64 results about "Rotordynamics" patented technology

The invention discloses a circumferential pull rod rotor test bench and method. The circumferential pull rod rotor test bench comprises a grooved platform, a driving motor, a load device and a circumferential pull rod rotor, wherein the driving motor and the load device are mounted on the grooved platform; the circumferential pull rod rotor comprises a plurality of gas compressor wheel discs, a plurality of turbine wheel discs and an intermediate shaft; a plurality of gas compressor pull rod bolts penetrate through the gas compressor wheel disc, and the gas compressor wheel disc is connected in a pre-tightening manner through the gas compressor pull rod nuts; a plurality of turbine pull rod bolts penetrate through the turbine wheel disc, and the turbine wheel disc is connected in a pre-tightening mode through turbine pull rod nuts. The test bed further comprises a gas compressor casing and a turbine casing, and the gas compressor casing and the turbine casing are both installed on the grooved platform and are adjustable in position. Dynamic characteristics and various rotor faults of the circumferential pull rod rotor of the gas turbine can be effectively simulated, and the test bench is reliable in structure and stable in operation.

This invention relates to the field of aero-engine maintenance engineering and quality assessment technology, and discloses an aero-engine overhaul assessment method based on a physical information Bayesian neural network. The method includes collecting multi-source heterogeneous data from maintenance and testing sites and converting it into key process indicator scores; extracting rotor dynamics, imbalance transmission, and empirical formula features to construct physical constraint regularization terms; establishing an initial Bayesian neural network containing deterministic and variational Bayesian layers; inputting the key process indicator scores into the network, and optimizing parameters by combining the physical constraint regularization terms with adaptive annealing and early stop mechanisms; performing multiple Monte Carlo samplings on the trained network to calculate the mean distribution of the output results and obtain distribution statistical characteristics; calculating the quality score, confidence interval, and attribution warning information based on the distribution statistical characteristics, and outputting an overhaul assessment report. This invention solves the problem that existing pure data models violate physical laws and cannot quantify confidence levels.

According to the thermal power plant equipment fault early warning method provided by the invention, the array type vibration sensor group and the infrared thermal imaging matrix are deployed to construct the three-dimensional space-time sensing network, and the independent component analysis algorithm is adopted to carry out edge denoising processing, so that the fault feature extraction accuracy under a complex working condition is improved, and the fault early warning efficiency is improved. According to the method, geometric coordinate mapping, rotor dynamics simulation and real-time data indexing are fused based on an equipment digital twinning model, part-level positioning of bearing faults is achieved, twinning derivative parameters are injected through a transfer learning mechanism to predict target equipment, the fault missing report rate of the equipment is reduced, and a safe-economical-sustainable triple gain closed loop is formed.

The application belongs to the technical field of simulation analysis, and particularly relates to a multi-physical field coupling simulation method of an electric spindle. The multi-physical field coupling simulation method of the electric spindle comprises the following steps: S100, a multi-physical field coupling model is established through finite element software, including: importing a geometric model, setting a material, setting a rotor dynamics module, setting a solid heat transfer module and mesh division; S200, solving is performed through the finite element software, including: performing multi-physical field coupling of a bearing nonlinear restoring force model, a motor unbalanced magnetic pull model and a spindle thermal model with the electric spindle rotor model, and obtaining dynamic performance by solving. The simulation model for the dynamic characteristic research of the electric spindle in the technical scheme can meet the demand of the dynamic characteristic research of the electric spindle under actual complex working conditions.

The application provides a magnetic suspension mixed three-degree-of-freedom bearing and an air compressor, wherein the bearing comprises a radial magnetic bearing assembly and an axial magnetic bearing assembly, a permanent magnet capable of providing a bias magnetic field is clamped between the radial magnetic bearing assembly and the axial magnetic bearing assembly, the axial magnetic bearing assembly comprises a first axial stator core and a second axial stator core, the first axial stator core has a first magnetic ring, the radial thickness of the first magnetic ring is la, the second axial stator core has a second magnetic ring, the radial thickness of the second magnetic ring is le, and la < le. The application increases the radial thickness of the side with smaller axial output, thereby improving the axial output of the second axial stator core, making the structures of the first axial stator core and the second axial stator core asymmetric, achieving axial force balance design without increasing the overall volume of the bearing, meeting the axial load demand, and thereby improving the rotor dynamics characteristics.

The application discloses a kind of based on multiple type signal dry vacuum pump working state intelligent diagnosis method and system, specifically related to vacuum pump monitoring technical field, by synchronous acquisition encoder pulse and vibration acceleration signal, equal-angle resampling establishes angular domain sequence, by pulse interval calculation instantaneous angular velocity and angular acceleration and combined with moment of inertia to obtain actual inertia moment, based on screw profile and ideal compression model generates theoretical aerodynamic load moment and difference integration obtains leakage flux index, corrects rotor dynamics aerodynamic term and iteratively inverts unbalance eccentricity, exports health status and fault grade.The application adopts angular domain alignment to make criterion consistent under speed fluctuation and working condition change, constructs leakage flux index by difference integration of aerodynamic load and inertia moment, and iteratively inverts physical unbalance eccentricity with residual error, so that leakage and unbalance have distinguishable physical quantity representation, improve evaluation consistency and traceability.

The invention discloses a gas foil bearing wear high-fidelity modeling method based on a physical neural network, and relates to the technical field of rotor dynamics and fault diagnosis. The method comprises the following steps: firstly, constructing physical models of gas foil bearing wear, wherein the physical models comprise a gas foil bearing structure and lubrication mechanism model and a gas bearing rotor system nonlinear dynamic model; and then building a hybrid modeling framework fusing a physical mechanism and data driving, training a model mismatch item by adopting a neural network, representing an unknown parameter by adopting a Sigmoid function, introducing a displacement compensation factor, and finishing model parameter updating by combining forward calculation and reverse calculation. According to the method, high-fidelity modeling of wear evolution and key parameter collaborative identification can be realized, the model adaptability and the data matching precision under complex working conditions are improved, and technical support is provided for a gas bearing digital twin system and predictive maintenance.

This application belongs to the field of engine modeling technology, specifically relating to a simplified modeling method and apparatus for the dynamics of an interstage elastic support structure in an engine. The method includes: determining the equivalent density of the elastic shaft segment using an equal-volume equivalence method based on the dimensional parameters of the elastic shaft segment of the elastic support structure; determining the equivalent elastic modulus of the elastic shaft segment based on the radial stiffness attenuation coefficient of the elastic support structure; equivalence the elastic shaft segment using equivalent beam elements according to the dimensional parameters of the elastic shaft segment of the elastic support structure, and assigning equivalent density and equivalent elastic modulus parameters to the equivalent beam elements; and establishing a coupling relationship between the established equivalent beam element model and the overall engine dynamics model to complete the establishment of the overall engine rotor dynamics model. This application establishes an equivalent beam element model for circumferentially discontinuous shaft segments suitable for rotor dynamics analysis, ensuring the accuracy of the overall engine rotor dynamics analysis and the rationality of the rotor dynamics structure optimization design direction.

The application discloses a large-length-diameter-ratio rotor structure with a separated turbine, comprising a four-stage fan, a two-stage front turbine, a single-stage rear turbine, four bearing supporting points, a connecting structure and the like. A 1-2-1 four supporting point supporting scheme is adopted, and an intermediate supporting point is additionally arranged at the front turbine to control the bending deformation of the large-length-diameter-ratio rotor. Meanwhile, the two-stage front turbine in the middle section of the rotor is designed as an integrated ring cavity structure, the structure angular rigidity is enhanced, and the overall gyroscopic moment effect is exerted. The front turbine and the rear turbine are connected with the rotor shaft through a large-space double-centering-face stop mouth-toothed sleeve connection, the bending moment bearing capacity is improved, the gyroscopic moment of the wheel disc is fully applied to the shaft section, the rotor resonance speed safety margin is improved, and the bending deformation is controlled. The application is the first rotor structure proposed for a new engine with an inter-stage combustion chamber, and meets the dynamic design requirements of the rotor with the characteristics of the multi-stage separated turbine and the large-length-diameter ratio.

The invention belongs to the field of engine design, and particularly relates to an aero-engine whole machine dynamic structure design parameter optimization method, which utilizes an APDL language of ANSYS software to carry out parametric modeling on an aero-engine whole machine (including a rotor, a support and a stator casing), and applies additional centrifugal force and additional gyroscopic moment generated by maneuvering flight. The stress level of the bearing case, the strain energy distribution of a rotor system and the rotor and stator gap change are obtained through bearing case stress analysis, critical speed analysis and unbalanced response analysis. Based on the analysis results, multi-objective optimization is carried out on complete machine dynamic design parameters, so that the stress level of a force bearing casing is lowest, rotor strain energy distribution meets rotor dynamic design requirements, rotor and stator gap changes are minimum, the rub-impact risk is reduced, optimization of the structural design parameters is completed through software, the design efficiency is improved, and the design cost is reduced. The design period is shortened.

This invention relates to a dynamic balancing method for a flexible rotor system in an engine, belonging to the technical field of mechanical rotor dynamic balancing. It is applicable to the dynamic balancing of low-pressure rotors or power turbine rotors in turbofan engines when using flexible rotors. The turbofan engine includes a compressor blade disk and a hollow connecting long shaft. The dynamic balancing method includes: S1, inspection of the manufacturing process; S2, dynamic balancing tests on the connecting long shaft and blade disk respectively; S3, assembly and testing of the connecting long shaft and blade disk bearing the first identification on the test bench of the dynamic balancing device according to design requirements; S4, checking whether the dynamic indicators meet the standards; S5, full-range speed vibration testing of the connecting long shaft and blade disk as a whole on the platform of a rotor dynamics experimental apparatus; and S6, verification of the repeatability of assembly parameters and dynamic balancing, thus improving the efficiency of dynamic balancing.

The invention belongs to the technical field of rotor dynamics, and discloses a blade tip clearance rapid prediction method in a maneuvering flight state. Additional load excitation and additional parametric excitation caused by maneuvering flight are derived based on the beam unit and the concentrated mass. A finite element model of the birotor-bladed disc-cartridge receiver coupling system is established based on a beam-shell hybrid model, additional load excitation and additional parameter excitation caused by maneuvering flight are fused, the finite element model of the birotor-bladed disc-cartridge receiver coupling system in a maneuvering flight state is finally established, and gaps of blade tips are calculated through a numerical integration method. A blade tip gap prediction model is constructed based on an artificial neural network, model training is completed based on a numerical calculation result serving as a training set, and finally rapid gap prediction under different working conditions is achieved. According to the method, the influence of centrifugal deformation of the blade, vibration displacement of the rotor, maneuvering flight deformation and other factors on the blade tip clearance is effectively considered, the morphology of the complex blade is comprehensively considered, and the model generalization ability is high.

The application relates to the technical field of rotor dynamics test, and discloses a device for simulating a misalignment fault of a support point of a rotor system and a foundation loading device. Misalignment loading modules are arranged at the bottoms of each support point bearing of a test rotor, and the first driving unit and the second driving unit of each misalignment loading module are used to realize misalignment or displacement loading of the support point bearing position of the test rotor. Through coordination of the positions of the three driving units, independent control of the support point bearing of the test rotor in three degrees of freedom can be realized, and horizontal direction offset misalignment, vertical direction offset misalignment and overturning direction misalignment of the support point bearing can be realized at the same time. In addition, displacement or rotation angle excitation can be controlled in the three misalignment directions, and a hardware foundation is provided for dynamics test of a rotor system in a real environment.

This application belongs to the field of aero-engine simulation technology, and relates to a method and apparatus for simulating the overall pulsation characteristics of a rotating detonation turbine engine. The method includes: obtaining the given total pressure pulsation characteristics of the rotating detonation combustor; calculating the total outlet pressure of the rotating detonation combustor at the current simulation moment; inputting the total outlet pressure of the rotating detonation combustor into a pre-constructed overall performance model of the turbojet engine in transition state. The overall performance model is formed by coupling various engine components through aerodynamic parameter interfaces in the order of airflow, considering rotor dynamics and volume effects during coupling; solving for independent engine variables and the characteristics of each component under the constraints of overall engine matching conditions of flow balance and power balance until the residuals converge; extracting the total inlet pressure of the rotating detonation combustor and calculating the characteristics of each engine component at the next simulation moment. This application realizes the simulation of the unsteady coupling characteristics of the rotating detonation combustor and the turbojet engine.

The application relates to the technical field of vibration active control and artificial intelligence, and discloses a keyless phase virtual dynamic balancing method and system for an aero-engine fan rotor based on a finite element method, which comprises the following modules: a modeling and simulation module configured to obtain a first-order critical rotating speed and a vibration mode of an initial rotor dynamics simulation model; a model calibration module configured to calibrate the initial rotor dynamics simulation model according to a first actual amplitude, and obtain a calibrated rotor dynamics simulation model; a model updating module configured to update the calibrated rotor dynamics simulation model, and obtain an updated rotor dynamics simulation model; a trial weight and counterweight module configured to substitute the second actual amplitude into a particle swarm optimization, calculate an actual rotor system total unbalance and a trial weight angle difference, finally add a counterweight and select a direction until vibration is reduced, and dynamic balancing is achieved. According to the application, the position of an unbalance can be accurately determined through amplitude analysis.

This invention discloses a pulse-based vibration reduction control method for the demagnetized rotor of a permanent magnet direct-drive wind turbine, comprising the following steps: based on rotor dynamics theory, the unbalanced magnetic pull generated by the demagnetization of the permanent magnet direct-drive wind turbine is decomposed into terms related to the eccentricity state of the rotor system and fault disturbance terms, thus constructing the dynamic equations of the permanent magnet direct-drive wind turbine rotor system; a pulse control scheme is designed; the terms related to the eccentricity state of the rotor system are linearized using the Lipschitz condition, and the fault disturbance terms are analyzed and processed by constructing peak-to-peak gain; sufficient conditions for the pulse control scheme are derived based on Lyapunov stability theory; and the effectiveness of the designed pulse control scheme is verified through numerical simulation. This invention realizes the analysis and processing of the unbalanced magnetic pull generated by the demagnetization of a permanent magnet direct-drive wind turbine, providing a foundation for the design of a demagnetization vibration controller for permanent magnet direct-drive wind turbines.

The invention belongs to the technical field of rotor dynamics, and discloses a gas turbine multi-disc rotor imbalance fault diagnosis method and a related device. The method comprises the following steps: extracting a feature vector based on acquired abnormal vibration data; on the basis of the feature vectors, a rotor unbalance fault diagnosis model is used for identifying and positioning a fault source, and a multi-disc rotor unbalance fault online identification and tracing result is obtained; the rotor imbalance fault diagnosis model is composed of a low-fidelity model network and a high-fidelity model network, and the low-fidelity model network is used for predicting a low-fidelity result under the condition of given input data after training. And the high-fidelity model network is used for acquiring a high-fidelity prediction result by learning a mapping relationship between the low-fidelity output result and the high-fidelity output result. According to the invention, accurate identification and online traceability of the unbalance fault parameters of the multi-disc rotor are realized.

The invention relates to a rotor system integrated topological optimization design method considering dynamic performance, and belongs to the technical field of high-performance calculation science, and the method comprises the following steps: taking statics and rotor dynamics as constraint conditions for a rotor two-dimensional structure, carrying out two-dimensional topological optimization design, and obtaining a new rotor two-dimensional structure; and on the basis of the new two-dimensional structure of the rotor, three-dimensional topological optimization design is carried out on the sector model of the rotor by taking the rotation period structure frequency and the statics property as constraint conditions, and a new three-dimensional configuration is obtained. According to the method, on the basis of traditional topological optimization which only considers the static performance, the constraint on the dynamic performance is increased, the dynamic performance requirement needed by the rotor system can be met while the maximum rigidity design is completed, the design period can be effectively shortened, and the design efficiency can be effectively improved.

This invention provides a method for tolerance analysis of the inlet ring clearance of a nuclear power plant main pump. By taking the clearance between the main pump impeller inlet ring and the suction duct as the optimization target and constructing a dimensional chain, and combining 3D modeling and tolerance analysis software, the method achieves precise definition of assembly relationships and tolerance parameters. At the same time, it introduces rotor dynamics deflection deformation calculation and conditional assembly logic, which can truly reflect the tolerance accumulation law of the main pump under 3D assembly and operating conditions. This significantly improves the accuracy and reliability of clearance tolerance analysis, effectively avoids the risk of rotor rubbing during operation, reduces testing and assembly costs, and thus ensures the long-term safe and stable operation of the nuclear power plant main pump.

The invention relates to a high-speed bearing structure matching design method driven by a bearing digital twin model. The method comprises the following steps that S1, structure parameters meeting the bearing capacity, the service life and the reliability of a main bearing are designed according to constraint conditions; s2, combining the structure size according to the structure size type, predicting vibration, rotation precision, power consumption and rigidity in combination with bearing-rotor dynamics, and realizing correlation of structure-dynamics-performance; and S3, according to the performance demand priority, determining a priority combination sequence of various types of structure sizes. The experiment cost can be remarkably reduced, and the experiment period can be shortened. According to the high-speed bearing structure matching design method driven by the bearing digital twin model, the bearing vibration, rotation precision, power consumption and rigidity can be predicted according to the bearing rotor dynamical model to match and design the structural size of the angular contact ball bearing, the cost can be effectively reduced, and the experimental period is shortened.

The application discloses an experimental device and method for researching high-speed instability interval of rotor oil liquid, and the experimental device comprises a frame, a rotating shaft, an oil tank, a first bearing, a second bearing, a storage plate, a plurality of partition plates and a processor; a circular hole is formed in the middle of the top plate and the storage plate, the first bearing and the second bearing are respectively installed in the circular hole of the top plate of the storage plate and the frame through a first bearing seat and a second bearing seat; the rotating shaft vertically penetrates the first bearing and the second bearing from top to bottom, is connected with the oil tank between the storage plate and the bottom plate, and rotates horizontally under the action of a motor; the plurality of partition plates are detachably and evenly distributed and installed in the oil tank, one end of the partition plate is connected with a stand column located in the center of the oil tank, the other end is connected with the inner side of the oil tank, and the oil tank is evenly separated into a plurality of sub-regions. The application can effectively simulate the vibration phenomenon of the oil liquid under the condition of the baffle, the baffle is convenient to assemble and disassemble, and is suitable for the research on the oil liquid rotary vibration of the rotor dynamics.

To address the problem of insufficient design margin caused by the inability to obtain design boundaries in existing turbopump seal-rotor design methods, this invention discloses a liquid rocket engine turbopump seal-rotor design method comprising the following steps: Step S1, establishing a deterministic dynamic model of the seal-rotor; Step S2, setting the optimization parameters, optimization constraints, and objective function of the engine turbopump seal-rotor; Step S3, sampling the dimension and range of the uncertainty parameters to generate a sample library; Step S4, constructing a polynomial surrogate model of the seal-rotor dynamic characteristics; Step S5, determining the boundaries of the seal-rotor dynamic characteristics; Step S6, screening and optimizing the deterministic dynamic model of the seal-rotor to determine the final seal-rotor model result. This invention optimizes the seal-rotor design by combining uncertainty with rotor design, improving the reliability and safety of the rotor, and is simple, efficient, and easy to operate.

The invention relates to the technical field of aero-engines, in particular to an embedded topological layout compact aero-engine combustion chamber and an engine. The combustion chamber is arranged on the downstream of an air inlet diffuser, and an annular concave cavity is defined by the wall face of the back of a diffuser hub, an inner flow channel casing and a shaft system space; the end wall of the head of the flame tube assembly extends in the countercurrent direction and is embedded into the annular concave cavity, and the axial position of the head of the flame tube assembly is located on the upstream of the outlet plane of the diffuser so that an axial structure overlapping section can be formed between the diffuser and the combustion chamber, and the head of the flame tube can be contained in a non-flow-channel space. An outer ring flow channel and an inner ring gas inlet flow channel folded back in a U-shaped or J-shaped mode under nesting constraint are formed in the combustion chamber, a tight coupling impact type evaporation pipe is arranged on the head portion and matched with an outer ring rear oil supply ring pipe and an oil supply structure of a cantilever oil injection rod, and a nozzle is inserted into an inlet of the evaporation pipe in a clearance fit mode to adapt to thermal expansion displacement. According to the scheme, on the premise of ensuring the combustion performance, the axial envelope size of the engine is remarkably reduced, and the thrust-weight ratio and the dynamic characteristics of the rotor are improved.

The invention provides a semi-superconducting electric propulsion system model construction method, and belongs to the technical field of aviation electric propulsion, and the method specifically comprises the steps: building a semi-superconducting electric propulsion system dynamic mathematical sub-model comprising a shared rotor kinetic equation of a semi-superconducting motor and a ducted fan, quantifying the key coupling effect parameters and evaluating the influence of each key coupling effect parameter on the overall performance of the semi-superconducting electric propulsion system by a shared rotor kinetic equation of the semi-superconducting motor and the ducted fan; and a cold source flow controller sub-model is constructed, the cold source flow controller sub-model associates the heat dissipation amount in the dynamic mathematical sub-model with the heat exchange capacity of the heat exchanger in real time, and the cold source flow is dynamically predicted based on the current temperature field distribution and the real-time rotating speed instruction signal of the semi-superconducting motor. And dynamically adjusting the cold source flow according to the predicted cold source flow. According to the processing scheme, accurate modeling support is provided for optimization of the actual temperature control strategy of the semi-superconducting electric propulsion system.

The application discloses a compensation control method of a magnetic bearing based on adaptive inherent frequency, and comprises the following steps: establishing a dynamic equation of an active electromagnetic bearing according to rotor dynamics theory; constructing a compensation current and extracting an unbalance coefficient according to the dynamic equation of the electromagnetic bearing rotor system; after adding the constructed unbalance compensation signal to the dynamic equation of the active electromagnetic bearing, analyzing the stability of the system; and based on the compensation control method of the magnetic bearing, the adaptive inherent frequency is changed to make the constructed compensation signal stabilize the control of the electromagnetic bearing rotor system within the whole rotating speed. According to the characteristics of the adaptive change of the inherent frequency of the magnetic bearing rotor system, the application solves the problem that the compensation algorithm cannot stably converge near the inherent frequency, and widens the working range of the compensation algorithm.

This invention relates to the field of aero-engine technology, and discloses an adjustable dual-blade tip clearance simulation test device and method for rotor elastic line reconstruction and fault identification tests. The invention employs a dual independent drive assembly design. During rotor rotation, the axial displacement of the first and second auxiliary bearings is controlled by the first and second drive assemblies, respectively. The axial movement of the first and second auxiliary bearings is converted into radial extension and retraction of the blades via a connecting rod structure, allowing both adjustable blades to extend or retract simultaneously, achieving synchronous adjustment of the tip clearance of both blades. Alternatively, the tip clearance of a single adjustable blade can be adjusted by extending or retracting it individually. This invention can meet the dynamic adjustment requirements of tip clearance in rotor elastic line reconstruction and fault identification tests, and can support rotor dynamics research in rotating turbomachinery.

This invention belongs to the field of rotating machinery technology, specifically relating to a method for solving the dynamic characteristics of a seal-rotor and seal-rotor bearing system. The method includes: 1. Obtaining four rotor dynamic coefficients at different speeds and whirl frequencies using steady-state or transient computational fluid dynamics methods; 2. Establishing a database of seal rotor dynamic coefficients based on two-dimensional cubic polynomial interpolation; 3. Setting the initial speed for the solution and specifying the initial operating condition; 4. Calculating the instantaneous whirl frequency of the rotor, finding the current seal rotor dynamic coefficients, and calculating the seal excitation force on the rotor; 5. Establishing the dimensionless dynamic model to be solved; 6. Substituting the seal excitation force obtained in step S4 into the dynamic equation established in step S5, performing numerical calculations, and determining whether the numerical solution converges. If not, returning to step S4; 7. Retaining the result when the calculation converges and determining whether the current speed is the upper limit of the desired speed.

The present invention relates to a rotor balancing system (900) for electric vehicle motors, aimed at enhancing operational efficiency and reducing noise, vibration, and harshness (NVH) characteristics. This system (900) utilizes a two-plane balancing technique in accordance with ISO 1940 G2.5 standards to dynamically adjust rotor balance. It comprises a rotor (102, 202, 302, 902) configured for material removal from end plates to correct imbalances, a calculation unit for determining permissible unbalance based on service speed (110), and a balancing unit directed by this calculation. Additionally, a simulation module (910) assesses the impact of unbalance on rotor dynamics, while an analysis module (912) monitors critical speeds and unbalance responses to maintain optimal operation. The system (900) further includes an interface (906) that displays balance status and allows for real-time adjustments, ensuring that the rotor maintains an optimal balance under varying conditions, thereby improving the longevity and performance of electric vehicle motors.

This invention relates to the field of equipment fault diagnosis, specifically providing a method, system, terminal, and medium for centrifugal fan fault diagnosis based on physical constraints. The method includes: collecting fan vibration, temperature, and rotational speed data, as well as shot blasting volume, steel shot velocity, and dust removal pressure difference data; extracting statistical features in the time domain, frequency domain, temperature variation, rotational frequency, and process parameters to construct a fused feature vector; establishing a shot blasting volume-vibration benchmark model using the instrumental variable method, and determining whether the anomaly is caused by a change in shot blasting volume or a fault in the fan itself by comparing the residuals between the actual vibration and the expected vibration; inputting the fused feature vector into a deep neural network, which, during training, uses the theoretical characteristic frequency calculated by the rotor dynamics equation as a constraint to output a fault type probability that conforms to physical laws. This invention achieves physically interpretable identification and causal root cause tracing of fan faults.

The invention relates to a rotor inherent frequency identification method and system, electronic equipment and a readable medium. The method comprises the following steps: acquiring an equivalent diameter and an equivalent elastic modulus of a rotor core when a rotating shaft density is taken as an equivalent density; and rotor inherent frequency identification is carried out on the equivalent diameter and the equivalent elastic modulus based on rotor dynamics calculation software to obtain the rotor inherent frequency, so that the problems that in the prior art, when the rotor inherent frequency of the high-speed permanent magnet direct drive motor is calculated, the contribution of the magnetic steel elastic modulus to the flexural rigidity of the rotor is ignored, so that the calculation result is too conservative, and the calculation accuracy is poor are solved. Therefore, the technical problem is solved, and the accuracy of the calculation of the inherent frequency of the rotor is remarkably improved.