Bearing health assessment method and system based on Mama probability prediction model

Abstract

The invention discloses a bearing health assessment method and system based on a Mama probability prediction model, and belongs to the technical field of health state assessment of bearing parts. The method comprises the following steps: predicting test data in a trained Mamba model to obtain an IMF component predicted value, performing fast Fourier transform on the IMF component predicted value to obtain a predicted frequency sequence, and constructing an evaluation model based on the distance between an actual frequency spectrum sequence of train running gear bearing vibration data and the predicted frequency sequence. And respectively substituting distance values between each predicted frequency sequence in a train rotating speed sequence to be detected and an actual frequency spectrum sequence of train running gear bearing vibration data into the evaluation model, and judging sigma intervals where all the distance values are located to obtain a judgment result of the health state of the bearing. According to the method, the health states of the bearing components such as the outer ring, the inner ring, the roller and the retainer are evaluated at the stable rotating speed, the current health level of each component of the bearing is obtained, and a maintenance basis can be provided.

Description

Technical Field

[0001] The present invention belongs to the technical field of bearing component health status assessment, and in particular relates to a bearing health assessment method and system based on a Mamba probability prediction model. Background Art

[0002] In today's digital age, smart railways have become part of the country's sustainable development. As an important part of smart railways, intelligent train operation and maintenance is an inevitable requirement for improving operational safety, efficiency, service quality and reducing operating costs.

[0003] Among them, the vibration, temperature and other status data of the train running gear bearings obtained by the intelligent operation and maintenance system can provide accurate basis for fault warning and fault alarm. However, it is still difficult to provide as a basis for maintenance, that is, the health status of the various bearing components is difficult to evaluate. Therefore, there is a need for a method to evaluate the health status of the various bearing components such as the outer ring, inner ring, roller and cage, which can obtain the current health level of the various bearing components and provide a basis for maintenance.

[0004] At present, the health assessment of the bearing components of the train running gear is determined by the vibration intensity. Some models are built through LSTM, and the predicted value is compared with the measured value for evaluation. However, these evaluation methods are all for determining whether there is a fault or not, and the credibility of the evaluation results is not clear. In the process of monitoring, data processing, and prediction, the LSTM model will still forget the long-term memory, and the model operation requires a large amount of resources, which is difficult to implement in the vehicle system. Summary of the invention

[0005] The purpose of the present invention is to solve the problems existing in the prior art and provide a bearing health assessment method and system based on the Mamba probability prediction model to complete the health status assessment of bearing components.

[0006] The specific technical solutions adopted by the present invention are as follows:

[0007] In order to achieve the above-mentioned invention object, the present invention specifically adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a bearing health assessment system based on the Mamba probability prediction model, which comprises:

[0009] A data monitoring module is used to obtain the vibration data and temperature status data of the train running gear bearing in real time, which includes a vibration sensor, a temperature sensor, a multiplexing switch, a sensor signal conditioning circuit, a current signal conditioning circuit, a voltage signal conditioning circuit, a voltage-dividing follower filter circuit, an A / D converter, a microcontroller module, a wireless transmission module and an overvoltage protection power supply module. The vibration sensor and the temperature sensor are connected to the microcontroller module after passing through the multiplexing switch, the sensor signal conditioning circuit, the current signal conditioning circuit, the voltage signal conditioning circuit, the voltage-dividing follower filter circuit and the A / D converter in sequence, and the wireless transmission module and the overvoltage protection power supply module are connected to the microcontroller module respectively;

[0010] The data processing module is used to process the train running gear bearing vibration data and temperature status data obtained by the data monitoring module to complete the health status assessment of the bearing components. It includes a prediction model acquisition module, an assessment model acquisition module, a health assessment module and a comprehensive judgment module.

[0011] Based on the above scheme, each step can be implemented in the following preferred specific manner.

[0012] As a preferred embodiment of the first aspect, the prediction model acquisition module is used to take the vibration data and temperature status data of the train running gear bearing as input data. When there are n spectral frequencies of the fault feature, the input data is subjected to low-pass filtering and then variational mode decomposition is used to generate n IMF components. The train speed sequence is taken as input and each IMF component is used as output to train the Mamba model.

[0013] The evaluation model acquisition module is used to obtain a new train speed sequence and form m groups of test data after obtaining the trained Mamba model, input each group of test data into the trained Mamba model for prediction, obtain n IMF component prediction values ​​for each group of test data, perform fast Fourier transform on the n IMF component prediction values ​​of each group of test data, and obtain a prediction frequency sequence for each IMF component prediction value, perform variational modal decomposition and fast Fourier transform on the train running gear bearing vibration data, and obtain an actual spectrum sequence for each IMF component of the train running gear bearing vibration data, calculate the distance between the actual spectrum sequence of the train running gear bearing vibration data and each prediction frequency sequence in turn, and form a distance sequence that obeys a normal distribution from the distances corresponding to the prediction frequency sequences with the same IMF component prediction value index, and estimate the mean of each distance sequence as the expectation of a normal distribution, and take the variance of each distance sequence as the variance of a normal distribution, and form an evaluation model from all the obtained normal distributions;

[0014] The health assessment module is used to obtain the distance value between each predicted frequency sequence in the train speed sequence to be detected and the actual frequency spectrum sequence of the train running gear bearing vibration data, and divide each normal distribution into four areas representing the bearing health level according to the 1sigma interval, the 2sigma interval, and the 3sigma interval, and substitute each distance value into each normal distribution in the assessment model to obtain the sigma interval in which each distance value is located; wherein, the area corresponding to the 1sigma interval indicates that the bearing state is excellent, the area corresponding to the 2sigma interval indicates that the bearing state is good, the area corresponding to the 3sigma interval indicates that the bearing state is reduced bearing performance, and other areas indicate that the bearing state is a bearing failure;

[0015] The comprehensive judgment module is used to judge the sigma intervals in which all distance values ​​are located: if there are other areas, bearing fault is taken as the judgment result of the bearing health state; if there are no other areas and there are 3sigma intervals, bearing performance degradation is taken as the judgment result of the bearing health state; if there are no other areas and 3sigma intervals at the same time, and the number of 2sigma intervals exceeds half, good is taken as the judgment result of the bearing health state; if there are no other areas and 3sigma intervals at the same time, and the number of 1sigma intervals is greater than or equal to half, excellent is taken as the judgment result of the bearing health state.

[0016] As a preferred embodiment of the above-mentioned first aspect, the microcontroller module includes a data acquisition control module, a data interpretation module, a power supply circuit, a reset circuit, a crystal oscillator circuit, a data processing and RAM read-write module, an interface chip control unit, a synchronous clock control module, a command deframing module, a configuration SPI Flash circuit and a download circuit; wherein the data acquisition control module, the data interpretation module, the power supply circuit, the reset circuit, the crystal oscillator circuit, the interface chip control unit, the synchronous clock control module, the command deframing module, the configuration SPI Flash circuit and the download circuit are each connected to the data processing and RAM read-write module.

[0017] As a preferred embodiment of the above-mentioned first aspect, the overvoltage protection power supply module includes a voltage source and an overvoltage protection circuit connected thereto, wherein the overvoltage protection circuit includes a first diode, a second diode, a third diode, a fourth diode, a fifth diode, a first resistor, a second resistor, a third resistor, a first PMOS tube, a second PMOS tube, a third PMOS tube and a fourth PMOS tube; wherein the first diode, the second diode and the third diode constitute a reference voltage circuit, which is used to generate a reference voltage according to the source voltage when the source voltage exceeds the clamping voltage; the fourth diode, the fifth diode, the first resistor, the second resistor, the third resistor, the first PMOS tube, the second PMOS tube, the third PMOS tube and the fourth PMOS tube constitute a feedback control circuit, which is used to receive the reference voltage and clamp the output voltage to the clamping voltage.

[0018] Further, in the overvoltage protection circuit, the anode of the first diode is connected to one end of the first resistor, the cathode of the first diode is connected to the cathode of the second diode, the anode of the second diode is connected to the cathode of the third diode, the anode of the third diode is respectively connected to one end of the second resistor, the anode of the fourth diode, one end of the third resistor, the anode of the fifth diode and the source of the first PMOS tube, the other end of the first resistor is respectively connected to the drain of the third PMOS tube, the gate of the third PMOS tube and the gate of the fourth PMOS tube, the source of the third PMOS tube is respectively connected to the source of the fourth PMOS tube, the drain of the second PMOS tube and the drain of the first PMOS tube, the drain of the fourth PMOS tube is respectively connected to the other end of the second resistor, the cathode of the fourth diode and the gate of the second PMOS tube, and the source of the second PMOS tube is respectively connected to the other end of the third resistor, the cathode of the fifth diode and the gate of the first PMOS tube.

[0019] As a preferred embodiment of the above-mentioned first aspect, the sensor signal conditioning circuit includes an analog signal input terminal, a fourth resistor, a fifth resistor, a first capacitor and a first operational amplifier, the analog signal input terminal is respectively connected to one end of the fourth resistor and one end of the fifth resistor, the other end of the fifth resistor is connected to one end of the first capacitor, the other end of the first capacitor is respectively connected to the other end of the fourth resistor and the positive input terminal of the first operational amplifier, and the negative input terminal of the first operational amplifier is connected to the output terminal of the first operational amplifier.

[0020] As a preferred embodiment of the above-mentioned first aspect, the voltage signal conditioning circuit includes a voltage signal input terminal, a sixth resistor, a seventh resistor, an eighth resistor, a second capacitor and a second operational amplifier, the voltage signal input terminal is connected to one end of the sixth resistor, the other end of the sixth resistor is respectively connected to one end of the seventh resistor and one end of the eighth resistor, the other end of the eighth resistor is connected to one end of the second capacitor, the other end of the second capacitor is respectively connected to the other end of the seventh resistor and the positive input terminal of the second operational amplifier, and the negative input terminal of the second operational amplifier is connected to the output terminal of the second operational amplifier.

[0021] As a preferred embodiment of the above-mentioned first aspect, the voltage divider follower filter circuit includes a third operational amplifier, a fourth operational amplifier, a third capacitor, a ninth resistor, a tenth resistor and an eleventh resistor, the output end of the third operational amplifier is connected to one end of the tenth resistor, the other end of the tenth resistor is respectively connected to one end of the eleventh resistor and the positive input end of the fourth operational amplifier, the other end of the eleventh resistor is connected to the current signal conditioning circuit, the output end of the fourth operational amplifier is connected to one end of the ninth resistor, the other end of the ninth resistor is respectively connected to one end of the third capacitor and the A / D converter, and the other end of the third capacitor is grounded.

[0022] In a second aspect, the present invention provides a bearing health assessment method based on the Mamba probability prediction model, which comprises the following steps:

[0023] S1. The vibration data and temperature status data of the train running gear bearing are used as input data. When there are n spectral frequencies of the fault characteristics, the input data is low-pass filtered and then used for variational mode decomposition to generate n IMF components. The train speed sequence is used as input and each IMF component is used as output to train the Mamba model to obtain a trained Mamba model;

[0024] S2. After obtaining the trained Mamba model, obtain a new train speed sequence and form m groups of test data. Input each group of test data into the trained Mamba model for prediction. Obtain n IMF component prediction values ​​for each group of test data. After performing fast Fourier transform on the n IMF component prediction values ​​of each group of test data, obtain a prediction frequency sequence for each IMF component prediction value. After performing variational modal decomposition and fast Fourier transform on the train running gear bearing vibration data, obtain an actual spectrum sequence for each IMF component of the train running gear bearing vibration data. Calculate the distance between the actual spectrum sequence of the train running gear bearing vibration data and each prediction frequency sequence in turn. Constitute a distance sequence that obeys a normal distribution from the distances corresponding to the prediction frequency sequences with the same IMF component prediction value index. Estimate the mean of each distance sequence as the expectation of a normal distribution. Take the variance of each distance sequence as the variance of a normal distribution. Constitute an evaluation model from all the obtained normal distributions.

[0025] S3. Obtain the distance values ​​between each predicted frequency sequence in the train speed sequence to be detected and the actual frequency spectrum sequence of the train running gear bearing vibration data, and divide each normal distribution into four regions representing the bearing health level according to the 1sigma interval, the 2sigma interval, and the 3sigma interval, and substitute each distance value into each normal distribution in the evaluation model to obtain the sigma interval in which each distance value is located; wherein, the region corresponding to the 1sigma interval indicates that the bearing condition is excellent, the region corresponding to the 2sigma interval indicates that the bearing condition is good, the region corresponding to the 3sigma interval indicates that the bearing condition is reduced bearing performance, and the other regions indicate that the bearing condition is a bearing failure;

[0026] S4. Judge the sigma intervals of all distance values: if there are other areas, bearing fault is taken as the result of the bearing health status; if there are no other areas and there are 3sigma intervals, bearing performance degradation is taken as the result of the bearing health status; if there are no other areas and 3sigma intervals, and the number of 2sigma intervals exceeds half, good is taken as the result of the bearing health status; if there are no other areas and 3sigma intervals, and the number of 1sigma intervals is greater than or equal to half, excellent is taken as the result of the bearing health status.

[0027] Further, in step S2, the distance dij between the i-th actual frequency spectrum sequence of the train running gear bearing vibration data and the predicted frequency sequence corresponding to the i-th IMF component predicted value in the j-th group of test data is calculated as follows:

[0028] dij=sqrt((Api j (f1)-Ai(f1)) 2 +(Api j (f2)-Ai(f2)) 2 +…+(Api j (fn)-Ai(fn)) 2 )

[0029] Among them, sqrt means square root; API j (f) represents the predicted frequency sequence corresponding to the predicted value of the ith IMF component in the jth test data set, Api j (f1),Api j (f2),…,Api j (fn) respectively represent API j(f) represents the 1st, 2nd, …, nth frequency components in Ai(f); Ai(f) represents the i-th actual frequency spectrum sequence of the train running gear bearing vibration data, and Ai(f1), Ai(f2), …, Ai(fn) represent the 1st, 2nd, …, nth frequency components in Ai(f), respectively.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] The present invention provides a bearing health assessment method and system based on the Mamba probability prediction model. The newly collected state data of the train running gear bearing vibration, temperature, etc. are input into the assessment model to obtain n distances dci between the prediction and the actual. The i data are matched in the probability density function obtained in step 2. By evaluating the health status of various bearing components such as the outer ring, inner ring, roller and retainer, the current health level of the various bearing components is obtained, providing a basis for maintenance. The assessment is performed at a steady speed to complete the health status assessment of the bearing components. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a flow chart of the steps of the method of the present invention;

[0033] Figure 2 A schematic diagram of the health status assessment of the present invention;

[0034] Figure 3 This is a structural principle diagram of the data monitoring module of the present invention;

[0035] Figure 4 It is a structural principle diagram of the microcontroller module of the present invention;

[0036] Figure 5 A circuit diagram of an overvoltage protection power supply module of the present invention;

[0037] Figure 6 A circuit diagram of a sensor signal conditioning circuit of the present invention;

[0038] Figure 7 A circuit diagram of a voltage signal conditioning circuit of the present invention;

[0039] Figure 8 A circuit diagram of a voltage-dividing follower filter circuit according to the present invention;

[0040] In the figure: a first diode Z1, a second diode Z2, a third diode Z3, a fourth diode Z4, a fifth diode Z5, a first resistor R1, a second resistor R2, a third resistor R3, a fourth resistor R4, a fifth resistor R5, a sixth resistor R6, a seventh resistor R7, an eighth resistor R8, a ninth resistor R9, a tenth resistor R10 and an eleventh resistor R11, a first capacitor C1, a second capacitor C2, a third capacitor C3, a first PMOS tube M1, a second PMOS tube M2, a third PMOS tube M3 and a fourth PMOS tube M4, a first operational amplifier U1, a second operational amplifier U2, a third operational amplifier U3 and a fourth operational amplifier U4. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purpose, features and advantages of the present invention more obvious and easy to understand, the specific implementation mode of the present invention is described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below. The technical features in each embodiment of the present invention can be combined accordingly without conflicting with each other.

[0042] In the description of the present invention, it is to be understood that when an element is considered to be "connected" to another element, it may be directly connected to the other element or indirectly connected, that is, there are intermediate elements. On the contrary, when an element is said to be "directly" connected to another element, there are no intermediate elements.

[0043] In the description of the present invention, it should be understood that the terms "first" and "second" are only used for the purpose of distinguishing descriptions, and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0044] In a preferred implementation of the present invention, a bearing health assessment system based on the Mamba probability prediction model is provided, which includes: a data monitoring module and a data processing module, the data monitoring module and the data processing module interact with each other, and the data processing module includes a prediction model acquisition module, an assessment model acquisition module, a health assessment module and a comprehensive judgment module.

[0045] like Figure 3As shown, the data monitoring module includes a vibration sensor, a temperature sensor, a multiplexing switch, a sensor signal conditioning circuit, a current signal conditioning circuit, a voltage signal conditioning circuit, a voltage divider follower filter circuit, an A / D converter, a microcontroller module, a wireless transmission module and an overvoltage protection power supply module. The vibration sensor and the temperature sensor are connected to the microcontroller module in sequence through the multiplexing switch, the sensor signal conditioning circuit, the current signal conditioning circuit, the voltage signal conditioning circuit, the voltage divider follower filter circuit and the A / D converter, and the wireless transmission module and the overvoltage protection power supply module are respectively connected to the microcontroller module.

[0046] It should be noted that in the present invention, the vibration sensor and the temperature sensor are used to collect vibration signal parameters and temperature parameters, the chip model of the multiplexer switch is AMC4601, which is used to select the output to the signal processing circuit through the multiplexer analog switch, and the current signal conditioning circuit is used for data preprocessing of the signal parameters, the A / D converter is used to input to AD7794 for digital-to-analog conversion, and the wireless transmission module is used for data transmission. During the operation of the train, the problem of effectively monitoring the health status assessment of the bearing components will be encountered. Therefore, the present invention designs a sensor signal conditioning circuit, a voltage signal conditioning circuit, a voltage division follower filter circuit, an overvoltage protection power supply module and a microcontroller module. The sensor signal conditioning circuit can perform data processing on the collected sensor signal parameters, the voltage signal conditioning circuit can process the sensor voltage signal, the voltage division follower filter circuit can pass through the voltage division follower filter circuit, and then input into the AD converter, and the voltage follower makes the circuit present high resistance input and low resistance output, thereby improving the circuit's load capacity. The overvoltage protection power supply module can improve power supply safety and provide overvoltage protection, and the microcontroller module can control the operation and collaboration of each module in real time. The specific implementation methods of the improved circuits and modules are introduced in detail below.

[0047] like Figure 4 As shown, the above-mentioned microcontroller module includes a data acquisition control module, a data interpretation module, a power supply circuit, a reset circuit, a crystal oscillator circuit, a data processing and RAM read-write module, an interface chip control unit, a synchronous clock control module, a command de-framing module, a configuration SPI Flash circuit and a download circuit; wherein, the data acquisition control module, the data interpretation module, the power supply circuit, the reset circuit, the crystal oscillator circuit, the interface chip control unit, the synchronous clock control module, the command de-framing module, the configuration SPI Flash circuit and the download circuit are respectively connected to the data processing and RAM read-write module.

[0048] It should be noted that in the microcontroller module of the present invention, the data acquisition control module is used for data acquisition control, the data interpretation module is used for data caching, the power supply circuit is used for power supply, the reset circuit is used for reset control, the data processing and RAM read-write module is used for data processing, the interface chip control unit is used for interface control, the synchronous clock control module is used for synchronous clock control, the command de-framing module is used for command de-framing control, the SPI Flash circuit is configured for serial peripheral device interface, and the download circuit is used for data download control. The present invention adopts the Spartan6 series FPGA of Xilinx company as the core control device, realizes the functions of data acquisition control, data caching, data processing, data storage, data transmission and synchronous clock control, and has the characteristics of high precision, fast speed, good reliability, strong real-time performance and low cost; the present invention uses FPGA as the main processor of the 16-channel real-time, high-speed and high-precision synchronous data acquisition system, the sampling frequency in the actual monitoring project is 200kHz, and the FPGA is used to reasonably control and coordinate the data flow transmission between each module, thereby realizing the real-time, synchronous and high-speed acquisition functions required by the system.

[0049] like Figure 5 As shown, the overvoltage protection power supply module includes a voltage source and an overvoltage protection circuit connected thereto. Specifically, the overvoltage protection circuit includes a first diode Z1, a second diode Z2, a third diode Z3, a fourth diode Z4, a fifth diode Z5, a first resistor R1, a second resistor R2, a third resistor R3, a first PMOS transistor M1, a second PMOS transistor M2, a third PMOS transistor M3 and a fourth PMOS transistor M4. The first diode Z1, the second diode Z2 and the third diode Z3 form a reference voltage circuit, which is used to generate a reference voltage according to the source voltage when the source voltage exceeds the clamping voltage; the fourth diode Z4, the fifth diode Z5, the first resistor R1, the second resistor R2, the third resistor R3, the first PMOS transistor M1, the second PMOS transistor M2, the third PMOS transistor M3 and the fourth PMOS transistor M4 form a feedback control circuit, which is used to receive the reference voltage and clamp the output voltage to the clamping voltage.

[0050] In the above overvoltage protection circuit, the anode of the first diode Z1 is connected to one end of the first resistor R1, the cathode of the first diode Z1 is connected to the cathode of the second diode Z2, the anode of the second diode Z2 is connected to the cathode of the third diode Z3, the anode of the third diode Z3 is respectively connected to one end of the second resistor R2, the anode of the fourth diode Z4, one end of the third resistor R3, the anode of the fifth diode Z5 and the source of the first PMOS tube M1, the other end of the first resistor R1 is respectively connected to the drain of the third PMOS tube M3, the gate of the third PMOS tube M3 and the gate of the fourth PMOS tube M4, the source of the third PMOS tube M3 is respectively connected to the source of the fourth PMOS tube M4, the drain of the second PMOS tube M2 and the drain of the first PMOS tube M1, the drain of the fourth PMOS tube M4 is respectively connected to the other end of the second resistor R2, the cathode of the fourth diode Z4 and the gate of the second PMOS tube M2, and the source of the second PMOS tube M2 is respectively connected to the other end of the third resistor R3, the cathode of the fifth diode Z5 and the gate of the first PMOS tube M1.

[0051] It should be noted that in the overvoltage protection circuit of the present invention, the third PMOS tube M3 and the fourth PMOS tube M4 form a current mirror for generating a reference current; the second PMOS tube M2 is used as a driving tube to generate a turn-on current of the first PMOS tube M1; the first PMOS tube M1 is a discharge tube for releasing surge current. The first diode Z1, the second diode Z2 and the third diode Z3 form a diode string. When the surge voltage is greater than the breakdown voltage of the diode string, the diode string generates a reference voltage, that is, Figure 5 The voltage value of Vx remains unchanged. At the same time, a reference current is generated on one side of the third PMOS tube M3, and the current is copied through the current mirror to act on the fourth PMOS tube M4. This current can raise the voltage across the second resistor R2 through the second resistor R2, so that the gate of the second PMOS tube M2 is greater than its threshold voltage, and the second PMOS tube M2 is turned on. After the second PMOS tube M2 is turned on, the driving current generated passes through the third resistor R3, raising the voltage across the third resistor R3, so that the main discharge device (the first PMOS tube M1) is turned on, and the first PMOS tube M1 can discharge a large amount of current, so that the entire chip is clamped at a certain voltage. Since the size of the first PMOS tube M1 is large, the second PMOS tube M2 is required to generate enough driving current to turn on the first PMOS tube M1.

[0052] Normally, a current of tens of microamperes is required to drive the discharge tube (the first PMOS tube M1). In addition, in order to improve the discharge efficiency of the first PMOS tube M1, the gate voltage of the first PMOS tube M1 can be appropriately raised. Raising the instantaneous gate voltage of the first PMOS tube M1 to exceed its maximum gate voltage is conducive to enhancing its discharge capability.

[0053] As the source voltage Vsource increases, more current is injected into the second PMOS tube M2, which further increases the gate voltage of the main clamping device (the first PMOS tube M1), thereby discharging more current and adjusting the output voltage of the regulator to the clamping voltage.

[0054] It can be seen that, by means of feedback control, the output voltage can be accurately clamped to the desired clamping voltage, regardless of the current discharged by the main clamping transistor (the first PMOS tube M1 ), and as a result, the final dynamic resistance of the overvoltage protection circuit can be made almost zero.

[0055] like Figure 6 As shown, the sensor signal conditioning circuit includes an analog signal input terminal, a fourth resistor R4, a fifth resistor R5, a first capacitor C1 and a first operational amplifier U1. The analog signal input terminal is respectively connected to one end of the fourth resistor R4 and one end of the fifth resistor R5, the other end of the fifth resistor R5 is connected to one end of the first capacitor C1, the other end of the first capacitor C1 is respectively connected to the other end of the fourth resistor R4 and the positive input terminal of the first operational amplifier U1, and the negative input terminal of the first operational amplifier U1 is connected to the output terminal of the first operational amplifier U1.

[0056] It should be noted that in the sensor signal conditioning circuit of the present invention, the operational amplifier is a key component of the conditioning circuit. This embodiment selects the AD8608 operational amplifier chip of ADI Company. The chip combines many excellent characteristics, has four-rail input and output while being powered by a single power supply, and can ensure high speed while also ensuring extremely low noise and input bias current, and is widely applicable to various circuits. Since the input impedance of the operational amplifier is generally very high, when the input pin is suspended, it is very susceptible to external interference. Therefore, the fifth resistor R5 is set to enable the input terminal to form a loop with the analog ground when the input pin is suspended, thereby ensuring the stability of the operational amplifier.

[0057] like Figure 7 As shown, the voltage signal conditioning circuit includes a voltage signal input terminal, a sixth resistor R6, a seventh resistor R7, an eighth resistor R8, a second capacitor C2 and a second operational amplifier U2, the voltage signal input terminal is connected to one end of the sixth resistor R6, the other end of the sixth resistor R6 is respectively connected to one end of the seventh resistor R7 and one end of the eighth resistor R8, the other end of the eighth resistor R8 is connected to one end of the second capacitor C2, the other end of the second capacitor C2 is respectively connected to the other end of the seventh resistor R7 and the positive input terminal of the second operational amplifier U2, and the negative input terminal of the second operational amplifier U2 is connected to the output terminal of the second operational amplifier U2.

[0058] It should be noted that in the voltage signal conditioning circuit of the present invention, the rail-to-rail operational amplifier can maximize the input and output voltage swings close to the power supply voltage value, but there is also a large deviation under high current conditions. Since the input voltage range of the chip AD8608 is 0-0.5V, the sixth resistor R6 and the eighth resistor R8 are set to form a voltage divider circuit to reduce the input voltage to below 5V.

[0059] According to the size of the current and the difference between AC and DC, the corresponding current acquisition methods are also different. Commonly used current acquisition methods include coaxial shunt method, current transformer method, Rogowski coil method, Hall sensor method and sampling resistor method, etc. The Hall sensor method is suitable for measuring both AC and DC currents, and can measure large currents. In the present invention, the current signal conditioning circuit adopts the ACS714 chip of Allegro Company, which is a current-isolated current sensor with common-mode suppression field effect, and is composed of high-precision low-bias linear Hall sensors. The maximum sampling current of the ACS714 chip is 5A.

[0060] The FGPA is used to control the analog switch to select the address switching channel to achieve the effect of time-sharing multiplexing. When switching channels, the analog switch will affect the change of the capacitive load, resulting in signal oscillation or ringing. The faster the analog switch switching speed, the more obvious this phenomenon is. Therefore, the selection of the analog switch is particularly important. By analyzing and comparing various types of analog switches, the present invention uses the ADG706 chip.

[0061] like Figure 8 As shown, the voltage divider follower filter circuit includes a third operational amplifier U3, a fourth operational amplifier U4, a third capacitor C3, a ninth resistor R9, a tenth resistor R10 and an eleventh resistor R11, the output end of the third operational amplifier U3 is connected to one end of the tenth resistor R10, the other end of the tenth resistor R10 is respectively connected to one end of the eleventh resistor R11 and the positive input end of the fourth operational amplifier U4, the other end of the eleventh resistor R11 is connected to the current signal conditioning circuit, the output end of the fourth operational amplifier U4 is connected to one end of the ninth resistor R9, the other end of the ninth resistor R9 is respectively connected to one end of the third capacitor C3 and the A / D converter, and the other end of the third capacitor C3 is grounded.

[0062] It should be noted that in the voltage-dividing follower filter circuit of the present invention, after the signal passes through the analog switch, it passes through the voltage-dividing follower filter circuit and is then input into the A / D converter. The voltage-dividing follower filter circuit makes the circuit present high-impedance input and low-impedance output, thereby improving the circuit's load capacity. The chip model of the third operational amplifier U3 and the fourth operational amplifier U4 is AD8031.

[0063] like Figure 1As shown, in a preferred implementation of the present invention, the bearing health assessment method based on the Mamba probability prediction model includes the following steps S1 to S4. The specific implementation process is described in detail below.

[0064] 1. Building a prediction model

[0065] S1. The vibration data and temperature status data of the train running gear bearing are used as input data. When there are n spectral frequencies of the fault characteristics, the input data is low-pass filtered and then variational mode decomposition (VMD) is used to generate n IMF components (i.e. IMF1, IMF2…IMFn). The train speed sequence r(t) is used as input and each IMF component is used as output to train the Mamba model.

[0066] 2. Building an Evaluation Model

[0067] S2. After obtaining the trained Mamba model, obtain a new train speed sequence and form m groups of test data. Input each group of test data into the trained Mamba model for prediction. Each group of test data corresponds to n IMF component prediction values. After performing fast Fourier transform (FFT) on the n IMF component prediction values ​​of each group of test data, each IMF component prediction value corresponds to a prediction frequency sequence, that is, the n prediction frequency sequences corresponding to the n IMF component prediction values ​​of a group of test data are recorded as Ap1(f), Ap2(f),…, Apn(f). After performing variational mode decomposition (VMD) and fast Fourier transform (FFT) on the train running gear bearing vibration data, each IMF component of the train running gear bearing vibration data corresponds to an actual spectrum sequence, that is, the train running gear bearing vibration data itself corresponds to n actual spectrum sequences, namely A1(f), A2(f),…, An(f). The distances between the actual spectrum sequence of the train running gear bearing vibration data and each predicted frequency sequence are calculated in turn. The distances corresponding to the predicted frequency sequences with the same IMF component prediction value index constitute a distance sequence that obeys the normal distribution. The mean of each distance sequence is estimated as the expectation of a normal distribution, and the variance of each distance sequence is taken as the variance of a normal distribution. The evaluation model is constructed by all the obtained normal distributions.

[0068] It should be noted that, in step S2 of the present invention, the distance dij between the i-th actual frequency spectrum sequence of the train running gear bearing vibration data and the predicted frequency sequence corresponding to the i-th IMF component predicted value in the j-th group of test data is calculated as follows:

[0069] dij=sqrt((Api j (f1)-Ai(f1)) 2 +(Api j(f2)-Ai(f2)) 2 +…+(Api j (fn)-Ai(fn)) 2 )

[0070] Among them, sqrt means square root; API j (f) represents the predicted frequency sequence corresponding to the predicted value of the ith IMF component in the jth test data set, Api j (f1),Api j (f2),…,Api j (fn) respectively represent API j (f) represents the 1st, 2nd, …, nth frequency components in Ai(f); Ai(f) represents the i-th actual frequency spectrum sequence of the train running gear bearing vibration data, and Ai(f1), Ai(f2), …, Ai(fn) represent the 1st, 2nd, …, nth frequency components in Ai(f), respectively.

[0071] 3. Health Assessment

[0072] S3. Obtain the distance values ​​between each predicted frequency sequence in the train speed sequence to be detected and the actual frequency spectrum sequence of the train running gear bearing vibration data, and divide each normal distribution into four regions representing the bearing health level according to the 1sigma interval, 2sigma interval, and 3sigma interval, and substitute each distance value into each normal distribution in the evaluation model to obtain the sigma interval in which each distance value is located; wherein, the 1sigma interval (i.e. Figure 2 The area corresponding to ①) in the figure indicates that the bearing condition is excellent, and the 2sigma interval (i.e. Figure 2 The area corresponding to ② in the figure indicates that the bearing is in good condition. The 3sigma interval (i.e. Figure 2 The area corresponding to ③) in the figure indicates that the bearing condition is that the bearing performance is reduced. The other areas (i.e. Figure 2 ④) in the figure indicates that the bearing status is a bearing failure.

[0073] 4. Comprehensive judgment

[0074] S4. After step S3, the sigma intervals of all distance values ​​are judged: if there are other areas, bearing fault is taken as the result of the determination of the bearing health status; if there are no other areas and there are 3sigma intervals, bearing performance degradation is taken as the result of the determination of the bearing health status; if there are no other areas and 3sigma intervals at the same time, and the number of 2sigma intervals exceeds half, good is taken as the result of the determination of the bearing health status; if there are no other areas and 3sigma intervals at the same time, and the number of 1sigma intervals is greater than or equal to half, excellent is taken as the result of the determination of the bearing health status.

[0075] The above-described embodiment is only a preferred solution of the present invention, but it is not intended to limit the present invention. A person skilled in the relevant technical field may make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, any technical solution obtained by equivalent replacement or equivalent transformation falls within the protection scope of the present invention.

Claims

1. A bearing health assessment system based on the Mamba probability prediction model, characterized in that: include: A data monitoring module is used to obtain the vibration data and temperature status data of the train running gear bearing in real time, which includes a vibration sensor, a temperature sensor, a multiplexing switch, a sensor signal conditioning circuit, a current signal conditioning circuit, a voltage signal conditioning circuit, a voltage-dividing follower filter circuit, an A / D converter, a microcontroller module, a wireless transmission module and an overvoltage protection power supply module. The vibration sensor and the temperature sensor are connected to the microcontroller module after passing through the multiplexing switch, the sensor signal conditioning circuit, the current signal conditioning circuit, the voltage signal conditioning circuit, the voltage-dividing follower filter circuit and the A / D converter in sequence, and the wireless transmission module and the overvoltage protection power supply module are connected to the microcontroller module respectively; The data processing module is used to process the train running gear bearing vibration data and temperature status data obtained by the data monitoring module to complete the health status assessment of the bearing components. It includes a prediction model acquisition module, an assessment model acquisition module, a health assessment module and a comprehensive judgment module.

2. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The prediction model acquisition module is used to take the vibration data and temperature status data of the train running gear bearing as input data. When there are n spectral frequencies of the fault characteristics, the input data is low-pass filtered and then variational mode decomposition is used to generate n IMF components. The train speed sequence is taken as input and each IMF component is used as output to train the Mamba model; The evaluation model acquisition module is used to obtain a new train speed sequence and form m groups of test data after obtaining the trained Mamba model, input each group of test data into the trained Mamba model for prediction, obtain n IMF component prediction values ​​for each group of test data, perform fast Fourier transform on the n IMF component prediction values ​​of each group of test data, and obtain a prediction frequency sequence for each IMF component prediction value, perform variational modal decomposition and fast Fourier transform on the train running gear bearing vibration data, and obtain an actual spectrum sequence for each IMF component of the train running gear bearing vibration data, calculate the distance between the actual spectrum sequence of the train running gear bearing vibration data and each prediction frequency sequence in turn, and form a distance sequence that obeys a normal distribution from the distances corresponding to the prediction frequency sequences with the same IMF component prediction value index, and estimate the mean of each distance sequence as the expectation of a normal distribution, and take the variance of each distance sequence as the variance of a normal distribution, and form an evaluation model from all the obtained normal distributions; The health assessment module is used to obtain the distance value between each predicted frequency sequence in the train speed sequence to be detected and the actual frequency spectrum sequence of the train running gear bearing vibration data, and divide each normal distribution into four areas representing the bearing health level according to the 1sigma interval, the 2sigma interval, and the 3sigma interval, and substitute each distance value into each normal distribution in the assessment model to obtain the sigma interval in which each distance value is located; wherein, the area corresponding to the 1sigma interval indicates that the bearing state is excellent, the area corresponding to the 2sigma interval indicates that the bearing state is good, the area corresponding to the 3sigma interval indicates that the bearing state is reduced bearing performance, and other areas indicate that the bearing state is a bearing failure; The comprehensive judgment module is used to judge the sigma intervals in which all distance values ​​are located: if there are other areas, bearing fault is taken as the judgment result of the bearing health state; if there are no other areas and there are 3sigma intervals, bearing performance degradation is taken as the judgment result of the bearing health state; if there are no other areas and 3sigma intervals at the same time, and the number of 2sigma intervals exceeds half, good is taken as the judgment result of the bearing health state; if there are no other areas and 3sigma intervals at the same time, and the number of 1sigma intervals is greater than or equal to half, excellent is taken as the judgment result of the bearing health state.

3. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The microcontroller module includes a data acquisition control module, a data interpretation module, a power supply circuit, a reset circuit, a crystal oscillator circuit, a data processing and RAM read-write module, an interface chip control unit, a synchronous clock control module, a command deframing module, a configuration SPI Flash circuit and a download circuit; wherein the data acquisition control module, the data interpretation module, the power supply circuit, the reset circuit, the crystal oscillator circuit, the interface chip control unit, the synchronous clock control module, the command deframing module, the configuration SPI Flash circuit and the download circuit are each connected to the data processing and RAM read-write module.

4. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The overvoltage protection power supply module comprises a voltage source and an overvoltage protection circuit connected thereto, wherein the overvoltage protection circuit comprises a first diode (Z1), a second diode (Z2), a third diode (Z3), a fourth diode (Z4), a fifth diode (Z5), a first resistor (R1), a second resistor (R2), a third resistor (R3), a first PMOS transistor (M1), a second PMOS transistor (M2), a third PMOS transistor (M3) and a fourth PMOS transistor (M4); wherein the first diode (Z1), the second diode (Z2) and the third diode (Z3) constitute a reference voltage circuit, which is used to generate a reference voltage according to the source voltage when the source voltage exceeds a clamping voltage; and the fourth diode (Z4), the fifth diode (Z5), the first resistor (R1), the second resistor (R2), the third resistor (R3), the first PMOS transistor (M1), the second PMOS transistor (M2), the third PMOS transistor (M3) and the fourth PMOS transistor (M4) constitute a feedback control circuit, which is used to receive the reference voltage and clamp the output voltage to the clamping voltage.

5. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 3, characterized in that: In the overvoltage protection circuit, the anode of the first diode (Z1) is connected to one end of the first resistor (R1), the cathode of the first diode (Z1) is connected to the cathode of the second diode (Z2), the anode of the second diode (Z2) is connected to the cathode of the third diode (Z3), the anode of the third diode (Z3) is respectively connected to one end of the second resistor (R2), the anode of the fourth diode (Z4), one end of the third resistor (R3), the anode of the fifth diode (Z5) and the source of the first PMOS tube (M1), and the other end of the first resistor (R1) is respectively connected to the drain of the third PMOS tube (M3), ... The gate of the S transistor (M3) and the gate of the fourth PMOS transistor (M4), the source of the third PMOS transistor (M3) are respectively connected to the source of the fourth PMOS transistor (M4), the drain of the second PMOS transistor (M2) and the drain of the first PMOS transistor (M1), the drain of the fourth PMOS transistor (M4) are respectively connected to the other end of the second resistor (R2), the cathode of the fourth diode (Z4) and the gate of the second PMOS transistor (M2), and the source of the second PMOS transistor (M2) are respectively connected to the other end of the third resistor (R3), the cathode of the fifth diode (Z5) and the gate of the first PMOS transistor (M1).

6. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The sensor signal conditioning circuit comprises an analog signal input terminal, a fourth resistor (R4), a fifth resistor (R5), a first capacitor (C1) and a first operational amplifier (U1); the analog signal input terminal is respectively connected to one end of the fourth resistor (R4) and one end of the fifth resistor (R5); the other end of the fifth resistor (R5) is connected to one end of the first capacitor (C1); the other end of the first capacitor (C1) is respectively connected to the other end of the fourth resistor (R4) and the positive input terminal of the first operational amplifier (U1); and the negative input terminal of the first operational amplifier (U1) is connected to the output terminal of the first operational amplifier (U1).

7. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The voltage signal conditioning circuit comprises a voltage signal input terminal, a sixth resistor (R6), a seventh resistor (R7), an eighth resistor (R8), a second capacitor (C2) and a second operational amplifier (U2), wherein the voltage signal input terminal is connected to one end of the sixth resistor (R6), the other end of the sixth resistor (R6) is respectively connected to one end of the seventh resistor (R7) and one end of the eighth resistor (R8), the other end of the eighth resistor (R8) is connected to one end of the second capacitor (C2), the other end of the second capacitor (C2) is respectively connected to the other end of the seventh resistor (R7) and the positive input terminal of the second operational amplifier (U2), and the negative input terminal of the second operational amplifier (U2) is connected to the output terminal of the second operational amplifier (U2).

8. A bearing health assessment system based on the Mamba probability prediction model as claimed in claim 1, characterized in that: The voltage-divider follower filter circuit comprises a third operational amplifier (U3), a fourth operational amplifier (U4), a third capacitor (C3), a ninth resistor (R9), a tenth resistor (R10) and an eleventh resistor (R11); the output end of the third operational amplifier (U3) is connected to one end of the tenth resistor (R10); the other end of the tenth resistor (R10) is respectively connected to one end of the eleventh resistor (R11) and the positive input end of the fourth operational amplifier (U4); the other end of the eleventh resistor (R11) is connected to a current signal conditioning circuit; the output end of the fourth operational amplifier (U4) is connected to one end of the ninth resistor (R9); the other end of the ninth resistor (R9) is respectively connected to one end of the third capacitor (C3) and an A / D converter; and the other end of the third capacitor (C3) is grounded.

9. A bearing health assessment method based on the Mamba probability prediction model, characterized in that: The following steps are involved: S1. The vibration data and temperature status data of the train running gear bearing are used as input data. When there are n spectral frequencies of the fault characteristics, the input data is low-pass filtered and then used for variational mode decomposition to generate n IMF components. The train speed sequence is used as input and each IMF component is used as output to train the Mamba model to obtain a trained Mamba model; S2. After obtaining the trained Mamba model, obtain a new train speed sequence and form m groups of test data. Input each group of test data into the trained Mamba model for prediction. Obtain n IMF component prediction values ​​for each group of test data. After performing fast Fourier transform on the n IMF component prediction values ​​of each group of test data, obtain a prediction frequency sequence for each IMF component prediction value. After performing variational modal decomposition and fast Fourier transform on the train running gear bearing vibration data, obtain an actual spectrum sequence for each IMF component of the train running gear bearing vibration data. Calculate the distance between the actual spectrum sequence of the train running gear bearing vibration data and each prediction frequency sequence in turn. Constitute a distance sequence that obeys a normal distribution from the distances corresponding to the prediction frequency sequences with the same IMF component prediction value index. Estimate the mean of each distance sequence as the expectation of a normal distribution. Take the variance of each distance sequence as the variance of a normal distribution. Constitute an evaluation model from all the obtained normal distributions. S3. Obtain the distance values ​​between each predicted frequency sequence in the train speed sequence to be detected and the actual frequency spectrum sequence of the train running gear bearing vibration data, and divide each normal distribution into four regions representing the bearing health level according to the 1sigma interval, the 2sigma interval, and the 3sigma interval, and substitute each distance value into each normal distribution in the evaluation model to obtain the sigma interval in which each distance value is located; wherein, the region corresponding to the 1sigma interval indicates that the bearing condition is excellent, the region corresponding to the 2sigma interval indicates that the bearing condition is good, the region corresponding to the 3sigma interval indicates that the bearing condition is reduced bearing performance, and the other regions indicate that the bearing condition is a bearing failure; S4. Judge the sigma intervals of all distance values: if there are other areas, bearing fault is taken as the result of the bearing health status; if there are no other areas and there are 3sigma intervals, bearing performance degradation is taken as the result of the bearing health status; if there are no other areas and 3sigma intervals, and the number of 2sigma intervals exceeds half, good is taken as the result of the bearing health status; if there are no other areas and 3sigma intervals, and the number of 1sigma intervals is greater than or equal to half, excellent is taken as the result of the bearing health status.

10. A bearing health assessment method based on the Mamba probability prediction model as claimed in claim 9, characterized in that: In step S2, the distance dij between the ith actual frequency spectrum sequence of the train running gear bearing vibration data and the predicted frequency sequence corresponding to the ith IMF component predicted value in the jth group of test data is calculated as follows: dij=sqrt((Api j (f1)-Ai(f1)) 2 +(Api j (f2)-Ai(f2)) 2 +...+(Api j (fn)-Ai(fn)) 2 ) Among them, sqrt means square root; API j (f) represents the predicted frequency sequence corresponding to the predicted value of the ith IMF component in the jth test data set, Api j (f1), API j (f2),…,Api j (fn) respectively represent API j (f) represents the 1st, 2nd, …, nth frequency components in Ai(f); Ai(f) represents the i-th actual frequency spectrum sequence of the train running gear bearing vibration data, and Ai(f1), Ai(f2), …, Ai(fn) represent the 1st, 2nd, …, nth frequency components in Ai(f), respectively.

Images