A visual intelligent inspection method and device based on digital twin digital-analog separation

Abstract

The present invention discloses a visual intelligent inspection method and device based on digital twin digital-analog separation. The method includes using digital twin and digital-analog separation technology to establish a three-dimensional visualization model of an oil and gas field station, construct a road network, and customize an inspection route based on the road network; during the inspection process of the virtual inspector along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at a set interval, and fault prediction is performed through a time series prediction model; if it is predicted that any equipment to be inspected has a risk of failure, the shortest path from the current position of the virtual inspector to the equipment to be inspected with a risk of failure is determined according to the road network, so that the virtual inspector reaches the equipment along the shortest path and performs corresponding processing. The method can realize the establishment of a lightweight simulation model of the working scene of the oil and gas field station based on digital twin digital-analog separation, and predict faults through mining and analysis of operating data, so as to achieve a rapid improvement in inspection quality and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent inspection technology, and in particular to a visualized intelligent inspection method and device based on digital-analog separation of digital twins. Background Art

[0002] An oil and gas field station refers to a collection of facilities and equipment located near an oil and gas field, which is used to collect, store and process crude oil and natural gas. It is the core of production and operation in the petrochemical industry.

[0003] The demand for oil and gas in industry, agriculture and life is increasing. At the same time, the development of old oil fields in my country has entered a period of extremely high water content. In order to ensure the long-term high and stable production of oil fields, the expansion of production scale has made the distribution of oil fields more and more extensive. Some oil and gas field stations are located in recognized dense areas, which brings great difficulties to the production control of the stations. In addition, the number of high water content, low production and low efficiency blocks in oil fields has increased year by year, and the imbalance of system load has become more and more serious. At present, the operation and maintenance of oil and gas field stations mainly adopts a combination of manual inspection and video monitoring technology. The station staff regularly check the equipment damage and pipeline leakage. However, the manual inspection method has high labor intensity but low work efficiency. The experience varies from person to person, and the video monitoring system has blind spots. In addition, most inspection scenes have the characteristics of a large number of equipment and wide distribution. High-frequency and high-risk operations bring high costs. At the same time, uncertain factors such as personnel safety, missed inspections, and wrong inspections bring more challenges to the inspection work. On-site personnel cannot view the overall equipment operation status in real time. In the process of equipment operation and maintenance in important areas, they are highly dependent on the relevant technical knowledge and experience of on-site personnel. Operation and maintenance personnel need to travel back and forth between the control center and the site, and the operation and maintenance efficiency needs to be improved urgently. During specific maintenance and troubleshooting, on-site personnel are often unable to quickly and accurately locate and understand the operating status and related data information of faulty equipment, which can easily lead to incomplete troubleshooting and lay hidden dangers for emergency handling of emergencies. As can be seen from the above, the extensive operation and maintenance management model of traditional oil and gas field stations restricts the efficient processing of production operations and becomes a key factor affecting production operation costs. Summary of the invention

[0004] In order to enrich the process routes and increase the selection space, the embodiments of the present invention provide a visual intelligent inspection method and device based on digital twin digital-analog separation, which can realize the establishment of a lightweight simulation model of the working scene of the oil and gas field station based on the digital twin digital-analog separation, and predict faults through mining and analysis of operation data, so as to achieve rapid improvement of inspection quality and efficiency.

[0005] In a first aspect, an embodiment of the present invention provides a visual intelligent inspection method based on digital twin digital-analog separation, comprising:

[0006] Use digital twin and digital-analog separation technology to establish a three-dimensional visualization model of oil and gas field stations, construct a road network, and customize inspection routes based on the road network;

[0007] During the inspection process of the virtual inspector along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at set intervals, and fault prediction is performed through a time series prediction model based on the current data sequence;

[0008] If it is predicted that any device to be inspected has a risk of failure, the shortest path from the current position of the virtual inspector to the device to be inspected with a risk of failure is determined based on the road network, so that the virtual inspector can reach the device to be inspected along the shortest path and perform corresponding processing.

[0009] In a second aspect, an embodiment of the present invention provides a visual intelligent inspection device based on digital-analog separation of digital twins, including:

[0010] A three-dimensional model building module is used to build a three-dimensional visualization model of the oil and gas field station using digital twins and digital-analog separation technology, construct a road network, and customize inspection routes based on the road network;

[0011] A fault prediction module is used to update the current data sequence of the equipment to be inspected in the model at set intervals during the inspection process of the virtual inspector along the inspection route, and perform fault prediction based on the current data sequence through a time series prediction model;

[0012] The shortest path determination module is used to determine the shortest path from the current position of the virtual inspector to the device to be inspected that has a risk of failure based on the road network if it is predicted that any device to be inspected has a risk of failure, so that the virtual inspector can reach the device to be inspected along the shortest path and perform corresponding processing.

[0013] In a third aspect, an embodiment of the present invention provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed by a processor, the above-mentioned visual intelligent inspection method based on digital twin digital-analog separation is implemented.

[0014] In a fourth aspect, an embodiment of the present disclosure provides a server, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the above-mentioned visual intelligent inspection method based on digital twin digital-analog separation is implemented.

[0015] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0016] (1) The visual intelligent inspection method based on digital twin digital-analog separation provided by the embodiment of the present invention uses digital twin and digital-analog separation technology to establish a three-dimensional visualization model of the oil and gas field station, construct a road network, and customize the inspection route based on the road network; during the virtual inspector's inspection along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at a set interval, and fault prediction is performed through a time series prediction model based on the current data sequence; if it is predicted that any equipment to be inspected has a risk of failure, the shortest path from the current position of the virtual inspector to the equipment to be inspected with a risk of failure is determined according to the road network, so that the virtual inspector can reach the equipment to be inspected along the shortest path and perform corresponding processing. It is possible to establish a lightweight simulation model of the working scene of the oil and gas field station based on digital twin and digital-analog separation technology, and predict faults through mining and analysis of operating data, so as to achieve a rapid improvement in inspection quality and efficiency.

[0017] (2) The visualized intelligent inspection method based on digital twin digital-analog separation provided in the embodiment of the present invention predicts the fault of the equipment to be inspected based on the current data sequence of the equipment to be inspected and by using the time series prediction model trained by the historical data sequence of the equipment to be inspected, so that corresponding processing can be carried out in advance before the fault occurs, thereby avoiding the occurrence of faults, achieving safe production, and saving manpower and financial resources for fault handling.

[0018] (3) The visualized intelligent inspection method based on digital twin digital-analog separation provided by the embodiment of the present invention predicts that any device to be inspected has a fault risk. According to the type of fault risk, the method matches the effect corresponding to the type through the pre-established special effect library, and displays the effect at the corresponding device to be inspected. The fault effect can be displayed visually through sound, image or video, so that the user can understand the location and type of the fault risk more quickly and vividly.

[0019] (4) The visualized intelligent inspection method based on digital twin digital-analog separation provided by the embodiment of the present invention predicts that any device to be inspected has a risk of failure, and generates a corresponding fault handling method based on the fault risk data, so that after the virtual inspector arrives at the device to be inspected, he or she can perform corresponding processing according to the received fault handling method. Virtual simulation training can be carried out to train manual inspections, which not only makes personnel more familiar with the inspection path, but also allows them to understand how to handle faults; it can replace manual inspections to a certain extent, reduce the frequency of manual inspections, and avoid the insecurity of personnel going to the site for training or inspections.

[0020] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0021] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0023] Figure 1 This is a flow chart of a visualized intelligent inspection method based on digital-analog separation of digital twins in Embodiment 1 of the present invention;

[0024] Figure 2a This is an example diagram of the three-dimensional visualization model of the oil and gas field station established in the first embodiment of the present invention;

[0025] Figure 2b For Figure 2a Example diagram of building a road network in the model;

[0026] Figure 2c For Figure 2b The road network diagram constructed in

[0027] Figure 3 For Figure 2c The inspection route is developed based on the road network diagram, and an example diagram of the shortest path from the current position of the virtual inspector to the fault point;

[0028] Figure 4a This is an example diagram of a three-dimensional model of an oil and gas field station production scene in the second embodiment of the present invention;

[0029] Figure 4b For Figure 4a Example diagram of inspection route customized in ;

[0030] Figure 4c For Virtual Inspector, press Figure 4b Inspection route inspection scene in;

[0031] Figure 5a This is the inspection scene of the virtual inspector in the second embodiment of the present invention;

[0032] Figure 5b for Figure 5a An example of a virtual inspector rushing to the scene of an accident based on an equipment failure warning in a mid-inspection scenario;

[0033] Figure 5c for Figure 5b An example of an emergency response scenario after a virtual inspector arrives at the scene of an accident;

[0034] Figure 6It is a structural schematic diagram of a visualized intelligent inspection device based on digital-analog separation of digital twins in an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0036] It should be understood that the terms described in the present invention are only for describing special embodiments and are not intended to limit the present invention. In addition, for the numerical range in the present invention, it should be understood that each intermediate value between the upper and lower limits of the scope is also specifically disclosed. Each smaller range between the intermediate value in any stated value or stated range and any other stated value or intermediate value in the described range is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded in the scope.

[0037] Unless otherwise indicated, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which the invention belongs. Although the present invention describes only preferred methods and materials, any methods and materials similar or equivalent to those described herein may also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials related to the documents. In the event of a conflict with any incorporated document, the content of this specification shall prevail.

[0038] With the continuous development of the economy, and the wave of digitalization represented by technologies such as the Internet of Things, artificial intelligence, and big data sweeping the world, the inventor believes that it is urgent to deeply combine intelligent technology with the development of oil fields, and rely on management and technological innovation to improve the management level of oil and gas field stations. After further research and development, the inventor made the present invention. The embodiment of the present invention provides a visual intelligent inspection method and device based on digital twin digital-analog separation, which realizes the establishment of a lightweight simulation model of the working scene of the oil and gas field station based on the digital twin digital-analog separation, and predicts faults through mining and analysis of operating data, so as to achieve rapid improvement of inspection quality and efficiency.

[0039] Embodiment 1

[0040] Embodiment 1 of the present invention provides a visual intelligent inspection method based on digital twin digital-analog separation, and its process is as follows: Figure 1 As shown, the following steps are included:

[0041] Step S11: Use digital twin and digital-analog separation technology to establish a three-dimensional visualization model of the oil and gas field station, construct a road network, and customize the inspection route based on the road network.

[0042] Digital twin is to create a digital version of a device or system based on the "clone". This "clone" is also called "digital twin".

[0043] The significance of the digital-analog separation function is to analyze and separate the three-dimensional model data, and fully explore and utilize the data information carried by the model.

[0044] This embodiment uses digital twin technology to extract relevant information from the traditional oil and gas field station industrial model (digital-analog integrated model), build a virtual oil and gas field station work scene, and obtain a lightweight three-dimensional visualization model of the oil and gas field station.

[0045] Based on this digital twin base, inspection routes can be customized. First, a road network is constructed, and each intersection is defined as a node. If two intersections have roads connected, an edge is added, and then the nodes and edges are connected in series to form a network structure to form a road network diagram, which supports the orderly actions of virtual inspectors in the road network.

[0046] For example, the connectivity between intersections can be set through mouse interaction to form a road network diagram.

[0047] You can also click on specific locations with the mouse to generate an inspection route based on the click sequence.

[0048] See also Figure 2a The following is an example of a 3D visualization model of an oil and gas field station. The connectivity between intersections is set by mouse interaction to build a road network. Figure 2b shown; see Figure 2c As shown in Figure 2, the constructed road network diagram is shown.

[0049] Step S12: When the virtual inspector inspects along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at set intervals, and fault prediction is performed based on the current data sequence through the time series prediction model.

[0050] The time series prediction model is a model trained using the historical data sequence of the equipment to be inspected. Specifically, the historical data sequence includes at least one data cycle, and the data cycle includes fault data.

[0051] Furthermore, the time series prediction model can be an autoregressive integrated moving average model (ARIMA) model, which is the most common statistical model used for time series prediction. Its full name is Autoregressive Integrated Moving Average Model, also known as ARIMA (p, d, q).

[0052] Based on the real-time data generated by the equipment to be inspected, a time series prediction model is used to perform trend prediction.

[0053] The following is an introduction using the ARIMA model as an example:

[0054] The ARIMA model has three parameters: p, d, and q.

[0055] p--represents the number of lags of the time series data sequence itself used in the prediction model, also called AR / Auto-Regressive term.

[0056] d-- represents the number of order differences that the time series data sequence needs to undergo to be stable, also called the Integrated term.

[0057] q--represents the number of lags of the forecast error used in the forecast model, also known as the MA / Moving Average term.

[0058] Let me explain the difference first: suppose y represents the difference of Y at time t.

[0059] if d=0,y t =Y t

[0060] if d=1,y t =Y t -Y t-1

[0061] ifd=2,y t =(Y t -Y t-1 )-(Y t-1 -Y t-2 )

[0062] =Y t -2Y t-1 +Y t-2

[0063] The predicted value of Y = constant c and / or the weighted sum of Y at one or more recent times and / or the prediction error at one or more recent times.

[0064] Assuming p, q, d are known, ARIMA can be expressed mathematically as:

[0065]

[0066] Using this model, given a time series, we can predict the value of the next period based on the learning results of the historical data series. In other words, we can infer the data value of the next period based on the historical data of the input device, such as the temperature, pressure, and pressure of the oil tank. When the predicted value exceeds the normal threshold, it is confirmed that the equipment is at risk of failure.

[0067] In some embodiments, after predicting that any device to be inspected has a risk of failure, the effect corresponding to the type of failure risk is matched through a pre-established special effect library, and the effect is displayed at the corresponding device to be inspected, such as smoke, fire, sound, etc., to achieve a fault prompt or automatic alarm.

[0068] Step S13: If it is predicted that any device to be inspected has a risk of failure, the shortest path from the current position of the virtual inspector to the device to be inspected with a risk of failure is determined based on the road network, so that the virtual inspector can reach the device to be inspected along the shortest path and perform corresponding processing.

[0069] Equipment in oil and gas field stations often require high-intensity and high-level operation, so when a fault occurs, emergency treatment is required immediately. In the past, most intelligent inspections set a path, and artificial intelligence walked repeatedly on the path, but this is not only inefficient, but also unable to respond to emergencies in a timely manner. In this embodiment, when the time series prediction model predicts that there are safety hazards in the equipment and triggers the fault special effect, the virtual inspector will automatically find the shortest path on the road network and reach the fault point in the fastest way to solve the problem in time.

[0070] Determining the shortest path from the current location of the virtual inspector to the equipment to be inspected that is at risk of failure can include taking the current location of the virtual inspector as the source node, and determining, based on the road network, a node that can directly reach the equipment to be inspected that is at risk of failure as the failure node; determining, based on the road network, the shortest path from the source node to each failure node; and determining the shortest path among the obtained shortest paths as the shortest path from the current location of the virtual inspector to the equipment to be inspected that is at risk of failure.

[0071] Specifically, the Dijkstra algorithm can be used to determine the shortest path from the source node to each faulty node. First, save the distance from the source node to all nodes (including the source node) and find the shortest one. Then mark this point, find the shortest one among the unmarked points, record the predecessor node of this point, and repeat this step until all points are marked. The algorithm steps are as follows:

[0072] Step 1: Construct a distance array dist[n] to represent the distance from the source node to all other nodes, where the distance to itself is 0. If the node cannot be reached directly, the distance is represented by infinity.

[0073] Step 2: Each time, select the node k that is closest to the source node and has not been marked as having the shortest distance determined from the dist[n] array, and mark it as having the shortest distance determined.

[0074] Step 3: Then use the idea of ​​relaxed edges to update the shortest distance from the source node to other nodes. As long as the condition dist[d]>dist[k]+w[k][d] is met, it means that the intermediate node k can be used to shorten the distance from the source node to the node d.

[0075] Step 4: Repeat steps 2-3 until all nodes are marked as confirmed.

[0076] See also Figure 3 As shown in Figure 2c An example diagram of the inspection route developed based on the road network diagram and the shortest path from the virtual inspector's current location to the fault point.

[0077] In some embodiments, after predicting that any device to be inspected has a risk of failure, the method further includes generating a corresponding fault handling method according to the fault risk data. Accordingly, corresponding processing is performed, including performing corresponding processing according to the received fault handling method.

[0078] The visual intelligent inspection method based on digital twin digital-analog separation provided in the first embodiment of the present invention uses digital twin and digital-analog separation technology to establish a three-dimensional visualization model of oil and gas field stations, construct a road network, and customize the inspection route based on the road network; during the inspection process of the virtual inspector along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at a set interval, and fault prediction is performed through a time series prediction model based on the current data sequence; if it is predicted that any equipment to be inspected has a risk of failure, the shortest path from the current position of the virtual inspector to the equipment to be inspected with a risk of failure is determined according to the road network, so that the virtual inspector can reach the equipment to be inspected along the shortest path and perform corresponding processing. It is possible to establish a lightweight simulation model of the working scene of the oil and gas field station based on digital twin and digital-analog separation technology, and predict faults through mining and analysis of operating data, so as to achieve a rapid improvement in inspection quality and efficiency.

[0079] The visual intelligent inspection method based on digital twin digital-analog separation provided in the first embodiment of the present invention predicts the fault of the equipment to be inspected according to the current data sequence of the equipment to be inspected by using the time series prediction model trained by the historical data sequence of the equipment to be inspected, so that corresponding processing can be performed in advance before the fault occurs, thereby avoiding the occurrence of faults, achieving safe production, and saving manpower and financial resources for fault handling.

[0080] The visualized intelligent inspection method based on digital twin digital-analog separation provided in the first embodiment of the present invention predicts that any device to be inspected has a fault risk. According to the type of fault risk, the method matches the effect corresponding to the type through a pre-established special effect library, and displays the effect at the corresponding device to be inspected. The fault effect can be displayed visually through sound, image or video, so that the user can understand the location and type of the fault risk more quickly and vividly.

[0081] The visualized intelligent inspection method based on digital twin digital-analog separation provided in the first embodiment of the present invention predicts that any device to be inspected has a risk of failure, and generates a corresponding fault handling method based on the fault risk data, so that after the virtual inspector arrives at the device to be inspected, he or she can perform corresponding processing according to the received fault handling method. Virtual simulation training can be carried out to train manual inspections, which not only makes personnel more familiar with the inspection path, but also allows them to understand how to handle failures; it can replace manual inspections to a certain extent, reduce the frequency of manual inspections, and avoid the insecurity of personnel going to the site for training or inspections.

[0082] Embodiment 2

[0083] Embodiment 2 of the present invention provides a specific application example of a visualized intelligent inspection method based on digital-analog separation of digital twins.

[0084] The 3D model of the oil and gas field production scene can be loaded through the editor. Figure 4a As shown in Figure 1, the 3D visualization model provides a visualization environment that is consistent with the on-site environment. Based on this digital twin base, the inspection route can be customized. Figure 4b As shown, by clicking the mouse on a specific location (indicated by the flag), the system generates an inspection route based on the click sequence. Users can further select a virtual inspector model and configure a device visualization chart. When you click Preview, the system will publish a new web page, and the virtual inspector will automatically roam around the scene according to the established inspection route and carry out inspection work. See Figure 4c shown.

[0085] During the virtual inspector's inspection along the inspection route, see Figure 5a As shown in the figure, the system provides equipment failure warning based on the time series prediction model and the data bound to the equipment, such as Figure 5bAs shown in the figure, when the temperature of a device is abnormal, particle effects such as smoke can be superimposed and displayed on the corresponding device. At this time, the virtual inspector no longer follows the established trajectory ( Figure 5a The dashed line in the figure) instead takes the shortest path ( Figure 5b The arrow line in the figure) rushes to the place where the accident occurred. Figure 5c As shown, when the virtual inspector arrives near the accident, the system automatically displays the emergency handling copy to help the user become familiar with and master the handling process. It can be seen that based on the method provided by this embodiment, users can conduct dynamic training on processes, production operations, equipment inspection and maintenance, equipment operation cards, safety emergency response, etc., and simulate process flows, theoretical knowledge of equipment inspection and maintenance, production operation flows, etc. in the form of animation, voice, text, video, etc., and conduct daily training for employees in a visual way, allowing employees to conduct training anytime and anywhere. The training courseware is realistic and vivid, and the training does not require a real environment, avoiding the insecurity of on-site training.

[0086] The visual intelligent inspection method based on digital twin digital-analog separation provided by the embodiment of the invention uses digital twin technology to quickly obtain on-site operation data and build a virtual work scene, and performs early warning and diagnosis of fault information through mining and analysis of operation data, which can achieve rapid improvement of inspection quality and efficiency. Therefore, the visual intelligent virtual inspection technology based on digital twin digital-analog separation can not only dynamically monitor equipment, predict faults and carry out timely repairs, but also realize remote control, thereby greatly reducing operating costs and improving equipment safety.

[0087] Based on the inventive concept of the present invention, the embodiment of the present invention also provides a visual intelligent inspection device based on digital twin digital-analog separation, the structure of the device is as follows Figure 6 As shown, including:

[0088] A three-dimensional model building module 61 is used to build a three-dimensional visualization model of the oil and gas field station by using digital twin and digital-analog separation technology, construct a road network, and customize an inspection route based on the road network;

[0089] A fault prediction module 62 is used to update the current data sequence of the equipment to be inspected in the model at a set interval during the inspection process of the virtual inspector along the inspection route, and perform fault prediction based on the current data sequence through a time series prediction model;

[0090] The shortest path determination module 63 is used to determine the shortest path from the current position of the virtual inspector to the device to be inspected that has a risk of failure based on the road network if it is predicted that any device to be inspected has a risk of failure, so that the virtual inspector can reach the device to be inspected along the shortest path and perform corresponding processing.

[0091] In some optional embodiments, the shortest path determination module 63 is used to:

[0092] The current position of the virtual inspector is taken as the source node, and the node that can directly reach the equipment to be inspected with a risk of failure is determined according to the road network as the fault node; the shortest path from the source node to each fault node is determined according to the road network; the shortest path among the obtained shortest paths is determined as the shortest path from the current position of the virtual inspector to the equipment to be inspected with a risk of failure.

[0093] In some optional embodiments, the shortest path determination module 63 is used to:

[0094] The shortest path from the source node to each fault node is determined by the Dijkstra algorithm.

[0095] In some optional embodiments, the above device further includes a special effect display module 64, which is used to:

[0096] After the fault prediction module 62 predicts that any device to be inspected has a fault risk, it matches the effect corresponding to the type of fault risk through a pre-established special effects library and displays the effect at the corresponding device to be inspected.

[0097] In some optional embodiments, the above device further includes a fault handling method generating module 65, which is used to:

[0098] A corresponding fault handling method is generated according to the fault risk data, so that the virtual inspector reaches the device to be inspected along the shortest path and performs corresponding processing according to the received fault handling method.

[0099] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0100] Based on the inventive concept of the present invention, an embodiment of the present invention also provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed by a processor, the above-mentioned visual intelligent inspection method based on digital twin digital-analog separation is implemented.

[0101] Based on the inventive concept of the present invention, an embodiment of the present invention also provides a server, including: a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein when the processor executes the program, the above-mentioned visual intelligent inspection method based on digital-analog separation of digital twins is implemented.

[0102] Unless otherwise specifically stated, terms such as processing, computing, calculating, determining, displaying, etc. may refer to the actions and / or processes of one or more processing or computing systems, or similar devices, which operate and convert data represented as physical (e.g., electronic) quantities within registers or memories of a processing system into other data similarly represented as physical quantities within memories, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals may be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0103] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0104] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that an embodiment of the claimed subject matter requires more features than those set forth in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0105] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0106] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0107] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0108] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A visual intelligent inspection method based on digital twin digital-analog separation, characterized in that: include: Use digital twin and digital-analog separation technology to establish a three-dimensional visualization model of the oil and gas field station, construct a road network, determine the selected virtual inspector model, the road network is used to support the orderly actions of the virtual inspectors in it, and customize the inspection route based on the road network; During the inspection process of the virtual inspector along the inspection route, the current data sequence of the equipment to be inspected in the model is updated at set intervals, and fault prediction is performed through a time series prediction model based on the current data sequence; If it is predicted that any device to be inspected has a risk of failure, the current position of the virtual inspector is used as the source node, and a node that can directly reach the device to be inspected with a risk of failure is determined according to the road network as the failure node; the shortest path from the source node to each failure node is determined according to the road network; The shortest path among the obtained shortest paths is determined as the shortest path from the current position of the virtual inspector to the device to be inspected with a risk of failure, so that the virtual inspector reaches the device to be inspected along the shortest path and performs corresponding processing.

2. The method according to claim 1, characterized in that The time series prediction model is a model trained using a historical data sequence of the equipment to be inspected, wherein the historical data sequence includes at least one data cycle, and the data cycle includes fault data.

3. The method according to claim 2, characterized in that The time series prediction model is an autoregressive integrated moving average model (ARIMA) model.

4. The method according to claim 1, characterized in that Determining the shortest path from the source node to each fault node includes: The shortest path from the source node to each fault node is determined by the Dijkstra algorithm.

5. The method according to claim 1, characterized in that After predicting that any device to be inspected has a risk of failure, the method further includes: According to the type of fault risk, the corresponding effect of the type is matched through the pre-established special effects library, and the effect is displayed at the corresponding equipment to be inspected.

6. The method according to any one of claims 1 to 5, characterized in that: After predicting that any device to be inspected has a risk of failure, it also includes: Generate corresponding fault handling methods according to fault risk data; accordingly, The corresponding processing includes: Perform corresponding processing according to the received fault handling method.

7. A visual intelligent inspection device based on digital twin digital-analog separation, characterized in that: include: A three-dimensional model building module is used to build a three-dimensional visualization model of the oil and gas field station using digital twin and digital-analog separation technology, construct a road network, determine the selected virtual inspector model, and customize the inspection route based on the road network. A fault prediction module is used to update the current data sequence of the equipment to be inspected in the model at set intervals during the inspection process of the virtual inspector along the inspection route, and perform fault prediction based on the current data sequence through a time series prediction model; The shortest path determination module is used to, if it is predicted that any device to be inspected has a risk of failure, use the current position of the virtual inspector as a source node, determine a node that can directly reach the device to be inspected with a risk of failure based on the road network, and determine the shortest path from the source node to each fault node based on the road network; The shortest path among the obtained shortest paths is determined as the shortest path from the current position of the virtual inspector to the device to be inspected with a risk of failure, so that the virtual inspector reaches the device to be inspected along the shortest path and performs corresponding processing.

8. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, which, when executed by a processor, implement the visual intelligent inspection method based on digital twin digital-analog separation as described in any one of claims 1 to 6.

9. A server, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the visual intelligent inspection method based on digital twin digital-analog separation as described in any one of claims 1 to 6 is implemented.

Images