Intelligent diagnosis method and system for working state of dry vacuum pump based on multiple types of signals

Abstract

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.

Description

Technical Field

[0001] This invention relates to the field of vacuum pump monitoring technology, and in particular to an intelligent diagnostic method and system for the working status of dry vacuum pumps based on multiple types of signals. Background Technology

[0002] Vacuum pumps, as core vacuum acquisition equipment in industrial production, directly impact production efficiency and safety through their operational status. Currently, the core of this technology lies in utilizing sensing and detection methods to acquire multi-physical quantity information during vacuum pump operation and assess the health of the mechanical structure. The overall technology encompasses the entire process from sensor selection and signal conditioning to feature analysis, primarily involving continuous tracking and monitoring of the vibration intensity, temperature changes, motor load current, and acoustic characteristics of the vacuum pump rotor, bearings, and transmission system. By analyzing the coupling relationship between mechanical vibration and fluid pulsation, an operational fingerprint of the equipment is constructed to identify potential fault risks such as mechanical wear, abnormal clearances, and foreign object jamming.

[0003] In existing technologies, a multi-type signal-based intelligent diagnostic method has been developed to address the mechanical faults and performance degradation of dry vacuum pumps under varying operating conditions. This method encompasses the simultaneous acquisition and fusion analysis of vacuum pump casing vibration signals, motor three-phase current signals, and pump body radiated noise signals. Specifically, it typically utilizes accelerometers and current transformers to collect time-series data. The time-domain signals are converted into frequency-domain spectra using Fast Fourier Transform (FFT), and the root mean square value, kurtosis index, and energy proportion of specific frequency bands are extracted as feature vectors. Subsequently, these multi-source features are input into a convolutional neural network (CNN) or support vector machine (SVM) classification model trained on historical fault data. By calculating the mapping relationship between real-time features and fault modes, the specific state category of the current vacuum pump, such as normal, rotor imbalance, bearing pitting, or screw jamming, is output.

[0004] Existing diagnostic schemes for the operating status of dry vacuum pumps mostly rely on single signal characteristics for judgment. Common practices focus on threshold comparisons of vibration amplitude and spectral changes in the time or frequency domains. This makes it difficult to maintain stable feature alignment and consistent judgment criteria under conditions of speed fluctuations and operating condition switching. At the same time, when factors such as significant changes in pneumatic load with rotation angle, gap leakage, and mechanical imbalance coexist, the diagnostic results often remain at the level of correlation description at the phenomenological level. They lack interpretable physical quantities that can correspond to the actual motion parameters of the rotor, inertial torque, and pneumatic load, which can easily lead to confusion between different sources of failure. This further limits the repeatability and engineering applicability of health status classification and fault level assessment. Summary of the Invention

[0005] The main objective of this invention is to provide an intelligent diagnostic method and system for the working state of a dry vacuum pump based on multiple signal types. By integrating encoder pulse signals and vibration signals and introducing angular domain analysis and a pneumatic-rotor dynamics coupling inversion mechanism, the invention solves the problem of accurately distinguishing and quantitatively determining the mechanical imbalance and gap leakage states of dry vacuum pumps under variable speed and complex working conditions.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for intelligent diagnosis of the operating status of a dry vacuum pump based on multiple signal types, the method comprising: Step 1: Synchronously acquire the motor photoelectric encoder pulse signal and pump body vibration acceleration signal of the dry vacuum pump to be diagnosed. Based on the pulse signal, resample the vibration acceleration signal at equal angles to establish an angular domain vibration sequence. Step 2: Calculate the instantaneous angular velocity based on the time interval of the pulse signal, differentiate it to obtain the instantaneous angular acceleration, and combine it with the rotor rotational inertia pre-obtained for the dry vacuum pump to calculate the actual inertial torque; Step 3: Call the pre-stored screw rotor profile parameters and ideal adiabatic compression model matched with the dry vacuum pump to generate the theoretical aerodynamic load torque, calculate the difference between it and the actual inertial torque, integrate the negative amplitude of the difference within the exhaust closed phase, and generate the gap gas leakage flux index. Step 4: Correct the aerodynamic parameter terms in the rotor dynamics equation using the gap gas leakage flux index, substitute the instantaneous angular velocity and the set initial mass eccentricity into the rotor dynamics equation to solve the theoretical vibration response; calculate the residual vector between the theoretical vibration response and the angular domain vibration sequence, and iteratively correct the initial mass eccentricity through a proportional-integral adjustment loop until the norm of the residual vector is less than a preset convergence threshold to obtain the rotor physical imbalance eccentricity. Step 5: Compare the physical imbalance eccentricity of the rotor with the preset dynamic balance calibration threshold and allowable upper limit to determine the mechanical health status and fault level of the dry vacuum pump.

[0007] Preferably, step 1 specifically includes: Step 11: Mark the synchronously acquired pulse signal and vibration acceleration signal with a unified time base timestamp, and perform time alignment based on the timestamp to generate a synchronous time domain digital signal set; Step 12: Identify the rising edge of the concentrated pulse waveform of the synchronous time-domain digital signal and calculate the adjacent interval. Combine the preset resolution of the motor photoelectric encoder to subdivide the rotation period by angle and construct a mapping relationship table between the rotation angle and the time coordinate. Step 13: Using the time coordinate index in the mapping table, interpolate the vibration data in the synchronous time-domain digital signal set to obtain the vibration amplitude corresponding to each equal angle time and reassemble them in ascending order of angle to establish the angular domain vibration sequence.

[0008] Preferably, the step 13 of interpolating the vibration data in the synchronous time-domain digital signal set specifically includes: using the time coordinates in the mapping table as nodes, constructing a time-continuous function of the vibration acceleration signal using a cubic spline interpolation algorithm, and substituting each equal angular moment into the time-continuous function to calculate the corresponding vibration amplitude, so as to generate the angular domain vibration sequence.

[0009] Preferably, step 2 specifically includes: Step 21: Based on the synchronously acquired motor photoelectric encoder pulse signal, extract the timestamp of each pulse moment and calculate the difference between adjacent timestamps to obtain the time interval sequence. Divide the angle increment corresponding to the preset resolution of the motor photoelectric encoder by the time interval sequence to generate the instantaneous angular velocity of each sampling point. Step 22: Call the instantaneous angular velocity sequence, perform time differentiation on it, and obtain the instantaneous angular acceleration during the rotor rotation process; Step 23: Obtain the rotor moment of inertia of the dry vacuum pump obtained in advance, and multiply it with the instantaneous angular acceleration to obtain the actual inertial torque.

[0010] Preferably, in step 22, the time differential operation on the instantaneous angular velocity sequence is specifically performed by: using the central difference method to calculate the difference between two adjacent velocity values ​​before and after any sampling point in the instantaneous angular velocity sequence, and then dividing the difference by half of the sum of two adjacent time intervals determined by the time interval sequence to obtain the instantaneous angular acceleration of the sampling point.

[0011] Preferably, step 3 specifically includes: Step 31: Substitute the rotor angle sequence generated in Step 1 when establishing the angular domain vibration sequence into the profile envelope relationship and the cavity volume change relationship point by point. Perform a product operation based on the pressure change and the radius of action corresponding to each angle to generate the aerodynamic torque data corresponding to each angle, and obtain the theoretical aerodynamic load torque sequence.

[0012] Step 32: Based on the theoretical aerodynamic load torque sequence and the actual inertial torque sequence, perform point-by-point difference calculation under the same rotation angle index, arrange the algebraic differences of torques corresponding to each rotation angle position in rotation angle order, and obtain the aerodynamic inertial torque difference sequence. Step 33: For the aerodynamic inertial torque difference sequence, select an interval according to the preset angle interval corresponding to the exhaust closure phase, perform sign judgment on the difference value in the selected interval and extract the negative amplitude, and perform integration calculation on the negative amplitude according to the angle step size to generate the gap gas leakage flux index.

[0013] Preferably, in step 33, the angle interval corresponding to the exhaust sealing phase is determined based on the exhaust port opening angle and closing angle in the screw rotor profile parameters, and the angle range between the opening angle and the closing angle is used as the angle interval corresponding to the exhaust sealing phase.

[0014] Preferably, step 4 includes: Step 41: Call the gap gas leakage flux index to correct the aerodynamic parameter terms in the rotor dynamics equation, and substitute the instantaneous angular velocity and the set initial mass eccentricity into the corrected rotor dynamics equation for numerical solution to obtain the theoretical vibration response.

[0015] Step 42: Based on the theoretical vibration response and the angular domain vibration sequence, calculate the difference between the two and establish a residual vector;

[0016] Step 43: Compare the magnitude of the residual vector with the preset residual convergence threshold. If the magnitude has not converged, iteratively correct the initial mass eccentricity through the proportional-integral adjustment loop and repeat steps 41 and 42 until the residual vector converges. Then, determine the mass eccentricity at this time as the rotor physical imbalance eccentricity.

[0017] Preferably, step 5 specifically includes: Step 51: Obtain the rotor physical imbalance eccentricity, compare it with the preset dynamic balance calibration threshold and allowable upper limit, and determine the healthy state interval to which the eccentricity belongs.

[0018] Step 52: Based on the health status interval to which the eccentricity belongs, call the preset fault level classification rules to determine the mechanical health status and corresponding fault level of the dry vacuum pump.

[0019] This invention also discloses an intelligent diagnostic system for the operating status of a dry vacuum pump based on multiple signal types, used to execute the above-described method. The system includes: An angular domain vibration sequence generation module is used to synchronously acquire the pulse signal of the motor photoelectric encoder and the vibration acceleration signal of the pump body of the dry vacuum pump, and to resample the vibration acceleration signal at equal angles based on the pulse signal to establish an angular domain vibration sequence.

[0020] The actual inertial torque calculation module is used to calculate the instantaneous angular velocity based on the time interval of the pulse signal, differentiate it to obtain the instantaneous angular acceleration, and calculate the actual inertial torque in combination with the preset rotor rotational inertia.

[0021] The gap gas leakage flux calibration module is used to call the pre-stored screw rotor profile parameters and ideal adiabatic compression model to generate the theoretical aerodynamic load torque, calculate the difference between it and the actual inertial torque, and integrate the negative amplitude of the difference within the exhaust closed phase to generate the gap gas leakage flux index.

[0022] The physical imbalance eccentricity calculation module is used to correct the aerodynamic parameter terms in the rotor dynamics equation using the gap gas leakage flux index, and to calculate the rotor physical imbalance eccentricity by iteratively calculating and converging the residual vector of the theoretical vibration response and the angular domain vibration sequence.

[0023] The mechanical health status assessment module is used to compare the physical imbalance eccentricity of the rotor with the preset dynamic balance calibration threshold and allowable upper limit to determine the mechanical health status and fault level of the dry vacuum pump.

[0024] Compared with the prior art, the present invention has the following beneficial effects: This invention synchronously acquires encoder pulse signals and pump vibration signals, and converts the vibration signals to the angular domain for unified characterization. This enables the diagnostic process to maintain a consistent alignment reference under conditions of speed fluctuations and operating changes, thereby improving the stability and repeatability of working status identification and fault location.

[0025] This invention derives the instantaneous motion parameters of the rotor from the pulse signal and obtains the actual inertial torque by combining the rotor inertia. Then, it performs differential and integral characterization with the theoretical aerodynamic load generated based on the rotor profile and ideal compression process. This allows key fault sources such as gap leakage and rotor imbalance to be distinguished and quantified in the form of interpretable physical quantities, thereby enhancing the interpretability and traceability of diagnostic results.

[0026] This invention corrects the rotor dynamics aerodynamic terms by using leakage flux index, and uses the residual between theoretical vibration response and measured vibration sequence in the angular domain as feedback to iteratively converge the solution of mass eccentricity. This transforms the output of unbalance quantity from empirical characteristic quantity into physical parameters that can be directly used for dynamic balance determination, thereby improving the consistency and engineering adaptability of mechanical health status assessment. Attached Figure Description

[0027] Figure 1 This is an exemplary flowchart illustrating an intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types, as shown in an embodiment of the present invention. Detailed Implementation

[0028] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the linguistic context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0029] It should be understood that the terms system, apparatus, unit, and / or module used in this specification are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0030] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or such terms do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "include" and "contain" only indicate that they include the expressly identified steps and elements, and these steps and elements do not constitute an exclusive list, as the method or apparatus may also include other steps or elements.

[0031] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0032] The intelligent diagnostic method and system for the working status of dry vacuum pumps based on multiple signal types, provided in the embodiments of this specification, will be described in detail below with reference to the accompanying drawings.

[0033] Figure 1 This is an exemplary flowchart illustrating an intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types, according to some embodiments of this specification. In some embodiments, the intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types can be executed by processing logic, which may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, etc.), software (instructions running on a processing device to execute hardware simulations), and any combination thereof. In some embodiments, Figure 1One or more operations in the flowchart of the intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types can be implemented by a processing device and / or a terminal device. For example, this intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types can be stored in a storage device in the form of a computer program and / or instructions, and can be invoked and / or executed by the processing device and / or the terminal device.

[0034] like Figure 1 As shown, the intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types disclosed in this invention specifically includes the following steps: Step 1: Collect the pulse sequence of the photoelectric encoder installed on the shaft end of the dry vacuum pump motor and the vibration amplitude signal of the accelerometer on the pump body shell. Use the pulse signal as the sampling trigger reference to extract the vibration amplitude signal at equal angular intervals. Map the time-domain vibration data to the screw rotor rotation angle coordinate system to generate an angular domain vibration state array. Step 2: Call the angular domain vibration state array, calculate the reciprocal of the number of processor clock cycles in the adjacent pulse interval to determine the instantaneous angular velocity, perform differential operation on the instantaneous angular velocity with respect to the rotation angle variable, extract the velocity fluctuation characteristics within the full circular rotation cycle, and obtain the instantaneous angular acceleration waveform; Step 3: Based on the instantaneous angular acceleration waveform, perform differential calculation with the theoretical aerodynamic drag torque generated based on the screw rotor profile data and the ideal adiabatic compression law, integrate the negative differential amplitude in the phase interval of the exhaust sealed cavity, and calculate the gap gas leakage flux index. Step 4: Use the gap gas leakage flux index to correct the aerodynamic load term in the rigid rotor dynamic equation set. Substitute the real-time rotational speed into the equation set containing the rotor mass distribution matrix and bearing stiffness coefficient to solve the theoretical vibration response. Subtract the theoretical vibration response from the measured vibration acceleration amplitude to obtain the residual vector. Extract the rotational frequency synchronization component in the residual vector and input it into the proportional-integral control loop to calculate the mass eccentricity correction increment. Add this increment to the dynamic equation parameters in real time until the residual vector magnitude converges to near zero. Establish the rotor physical imbalance eccentricity value. Step 5: Based on the value of the rotor's physical imbalance eccentricity, compare this value with the factory dynamic balance calibration threshold of the vacuum pump and the upper limit of the allowable imbalance of the screw rotor to determine the current mechanical operating stability status of the equipment and generate the vacuum pump health status diagnosis level.

[0035] It should be noted that, in some embodiments of the present invention, step 1 specifically includes: Step 11: Mark the synchronously acquired pulse signal and vibration acceleration signal with a unified time base timestamp, and perform time alignment based on the timestamp to generate a synchronous time domain digital signal set; In a specific example, for step 11, two signal data streams are first received from the data acquisition card. The sampling frequency of the vibration acceleration signal is set to 51.2kHz, and the pulse signal is a TTL level signal. The two signal streams are then sent to a unified timestamp marking module. This module uses the system clock as a reference and appends a high-precision timestamp to each data point entering the module (e.g., the nth sampling point of the vibration signal and its amplitude, the level transition point of the pulse signal). For example, if the amplitude of the vibration signal at t=0.00100s is 0.5m / s, then its data point is recorded as (0.00100, 0.5). The pulse signal at t=0.00105s... The rising edge of the next voltage level transitioning from 0V to 5V is recorded as (0.00105, Rise). These timestamped data points are stored in the same data buffer in chronological order. Then, the data in the buffer is sorted and arranged, aligning data points from different channels with similar timestamps to form a data matrix with time as the main axis. Each row of the matrix represents a time point, and each column corresponds to the vibration signal amplitude and pulse signal state, respectively. For example, one row in the matrix may be [0.00100s, 0.5m / s, 0V], and the next row may be [0.00105s, 0.52m / s, 5V], generating a synchronous time-domain digital signal set. Step 12: Identify the rising edge of the concentrated pulse waveform of the synchronous time-domain digital signal and calculate the adjacent interval. Combine the preset resolution of the motor photoelectric encoder to subdivide the rotation period by angle and construct a mapping relationship table between the rotation angle and the time coordinate. Furthermore, a rising edge detection threshold is first set, based on the TTL level standard, for example, 2.5V. During execution, the program scans the pulse signal column in the synchronous time-domain digital signal set line by line. When the voltage value of the current sampling point is greater than 2.5V and the voltage value of the previous sampling point is less than 2.5V, the timestamp of the current sampling point is recorded. For example, a series of rising edge times such as T1=0.00105s, T2=0.02105s, T3=0.04105s are recorded sequentially. Then, the time difference between two adjacent rising edge times is calculated to obtain the pulse time interval T. i =T i+1 -T iFor example, T1 = T2 - T1 = 0.02105s - 0.00105s = 0.020s. These time intervals are grouped into a sequence. Then, a preset encoder resolution is retrieved, for example, 1024 pulses per revolution. The angle increment corresponding to each pulse interval is 360 / 1024 = 0.3516. Based on this, each pulse starting from the first rising edge (denoted as 0) is assigned a cumulative angle value. For example, the first rising edge corresponds to angle 0 and time T1, the second rising edge corresponds to angle 0.3516 and time T2, and so on, with the kth rising edge corresponding to angle (k-1)0.3516 and time T. k In this way, a one-to-one correspondence between the rotor rotation angle and a specific time point is obtained, and a mapping table between the rotation angle and the time coordinate is constructed. Step 13: Using the time coordinate index in the mapping table, interpolate the vibration data in the synchronous time-domain digital signal set to obtain the vibration amplitude corresponding to each equal angular moment and reassemble them in ascending order of angle to establish the angular domain vibration sequence. Specifically, the interpolation method for the vibration data in the synchronous time-domain digital signal set in Step 13 is as follows: using the time coordinate in the mapping table as nodes, construct a time-continuous function of the vibration acceleration signal using a cubic spline interpolation algorithm, and substitute each equal angular moment into the time-continuous function to calculate the corresponding vibration amplitude, thereby generating the angular domain vibration sequence.

[0036] Building upon the previous example, using the time coordinate index in the mapping table, we first extract all time coordinate nodes marked as equal-angle moments from the mapping table. For example, if we need to resample every 1, the target angle points are 0, 1, 2, ..., 359. We then find or calculate the corresponding time coordinates t for these angle points based on the mapping table. D ,t1,t2,...,t 359 Then, for the original time-based vibration acceleration signal data sequence, two original data points are taken before and after each target time point tᵢ. For example, for the target time point t1=0.00160s, we find the four closest points before and after it in the original vibration data: (0.00158s, 0.61m / s), (0.00159s, 0.63m / s), (0.00161s, 0.68m / s), (0.00162s, 0.71m / s). Using these four data points, a unique cubic polynomial function is established. Substituting the time t1=0.00160s into this function, the precise vibration amplitude corresponding to that moment is calculated, for example, 0.65m / s. For all target angles, the corresponding tᵢ is calculated. D To t 359Repeat this interpolation calculation process to obtain a series of vibration amplitudes that precisely correspond to the equiangular positions. Obtain the vibration amplitudes corresponding to each equiangular time and recombine them in ascending order of angle. Arrange these calculated vibration amplitudes in the order of 0 to 359 to form a new sequence containing 360 data points, thus establishing the angular domain vibration sequence.

[0037] In another embodiment of the present invention, step 2 specifically includes: Step 21: Based on the synchronously acquired motor photoelectric encoder pulse signal, extract the timestamp of each pulse moment and calculate the difference between adjacent timestamps to obtain the time interval sequence. Divide the angle increment corresponding to the preset resolution of the motor photoelectric encoder by the time interval sequence to generate the instantaneous angular velocity of each sampling point. For example, firstly, extract the rising edge timestamp sequence of the pulse signal from the synchronized time-domain digital signal set generated in the previous steps, such as T1=0.00105s, T2=0.02105s, T3=0.04105s, T4=0.06100s. Then, perform the difference operation between adjacent terms on this timestamp sequence, i.e., T i =T i+1 -T i The time interval sequence is calculated, for example, T1=T2-T1=0.02000s, T2=T3-T2=0.02000s, T3=T4-T3=0.01995s. Then, the preset resolution of the motor photoelectric encoder is retrieved, which is 1024 pulses / revolution. The angle increment corresponding to each pulse is calculated as 2 / 1024 = 0.006136 rad. Finally, this fixed angle increment is divided one by one by the time interval sequence T. i For each element in the equation, the average instantaneous angular velocity within each time interval is obtained. i = / T i We assume that the instantaneous angular velocity corresponding to the second pulse is 1 = 0.006136 rad / 0.02000 s = 0.3068 rad / s, the instantaneous angular velocity corresponding to the third pulse is 2 = 0.006136 rad / 0.02000 s = 0.3068 rad / s, and the instantaneous angular velocity corresponding to the fourth pulse is 3 = 0.006136 rad / 0.01995 s = 0.3076 rad / s, and generate the instantaneous angular velocities at each sampling point; Step 22: Call the instantaneous angular velocity sequence, perform time differentiation on it, and obtain the instantaneous angular acceleration during the rotor rotation process; It should be noted that the method for performing time differentiation on the instantaneous angular velocity sequence is as follows: using the central difference method, the difference between two adjacent velocity values ​​before and after any sampling point in the instantaneous angular velocity sequence is calculated, and then the difference is divided by half of the sum of two adjacent time intervals determined by the time interval sequence to obtain the instantaneous angular acceleration of that sampling point.

[0038] Furthermore, the instantaneous angular velocity sequence is invoked. First, the instantaneous angular velocity sequence generated in the previous step is read from memory, for example, 1=0.3068 rad / s, 2=0.3068 rad / s, 3=0.3076 rad / s, and the corresponding time interval sequence T1=0.02000s, T2=0.02000s, T3=0.01995s. Then, for any sampling point i that is not at the beginning or end of the sequence (for example, i=2), the velocity value of the next sampling point is retrieved. i+1 (i.e., 3 = 0.3076 rad / s) and the velocity value of the previous sampling point i-1 (i.e., 1 = 0.3068 rad / s), calculate the difference between the two, and obtain the change in velocity = i+1 - i-1 (=0.3076-0.3068=0.0008rad / s, then extract the two time interval values ​​T before and after this sampling point from the time interval sequence) i-1 (i.e., T1 = 0.02000s) and T i (i.e., T2 = 0.02000s); Calculate half the sum of these two time intervals to obtain the time step t = (T i-1 +T i ) / 2=(0.02000s+0.02000s) / 2=0.02000s, and finally divide the calculated velocity change by the time step t, that is, 2= / t=0.0008 / 0.02000=0.04rad / s, to obtain the instantaneous angular acceleration during the rotor rotation process; Step 23: Obtain the rotor moment of inertia of the dry vacuum pump obtained in advance, and multiply it with the instantaneous angular acceleration to obtain the actual inertial torque.

[0039] Based on the above, the pre-stored rotor moment of inertia value is first retrieved from the equipment's configuration file or database. This value is provided by the vacuum pump manufacturer or obtained through experimental calibration. Its value is determined based on the mass distribution, geometry, and dimensions of the rotor (usually a pair of screw rotors). For example, the rotor moment of inertia J of this specific model of dry vacuum pump is set to 0.15 kgm. Then, this moment of inertia J is multiplied by each value in the instantaneous angular acceleration sequence calculated in the previous step, i.e., M... i =J iFor example, for the instantaneous angular acceleration 2 = 0.04 rad / s at the second sampling point calculated in the previous step, calculate the corresponding torque M2 = 0.15 kgm 0.04 rad / s = 0.006 Nm. Perform this calculation on the entire angular acceleration sequence to obtain the actual inertial torque.

[0040] In some embodiments of the present invention, step 3 specifically includes: Step 31: Substitute the rotor angle sequence generated in Step 1 when establishing the angular domain vibration sequence into the profile envelope relationship and the cavity volume change relationship point by point. Perform a product operation based on the pressure change and the radius of action corresponding to each angle to generate the aerodynamic torque data corresponding to each angle, and obtain the theoretical aerodynamic load torque sequence. It should be noted that the rotor angle sequence generated when establishing the angular domain vibration sequence in step 1 consists of a series of discrete angle values, for example, starting from 0 and increasing by 1 step size until 359, forming a sequence containing 360 elements [0,1,2,...,359]. First, the mathematical equation describing the rotor geometry is retrieved from the pre-stored screw rotor profile parameter file. This equation defines the position of the profile in the coordinate system at any angle. At the same time, the function V() describing the change in cavity volume is retrieved. This function is also related to the angle. Next, for the first angle value in the angle sequence... D =0, substituting it into the ideal adiabatic compression model, which describes the relationship between gas pressure P and volume V, i.e., P( D )V( D ) 1.4 =C, where C is a constant determined by the pump's inlet pressure, from which the following can be calculated. D When =0, the theoretical pressure P of the compressed gas in a specific closed cavity is... D） For example, if the calculated value is 0.1 MPa, then the angle is... D Substituting 0 into the profile envelope relationship, we determine the average point of application of the gas pressure on the rotor at this time, thus obtaining an effective radius of action r. D） For example, if it is 0.05 meters, the calculated pressure P( D） Converted into force F( D） Then, with the radius of action r ( D） Multiply to obtain D =0 corresponds to aerodynamic torque data of 0.005Nm. Then, the above pressure calculation, radius determination and torque product operation are repeated for the remaining 359 angle points (1 to 359) in the angle sequence. Finally, the torque values ​​calculated under all angles are arranged in angular order to obtain the theoretical aerodynamic load torque sequence.

[0041] Step 32: Based on the theoretical aerodynamic load torque sequence and the actual inertial torque sequence, perform point-by-point difference calculation under the same rotation angle index, arrange the algebraic differences of torques corresponding to each rotation angle position in rotation angle order, and obtain the aerodynamic inertial torque difference sequence. The theoretical aerodynamic load torque sequence and the actual inertial torque sequence are sets of torque values ​​containing 360 elements, each corresponding one-to-one with the rotation angle sequence [0,1,2,...,359]. For example, at the rotation angle index i=2 (corresponding to rotation angle 2), the torque value M_actual,2 is extracted from the actual inertial torque sequence as 0.006 Nm, and the corresponding torque value M_theory,2 is extracted from the theoretical aerodynamic load torque sequence as 0.005 Nm. Given a torque of 5 Nm, at the same angle index i=2, performing algebraic subtraction on these two torque values, i.e., M2=M_theory,2-M_actual,2, we obtain the result M2=0.0055-0.006=-0.0005Nm. This calculation process starts from angle index i=0 and continues until i=359, performing this difference operation on each pair of torque values ​​at the same index. The resulting 360 torque differences are then calculated, for example, [M...]. D ,M1,-0.0005Nm,...,M 359 The aerodynamic inertial torque difference sequence is obtained by arranging the original rotation angles from 0 to 359. Step 33: For the aerodynamic inertial torque difference sequence, the rotation angle interval corresponding to the preset exhaust closure phase is selected. The sign of the difference value within the selected interval is judged and the negative amplitude is extracted. The negative amplitude is integrated according to the rotation angle step size to generate the gap gas leakage flux index. The rotation angle interval corresponding to the exhaust closure phase is determined based on the exhaust port opening angle and closing angle in the screw rotor profile parameters, and the rotation angle range between the opening angle and the closing angle is used as the rotation angle interval corresponding to the exhaust closure phase.

[0042] Step 33: For the aerodynamic inertial torque difference sequence, select the interval according to the preset angle interval corresponding to the exhaust closure phase, perform sign judgment on the difference value in the selected interval and extract the negative amplitude, and perform integration calculation on the negative amplitude according to the angle step size to generate the gap gas leakage flux index. For the aforementioned aerodynamic inertial moment difference sequence, firstly, two key angle values ​​are retrieved from the screw rotor profile parameter file: the exhaust port opening angle and the exhaust port closing angle. For example, the opening angle is set to 280° and the closing angle is set to 340°, thus determining the angle interval [280°, 340°] corresponding to the exhaust closing phase. Next, elements in the aerodynamic inertial moment difference sequence whose indices correspond to this angle interval [280°, 340°] are selected to form a subsequence. Then, each difference value in this subsequence is checked one by one. The sign judgment is performed. Specifically, each difference value is compared with 0. If the value is less than 0, it is retained; if the value is greater than or equal to 0, it is discarded. For example, if the difference value at 281 is -0.0008 Nm, its negative amplitude of 0.0008 Nm is extracted; if the difference value at 282 is 0.0001 Nm, it is not extracted. Finally, all extracted negative amplitudes are multiplied by the rotation step size d (1 in this case, which needs to be converted to radians, i.e., / 180 rad) and then summed. The specific calculation process is as follows: Wherein, is the gap gas leakage flux index, which represents the summation of all points that meet the conditions within the exhaust closed phase interval, represents the discrete turning angle within the interval, is the negative torque differential amplitude extracted at the turning angle, and is the turning angle step size ( / 180rad). For example, if the sum of all extracted negative amplitudes in the interval [280,340] is 0.015Nm, then an integral operation of 0.015Nm( / 180)rad is performed to generate the gap gas leakage flux index. In some embodiments of the present invention, step 4 specifically includes: Step 41: Call the gap gas leakage flux index to correct the aerodynamic parameter terms in the rotor dynamics equation, and substitute the instantaneous angular velocity and the set initial mass eccentricity into the corrected rotor dynamics equation for numerical solution to obtain the theoretical vibration response. Based on the aforementioned example, and using the gap gas leakage flux index obtained in the previous steps, the original aerodynamic parameter items are first retrieved from the rotor dynamics parameter table. This leakage flux index is then directly superimposed onto the corresponding aerodynamic damping or gas action coefficient as a correction, forming an updated aerodynamic parameter set. Subsequently, angular velocity values ​​consistent with the angular index of the angular domain vibration sequence are read point-by-point from the instantaneous angular velocity sequence. For example, the instantaneous angular velocity at a rotation angle of 2 is 0.3068 rad / s. Simultaneously, the set initial mass eccentricity value is read from the initialization configuration, for example... After converting the eccentricity to 0.020mm (metric unit 0.000020m), it is substituted into the rotor dynamics numerical expression along with the corrected aerodynamic parameters and instantaneous angular velocity. The numerical substitution and solution operation is performed once within a single rotation angle step. The above substitution and calculation operation is repeated for all angle points from 0 to 359 to obtain the theoretical vibration amplitude corresponding to each angle position. For example, the theoretical vibration acceleration at point 2 is calculated to be 0.45m / s. Finally, the calculation results for all angle points are arranged in ascending order of angle to form a complete theoretical vibration response sequence.

[0043] Step 42: Based on the theoretical vibration response and the angular domain vibration sequence, calculate the difference between the two and establish a residual vector; After obtaining the theoretical vibration response sequence, the measured vibration amplitude data that is completely consistent with its angle index is read from the established angular domain vibration sequence. Numerical difference operation is performed for each angular position. Specifically, the theoretical vibration amplitude at that angle is directly subtracted from the measured vibration amplitude. For example, at position 2, the theoretical vibration amplitude is 0.45 m / s and the measured angular domain vibration amplitude is 0.50 m / s, so the corresponding difference is -0.05 m / s. The same subtraction operation is performed for all angle points from 0 to 359. The 360 ​​difference results are combined in angular order to form a difference data set that corresponds one-to-one with the rotation angle sequence. This set constitutes the residual vector under the current mass eccentricity condition.

[0044] Step 43: Compare the magnitude of the residual vector with the preset residual convergence threshold. If the magnitude has not converged, iteratively correct the initial mass eccentricity through the proportional-integral adjustment loop and repeat steps 41 and 42 until the residual vector converges. Then, determine the mass eccentricity at this time as the rotor physical imbalance eccentricity.

[0045] For the residual vector, first perform an absolute value operation on the difference corresponding to each angular position in the vector to obtain a set of unsigned residual amplitude data. Then square all the residual amplitudes and accumulate them term by term. Finally, perform a square root operation on the accumulated result to obtain a residual amplitude index for characterizing the overall residual level. Numerically compare this residual amplitude with a preset residual convergence threshold, where this threshold is set according to the noise level of the vibration measurement system, for example, set to 0.10 m / s. When the calculated residual amplitude is 0.18 m / s, it is determined that the convergence condition is not met. Subsequently, according to the difference between the current residual amplitude and the residual amplitude of the previous iteration, calculate the eccentricity increment that needs to be corrected. Multiply this increment by a proportionality coefficient of 0.6 and an integral coefficient of 0.2 respectively and then perform an algebraic superposition with the current mass eccentricity value. For example, correct the original 0.020 mm to 0.018 mm. Then substitute the updated mass eccentricity back into the aforementioned theoretical vibration calculation and residual generation process. When the residual amplitude calculated in a certain iteration drops to 0.08 m / s and the change is less than 0.005 m / s for two consecutive rounds, stop the iteration and record the corresponding mass eccentricity value at this time as the physical unbalance eccentricity of the rotor.

[0046] In some embodiments of the present invention, step 5 specifically includes: Step 51: Obtain the physical unbalance eccentricity of the rotor, numerically compare it with a preset dynamic balance calibration threshold and the allowable upper limit, and determine the health status interval to which this eccentricity belongs; Based on the physical unbalance eccentricity value of the rotor recorded after the aforementioned iterative convergence, first read this eccentricity from the diagnostic record and convert the unit to mm. For example, read the eccentricity e = 0.018 mm. Then read the dynamic balance calibration threshold e_cal from the device dynamic balance calibration file and check its source as the calibration record of this type of rotor at the factory dynamic balance station. For example, this record gives e_cal = 0.010 mm. At the same time, read the allowable upper limit e_lim from the assembly acceptance parameter table of the same model and check its source as the mechanical allowable eccentricity upper limit given by the manufacturer. For example, this table gives e_lim = 0.030 mm. Then establish the boundaries of the health status interval in memory and write four closed-open relationship determination conditions. Interval 1 is defined as 0 ≤ e < 0.010 mm, interval 2 is defined as 0.010 mm < e < 0.020 mm, interval 3 is defined as 0.020 mm < e < 0.030 mm, and interval 4 is defined as e > 0.030 mm. Then perform magnitude comparison operations on e = 0.018 mm with 0.010 mm, 0.020 mm, and 0.030 mm in sequence. First, judge e < 0.010 mm to get no, then judge 0.010 mm < e < 0.020 mm to get yes, record the interval number as interval 2, and write this interval number into the current diagnostic result entry.

[0047] Step 52: Based on the health status interval to which the eccentricity belongs, call the preset fault level classification rules to determine the mechanical health status and corresponding fault level of the dry vacuum pump.

[0048] Based on the health status interval numbers written above, first read the correspondence between interval numbers and fault levels from the fault level classification table and verify that the table is set based on the dynamic balance acceptance file and on-site maintenance classification record of the same model vacuum pump. For example, the table sets interval 1 to level 0 and status mark as normal, interval 2 to level 1 and status mark as mild, interval 3 to level 2 and status mark as moderate, and interval 4 to level 3 and status mark as severe. Then, read interval number = 2 and locate the corresponding row in the table, extract the level field value of the row as 1 and extract the status field value as mild. Then, write the level field and status field together with the eccentricity e = 0.018mm into the diagnostic output structure and generate a text output entry to output the mechanical health status and corresponding fault level of the dry vacuum pump.

[0049] This invention also discloses an intelligent diagnostic system for the operating status of a dry vacuum pump based on multiple signal types, used in the above-mentioned method. The system includes: An angular domain vibration sequence generation module is used to synchronously acquire the pulse signal of the motor photoelectric encoder and the vibration acceleration signal of the pump body of the dry vacuum pump, and to resample the vibration acceleration signal at equal angles based on the pulse signal to establish an angular domain vibration sequence.

[0050] The actual inertial torque calculation module is used to calculate the instantaneous angular velocity based on the time interval of the pulse signal, differentiate it to obtain the instantaneous angular acceleration, and calculate the actual inertial torque in combination with the preset rotor rotational inertia.

[0051] The gap gas leakage flux calibration module is used to call the pre-stored screw rotor profile parameters and ideal adiabatic compression model to generate the theoretical aerodynamic load torque, calculate the difference between it and the actual inertial torque, and integrate the negative amplitude of the difference within the exhaust closed phase to generate the gap gas leakage flux index.

[0052] The physical imbalance eccentricity calculation module is used to correct the aerodynamic parameter terms in the rotor dynamics equation using the gap gas leakage flux index, and to calculate the rotor physical imbalance eccentricity by iteratively calculating and converging the residual vector of the theoretical vibration response and the angular domain vibration sequence.

[0053] The mechanical health status assessment module is used to compare the physical imbalance eccentricity of the rotor with the preset dynamic balance calibration threshold and allowable upper limit to determine the mechanical health status and fault level of the dry vacuum pump.

[0054] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0055] Furthermore, specific terms are used in this specification to describe embodiments thereof. For example, "an embodiment," "an embodiment," and / or "a number of embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that an embodiment, an embodiment, or an alternative embodiment mentioned twice or more in different locations in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0056] Furthermore, those skilled in the art will understand that various aspects of this specification can be described and illustrated in several patentable ways or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, various aspects of this specification can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as data blocks, modules, engines, units, components, or systems. Furthermore, various aspects of this specification may be represented as computer products located on one or more computer-readable media, including computer-readable program code.

[0057] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0058] The computer program code required for the operation of each part of this manual can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc.; conventional procedural programming languages ​​such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP; dynamic programming languages ​​such as Python, Ruby, and Groovy; or other programming languages. This program code can run entirely on the user's computer, or as a standalone software package on the user's computer, or partially on the user's computer and partially on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the user's computer through any network, such as a local area network (LAN) or wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as Software as a Service (SaaS).

[0059] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented by hardware devices, they can also be implemented solely by software solutions, such as installing the described system on existing processing devices or mobile devices.

[0060] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0061] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for intelligent diagnosis of the operating status of a dry vacuum pump based on multiple signal types, characterized in that, The method includes: Step 1: Synchronously acquire the motor photoelectric encoder pulse signal and pump body vibration acceleration signal of the dry vacuum pump to be diagnosed. Based on the pulse signal, resample the vibration acceleration signal at equal angles to establish an angular domain vibration sequence. Step 2: Calculate the instantaneous angular velocity based on the time interval of the pulse signal, differentiate it to obtain the instantaneous angular acceleration, and combine it with the rotor rotational inertia pre-obtained for the dry vacuum pump to calculate the actual inertial torque; Step 3: Call the pre-stored screw rotor profile parameters and ideal adiabatic compression model matched with the dry vacuum pump to generate the theoretical aerodynamic load torque, calculate the difference between it and the actual inertial torque, integrate the negative amplitude of the difference within the exhaust closed phase, and generate the gap gas leakage flux index. Step 4: Correct the aerodynamic parameter terms in the rotor dynamics equation using the gap gas leakage flux index, substitute the instantaneous angular velocity and the set initial mass eccentricity into the rotor dynamics equation to solve the theoretical vibration response; calculate the residual vector between the theoretical vibration response and the angular domain vibration sequence, and iteratively correct the initial mass eccentricity through a proportional-integral adjustment loop until the norm of the residual vector is less than a preset convergence threshold to obtain the rotor physical imbalance eccentricity. Step 5: Compare the physical imbalance eccentricity of the rotor with the preset dynamic balance calibration threshold and allowable upper limit to determine the mechanical health status and fault level of the dry vacuum pump.

2. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 1, characterized in that, Step 1 specifically includes: Step 11: Mark the synchronously acquired pulse signal and vibration acceleration signal with a unified time base timestamp, and perform time alignment based on the timestamp to generate a synchronous time domain digital signal set; Step 12: Identify the rising edge of the concentrated pulse waveform of the synchronous time-domain digital signal and calculate the adjacent interval. Combine the preset resolution of the motor photoelectric encoder to subdivide the rotation period by angle and construct a mapping relationship table between the rotation angle and the time coordinate. Step 13: Using the time coordinate index in the mapping table, interpolate the vibration data in the synchronous time-domain digital signal set to obtain the vibration amplitude corresponding to each equal angle time and reassemble them in ascending order of angle to establish the angular domain vibration sequence.

3. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types, as described in claim 2, is characterized in that... Step 13 involves interpolating the vibration data in the synchronous time-domain digital signal set. Specifically, this includes: using the time coordinates in the mapping table as nodes, constructing a time-continuous function of the vibration acceleration signal using a cubic spline interpolation algorithm, and substituting each equal angular moment into the time-continuous function to calculate the corresponding vibration amplitude, thereby generating the angular domain vibration sequence.

4. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 1, characterized in that: Step 2 specifically includes: Step 21: Based on the synchronously acquired motor photoelectric encoder pulse signal, extract the timestamp of each pulse moment and calculate the difference between adjacent timestamps to obtain the time interval sequence. Divide the angle increment corresponding to the preset resolution of the motor photoelectric encoder by the time interval sequence to generate the instantaneous angular velocity of each sampling point. Step 22: Call the instantaneous angular velocity sequence, perform time differentiation on it, and obtain the instantaneous angular acceleration during the rotor rotation process; Step 23: Obtain the rotor moment of inertia of the dry vacuum pump obtained in advance, and multiply it with the instantaneous angular acceleration to obtain the actual inertial torque.

5. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 4, characterized in that: In step 22, the instantaneous angular velocity sequence is subjected to time differentiation operation, specifically by using the central difference method to calculate the difference between two adjacent velocity values ​​before and after any sampling point in the instantaneous angular velocity sequence, and then dividing the difference by half of the sum of two adjacent time intervals determined by the time interval sequence to obtain the instantaneous angular acceleration of the sampling point.

6. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 1, characterized in that, Step 3 specifically includes: Step 31: Substitute the rotor angle sequence generated in Step 1 when establishing the angular domain vibration sequence into the profile envelope relationship and the cavity volume change relationship point by point. Perform a product operation based on the pressure change and the radius of action corresponding to each angle to generate the aerodynamic torque data corresponding to each angle, and obtain the theoretical aerodynamic load torque sequence. Step 32: Based on the theoretical aerodynamic load torque sequence and the actual inertial torque sequence, perform point-by-point difference calculation under the same rotation angle index, arrange the algebraic differences of torques corresponding to each rotation angle position in rotation angle order, and obtain the aerodynamic inertial torque difference sequence. Step 33: For the aerodynamic inertial torque difference sequence, select an interval according to the preset angle interval corresponding to the exhaust closure phase, perform sign judgment on the difference value in the selected interval and extract the negative amplitude, and perform integration calculation on the negative amplitude according to the angle step size to generate the gap gas leakage flux index.

7. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 6, characterized in that, In step 33, the angle interval corresponding to the exhaust sealing phase is determined based on the exhaust port opening angle and closing angle in the screw rotor profile parameters, and the angle range between the opening angle and the closing angle is used as the angle interval corresponding to the exhaust sealing phase.

8. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 1, characterized in that, Step 4 includes: Step 41: Call the gap gas leakage flux index to correct the aerodynamic parameter terms in the rotor dynamics equation, and substitute the instantaneous angular velocity and the set initial mass eccentricity into the corrected rotor dynamics equation for numerical solution to obtain the theoretical vibration response. Step 42: Based on the theoretical vibration response and the angular domain vibration sequence, calculate the difference between the two and establish a residual vector; Step 43: Compare the magnitude of the residual vector with the preset residual convergence threshold. If the magnitude has not converged, iteratively correct the initial mass eccentricity through the proportional-integral adjustment loop and repeat steps 41 and 42 until the residual vector converges. Then, determine the mass eccentricity at this time as the rotor physical imbalance eccentricity.

9. The intelligent diagnostic method for the operating status of a dry vacuum pump based on multiple signal types as described in claim 1, characterized in that, Step 5 specifically includes: Step 51: Obtain the rotor physical imbalance eccentricity, compare it with the preset dynamic balance calibration threshold and allowable upper limit, and determine the healthy state interval to which the eccentricity belongs. Step 52: Based on the health status interval to which the eccentricity belongs, call the preset fault level classification rules to determine the mechanical health status and corresponding fault level of the dry vacuum pump.

10. A smart diagnostic system for the operating status of a dry vacuum pump based on multiple signal types, used to execute the method described in any one of claims 1-9, characterized in that, include: An angular domain vibration sequence generation module is used to synchronously acquire the pulse signal of the motor photoelectric encoder and the vibration acceleration signal of the pump body of the dry vacuum pump, and to resample the vibration acceleration signal at equal angles based on the pulse signal to establish an angular domain vibration sequence. The actual inertial torque calculation module is used to calculate the instantaneous angular velocity based on the time interval of the pulse signal, differentiate it to obtain the instantaneous angular acceleration, and calculate the actual inertial torque in combination with the preset rotor rotational inertia. The gap gas leakage flux calibration module is used to call the pre-stored screw rotor profile parameters and ideal adiabatic compression model to generate the theoretical aerodynamic load torque, calculate the difference between it and the actual inertial torque, and integrate the negative amplitude of the difference within the exhaust closed phase to generate the gap gas leakage flux index. The physical imbalance eccentricity calculation module is used to correct the aerodynamic parameter terms in the rotor dynamics equation using the gap gas leakage flux index, and to calculate the rotor physical imbalance eccentricity by iteratively calculating and converging the residual vector of the theoretical vibration response and the angular domain vibration sequence. The mechanical health status assessment module is used to compare the physical imbalance eccentricity of the rotor with the preset dynamic balance calibration threshold and allowable upper limit to determine the mechanical health status and fault level of the dry vacuum pump.

Images