A method and system for adjusting control parameters of a magnetic levitation air supply fan

Abstract

The application discloses a kind of control parameter adjustment method and system of magnetic levitation air supply machine, it is related to high-precision control technical field, including, construct information fusion model, the electromechanical thermal coupling characteristic input information fusion model of acquisition, generate electromechanical thermal characteristic vector;With vector decoupling operator, electromechanical thermal characteristic vector is separated into electromechanical thermal characteristic component, and energy stable scalar value is generated in combination with real-time magnetic levitation air supply machine operation data;Distributed digital gene library is constructed, energy stable scalar value is mapped into discrete working condition label, discrete working condition label and gene fragment in distributed digital gene library are matched, and optimal gene fragment is output;Analysis optimal gene fragment generates control parameter set, and generates multiple parameter change trajectory by smoothing operation function group.The application is by constructing distributed digital gene library, so that control parameter self-adapting adaptation continuous change operating condition and equipment aging Slow time-varying factor, significantly improve system robustness.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of high-precision control, and in particular to a control parameter adjustment method and system of a magnetic levitation air blower. BACKGROUND

[0002] The control technology of the magnetic levitation air blower has developed from the early single-loop PID regulation to a multi-physical field collaborative optimization system. The sensorless control strategy realizes real-time estimation of the rotor position through back electromotive force observation and a sliding mode observer, thereby significantly reducing the dependence on displacement sensors; the adaptive control algorithm combines Lyapunov stability theory to dynamically adjust gain parameters to suppress load mutation disturbances. In recent years, the parameter setting method based on deep learning uses a long short-term memory network to mine historical working condition data, realizes adaptive mapping of control parameters, and improves the robustness of the system under variable working conditions.

[0003] In the current operation of the magnetic levitation air blower, the dynamic decoupling capability of the electromechanical thermal strong coupling effect is insufficient, the strong nonlinear interaction of the electromagnetic field, mechanical vibration and thermal deformation is difficult to effectively separate, which leads to the mismatch between the control parameters and the actual physical state, and further causes the risk of high-frequency oscillation and systematic instability; in addition, the working condition recognition and parameter switching mechanism relies on the coarse-grained division of discrete working condition labels and the matching of a static rule base, and cannot accurately respond to continuous time-varying working conditions, which leads to continuous degradation of control accuracy and significant decline in system robustness. SUMMARY

[0004] In view of the above existing problems, the application is proposed.

[0005] Therefore, the application provides a control parameter adjustment method of a magnetic levitation air blower to solve the problems of control parameter mismatch and working condition switching delay.

[0006] To solve the above technical problems, the application provides the following technical solutions:

[0007] In a first aspect, the present application provides a control parameter adjustment method for a magnetic levitation air supply machine, which comprises: constructing an information fusion model; inputting collected electromechanical thermal coupling characteristics into the information fusion model to generate an electromechanical thermal characteristic vector; separating the electromechanical thermal characteristic vector into electromechanical thermal characteristic components by using a vector decoupling operator, and combining real-time magnetic levitation air supply machine operation data to generate an energy stability scalar value; constructing a distributed digital gene library, mapping the energy stability scalar value to a discrete working condition label, matching the discrete working condition label with gene segments in the distributed digital gene library, and outputting an optimal gene segment; analyzing the optimal gene segment to generate a control parameter set, generating a multi-parameter change trajectory through a smoothing operation function group, and generating a proportional control signal and an integral control signal through a time-space crystal oscillation mechanism for high-frequency carrier modulation; performing phase alignment on the proportional control signal and the integral control signal using a time-sensitive network protocol, achieving phase locking within a preset time window, generating a synchronization signal and loading it to an execution path, wherein the execution path comprises a main path and an auxiliary path; executing the synchronization signal through the main path, calling a historical control parameter set to the auxiliary path for simulation execution, calculating a Lyapunov index difference value and outputting a stability margin value according to the main path execution result and the auxiliary path simulation result;

[0008] When the stability margin value is in a preset safety interval, outputting the synchronization signal to a power drive unit, otherwise outputting the auxiliary path simulation result as a final execution instruction.

[0009] As a preferred scheme of the control parameter adjustment method for the magnetic levitation air supply machine, the energy stability scalar value is generated by the following specific steps,

[0010] The collected mechanical characteristics, electrical characteristics and thermodynamic characteristics are coupled into electromechanical thermal coupling characteristics, and input into the constructed information fusion model to generate an electromechanical thermal characteristic vector;

[0011] The electromechanical thermal characteristic vector is separated into mechanical characteristic components, electrical characteristic components and thermodynamic characteristic components by a vector decoupling operator, and integrated into electromechanical thermal characteristic components;

[0012] The electromechanical thermal characteristic components and the magnetic levitation air supply machine operation data are coupled through multi-field coupling arbitration to generate an energy stability scalar value.

[0013] As a preferred scheme of the control parameter adjustment method for the magnetic levitation air supply machine, the optimal gene segment is output by the following specific steps,

[0014] Each magnetic levitation air supply machine equipment node generates a corresponding gene segment based on historical working condition data and adds an equipment node identifier, receives multiple gene segments, and forms a distributed digital gene library;

[0015] The discrete working condition label is generated by the energy stable scalar value, the feature similarity distance between the discrete working condition label and the gene fragment is calculated, the gene fragment with the minimum feature similarity distance is selected as the optimal gene fragment.

[0016] As a preferred scheme of the control parameter adjustment method of the magnetic suspension blower fan, the proportional control signal and the integral control signal are generated, and the specific steps are as follows,

[0017] The optimal gene fragment is input into a preset parameter mapping table, and a control parameter set is extracted;

[0018] The control parameter set generates a multi-parameter change trajectory through a linear interpolation function and a spline interpolation function;

[0019] The multi-parameter change trajectory and the high-frequency carrier signal are generated by an analog modulation method to generate the proportional control signal and the integral control signal.

[0020] As a preferred scheme of the control parameter adjustment method of the magnetic suspension blower fan, the proportional control signal and the integral control signal are generated, and the specific steps are as follows,

[0021] A uniform time reference of the magnetic suspension blower fan device node is established through a time-sensitive network protocol, and the zero-crossing time difference of the proportional control signal and the integral control signal is calculated as a phase difference;

[0022] Based on the phase difference, the signal transmission delay and the phase response are adjusted to restore the orthogonal relationship of the proportional control signal and the integral control signal;

[0023] The phase difference is continuously monitored within a fixed time window, and when the phase difference continuously exceeds the phase difference locking range, it is determined that the phase locking is completed, and a synchronization signal is generated and loaded to the execution path.

[0024] As a preferred scheme of the control parameter adjustment method of the magnetic suspension blower fan, the proportional control signal and the integral control signal are generated, and the specific steps are as follows,

[0025] The synchronization signal is transmitted to the double-loop cooperative controller through the main path, and the rotor displacement and the coil current are collected as the main path execution result;

[0026] The auxiliary path calls the historical control parameter set and loads it to the virtual double-loop cooperative controller, and outputs the simulated rotor displacement and the simulated coil current as the auxiliary path simulation result under the same discrete working condition label;

[0027] The Lyapunov index of the main path execution result and the auxiliary path simulation result is calculated respectively, and the stable margin value is generated according to the calculation result.

[0028] As a preferred scheme of the control parameter adjustment method of the magnetic levitation air supply fan, the output auxiliary path simulation result is used as the final execution instruction, and the specific steps are as follows,

[0029] The stability margin value is compared with the preset safety interval, if the stability margin value is in the preset safety interval, it is marked as a safe state, otherwise it is marked as a risk state;

[0030] When it is determined that the state is safe, the synchronization signal is transmitted to the power driving unit;When it is determined that the state is risky, the auxiliary path simulation result is reconstructed into the final execution instruction and output to the power driving unit.

[0031] In a second aspect, the present application provides a control parameter adjustment system of a magnetic levitation air supply fan, comprising a feature extraction module, a gene matching module, a trajectory modulation module, a phase synchronization module, a channel verification module and a decision execution module;The feature extraction module is used to construct an information fusion model, input the collected electromechanical thermal coupling characteristics into the information fusion model, and generate an electromechanical thermal characteristic vector;The electromechanical thermal characteristic vector is separated into electromechanical thermal characteristic components by using vector decoupling operator, and combined with real-time magnetic levitation air supply fan operation data to generate energy stability scalar value;The gene matching module is used to construct a distributed digital gene library, map the energy stability scalar value to a discrete working condition label, match the discrete working condition label with the gene fragments in the distributed digital gene library, and output the optimal gene fragment;The trajectory modulation module is used to analyze the optimal gene fragment to generate a control parameter set, generate a multi-parameter change trajectory through a smoothing operation function group, and generate a proportional control signal and an integral control signal through a time-space crystal oscillation mechanism;The phase synchronization module is used to perform phase alignment on the proportional control signal and the integral control signal by using a time-sensitive network protocol, realize phase locking within a preset time window, generate a synchronization signal and load it to an execution path, and the execution path includes a main path and an auxiliary path;The channel verification module is used to execute the synchronization signal through the main path, call the historical control parameter set to the auxiliary path for simulation execution, calculate the Lyapunov index difference value according to the main path execution result and the auxiliary path simulation result, and output the stability margin value;The decision execution module is used to output the synchronization signal to the power driving unit when the stability margin value is in the preset safety interval, otherwise output the auxiliary path simulation result as the final execution instruction.

[0032] In a third aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, wherein the computer program is executed by the processor to realize any step of the control parameter adjustment method of the magnetic levitation air supply fan according to the first aspect of the present application.

[0033] In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements any step of the method for adjusting control parameters of a magnetic levitation air supply fan according to the first aspect of the present application.

[0034] The present application has the following advantages: by constructing a distributed digital gene library, the energy stable scalar value is dynamically mapped to a discrete working condition label, the control parameters are self-adaptively adapted to the continuous change of the running working condition and the slow time-varying factors such as equipment aging, and the system robustness is significantly improved; by the main and auxiliary path collaborative verification and risk decision mechanism, the real-time prediction of instability risk is realized in combination with the preset safety interval, and the auxiliary path simulation result is reconstructed into continuous instruction output in the risk state, and the transient overshoot and secondary oscillation in the working condition switching process are completely eliminated. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0036] Fig. 1 The flowchart of the method for adjusting control parameters of a magnetic levitation air supply fan.

[0037] Fig. 2 The schematic diagram of the control parameter adjustment system of the magnetic levitation air supply fan.

[0038] Fig. 3 The flowchart of generating a control signal.

[0039] Fig. 4 The flowchart of executing a path and final instruction verification. DETAILED DESCRIPTION

[0040] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification.

[0041] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the concept of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0042] Second, the "one embodiment" or "an embodiment" referred to herein means a specific feature, structure, characteristic, or combination of features and / or characteristics described herein that can be included in at least one implementation of the present application. The various appearances of "in one embodiment" or "an embodiment" are not necessarily all referring to the same embodiment, although they can. Rather, they are each referring to a particular feature or characteristic or combination of features and / or characteristics that are included in at least one implementation of the present application.

[0043] Referring to Figs. 1-4 For one embodiment of the present application, the embodiment provides a control parameter adjustment method of a magnetic levitation blower, comprising the following steps:

[0044] S1, constructing an information fusion model, inputting the collected electromechanical thermal coupling characteristic information into the information fusion model to generate an electromechanical thermal characteristic vector; using a vector decoupling operator to separate the electromechanical thermal characteristic vector into electromechanical thermal characteristic components, and combining real-time magnetic levitation blower operation data to generate an energy stability scalar value;

[0045] S1.1, defining a feature alignment layer based on an industrial real-time synchronization standard, defining an associated calculation layer based on a device coupling matrix, defining an output layer based on the law of conservation of energy, and constructing an information fusion model according to the feature alignment layer, the associated calculation layer and the output layer;

[0046] It should be noted that when defining the feature alignment layer, a clock alignment framework is constructed according to the precise time synchronization protocol, the standard unit conversion rules of mechanical vibration, current and temperature are defined through a unified dimension system to form a space-time normalized constraint structure; the constraint structure is output to the associated calculation layer definition link, based on the electromechanical thermal interaction coefficient matrix of the device standard document, the bearing displacement, current harmonic and temperature monitoring three blocks are divided according to the principle of multi-physical field coupling, and a fusion calculation rule framework is generated; the fusion calculation rule framework is transmitted to the output layer definition link, and according to the law of conservation of energy, the anisotropic weight of the bearing, the harmonic suppression coefficient and the heat conduction compensation coefficient and other physical constraint parameters are solidified to form an output structure with physical interpretation; the constraint structure, the fusion calculation rule framework and the output structure with physical interpretation are interconnected through a standardized interface: the output interface of the feature alignment layer is directly connected to the input interface of the associated calculation layer, the output interface of the associated calculation layer is directly connected to the input interface of the output layer, and the construction of the information fusion model is completed;

[0047] The equipment standard document is a set of specifications formed by the manufacturer of the magnetic levitation blower during the research and development stage, which contains the equipment node identification of the magnetic levitation blower, and the equipment node identification adopts a three-part coding structure (type code 3 bits, production line number 2 bits, and serial number 6 bits). The first three bits of the type code directly define the equipment type, which is divided into high-speed and energy-saving types. The mechanical assembly drawing marks the spatial coordinates and tolerance cooperation of the bearing, stator and rotor. The electrical winding topology diagram specifies the coil turn number and permanent magnet arrangement parameters. The thermodynamic simulation report specifies the heat conduction path of the cooling fin, as well as the core parameter set of the mechanical transmission efficiency coefficient table, electromagnetic coupling strength coefficient table and heat conduction compensation coefficient table determined by the engineering calculation book.

[0048] The multi-physics coupling principle describes the physical mechanism of the interaction between the mechanical vibration field, electromagnetic field and temperature field during the operation of the magnetic levitation blower. Specifically, the bearing displacement change affects the stator winding current distribution through the Lorentz force, the winding current joule heat effect changes the temperature gradient of the cooling fin, and the temperature rise of the cooling fin reacts on the bearing gap through material thermal expansion, forming a closed-loop energy transfer chain of displacement-current-temperature. The quantification of the multi-physics coupling principle relies on the simultaneous solution of Newton's second law of mechanical dynamics, Maxwell's equations of electromagnetic field and Fourier's law of heat conduction.

[0049] The information fusion model does not have a traditional training process in industrial implementation and is completely based on pre-solidification of physical laws and design specifications of the magnetic levitation blower: the clock synchronization parameters of the feature alignment layer are directly determined by the precise time protocol microsecond-level alignment requirement, and the standard unit conversion rules are defined according to the unified dimension system; the coupling matrix coefficients of the association calculation layer are derived from the mechanical transmission efficiency, electromagnetic coupling strength and heat conduction compensation coefficient table in the equipment standard document, which are recorded to the read-only memory after quantification by the engineering calculation book; the energy conservation law of the output layer is calculated and generated based on the first law of thermodynamics, the mechanical momentum conservation and the electromagnetic field energy theorem according to the measured data of the bearing three-axis kinetic energy distribution, the specific harmonic frequency eddy current loss proportion and the heat dissipation gradient efficiency verification results of the manufacturer, and finally it is written into the solidification to form a permanent framework through the production line calibration equipment once, all parameters cannot be modified in the life cycle of the equipment, and there is no gradient descent, back propagation or iterative optimization link throughout the process.

[0050] S1.2, collect mechanical features, electrical features and thermodynamic features, and couple them into electromechanical thermal coupling features, input the electromechanical thermal coupling features into the information fusion model, and generate electromechanical thermal feature vectors through time synchronization and cross-domain fusion;

[0051] It should be noted that the bearing six-degree-of-freedom displacement signals are acquired by the eddy current displacement sensor when collecting mechanical characteristics, and are converted into 0-10V voltage analog quantity by a signal conditioning circuit, and are quantitatively stored as mechanical vibration digital sequences with a sampling rate of 1 kHz; the three-phase winding current waveforms are captured by a Hall current sensor when collecting electrical characteristics, and are quantitatively stored as current digital sequences with a sampling rate of 50 kHz after anti-aliasing filter processing; the temperatures of 14 monitoring points are acquired by a PT100 platinum resistance temperature sensor when collecting thermodynamic characteristics, and are quantitatively stored as temperature digital sequences with a sampling rate of 10 Hz after linearization by an RTD transmitter; the mechanical vibration digital sequences, the current digital sequences and the temperature digital sequences are aligned according to the collection time stamp, and are coupled into electromechanical-thermal coupling characteristics;

[0052] The electromechanical-thermal coupling characteristics are input into the feature alignment layer of the information fusion model, are unified to a microsecond time reference according to the precise time synchronization protocol, are converted into corresponding standard dimensions according to standard unit conversion rules, and three-way signals synchronized in time and normalized in dimension are output; after the three-way signals are input into the correlation calculation layer, a 32x32 fixed coupling matrix is called to perform matrix multiplication operation, and a 32-dimensional initial fusion vector is generated; the 32-dimensional initial fusion vector is transmitted to the output layer, physical constraint parameters are loaded according to the law of conservation of energy, and the physical constraint parameters are injected into the 32-dimensional initial fusion vector through element-by-element multiplication operation, and a 32-dimensional electromechanical-thermal characteristic vector is output, and the expression is,

[0053] F=H⊙W·T(g(X));

[0054] Wherein, F represents the 32-dimensional electromechanical-thermal characteristic vector; H represents the physical constraint parameter; W represents the fixed coupling matrix; T(·) represents the time synchronization function; g(·) represents the dimension normalization function; X represents the electromechanical-thermal coupling characteristics.

[0055] S1.3, separate the electromechanical-thermal characteristic vector into mechanical characteristic component, electrical characteristic component and thermodynamic characteristic component by diagonal matrix type vector decoupling operator, and integrate into electromechanical-thermal characteristic component;

[0056] It should be noted that the 32-dimensional electromechanical-thermal characteristic vector is input into the diagonal matrix type vector decoupling operator, the diagonal matrix type vector decoupling operator is a 32x32-dimensional diagonal matrix, and the mechanical characteristic component (1-6-dimensional elements constitute a 6-dimensional displacement vector), the electrical characteristic component (7-18-dimensional elements constitute a 12-dimensional harmonic amplitude vector), and the thermodynamic characteristic component (19-32-dimensional elements constitute a 14-dimensional temperature vector) are separated out by matrix multiplication operation; the separated mechanical characteristic component, electrical characteristic component and thermodynamic characteristic component are integrated into structured electromechanical-thermal characteristic component according to the device node identification.

[0057] S1.4, the electromechanical thermal characteristic component and the magnetic suspension air supply fan operation data are coupled through the multi-field coupling arbitration to generate an energy stability scalar value.

[0058] It should be noted that the electromechanical thermal characteristic component and the real-time operation data (output air pressure and power factor) of the magnetic suspension air supply fan are input into the multi-field coupling arbitration mechanism, the basic weight value of each physical quantity in the electromechanical thermal characteristic component is extracted according to the weight distribution rule, the mechanical energy stability factor, the electric energy quality factor and the thermal balance factor are calculated through the weighted aggregation formula; the working condition compensation coefficient is calculated by combining the power factor and the output air pressure; the mechanical energy stability factor, the electric energy quality factor, the thermal balance factor and the working condition compensation coefficient are substituted into the energy conservation arbitration equation to generate an energy stability scalar value, the expression is,

[0059]

[0060] Wherein, S represents the energy stability scalar value; M represents the mechanical energy stability factor; E represents the electric energy quality factor; O represents the thermal balance factor; κ represents the working condition compensation coefficient; ∈ represents the anti-zero constant, the fixed value is 10-6; η represents the dimensionless normalization coefficient, which is calculated from the rated working condition reference value;

[0061] It should also be noted that the weight distribution rule refers to distributing the weight according to the three-axis (xyz) kinetic energy proportion for the bearing six-degree-of-freedom displacement, defining the suppression coefficient according to the eddy current loss proportion for the specific harmonic current, and giving the compensation factor according to the heat conduction efficiency demand for the temperature monitoring point.

[0062] S2, construct a distributed digital gene library, map the energy stability scalar value to a discrete working condition label, match the discrete working condition label with the gene fragments in the distributed digital gene library, and output the optimal gene fragment;

[0063] S2.1, each magnetic suspension air supply fan equipment node generates a corresponding gene fragment based on historical working condition data, and adds an equipment node identifier, and the central server receives multiple gene fragments to form a distributed digital gene library;

[0064] It should be noted that each magnetic levitation fan equipment node extracts the historical working condition data (including bearing vibration spectrum, three-phase current waveform and temperature distribution curve) of nearly 30 days in the local storage unit, and compresses the historical working condition data of every 10 minutes into a 128-dimensional feature vector as the basic data of the gene segment through a feature dimension reduction algorithm; an equipment node identifier is attached to each gene segment, and the gene segment is packaged as a structured gene segment; each magnetic levitation fan equipment node uploads the structured gene segment to the central server through the industrial Ethernet, and the central server receives all the structured gene segments uploaded by the magnetic levitation fan equipment nodes, analyzes the equipment node identifier, distinguishes the equipment type according to the type code in the equipment node identifier, stores the gene segment according to the equipment type grouping, and at the same time establishes an equipment node identifier-gene segment index table, forming a distributed digital gene library.

[0065] S2.2, the energy stability scalar value is generated into a discrete working condition label through discretization coding, the feature similarity distance between the discrete working condition label and the gene segment is calculated in the distributed digital gene library, and the gene segment with the smallest feature similarity distance is selected as the optimal gene segment.

[0066] It should be noted that the working condition grade threshold is defined based on the physical boundary and energy efficiency comprehensive analysis method: the mechanical load is gradually increased through the magnetic suspension bearing overload test until the vibration sensor triggers the safety alarm, the alarm critical point energy stability scalar value is recorded, and the upper limit of the unstable working condition σ is calculated by superimposing the three times standard deviation safety margin; the fan energy efficiency inflection point test is performed, the energy stability scalar value position corresponding to the best efficiency load rate is identified, and the stable working condition lower limit is determined by deducting the measurement instrument calibration error The hardness values of 30 bearing alloy samples are calculated by performing Rockwell hardness test on the same batch of bearing alloy samples, and the scalar compensation amount is converted according to the hardness-life attenuation correlation formula; the critical energy stability scalar value of the bearing alloy material fatigue life test caused by temperature rise leading to 50% life attenuation is recorded, and the scalar compensation amount is superimposed to obtain the lower limit of the transition working condition after calibration; the scalar value interval of the unstable working condition upper limit, the transition working condition lower limit and the stable working condition lower limit is formed to form the working condition grade threshold, 0.0-σ is the unstable working condition, and the discrete working condition label is 000; For the transition working condition, the discrete working condition label is 001; For the stable working condition, the discrete working condition label is 010;

[0067] The energy stable scalar value is input into a discretization encoder, and a 3-bit discrete working condition label is generated according to a working condition level threshold; a gene segment corresponding to a target device type (such as a high-speed device search partition A) is loaded in a distributed digital gene library, and a 128-dimensional feature vector of each gene segment is directly extracted; a feature similarity distance between the discrete working condition label and the 128-dimensional feature vector of each gene segment is calculated, a gene segment storage address corresponding to a minimum feature similarity distance is selected by using a minimum value selector, and the output is an optimal gene segment.

[0068] S3, the optimal gene segment is parsed to generate a control parameter set, a multi-parameter variation trajectory is generated through a smoothing operation function group, and a proportional control signal and an integral control signal are generated through a time-space crystal oscillation mechanism;

[0069] S3.1, the optimal gene segment is input into a parameter mapping table, and a displacement control loop parameter set and a current control loop parameter set are extracted;

[0070] It should be noted that the bearing displacement original waveform and the stator winding current instantaneous value of the magnetic levitation air supply fan under the test conditions of rated load and overload are collected; the displacement amplitude mean value is obtained by performing time-frequency conversion on the bearing displacement original waveform to form the displacement frequency domain characteristic value; the fundamental wave is extracted by performing harmonic decomposition on the stator winding current instantaneous value to form the current harmonic characteristic value; the displacement frequency domain characteristic value and the current harmonic characteristic value are combined to generate a displacement control loop parameter set and a current control loop parameter set through multi-physical field coupling simulation; the displacement frequency domain characteristic value is input into a mechanical vibration field simulation unit, the stiffness matrix and the damping coefficient of the rotor are calculated based on the bearing dynamics equation, and the displacement control loop parameter set is output; the current harmonic characteristic value is input into an electromagnetic field simulation unit, a control equation is established according to the Maxwell equation set combined with the stator winding, the spatial electromagnetic field distribution is solved by the finite element method, the eddy current loss density is calculated and the eddy current loss distribution is output, and the current control loop parameter set is generated; the characteristic vector index address is established, and the displacement control loop parameter set, the current control loop parameter set and the characteristic vector index address are solidified into a parameter mapping table;

[0071] The optimal gene segment is input into a parameter mapping table, the characteristic vector index address is matched through a type code, and the displacement control loop parameter set and the current control loop parameter set are extracted according to the characteristic vector index address.

[0072] S3.2, the displacement control loop parameter set and the current control loop parameter set generate a multi-parameter variation trajectory through a linear interpolation function and a spline interpolation function;

[0073] It should be pointed out that the displacement control loop parameters are processed by a linear interpolation function, taking 1 ms control period as the time reference, linearly transitioning the displacement control loop parameters of adjacent control periods to generate a continuous displacement parameter trajectory; the current control loop parameters are processed by a cubic spline interpolation function, a harmonic order sequence is defined according to the electromagnetic characteristics of the motor, and the harmonic order sequence is used as a node vector to insert B-spline control points between adjacent harmonic orders to generate a smooth current parameter trajectory; the continuous displacement parameter trajectory and the smooth current parameter trajectory are aligned according to the precision time protocol and merged into a multi-parameter change trajectory.

[0074] S3.3, activate the spatiotemporal crystal oscillation mechanism to generate a high-frequency carrier signal with a fixed frequency, and generate proportional control signals and integral control signals by analog modulation method.

[0075] It should be pointed out that the spatiotemporal crystal oscillation mechanism is activated to generate a high-frequency carrier signal (center frequency 2MHz, stability ±1ppm) through a phase-locked loop circuit; the product of the continuous displacement parameter trajectory in the multi-parameter change trajectory and the high-frequency carrier signal generates a proportional control signal (0-10V sine wave); the smooth current parameter trajectory is input into the integral modulation circuit to perform time-varying integral operation on the high-frequency carrier to generate an integral control signal (-5V~+5V triangle wave); the high-frequency component of the carrier is filtered out by a low-pass filter to output smooth proportional control signals and integral control signals.

[0076] S4, adopt time-sensitive network protocol to perform phase alignment on proportional control signals and integral control signals, realize phase locking within a preset time window, generate a synchronization signal and load it to an execution path, which includes a main path and an auxiliary path;

[0077] S4.1, establish a unified time reference for magnetic levitation air supply equipment nodes through a time-sensitive network protocol, calculate the time difference of the zero-crossing points of the proportional control signal and the integral control signal as the phase difference;

[0078] It should be pointed out that the time-sensitive network protocol is deployed in each magnetic levitation air supply equipment node, and a nanosecond-level clock distribution mechanism is used to establish a unified time reference for all equipment nodes; the proportional control signal and the integral control signal are input into a high-speed voltage comparison circuit, and when the proportional control signal crosses the amplitude midpoint threshold (5.0V), the current timestamp is recorded, and when the integral control signal crosses the phase reference threshold (0.0V), the current timestamp is recorded; the phase difference is generated by calculating the absolute value of the time difference between the two time stamps;

[0079] It should be noted that the time-sensitive network protocol refers to a communication framework for achieving microsecond-level time synchronization in industrial control networks. The core is to generate a nanosecond-level time reference signal through a precise clock source, eliminate transmission path differences using a point-to-point delay compensation mechanism, and reduce the clock deviation of all network devices based on master-slave clock calibration algorithms.

[0080] The proportional control signal is a single-polarity sine wave. When the proportional control signal rises from below 5V to above 5V, it indicates that the sine wave has entered the positive half cycle from the negative half cycle. The midpoint of the amplitude of the proportional control signal (the midpoint of the 0-10V range, 5.0V) is the amplitude midpoint threshold. The integral control signal is a bipolar triangular wave, and the true zero-crossing point is at the voltage zero point. When the integral control signal crosses the voltage zero point from a negative value, it indicates that the triangular wave has entered the rising edge from the falling edge. The voltage zero point is the phase reference threshold.

[0081] S4.2, based on the phase difference, dynamically adjusting the signal transmission delay and the phase response, restoring the orthogonal relationship of the proportional control signal and the integral control signal;

[0082] It should be noted that the phase difference is input into the proportional-integral controller, and the output of the proportional-integral controller is divided into two paths: one path inputs the phase difference into a 12-bit digital-to-analog converter, converting it into a 0-3.3V analog voltage signal. The analog voltage signal drives a capacitor array composed of 64 binary weighted capacitors. Each weighted capacitor is controlled by a CMOS switch to access the analog voltage signal transmission path. When the voltage rises, the number of switches turned on increases, causing the total access capacitance value to increase linearly, according to the transmission delay formula, the propagation time of the proportional control signal in the transmission line is extended. The adjusted proportional control signal is buffered and isolated by two stages of emitter followers and then output, generating a delay-compensated proportional control signal.

[0083] The other path loads the correction voltage output by the proportional-integral controller onto the cathodes of four parallel varactor diodes, controlling the total junction capacitance through reverse bias variation. The four varactor diodes are connected in series and inserted into the physical transmission path of the integral control signal, forming an LC phase-shifting structure with a fixed inductance (determined based on the resonance frequency inequality, with a value of 22μH). According to the phase offset formula, the phase of the integral control signal is changed in real time, and the integral control signal with an accurately offset phase is output.

[0084] The delay-compensated proportional control signal and the integral control signal with an accurately offset phase are input into an analog multiplier to perform instantaneous multiplication and generate an alternating current signal containing sum frequency components and difference frequency components. The alternating current signal is connected to a four-order RC low-pass filter, and the direct current voltage is extracted through integration operation, with the expression being,

[0085]

[0086] V1(t) = δ v1 + δv1 • sin(2π·10 4 t) ;

[0087] V2(t) = δ v2 • sawtooth(2π·10 4 t)

[0088] wherein V0 represents a direct current voltage; Q represents a signal period, taking a value of 0.1 ms; t represents a certain time; V1(t) represents an instantaneous voltage of the proportional control signal at a certain time t; V2(t) represents an instantaneous voltage of the integral control signal at a certain time t; δ v1 represents a proportional control signal amplitude constant, taking a value of 5; δ v2 represents an integral control signal amplitude peak value, taking a value of 5; sawtooth(·) represents an asymmetric sawtooth wave function, used for accurate control of the phase shift of the integral signal;

[0089] The direct current voltage is calculated by the inverse cosine function to generate a phase difference Δθ, and the expression is,

[0090]

[0091] wherein Δθ represents a phase difference;

[0092] When the phase difference Δθ is within the phase difference locking range (90°±0.1°, defined based on the hardware detection limit and stability boundary), the analog voltage signal and the correction voltage are locked, and the orthogonal relationship reconstruction of the proportional control signal and the integral control signal is completed.

[0093] S4.3, continuously monitor the phase difference between the proportional control signal and the integral control signal within a fixed time window, and when the phase difference continuously does not exceed the phase difference locking range, determine that the phase locking is completed, generate a synchronization signal and load it to the execution path.

[0094] It should be noted that the phase difference Δθ is input into the window comparator and compared with the phase difference locking range; when Δθ continuously stays within the phase difference locking range, a 200 ms timing counter is started, and the cumulative counter is triggered once every signal period (0.1 ms); if Δθ does not exceed the limit within 2000 consecutive periods (corresponding to 200 ms), the phase locking is completed; the count value of the cumulative counter reaches 2000 to trigger an overflow interrupt, generate an interrupt signal, the interrupt signal drives the output end of the D flip-flop to jump from low to high, generates a rising edge synchronization signal and loads it to the main path of the execution path.

[0095] S5, execute the synchronization signal through the main path, call the historical control parameter set to the auxiliary path for simulation execution, calculate the Lyapunov index difference value and output the stability margin value according to the main path execution result and the auxiliary path simulation result;

[0096] S5.1, transmitting the synchronization signal to the magnetic bearing position loop controller and the motor drive current loop controller through the main path, collecting the rotor displacement and the coil current as the main path execution result;

[0097] It should be noted that the serial peripheral interface data line of the synchronization signal is transmitted to the magnetic bearing position loop controller and the controller area network bus transceiver of the motor drive current loop controller; the rising edge of the synchronization signal triggers the magnetic bearing position loop controller to execute the position loop activation instruction, and simultaneously sends the pulse width modulation enable instruction to the motor drive current loop controller; the rotor displacement is collected in real time by the magnetic bearing eddy current displacement sensor, converted into a digital displacement signal by an analog-to-digital converter, and the coil current is collected by a motor phase current shunt resistor and a signal conditioning circuit, converted into a digital current signal by a high-precision analog-to-digital converter; the rotor displacement and the coil current are aligned by the time synchronization protocol.

[0098] S5.2, calling the historical displacement control loop parameter set and the historical current control loop parameter set to the auxiliary path, and loading them to the virtual position loop controller and the virtual current loop controller to build a virtual execution environment;

[0099] It should be noted that the historical displacement control loop parameter set (including proportional coefficient, integral time and differential gain parameter) and the historical current control loop parameter set (including proportional coefficient, integral time and feedforward gain parameter) stored in the distributed digital gene library are transmitted to the auxiliary path memory buffer through the high-speed serial bus; the historical displacement control loop parameter set is loaded to the virtual position loop controller, and the historical current control loop parameter set is loaded to the virtual current loop controller;

[0100] The virtual position loop controller instantiates three independent operation units of proportional operation multiplier, integral accumulator and differential differentiator in the programmable logic device, writes the proportional coefficient of the historical displacement control loop parameter set to the coefficient register of the proportional operation multiplier, writes the integral time to the clock division register of the integral accumulator, and writes the differential gain parameter to the gain register of the differential differentiator; the virtual current loop controller instantiates proportional integral operation core and feedforward compensator, loads the proportional coefficient and the integral time of the historical current control loop parameter set to the coefficient register group of the proportional integral operation core, and writes the feedforward gain parameter to the amplification coefficient register of the feedforward compensator; the proportional operation multiplier, the integral accumulator and the differential differentiator are interconnected through a parallel data bus to form a proportional integral differential operation unit; the proportional integral operation core and the feedforward compensator are interconnected through an adder to form a proportional integral feedforward operation unit; finally, cross-clock domain synchronization logic is configured to connect the proportional integral differential operation unit and the proportional integral feedforward operation unit to form a virtual execution environment;

[0101] It should be noted that the relational database continuously collects historical working condition data (including bearing vibration spectrum, three-phase current waveform and temperature distribution curve) through the magnetic levitation blower equipment node, generates data snapshots every 10 minutes, compresses them into 128-dimensional feature vectors through feature dimension reduction algorithm, adds equipment node identifier (three-section code: type code 3 bits + production line number 2 bits + serial number 6 bits) to form a structured gene fragment, uploads it to the central server through industrial Ethernet (EtherCAT, 100 Mbps), stores it according to equipment type (such as high-speed type HS1 and energy-saving type ES2 partition), and establishes an index table with equipment node identifier and time stamp as the primary key

[0102] S5.3, under the same discrete working condition label condition, the virtual position loop controller and the virtual current loop controller are synchronously operated, and analog rotor displacement and analog coil current are output as auxiliary path simulation results.

[0103] It should be noted that the discrete working condition label is input into the working condition parser to retrieve the historical rotor displacement reference trajectory and the historical coil current reference instruction corresponding to the discrete working condition label; the virtual position loop controller receives the historical displacement reference trajectory as input, performs proportional integral differential operation according to the loaded historical displacement control loop parameter set, and generates analog rotor displacement; the virtual current loop controller synchronously receives the historical coil current reference instruction, performs proportional integral feedforward operation based on the historical current control loop parameter set, and outputs analog coil current; the operation processes of the virtual position loop controller and the virtual current loop controller are triggered by a global clock synchronization signal every microsecond to perform control cycle update; after the analog rotor displacement and the analog coil current are encapsulated, the discrete working condition label and the time stamp are added, and stored in the auxiliary path result buffer, the auxiliary path simulation result output is completed.

[0104] S5.4, respectively calculate the Lyapunov index of the main path execution result and the auxiliary path simulation result, and generate a stability margin value according to the calculation result.

[0105] It should be noted that the rotor displacement collected by the main path and the coil current are matched to the same time reference through time stamp alignment, while the analog rotor displacement and analog coil current output by the auxiliary path are extracted; the rotor displacement and the analog rotor displacement are respectively reconstructed in the phase space, the rotor displacement and the analog rotor displacement are respectively mapped to the high-dimensional phase space, the maximum Lyapunov exponent of the rotor displacement and the analog rotor displacement is respectively calculated by the small data method, and the displacement difference is obtained; the coil current and the analog coil current are respectively reconstructed in the phase space, the coil current and the analog coil current are respectively mapped to the high-dimensional phase space, the maximum Lyapunov exponent of the coil current and the analog coil current is respectively calculated, and the current difference is obtained; the displacement difference and the current difference respectively generate the displacement stability margin value and the current stability margin value through the negative value operation; the arithmetic mean of the displacement stability margin value and the current stability margin value is obtained to generate the stability margin value, and the expression of the maximum Lyapunov exponent is,

[0106]

[0107] Wherein, λ represents the maximum Lyapunov exponent; t0 represents the initial time of phase space reconstruction; t1 represents the termination time of phase space reconstruction; N represents the total number of trajectory points in the phase space; k represents the trajectory point index in the phase space, and the value is 1-N; t k represents the time t corresponding to the kth trajectory point; L(t k ) represents the trajectory distance at time t; L(t k-1 ) represents the trajectory distance at time t corresponding to the k-1th trajectory point.

[0108] S6, when the stability margin value is in the preset safety interval, output the synchronization signal to the power driving unit, otherwise output the auxiliary path simulation result as the final execution instruction.

[0109] S6.1, compare the stability margin value with the preset safety interval, if the stability margin value is in the preset safety interval, mark as a safe state, otherwise mark as a risk state;

[0110] It should be noted that the lower threshold of the safety interval is defined as 0.5s -1 according to the A-level phase margin requirement in the magnetic bearing industry mandatory stability standard; -1 ;

[0111] When the stability margin value is ≥0.5s -1 and ≤10s -1 , the safety state code "1" (safe state) is attached to the stability margin value in the state register; if the margin value is <0.5s -1 or >10s-1 If the state code in the state register is "0" (risk state), the risk state code "0" (risk state) is added to the stability margin value in the state register.

[0112] S6.2, when the safety state is determined, the synchronization signal is transmitted to the power driving unit; when the risk state is determined, the auxiliary path simulation result is reconstructed into the final execution instruction and output to the power driving unit.

[0113] It should be noted that when the state code in the state register is "1" (safe state), the synchronization signal is read and transmitted to the instruction register of the power driving unit through the SPI interface, triggering the power amplifier to unlock the output; when the state code in the state register is "0" (risk state), the simulated rotor displacement and simulated coil current are extracted from the auxiliary path result buffer, reconstructed into a continuous time sequence through cubic spline interpolation, and input into the proportional integral feedforward operation unit of the virtual current loop controller to generate a virtual control quantity. Then, the three-phase driving instruction is converted through inverse Clarke transformation and sent to the instruction register of the power driving unit through the CAN bus; finally, the power driving unit executes the corresponding operation according to the received instruction type to complete the control in the safe or risk state.

[0114] The embodiment also provides a control parameter adjustment system of a magnetic levitation blower, comprising: a feature extraction module, a gene matching module, a trajectory modulation module, a phase synchronization module, a channel verification module, and a decision execution module;

[0115] The feature extraction module is configured to construct an information fusion model, input the collected electromechanical-thermal coupling features into the information fusion model, generate an electromechanical-thermal feature vector, separate the electromechanical-thermal feature vector into electromechanical-thermal feature components by using a vector decoupling operator, and generate an energy stability scalar value in combination with real-time magnetic levitation blower operation data.

[0116] The gene matching module is configured to construct a distributed digital gene library, map the energy stability scalar value to a discrete working condition label, match the discrete working condition label with a gene segment in the distributed digital gene library, and output an optimal gene segment.

[0117] The trajectory modulation module is configured to analyze the optimal gene segment to generate a control parameter set, generate a multi-parameter change trajectory by using a smoothing operation function group, and generate a proportional control signal and an integral control signal by using a time-space crystal oscillation mechanism for high-frequency carrier modulation.

[0118] The phase synchronization module is configured to perform phase alignment on the proportional control signal and the integral control signal by using a time-sensitive network protocol, realize phase locking within a preset time window, generate a synchronization signal, and load the synchronization signal to an execution path, wherein the execution path comprises a main path and an auxiliary path.

[0119] The channel verification module is configured to execute the synchronization signal through the main path, call a historical control parameter set to the auxiliary path for simulation execution, calculate a Lyapunov index difference value and output a stability margin value according to a main path execution result and an auxiliary path simulation result.

[0120] The decision execution module is configured to output the synchronization signal to the power driving unit when the stability margin value is in a preset safety interval, and output the auxiliary path simulation result as a final execution instruction otherwise.

[0121] The embodiment further provides a computer device suitable for the control parameter adjustment method of the magnetic levitation air supply fan, which comprises a memory and a processor.

[0122] The computer device can be a terminal, and the computer device comprises a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0123] The embodiment also provides a storage medium on which a computer program is stored, the program being executed by a processor to implement the control parameter adjustment method for realizing the magnetic suspension air supply fan proposed in the above embodiment; the storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

[0124] To sum up, the application realizes the dynamic mapping of the energy stable scalar value to the discrete working condition label by constructing a distributed digital gene library, so that the control parameters are self-adaptively adapted to the slow time-varying factors such as continuous change of the running working condition and device aging, and the system robustness is significantly improved; the instability risk is real-time predicted by the main and auxiliary path collaborative verification and risk decision mechanism in combination with the preset safety interval, and the auxiliary path simulation result is reconstructed to a continuous instruction output in the risk state, so that the transient overshoot and secondary oscillation in the working condition switching process are completely eliminated.

[0125] It should be noted that the above embodiments are only used to illustrate the technical solutions of the application but not limit the application. Although the application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the application can be modified or replaced equivalently without departing from the spirit and scope of the application, and all of them should be covered in the scope of the claims of the application.

Claims

1. A method of adjusting control parameters of a magnetic levitation blower, characterized by: comprising, constructing an information fusion model, inputting the collected electromechanical thermal coupling characteristic information into the information fusion model to generate an electromechanical thermal characteristic vector; separating the electromechanical thermal characteristic vector into electromechanical thermal characteristic components by using a vector decoupling operator, and combining real-time magnetic levitation fan operation data to generate an energy stability scalar value; constructing a distributed digital gene library, mapping the energy stability scalar value to a discrete working condition label, matching the discrete working condition label with a gene segment in the distributed digital gene library, and outputting an optimal gene segment; analyzing the optimal gene segment to generate a control parameter set, generating a multi-parameter change trajectory through a smoothing operation function group, and generating a proportional control signal and an integral control signal through a time-space crystal oscillation mechanism for high-frequency carrier modulation; performing phase alignment on the proportional control signal and the integral control signal using a time-sensitive network protocol, achieving phase locking within a preset time window, generating a synchronization signal, and loading the synchronization signal to an execution path, the execution path including a main path and an auxiliary path; executing the synchronization signal through the main path, calling a historical control parameter set to the auxiliary path for simulation execution, calculating a Lyapunov index difference value based on the main path execution result and the auxiliary path simulation result, and outputting a stability margin value; when the stability margin value is within a preset safety interval, outputting the synchronization signal to a power drive unit, otherwise outputting the auxiliary path simulation result as a final execution instruction.

2. The method of claim 1, wherein: The specific steps of generating the energy stability scalar value are as follows, coupling the collected mechanical characteristics, electrical characteristics, and thermodynamic characteristics into electromechanical thermal coupling characteristics, and inputting them into the constructed information fusion model to generate an electromechanical thermal characteristic vector; separating the electromechanical thermal characteristic vector into mechanical characteristic components, electrical characteristic components, and thermodynamic characteristic components by using a vector decoupling operator, and integrating them into electromechanical thermal characteristic components; generating an energy stability scalar value by multi-field coupling arbitration of the electromechanical thermal characteristic components and the magnetic levitation fan operation data.

3. The method of claim 2, wherein: The specific steps of outputting the optimal gene segment are as follows, each magnetic levitation fan equipment node generates a corresponding gene segment based on historical working condition data and appends an equipment node identifier, receives multiple gene segments, and forms a distributed digital gene library; generate a discrete working condition label from the energy stability scalar value, calculate the feature similarity distance between the discrete working condition label and the gene segment, and select the gene segment with the smallest feature similarity distance as the optimal gene segment.

4. The method of claim 3, wherein: The specific steps of generating the proportional control signal and the integral control signal are as follows, inputting the optimal gene segment into a preset parameter mapping table to extract a control parameter set; generating a multi-parameter change trajectory through a linear interpolation function and a spline interpolation function; activating the time-space crystal oscillation mechanism to generate a high-frequency carrier signal with a fixed frequency, and generating a proportional control signal and an integral control signal through analog modulation of the multi-parameter change trajectory and the high-frequency carrier signal.

5. The method of claim 4, wherein: The specific steps of generating the synchronization signal and loading it to the execution path are as follows, establishing a unified time reference for the magnetic levitation fan equipment nodes through a time-sensitive network protocol, calculating the zero-crossing time difference between the proportional control signal and the integral control signal as a phase difference; Based on the phase difference, the signal transmission delay and the phase response are adjusted to restore the orthogonal relationship between the proportional control signal and the integral control signal; The phase difference is continuously monitored within a fixed time window. When the phase difference continuously fails to exceed the phase difference locking range, it is determined that the phase locking is completed, a synchronization signal is generated and loaded to the execution path.

6. The method of claim 5, wherein: The output stability margin value is outputted, and the specific steps are as follows, The synchronization signal is transmitted to the dual-loop cooperative controller through the main path, and the rotor displacement and coil current are collected as the main path execution result; The historical control parameter set is called through the auxiliary path, and loaded to the virtual dual-loop cooperative controller. Under the same discrete working condition label, the simulated rotor displacement and the simulated coil current are outputted as the auxiliary path simulation result; The Lyapunov index of the main path execution result and the auxiliary path simulation result is calculated respectively, and the stability margin value is generated according to the calculation result.

7. The method of claim 6, wherein: The auxiliary path simulation result is outputted as the final execution instruction, and the specific steps are as follows, The stability margin value is compared with the preset safety interval. If the stability margin value is within the preset safety interval, it is marked as a safe state, otherwise it is marked as a risk state; When it is determined to be a safe state, the synchronization signal is transmitted to the power driving unit; When it is determined to be a risk state, the auxiliary path simulation result is reconstructed as the final execution instruction and outputted to the power driving unit.

8. A control parameter adjustment system of a magnetic levitation blower, based on the control parameter adjustment method of the magnetic levitation blower according to any one of claims 1 to 7, characterized by: It comprises a feature extraction module, a gene matching module, a trajectory modulation module, a phase synchronization module, a channel verification module and a decision execution module; The feature extraction module is used to construct an information fusion model, input the collected electromechanical-thermal coupling features into the information fusion model to generate electromechanical-thermal feature vectors, separate the electromechanical-thermal feature vectors into electromechanical-thermal feature components by using a vector decoupling operator, and generate an energy stability scalar value in combination with real-time magnetic levitation air supply fan operation data; The gene matching module is used to construct a distributed digital gene library, map the energy stability scalar value to a discrete working condition label, match the discrete working condition label with a gene fragment in the distributed digital gene library, and output an optimal gene fragment; The trajectory modulation module is used to analyze the optimal gene fragment to generate a control parameter set, generate a multi-parameter change trajectory through a smoothing operation function group, and generate a proportional control signal and an integral control signal through a time-space crystal oscillation mechanism for high-frequency carrier modulation; The phase synchronization module is used to perform phase alignment on the proportional control signal and the integral control signal by using a time-sensitive network protocol, realize phase locking within a preset time window, generate a synchronization signal and load it to an execution path, and the execution path comprises a main path and an auxiliary path; The channel verification module is used to execute the synchronization signal through the main path, call the historical control parameter set to the auxiliary path for simulation execution, calculate a Lyapunov index difference value according to the main path execution result and the auxiliary path simulation result, and output a stability margin value; The decision execution module is used to output the synchronization signal to the power driving unit when the stability margin value is within a preset safety interval, otherwise output the auxiliary path simulation result as the final execution instruction. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the control parameter adjustment method of the magnetic levitation air supply fan according to any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program, when executed by a processor, implements the steps of the control parameter adjustment method of the magnetic levitation blower according to any one of claims 1-7.

Images