54 results about "Inertial systems" patented technology

The present invention provides a flight attitude control method based on inertial navigation technology, which relates to the field of aircraft control technology and includes an attitude control system. The attitude control system includes a quantum inertial navigation fusion module, a distributed multi-source collaborative inertial navigation module, a real-time error compensation module based on deep learning, an energy collection and self-powered inertial system module, a distributed attitude data management module based on blockchain, a multimodal fusion and virtual twin collaborative control module, and a terahertz communication and inertial navigation fusion anti-interference module. The present invention uses a quantum annealing algorithm combined with a compressed sensing algorithm to optimize quantum sensor data, and then combines the D-S evidence theory and the particle swarm optimization algorithm in the distributed multi-source collaborative inertial navigation module to fuse multi-source data, which can deeply mine the deep connection and complementary information between different sensor data, break the simple data level superposition limitation, and greatly improve the accuracy of the attitude information after fusion.

The modular inertial measurement device comprises a sensitive assembly, a circuit assembly and a structural assembly, the sensitive assembly comprises a fiber-optic gyroscope ring assembly, an accelerometer assembly and a temperature sensor, and the fiber-optic gyroscope ring assembly comprises an X-axis fiber-optic gyroscope ring assembly, a Y-axis fiber-optic gyroscope ring assembly and a Z-axis fiber-optic gyroscope ring assembly. The accelerometer assembly comprises three paths of accelerometers; the circuit assembly comprises an inertial measurement component and an optical fiber gyroscope digital closed-loop control component; the structure assembly comprises a body support and a flexible cable assembly, the body support is of a hexahedron structure, and ten mounting table boards are arranged and used for mounting the fiber-optic gyroscope ring assembly, the accelerometer assembly and the circuit assembly; and the flexible cable assembly is used for connecting the fiber-optic gyroscope ring assembly, the accelerometer assembly and the circuit assembly. According to the invention, an inertial product is designed into a modular scheme for realizing decoupling with a system circuit in structural form, so that the adaptability of an inertial system is ensured, the assembly is convenient, and the pain point restricting the layout of the system is solved.

The invention provides an improved active-disturbance-rejection control method based on pre-compensation and quantitative parameter setting, and the method comprises the steps: designing a pre-compensation structure, enabling the designed pre-compensation structure and an original high-order inertial system to be equivalent to a new high-order inertial system, and designing an expected dynamic equation of a closed-loop system; based on the current value output by the new high-order inertial system, obtaining a compensation value of the next calculation step sequence of the new high-order inertial system through a compensation algorithm; obtaining the tracking values of the next two calculation step sequence values of the output of the new high-order inertial system and the received total disturbance through an extended state observer algorithm; obtaining the next three calculation step sequence values of the improved active-disturbance-rejection control algorithm based on pre-compensation through a control law algorithm; determining a dynamic equation of a closed-loop system, and quantitatively calculating a parameter setting formula; updating a quantitative calculation parameter setting formula; and substituting the parameters obtained by quantitative calculation into the control loop to obtain the next four calculation step sequence numerical values of the updated control quantity, thereby realizing the control quantity adjustment of the closed-loop system.

The invention discloses an MEMS three-axis gyroscope thermal drift error calibration method based on segmented calibration, which comprises the following steps: forming an inertial system by using a three-axis accelerometer and a gyroscope, rotating an inertial unit according to a designed rotation scheme by using a low-cost indexing mechanism, and collecting data of the three-axis gyroscope and the accelerometer in a temperature rising process; and carrying out segmentation processing on rotation data in the temperature rise process, calibrating each piece of segmented data in a proposed 24-dimensional system state, and finally obtaining a zero-offset temperature drift curve of the MEMS gyroscope and a temperature drift curve of a non-orthogonal transformation matrix component. According to the method, the application precision of the MEMS three-axis gyroscope is improved, the calibration cost is reduced, and the positioning precision of intelligent mobile terminals such as an unmanned aerial vehicle and a mobile robot can be improved.

The invention discloses a rapid alignment and air correction method during emergency launch, which comprises the following steps: in a ground analysis coarse alignment stage, a strapdown inertial navigation system performs analysis coarse alignment according to bound launch position coordinates and flight target coordinates; determining an initial horizontal attitude angle and an initial azimuth angle and calculating an initial attitude matrix for inertial navigation; in the air correction stage, the strapdown inertial navigation system carries out inertial navigation calculation; when the aircraft is in the rising section of the flight route and the satellite navigation information is valid, performing coarse correction on the strapdown inertial navigation system according to the satellite navigation information, performing fine alignment for a period of time through a Kalman filter, and correcting the attitude matrix by utilizing a fine alignment result, so as to realize integrated navigation; and in the precision verification and secondary correction stage, the aircraft verifies the precision of the inertial system in the flight process, and if the precision does not meet the requirement, secondary correction is performed on the strapdown inertial navigation system.

The embodiment of the invention provides a visual inertia fusion positioning method, a visual inertia fusion positioning device and a binocular visual inertia system. The method comprises the following steps: calibrating an initialized object based on acquired binocular vision sensor data and inertial sensor data to generate a vision and inertia combined calibration result; performing feature point extraction and object tracking according to a visual inertia joint calibration result to generate an optical flow tracking result; performing pose nonlinear optimization based on an optical flow tracking result and the obtained integral residual term to generate a camera pose and a road sign point position; and carrying out information matrix calculation on the camera pose and the road sign point position so as to carry out visual inertia fusion positioning. According to the technical scheme provided by the embodiment of the invention, visual inertial fusion positioning is carried out through joint calibration, feature point calibration, optical flow tracking, nonlinear optimization and information matrix calculation of binocular visual sensor data and inertial sensor data, so that the precision, real-time performance, accuracy and high efficiency of navigation positioning are improved.

The invention discloses a map construction method fusing laser radar inertial navigation satellite navigation multi-modal data, and relates to the technical field of vehicle autonomous positioning and high-precision map construction. The method comprises the steps of obtaining multi-source original data of a laser radar point cloud, and performing preprocessing; sequentially constructing a laser speedometer constraint, an inertia pre-integration constraint, a loopback detection constraint and a global satellite navigation system constraint based on the preprocessed data, and constructing a factor graph optimization framework according to each constraint; in the loopback detection constraint, a point cloud descriptor construction method based on vertical layering of a cylindrical coordinate system is adopted, and a low-dimensional global descriptor with discrimination capability is formed by performing space division on a point cloud and extracting local height features; a delay switching strategy between a laser inertial system and a satellite inertial system is adopted in the factor graph optimization framework; and carrying out positioning and mapping service based on the factor graph optimization framework. According to the method, the precision and reliability of map construction in a complex environment can be remarkably improved.

The invention discloses a multi-source fusion continuous positioning method in combination with a prior feature map, and aims to solve the problem that an existing vision-inertial odometer easily generates accumulative errors in a GNSS denial environment, the method comprises the following steps: constructing a prior feature map comprising key frame poses, feature point descriptors and 3D coordinates based on an open source algorithm; a track displacement difference alignment strategy is adopted to complete visual-inertial system and GNSS joint initialization, and ESIKF is used to replace EKF to improve fusion precision; robust alignment of a local coordinate system and a map coordinate system is achieved through a single-frame geometric constraint accumulation-batch manifold alignment strategy; based on the reverse PnP, the current 3D point cloud and the historical 2D observation constraint are utilized to resolve the relative pose, the map matching result is used as observation to be fused with the GNSS or replace GNSS observation, the ESIKF loose coupling is utilized to eliminate accumulative errors, and continuous high-precision positioning in the GNSS failure scene is achieved.

The present application discloses a method, device, equipment and medium for dynamic load balance in aircraft dynamics analysis under a non-inertial system, and relates to the field of structural dynamics analysis, including: determining the inertial parameters of the aircraft finite element model, and calculating the position vector of the unit integration point based on the coordinates of the unit node; solving the rigid body motion based on the inertial parameters and the external load of the finite element model, obtaining the target vector, and determining the acceleration vector of each unit integration point according to the position vector and the target vector; determining the inertial load of the unit integration point based on the acceleration vector, generating an equivalent node inertial load through the inertial load, accumulating each equivalent node inertial load and the non-inertial system external load vector, and obtaining the node load vector of the non-inertial system; determining the unbalanced force and unbalanced moment according to the node load vector and the non-inertial system coordinate origin, and correcting the equivalent node inertial load to complete the load balance. The present application realizes the dynamic balance of the load in the non-inertial system.

The invention discloses an improved active-disturbance-rejection control method based on error and input delay compensation, relates to the technical field of industrial control, and aims to solve the problem of insufficient input delay and control precision of a high-order inertial system. The method comprises the following steps of: modeling a controlled object into a dynamic system with inertia characteristics, constructing an input delay compensation link and an error-based active-disturbance-rejection link, inputting a control error and a compensation value into an extended state observer (ESO), estimating an error related state quantity and a disturbance tracking value in real time, calculating a control quantity through a state error feedback control law, and compensating the control quantity; and closed-loop accurate adjustment is realized. The invention further comprises an improved second-order active-disturbance-rejection control scheme to adapt to higher precision requirements. The control structure is simplified, control signals and system output are synchronously controlled, the anti-interference capability and the tracking performance are considered, and the method can be widely applied to high-order inertial industrial system control in the fields of chemical engineering, thermal power generation and the like.

A kind of compound inertial system attitude simulation test method, compound inertial system obtains launch system initial attitude angle by initial alignment mode;In dynamic loading process, the inertial data of compound inertial system is collected, and the angle signal of attitude simulation platform excitation is synchronously acquired;The attitude of compound inertial system is converted from launch system to local horizontal coordinate system by navigation solution method, while the angle signal of attitude simulation test platform is converted to the attitude angle of local horizontal coordinate system, and relevant operation is carried out, to obtain the dynamic performance parameter of compound inertial system.

The application discloses a 3-parameter variable structure quaternion solution method for inertial navigation, which comprises the following steps: determining 3 parameters in a quaternion as real-time updated variables; adopting an integral formula to perform integral updating calculation on a 3-parameter differential equation to obtain values of the 3 parameters at t k ; calculating the remaining 1 parameter in the quaternion to finally obtain an updated value of the quaternion, and obtaining a coordinate transformation matrix to support velocity updating and position updating, so as to improve the precision of inertial navigation. The application takes angular rates output by gyroscopes orthogonally installed on a body of a strapdown inertial system as input information, realizes real-time updating of the coordinate transformation matrix for inertial navigation, and simplifies the calculation amount while ensuring the solution precision.

The present invention provides a generalized improved active disturbance rejection control method based on model assistance and Smith predictor-like, belonging to the field of automatic control. The method includes the following steps: describing a class of actual industrial systems by using a high-order inertial system; designing a Smith predictor-like algorithm based on the input and output of the high-order inertial system; designing an extended state observer algorithm based on model assistance with the output of the obtained Smith predictor-like algorithm and the input of the high-order inertial system; designing a control law with the output of the obtained extended state observer algorithm and the system set value; obtaining a new input value of the high-order inertial system, and adjusting and controlling the output of the high-order inertial system according to this value. This method can make full use of the known model information, retain the characteristics of simple structure and easy parameter tuning of the active disturbance rejection control, enable the closed-loop system to better balance the tracking ability and anti-interference ability, and make the closed-loop system have strong robustness.

The present invention discloses a method for rapid alignment and in-air correction during emergency launch, including: during the ground parsing and rough alignment stage, the strapdown inertial navigation system performs parsing and rough alignment according to the already bound launch position coordinates and flight target coordinates, determines the initial horizontal attitude angle and the initial azimuth angle, and calculates the initial attitude matrix for inertial navigation; during the in-air correction stage, the strapdown inertial navigation system performs inertial navigation solution; when the aircraft is in the ascending section of the flight path and the satellite navigation information is valid, the strapdown inertial navigation system is roughly corrected according to the satellite navigation information and fine alignment is performed through a Kalman filter for a period of time, and the attitude matrix is corrected using the fine alignment result, thereby realizing integrated navigation; during the accuracy verification and secondary correction stage, the accuracy of the inertial system is verified during the flight of the aircraft. If the accuracy does not meet the requirements, the strapdown inertial navigation system is secondarily corrected.

The invention discloses a laser inertial measurement unit performance hierarchical evaluation method considering index non-equal priorities, and belongs to the field of supervision and evaluation of laser inertial measurement units in aerospace inertial systems, and the method comprises the following steps: obtaining a predetermined initial performance hierarchical evaluation model of the laser inertial measurement units; the method comprises the following steps: establishing a hierarchical evaluation model by analyzing indexes related to the performance of the laser inertial measurement unit, and establishing a BRB-NEP model considering non-equal priorities of the indexes for the problem of index priority inconsistency; acquiring a training sample of a to-be-evaluated laser inertial measurement unit; optimizing parameters in the initial performance hierarchical evaluation model by using a training sample of a to-be-evaluated laser inertial measurement unit and adopting a preset optimization algorithm to obtain an optimized performance hierarchical evaluation model for the to-be-evaluated laser inertial measurement unit; and evaluating the performance of the to-be-evaluated laser inertial measurement unit by using the optimized performance hierarchical evaluation model. The performance evaluation precision of the laser inertial measurement unit can be improved, and the problems of rule explosion, difficulty in embedding expert knowledge and the like caused by numerous indexes are solved.

The application discloses a normalization-based inertial navigation 5-parameter coordinate transformation matrix solving method, which comprises the following steps: determining five parameters in two rows of a coordinate transformation matrix as real-time updated variables; adopting an integral formula to perform integral updating calculation on a 5-parameter differential equation to obtain values of the five parameters at t k time; calculating the remaining four parameters of the coordinate transformation matrix to finally obtain coordinate transformation matrix updating and support velocity updating and position updating, so as to improve the precision of inertial navigation. The application takes angular rates output by gyroscopes orthogonally installed on a body of a strapdown inertial system as input information, realizes real-time updating of the inertial navigation coordinate transformation matrix, and simplifies the calculation amount while ensuring the solving precision.

This invention discloses a multi-source assisted ADS-B traffic situation awareness processing method. It utilizes data from airborne inertial systems, airspace traffic data received via TCAS and ADS-B IN, and other data sources as auxiliary data sources for ADS-B situation awareness processing. The method acquires the aircraft's absolute position data for verification and filtering to determine the optimal data source for ADS-B situation calculation. This results in more stable and reliable ADS-B traffic situation information compared to existing equipment that uses only GNSS as the sole aircraft positioning data source. This improves the reliability of backend data applications and contributes to enhancing aircraft operational safety and efficiency.

This invention discloses a method for solving the 5-parameter coordinate transformation matrix of inertial navigation. The method includes: determining five parameters in two rows of the coordinate transformation matrix as variables for real-time updates; and using an integral formula to perform integral update calculations on the 5-parameter differential equation to obtain the five parameters at time t. k The time value is calculated; five parameters are orthogonalized and normalized; the remaining three parameters of the coordinate transformation matrix are calculated, and the updated coordinate transformation matrix is ​​obtained, supporting velocity and position updates to improve the accuracy of inertial navigation. This invention uses the angular rate output by the gyroscope orthogonally mounted on the strapdown inertial system as input information to achieve real-time updating of the inertial navigation coordinate transformation matrix, simplifying the computation while ensuring solution accuracy.

The invention provides a virtual beam-assisted inertial / Doppler tight integrated navigation method under an incomplete beam, which specifically comprises the following steps: step 1: establishing an inertial / acoustic Doppler velocimeter tight integrated system, comprising an inertial system error model, an acoustic Doppler velocimeter beam error model, a combined system state equation, and a combined system observation equation; step 2: when all four beams of the acoustic Doppler velocimeter are valid, constructing an artificial intelligence module based on a minimum support vector machine, taking the speed of each beam of the acoustic Doppler velocimeter as output, and training the artificial intelligence network; step 3: when a beam of the acoustic Doppler velocimeter fails, entering an intelligent prediction stage, using the artificial intelligence module that has completed training and learning to continuously predict the speed of the failed beam, and forming virtual beam information; step 4: combining the virtual beam information with the valid beam information as system observation, and continuously performing an inertial / Doppler tight integrated navigation algorithm.

The present invention discloses a method for monitoring bridge deflection by integrating GNSS / accelerometer and MEMS-IMU. The method can reasonably weight the observation value of the inertial system according to the hard constraint of MEMS-IMU heading attitude and the output of high-precision attitude in a short time, take into account the deformation characteristics of the bridge, and fully exploit the non-complete constraint information such as quaternion digital model constraint and heading angle hard constraint, and use the constrained smooth variable structure filter to update and feedback correct the random drift error of the MEMS-IMU device, use the noise information and error information to force the estimated state to switch at the upper limit of the error by using the saturation term, and use the error new information to update in the upper and lower sliding mode surfaces, so as to suppress the multi-path error and other unknown or unmodeled errors in the bridge monitoring environment due to modeling residuals; construct the consistency monitoring index based on the state vector such as rate, and realize the reliable monitoring of GNSS / accelerometer and MEMS-IMU fusion.

A method for solving the coordinate transformation matrix of inertial navigation with few parameters and a fixed structure includes: determining m parameters of the coordinate transformation matrix as variables updated in real time, wherein the remaining 9-m parameters can be directly calculated from these m parameters; and based on the m parameters at time t... k The angular velocity value at time t is obtained by integrating and updating the m parameters using trigonometric integral formulas. k+1 The value at time is used to calculate the remaining 9-m parameters of the coordinate transformation matrix, ultimately obtaining an updated coordinate transformation matrix that supports velocity and position updates, thereby improving the accuracy of inertial navigation. This invention uses the angular rate output from a gyroscope orthogonally mounted on the strapdown inertial system as input information, achieving real-time updates to the inertial navigation coordinate transformation matrix while ensuring solution accuracy and simplifying computation.

This invention relates to the field of navigation and positioning technology, and discloses an unmanned inspection autonomous navigation, positioning, and orientation calibration method, comprising: acquiring acceleration information and extracting gravity vectors from it to establish a horizontal reference plane; collecting three-dimensional point cloud data of the environment and dividing it into time-series data segments according to the sampling time; performing pose compensation on the ranging point based on angular rate data and mapping it to a time reference coordinate system; orthogonally projecting the compensated ranging point onto the horizontal reference plane to generate a two-dimensional projection distribution map; extracting the principal axis direction of the structure and performing geometric alignment with the orthogonal constraint rules of the building, and using angular deviation to correct heading drift. This invention uses gravity vectors to establish an absolute physical horizontal reference, transforming orientation measurement into orientation based on physical vectors. Combined with the orthogonal constraint mechanism inherent in industrial scenarios, it can effectively eliminate coupling errors introduced by attitude fluctuations and solve the problem of heading cumulative drift under long-period operation of inertial systems.

The present invention discloses a heave measurement method based on complementary filtering, which belongs to the field of inertial navigation measurement and ship motion measurement and is used to measure the heave of a ship. The method comprises: based on the concept of complementary filtering, indirectly realizing its complementary high-pass filter by designing a low-pass filter; using the attitude information solved by the inertial system to calculate the attitude matrix between the carrier system, the navigation system, and the semi-fixed system, and then projecting the heave acceleration information under the navigation system to the semi-fixed system; setting a sliding window for recording the heave acceleration information, and calculating the dominant frequency of the acceleration in the window through FFT to update the high-pass filter; filtering and integrating the acceleration information to obtain the heave displacement of the ship, and performing a certain amplitude compensation on the heave displacement. The present invention can adaptively adjust the filter parameters according to changes in sea conditions, without obvious phase advance phenomenon, is easy to implement, and has high heave measurement accuracy.

The application discloses a 4-parameter coordinate transformation matrix solution method of inertial navigation combining normalization and orthogonality, which comprises the following steps: determining 4 parameters in two columns of a coordinate transformation matrix as real-time updated variables; using an integral formula to perform integral updating calculation on 4-parameter differential equations to obtain values of the 4 parameters at t k time; calculating the remaining 5 parameters of the coordinate transformation matrix to finally obtain coordinate transformation matrix updating and support velocity updating and position updating, so as to improve the precision of inertial navigation. The application takes angular rates output by gyroscopes orthogonally installed on a body of a strapdown inertial system as input information, realizes real-time updating of the coordinate transformation matrix of inertial navigation, and simplifies the calculation amount while ensuring the solution precision.

The invention belongs to the technical field of inertial systems, and particularly relates to a double-sensor data cross-regional smooth transition processing method, which comprises the following steps of: measuring the acceleration in a centrifugal test process by using a wide-range acceleration sensor and a small-range acceleration sensor, setting a transition interval, and calculating the acceleration in the centrifugal test process; a small-range measured value is used as an output before the small-range sensor measured value is smaller than the minimum value of the transition interval, and a large-range measured value is used as an output after the small-range sensor measured value is larger than the maximum value of the transition interval. According to the invention, smooth transition synthesis output of cross-interval data is realized, the precision of output data in a small-range range is ensured, a data output function in a wide-range range is ensured, a design scheme depending on a high-precision wide-range device in a full-range range is avoided, and the hardware design cost of a product is effectively reduced.

This invention discloses an inertial navigation four-angle full attitude navigation solution method, including: calculating θ0, α0, β0, and γ0; determining t k The angular velocity of the strapdown inertial system relative to the navigation coordinate system at any given time is calculated using a differential equation, θ. k α k β k and γ k According to θ k α k β k γ k And perform an update calculation to obtain θ k+1 α k+1 β k+1 and γ k+1 According to θ k+1 α k+1 β k+1 and γ k+1 The method involves updating the coordinate transformation matrix to obtain the updated matrix, and then updating the velocity and position based on this updated matrix. The method described in this invention uses the output information from the accelerometer and gyroscope as input information for the four-angle kinematic equations. Through integral calculation, it achieves real-time updating of the coordinate transformation matrix of the carrier relative to the navigation coordinate system. No singular values ​​occur during the calculation process, and the solution result is unique, ensuring the requirements of full attitude and high precision of the carrier coordinate system relative to the navigation coordinate system.

A self-calibration method for frame non-orthogonality error and accelerometer error in a dual-axis frame inertial system is proposed. Under static base conditions, the platform is locked at 10 frame angular positions, accelerometer measurements are collected, and the specific force measurement of the inertial system in the platform coordinate system at each locked position is calculated. The attitude matrix of the inertial system from the platform coordinate system to the local horizontal coordinate system at each locked position is also calculated, yielding the acceleration of the inertial system in the local horizontal coordinate system at each locked position, which is used as the error observation. The residuals of the error coefficients are calculated using a total least squares algorithm, and the estimated values ​​of the measured parameters are corrected. Iterative calculations are performed until the iterative convergence criterion is met, obtaining the self-calibration results for each error coefficient. Through the self-calibration and compensation of the error coefficients, the accuracy of attitude measurement of the dual-axis frame inertial system carrier or base affected by the non-orthogonality error of the axis system can be improved.

The application discloses a kind of inertial navigation unit rotation axis and full attitude calculation method of rotation angle, comprising:θ x0 ,ξ y0 Andξ z0 Are solved;Determine the angular velocity of body relative navigation coordinate system of strapdown inertial system at t k Based on differential equation,θ k ,ξ xk ,ξ yk Andξ zk Are solved;According to θ k ,ξ xk ,ξ yk ,ξ zk Update calculation,θ k+1 ,ξ xk+1 ,ξ yk+1 Andξ zk+1 Are obtained;According to θ k+1 ,ξ xk+1 ,ξ yk+1 Andξ zk+1 , coordinate transformation matrix update is carried out, and velocity update and position update based on updated coordinate transformation matrix are carried out.The method disclosed in the application uses accelerometer and gyroscope output information as the input information of unit rotation axis and rotation angle kinematics equation, realizes the real-time update of coordinate transformation matrix of carrier relative navigation coordinate system by integral calculation, singular value does not appear in the solving process, solution is unique, ensure that the full attitude of body coordinate system relative navigation coordinate system, high-precision requirement.

A kind of fusion time-of-flight ranging monocular vision inertial system initialization method and system, comprising: synchronizing monocular camera, IMU and ToF sensor;Visual SfM preliminary reconstruction;Data collected by ToF sensor is converted to camera coordinate system by external parameter and projected to image plane, to each projection point as center establishes search domain, looks for the nearest neighbor visual feature point in search domain, and outputs feature point-depth pair set after verification;Dual-mode strategy is used to restore metric scale;In sliding window, construct target function, joint optimization, iterative solution, so that depth constraint and motion estimation form strong coupling;System determines initialization success, injects the optimized system state into VIO back-end process, sends low-power instruction to close ToF sensor to sleep mode, and switches to pure monocular-IMU mode operation.The present application guarantees the robustness and accuracy of the initialization stage of the monocular vision inertial system of unmanned aerial vehicle.

The present invention discloses a method for hierarchical performance evaluation of a laser inertial navigation system (IRU) that considers non-equal priority indicators. This method belongs to the field of monitoring and evaluating laser IRUs in aerospace inertial systems, and includes the following steps: obtaining a predetermined initial IRU performance hierarchical evaluation model; constructing a hierarchical evaluation model by analyzing indicators related to the IRU's performance, and addressing the issue of inconsistent indicator priorities by establishing a BRB-NEP model that considers non-equal priority indicators; obtaining training samples of the IRU to be evaluated; optimizing the parameters in the initial hierarchical performance evaluation model using the training samples of the IRU to be evaluated and a preset optimization algorithm to obtain an optimized hierarchical performance evaluation model for the IRU to be evaluated; and evaluating the performance of the IRU to be evaluated using the optimized hierarchical performance evaluation model. The present invention can improve the accuracy of IRU performance evaluation and address issues such as rule explosion caused by numerous indicators and difficulty embedding expert knowledge.