12 results about "Bond graph" patented technology

The invention relates to the field of fault diagnosis, and provides a multistage-flow-based electromechanical system fault diagnosis rule automatic generation method and system, and the method comprises the following steps: S1, building a multistage-flow electromechanical system fault model; s2, generating the fault propagation table, wherein the fault propagation table is generated by adopting a fuzzy cognitive graph or a bonding graph; s3, performing sensor layout optimization according to the fault propagation table; and S4, generating a diagnosis rule. The system comprises a multistage turbomachine system fault modeling unit, a fuzzy cognitive graph fault propagation analysis unit, a bonding graph fault propagation analysis unit, a sensor layout optimization unit and a diagnosis rule generation unit. According to the method, a multilevel flow fault model considering material, energy and information flow is taken as a core, a fault propagation path is dynamically simulated by using a fuzzy cognitive graph or a bonding graph, and the operation and maintenance cost is reduced by optimizing the layout of a sensor; and explainable diagnosis rules are automatically generated to realize accurate fault diagnosis of the complex electromechanical system.

The invention belongs to the technical field of automatic control, and particularly relates to a methanol engine heat management unit control method based on air pressure heat compensation and waste gas heat exchange. The method comprises the following steps: uniformly modeling a heat transfer process and a fluid flow process in a methanol engine heat management unit into a multi-physical domain bonding graph model containing a heat domain and a fluid domain, and setting a feature vector containing a heat domain feature and a fluid domain feature for each node; step 2, executing message passing on the graph neural network, and reading a heat domain temperature feature of a node corresponding to an air inlet of the methanol engine as a predicted air inlet temperature; and 3, the PLC enables the air inlet temperature to reach the target air inlet temperature according to the comparison result of the predicted air inlet temperature and the target air inlet temperature. According to the method, through multi-physical domain coupling modeling and graph neural network online iteration solving, the defects that in the prior art, all heat exchange parts are independently controlled, and the heat flow coupling relation of the system is ignored are overcome.

The invention relates to the technical field of electrolytic cell monitoring, in particular to an electrolytic cell power loss analysis method and system based on a coupling bonding graph. The method comprises the following steps: acquiring a potential variable signal and a flow variable signal in an operation process of an electrolytic cell, and converting into a modulation potential source and a modulation flow source; constructing a coupling bonding graph reference model comprising an electro-thermal sub-model, an electro-chemical sub-model, a thermal sub-model and a fluid sub-model; configuring an energy storage element and a resistive element in the model by adopting a differential causal relationship; inputting the modulation source to a corresponding node to calculate and obtain an energy residual error; the instantaneous power loss is obtained by multiplying the residual error by the measurement signal, and the fault type is positioned according to the positive and negative characteristics of the power loss and the occurrence position. According to the invention, dependence on initial conditions is eliminated, online real-time monitoring and accurate fault positioning are realized, and a physical basis is provided for health management and life prediction of the electrolytic cell.

The invention discloses a molecular property prediction and drug design system based on graph comparative learning. The molecular property prediction and drug design system comprises a data preprocessing module, a graph coding module, a comparative learning module, a property prediction module and an interpretability analysis module. According to the method, molecules are modeled into an atom-bond graph structure, a self-supervised contrast learning mechanism is adopted to learn general representation from a large-scale unlabeled molecule library, and a graph neural network with multi-view graph enhancement, a molecule similarity keeping mechanism and substructure perception is combined to obtain a multi-view graph structure; accurate prediction of molecular properties, drug-target interaction prediction and molecular optimization design based on property targets are realized.

The present application relates to a kind of based on extended Kalman filter prediction deep drilling overflow state perception method, belong to drilling well control technical field, including based on bond graph principle establishes the state space model of drilling wellbore and formation coupling flow system;Real-time data of logging parameters such as pressure before and after overflow occurs, inlet and outlet flow, mud pit increment are used to establish the observation equation model of the state space model of drilling wellbore and formation coupling flow system;The state equation model of the state space model of drilling wellbore and formation coupling flow system is established using pore medium seepage theory and oil and gas well fluid mechanics principle;Formation pressure and wellbore and formation coupling flow state are predicted in real time by introducing extended Kalman filter prediction method.The present application can reduce the false positive rate of system while discovering downhole overflow in advance, effectively reduce the risk of well kick when drilling abnormal high pressure formation, avoid blowout accident, provide safety guarantee for subsequent drilling operation.

This invention belongs to the field of automatic control technology, specifically relating to a control method for a methanol engine thermal management unit based on compressed air heat compensation and exhaust gas heat exchange. The control method includes the following steps: Step 1, unifying the heat transfer process and fluid flow process in the methanol engine thermal management unit into a multi-physics domain bonded graph model containing both thermal and fluid domains, and setting feature vectors containing both thermal and fluid domain features for each node; Step 2, executing message passing on the graph neural network to read the thermal domain temperature features of the corresponding node at the methanol engine intake as the predicted intake temperature; Step 3, the PLC controller, based on the comparison between the predicted and target intake temperatures, ensures the intake temperature reaches the target intake temperature. This invention overcomes the shortcomings of existing technologies that rely on independent control of each heat exchange component and neglect of the system's thermal-fluid coupling relationship through multi-physics domain coupled modeling and online iterative solution using graph neural networks.

The invention discloses a method for carrying out coupling fault analysis on a more-electric aircraft actuation system by using a bonding graph model, which comprises the following steps of: constructing a heterogeneous actuation system by using the bonding graph model, and considering degeneration behaviors such as abrasion, fatigue and aging of elements in the operation of the system; and the fault coupling phenomenon caused by accumulation of dissipated energy in space and time is fused to construct the multi-electric aircraft actuation system fault coupling degradation model with clear mechanism support. According to the fault coupling model, the physical process of component degradation and fault coupling caused by energy dissipation are combined with an actuation model through coding, and the degradation process and the fault of the aircraft actuation system can be accurately analyzed. According to the method, fault mechanism analysis is adopted, different types of faults are injected into the bonding graph model, simulation results are compared, and the influence of propagation of the faults in the more-electric aircraft actuation system on system output is analyzed.

The application discloses a control method of operating parameters of a vanadium redox flow battery system, and comprises the following steps: constructing a hybrid model of the vanadium redox flow battery and constructing a power bond graph model of the vanadium redox flow battery; writing a system state equation according to the bond graph model, converting the system state equation into a corresponding mathematical model, and controlling and optimizing the output performance of the system according to parameters in the mathematical model. In the simulation analysis, the power bond graph model of the vanadium redox flow battery is converted into a corresponding block diagram model according to the power bond graph model; a dynamic simulation model of the vanadium redox flow battery system is established by combining the block diagram model and actual operating conditions of the system; corresponding parameter values in the bond graph model are obtained to obtain accurate output performance; the values of different parameters are changed to observe the change of the output performance, so that the influence of the values of different parameters on the output performance is determined. The application is more suitable for engineering application while realizing the control of the operating parameters of the whole system.

The invention discloses a physical object modeling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-modeled physical object in response to a modeling request submitted by a user; determining the working principle of the physical object; based on the working principle, a bonding graph is generated for the physical object; generating a signal flow graph of the physical object based on the bonding graph; and constructing a simulation model of the physical object by using the bonding graph and the signal flow graph. Therefore, by determining the working principle of the physical object, a unified physical rule support can be provided for subsequent modeling, it is ensured that the model conforms to objective physical essence, and the modeling accuracy is improved without guarantee. In this way, the bonding graph and the signal flow graph are generated subsequently based on the working principle, and then the simulation model of the physical object is generated, manual building by a user is not needed, the operation complexity of the user is reduced, and the simulation modeling efficiency is improved.

The invention discloses an undercarriage dynamics modeling simulation method based on a bonding graph principle. The simulation method comprises the following steps: S1, constructing an undercarriage model; s2, simplifying the physical model; s3, creating a bonding graph model; s4, creating a state-space equation physical model; and S5, carrying out simulation solution. By adopting the modeling simulation method, the undercarriage is simplified into the four-mass physical model, the state-space equation of the four-mass physical model is established by utilizing a bonding graph principle, the state-space equation is established in simulation software, and simulation analysis is performed based on parameter setting, so that the operation efficiency of the model is improved; compared with a traditional method for obtaining modal parameters, the method is simpler, more direct and easy to operate, can accurately predict the reaction of the undercarriage to the ground in the sliding process in the initial stage of model design, can provide technical support for the stability of an airframe in the movement process, and is worthy of application and popularization.

The invention provides an electromechanical hydraulic equipment fault diagnosis method and system based on a bonding graph structure, and belongs to the field of hydraulic equipment fault diagnosis. The problems that in current electro-hydraulic system fault diagnosis, integration of physical information and a data driving method is insufficient, and the capacity of tracking a composite fault source is limited are solved. According to the strong coupling characteristic of the electro-hydraulic system, a power bonding graph is adopted as a physical constraint carrier, the core characteristics of a system flow transmission path and component interaction logic are converted into quantifiable mathematical constraint equations, and the equations clearly express the inherent physical relation of the strong coupling system; through the framework, accurate diagnosis and interpretable tracking of the composite fault are realized, so that the model makes a fundamental breakthrough in the aspects of physical interpretability, composite fault tracking and cross-subsystem correlation analysis.

The application discloses a semi-quantitative fault diagnosis system based on the combination of bond graph and expert system, which comprises the following steps: a data module is used for importing fault data into the system; a field graph module is used for drawing a nuclear power plant equipment and system graph; a reasoning machine module is used for designing a reasoning logic architecture, adaptively changing a quantitative bond graph model and designing the reasoning machine module through a qualitative bond graph method; and a threshold setting module is used for setting a parameter alarm threshold; if an input parameter deviates from the range, a corresponding reasoning event is triggered in the reasoning machine module, and a change trend and a diagnosis result of other parameters are obtained according to reasoning of the reasoning machine module. The application can also diagnose unknown faults through coefficient abnormalities, and can judge fault sizes through parameter abnormal ranges to realize semi-quantification. Compared with other methods, the application has higher adaptability and wider diagnosis range in the fault diagnosis of a nuclear power plant complex system, and a new expert system knowledge acquisition method is added.