CN115562158A - Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal - Google Patents
Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal Download PDFInfo
- Publication number
- CN115562158A CN115562158A CN202211405385.0A CN202211405385A CN115562158A CN 115562158 A CN115562158 A CN 115562158A CN 202211405385 A CN202211405385 A CN 202211405385A CN 115562158 A CN115562158 A CN 115562158A
- Authority
- CN
- China
- Prior art keywords
- numerical control
- control machine
- machine tool
- digital twin
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/401—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/34—Director, elements to supervisory
- G05B2219/34242—For measurement only
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention provides a digital twin driven numerical control machine tool intelligent diagnosis method, a system and a terminal, which relate to the technical field of numerical control machine tool diagnosis and are used for collecting data information of a numerical control machine tool; constructing a digital twin model of the numerical control machine tool; updating the constructed digital twin model of the numerical control machine tool; injecting the faults of the numerical control machine tool into a numerical twin model of the numerical control machine tool; constructing a digital twin model library, wherein each numerical control machine tool digital twin model in the library can be mapped to a certain working state of the numerical control machine tool; constructing a model selector; inputting real-time monitoring data of the numerical control machine tool into a model selector, selecting a numerical control machine tool digital twin model representing the current state of the numerical control machine tool by the model selector, and judging the real state of the numerical control machine tool according to the state of the numerical control machine tool digital twin model when the numerical control machine tool is abnormal to realize fault diagnosis. The invention can not only reflect the health state of the numerical control machine tool, but also reflect the fault state of the numerical control machine tool.
Description
Technical Field
The invention relates to the technical field of numerical control machine tool diagnosis, in particular to a numerical control machine tool intelligent diagnosis method, system and terminal machine driven by a digital twin.
Background
Along with the advance of intelligent manufacturing, the automation, intellectualization and integration level of the numerical control machine tool is continuously improved, and higher requirements are put forward on the safety and reliability of the numerical control machine tool. However, as a complex electromechanical device formed by coupling a plurality of discipline systems such as mechanical, electrical, thermal, liquid and the like, a numerical control machine has the characteristics of time-varying property, nonlinearity, strong coupling and the like, and has a complex structure, various fault modes and an intricate and implicit relationship between fault reasons and signal characteristics. In case break down, be difficult to in time carry out fault identification, location, quantization, traceability analysis etc. maintenance duration is long, and is with high costs, influences the machining precision of part, reduces operating mass, can cause huge economic loss, can lead to the paralysis of whole production line when serious, causes the injury to the human body. Therefore, the invention provides an efficient numerical control machine tool fault diagnosis method, which ensures the safe and reliable operation of the numerical control machine tool and has important significance on the production level of the manufacturing industry.
The current traditional fault diagnosis methods mainly comprise three types: knowledge-based methods, model-based methods, and data-driven methods. The knowledge-based method is based on knowledge and experience of experts, and diagnoses equipment faults by applying subjective analysis methods such as manual reasoning, logic judgment and the like, such as an expert system, fuzzy logic and the like. The method can only diagnose the occurred faults and depends on the knowledge base to a great extent, the accuracy of the diagnosis result has a direct relation with the completeness of the knowledge base, and for numerical control machine tools with various fault modes, establishing the complete knowledge base has certain difficulty; in addition, the method is subjective due to human analysis. Model-based methods require the construction of an appropriate mechanistic model to describe the system to be diagnosed. However, the numerically controlled machine tool has a complex structure, coupling relationships exist among subsystems, and it is difficult to establish a model capable of reflecting the whole life cycle state of the numerically controlled machine tool. The data-driven method overcomes the problem that other two methods excessively depend on expert experience and a diagnosis model, and can realize online, efficient and accurate fault diagnosis of complex equipment. However, this method requires a large number of failure samples to train the model to obtain accurate results. With the improvement of the reliability of the equipment, the equipment is in a normal state for most of the time, and available fault data samples are few. In addition, obtaining fault data using experimental methods is expensive and time consuming, and for complex fault patterns, it is difficult to obtain data experimentally. Therefore, the lack of efficient data becomes a major obstacle to the development of data-driven methods for use in the fault diagnosis of numerically controlled machines.
At present, in order to solve the problem of insufficient data samples for fault diagnosis, researchers have proposed various data generation methods, and these methods are generally classified into two types. One is to apply a deep learning method such as GAN to expand the data set so as to train a diagnostic model when there are a small number of valid fault samples; and the other method is to simulate or acquire the fault data characteristics of similar equipment by using a transfer learning method so as to realize fault diagnosis of the target equipment. Although the method makes up for the problem of data sample loss, the method ignores the problem that the data characteristics change along with the actual working condition change of the equipment, so that the expanded fault sample has non-uniformity and poor reliability, and the accuracy of fault diagnosis is reduced. In addition, the data-driven fault diagnosis method has good application in fault mode identification and fault positioning, but how to realize quantitative fault analysis and fault tracing is still a big problem.
Disclosure of Invention
The invention provides a digital twin driven numerical control machine tool intelligent diagnosis method and system, which realize real-time interactive mapping of a machine tool and a digital space twin model so as to reflect the full life cycle state of the numerical control machine tool, and can effectively diagnose the real-time state of the numerical control machine tool by utilizing the digital twin model.
The intelligent diagnosis method of the numerical control machine tool driven by the digital twin comprises the following steps:
step 1: collecting static data information and dynamic data information in the operation process of the numerical control machine tool;
step 2: constructing a digital twin model of the numerical control machine tool;
and step 3: packaging the constructed numerical control machine tool digital twin model, configuring a data interface, transmitting the acquired numerical control machine tool information to the numerical control machine tool digital twin model, and updating the numerical control machine tool digital twin model;
and 4, step 4: injecting the faults of the numerical control machine tool into a numerical twin model of the numerical control machine tool;
and 5: collecting a plurality of numerical control machine tool digital twin models representing different states of a numerical control machine tool, and building the plurality of numerical control machine tool digital twin models into a digital twin model library, wherein each numerical control machine tool digital twin model in the digital twin model library can be mapped to a certain working state of the numerical control machine tool;
step 6: constructing a model selector, taking sensor data of a physical system of the numerical control machine tool as input, and selecting a numerical control machine tool digital twin model matched with the current sensor data from a numerical control machine tool digital twin model library;
and 7: inputting real-time monitoring data of the numerical control machine tool into a model selector, selecting a numerical control machine tool digital twin model representing the current state of the numerical control machine tool by the model selector according to the input real-time monitoring data, and judging the real state of the numerical control machine tool according to the state of the numerical control machine tool digital twin model when the numerical control machine tool is abnormal to realize fault diagnosis.
It should be further noted that the static data information includes: the geometric dimension, system structure, physical property, working capacity and model of the numerical control machine tool;
the dynamic data information includes: working condition information, vibration information, temperature information, stiffness information, noise information, and loading force information.
It should be further noted that, in the step 2, the structure and the coupling relationship of the numerical control machine tool system are analyzed, and the numerical control machine tool system is divided into a plurality of subsystems such as a mechanical subsystem, an electrical subsystem, a heat transfer subsystem and the like in a modularization and modularization manner;
compiling and describing the operation mechanism of each functional element of each subsystem of the numerical control machine tool by adopting Modelica multi-field unified modeling language according to the mechanical structure and functional characteristics of the numerical control machine tool to form each functional element model;
constructing a digital twin model of each subsystem through the connection of each element;
connecting the subsystem models according to the coupling relation and the coupling mechanism among the subsystems to form a multi-system coupling digital twin model of the numerical control machine;
and verifying the constructed numerical control machine tool digital twin model by using sensor data from a physical system and adopting model fitting degree and relative error.
It is further noted that the degree of model fitting R 2 The calculation method of (2) is as follows:
wherein RSS represents the residual sum of squares, TSS represents the sum of squares, and ESS represents the sum of squares;
the relative error Δ E is calculated as follows:
in the formula, ns represents sensor monitoring data of a physical system of the numerical control machine, and Nm represents data of a digital twin model of the numerical control machine.
It should be further noted that step 5 further includes:
at a certain time t, the relationship between the physical system of the numerical control machine tool and the digital twin model is expressed as
M t ∈M→P t
Wherein M is t Is a digital twin model, maps the state of the physical system of the numerical control machine at time t, P t Showing the state of the numerical control machine tool at the time t.
It is further noted that the CART decision tree algorithm is used to construct the model selector in step 6.
It should be further noted that, assuming that there are i data sources reflecting the physical system state and there are | M | models in the model library M, the data set generated by the model library is represented as:
F＝(X,M)X∈R |M|×i ,M∈R |M|
wherein X represents a matrix composed of twin data and M is a matrix of all models in the model library;
the construction of the model selector using the CART decision tree algorithm is implemented as follows:
(1) Calculating Gini coefficients of the data set F;
if the data set F has | M | model types, the Keyny coefficient of F is expressed as:
wherein C is n Sample subset, C, representing the n-th type of model n | is the number of sample subsets of the nth type, | F | is the total number of samples of the data set F;
(2) Segmenting a data set F into F using a characteristic condition A 1 And F 2 Then the Gini coefficient under condition a is expressed as:
wherein | F 1 I and I F 2 Respectively represents F 1 And F 2 The number of samples in (1);
continuously adjusting the characteristic condition A until Gini (F, A) is taken as the minimum value, and then segmenting the data set F;
(3) F is to be 1 And F 2 As the child nodes, repeating the step (2) until the number of samples of the child nodes is smaller than a preset threshold value, or the Gini index is smaller than the preset threshold value, and stopping dividing;
(4) A model selector S is constructed.
The invention also provides a digital twin driven numerical control machine tool intelligent diagnosis system, which comprises: the system comprises a numerical control machine tool data sensing module, a numerical control machine tool digital twin model building module, a digital twin model real-time mapping module, a digital twin model fault injection module, a digital twin model library building module, a model selector building module and a numerical control machine tool fault diagnosis module;
the numerical control machine tool data sensing module is used for acquiring static data information and dynamic data information in the operation process of the numerical control machine tool;
the numerical control machine tool digital twin model building module is used for dividing a numerical control machine tool structure into a plurality of subsystems based on the numerical control machine tool structure, respectively modeling each subsystem by adopting a multi-field modeling method, analyzing the running characteristics of the numerical control machine tool and the coupling relation among the subsystems, coupling and connecting each subsystem model to obtain a numerical control machine tool multi-system coupling digital twin model, then verifying the model by using sensing monitoring data from a physical system, continuously updating, iterating and optimizing model parameters, and completing the construction of the numerical control machine tool digital twin model when the fitting degree and the relative error of the model meet preset conditions;
the digital twin model real-time mapping module is used for encapsulating the constructed digital twin model of the numerical control machine tool, configuring a data interface, transmitting the acquired numerical control machine tool information to the digital twin model of the numerical control machine tool and updating the digital twin model of the numerical control machine tool;
the digital twin model fault injection module is used for injecting a fault mode and a fault reason of the numerical control machine tool into the digital twin model of the numerical control machine tool by combining with the set working condition, the model physical parameters and the geometric attributes to obtain the digital twin model of the numerical control machine tool capable of representing different states of the numerical control machine tool;
the digital twin model library construction module is used for collecting a plurality of numerical control machine tool digital twin models representing different states of the numerical control machine tool and constructing the plurality of numerical control machine tool digital twin models into a digital twin model library, and each numerical control machine tool digital twin model in the digital twin model library can be mapped to a certain working state of the numerical control machine tool;
the model selector construction module is used for taking sensor data of a physical system of the numerical control machine tool as input and selecting a numerical control machine tool digital twin model matched with the current sensor data from a numerical control machine tool digital twin model library;
the numerical control machine tool fault diagnosis module is used for inputting real-time monitoring data of the numerical control machine tool into the model selector, the model selector selects a numerical control machine tool digital twin model representing the current time state of the numerical control machine tool according to the input real-time monitoring data, and when the numerical control machine tool is abnormal, the real state of the numerical control machine tool is judged according to the state of the numerical control machine tool digital twin model, so that fault diagnosis is realized.
Further, it should be noted that the method further includes: a development module of an intelligent diagnosis system of the numerical control machine;
the intelligent diagnosis system development module of the numerical control machine tool develops the intelligent diagnosis system of the numerical control machine tool based on Vue and a FastAPI system architecture, integrates functions of data acquisition, data analysis, state information monitoring, digital twin model visualization and numerical control machine tool fault diagnosis, and achieves online real-time intelligent diagnosis of the numerical control machine tool.
The invention also provides a terminal machine, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the intelligent diagnosis method of the numerical control machine driven by the digital twin.
According to the technical scheme, the invention has the following advantages:
the intelligent diagnosis method of the numerical control machine tool aims at high coupling of a mechanical structure and each subsystem of the numerical control machine tool, solves the problem that the existing digital twin model is lack of coupling relation description, constructs a multi-system coupling digital twin model for the numerical control machine tool by utilizing a multi-field modeling technology, describes the coupling relation among the subsystems of the machine tool in the same modeling environment, and simulates the overall corresponding characteristics of a physical system of the numerical control machine tool. Meanwhile, the method can carry out combined simulation among models established by different simulation software through FMU model encapsulation, and can obtain more accurate and richer analysis results.
Aiming at the problems that the existing digital twin model is mostly a model under the health state of the numerical control machine tool and is difficult to reflect the information under the fault state, the fault injection of the digital twin model is realized by combining the characteristics of the digital twin model and the fault mode and the fault reason of the numerical control machine tool through methods of working condition setting, physical parameter setting, geometric attribute setting and the like, so that the health state of the numerical control machine tool can be reflected, and the fault state of the numerical control machine tool can also be reflected.
Aiming at the situation that a single and static digital twin model is difficult to reflect the state change of the whole life cycle of the numerical control machine, the construction method ensures that any possible state of the physical system of the numerical control machine can be represented by one model at any moment by constructing the digital twin model library, and the optimal model is matched by the model selector, so that the capability of the digital twin model for simulating the physical system of the numerical control machine is improved.
The method provided by the invention aims at the problems that the numerical control machine tool fault diagnosis result is inaccurate due to insufficient fault samples, the actual working conditions are neglected in the existing data generation method, the data is unbalanced and the like, and by utilizing the interpretability and the visualization of the digital twin model, the accurate fault diagnosis can be realized under the condition of insufficient data, and the analysis such as fault positioning, fault quantification, fault tracing and the like is carried out. In addition, the invention integrates a digital twin model of the numerical control machine, real-time sensing monitoring data and related machine learning algorithms, realizes the online and real-time fault diagnosis of the numerical control machine, finally forms a digital twin driven fault diagnosis method and system of the numerical control machine, ensures the safe and reliable operation of the numerical control machine, improves the starting rate and the working efficiency of the numerical control machine, and reduces the monitoring, maintenance and repair costs.
The intelligent diagnosis system for the numerical control machine tool built by the invention realizes the functions of online intelligent diagnosis, real-time state monitoring and the like of the numerical control machine tool through the webpage system, and through online monitoring, a worker can remotely check the state of the machine tool in real time, and when the state is abnormal, the machine tool is analyzed in time by utilizing the fault diagnosis function, and the physical system of the numerical control machine tool is maintained and maintained according to the analysis result, so that the maintenance efficiency and the starting rate of the machine tool are greatly improved, the maintenance and maintenance cost is reduced, and the manpower and material resources are saved.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a digital twin driven numerically controlled machine tool intelligent diagnostic system;
FIG. 2 is a flow chart of a numerical control machine tool intelligent diagnosis method driven by a digital twin;
FIG. 3 is an exemplary diagram of a model selector.
Detailed Description
As shown in fig. 1 and 2, the diagram provided in the method for intelligent diagnosis of a numerically controlled machine tool driven by a digital twin according to the present invention is only a schematic diagram illustrating the basic idea of the present invention, and only the modules related to the present invention are shown in the drawings rather than the number and functions of the modules in the actual implementation, and the functions, number and functions of the modules in the actual implementation may be changed at will, and the functions and purposes of the modules may be more complicated.
The digital twin driven numerical control machine tool intelligent diagnosis method can acquire and process the associated data based on the artificial intelligence technology. The intelligent diagnosis method of the numerical control machine driven by the digital twin simulates, extends and expands the intelligence of people by using a digital computer or a machine controlled by the digital computer, senses the environment, acquires knowledge and obtains the theory, the method, the technology and the application device of the best result by using the knowledge.
The intelligent diagnosis method for the numerical control machine tool has the technology of a hardware layer and the technology of a software layer. The basic technologies of the intelligent diagnosis method of the numerical control machine tool generally comprise technologies such as a sensor, a special artificial intelligence chip, cloud computing, distributed storage, a big data processing technology, an operation/interaction system, electromechanical integration and the like. The intelligent diagnosis method software technology for the numerical control machine mainly comprises a computer visual angle technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The intelligent diagnosis method of the numerical control machine tool also has a machine learning function, wherein the machine learning and the deep learning in the method generally comprise the technologies of artificial neural network, belief network, reinforcement learning, transfer learning, inductive learning, formula teaching learning and the like.
The intelligent diagnosis method of the numerical control machine tool utilizes a Digital Twin (DT) technology, realizes real-time interactive mapping of the machine tool and the digital space twin model by establishing the twin model of the numerical control machine tool and utilizing the technologies of sensor monitoring, data transmission and the like, and further reflects the full life cycle state of the numerical control machine tool, so that the real-time state of the numerical control machine tool can be effectively diagnosed by utilizing the digital twin model.
The intelligent diagnosis method for the numerical control machine tool fuses a large amount of data generated by the digital twin model with real-time monitoring data of the numerical control machine tool, can realize interactive feedback, data fusion and analysis of a digital space and a physical space, and further effectively solves the problems of missing, non-uniform and inaccurate fault diagnosis of a fault sample caused by insufficient data in the traditional data generation method.
Fig. 1 and 2 show a flow chart of a preferred embodiment of the intelligent diagnosis method of the numerical control machine tool of the present invention. The intelligent diagnosis method for the numerical control machine tool is applied to one or more terminal machines, wherein the terminal machine is a device capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware of the terminal machine comprises but is not limited to a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded device and the like.
The terminal may be any electronic product capable of performing human-computer interaction with a user, for example, a Personal computer, a tablet computer, a smart phone, a Personal Digital Assistant (PDA), an interactive Internet Protocol Television (IPTV), and the like.
The terminal may also include network equipment and/or user equipment. The network device includes, but is not limited to, a single network server, a server group consisting of a plurality of network servers, or a Cloud Computing (Cloud Computing) based Cloud consisting of a large number of hosts or network servers.
The Network where the terminal is located includes, but is not limited to, the internet, a wide area Network, a metropolitan area Network, a local area Network, a Virtual Private Network (VPN), and the like.
The intelligent diagnosis method for the numerical control machine tool driven by the digital twin is elaborated in detail by combining with the figures 1 to 2, the diagnosis method comprises the steps of acquiring real-time state information of the machine tool, describing coupling relations among subsystems of the numerical control machine tool, electricity, heat, liquid and the like by combining with a multi-field modeling language, establishing a multi-system coupling digital twin model of the numerical control machine tool, and then establishing a model updating strategy based on real-time working conditions to realize virtual-real mapping between the digital twin model of the numerical control machine tool and a physical entity. Establishing digital twin models capable of representing different fault modes and fault degrees of the numerical control machine tool by utilizing a fault injection technology to form a numerical twin model library of the numerical control machine tool so as to obtain fault sample data; and further training a model selector by using a machine learning algorithm, taking real-time sensing monitoring data as input, selecting an optimal model from a model library, and realizing fault mode identification, fault positioning, fault quantitative analysis, fault tracing and the like of the numerical control machine tool according to the twin model state.
The method can also analyze the change trend of the running state of the numerical control machine tool, evaluate whether the running of the numerical control machine tool meets the requirements or not and whether abnormal risks exist or not, and has a positive effect on the stable running of the numerical control machine tool.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 2, a flow chart of a digital twin driven numerical control machine tool intelligent diagnosis method according to an embodiment is shown, the method includes:
s101: and collecting static data information and dynamic data information in the operation process of the numerical control machine tool.
In this embodiment, the entity-related data of the cnc machine is the factual basis for constructing the digital twin model of the cnc machine. The method is characterized in that static data information such as the geometric dimension, the system structure, the physical attribute, the working capacity and the model of the numerical control machine can be directly obtained through tools such as machine tool design parameters and design drawings, dynamic data information such as the working condition, vibration, temperature, rigidity, noise and loading force of a numerical control machine entity is obtained through analyzing the structure and the working environment of the numerical control machine, a proper data acquisition point is selected, a reasonable sensing monitoring scheme is formulated, sensors such as vibration, temperature, rotating speed and displacement are installed, real-time data information in the running process of the numerical control machine is acquired, and complete physical data are provided for the construction of a numerical twin model of the numerical control machine.
S102: constructing a digital twin model of the numerical control machine tool; the digital twin model, the model and the digital model are all expressed as numerical control machine tool digital twin models.
Aiming at the high coupling of a numerical control machine tool, when a digital twin model is constructed, firstly, the system is divided into a plurality of subsystems such as mechanical subsystem, electrical subsystem, heat transfer subsystem and the like in a modularization and modularization mode by analyzing the structure and the coupling relation of the numerical control machine tool system; secondly, selecting proper physical parameters such as torque, rigidity, heat transfer coefficient and the like according to the mechanical structure and functional characteristics of the numerical control machine tool, compiling and describing the operation mechanism of each functional element of each subsystem of the numerical control machine tool by adopting Modelica multi-field unified modeling language to form each functional element model, and further constructing a digital twin model of each subsystem through the connection of each element; and then connecting the subsystem models according to the complex coupling relation and the coupling mechanism among the subsystems to form a multi-system coupling digital twin model of the numerical control machine.
In the process of digital twin modeling, physical parameters need to be selected, and some parameters can greatly influence the performance of the model, so that the model is verified by using the data of the sensor from a physical system and by adopting the fitting degree and the relative error of the model. Degree of model fitting R 2 The calculation method of (2) is as follows:
in the formula, RSS represents the sum of residuals squared, TSS represents the sum of squares, and ESS represents the sum of squares.
The relative error Δ E is calculated as follows:
in the formula, ns represents sensor monitoring data of a physical system of the numerical control machine, and Nm represents data of a digital twin model of the numerical control machine.
The closer the model fit is to 1, the higher the fidelity of the model. In addition, since the data of the digital twin model is basically obtained from a mechanical formula, a certain error occurs compared with the sensor data of the physical system. Statistically, the digital twin model is considered to have good fidelity when the relative error is kept within 5%.
Through the steps, the high-fidelity numerical control machine tool digital twin model of the numerical control machine tool is obtained. In order to facilitate calling and using the model, the model can be packaged into an FMU (Functional Module-up Units) model with a unified platform Interface through an FMI (Functional Module-Up Interface) standard model.
S103: and mapping the digital twin model of the numerical control machine tool in real time.
The invention has the advantages that the compatibility and the openness of the constructed digital twin model are poor in consideration of the fact that the digital twin modeling tool emphasizes a specific aspect, and the model is encapsulated, so that the models established by different tools can be conveniently coupled and interacted. The constructed numerical control machine tool multi-system coupling digital twin model is packaged, relevant data interfaces are reserved, collected numerical control machine tool static data information and real-time dynamic data information are transmitted to the digital twin model, the model is updated, real-time mapping of the model from multiple dimensions such as geometry, physics, behaviors and rules is achieved, and good consistency of operation of a numerical control machine tool physical system and response of the model is guaranteed.
S104: and injecting the numerical control machine tool fault into the numerical control machine tool digital twin model.
The digital twin model constructed by the embodiment can only reflect the characteristics of the numerical control machine tool in the health state, and the digital twin model has the characteristic of real-time mapping, so that the health state of the equipment can be reflected, and the fault state of the equipment can also be reflected.
The system enables the digital twin model to represent the state of the numerical control machine tool at any time by injecting faults into the model, wherein the state comprises a health state and a fault state.
The invention also provides the following three fault injection methods aiming at the digital twin model by combining the characteristics of the digital twin model and the fault mode and the fault reason of the numerical control machine tool: a fault injection method for setting working conditions, a fault injection method for setting physical parameters and a fault injection method for setting geometric attributes.
(1) Fault injection under working condition setting;
the working condition refers to the working condition of the numerical control machine tool under a certain condition, including environmental condition, working condition and the like. The numerical control machine tool has complex working conditions, particularly for some high-precision machine tools, the requirement on the environment is high, and the change of the working conditions can often cause the change of factors such as stress born by a supporting system of the numerical control machine tool and the like, so that the factors become one of important factors for inducing partial faults of the numerical control machine tool.
(2) Fault injection of physical parameter setting;
the fault mode of the numerical control machine tool is that the part structure of the machine tool is changed from the fault phenomenon, but the reason is studied from the physical perspective and can be abstracted as the change of the characteristic parameters of the corresponding parts, so that the fault injection can be realized by setting the relevant parameters of the model. Such as the main shaft and the bearing wear causes the friction coefficient to become large, thereby causing the temperature rise fault; cooling system failure may be achieved by setting a cooling system temperature parameter; lubrication system failures can be simulated by setting the lubrication coefficient of the bearing.
(3) Fault injection of geometric attribute setting;
mechanical faults of the numerical control machine tool are mostly caused by that the geometrical properties of parts of the machine tool are changed, for the fault modes, the fault modes cannot be realized by simply setting parameters, and fault injection such as bearing cracks, abrasion and eccentricity can be realized only by changing the geometrical structure of a model; main shaft cracks, pitting, unbalance, related faults of the electrical system, etc.
S105: and constructing a numerical twin model library of the numerical control machine tool.
In the actual production process, the state of the physical system of the numerical control machine tool is constantly changed and accompanied by faults due to the working conditions, the manufacturing process, the material performance and the like. It is difficult to accurately reflect this change using a single static model, thereby reducing the ability of the digital twin to simulate a physical system. Thus, by developing a method of a library M of digital twin models, each model in the library is made to map every possible state of the physical system. Assuming that at a certain time t, the relationship between the physical system of the NC machine tool and the digital twin model can be expressed as
M t ∈M→P t
Wherein M is t Is a digital twin model and can map the state P of the physical system of the numerical control machine tool at the moment t t And showing the state of the numerical control machine tool at the time t.
Through the digital twin model library M, a reliable digital twin model can be ensured to exist all the time, and the model can represent any possible state of a physical system of the numerical control machine.
There are two ways to extend the digital twin model library M.
The first approach is to add different state models by modifying parameters on the original model. And secondly, reconstructing a digital twin model of the numerical control machine tool, setting new parameters and acquiring models in different states. This method is more flexible and expressive.
S106: and constructing a model selector.
In order for the system to efficiently match the sensor monitoring data of the cnc physical system with the models in the model library, the model selector S is trained using the twin data set generated by the digital twin model and the sensor data of the cnc physical system is taken as input to determine which model in the model library best matches the data at the current time.
For CART decision trees to construct model selectors. Each node of the decision tree contains a conditional test to determine which branch the test sample belongs to, thus providing a good interpretation of the classification results. The CART algorithm uses Gini coefficients to judge the data set division conditions, so that the accuracy of decision tree division is improved.
Assuming there are i data sources reflecting the physical system state and | M | models in the model library M, the data set generated by the model library is represented as:
F＝(X,M)X∈R |M|×i ,M∈R |M|
where X represents a matrix consisting of twin data and M is a matrix of all models in the model library.
With the CART decision tree algorithm, the model selector S is constructed using the data set F. The method comprises the following implementation steps:
(1) Gini coefficients of the data set F are calculated. If the data set F has | M | model types, the Keyny coefficient for F can be expressed as:
wherein C is n Sample subset, C, representing the n-th type of model n | is the number of sample subsets of the nth type, | F | is the total number of samples of the data set F.
(2) Segmenting a data set F into F using a characteristic condition A 1 And F 2 Then the Gini coefficient under condition a is expressed as:
wherein | F 1 I and I F 2 Respectively represents F 1 And F 2 Number of samples in (1).
And continuously adjusting the characteristic condition A until Gini (F, A) takes the minimum value, and then segmenting the data set F.
(3) F is to be 1 And F 2 And (3) as the child node, repeating the step (2) until the number of samples of the child node is smaller than a preset threshold value or the Gini index is smaller than the preset threshold value, and stopping dividing.
(4) A model selector S is constructed.
According to the above steps, a model selector S is constructed, the sensor data of the physical system of the numerical control machine tool is used as input, a model which can optimally represent the current state of the physical system is selected, and then the model interpretability is utilized to determine the actual state of the physical system of the numerical control machine tool. FIG. 3 shows an example where (a) is a dataset partition and (b) is a decision tree. Given the data point (3.5,4), it can be judged by the model selector to belong to Δ.
S107: and diagnosing the fault of the numerical control machine tool.
The method is based on a digital twin model library and a model selector, and inputs real-time sensing monitoring data of a physical system of the numerical control machine tool into the model selector, so that a model which can most represent the current state of the numerical control machine tool is selected from the model library. Because the digital twin model has better interpretability and visualization, when the numerical control machine tool fails, the position, reason and degree of the failure can be analyzed through the digital twin model, the failure positioning, the failure quantification, the failure tracing and the like are realized, and further maintenance, maintenance guidance and suggestion are provided for a physical system of the numerical control machine tool.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
The following is an embodiment of the digital twin-driven intelligent diagnosis system for a numerical control machine tool provided in the embodiment of the present disclosure, which belongs to the same inventive concept as the digital twin-driven intelligent diagnosis method for a numerical control machine tool in the above embodiments, and reference may be made to the above embodiment of the digital twin-driven intelligent diagnosis method for a numerical control machine tool in the embodiment of the digital twin-driven intelligent diagnosis system for a numerical control machine tool, which is not described in detail in the above embodiments.
The system comprises: the system comprises a numerical control machine tool data sensing module, a numerical control machine tool digital twin model building module, a digital twin model real-time mapping module, a digital twin model fault injection module, a digital twin model library building module, a model selector building module and a numerical control machine tool fault diagnosis module;
the numerical control machine tool data sensing module is used for acquiring static data information and dynamic data information in the operation process of the numerical control machine tool;
the numerical control machine tool data perception module mainly analyzes the mechanical structure and the working environment characteristics of the numerical control machine tool in the operation process, a reasonable sensing monitoring scheme is formulated, and real-time data information in the operation process of the numerical control machine tool is collected, wherein data perceived by the numerical control machine tool data perception module can comprise static data information of the numerical control machine tool such as the geometric dimension, the system structure, the physical attribute, the working capacity and the model, and dynamic data information of the numerical control machine tool entity such as the working condition, the vibration, the temperature, the rigidity, the noise and the loading force, so that a factual basis is provided for the construction of a digital twin model.
The numerical control machine tool digital twin model building module is used for dividing a structure based on a numerical control machine tool into a plurality of subsystems, respectively modeling each subsystem by adopting a multi-field modeling method, analyzing the running characteristics of the numerical control machine tool and the coupling relation among the subsystems, coupling and connecting the subsystem models to obtain a numerical control machine tool multi-system coupling digital twin model, verifying the model by using sensing monitoring data from a physical system, continuously updating, iterating and optimizing model parameters, and completing the building of the numerical control machine tool digital twin model when the fitting degree and the relative error of the model meet preset conditions. When the fitting degree and the relative error of the model meet certain conditions, the digital twin model is considered to have good fidelity and can be used for fault diagnosis.
The digital twin model real-time mapping module is used for packaging the constructed digital twin model of the numerical control machine tool, configuring a data interface, transmitting the acquired numerical control machine tool information to the digital twin model of the numerical control machine tool, and updating the digital twin model of the numerical control machine tool; the real-time mapping module of the digital twin model realizes the real-time mapping of the model from multiple dimensions such as geometry, physics, behavior, rules and the like.
The digital twin model fault injection module is used for injecting a fault mode and a fault reason of the numerical control machine tool into the digital twin model of the numerical control machine tool by combining with the set working condition, model physical parameters and geometric attributes to obtain the digital twin model of the numerical control machine tool capable of representing different states of the numerical control machine tool;
the digital twin model library construction module is used for collecting a plurality of numerical control machine tool digital twin models representing different states of the numerical control machine tools, and constructing the plurality of numerical control machine tool digital twin models into a digital twin model library, wherein each numerical control machine tool digital twin model in the digital twin model library can be mapped to a certain working state of the numerical control machine tool;
the model selector construction module is used for taking sensor data of a physical system of the numerical control machine tool as input and selecting a numerical control machine tool digital twin model matched with the current sensor data from a numerical control machine tool digital twin model library;
the numerical control machine tool fault diagnosis module is used for inputting real-time monitoring data of the numerical control machine tool into the model selector, the model selector selects a numerical control machine tool digital twin model representing the current state of the numerical control machine tool according to the input real-time monitoring data, and when the numerical control machine tool is abnormal, the real state of the numerical control machine tool is judged according to the state of the numerical control machine tool digital twin model, so that fault diagnosis is realized.
The system of the present invention further comprises: a development module of an intelligent diagnosis system of the numerical control machine;
the intelligent diagnosis system development module of the numerical control machine tool is used for realizing online diagnosis of the numerical control machine tool and visualizing a digital twin model and data, and mainly comprises the following functions:
(1) The data acquisition function of the numerical control machine tool is as follows: the data base of the numerical control machine tool is constructed, real-time sensing monitoring data are collected and stored, and a data basis is provided for fault diagnosis and a digital twin model.
(2) The state monitoring function of the numerical control machine tool is as follows: the method comprises the steps of cleaning, normalizing, obtaining the most value and the like of original monitoring data of the numerical control machine tool in a database, and visually displaying in the forms of a bar chart, a broken line chart, a pie chart and the like, so that the monitoring of real-time states of the numerical control machine tool, including a temperature state, a vibration state, a rigidity state, a rotating speed, a loading force and the like, is realized.
(3) The model visualization function: and exporting related subsystems in the digital twin model into an FMU file through an FMI standard interface, and reserving a specific data interface for inputting sensing and monitoring data of the numerical control machine tool so as to realize virtual-real mapping of the model and the entity and realize visualization of the model.
(4) A fault diagnosis function: and when the state of the numerical control machine tool is abnormal, inputting real-time monitoring data to a packaged model selector, matching an optimal model from a model library through the model selector, and performing fault diagnosis on the numerical control machine tool according to the visualization effect and interpretability of the model.
Due to the complex function of intelligent diagnosis, a Vue + FastAPI webpage system front-end and rear-end framework is selected to be used for building a platform, the functions of man-machine interaction, parameter setting and instruction input are realized at the front end of the system, and the set parameter content is transmitted to the rear end; the functions of uploading and downloading related data, data processing and communication with the physical entity numerical control system are realized at the rear end of the system, and the original data and the processing operation result are sent to the front end for visual display.
The units and algorithm steps of each example described in the embodiments disclosed in the present invention can be implemented by electronic hardware, computer software, or a combination of both, and in the above description, the components and steps of each example have been generally described in terms of functions in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Flow charts and block diagrams in the figures of a numerically controlled machine tool intelligent diagnostic method and system illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. Illustratively, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the present numerically controlled machine tool intelligent diagnosis method and system, the computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C + +, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages, or a combination thereof. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or power server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A digital twin driven numerical control machine tool intelligent diagnosis method is characterized by comprising the following steps:
step 1: collecting static data information and dynamic data information in the operation process of the numerical control machine tool;
and 2, step: constructing a digital twin model of the numerical control machine tool;
and step 3: packaging the constructed numerical control machine tool digital twin model, configuring a data interface, transmitting the acquired numerical control machine tool information to the numerical control machine tool digital twin model, and updating the numerical control machine tool digital twin model;
and 4, step 4: injecting the faults of the numerical control machine tool into a numerical twin model of the numerical control machine tool;
and 5: collecting a plurality of numerical control machine tool digital twin models representing different states of a numerical control machine tool, and building the plurality of numerical control machine tool digital twin models into a digital twin model library, wherein each numerical control machine tool digital twin model in the digital twin model library can be mapped to a certain working state of the numerical control machine tool;
and 6: constructing a model selector, taking sensor data of a physical system of the numerical control machine tool as input, and selecting a numerical control machine tool digital twin model matched with the current sensor data from a numerical control machine tool digital twin model library;
and 7: inputting real-time monitoring data of the numerical control machine tool into a model selector, selecting a numerical control machine tool digital twin model representing the current state of the numerical control machine tool by the model selector according to the input real-time monitoring data, and judging the real state of the numerical control machine tool according to the state of the numerical control machine tool digital twin model when the numerical control machine tool is abnormal to realize fault diagnosis.
2. The intelligent diagnosis method for a numerical control machine tool driven by a digital twin according to claim 1,
the static data information includes: the geometric dimension, system structure, physical property, working capacity and model of the numerical control machine tool;
the dynamic data information includes: the system comprises working condition information, vibration information, temperature information, rigidity information, noise information and loading force information.
3. The intelligent diagnosis method for a numerical control machine tool driven by a digital twin according to claim 1,
in the step 2, the structure and the coupling relation of a system of the numerical control machine tool are analyzed, and the system is divided into a plurality of subsystems such as mechanical subsystems, electrical control subsystems, heat transfer subsystems and the like in a modularization and modularization mode;
compiling and describing the operation mechanism of each functional element of each subsystem of the numerical control machine tool by adopting Modelica multi-field unified modeling language according to the mechanical structure and functional characteristics of the numerical control machine tool to form each functional element model;
constructing a digital twin model of each subsystem through the connection of each element;
connecting the subsystem models according to the coupling relation and the coupling mechanism among the subsystems to form a multi-system coupling digital twin model of the numerical control machine;
and verifying the constructed numerical control machine tool digital twin model by using sensor data from a physical system and adopting the degree of model fitting and relative error.
4. The intelligent diagnosis method for a numerical control machine tool driven by a digital twin according to claim 3,
degree of model fitting R 2 The calculation method of (2) is as follows:
wherein RSS represents the sum of residuals squared, TSS represents the sum of squares, and ESS represents the sum of squares;
the relative error Δ E is calculated as follows:
in the formula, ns represents sensor monitoring data of a physical system of the numerical control machine, and Nm represents data of a digital twin model of the numerical control machine.
5. The intelligent diagnosis method for digital twin driven numerical control machine tool according to claim 1, wherein the step 5 further comprises:
at a certain time t, the relationship between the physical system of the numerical control machine tool and the digital twin model is expressed as
M t ∈M→P t
Wherein M is t Is a digital twin model, maps the state of the physical system of the numerical control machine at time t, P t And showing the state of the numerical control machine tool at the time t.
6. The intelligent diagnosis method for digital twin driven numerical control machine tool according to claim 1, wherein the CART decision tree algorithm is used to construct the model selector in step 6.
7. The intelligent diagnosis method for digital twin-driven CNC machine according to claim 6, wherein assuming that there are i data sources reflecting the state of the physical system and there are | M | models in the model library M, the data set generated by the model library is expressed as:
F＝(X,M)X∈R M×i ,M∈R M
wherein X represents a matrix composed of twin data and M is a matrix of all models in the model library;
the construction of the model selector using the CART decision tree algorithm is implemented as follows:
(1) Calculating Gini coefficients of the data set F;
if the data set F has | M | model types, the Keyny coefficient of F is expressed as:
wherein C is n Sample subset, C, representing the n-th type of model n | is the number of sample subsets of the nth type, | F | is the total number of samples of the data set F;
(2) Segmenting a data set F into F using a characteristic condition A 1 And F 2 Then the Gini coefficient under condition a is expressed as:
wherein | F 1 I and I F 2 Respectively represents F 1 And F 2 The number of samples in (1);
continuously adjusting the characteristic condition A until Gini (F, A) reaches the minimum value, and then segmenting the data set F;
(3) F is to be 1 And F 2 As the child nodes, repeating the step (2) until the number of samples of the child nodes is smaller than a preset threshold value, or the Gini index is smaller than the preset threshold value, and stopping dividing;
(4) A model selector S is constructed.
8. A digital twin driven numerical control machine tool intelligent diagnosis system, characterized in that the system adopts the digital twin driven numerical control machine tool intelligent diagnosis method according to any one of claims 1 to 7;
the system comprises: the system comprises a numerical control machine tool data sensing module, a numerical control machine tool digital twin model building module, a digital twin model real-time mapping module, a digital twin model fault injection module, a digital twin model library building module, a model selector building module and a numerical control machine tool fault diagnosis module;
the numerical control machine tool data sensing module is used for acquiring static data information and dynamic data information in the operation process of the numerical control machine tool;
the numerical control machine tool digital twin model building module is used for dividing a numerical control machine tool structure into a plurality of subsystems based on the numerical control machine tool structure, respectively modeling each subsystem by adopting a multi-field modeling method, analyzing the running characteristics of the numerical control machine tool and the coupling relation among the subsystems, coupling and connecting each subsystem model to obtain a numerical control machine tool multi-system coupling digital twin model, then verifying the model by using sensing monitoring data from a physical system, continuously updating, iterating and optimizing model parameters, and completing the construction of the numerical control machine tool digital twin model when the fitting degree and the relative error of the model meet preset conditions;
the digital twin model real-time mapping module is used for packaging the constructed digital twin model of the numerical control machine tool, configuring a data interface, transmitting the acquired numerical control machine tool information to the digital twin model of the numerical control machine tool, and updating the digital twin model of the numerical control machine tool;
the digital twin model fault injection module is used for injecting a fault mode and a fault reason of the numerical control machine tool into the digital twin model of the numerical control machine tool by combining with the set working condition, the model physical parameters and the geometric attributes to obtain the digital twin model of the numerical control machine tool capable of representing different states of the numerical control machine tool;
the digital twin model library construction module is used for collecting a plurality of numerical control machine tool digital twin models representing different states of the numerical control machine tool and constructing the plurality of numerical control machine tool digital twin models into a digital twin model library, and each numerical control machine tool digital twin model in the digital twin model library can be mapped to a certain working state of the numerical control machine tool;
the model selector construction module is used for taking sensor data of a physical system of the numerical control machine tool as input and selecting a numerical control machine tool digital twin model matched with the current sensor data from a numerical control machine tool digital twin model library;
the numerical control machine tool fault diagnosis module is used for inputting real-time monitoring data of the numerical control machine tool into the model selector, the model selector selects a numerical control machine tool digital twin model representing the current state of the numerical control machine tool according to the input real-time monitoring data, and when the numerical control machine tool is abnormal, the real state of the numerical control machine tool is judged according to the state of the numerical control machine tool digital twin model, so that fault diagnosis is realized.
9. The intelligent diagnosis system of a digital twin driven numerical control machine tool according to claim 8,
further comprising: a development module of the intelligent diagnosis system of the numerical control machine;
the numerical control machine intelligent diagnosis system development module develops the numerical control machine intelligent diagnosis system based on Vue and the FastAPI system architecture, integrates the functions of data acquisition, data analysis, state information monitoring, digital twin model visualization and numerical control machine fault diagnosis, and realizes online real-time intelligent diagnosis of the numerical control machine.
10. A terminal comprising a memory, a processor and a computer program stored in said memory and executable on said processor, wherein said processor implements the steps of the digital twin driven numerical control machine tool intelligent diagnosis method according to any one of claims 1 to 7 when executing said program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405385.0A CN115562158A (en) | 2022-11-10 | 2022-11-10 | Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211405385.0A CN115562158A (en) | 2022-11-10 | 2022-11-10 | Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115562158A true CN115562158A (en) | 2023-01-03 |
Family
ID=84769931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211405385.0A Pending CN115562158A (en) | 2022-11-10 | 2022-11-10 | Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115562158A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115826935A (en) * | 2023-02-14 | 2023-03-21 | 中国航空油料集团有限公司 | Digital twin model integration system and method based on unified language middleware |
| CN116050678A (en) * | 2023-04-03 | 2023-05-02 | 江苏中科云控智能工业装备有限公司 | Die-casting product processing test system and method based on cloud computing |
| CN116125958A (en) * | 2023-03-08 | 2023-05-16 | 中科海慧（北京）科技有限公司 | Intelligent factory fault diagnosis and decision-making system based on digital twinning |
| CN116224930A (en) * | 2023-01-17 | 2023-06-06 | 扬州市职业大学(扬州开放大学) | Processing control method and system for numerically controlled grinder product |
| CN116449771A (en) * | 2023-05-10 | 2023-07-18 | 中国标准化研究院 | Digital twin modeling method of numerical control machine tool |
| CN116520769A (en) * | 2023-07-05 | 2023-08-01 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
| CN116578040A (en) * | 2023-07-13 | 2023-08-11 | 北京机床研究所有限公司 | Digital twin model construction method, system and terminal for machine tool fault diagnosis |
| CN116776289A (en) * | 2023-08-25 | 2023-09-19 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
| CN117086698A (en) * | 2023-10-19 | 2023-11-21 | 齐鲁工业大学(山东省科学院) | Digital twinning-based cutter multi-working-condition state monitoring method and system |
| CN117272704A (en) * | 2023-11-23 | 2023-12-22 | 湖南华自卓创智能技术有限责任公司 | Digital twin-drive data processing system for multi-source heterogeneous data |
| CN117452877A (en) * | 2023-11-09 | 2024-01-26 | 四川大学 | On-machine measurement realization method of numerical control machine tool based on digital twin model |
-
2022
- 2022-11-10 CN CN202211405385.0A patent/CN115562158A/en active Pending
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224930B (en) * | 2023-01-17 | 2023-08-22 | 扬州市职业大学(扬州开放大学) | Processing control method and system for numerically controlled grinder product |
| CN116224930A (en) * | 2023-01-17 | 2023-06-06 | 扬州市职业大学(扬州开放大学) | Processing control method and system for numerically controlled grinder product |
| CN115826935A (en) * | 2023-02-14 | 2023-03-21 | 中国航空油料集团有限公司 | Digital twin model integration system and method based on unified language middleware |
| CN116125958A (en) * | 2023-03-08 | 2023-05-16 | 中科海慧（北京）科技有限公司 | Intelligent factory fault diagnosis and decision-making system based on digital twinning |
| CN116050678A (en) * | 2023-04-03 | 2023-05-02 | 江苏中科云控智能工业装备有限公司 | Die-casting product processing test system and method based on cloud computing |
| CN116449771A (en) * | 2023-05-10 | 2023-07-18 | 中国标准化研究院 | Digital twin modeling method of numerical control machine tool |
| CN116449771B (en) * | 2023-05-10 | 2024-02-23 | 中国标准化研究院 | Digital twin modeling method of numerical control machine tool |
| CN116520769B (en) * | 2023-07-05 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
| CN116520769A (en) * | 2023-07-05 | 2023-08-01 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
| CN116578040A (en) * | 2023-07-13 | 2023-08-11 | 北京机床研究所有限公司 | Digital twin model construction method, system and terminal for machine tool fault diagnosis |
| CN116578040B (en) * | 2023-07-13 | 2023-09-19 | 北京机床研究所有限公司 | Digital twin model construction method, system and terminal for machine tool fault diagnosis |
| CN116776289A (en) * | 2023-08-25 | 2023-09-19 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
| CN116776289B (en) * | 2023-08-25 | 2023-11-17 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
| CN117086698A (en) * | 2023-10-19 | 2023-11-21 | 齐鲁工业大学(山东省科学院) | Digital twinning-based cutter multi-working-condition state monitoring method and system |
| CN117086698B (en) * | 2023-10-19 | 2024-02-06 | 齐鲁工业大学(山东省科学院) | Digital twinning-based cutter multi-working-condition state monitoring method and system |
| CN117452877A (en) * | 2023-11-09 | 2024-01-26 | 四川大学 | On-machine measurement realization method of numerical control machine tool based on digital twin model |
| CN117272704A (en) * | 2023-11-23 | 2023-12-22 | 湖南华自卓创智能技术有限责任公司 | Digital twin-drive data processing system for multi-source heterogeneous data |
| CN117272704B (en) * | 2023-11-23 | 2024-01-26 | 湖南华自卓创智能技术有限责任公司 | Digital twin-drive data processing system for multi-source heterogeneous data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115562158A (en) | Digital twin driven numerical control machine tool intelligent diagnosis method, system and terminal | |
| CN110348103B (en) | Vehicle damage resistance assessment method based on digital twins | |
| Isermann et al. | Process fault diagnosis based on process model knowledge: Part I—Principles for fault diagnosis with parameter estimation | |
| Matinnejad et al. | Search-based automated testing of continuous controllers: Framework, tool support, and case studies | |
| KR930004437B1 (en) | Technique for producing an expert system for system fault diagnosis | |
| US8423226B2 (en) | Dynamic decision sequencing method and apparatus for optimizing a diagnostic test plan | |
| CN116578040B (en) | Digital twin model construction method, system and terminal for machine tool fault diagnosis | |
| CN110807257A (en) | Method for predicting residual life of aircraft engine | |
| Safiyullah et al. | Prediction on performance degradation and maintenance of centrifugal gas compressors using genetic programming | |
| CN112101431A (en) | Electronic equipment fault diagnosis system | |
| CN105095918A (en) | Multi-robot system fault diagnosis method | |
| CN110705812A (en) | Industrial fault analysis system based on fuzzy neural network | |
| Friederich et al. | Towards data-driven reliability modeling for cyber-physical production systems | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN113420465A (en) | Hydraulic support full-life cycle management method based on digital twin model | |
| CN115422814A (en) | Closed-loop optimization design method for complex electromechanical product driven by digital twin | |
| CN115204491A (en) | Production line working condition prediction method and system based on digital twinning and LSTM | |
| CN117252051A (en) | Cable tunnel monitoring and early warning method and system based on digital twinning | |
| Hess et al. | The maintenance aware design environment: Development of an aerospace phm software tool | |
| Xue et al. | Digital twin-driven fault diagnosis for CNC machine tool | |
| CN114818361A (en) | Digital twin model construction method based on application scene | |
| CN116611523B (en) | Method and system for predicting interpretable faults of turbofan engine | |
| Lu et al. | Digital twin-based operation simulation system and application framework for electromechanical products | |
| CN116305556A (en) | Spacecraft evaluation tool library system based on visual modeling and operation management | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |