the steps involved in implementing SOPs; and
[0041] • Workers are assigned to participate in the steps of implementing SOPs; and
[0042] • The components of the graphical user interface are highly relevant to the implementation.
[0043] In other words, a “fuzzy alignment” process can be performed to cluster measurement data related to a specific SOP step, thereby discarding data that is irrelevant to SOP implementation and mapping the remaining data to the SOP step.
[0044] For example, the equipment associated with the steps of implementing the SOP can be extracted from the SOP description using appropriate heuristics. Similarly, the roles of the workers required to participate in implementing the SOP steps can be extracted from the SOP description. The time slots in which the SOP steps are performed can be extracted from the measurement data itself, in conjunction with the SOP description. For example, the completion of certain steps of the SOP may be reflected in some signatures in the measurement data (such as records of valve closure or flow rate dropping to zero).
[0045] Each individual filtering criterion applied to the measurement data can be considered a “weak learner,” providing some conceptual framework, but the relevance of a record of measurement data to a specific step of the SOP is not clearly defined. However, a combination of multiple such “weak learners” can more accurately assess whether certain records of the measurement data are relevant to certain steps of the SOP. Therefore, in a particularly advantageous embodiment, the measurement data is filtered according to multiple criteria. A relevance score is assigned to each record of the measurement data. This relevance score increases with the number of criteria satisfied by that particular record of the measurement data. Then, in response to a relevance score exceeding a predetermined threshold, the record of the measurement data can be included in a subset relevant to a specific step of the SOP.
[0046] In another advantageous embodiment, the method further includes determining, based on measurement data, a determined subset, and / or determined instructions, at least one directional sequence of actions leading to the execution of the complete SOP as the sought protocol. This means that the method can not only fill in the execution protocol for the SOP in more detail, but also clarify one or more ways to traverse the SOP as a whole. The SOP itself may not be clear about the order of certain actions that need to be performed. Specifically, the method can attach a single action graph derived from measurements to the SOP, but there can be multiple ways to traverse that graph.
[0047] For example, an SOP might only require powering on a machine, which can be controlled by a separate control unit. There are two ways to power on the machine: first powering on the control unit, then powering on the machine; or first powering on the machine, then powering on the control unit. Superficially, both approaches seem justified. Powering on the control unit first ensures the machine won't be powered without the control unit's control. Powering on the machine first ensures the control unit isn't confused by the machine "disappearing" while the control unit is starting up. Based on measurement data, this method can determine which of the two reasons is considered more convincing in the context of this particular factory. Furthermore, because the motion diagram is traversed in different ways, the instructions and / or more detailed support communicated to the worker can be dynamic to some extent. For example, regardless of whether the worker powers on the machine or the control unit first, he can always receive dynamic support for operating the equipment he has selected to start first.
[0048] There are many more examples of how SOPs can be implemented on multiple different paths. For safety reasons, it might even be desirable to have multiple such paths. For instance, releasing pressure inside a container can typically be done by an automatically controlled valve, but if that valve jams or there is a power failure, a manually operated valve might be needed to release the pressure.
[0049] Therefore, in another advantageous embodiment, the sequence of multiple actions leading to the implementation of a complete SOP is combined into a orientation map of these actions. In this way, the method can identify all available alternatives for further action within the SOP. This includes alternatives not anticipated when the SOP was developed. For example, in the event of a equipment failure, factory personnel might find a creative way to substitute the missing function by repurposing other equipment.
[0050] For example, if it is impossible to remove a large amount of acid from the reaction vessel due to a leak in a subsequent container used to neutralize the acid, different ports of the reaction vessel may be repurposed to deliver the acid to another container elsewhere in the plant, where it can be neutralized and safely discharged.
[0051] Preferably, in this orientation map, based on the provided measurement data, each edge connecting the first action and the subsequent second action is assigned a probability of performing the second action given the first action. This clearly illustrates the preferred method and the auxiliary method to be further performed in the SOP.
[0052] Therefore, in another advantageous embodiment, the path through the graph is determined as the implementation protocol for the SOP, which selects the next action with the higher probability at each action connecting two or more possible next actions. In this way, if different methods for implementing certain steps of the SOP have been previously used by different workers, a standard method can be generated, which should be used unless there is a convincing reason for deviating from this standard method (such as failure). Having a standard method increases the probability of correctly implementing the SOP because it reduces potential errors. For example, if a first worker performing the SOP in one way sees a second worker performing a specific step in a different way, he might take that action, even if it is incorrect in the context of the path the first worker is following. That is, different workers using multiple different implementation protocols can lead to a mixture of different implementation protocols violating the SOP.
[0053] The present invention also provides a computer-implemented method for coordinating the implementation of at least one standard operating procedure (SOP) in an industrial plant.
[0054] In the course of this method, at least one implementation protocol for the SOP, which has been generated and / or extended by the method described above, is provided. This generation and / or extension may have been performed by the same entity coordinating the implementation of the SOP, or it may have been performed at least partially by different entities. For example, a company owning the plant that will be implementing the SOP may seek the assistance of another company that provides the service of generating implementation protocols based on measurement data.
[0055] Obtain measurement data that indicates at least one activity being performed by at least one worker involved in implementing the SOP. For example, the measurement data could indicate the worker's location or direction of gaze, or what the worker is currently seeing. The measurement data could also relate to the state of the plant or any part thereof. For example, the measurement data could indicate if a worker has opened or closed a valve that was to be opened or closed.
[0056] Based at least in part on measurement data, at least one instruction to be performed by the worker is selected from the implementation protocol. The instruction to perform at least one action is communicated to the worker. This communication can be performed in any suitable manner. For example, the information can be overlaid on an augmented reality display being used by the worker. For example, the worker can be guided to the location where the action is to be performed. The equipment that the worker should handle can then be highlighted on the augmented reality display. This occurs when the worker is interacting with the factory via a human-machine interface of a distributed control system.
[0057] In a particularly advantageous embodiment, during the instruction selection process, it is determined whether the worker has already implemented the instruction and / or is already at the location where the instruction is to be implemented. If so, the instruction and / or the direction used for navigation to the location where the instruction is to be implemented are disabled. In this way, the worker is not overloaded with unnecessary information. Such unnecessary information, which can be safely ignored, may cause the worker to ignore other, more safety-related information.
[0058] Similarly, in another advantageous embodiment, the worker's skill level is determined based on current and / or past measurement data. The level of detail in the instructions is based on this skill level. For example, a worker already familiar with the factory may only need instructions to go to equipment with a specific name or other label, while a novice worker may need step-by-step instructions on how to find that equipment. For instance, the level of detail in the instructions may gradually decrease if the worker consistently goes to the correct location when instructed to go to a particular piece of equipment.
[0059] The computer implementation of the methods described above means that these methods can be implemented in a computer program. Therefore, the present invention also provides a computer program having machine-readable instructions that, when executed by one or more computers, cause the one or more computers to perform one of the methods described above. The present invention also provides a non-transitory machine-readable storage medium having a computer program and / or a downloadable product. The downloadable product is a product that can be sold in an online store for immediate use via download. The present invention also provides a computer program and / or a non-transitory machine-readable storage medium and / or a downloadable product to one or more computers. Attached Figure Description
[0060] The invention is illustrated below with the accompanying drawings, but is not intended to limit the scope of the invention. These drawings show:
[0061] Figure 1 Exemplary embodiments of the method 100 for generating and / or expanding the implementation protocol 4 for SOP 2;
[0062] Figure 2 :Exemplary implementation protocol 4 generated by method 100;
[0063] Figure 3 Exemplary embodiment of method 200 for coordinating the implementation of SOP 2. Detailed Implementation
[0064] Figure 1 This is a schematic flowchart of an embodiment of a method 100 for generating and / or expanding implementation protocol 4 for SOP 2.
[0065] In step 110, at least one SOP 2 is provided, which includes multiple steps 2a-2g. In step 120, measurement data 3 is provided. This measurement data 3 has been acquired during multiple implementations of at least one SOP 2. It indicates actions performed in plant 1 that modify the state and / or behavior of plant 1 or any part thereof in order to implement SOP 2.
[0066] In step 130, for each step 2a-2g of SOP 2, a subset 3a-3g of measurement data 3 is determined, which indicates the action to be performed in order to implement that particular step 2a-2g of SOP.
[0067] According to box 131, the determination 130 may specifically include: “fuzzy filtering” of the measurement data according to one or more criteria, each of which may be a “weak learner”. Specifically, according to box 131a, the measurement data 3 may be filtered according to multiple criteria. According to box 131b, a relevance score may be assigned to each record of the measurement data 3, the relevance score increasing with the number of criteria satisfied by that particular record in the measurement data 3. According to box 131c, in response to the relevance score exceeding a predetermined threshold, records of the measurement data 3 may be included in subsets 3a-3g.
[0068] In step 140, subsets 3a-3g of measurement data 3 determined for each step 2a-2g of SOP 2 are aggregated into at least one instruction 4a-4g for implementing that particular step 2a-2g of SOP. This instruction 4a-4g is part of the sought protocol 4.
[0069] In step 150, based on measurement data 3, subsets 3a-3g, and / or instructions 4a-4g, the orientation sequence of actions that result in the execution of the complete SOP 2 can be determined as the sought protocol 4. Actions may correspond to instructions 4a-5g, but one or more instructions in 4a-4g may also be broken down into finer-grained sub-actions.
[0070] According to box 151, a sequence of multiple actions leading to the execution of the complete SOP 2 can be combined into a directional graph of these actions. Specifically, according to box 151a, a probability of executing the second action given the first action can be assigned to each edge connecting the first action and the subsequent second action. According to box 151b, the path through the graph can be determined as an execution protocol 4 for SOP 2, which selects the next action with the higher probability at each action connecting to two or more possible next actions.
[0071] Figure 2This is an example of implementation protocol 4 for SOP 2. Implementation protocol 4 is in the form of a orientation diagram and includes instructions 4a-4g corresponding to steps 2a-2g of SOP 2. After the second step 4b, there are two options. The first option is to implement instruction 4c. The second option is to implement a combination of instructions 4d and 4e. Both options yield the same result, which puts factory 1 in a state where it can implement the next instruction 4f and then finally implement instruction 4g.
[0072] For example, instruction 4c can be associated with a direct way of achieving the desired result, while the combination of instructions 4d and 4e can be associated with an indirect way of achieving the same result. Therefore, as... Figure 2 As shown in Figure 3, the probability of the direct method is 80%, while the probability of the indirect method is 20%. For example, the indirect method may be useful as a backup when the equipment required for the direct method is unavailable.
[0073] Figure 3 This is a schematic flowchart of an exemplary embodiment of a method 200 for coordinating the implementation of at least one SOP 2.
[0074] In step 210, at least one implementation protocol 4 with instructions 4a-4g has been generated and / or expanded by the method 100 described above. In step 220, measurement data 3 is obtained. This measurement data 3 indicates at least one activity being performed by at least one worker 5. Worker 5 will be participating in the implementation of SOP 2.
[0075] In step 230, at least one instruction 4a-5g to be implemented by worker 5 is selected from implementation protocol 4, based at least in part on measurement data 3. Hereinafter, according to box 231, it is determined whether worker 5 has already implemented instruction 4a-4g and / or is already at the location where instruction 4a-4g is to be implemented. If this is the case (truth value 1), then according to box 232, instruction 4a-4g and / or the direction used for navigation to the location where instruction 4a-4g is to be implemented can be disabled.
[0076] In step 240, instructions 4a-4g are communicated to worker 5. Herein, according to box 241, the skill level of worker 5 can be determined based on current and / or past measurement data 3. According to box 242, the level of detail in the instructions can be adjusted based on this skill level.
[0077] List of reference numerals
[0078] 1 Industrial factory
[0079] 2. Standard Operating Procedures (SOP)
[0080] Steps for 2a-2g SOP 2
[0081] 3 Measurement Data
[0082] 3a-3g corresponds to the subset of measurement data from steps 2a-2g.
[0083] 4. Implementation Agreement of SOP 2
[0084] 4a-4g implements the instructions in Protocol 4.
[0085] 5 workers
[0086] 100 Methods for generating and / or expanding implementation protocol 4
[0087] 110 provides SOP 2
[0088] 120 provides measurement data 3
[0089] 130. Determine a subset 3a-3g of the measurement data from steps 2a-2g.
[0090] 131 Fuzzy Filtering of Measurement Data 3
[0091] 131a Filtering based on multiple criteria
[0092] 131b Assigning correlation to measurement data 3
[0093] 131c Considering measurement data based on correlation 3
[0094] 140 Aggregate subsets 3a-3g into instructions 4a-4g
[0095] 150 Determine the orientation sequence of actions
[0096] 151 Generate an orientation map for actions
[0097] 151a Assignment Probability to the Margins
[0098] 151b Determine the path with the highest probability.
[0099] 200 Methods for coordinating the implementation of SOP 2
[0100] 210 Provide implementation agreement 4
[0101] 220 Obtained measurement data 3
[0102] 230 Select instruction 4a-4g
[0103] 231 Determine whether instructions 4a-4g were executed and whether the position was reached.
[0104] 232 Forbidden Commands 4a-4g
[0105] 240. Instructions 4a-4g are given to worker 5.
[0106] 241 Determine the skill level of worker 5.
[0107] 242 Adjust the level of detail according to skill level
Claims
1. A computer-implemented method (100) for generating and / or expanding an implementation protocol (4) for at least one given standard operating procedure (SOP) (2) in an industrial plant (1), comprising the steps of: • Provide at least one given SOP (2) in the industrial plant (1), the at least one given SOP (2) comprising multiple steps (2a-2g); • Provide measurement data (3), which has been acquired during the implementation of the plurality of steps (2a-2g) of the at least one given SOP (2) and indicates actions performed in the industrial plant (1) that modify the state and / or behavior of the industrial plant (1) or any part thereof in order to implement the at least one given SOP (2); • For each step (2a-2g) of the at least one given SOP (2), a subset (3a-3g) of the measurement data (3) is determined based on the measurement data (3), the subset (3a-3g) indicating the action to be performed in order to carry out the specific step (2a-2g) of the at least one given SOP (2), wherein determining the subset (3a-3g) includes: segmenting the measurement data (3) according to the step of the given SOP (2) to which the measurement data (3) belongs; as well as • The subset (3a-3g) of the measurement data (3) determined for each step (2a-2g) of the at least one given SOP (2) is aggregated into at least one instruction (4a-4g) for implementing the specific step (2a-2g) of the at least one given SOP (2), wherein the instruction (4a-14g) is part of the sought implementation protocol (4).
2. The method (100) according to claim 1, wherein the measurement data (3) includes one or more of the following: • Log data indicating that at least one instruction to modify the state or behavior of the industrial plant (1) or any part thereof is input into the distributed control system of the industrial plant (1); • Measurement data (3), delivered by at least one field device, said at least one field device being directly related to the industrial process carried out by said industrial plant (1); and • Monitor data to indicate the location and / or behavior of at least one worker (5) involved in implementing at least one given SOP (2).
3. The method (100) according to claim 2, wherein the log data indicates one or more of the following: • Setting of new setting points for low-level controllers in the industrial plant (1); • The opening or closing of at least one valve in the industrial plant (1); • The start-up or shutdown of at least one piece of equipment in the industrial plant (1); and • Commands to modify the state or behavior of any other actuator of the industrial plant (1) or any part thereof.
4. The method (100) according to claim 2, wherein the monitoring data includes one or more of the following: • At least one video stream showing at least one worker (5) participating in the implementation of the at least one given SOP (2) and / or captured by a camera worn by the worker (5); • Data indicating the gaze direction of at least one worker (5) participating in the implementation of at least one given SOP (2); • A radio or audio recording of the voice of at least one worker (5) who is involved in implementing at least one given SOP (2); as well as • Interaction, which is an interaction between at least one worker (5) participating in the implementation of at least one given SOP (2) and the human-machine interface of the distributed control system of the industrial plant (1), such as cursor movement and menu selection.
5. The method (100) according to any one of claims 1 to 4, wherein determining a subset (3a-3g) of the measurement data (3) associated with step (2a-2g) of the at least one given SOP (2) comprises: Filter (131) the portions of the measurement data (3) that relate to one or more of the following: • Time slot, in which the steps (2a-2g) of the at least one given SOP (2) are performed; • Equipment, which is associated with the steps (2a-2g) for carrying out the at least one given SOP (2); • The location in the industrial plant (1), which is related to the steps (2a-2g) for carrying out the at least one given SOP (2); • Worker (5), who is assigned to participate in the steps (2a-2g) of the at least one given SOP (2); as well as • Components of the graphical user interface, which are highly relevant to the implementation protocol (4).
6. The method (100) according to claim 5, further comprising: • The measurement data is filtered according to multiple criteria (3); • Assign a correlation score to each record of the measurement data (3), wherein the correlation score increases with the number of criteria satisfied by a particular record of the measurement data (3); and • In response to the correlation score exceeding a predetermined threshold, records of the measurement data (3) are included in the subset (3a-3g).
7. The method (100) according to any one of claims 1 to 4 and 6, further comprising: Based on the measurement data (3), the subset (3a-3g), and / or the instructions (4a-4g), determine at least one directional sequence of actions that leads to the full implementation of the given SOP (2) as the sought implementation protocol (4).
8. The method (100) according to claim 7, further comprising: Multiple sequences of actions that lead to the execution of the given SOP (2) are combined into a direction graph of these actions.
9. The method (100) according to claim 8, further comprising: Based on the provided measurement data (3), assign the probability of performing the second action given the first action to each edge connecting the first action and the subsequent second action.
10. The method (100) according to claim 9, further comprising: The path through the orientation graph is determined as the implementation protocol (4) for the complete given SOP (2), wherein the path selects the next action with higher probability at each action that connects to two or more possible next actions.
11. The method (100) according to claim 1, wherein the aggregation of the subset (3a-3g) of the measurement data (3) determined for each step (2a-2g) of the at least one given SOP (2) comprises: The action represented by the measurement data (3) is aggregated with the measurement data (3); and / or The predetermined correspondence is used to find which instruction(s) need to be implemented to perform the one or more actions.
12. The method according to claim 1, wherein for each step (2a-2g) of the at least one given SOP (2), a subset (3a-3g) of the measurement data (3) indicating actions to be performed for a particular step (2a-2g) of the at least one given SOP (2) is determined based on the measurement data (3), meaning for each step (2a-2g) of the given SOP (2), which manual actions are performed for that particular step, and the manual actions and the measurement data (3) indicating those manual actions are grouped according to each step (2a-2g) of the given SOP steps.
13. A computer-implemented method (200) for coordinating the implementation of at least one given standard operating procedure (SOP) (2) in an industrial plant (1), comprising the following steps: • Provide at least one implementation protocol (4) for the at least one given SOP (2), the at least one given SOP being generated and / or extended by the method (100) according to any one of claims 1 to 12; • Obtain measurement data (3) indicating at least one activity being performed by at least one worker (5) who is to participate in implementing at least one given SOP (2); • Based at least in part on the measurement data (3), select at least one worker (5) to implement at least one instruction (4a-4g) in accordance with the implementation agreement (4). as well as • The instructions (4a-4g) are conveyed to at least one worker (5).
14. The method (200) of claim 13, wherein selecting at least one instruction comprises: • Determine whether the worker (5) has carried out the instructions (4a-4g) and / or is at the location where the instructions (4a-14g) are to be carried out; as well as • If this is the case, then the instructions (4a-4g) and / or the directions used for navigation to the location where the instructions (4a-4g) are to be implemented are prohibited.
15. The method (200) according to claim 13 or 14, wherein conveying the instructions (4a-4g) comprises: • Based on current measurement data (3) and / or past measurement data (3), determine the skill level of the at least one worker (5), and • Adjust the level of detail of the instruction (242) based on the skill level.
16. A computer program comprising machine-readable instructions that, when executed by one or more computers, cause the one or more computers to perform the method (100, 200) according to any one of claims 1 to 15.
17. A non-transitory machine-readable storage medium and / or a computer program product having the computer program according to claim 16.
18. One or more computers having a computer program as claimed in claim 16, and / or having a non-transitory storage medium and / or computer program product as claimed in claim 17.