129 results about "Electrical model" patented technology

The invention provides a power generation performance evaluation method for an offshore floating photovoltaic power generation system, and the method comprises the steps: considering the influence of offshore wind wave fluctuation, researching the inclination angle change characteristics of a photovoltaic module installed on a floating body structure under different sea conditions, and building a single-sided and double-sided photovoltaic module dynamic and static irradiance model considering the influence of sea wave motion; the invention provides a method for generating a scene with uniform and non-uniform irradiance distribution of an offshore floating type photovoltaic array. The irradiance distribution model and the electrical model of the offshore floating photovoltaic array are combined to form a method for simulating the maximum output power Pmax change characteristic of the offshore floating photovoltaic array under the influence of sea wave operation; and evaluating the annual energy output in the target sea area by combining the wind wave data and irradiance distribution in the target sea area and the maximum output power Pmax change characteristics of the floating photovoltaic array. Compared with an existing photovoltaic power generation performance evaluation method, the influence of sea wave fluctuation on the power generation characteristics of the photovoltaic array is considered, and the method is suitable for an offshore floating type photovoltaic power generation scene.

The invention discloses a power grid lightning stroke fault risk assessment method and system, and relates to the technical field of risk assessment, and the method comprises the following steps: obtaining the operation parameters of a power grid region with dense lightning activities, and constructing a dynamic power grid electrical model considering the load level and reactive compensation influence; obtaining thunder and lightning data and power grid fault data of the current thunder and lightning activity dense power grid area; constructing a lightning stroke fault risk assessment model based on a bp neural network according to the lightning related data and the power grid fault related data; and combining output results of the lightning stroke fault risk assessment model and the dynamic power grid electrical model, simulating power grid operation states and fault risks under different lightning protection strategies, and obtaining a lightning stroke fault risk level. According to the invention, the dynamic power grid electrical model and the lightning stroke fault risk assessment model are constructed to predict and assess the future operation state and the lightning stroke fault risk of the power grid.

The invention provides a 110V transformer winding insulation resistance absorption ratio detection method, which belongs to the technical field of transformer windings, and is characterized in that transformer operation state parameters and environmental influence factors are acquired through a multi-channel synchronous acquisition system, and thermodynamic and electrical models are established. The research adopts methods of principal component analysis, numerical integration and the like, an insulation resistance change rule is analyzed under a standard test voltage, a weight coefficient matrix is constructed in combination with an operation state and an environmental factor, a measured value is corrected through multiple linear regression and a correction coefficient method, and finally, the insulation resistance is obtained through statistical average and standard deviation analysis. The accurate evaluation of the insulation resistance absorption ratio of the transformer winding is realized; according to the method, the influence of the complex working environment and the operation state of the transformer on the insulation performance is fully considered, and the problem that various complex factors in the operation process of the transformer cannot be comprehensively considered and compensated in the prior art is solved by adopting the means of mathematical modeling, data correction, statistical analysis and the like; therefore, the technical problem of large deviation of the measurement result is solved.

The invention discloses a power distribution system fault analysis method and system. The method comprises the steps of collecting operation related data of a power distribution system in real time through various sensors and intelligent metering equipment; preprocessing the collected operation related data to remove noise and interference signals, and establishing a multi-dimensional feature set of the real-time operation state of the power distribution system; extracting potential fault features from the multi-dimensional feature set by using a convolutional neural network, and generating a fault feature vector; performing time sequence analysis on the fault feature vector by using a recurrent neural network, and identifying a possible fault type in the current power distribution system; and in combination with the topological structure and the electrical model of the power distribution system, spatial positioning is performed on the identified fault type based on the graph neural network, and specific nodes of the fault and corresponding fault severity levels are output. According to the embodiment of the invention, the fault detection capability and response speed of the power distribution system can be remarkably improved, and the power distribution system is promoted to develop towards intelligentization and automation directions.

The invention relates to the technical field of electric vehicle charging, in particular to a flexible actor commentator fast charging method based on an electrothermal aging coupling model, and the method comprises the steps: building an electrothermal aging coupling model of a battery; acquiring the temperature, the terminal voltage and the terminal current of the load at the t moment; a relational expression of the state of charge and the open-circuit voltage of the battery is determined through formula fitting; respectively identifying an electric model parameter, a thermal model parameter and an aging model parameter by adopting a recursive least square method and a genetic algorithm; determining an optimal charging strategy by using a flexible actor commentator algorithm; carrying out simulation verification on the optimal charging strategy by using PyBaMM; according to the method, multiple factors influencing the charging safety of the vehicle lithium ion power battery are analyzed in a multi-dimensional mode, the electric heating aging coupling model considering aging is established, and the dynamic behavior of the battery in the charging process is accurately described and predicted; and the safety and robustness of the flexible actor commentator fast charging method based on the electrothermal aging coupling model are improved.

The invention discloses an electric vehicle charging monitoring method and device based on a heterogeneous feature fusion network, and the method comprises the steps: S01, collecting various time domain feature parameters and high-frequency key current signals of an electric vehicle battery in different charging states, and building a sample database; step S02, constructing an electric vehicle charging state prediction model, wherein the model comprises a time-frequency feature fusion network, a CNN-LSTM feature fusion module and a predicted value output module which are connected in sequence; step S04, the edge device receives the time domain characteristic parameters and the high-frequency key current of the tested electric vehicle battery in real time, and calls the deployed electric model for prediction to obtain a charging state prediction value; and S05, judging the abnormal charging state of the detected electric vehicle according to the state prediction value. The method has the advantages of being simple in implementation method, low in cost, high in monitoring precision, fast in early warning response, easy to apply on a large scale and the like.

The invention relates to the technical field of relay protection, in particular to an automatic checking method and system for a relay protection setting value of a power plant, and the method comprises the steps: obtaining relay protection data, including obtaining electrical parameters, equipment parameters and power topological structure information; constructing a topological graph model of the power network by using the power topological structure information, constructing an electrical model based on elements according to the electrical parameters and the equipment parameters, and combining the topological graph model with the electrical model by using node parameter association to obtain a power system integrated model; and performing constant value check calculation based on the power system integrated model, and generating a report according to a constant value check calculation result. Hidden layers are set for different fault types by adopting the multi-branch structure network, so that the neural network can perform specialized learning for different types of fault features, and the adaptability of the system to different fault scenes is enhanced.

The invention relates to the technical field of computer simulation, in particular to a thermal simulation method and system for a semiconductor power assembly. The method comprises the following steps: obtaining geometric structures, material attributes and working characteristics corresponding to each semiconductor power assembly, and carrying out finite element simulation modeling to generate a finite element model of each semiconductor power assembly; performing heat source distribution response analysis on the finite element model of each semiconductor power component based on the working characteristics to generate corresponding heat source distribution fields of each semiconductor power component under different working conditions; based on material attributes, heat conduction simulation analysis is carried out on heat source distribution fields corresponding to the semiconductor power assemblies under different working conditions, and a semiconductor assembly electrical model is constructed to carry out electric heat distribution influence evaluation calculation and thermal simulation iterative optimization; and generating a heat flow temperature distribution simulation optimization result among the semiconductor power components. The thermal simulation precision corresponding to the semiconductor power assembly can be improved.

The invention discloses a dual-motor driving system of a variable-stiffness robot joint and a dual-motor cooperative variable-stiffness control method of the dual-motor driving system. The dual-motor cooperative variable-stiffness control method comprises the steps that motor parameters of a first motor and a second motor and joint parameters of the variable-stiffness robot joint are obtained; constructing a motor electrical model, a motor mechanical model, a joint mechanical model and a spring-damping model of the backlash according to the motor parameters and the joint parameters; determining a total optimization objective function, and solving the total optimization objective function according to the motor electrical model, the motor mechanical model, the joint mechanical model and the spring-damping model to obtain a first current error and a second current error; designing a cooperative controller according to the first current error and the second current error, and outputting a control quantity; and performing dual-motor cooperative variable stiffness control on the first motor and the second motor according to the control quantity. The response speed and rigidity flexibility of the variable-rigidity robot joint can be improved, and the variable-rigidity robot joint can be widely applied to the technical field of motor control.

The invention discloses a simulation analysis method for single-particle electric leakage of a wide bandgap semiconductor device, and the method comprises the steps: constructing a geometric model of a to-be-simulated power device, calculating the vacancy defect density of the power device, carrying out the two-dimensional modeling and grid division, building an electrical model of the power device, and fitting an electrical curve of the power device; then, a collision ionization model after high-energy particle incidence is introduced, mobility and electric leakage degradation parameters are optimized, and an electric leakage degradation model corresponding to the power device is established; and finally, carrying out damage mechanism analysis, extracting the change of microscopic physical parameters of the power device along with time by changing influence parameters in the radiation process, and carrying out reinforcement and optimization on the power device. According to the method, the physical processes of different particle radiation devices can be accurately simulated, different microscopic physical parameters in the electric leakage process of the wide bandgap semiconductor device are extracted, and a technical basis is provided for radiation effect mechanism analysis and reliability evaluation of the wide bandgap semiconductor device by establishing different electric leakage models.

The invention belongs to the technical field of lithium ion batteries, and discloses a novel lithium ion battery estimation method and system considering the core temperature, and the method comprises the steps: building a thermoelectric coupling model of a lithium ion battery, the thermoelectric coupling model comprises an electric model and a thermal model, respectively determining parameters of the electric model and the thermal model by adopting a maximum likelihood method MLM and an adaptive genetic algorithm AGA; on the basis of the thermoelectric coupling model with the determined parameters, an unscented Kalman filter UKF is adopted to estimate the SOC, the terminal voltage and the battery nuclear temperature of the lithium ion battery, a basis is provided for energy management and service life prolonging of the lithium battery, and the safety of the lithium battery at the high temperature can be improved.

The invention relates to the technical field of vehicles, in particular to a vehicle frame multi-objective optimization method based on rollover collision battery pack safety, which comprises the following steps of: constructing a battery homogenization mechanical model to obtain the distance between current collectors of a positive electrode and a negative electrode of a battery under stress; establishing a battery electrical model through the equivalent circuit, and judging whether the battery is short-circuited in the battery electrical model according to the distance between the current collectors of the positive electrode and the negative electrode; establishing a mobile charging vehicle frame three-dimensional model to obtain an instant angular velocity, and analyzing the damage degree of the battery through the coupling model; and converting each unit of the finite element analysis model into independent cells, adjusting cell attributes according to a preset rule, and performing multi-round iteration by adjusting the cell attributes so as to complete optimization of the frame model. According to the method, aiming at the defect of safety optimization of the battery pack during rollover collision, the lightweight of the frame and the improvement of the safety of the battery pack can be realized at the same time, and the optimization efficiency of a complex model is effectively improved.

The invention provides a fault analysis method and system for a direct current converter valve, and the method comprises the steps: applying a test voltage to the direct current converter valve through a voltage generator, and collecting the voltage of each potential sampling point in the direct current converter valve; and performing fault analysis on the direct current converter valve based on the voltage of each potential sampling point. According to the method, the potential distribution testing electrical model of each type of testing voltage is established, a potential distribution theoretical calculation method and potential distribution abnormity reason analysis are provided, and targeted testing and analysis are realized, the correctness of converter valve design is checked, and the circuit abnormity reason is analyzed.

The invention relates to the technical field of motor control, and discloses a sensorless direct-current brushless motor control system which comprises a motor modeling module, a state estimation module, a deep learning prediction module, a filtering fusion module, a self-adaptive control module and a control execution module. The invention also discloses a sensorless direct current brushless motor control method, which comprises the following steps of: model establishment: constructing an electrical model and a mechanical model for describing the dynamic behavior of the motor so as to obtain a motor operation dynamic model suitable for control calculation; and state estimation: performing preliminary estimation on the rotor position and the rotor speed of the motor by utilizing the running dynamic model and combining current and voltage real-time signals acquired in the running process of the motor. According to the method, high-precision and high-stability control of the motor under different load and operation conditions is realized through adaptive control and rotor state estimation optimization technologies, real-time dynamic adjustment and commutation accuracy of the motor are ensured, and the overall control performance is improved.

The invention discloses a resistance-type high-temperature superconducting current limiter simulation model building method, which is used for carrying out analogue simulation on a resistance-type superconducting current limiter made of YBCO (Yttrium Barium Copper Oxide) superconducting tape, and comprises the following steps: S1, building an electrical model module of the resistance-type superconducting current limiter; s2, building a thermodynamic model module of the resistance type superconducting current limiter; s3, carrying out iterative circulation on the electrical model module and the thermodynamic model module; and S4, packaging the electrical model module, the thermodynamic model module and the oscilloscope reading module to obtain a resistance-type superconducting current limiter simulation model so as to access a power grid model. According to the invention, analogue simulation of the resistance-type high-temperature superconducting current limiter can be realized, and the resistance-type high-temperature superconducting current limiter can be connected into a simulation power grid for testing.

The present disclosure provides a power grid voltage stability analysis method and system taking into account new energy control switching, an electronic device, a storage medium and a computer program product. The method comprises: step 2: performing time domain simulation for a preset time on a mathematical model and a state transition model, if the new energy enters a ride-through state during the time domain simulation process, directly entering step 3, and otherwise outputting attention information and then entering step 3; step 3: on the basis of an electrical model, in a rated operation mode of a power system, calculating a power flow of the power system, and obtaining a terminal voltage of the new energy; step 4: on the basis of the electrical model and the mathematical model, in the rated operation mode of the power system, calculating the power flow of the power system, and obtaining a bus voltage of a POC bus; and, on the basis of the terminal voltage of the new energy, a threshold voltage for the new energy entering the ride-through state, and the bus voltage, outputting corresponding prompt information.

The invention discloses a battery temperature estimation method and an electric bicycle, and relates to the technical field of battery management. The method comprises the following steps: constructing an electrical model and a thermal model of a battery under a preset operation condition; constructing an electrothermal coupling model of the battery under a preset operation condition according to the electrical model and the thermal model; the electrothermal coupling model is used for describing the electrical and heat change process in the battery; and based on the electrothermal coupling model and the electrical measurement data of the battery in the charging and discharging process, estimating the internal temperature and the surface temperature of the battery under the preset operation condition by adopting an extended Kalman filtering algorithm. Compared with a traditional monitoring method depending on a temperature sensor, the internal and surface temperature changes of the electric bicycle battery can be reflected more accurately, thermal characteristic changes under complex working conditions can be dynamically adapted, the complexity and the cost of the system are reduced, and the safety and the reliability of the battery management system are effectively improved.

The invention belongs to the technical field of geophysical exploration, and particularly discloses a ground well controllable source electromagnetic method joint inversion method and system based on a tensor source, and the method comprises the steps: carrying out the forward modeling of an established three-dimensional electrical model through a CSEM in a ground well, and obtaining the impedance tensor and a tipper of a tensor controllable source; constructing a three-dimensional ground and in-well CSEM combined inversion objective function and a gradient of the inversion objective function by using the model roughness matrix and the data fitting item; and solving the gradient of the inversion objective function by adopting an improved L-BFGS optimization algorithm based on a momentum method, and inverting the underground electrical structure. According to the method, through joint inversion and in combination with controllable source electromagnetic data in the ground and the well, the transverse and longitudinal resolution of exploration is improved, the multiplicity of inversion is reduced, and the inversion result is more reliable.

The invention discloses a multi-field coupling modeling method for a lithium ion battery. The method comprises the following steps: initially setting parameters and given working conditions of the lithium ion battery; constructing an electrical model, a thermal model and an aging model to realize bottom-layer electrical simulation, thermal simulation and aging simulation; completing parameter coupling and transmission to obtain a new parameter and taking the new parameter as an input variable; and continuously iterating to obtain real-time battery state parameters and a relationship between the real-time battery state parameters Compared with a traditional lithium ion battery electric-thermal coupling model, the method has the advantages that the research on the aging which is a long-time scale variable is added, and the working state of the whole life cycle of the lithium ion battery can be described. The behavior and the state of the lithium ion battery are described more accurately and comprehensively by establishing a simulation model of'multi-time scale 'and'multi-physical field coupling'.

The embodiment of the invention provides a cable early-stage fault positioning method and device based on metal sheath parameters. The cable early-stage fault positioning method based on the metal sheath parameters comprises the steps that a cable electrical model is established based on electrical parameters; obtaining a key electrical quantity, comparing the key electrical quantity with a preset threshold value, and determining a comparison result; determining fault feature information based on the comparison result; and determining a fault point based on the fault feature information and the fault positioning equation. According to the scheme, the impedance characteristic of the cable metal sheath is utilized, and the parameters of the metal sheath are introduced into a fault positioning algorithm. According to the method, the positioning error is effectively reduced, the accuracy of the early fault positioning process is remarkably improved, and a more efficient and more accurate solution is provided for solving the detection and positioning problems of the power system in the early stage of the fault.

The invention provides a virtual power plant efficient aggregation intelligent scheduling method and system oriented to wide-area distributed resources, and the method comprises the steps: selecting a plurality of distributed resources, depicting a feasible region of each resource, and constructing a dynamic electrical model corresponding to each resource; the method comprises the following steps of: approximating feasible regions of various distributed resources based on Zonotope so as to aggregate the distributed resources; converting the aggregated Zonope form into a half-space form to obtain a first constraint condition for optimization regulation and control, and constructing an aggregation resource cluster optimization regulation and control model by taking optimal operation efficiency of the virtual power plant VPP as a target; and solving the optimization regulation and control model under a first constraint condition, and performing two-stage regulation and control on each distributed resource cluster according to a solving result. According to the method, the accuracy degree of aggregation regulation and control of the distributed resources in the virtual power plant scene is improved, the flexibility of the distributed resources is ensured, and optimal configuration of the resources is realized.

The invention discloses a distributed flexible resource energy management method and system for a virtual power plant. The method comprises the steps of designing a distributed flexible resource energy management system framework in a virtual power plant scene, managing two distributed flexible resources of an energy storage system and a water treatment system by controlling charging and discharging power of a battery and operating power of a water pump, and constructing dynamic electrical models of the energy storage system and the water treatment system; establishing a dynamic energy management model of each distributed flexible resource based on a Markov decision process by taking economical efficiency maximization as a target and considering power flow constraints of the power distribution network; and training the dynamic energy management model through an improved deep reinforcement learning algorithm to form a real-time energy management strategy of the distributed flexible resources. According to the scheme of the invention, distributed flexible resource operation regulation and control considering high efficiency, economical efficiency, robustness and safety is formed.

The invention relates to a power distribution network planning adjustment method and device based on digital twin and multi-objective optimization, belongs to the technical field of power distribution network planning, and solves the problems that an existing planning result is not accurate enough, the anti-risk capability is insufficient and a dynamic adjustment mechanism is lacked. The method comprises the following steps: constructing a digital twinborn model of the power distribution network; a prediction model is constructed, and a prediction result is fed back to the digital twinborn model; introducing Monte Carlo simulation to generate a plurality of operation scene sets, executing digital twin simulation on each operation scene set to obtain network state distribution under different scenes, and quantifying system response characteristics under uncertainty; constructing a multi-target robust optimization model in combination with the network state distribution and the system response characteristics, and optimizing a power distribution network planning and equipment investment scheme; and the actual power distribution network investment data and the operation state are transmitted back to the digital twinborn model so as to adjust the electrical model and the prediction model of the digital twinborn model. And closed-loop self-learning of planning-implementation-correction is realized.

A method for monitoring a battery system is proposed. The method includes providing a sequence of pairs of measured current and voltage values that follow one another in time. The pairs of current and voltage values indicate the current flowing through the battery system and the voltage present at the battery system. The method also provides for an electrical equivalent model of the battery system to be provided. The equivalent electrical model has several impedances connected in series. Initial impedance parameter values are provided for the impedances of the equivalent electrical model. The method provides for adjusting a first impedance parameter of an impedance of the equivalent electrical model based on the difference between a first voltage value simulated based on the initial impedance parameter values and the first current value of the finite sequence and the first measured voltage value of the finite sequence. An optimized first impedance parameter value is thereby obtained. By minimizing the deviation of a sequence of simulated voltage values obtained on the basis of the electrical equivalent model and the first sequence of measured current values from the sequence of measured voltage values by adapting at least one further impedance parameter of the impedances of the electrical equivalent model, at least one optimized further impedance parameter value of the at least one further impedance parameter is obtained. A battery management system for carrying out the method is also proposed.

The invention provides a deep and large fracture depicting method based on low-frequency electromagnetic information recovery enhancement, and the method comprises the steps: S1, collecting electromagnetic data, and carrying out the preprocessing of the electromagnetic data, and obtaining the preprocessed electromagnetic data; s2, obtaining frequency domain apparent resistivity and phase according to the preprocessed electromagnetic data; s3, establishing a shallow stratum electrical model; s4, acquiring a depth domain apparent resistivity profile according to the shallow stratum electrical model; and S5, depicting deep and large fracture distribution based on the depth domain apparent resistivity profile. According to the invention, enhancement of low-frequency electromagnetic signals is realized, the inversion precision of electromagnetic data is improved, low-frequency geological information is effectively recovered, and deep and large fractures can be effectively described.

The application discloses a kind of electrical model light weight translation software methods based on IFC data format, it is related to model data processing technical field, including the following steps: extracting industrial foundation IFC data format electrical model geometry data, attribute data and topological relation data, based on the electrical equipment shell of the electrical model, electrical circuit and electrical component, the electrical model is divided into geometry layer, attribute layer and topological layer, and the geometry layer, attribute layer and topological layer are removed to redundant information, obtain the simplified simplified electrical model.This is through the geometry, attribute and topological data of electrical model and implements hierarchical light weight processing, rather than using general simplification strategy, effectively removes the redundant information of each level, achieves the effect of accurately reducing model data amount, realizes the efficient transmission and quick loading of translated model in different hardware terminal, improves the basic application ability of model cross-device platform.

An optimization method for BLDC non-inductive low-speed starting based on IF starting and flux estimation, comprising the following steps: step one: establishing a BLDC motor electrical model, and obtaining relevant parameters for building a current double closed loop model through the BLDC motor electrical model; step two: based on the simulink simulation software, building a current double closed loop model of d and q axes; step three: based on the current double closed loop model built in step two, realizing IF open loop low-speed starting and acceleration of the BLDC motor; step four: constructing a discrete nonlinear flux observer, and online estimating the flux to obtain the rotor electric angle_ref and the equivalent back electromotive force component; step five: according to the equivalent back electromotive force component, online following and correcting the open loop electric angle. The present application can realize quick and undisturbed switching from open loop starting to non-inductive closed loop control, thereby significantly improving the starting success rate and operation stability of the BLDC motor under low-speed working conditions.

The present invention relates to a sensing system (10) for monitoring a substrate (1), comprising a sensing unit (4) with first and second sensing elements (3A, 3B) configured to be inserted into the substrate (1); a signal generation unit (5) configured to apply an electrical signal to the sensing elements; a readout unit (6) configured to determine at least one electrical parameter as a result of the electrical signal being applied to the sensing elements (3A, 3B); and a processing unit (7) configured to determine at least an amount of water inside the substrate (1) among an amount of water in the substrate (1) and a nutrient concentration in the substrate (1), based on the determined at least one electrical parameter and an electrical model of a combination of the sensing elements (3A, 3B) and the substrate (1) in which they are inserted, wherein the electrical model comprises a first inductor modelling a first inductance (Lp1) of the first sensing element (3A) and a second inductor modelling a second inductance (Lp2) of the second sensing element (3B); a capacitor modelling a capacitance (Cp) between the sensing elements (3A, 3B); a resistor modelling a conductance (Gp) between the sensing elements (3A, 3B); wherein the first inductance (Lp 1) is modelled as a known first function of the amount of water inside the substrate (1), wherein the second inductance (Lp2) is modelled as a known second function of the amount of water inside the substrate (1), wherein the capacitance (Cp) is modelled as a known third function of the amount of water inside the substrate (1), and wherein the conductance (Gp) is modelled as a known fourth function of the amount of water inside the substrate (1) and an amount of mobile ions representing the amount of nutrients inside the substrate (1).

The present invention relates to an arc fault detection and location method based on system modeling analysis, including: simulating an arc fault experiment, recording the fault voltage and current of the branch where the arc is located, determining the series connection of the voltage source and the resistor, and constructing an arc electrical model; constructing a first state space equation and a second state space equation, and establishing an equivalent model based on the first state space equation and the second state space equation, and an equivalent simulation model; judging whether a system fails, if a fault occurs, determining the location of the fault, and judging the type of fault. The method of the present invention is based on real test data, and reduces the influence of power electronic devices on arc fault detection and location. The simulation verification algorithm has high accuracy, strong real-time performance and low cost, and is more suitable for DC microgrid systems.

This invention provides new and useful methods for accurately imaging heart rhythm disorders. Novel panoramic optical mapping methods, and recent advances in machine learning techniques, are used to create a mechano-electrical model effective in predicting electrical activity of a tissue based on motion of the tissue. Deep learning techniques for constructing three-dimensional intramural electrical wave patterns from surface data, imaging chambers for performing panoramic optical mapping methods, and deep learning techniques for motion tracking tissue via optical and / or ultrasound data are also provided. The optical mapping and deep learning techniques of the disclosure may be applied in a plurality of different ways, individually or in combination, to improve the diagnosis and treatment of heart rhythm disorders. Also provided are systems for performing the methods described herein as well as non-transitory computer readable storage media and computer products.