CN116108717A - A digital twin-based transportation equipment operation prediction method and device - Google Patents

Abstract

The invention relates to the technical field of transportation and discloses a transportation equipment operation prediction method and device based on digital twinning. The method comprises the steps of constructing a digital twin model based on topological structure data and basic environment data of target transportation equipment, importing operation data generated in a historical operation process of the target transportation equipment into the digital twin model, performing simulation calculation on the obtained target digital twin model, training the target digital twin model according to the obtained simulation operation data and the operation data to obtain a target operation state prediction model, inputting real-time state data of the target digital twin model into the target operation state prediction model to perform prediction calculation, and finally obtaining an operation state prediction result. The invention realizes intelligent prediction of the running state of the transportation equipment and provides objective and effective data basis for realizing the running reliability and safety of the transportation equipment.

Description

A digital twin-based transportation equipment operation prediction method and device

technical field

The invention relates to the field of transportation technology, in particular to a digital twin-based transportation equipment operation prediction method and device.

Background technique

Due to the needs of population mobility and cargo transportation, people's production and life are inseparable from transportation. With the development of transportation in a more efficient and efficient direction, the losses and injuries caused by traffic accidents are also increasing, and the reliability and safety of transportation are particularly important.

In the current transportation, most of the cases still rely on human driving control, and human driving control has interference from human factors, and there may be problems of fatigue and misjudgment, which may cause traffic accidents. Although some methods such as unmanned driving can avoid the interference of some human factors, various program loopholes and poor ability to deal with complex environments make it still unable to be effectively popularized.

If the traffic operation status can be intelligently predicted, and corresponding countermeasures can be quickly taken according to the predicted status results, the incidence of traffic accidents can be reduced, and the loss and casualty can also be minimized in the case of unavoidable traffic accidents.

At the same time, whether it is mechanical or electronic devices in transportation equipment, there is a problem of working life, and its working life will be different under different environments and different working intensities, so it is easy to have relatively large safety hazards. With the continuous improvement of the functions and performance of current transportation equipment, the number of parts and components has greatly increased and the complexity of connection has greatly increased, and the possibility of sudden abnormalities such as equipment failures and traffic accidents has greatly increased. In the general inspection process, it is difficult to directly locate a potentially risky component. The failure of parts and components of transportation equipment can easily cause damage and loss of control of transportation equipment, and lead to huge damage under high-speed and high-load conditions.

Contents of the invention

The present invention provides a digital twin-based transportation equipment operation prediction method and device, which solves the technical problem that it is difficult to realize the operation state prediction of transportation equipment in the prior art.

The first aspect of the present invention provides a method for predicting the operation of transportation equipment based on digital twins, including:

Obtain the topological structure data and basic environmental data of the target transportation equipment;

Constructing a corresponding digital twin equipment model according to the topology data, constructing a corresponding digital twin environment model according to the basic environment data, and correlating the digital twin equipment model and the digital twin environment model to obtain a digital twin model;

Obtaining operation data generated by the target transportation equipment during historical operation;

importing the operating data into the digital twin model to obtain a target digital twin model matching the target transportation equipment;

Performing simulation calculations on the target digital twin model to obtain simulation operation data generated during the operation of the target digital twin model;

Train the target digital twin model according to the operation data and the simulation operation data to obtain a target operation state prediction model;

Perform real-time status update on the target digital twin model to obtain corresponding real-time status data;

The real-time state data is input into the target operation state prediction model for prediction calculation, and the operation state prediction result of the target transportation equipment is obtained.

According to an achievable manner of the first aspect of the present invention, the training of the target digital twin model according to the operation data and the simulation operation data includes:

Comparing the operating data with the simulated operating data to obtain error data;

Correcting the target digital twin model according to the error data;

Constructing a sample set based on the operating data and the simulation operating data;

The corrected target digital twin model is trained according to the sample set.

According to an achievable manner of the first aspect of the present invention, the operating state prediction results include fault diagnosis results, and the target digital twin model generates several functional chain groups during the training process and records the functional chain groups to which each component belongs , the function chain group is composed of several components that realize specific functions; the input of the real-time state data into the target operating state prediction model for prediction calculation includes:

Judging the fault according to the output response of the function chain group;

Combining with component crossing of functional chain group for fault location.

According to an implementable manner of the first aspect of the present invention, the operation data includes environmental history data, equipment operation data, equipment component data, equipment maintenance data and cost data;

The operation status prediction results also include health assessment results, lifetime prediction results and cost calculation results.

According to an achievable manner of the first aspect of the present invention, the method further includes:

determining a target operating strategy according to the operating state prediction result;

The operating state of the target transportation equipment is controlled according to the target operating strategy.

According to an achievable manner of the first aspect of the present invention, the method further includes:

The real-time state data is stored parametrically through the target digital twin model.

According to an achievable manner of the first aspect of the present invention, the method further includes:

Obtaining target traffic accident data of the target transportation equipment; the target traffic accident data includes operation control data before the target traffic accident and operation status data after the target traffic accident;

Derivation analysis is performed on the target traffic accident data based on the target operating state prediction model to obtain deduction analysis data on the target traffic accident process.

The second aspect of the present invention provides a digital twin-based transportation equipment operation prediction device, including:

The first acquisition module is used to acquire topology data and basic environment data of the target transportation equipment;

A building module, configured to construct a corresponding digital twin equipment model according to the topology data, construct a corresponding digital twin environment model according to the basic environment data, and correlate the digital twin equipment model and the digital twin environment model to obtain digital twin model;

The second acquisition module is used to acquire the operation data generated by the target transportation equipment during the historical operation process;

An import module, configured to import the operating data into the digital twin model to obtain a target digital twin model matching the target transportation equipment;

A simulation module, configured to perform simulation calculations on the target digital twin model, and obtain simulation operation data generated during the operation of the target digital twin model;

A training module, configured to train the target digital twin model according to the operating data and the simulated operating data to obtain a target operating state prediction model;

An update module, configured to update the target digital twin model in real time to obtain corresponding real-time state data;

A predictive calculation module, configured to input the real-time state data into the target operating state prediction model to perform predictive calculation, and obtain the predicted result of the operating state of the target transportation equipment.

According to an achievable manner of the second aspect of the present invention, the training module includes:

a comparison unit, configured to compare the operation data with the simulation operation data to obtain error data;

a correction unit, configured to correct the target digital twin model according to the error data;

a construction unit, configured to construct a sample set based on the operation data and the simulation operation data;

A training unit, configured to train the corrected target digital twin model according to the sample set.

According to an achievable manner of the second aspect of the present invention, the operating state prediction results include fault diagnosis results, and the target digital twin model generates several functional chain groups during the training process and records the functional chain groups to which each component belongs , the functional chain group is made up of several components that realize specific functions; the predictive calculation module includes:

a fault judging unit, configured to judge a fault according to the output response of the functional chain group;

The fault locating unit is used for fault locating in combination with component crossing of the functional chain group.

According to an implementable manner of the second aspect of the present invention, the operation data includes environmental history data, equipment operation data, equipment component data, equipment maintenance data and cost data;

The operation status prediction results also include health assessment results, lifetime prediction results and cost calculation results.

According to an implementable manner of the second aspect of the present invention, the device further includes:

A determining module, configured to determine a target operating strategy according to the operating state prediction result;

A control module, configured to control the operating state of the target transportation equipment according to the target operating strategy.

According to an implementable manner of the second aspect of the present invention, the device further includes:

A storage module, configured to parametrically store the real-time state data through the target digital twin model.

According to an implementable manner of the second aspect of the present invention, the device further includes:

A third acquisition module, configured to acquire target traffic accident data of the target transportation equipment; the target traffic accident data includes operation control data before the target traffic accident and operation status data after the target traffic accident;

The derivation analysis module is configured to perform deduction analysis on the target traffic accident data based on the target operating state prediction model to obtain deduction analysis data on the target traffic accident process.

The third aspect of the present invention provides a digital twin-based transportation equipment operation prediction device, including:

The memory is used to store instructions; wherein, the instructions are used to implement the digital twin-based transport equipment operation prediction method described in any of the ways that can be realized;

a processor configured to execute instructions in the memory.

The fourth aspect of the present invention is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the digital twin-based Transportation equipment operation prediction method.

As can be seen from the above technical solutions, the present invention has the following advantages:

The present invention constructs a digital twin model based on the topological structure data and basic environment data of the target transportation equipment, imports the operation data generated by the target transportation equipment during the historical operation process into the digital twin model, and performs simulation calculation on the obtained target digital twin model, Train the target digital twin model according to the obtained simulation operation data and the operation data to obtain the target operation state prediction model, input the real-time state data of the target digital twin model into the target operation state prediction model for prediction calculation, and finally obtain the operation state Prediction results; the present invention can effectively, comprehensively and accurately realize the digital description of the physical entity of transportation equipment by constructing a digital twin model; the simulation calculation of the obtained target digital twin model can comprehensively consider multi-directional influencing factors, so that the simulation The calculation is more realistic; by importing historical data into the digital twin model and performing model training on the digital twin model, the simulation data and historical data can be effectively used to build an effective model to ensure the effective matching of virtual and real objects; Real-time status update, predictive calculation based on the status information of the digital model, so that the digital twin model is always in a state of learning and progress, predictive calculation based on real-time status data, and realizes intelligent prediction of the operating status of transportation equipment; the operating status prediction The results can be used in transportation equipment maintenance and accident analysis, providing an objective and effective data basis for the reliability and safety of transportation equipment operation.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings on the premise of not paying creative efforts.

Fig. 1 is a flow chart of a digital twin-based transportation equipment operation prediction method provided by an optional embodiment of the present invention;

Fig. 2 is a structural connection block diagram of a digital twin-based transportation equipment operation prediction device provided by an optional embodiment of the present invention.

Reference signs:

1-first acquisition module; 2-construction module; 3-second acquisition module; 4-import module; 5-simulation module; 6-training module; 7-update module; 8-forecast calculation module.

Detailed ways

Embodiments of the present invention provide a digital twin-based transportation equipment operation prediction method and device, which are used to solve the technical problem that it is difficult to realize the operation status prediction of transportation equipment in the prior art.

In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

The invention provides a digital twin-based transportation equipment operation prediction method.

Please refer to FIG. 1 . FIG. 1 shows a flow chart of a digital twin-based transportation equipment operation prediction method provided by an embodiment of the present invention.

A digital twin-based transportation equipment operation prediction method provided by an embodiment of the present invention includes:

Step S1, acquiring topology data and basic environment data of the target transportation equipment.

The target transportation equipment in this embodiment is a transportation equipment that needs to perform operation state prediction, and the type of the transportation equipment may be a vehicle, a ship, an airplane, and the like.

Among them, the basic environmental data may include road condition data, climate data, personnel data and cargo data.

The topology data and basic environment data can be obtained based on the information collection component. The information collection component may include a GPS data sensor, an acceleration sensor, a gyroscope sensor, an attitude sensor, a laser ranging sensor, an environment sensor and a camera. Among them, the GPS data sensor is mainly used to collect the positioning information of the operating equipment to determine the position and speed of the transportation equipment. The acceleration sensor is used to obtain the running acceleration of the transportation equipment. The gyroscope sensor is used to sense the change of the acceleration of the transportation equipment and the attitude of the transportation equipment, so as to further obtain the overall state of the transportation equipment. Attitude sensors can obtain data such as three-dimensional attitude and orientation of transportation equipment, and accurately obtain the state of transportation equipment in three-dimensional space. Laser ranging sensors can be used to determine the distance to a target. Environmental sensors are used to collect the temperature, humidity and wind direction of the environment where the transportation equipment is located. Cameras can be used to obtain image data of transportation equipment during operation.

Step S2, constructing a corresponding digital twin equipment model according to the topology data, constructing a corresponding digital twin environment model according to the basic environment data, and correlating the digital twin equipment model and the digital twin environment model to obtain a digital twin Model.

When constructing a digital twin equipment model, first establish a geometric model, and the assembly connection relationship of each component in the geometric model is consistent with the physical space. For the convenience of description, the physical space here refers to the actual space, while the virtual space refers to the space where the digital twin model is located. Sometimes, in order to simplify the digital twin equipment model, certain restrictions are set for the digital twin equipment model in the virtual space, so that it can meet certain production and operation functions, and an integrated digital twin equipment model with topology characteristics is formed. According to the established geometric model, physical attributes are added to the digital twin equipment model in the virtual space, such as the process requirements of some parts, constraints on the connecting parts, material property information, etc., to make it more in line with the equipment in the physical space.

The construction of the digital twin environment model takes into account the interrelationship between equipment and the environment in the physical space. The normal operation of the equipment has a lot to do with the environment, and to fully present the simulated operation of the equipment in the virtual space cannot leave the environment. The basic environmental data mainly includes data such as personnel conditions, climate conditions, and environmental temperature and humidity. For transportation equipment, road conditions, transportation roads and surrounding environment data also need to be taken into account when obtaining basic environmental data.

In this embodiment, the digital twin model is obtained by associating the digital twin equipment model with the digital twin environment model, which can completely map the digital twin model from the physical space, facilitate subsequent scientific and comprehensive simulation calculations, and then build an accurate Run the predictive model.

Step S3, acquiring operation data generated during historical operation of the target transportation equipment.

As a specific implementation, in order to comprehensively consider physical reality, the operation data includes environmental history data, equipment operation data, equipment component data and equipment maintenance data.

Wherein, the environmental history data refers to the environmental data during the operation of the equipment, and the data can represent the change of the environment. Excluding the impact of climate change, it can be analyzed based on the environmental data that the environment is affected by the operation of the equipment.

The equipment operation data is the reaction data of various actions of the equipment during operation, as well as the cooperation data of the components during the operation, including the response to specific inputs.

The data of equipment parts generally includes the load bearing capacity, life parameters and connection strength torque of the parts, which can fully reflect the physical characteristics of the parts.

Equipment maintenance data includes maintenance and replacement information of specific components, maintenance cycle, and maintenance methods and costs of specific different faults. This data can be used to estimate maintenance costs at a later stage while making intelligent operational predictions.

Step S4, importing the operation data into the digital twin model to obtain a target digital twin model matching the target transportation equipment.

In this embodiment, by importing operating data into the digital twin model, it can be transformed and matched from an ideal model to an actual physical object to improve the accuracy and reliability of predictive calculations.

Step S5, performing simulation calculation on the target digital twin model to obtain simulation running data generated during the running process of the target digital twin model.

Among them, the content of the simulation calculation includes some calculations that can fully conform to the physical space, such as the load calculation of the components, the heat generation calculation, and the structural stability calculation. The way of simulation calculation can be finite element analysis, aerodynamic calculation and so on. The simulation operation data is mainly used for future intelligent prediction and judgment.

The degree of conformity between the digital twin model and the physical space can be judged through simulation calculations. Generally, some general simulation calculations can be done at the beginning, and the calculation results can be compared with the results of the physical space, and the digital twin model can be adjusted according to the comparison results. Get results consistent with physical space. Usually, a calibration module can be established to calibrate the digital twin model, so that the properties and behaviors in the digital twin model are closer to the real objects in the physical space.

In this embodiment, by performing simulation calculation on the target digital twin model to obtain simulation operation data, compared with the method of obtaining data based on actual physical space experiments, the time cost of data acquisition can be reduced.

In step S6, the target digital twin model is trained according to the operation data and the simulation operation data to obtain a target operation state prediction model.

In an achievable manner, the training of the target digital twin model according to the operation data and the simulation operation data includes:

Comparing the operating data with the simulated operating data to obtain error data;

Correcting the target digital twin model according to the error data;

Constructing a sample set based on the operating data and the simulation operating data;

The corrected target digital twin model is trained according to the sample set.

In this embodiment, the target digital twin model is first corrected during the model training process, which can ensure that the digital twin model is consistent with the functional characteristics of the equipment and environment in the physical space, which is beneficial to improve the accuracy of training.

In model training, an efficient and applicable intelligent prediction model can be obtained based on the combination of judgment model and generative model. This refers to performing evolutionary calculations on the basis of a suitable model based on operating data and simulation data to obtain suitable model parameters. The judgment model may be one or more combinations of linear regression, logarithmic regression, linear discriminant analysis, support vector machine, boosting, conditional random field, neural network, and the like. The generative model can be a collection of one or more models, such as Gaussian mixture model, hidden Markov model and naive Bayesian model.

The generated target operating state prediction model can predict the operating state of the equipment according to the input state, usually it can give the results of health assessment, fault diagnosis and life prediction, so as to help relevant personnel find problems in advance and take measures to deal with them. To reduce or reduce losses and casualties.

It should be noted that, for the process of generating the prediction model based on the method of combining the judgment model and the generation model, reference may be made to the corresponding process in the prior art, which is not limited in this embodiment.

Step S7, updating the real-time status of the target digital twin model, and acquiring corresponding real-time status data.

Among them, the real-time state usually includes equipment state, environment state and input and output state. The equipment state and environment state belong to the state that evolves with time; while the input and output state refers to the response state, that is, the response to a specific input. The update of equipment status and environmental status can make the digital twin model change with the physical space. The input-output state includes the output of the device and the output of the environment under the specific input of the device.

Step S8, inputting the real-time state data into the target operation state prediction model to perform prediction calculation, and obtain the operation state prediction result of the target transportation equipment.

In an achievable manner, the operating state prediction results include fault diagnosis results, and the target digital twin model generates several functional chain groups during the training process and records the functional chain groups to which each component belongs. The functional chain The group is composed of several components that realize specific functions; the input of the real-time state data into the target operating state prediction model for prediction calculation includes:

Judging the fault according to the output response of the function chain group;

Combining with component crossing of functional chain group for fault location.

Among them, the function chain group here is a combination of parts that realize a certain function, and there will be mutual cross-connections of parts in the function chain group. For example, it is assumed that the first functional chain group and the second functional chain group are composed of several components, and there is an intersection of target components. Then, the operation status of the target component can be determined through the input and output of the first functional chain group and the second functional chain group, so as to realize rapid determination and location of the fault.

Taking the target transportation equipment as a car as an example, the functional chain group that realizes the buffering and stable operation of the car is composed of tires, rims, springs, shock absorbers, stabilizers, lower arms and other components, while the functional components that realize the steering of the car are composed of Tires, rims, lower arms, steering gears, steering wheels, etc., there are intersections of parts. By turning the steering wheel (input), it is found that the steering of the car is unstable (output), and when the car is bumpy (output) when passing the rough road (input), it can be located on the cross parts, so as to realize the rapid positioning of the faulty parts.

In an implementable manner, the operation data further includes cost data; and the operation status prediction result further includes a cost calculation result.

Wherein, the cost data may include cost data information such as operating cost, parts cost and labor cost.

In an achievable manner, the method also includes:

determining a target operating strategy according to the operating state prediction result;

The operating state of the target transportation equipment is controlled according to the target operating strategy.

As a specific implementation manner, a list of correspondences between operation state prediction results and target operation strategies may be constructed, and the target operation strategy may be determined based on the list.

As another specific implementation manner, the operation state prediction result may be fed back to a preset user terminal, and the fed-back operation strategy may be used as a target operation strategy.

When determining the target operation policy, the protection priority can be set, and the restriction conditions determined by the operation policy can be constructed according to the set protection priority. For example, the personal safety of the staff can be set as the first element, so that when the target operation strategy is determined, the protection of the staff's safety can be used as a restrictive condition.

Corresponding restrictive conditions can also be set according to the restrictions of the equipment or environment, and the best measures that the target can take are determined according to the restrictive conditions as the target operation strategy. If the brake is found to be damaged during the operation of the equipment, the operation input is limited at this time. It can be dealt with by using the rigid parts such as the bumper and carriage of the car to rub and collide with the natural obstacles on the roadside to achieve a forced stop speed.

In this embodiment, the target operation strategy is obtained according to the operation state prediction results, and then the operation state of the target transportation equipment is controlled, which can effectively reduce the number of operators, realize mechanized and intelligent operation management, and realize intelligent operation when combined with unmanned driving. transportation.

In an achievable manner, the method also includes:

The real-time state data is stored parametrically through the target digital twin model.

Parametric storage can effectively save storage space, and by importing parameters into the digital twin model, the digital twin model can be efficiently used to visually describe the physical entities of transportation equipment.

For the established target operating state prediction model, some possible processes can be determined when the input (operating control) and output (operating state) are determined. For example, based on the state of the equipment and the state of the environment immediately before the accident, the accident process can be calculated. Based on this, in an achievable manner, the method also includes:

Obtaining target traffic accident data of the target transportation equipment; the target traffic accident data includes operation control data before the target traffic accident and operation status data after the target traffic accident;

Derivation analysis is performed on the target traffic accident data based on the target operating state prediction model to obtain deduction analysis data on the target traffic accident process.

Further, the existing information recording system can be used to receive and save the data obtained during the execution of the method. As a specific implementation, the information recording system is a black box.

In transportation, especially in the case of air transportation, once a traffic accident occurs, it will cause huge injuries and losses. When a traffic accident occurs, in the prior art, the information of the traffic accident is generally obtained by analyzing the data stored in the black box. This method is relatively one-sided, and it is difficult to find out the specific cause of the traffic accident. However, in this application, by saving the state information of the traffic accident when it occurs, the final state of the traffic accident and the data in the black box can be imported into the target operating state prediction model, and the traffic accident can be analyzed by using the target operating state prediction model. The process is calculated, so as to reproduce the accident process concretely and vividly, and the specific cause can be quickly and accurately obtained.

In the above-mentioned embodiments of the present invention, by constructing a digital twin model, the digital description of the physical entity of transportation equipment can be effectively, comprehensively and accurately realized; the simulation calculation of the obtained target digital twin model can comprehensively consider multi-directional influencing factors, so that The simulation calculation is more realistic; by importing historical data into the digital twin model and performing model training on the digital twin model, the simulation data and historical data can be effectively used to build an effective model to ensure the effective matching and combination of virtual and real objects; the digital twin model Perform real-time status updates and predictive calculations based on the status information of the digital model, so that the digital twin model is always in a state of learning and progress. Predictive calculations are performed based on real-time status data to realize intelligent prediction of the operating status of transportation equipment; the operating status The prediction results can be used in transportation equipment maintenance and accident analysis, providing an objective and effective data basis for the reliability and safety of transportation equipment operation.

The present invention also provides a digital twin-based transportation equipment operation prediction device, which can be used to implement the digital twin-based transportation equipment operation prediction method described in any one of the above-mentioned embodiments of the present invention.

Please refer to FIG. 2 . FIG. 2 shows a structural connection block diagram of a digital twin-based transportation equipment operation prediction device provided by an embodiment of the present invention.

An embodiment of the present invention provides a device for predicting the operation of transportation equipment based on digital twins, including:

The first acquisition module 1 is used to acquire the topology data and basic environment data of the target transportation equipment;

A construction module 2, configured to construct a corresponding digital twin equipment model according to the topology data, construct a corresponding digital twin environment model according to the basic environment data, and correlate the digital twin equipment model and the digital twin environment model with each other Get the digital twin model;

The second acquisition module 3 is used to acquire the operating data generated during the historical operation of the target transportation equipment;

An import module 4, configured to import the operating data into the digital twin model to obtain a target digital twin model matching the target transportation equipment;

The simulation module 5 is used to perform simulation calculation on the target digital twin model, and obtain the simulation operation data generated during the operation of the target digital twin model;

A training module 6, configured to train the target digital twin model according to the operating data and the simulated operating data to obtain a target operating state prediction model;

An update module 7, configured to update the target digital twin model in real time to obtain corresponding real-time status data;

The prediction calculation module 8 is configured to input the real-time state data into the target operation state prediction model to perform prediction calculation, and obtain the operation state prediction result of the target transportation equipment.

In an achievable manner, the training module 6 includes:

a comparison unit, configured to compare the operation data with the simulation operation data to obtain error data;

a correction unit, configured to correct the target digital twin model according to the error data;

a construction unit, configured to construct a sample set based on the operation data and the simulation operation data;

A training unit, configured to train the corrected target digital twin model according to the sample set.

In an achievable manner, the operating state prediction results include fault diagnosis results, and the target digital twin model generates several functional chain groups during the training process and records the functional chain groups to which each component belongs. The functional chain The group is made up of several parts that realize specific functions; the predictive calculation module 8 includes:

a fault judging unit, configured to judge a fault according to the output response of the functional chain group;

The fault locating unit is used for fault locating in combination with component crossing of the functional chain group.

In an implementable manner, the operation data includes environmental history data, equipment operation data, equipment component data, equipment maintenance data and cost data;

The operation status prediction results also include health assessment results, lifetime prediction results and cost calculation results.

In an achievable manner, the device also includes:

A determining module, configured to determine a target operating strategy according to the operating state prediction result;

A control module, configured to control the operating state of the target transportation equipment according to the target operating strategy.

In an achievable manner, the device also includes:

A storage module, configured to parametrically store the real-time state data through the target digital twin model.

In an achievable manner, the device also includes:

A third acquisition module, configured to acquire target traffic accident data of the target transportation equipment; the target traffic accident data includes operation control data before the target traffic accident and operation status data after the target traffic accident;

The derivation analysis module is configured to perform deduction analysis on the target traffic accident data based on the target operating state prediction model to obtain deduction analysis data on the target traffic accident process.

The present invention also provides a digital twin-based transportation equipment operation prediction device, including:

The memory is used to store instructions; wherein the instructions are used to implement the digital twin-based transportation equipment operation prediction method described in any one of the above embodiments;

a processor configured to execute instructions in the memory.

The present invention also provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the digital twin-based traffic as described in any one of the above embodiments is realized. Transportation equipment operation forecasting method.

Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described devices and modules can refer to the corresponding processes in the foregoing method embodiments, and the specific beneficial effects of the above-described devices and modules , reference can be made to the corresponding beneficial effects in the foregoing method embodiments, and details are not repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or It may be integrated into another device, or some features may be omitted, or not implemented.

The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, each module may exist separately physically, or two or more modules may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software function modules.

If the integrated modules are realized in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the essence of the technical solution of the present invention or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-OnlyMemory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc and other media that can store program codes.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still understand the foregoing The technical solutions recorded in each embodiment are modified, or some of the technical features are replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (10)

1. A method for predicting the operation of transportation equipment based on digital twins, characterized in that it comprises: Obtain the topological structure data and basic environmental data of the target transportation equipment; Constructing a corresponding digital twin equipment model according to the topology data, constructing a corresponding digital twin environment model according to the basic environment data, and correlating the digital twin equipment model and the digital twin environment model to obtain a digital twin model; Obtaining operation data generated by the target transportation equipment during historical operation; importing the operating data into the digital twin model to obtain a target digital twin model matching the target transportation equipment; Performing simulation calculations on the target digital twin model to obtain simulation operation data generated during the operation of the target digital twin model; Train the target digital twin model according to the operation data and the simulation operation data to obtain a target operation state prediction model; Perform real-time status update on the target digital twin model to obtain corresponding real-time status data; The real-time state data is input into the target operation state prediction model for prediction calculation, and the operation state prediction result of the target transportation equipment is obtained. 2. The transportation equipment operation prediction method based on digital twins according to claim 1, wherein said target digital twin model is trained according to said operation data and said simulation operation data, comprising: Comparing the operating data with the simulated operating data to obtain error data; Correcting the target digital twin model according to the error data; Constructing a sample set based on the operating data and the simulation operating data; The corrected target digital twin model is trained according to the sample set. 3. The transportation equipment operation prediction method based on digital twins according to claim 1, wherein the operation state prediction results include fault diagnosis results, and the target digital twin model generates several functional chain groups during the training process And record the function chain group to which each component belongs, the function chain group is composed of several parts that realize specific functions; the described real-time state data is input to the target operating state prediction model for prediction calculation, including: Judging the fault according to the output response of the function chain group; Combining with component crossing of functional chain group for fault location. 4. The digital twin-based transportation equipment operation prediction method according to claim 3, wherein the operation data includes environmental history data, equipment operation data, equipment component data, equipment maintenance data and cost data; The operation status prediction results also include health assessment results, lifetime prediction results and cost calculation results. 5. The transportation equipment operation prediction method based on digital twin according to claim 1, is characterized in that, described method also comprises: determining a target operating strategy according to the operating state prediction result; The operating state of the target transportation equipment is controlled according to the target operating strategy. 6. The transportation equipment operation prediction method based on digital twin according to claim 1, is characterized in that, described method also comprises: The real-time state data is stored parametrically through the target digital twin model. 7. The transportation equipment operation prediction method based on digital twin according to claim 1, is characterized in that, described method also comprises: Obtaining target traffic accident data of the target transportation equipment; the target traffic accident data includes operation control data before the target traffic accident and operation status data after the target traffic accident; Derivation analysis is performed on the target traffic accident data based on the target operating state prediction model to obtain deduction analysis data on the target traffic accident process. 8. A digital twin-based transportation equipment operation prediction device, characterized in that it includes: The first acquisition module is used to acquire topology data and basic environment data of the target transportation equipment; A building module, configured to construct a corresponding digital twin equipment model according to the topology data, construct a corresponding digital twin environment model according to the basic environment data, and correlate the digital twin equipment model and the digital twin environment model to obtain digital twin model; The second acquisition module is used to acquire the operation data generated by the target transportation equipment during the historical operation process; An import module, configured to import the operating data into the digital twin model to obtain a target digital twin model matching the target transportation equipment; A simulation module, configured to perform simulation calculations on the target digital twin model, and obtain simulation operation data generated during the operation of the target digital twin model; A training module, configured to train the target digital twin model according to the operating data and the simulated operating data to obtain a target operating state prediction model; An update module, configured to update the target digital twin model in real time to obtain corresponding real-time state data; A predictive calculation module, configured to input the real-time state data into the target operating state prediction model to perform predictive calculation, and obtain the predicted result of the operating state of the target transportation equipment. 9. A digital twin-based transportation equipment operation prediction device, characterized in that it includes: A memory for storing instructions; wherein the instructions are used to implement the digital twin-based transportation equipment operation prediction method according to any one of claims 1-7; a processor configured to execute instructions in the memory. 10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method based on any one of claims 1-7 is implemented. Operation prediction method of transportation equipment based on digital twin.

Images