Method and apparatus for maintaining field equipment in a factory

By establishing a knowledge model to integrate maintenance knowledge of different field equipment and generating recommended actions, the problems of inconsistent maintenance information and poor scalability in the existing technology are solved, the accuracy and efficiency of maintenance are improved, and more intelligent maintenance suggestions are achieved.

CN111882084BActive Publication Date: 2024-11-08SIEMENS FACTORY AUTOMATION ENG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010730397.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-27
Publication Date
2024-11-08
Estimated Expiration
2040-07-27

AI Technical Summary

Technical Problem

Existing data exception alert systems cannot effectively integrate maintenance information from different types and from different manufacturers, resulting in high maintenance pressure, and the maintenance system of a single field device cannot achieve unified and flexible information expansion, making it difficult to promote expert knowledge and experience .

Method used

By establishing a knowledge model, integrating maintenance knowledge of different on-site equipment, generating recommended actions for events, providing a unified maintenance system, using the knowledge model to analyze equipment data, providing accurate maintenance suggestions for on-site personnel, and saving all equipment through a unified database. information.

Benefits of technology

It improves the knowledge integration and transparency of field equipment, reduces the time for maintenance personnel to learn maintenance manuals, improves maintenance accuracy and efficiency, and achieves more intelligent and accurate maintenance recommendations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111882084B_ABST
    Figure CN111882084B_ABST
Patent Text Reader

Abstract

This disclosure provides a method for maintaining field equipment in a factory, comprising: acquiring equipment data of the field equipment, the equipment data representing events currently occurring on the field equipment; generating recommended actions for events based on the equipment data using a knowledge model of the field equipment, wherein the knowledge model includes possible event types for the field equipment and corresponding actions for each event type; and providing recommended actions to maintain the field equipment. This method improves the knowledge integration and transparency of field equipment and enables accurate maintenance recommendations to be given to field personnel. Field personnel no longer need to spend time and effort learning maintenance manuals for different field equipment, and can quickly and effectively maintain the field equipment, ensuring accuracy and efficiency, and improving factory productivity. Furthermore, as the knowledge model continues to expand and accumulate knowledge, more intelligent and accurate recommendations can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the technical field of industrial manufacturing, and more particularly, to a method, an apparatus, a computing device, a computer-readable storage medium, and a program product for maintaining field equipment in a factory. Background Art

[0002] The current automotive industry is highly automated. In order to improve production capacity and efficiency, many advanced field devices are used in the automotive industry, such as robots, AGV (automatic guided vehicles) and other automation equipment. However, as field devices become more efficient and intelligent, the maintenance of these field devices still faces great challenges. Poor maintenance will affect the production capacity of the factory, and frequent production interruptions will also cause huge losses to the factory.

[0003] Some factories have established data anomaly alarm systems to assist in the maintenance of field equipment. This system sets data thresholds to generate anomaly alarms, generates maintenance work orders, and dispatches field personnel to inspect and maintain field equipment. Currently, some field equipment manufacturers also provide maintenance systems for single field equipment, which integrate maintenance information support and auxiliary maintenance for the field equipment. Summary of the invention

[0004] The existing data anomaly alarm system can only simply identify the occurrence of abnormal events, and there are a large number of field devices of different types and from different manufacturers in the factory, which still brings high maintenance pressure to field personnel. Moreover, different field devices have different and separately stored maintenance manuals, which not only requires field personnel to spend a lot of energy to learn the maintenance knowledge of different field devices, but also makes it difficult to query and locate the cause of abnormal events. In addition, expert knowledge and experience are also difficult to be promoted and applied.

[0005] Although the maintenance system of a single field device can support and assist maintenance, it only integrates the maintenance information of a certain field device. Therefore, for the entire factory, the maintenance systems of these single field devices are scattered, rather than a unified maintenance system. Moreover, the maintenance information in the maintenance system of a single field device cannot be flexibly expanded and accumulated.

[0006] A first embodiment of the present disclosure proposes a method for maintaining field equipment in a factory, comprising: acquiring equipment data of the field equipment, the equipment data representing events currently occurring in the equipment; utilizing a knowledge model of the field equipment to generate recommended actions for the events based on the equipment data, wherein the knowledge model includes possible event types for the field equipment and corresponding actions for each event type; and providing recommended actions to maintain the field equipment.

[0007] By building a knowledge model for the field equipment in the factory, the maintenance knowledge of different knowledge sources of the field equipment can be integrated together, improving the knowledge integration and transparency of the field equipment. In addition, the knowledge model can be used to analyze the current equipment data of the field equipment, so as to recommend accurate maintenance suggestions to the field personnel. Not only do the field personnel no longer need to spend time and energy to learn the maintenance manuals of different field equipment, but they can also use the maintenance knowledge of different knowledge sources contained in the knowledge model to quickly and effectively maintain the field equipment, ensuring the accuracy and efficiency of maintenance and improving the production efficiency of the factory. In addition, the knowledge model is easy to expand. As the knowledge model continues to expand and accumulate knowledge, it can achieve more intelligent and accurate recommendations.

[0008] A second embodiment of the present disclosure proposes an apparatus for maintaining field equipment in a factory, comprising: a data acquisition unit, configured to acquire equipment data of the field equipment, the equipment data representing events currently occurring in the field equipment; an action recommendation unit, configured to utilize a knowledge model of the field equipment to generate recommended actions for events based on the equipment data, wherein the knowledge model includes possible event types for the field equipment and corresponding actions for each event type; and an action providing unit, configured to provide recommended actions to maintain the field equipment.

[0009] A third embodiment of the present disclosure provides a computing device, which includes: a processor; and a memory for storing computer-executable instructions, which enables the processor to execute the method in the first embodiment when the computer-executable instructions are executed.

[0010] A fourth embodiment of the present disclosure provides a computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are used to execute the method of the first embodiment.

[0011] A fifth embodiment of the present disclosure proposes a computer program product, which is tangibly stored on a computer-readable storage medium and includes computer-executable instructions, which, when executed, cause at least one processor to perform the method of the first embodiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The features, advantages and other aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings, in which several embodiments of the present disclosure are shown in an exemplary and non-limiting manner. In the accompanying drawings:

[0013] Figure 1 A method for maintaining a field device in a factory according to an embodiment of the present disclosure is shown;

[0014] Figure 2 A method for implementing an embodiment of the present disclosure is shown. Figure 1 System architecture diagram of the method in;

[0015] Figure 3 Shows the use of Figure 2 The workflow of on-site equipment maintenance based on the system;

[0016] Figure 4 Shown in Figure 2 A schematic diagram of a portion of an ontology model of a field device established in an embodiment of the present invention;

[0017] Figure 5 Shown in Figure 2 A schematic diagram of a portion of a knowledge model of an AGV established in an embodiment;

[0018] Figure 6 Shown in Figure 2 A schematic diagram of mapping current events and historical events into a vector space and grouping them in an embodiment of the present invention;

[0019] Figure 7 Shown in Figure 2 A schematic diagram of a rule-based action query in an embodiment of the present invention;

[0020] Figure 8 Shown in Figure 2 A schematic diagram of a relation-based action reasoning in an embodiment of the present invention;

[0021] Fig. 9 An apparatus for maintaining a field device in a factory according to an embodiment of the present disclosure is shown; and

[0022] Fig.10 A block diagram of a computing device for maintaining field devices in a factory is shown according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The various exemplary embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. Although the exemplary methods and devices described below include software and / or firmware executed on hardware among other components, it should be noted that these examples are merely illustrative and should not be regarded as restrictive. For example, it is considered that any or all hardware, software, and firmware components can be implemented exclusively in hardware, exclusively in software, or in any combination of hardware and software. Therefore, although exemplary methods and devices have been described below, it should be readily understood by those skilled in the art that the examples provided are not intended to limit the manner in which these methods and devices are implemented.

[0024] In addition, the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the methods and systems according to the various embodiments of the present disclosure. It should be noted that the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession may actually be executed substantially in parallel, or they may sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the flowchart and / or block diagram, and the combination of boxes in the flowchart and / or block diagram, may be implemented using a dedicated hardware-based system that performs a specified function or operation, or may be implemented using a combination of dedicated hardware and computer instructions.

[0025] The terms "include", "comprising" and similar terms used herein are open terms, i.e., "including / includes but not limited to", indicating that other contents may also be included. The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment", etc.

[0026] Figure 1 A method for maintaining a field device in a factory according to an embodiment of the present disclosure is shown. Figure 1 , method 100 starts from step 101. In step 101, device data of a field device is obtained, and the device data indicates an event currently occurring in the device. A field device may be any device in an industrial field in a factory, such as equipment used for production, manufacturing, and transportation. Each field device includes multiple components, and an event currently occurring in a field device indicates that an abnormal condition currently occurs in a component of the field device. The device data includes the event type of the event that occurred, such as abnormal motor temperature, abnormal motor vibration, industrial field bus error, etc. Field device maintenance includes not only various types of regular and non-regular maintenance (such as predictive maintenance) performed on the field device or its components before they are damaged, but also includes repairs to the field device or its components when necessary.

[0027] In some embodiments, Figure 1The method is executed by a server device based on a web application. The server device can be a field server located in a factory or a cloud server outside the factory. Multiple edge devices connected to the server device network receive real-time process data of multiple field devices respectively. The edge device determines whether a certain component of the field device is abnormal, that is, whether an event occurs, based on the received process data and the pre-set data threshold. If an event occurs, the edge device determines the event type of the current event (such as abnormal motor temperature) and generates device data. In addition to the event type of the current event, the device data also includes a field device identifier and the current status data of the field device. The status data is used to represent the status of the field device, for example, the location, speed, load condition, current value, voltage value, motor temperature value, motor vibration value, etc. of the field device. Subsequently, the edge device uploads the device data to the event database at the server device or other devices through the network. In order to form a unified maintenance system, the device data of all field devices are stored in a unified event database. The server device can periodically access the event database to read the device data of a certain field device. In other embodiments, determining whether an event occurs and determining the event type of the event can be completed by the server device.

[0028] Continue to refer Figure 1 In step 102, a knowledge model of the field device is used to generate a recommended action for the event based on the device data, wherein the knowledge model includes possible event types for the field device and corresponding actions for each event type. In order to establish a knowledge model (or a knowledge graph), first, an ontology model related to the maintenance of the field device can be established through any existing ontology model creation software or tool. The ontology model describes all classes (abstract concepts) related to the maintenance of the field device and the relationships between them. Classes can include equipment types, components, events, actions, means, personnel, tasks, states, other related equipment / components, etc. For example, equipment types can include sports equipment and elevator equipment, and sports equipment can include classes of AGV equipment; components can include parent components, child components, etc. Relationships can include whole-part relationships, class-based relationships, attribute relationships, etc. For example, the relationship between sports equipment and AGV equipment belongs to a class-based relationship, the relationship between AGV equipment and its components belongs to a whole-part relationship, and the relationship between actions, means, and personnel belongs to an attribute relationship. Actions can be maintenance / repair actions required due to the occurrence of an event, or they can be maintenance actions required regularly by components of the field device.

[0029] After establishing the ontology model, for each field device, the specific instances of the device type, components, events, actions, means, personnel, tasks, states, other related devices / components, etc. involved in the field device are used as nodes, and the relationships between these instances are used as the relationships between nodes to instantiate the ontology model, thereby generating a knowledge model of the field device and saving it in a knowledge database. The knowledge database can be, for example, a graph database suitable for reflecting nodes and relationships between nodes. Therefore, the knowledge model includes the hierarchical structure of the field device, the possible event types for the field device and the corresponding actions for each event type, and the association relationship between the field device or its components and other devices or components. The knowledge model can also include the regular maintenance actions required for the components of the field device.

[0030] Specific instances in the knowledge model can come from knowledge source data related to field equipment, such as maintenance manuals of field equipment, maintenance / repair records of field equipment, and expert maintenance knowledge of field equipment. Maintenance manuals are usually provided by equipment manufacturers, and include hierarchical structure information of field equipment, events that may occur in field equipment and corresponding status data of field equipment, maintenance / repair actions and regular maintenance actions for events guided by equipment manufacturers, etc. Maintenance / repair records of field equipment usually include events that have occurred in the production process of field equipment in the factory and the corresponding status data of field equipment, maintenance / repair actions of field personnel for the events, and regular maintenance actions for components of field equipment, etc. Expert maintenance knowledge of field equipment usually includes experts' judgment of the occurrence of various events based on the status data of field equipment, maintenance / repair actions taken for various events, and regular maintenance actions for components of field equipment, etc.

[0031] In some embodiments, method 100 further includes: Figure 1(not shown): obtaining knowledge source data related to the field equipment; and generating a knowledge model of the field equipment based on the knowledge source data. Since the knowledge source data are usually stored in various places in a scattered manner or are mastered by the experts themselves, the knowledge source data can be integrated together through the import of documents in commonly used formats (for example, word documents, PDF documents, Excel documents, etc.), acquisition through API interfaces, and manual input. The data required to establish a knowledge model of a certain field device can be found from these knowledge source data through semantic search and / or manual methods, and then these data are used as specific instances of the classes in the ontology model to generate the knowledge model of the field device. When establishing a knowledge model, various types of knowledge source data can be prioritized to make the knowledge model more accurate and effective. For example, expert maintenance knowledge can be set to have the highest priority, maintenance / repair records of field equipment can be set to have the second highest priority, and maintenance manuals of field equipment can be set to have the lowest priority. The knowledge model can be re-established periodically or when needed.

[0032] As mentioned above, the knowledge model of the field device integrates the hierarchical structure of the field device, the possible event types for the field device and the corresponding actions for each event type, and the relevant knowledge of the association relationship between the field device or its components and other devices or components. Therefore, the knowledge model can be used to generate recommended actions for the current event based on the current device data of the field device. The corresponding action of the event type in the knowledge model can be one or more actions, and each action can include the means and personnel (such as maintenance workers, technicians) to implement the action. Similarly, the recommended action can also be one or more actions. In addition, the knowledge model can also be used to generate the recommended actions required for the regular maintenance of the components of the field device. The regular maintenance action of the components in the knowledge model can also be one or more actions, and each action can include the means, frequency and personnel (such as maintenance workers, technicians) to implement the action. In some embodiments, each action in the knowledge model is marked with a priority index, so the generated recommended actions can be prioritized before outputting the recommended actions.

[0033] In some embodiments, using the knowledge model of the field device, generating a recommended action for an event based on the device data further includes: querying the knowledge model for a corresponding action of the event type according to the event type of the event; and generating a recommended action based on the corresponding action. Specifically, a rule between component-event type-action is pre-established, and a recommended action for the event is generated through a rule-based action query. The rule may be "if an event of a certain event type occurs in a certain component, and the event type requires a certain action, then the action is applied to the component". According to the event type included in the device data, the knowledge model is queried for a corresponding action of the event type, and the corresponding action is the action applied to the component where the event occurs. After the corresponding action is queried, the corresponding action is used as a recommended action. In this way, the recommended action is an action in the knowledge model that is related to a specific event type and a specific component. The recommended action can be stored in the event storage mentioned above.

[0034] In some embodiments, using the pre-established knowledge model of the field device, generating a recommended action for the event based on the device data further includes: determining the associated device or component related to the event based on the knowledge model; querying the corresponding action of the event type and the associated action of the associated device or component in the knowledge model according to the event type of the event; and generating a recommended action based on the corresponding action and the associated action. In these embodiments, the recommended action for the event is generated by action reasoning based on the relationship. In some cases, an event occurring in a component of the field device may be related to other components of the field device or other devices in the environment or components of other devices. For example, an error in the industrial field bus of the AGV may be caused by a failure of the industrial field bus itself, or it may be caused by a failure of the sensor connected to it or even the entire navigation system including the sensor. In addition, events occurring simultaneously in multiple components of the field device may be related to the same parent component to which the multiple components belong. For example, the simultaneous breakage of two axes on a robotic arm may be caused by a failure of the entire robotic arm. Therefore, in addition to the component where the event occurs, it is also necessary to determine the associated device or component related to the event. The associated device or component may be a component on the same field device as the component where the event occurs, or it may be a component on other devices or other devices. After acquiring the device data, the component corresponding to the event type is queried in the knowledge model, and then the associated device or component is determined based on the association relationship between the component and other devices or components in the knowledge model. After that, the corresponding action of the event type and the associated action of the determined associated device or component are queried, and they are used as recommended actions. In this way, the recommended action is an action related to multiple components in the knowledge model. Similarly, the recommended action can be stored in the event storage mentioned above.

[0035] In some embodiments, using the knowledge model of the field device, generating recommended actions for events based on device data further includes: obtaining historical recommended actions for similar historical events, wherein the historical recommended actions are previously generated according to the knowledge model; and generating recommended actions based on the historical recommended actions. In these embodiments, recommended actions for events are generated based on event similarity identification. As described above, in addition to storing the device data provided by the edge device, the event database also stores recommended actions for each event. Therefore, all historical recommended actions for historical events are stored therein. These historical recommended actions for similar historical events can be used to provide reference for the current event. The event type of a similar historical event may be the same as the event type of the current event, but the historical state data of the field device when a similar historical event occurred is similar to the state data of the current field device.

[0036] In some embodiments, method 100 further includes: determining historical events of the same event type as the event; and selecting similar historical events from the historical events based on the status data. In the event database, historical status data of multiple historical events of the same event type that occurred on the same type of field equipment are queried according to the event type and field equipment identification in the device data. The historical events are grouped (or classified) according to the historical status data corresponding to these historical events, and a group (or a class) of historical events whose historical status data is closest to the current status data is selected. The selected group of historical events is used as similar historical events. In other embodiments, other methods can also be used to select similar historical events.

[0037] After similar historical events are determined, one or more historical recommended actions for these similar historical events are obtained. As described above, the historical recommended actions are previously generated according to the knowledge model and stored in the event database. Afterwards, the obtained historical recommended actions are used as recommended actions.

[0038] In some embodiments, each action in the knowledge model is labeled with a priority index, so the generated historical recommended actions are also labeled with a priority index. When there are multiple historical recommended actions for similar historical events, these historical recommended actions can be sorted according to the priority index and the sorted historical recommended actions are used as recommended actions.

[0039] In some embodiments, the recommended actions for the event can be generated by any two or all of the rule-based action query, relationship-based action reasoning, and event similarity identification. In these embodiments, after generating multiple recommended actions in different ways, the recommended actions can be prioritized according to the priority index marked by each action, and the ranked recommended actions are saved as the final recommended actions in the event database.

[0040] Next, in step 103, recommended actions are provided to maintain the field equipment. As described above, the generated recommended actions are saved in the event database. The field personnel are notified of the events and recommended actions that occurred in the field equipment via the client device (such as a handheld device). In addition to the recommended actions for the events, the recommended actions for maintenance can also be sent to the field personnel regularly according to the frequency required for the regular maintenance of the field equipment components in the knowledge model. The client device receives the events and recommended actions that occurred in the field equipment and displays them in the form of a web page. The field personnel go to the field equipment to view the events that occurred and maintain the field equipment with reference to the recommended actions.

[0041] In some embodiments, method 100 further includes: Figure 1 (not shown): obtaining feedback data on the recommended action; and adjusting the knowledge model based on the feedback data. After maintaining the field equipment, the field personnel can provide feedback on the recommended action. They can select the actual action taken from the recommended action, or enter a new action when the recommended action is not used. These feedback data are sent to and stored in the event database via the client device. The server device periodically reads the event database and obtains feedback data on the recommended action from it. The feedback data can be used as a new knowledge source to expand and / or update the knowledge model of the field device.

[0042] In some embodiments, adjusting the knowledge model based on feedback data further includes: modifying the corresponding action of the event type of the event in the knowledge model and / or changing the priority of the corresponding action. If the feedback data includes a new action input by the on-site personnel, the corresponding action of the event type can be added to the knowledge model. If the feedback data includes the actual action taken by the on-site personnel selected in the recommended action, the priority index of the actual action taken can be added to the knowledge model. In addition, in some cases, one or more actions with a lower priority index can also be deleted from the knowledge model. In some embodiments, the feedback data can also be used to adjust the historical event grouping (or classification) algorithm to obtain similar historical events that are more similar to the current event in the future.

[0043] By adjusting the knowledge model based on feedback data from on-site personnel, the knowledge model can be continuously expanded and improved, thereby further improving the accuracy of recommended actions and the maintenance efficiency of on-site equipment, and further reducing reliance on personal experience.

[0044] In the above embodiment, by establishing a knowledge model for each field device in the factory, the maintenance knowledge of different knowledge sources of the field devices can be integrated together, and the knowledge model can be used to analyze the equipment data of the field devices, so as to accurately recommend maintenance suggestions to the field personnel. Not only do the field personnel no longer need to spend energy and time to learn the maintenance manuals of different field devices, but they can also use the maintenance knowledge of each knowledge source contained in the knowledge model to better understand the root cause of the fault and quickly and effectively maintain the field equipment, thereby improving the knowledge integration and transparency of the field equipment and ensuring the accuracy and efficiency of maintenance. Moreover, the knowledge models and event data of all field devices are stored in a unified database, so that a unified field equipment maintenance system can be implemented in the factory, and the production and maintenance efficiency of the entire factory can be increased. In addition, the knowledge model is easy to expand, and as the knowledge model continues to expand and accumulate knowledge, more intelligent and accurate recommendations can be achieved.

[0045] The following is a specific example to illustrate Figure 1 A method for maintaining field equipment in a factory.

[0046] Also refer to Figure 2-Figure 8 This embodiment is described. Figure 2 A method for implementing an embodiment of the present disclosure is shown. Figure 1 The system architecture diagram of the method in Figure 3 Shows the use of Figure 2 The system performs on-site equipment maintenance workflow.

[0047] exist Figure 3 In the example, the workflow 300 first includes step 301, obtaining knowledge source data related to the field device, and generating a knowledge model of the field device based on the knowledge source data. Figure 2 , the knowledge acquisition module 20 in the system 200 acquires the knowledge source data. The system 200 is deployed at a server device in the factory or at a cloud device outside the factory. In this embodiment, the knowledge acquisition module 20 includes three submodules, namely a manual reading module 201, a record reading module 202 and an expert knowledge reading module 203. The manual reading module 201 is used to acquire data from the maintenance manual of the field equipment, the record reading module 202 is used to acquire data from the maintenance / repair record of the field equipment, and the expert knowledge reading module 203 is used to acquire data from experts by manual input or reading documents. In other embodiments, data can also be acquired from other knowledge sources.

[0048] Each submodule of the knowledge acquisition module 20 provides the acquired knowledge source data to the model generation module 21. Before generating the knowledge model of the field device, the model generation module 21 pre-establishes an ontology model related to the maintenance of the field device. Figure 4Shown in Figure 2 Schematic diagram of a portion of an ontology model of a field device established in an embodiment. Figure 4 , equipment type, elevator equipment class, sports equipment class, AGV equipment class, components, subcomponents, events, joint events, actions, means, frequencies, personnel, states, workstations, tasks, and areas all belong to classes, and the lines between classes represent the relationships between them. The relationships between classes include whole-part relationships, class-attribute relationships, and attribute relationships. For example, in Figure 4 In the example, the elevator equipment class and the motion equipment class are both subclasses of the equipment type. The elevator equipment class has components, and the components have sub-components. The AGV equipment class is a subclass of the motion equipment system class. The AGV equipment class has components, and the components have sub-components. Events occur in sub-components, and events require actions. Actions include means and personnel. Multiple sub-components may also jointly cause joint events. The joint events form events that occur in the parent components of the multiple sub-components. Both the event and the joint event require actions. In addition, components also apply actions (such as regular maintenance actions) without the need for event triggering. The actions include means, frequency, and personnel. The AGV equipment class has states, which are located in workstations and have tasks. The tasks work in workstations, and the workstations are located in regions. Therefore, the ontology model of field equipment describes all classes related to the maintenance of field equipment and the relationships between them.

[0049] The model generation module 21 includes three submodules, namely, the device description module 211, the event and action description module 212 and the system relationship description module 213. The device description module 211 extracts the hierarchical structure information of the field equipment in the knowledge source data, and instantiates the relevant classes in the ontology model. The event and action description module 212 extracts the event types of events that may occur in the field equipment in the knowledge source data and the corresponding actions of the event types and the regular maintenance actions of the field equipment, and instantiates the relevant classes in the ontology model. The system relationship description module 213 extracts the association relationship between the field equipment and its components and other equipment or components in the knowledge source data, and instantiates the relevant classes in the ontology model. The instantiated ontology model constitutes the knowledge model (or knowledge graph) of the field equipment.

[0050] When establishing a knowledge model, if the corresponding actions of the same event type are different in different knowledge sources, these different actions are prioritized, marked with different priority indexes, and all of them are included in the knowledge model. In this embodiment, the highest priority index is marked for actions from expert maintenance knowledge, the second highest priority index is marked for actions from maintenance / repair records, and the lowest priority index is marked for actions from maintenance manuals. The model generation module 21 establishes such a knowledge model for each field device that needs to be maintained in the factory, and saves the established knowledge model of the field device in the graph database 22. The knowledge model can be derived from the graph database 22 for use in other systems. The knowledge model can also be re-established or expanded on its basis when necessary. The established knowledge model can be displayed via the visualization module 23 for manual modification and / or viewing.

[0051] Figure 5 Shown in Figure 2 A schematic diagram of a portion of a knowledge model of an AGV established in an embodiment. Figure 5 As shown in FIG, the knowledge model of the device AGV1 describes the hierarchical structure of AGV1, possible event types for AGV1 and corresponding actions for each event type, and the association relationship between components of AGV1. The following takes AGV1 as an example to specifically illustrate the process of recommending maintenance actions.

[0052] return Figure 3 , step 302 includes obtaining the device data of AGV1, which represents the event currently occurring in AGV1. The edge device receives real-time process data from AGV1 and determines whether an event occurs. If an event occurs, the edge device determines the event type of the event and generates device data. The device data includes the device identifier AGV1, the event type, and the status data of AGV1. In this embodiment, the event type may include abnormal motor temperature, abnormal motor vibration, and industrial field bus error, etc., and the status data may include the position, speed, load, motor temperature value, and motor vibration value of AGV1. Subsequently, the edge device uploads the device data to the event database 24 of the system 200. In addition to the currently obtained device data, the event database 24 also stores historical device data of historical events and historical recommended actions for historical events. In addition, the feedback data of the on-site personnel on these recommended actions are also stored in the event database 24.

[0053] Next, step 303 includes using the knowledge model of AGV1 to generate recommended actions for events occurring in AGV1 based on device data. This step is completed by the event processing module 25 and the action recommendation module 26 of the system 200. The event processing module 25 obtains the device data of AGV1 from the event database 24 and provides it to the action recommendation module 26. The action recommendation module 26 includes three submodules, namely, an event similarity identification module 261, a rule-based action query module 262, and a relationship-based action reasoning module 263. They respectively generate recommended actions for events occurring in AGV1 based on device data, and the recommended actions include specific means and required personnel.

[0054] The event similarity identification module 261 queries similar historical events from the event database 24 via the event processing module 25. Specifically, taking the event type of the current event of AGV1 as abnormal motor vibration as an example, the event similarity identification module 261 queries the historical device data and corresponding historical recommended actions whose device type is AGV and event type is abnormal motor vibration in the event database 24 via the event processing module 25. These historical device data indicate that the same type of historical events have occurred on the same type of field equipment (in this embodiment, AGV). Afterwards, the event similarity identification module 261 uses a pre-set algorithm to group these historical events according to the historical status data in the historical device data. Figure 6 Shown in Figure 2 A schematic diagram of mapping current events and historical events into a vector space for grouping in an embodiment of FIG. Figure 6 As shown in FIG, these historical events are divided into three groups A, B and C according to the historical state data, and are represented by different shapes respectively. "×" represents the current event, which is closest to the historical events of group A, so it is included in group A. At the same time, the historical events of group A are selected as similar historical events of the current event. After determining the similar historical events, the event similarity identification module 261 obtains multiple historical recommended actions for the similar historical events, and sorts these historical recommended actions according to the priority index of the historical recommended actions as recommended actions.

[0055] The rule-based action query module 262 queries the knowledge model of AGV1 for the corresponding action of the event type according to the event type included in the device data, and uses the corresponding action found as the recommended action. Specifically, taking the event type of the current event of AGV1 as abnormal motor vibration as an example, Figure 7 Shown in Figure 2 Schematic diagram of rule-based action query in an embodiment of FIG. Figure 7As shown in FIG. 1 , the pre-established rule is “motor 1 has a motor vibration abnormality event, and the motor vibration abnormality event requires an action for the motor vibration abnormality, then the action is applied to motor 1”. The action for the motor vibration abnormality may be, for example, checking whether there is an external collision or debris. The rule-based action query module 262 selects the event type of the motor vibration abnormality of the current event in the Figure 5 The knowledge model of AGV1 shown in the figure queries the event type of abnormal motor vibration and the corresponding action for abnormal motor vibration, and uses the action as the recommended action to be applied to motor 1.

[0056] The relation-based action reasoning module 263 queries the event type of the event in the knowledge model of AGV1 and determines the associated devices or components related to the event, and takes the corresponding action of the event type and the associated actions of the associated devices or components as the recommended actions. Specifically, taking the event type of the current event of AGV1 as an industrial field bus error as an example, Figure 8 Shown in Figure 2 Schematic diagram of action reasoning based on relationship in an embodiment of FIG. Figure 8 As shown in , the relationship-based action reasoning module 263 queries from the knowledge model of AGV1 that an event of the type of industrial field bus error occurs on the industrial field bus, and the industrial field bus is linked to the tracking sensor, and the parent component of the tracking sensor is the navigation component. The relationship-based action reasoning module 263 determines the tracking sensor and the parent component navigation component of the tracking sensor as associated components related to the industrial field bus error, and uses the action for the tracking sensor and the action for the navigation component as associated actions of the associated components. The relationship-based action reasoning module 263 uses the action for the industrial field bus error, the action for the tracking sensor, and the action for the navigation component as recommended actions. Similarly, these recommended actions can be sorted according to the priority index.

[0057] When applicable, for the same event type, the event similarity identification module 261, the rule-based action query module 262, and the relationship-based action reasoning module 263 can be used simultaneously to generate recommended actions respectively. After each submodule generates recommended actions respectively, these recommended actions are sorted according to the priority index and provided as the final recommended actions to the event processing module 25. The event processing module 25 saves the final recommended actions in the event database 24.

[0058] Next return Figure 3In step 304, the on-site personnel maintain the on-site equipment according to the recommended actions and provide feedback on the recommended actions. Specifically, the on-site personnel obtain the equipment data and recommended actions from the event database 24 via the client device, and maintain the AGV 1 according to the specific means and required personnel included in the recommended actions to handle the occurred events. In step 305, after the maintenance is completed, the on-site personnel select the actual action from the recommended actions via the client device, or input the actual new action if the recommended action is not used. The feedback data is saved in the event database 24 via the client device.

[0059] In step 306, the knowledge model is adjusted based on the feedback data. This step is performed by the model adjustment module 27 and the model generation module 21 in the system 200. The model adjustment module 27 obtains the feedback data for the recommended action from the event database 24 and provides it to the model generation module 21 to expand and / or update the knowledge model. The model generation module 21 can add the priority index of the action actually taken in the feedback data and / or add a new action and the relationship between the new action and the corresponding component and event type to the knowledge model.

[0060] In addition, despite Figure 2 Although specific modules are not shown in the figure, the action recommendation module 26 can also periodically generate recommended actions according to the frequency of periodic maintenance actions in the knowledge model of the field equipment, so as to perform periodic maintenance on the field equipment.

[0061] By establishing a knowledge model for each field device in the factory, the maintenance knowledge of different knowledge sources of the field devices can be integrated together, and the knowledge model can be used to analyze the equipment data of the field devices, so as to accurately recommend maintenance suggestions to the field personnel. Not only do the field personnel no longer need to spend energy and time to learn the maintenance manuals of different field devices, but they can also use the maintenance knowledge of each knowledge source contained in the knowledge model to better understand the root cause of the fault and quickly and effectively maintain the field equipment. Therefore, the knowledge integration and transparency of the field equipment are improved, and the accuracy and efficiency of maintenance are ensured. Moreover, the knowledge models and event data of all field devices are stored in a unified database, which can realize a unified field equipment maintenance system in the factory and increase the production and maintenance efficiency of the entire factory. In addition, the knowledge model is easy to expand. As the knowledge model continues to expand and accumulate knowledge, more intelligent and accurate recommendations can be achieved.

[0062] Fig. 9 An apparatus for maintaining a field device in a factory according to an embodiment of the present disclosure is shown. Fig. 9The device 900 includes a data acquisition unit 901, an action recommendation unit 902, and an action providing unit 903. The data acquisition unit 901 is configured to acquire device data of a field device, where the device data represents an event currently occurring in the field device. The action recommendation unit 902 is configured to generate a recommended action for an event based on the device data using a knowledge model of the field device, wherein the knowledge model includes possible event types for the field device and corresponding actions for each event type. The action providing unit 903 is configured to provide a recommended action to maintain the field device. Fig. 9 Each unit in the system can be implemented by software, hardware (such as integrated circuit, FPGA, etc.) or a combination of software and hardware.

[0063] In some embodiments, the action recommendation unit 903 is further configured to: query the knowledge model for a corresponding action of the event type according to the event type; and generate a recommended action based on the corresponding action.

[0064] In some embodiments, the knowledge model also includes the association relationship between the field device and its components and other devices or components, and the action recommendation unit 903 is further configured to: determine the associated devices or components related to the event based on the knowledge model; according to the event type of the event, query the knowledge model for the corresponding action of the event type and the associated actions of the associated devices or components; and generate recommended actions based on the corresponding actions and associated actions.

[0065] In some embodiments, the action recommendation unit 903 is further configured to: obtain historical recommended actions for similar historical events, wherein the historical recommended actions are previously generated according to the knowledge model; and generate recommended actions based on the historical recommended actions.

[0066] In some embodiments, the device data includes status data of the field device, and the action recommendation unit is further configured to: determine historical events of the same event type as the event; and select similar historical events from the historical events based on the status data.

[0067] In some embodiments, the apparatus 900 further includes a feedback acquisition unit and a model adjustment unit ( Fig. 9 (not shown in the figure). The feedback acquisition unit is configured to acquire feedback data for the recommended action, and the model adjustment unit is configured to adjust the knowledge model based on the feedback data.

[0068] In some embodiments, the model adjustment unit is further configured to: modify a corresponding action of an event type of an event in the knowledge model and / or change a priority of the corresponding action.

[0069] In some embodiments, the apparatus 900 further includes a knowledge acquisition unit and a model generation unit ( Fig. 9The knowledge acquisition unit is configured to acquire knowledge source data related to the field device. The model generation unit is configured to generate a knowledge model of the field device based on the knowledge source data, wherein the knowledge source data includes at least one of the following items: a maintenance manual of the field device, a maintenance / repair record of the field device, and expert maintenance knowledge of the field device.

[0070] In some embodiments, the knowledge model of the field device is stored in a knowledge database, and the knowledge database further stores the knowledge model of at least one other field device in the plant.

[0071] Fig.10 A block diagram of a computing device for maintaining field devices in a factory according to an embodiment of the present disclosure is shown. Fig.10 As can be seen in FIG. 1 , the computing device 1000 for maintaining field devices in a factory includes a processor 1001 and a memory 1002 coupled to the processor 1001. The memory 1002 is used to store computer executable instructions, which, when executed, enable the processor 1001 to execute the method in the above embodiment.

[0072] In addition, alternatively, the above method can be implemented by a computer-readable storage medium. Computer-readable storage media are loaded with computer-readable program instructions for executing various embodiments of the present disclosure. Computer-readable storage media can be a tangible device that can hold and store instructions used by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the above. More specific examples (non-exhaustive lists) of computer-readable storage media include: portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), static random access memories (SRAM), portable compact disk read-only memories (CD-ROM), digital versatile disks (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or protruding structures in grooves on which instructions are stored, and any suitable combination of the above. The computer-readable storage medium used herein is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., light pulses through a fiber optic cable), or an electrical signal transmitted through wires.

[0073] Therefore, in another embodiment, the present disclosure provides a computer-readable storage medium having computer-executable instructions stored thereon, where the computer-executable instructions are used to execute the methods in various embodiments of the present disclosure.

[0074] In another embodiment, the present disclosure proposes a computer program product, which is tangibly stored on a computer-readable storage medium and includes computer-executable instructions that, when executed, cause at least one processor to perform the methods in various embodiments of the present disclosure.

[0075] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0076] Computer-readable program instructions or computer program products for executing the various embodiments of the present disclosure can also be stored in the cloud. When needed, users can access the computer-readable program instructions for executing an embodiment of the present disclosure stored in the cloud through mobile Internet, fixed network or other networks, thereby implementing the technical solutions disclosed in accordance with the various embodiments of the present disclosure.

[0077] Although the embodiments of the present disclosure have been described with reference to several specific embodiments, it should be understood that the embodiments of the present disclosure are not limited to the specific embodiments disclosed. The embodiments of the present disclosure are intended to cover various modifications and equivalent arrangements included in the spirit and scope of the appended claims. The scope of the claims is consistent with the broadest interpretation, thereby including all such modifications and equivalent structures and functions.

Claims

1. A method for maintaining field equipment in a factory, comprising: Acquire device data of the field device, wherein the device data indicates an event currently occurring in the field device; generating a recommended action for the event based on the device data using a knowledge model of the field device, wherein the knowledge model includes possible event types for the field device and corresponding actions for each event type; and providing the recommended action to perform maintenance on the field device; The step of utilizing the knowledge model of the field device to generate a recommended action for the event based on the device data further includes: Obtaining historical recommended actions for similar historical events, wherein the historical recommended actions are previously generated according to the knowledge model; and Generating the recommended action based on the historical recommended action; wherein the device data includes status data of the field device, and the method further comprises: According to the event type and the field device identifier in the device data, query the historical status data of multiple historical events with the same event type that occurred on the field devices of the same type; and Grouping the plurality of historical events according to their historical status data, and selecting a group of historical events whose historical status data is closest to the status data of the field device; The selected group of historical events is used as the similar historical events.

2. The method according to claim 1, wherein: Using the knowledge model of the field device to generate a recommended action for the event based on the device data further includes: According to the event type of the event, querying the knowledge model for a corresponding action of the event type; and The recommended action is generated based on the corresponding action.

3. The method according to claim 1, wherein: The knowledge model also includes associations between the field device and its components and other devices or components, and generating a recommended action for the event based on the device data using the pre-established knowledge model of the field device further includes: Determine associated devices or components related to the event based on the knowledge model; According to the event type of the event, querying the knowledge model for a corresponding action of the event type and an associated action of the associated device or component; and The recommended action is generated based on the corresponding action and the associated action.

4. The method according to claim 1, further comprising: Obtaining feedback data on the recommended action; as well as The knowledge model is adjusted based on the feedback data.

5. The method according to claim 4, wherein: Adjusting the knowledge model based on the feedback data further includes: Modify the corresponding action of the event type of the event in the knowledge model and / or change the priority of the corresponding action.

6. The method according to claim 1, further comprising: Acquiring knowledge source data related to the field device; as well as A knowledge model of the field device is generated based on the knowledge source data, wherein: The knowledge source data includes at least one of the following: a maintenance manual of the field device, a maintenance / repair record of the field device, and expert maintenance knowledge of the field device.

7. The method according to claim 1, wherein: The knowledge model of the field device is stored in a knowledge database, and the knowledge database further stores a knowledge model of at least one other field device in the plant.

8. A device for maintaining field equipment in a factory, comprising: a data acquisition unit configured to acquire device data of the field device, wherein the device data represents an event currently occurring in the field device; an action recommendation unit configured to generate a recommended action for the event based on the field device data by using a knowledge model of the field device, wherein the knowledge model includes possible event types for the field device and corresponding actions for each event type; and an action providing unit configured to provide the recommended action to perform maintenance on the field device; Wherein, the action recommendation unit is further configured as follows: Obtaining historical recommended actions for similar historical events, wherein the historical recommended actions are previously generated according to the knowledge model; and generating the recommended action based on the historical recommended action; The device data includes status data of the field device, and the action recommendation unit is further configured to: According to the event type and field device identification in the device data, query the historical status data of multiple historical events with the same event type that occurred on the same type of field equipment; and group the multiple historical events according to the historical status data of the multiple historical events, and select a group of historical events whose historical status data is closest to the status data of the field device; and use the selected group of historical events as the similar historical events.

9. The device according to claim 8, wherein: The action recommendation unit is further configured to: According to the event type of the event, querying the knowledge model for a corresponding action of the event type; and The recommended action is generated based on the corresponding action.

10. The device according to claim 8, wherein: The knowledge model also includes the association relationship between the field device and its components and other devices or components, and the action recommendation unit is further configured to: Determine associated devices or components related to the event based on the knowledge model; According to the event type of the event, querying the knowledge model for a corresponding action of the event type and an associated action of the associated device or component; as well as The recommended action is generated based on the corresponding action and the associated action.

11. The apparatus according to claim 8, further comprising: a feedback acquisition unit, configured to acquire feedback data on the recommended action; as well as A model adjustment unit is configured to adjust the knowledge model based on the feedback data.

12. The device according to claim 11, wherein: The model adjustment unit is further configured to: Modify the corresponding action of the event type of the event in the knowledge model and / or change the priority of the corresponding action.

13. Computing equipment, including: processor; as well as A memory for storing computer executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1 to 7.

14. A computer-readable storage medium having computer-executable instructions stored thereon, the computer-executable instructions being used to perform the method according to any one of claims 1-7.

15. A computer program product tangibly stored on a computer-readable storage medium and comprising computer-executable instructions which, when executed, cause at least one processor to perform the method according to any one of claims 1-7.