Passive wireless motor train unit brake disc bolt pre-tightening force real-time monitoring assembly, device and system

Abstract

The invention discloses a passive and wireless motor train unit brake disc bolt pre-tightening force real-time monitoring assembly, device and system, and belongs to the technical field of rail transit intelligent operation and maintenance operation safety monitoring, and the brake disc bolt pre-tightening force real-time monitoring assembly comprises a brake disc bolt body. A mandrel which is arranged in the extending direction of a screw rod and used for sensing the pretightening force change of the brake disc bolt body is packaged in the screw rod of the bolt body, and a sensor connected with the mandrel and a signal processor connected with the sensor are packaged in a screw head of the bolt body. According to the passive wireless motor train unit brake disc bolt pre-tightening force real-time monitoring assembly, device and system, the change condition of the brake disc bolt pre-tightening force in operation is monitored in real time, the monitoring precision is high, the timeliness is high, the maintenance cost is low, and operation and application are convenient.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent operation and maintenance of rail transit and operation safety detection, and specifically relates to a passive wireless EMU brake disc bolt preload real-time monitoring component, device and system thereof. Background Art

[0002] As a key core component of the EMU braking system, the brake disc is mainly composed of a disc hub, a friction disc, a pressure ring and other components, which are fastened and connected by multiple bolts evenly distributed around the circumference. When the EMU brakes, the brake disc is subjected to the thermomechanical coupling of the brake pad pressure, friction and friction heat, which causes a drastic change in the preload force of the connecting bolts, resulting in varying degrees of looseness and fatigue damage, reducing the reliability of the brake disc and posing a serious threat to the operation safety of the EMU. There are even catastrophic accidents caused by the breaking of the connecting bolts, resulting in the fall of the brake disc. Therefore, in the field of rail transit, real-time and effective monitoring of the preload force of the brake disc bolts is of great significance for improving the efficiency of daily maintenance of the EMU braking system and ensuring driving safety.

[0003] At present, the commonly used monitoring methods for bolt preload detection include: image recognition method, symbol marking method, vibration detection method, etc. However, these methods are difficult to achieve effective detection for EMU brake disc bolt preload detection. The main reasons are as follows:

[0004] 1) The service environment of EMU brake disc bolts is harsh. During long-term service, the symbols marked by image recognition method, symbol marking method, etc. will be blocked by dirt or fall off, making it difficult to use them effectively;

[0005] 2) The brake disc of the EMU has a complex structure and strong vibration noise. The vibration response signal generated by the brake disc bolts in the loose and tight states is very small, which makes it difficult to distinguish the tightness of the brake disc bolts using the vibration detection method.

[0006] 3) Under the influence of complex external environmental forces and thermal factors, the variation of bolt load is extremely complex. At present, there is a lack of real-time online monitoring means for the variation of brake disc bolt preload during operation. Summary of the invention

[0007] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a passive wireless EMU brake disc bolt preload real-time monitoring component, device and system thereof, which have high monitoring accuracy, high real-time performance and low maintenance cost.

[0008] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0009] In a first aspect, the present invention provides a passive wireless EMU brake disc bolt preload real-time monitoring component, comprising a brake disc bolt body, a screw rod of the bolt body encapsulating a core shaft arranged along the extension direction of the screw rod and used to sense changes in the preload force of the brake disc bolt body, a screw head of the bolt body encapsulating a sensor connected to the core shaft and a signal processor connected to the sensor.

[0010] Furthermore, a packaging groove and a core groove are sequentially opened from the screw head to the screw rod, which are interconnected and located on the same axis as the bolt body, the diameter of the packaging groove is larger than the diameter of the core groove, and a spacing is reserved between the bottom of the core groove and the top of the screw rod;

[0011] The sensor and the signal processor are installed in the packaging groove from the inside to the outside in sequence, the core shaft is matched and embedded in the core groove coated with grease on all sides and connected to the sensor in the packaging groove, and a protective cover that is annularly wrapped around the sensor and the signal processor and a protective cover that matches the size of the notch of the packaging groove and is flush are installed circumferentially in the packaging groove.

[0012] In a first aspect, the present invention provides a passive wireless EMU brake disc bolt preload real-time monitoring device, comprising:

[0013] Display terminal,

[0014] Multiple repeaters, each of which is interconnected;

[0015] And multiple passive wireless EMU brake disc bolt preload real-time monitoring components as described in the first aspect, and the repeaters and monitoring components are connected one-to-one, and each repeater receives the bolt preload status signal sent by the corresponding monitoring component and converges it to the display terminal.

[0016] Furthermore, the repeater includes a temperature difference power generation module, an energy storage module, a control module and a remote transmission module;

[0017] The temperature difference power generation module is connected to the energy storage module through a conversion circuit and is connected to the control module through a trigger circuit; the control module is respectively connected to the energy storage module, the monitoring component and the remote transmission module; the energy storage module is respectively connected to the monitoring component and the remote transmission module.

[0018] Furthermore, the trigger circuit determines whether the disc brake device is in a working state based on whether the temperature difference power generation module generates electricity. If it is in a working state, the temperature difference power generation module generates electrical energy, and the trigger circuit sends a trigger signal to the control module so that the control module responds and enters a timed wake-up mode.

[0019] Furthermore, when the disc brake device is in a non-operating state, the temperature difference power generation module does not generate electric energy, and the control module and the remote transmission module are in a sleep mode;

[0020] When the disc brake device is in working state, the control module is in timed wake-up mode with T c It wakes up at time intervals and transmits acquisition control commands to the sensor. s The time interval wakes up the remote sending module to transmit the wake-up control command and the brake disc bolt preload data to be sent, where T s =nT c , n is a positive integer; so that the remote sending module responds after receiving the wake-up control command and enters the sending mode from the sleep mode, and after receiving the brake disc bolt preload force data, sends the brake disc bolt preload force data out, and enters the sleep mode again to wait for the next wake-up control command.

[0021] Furthermore, the monitoring component is configured with a signal receiving unit and a signal processing unit;

[0022] The signal receiving unit is used to receive a bolt preload state signal collected after the brake disc bolt is axially deformed;

[0023] The signal processing unit pre-trains the bolt preload state signal, performs abnormal data screening, sequence correlation and decomposition processing, wavelet packet decomposition, and frequency band energy screening to obtain a historical feature vector; the historical feature vector is input into a support vector machine classification model for training to obtain a bolt state detection model, and a brake disc bolt preload monitoring signal is obtained.

[0024] Further, screening to obtain historical feature vectors and inputting the historical feature vectors into a support vector machine classification model for training to obtain a bolt state detection model includes the following steps:

[0025] The sensor collects the resistance change signal caused by the axial deformation of the bolt in real time and converts it into a voltage signal of 0-5V. The instrument amplifier gain amplifies the signal by 100 times, and the low-pass filter is used to set the cutoff frequency to 2kHz to remove high-frequency noise. The 16-bit ADC module is used to convert the analog signal into a digital signal with a resolution of 0.076mV / LSB.

[0026] The mean μ and standard deviation δ of 10,000 data points in the window are calculated with a window length of 1 second. If a data point is out of the range of μ±3δ, it is marked as an abnormality and the abnormal value is replaced by linear interpolation.

[0027] The linear trend term is fitted using the least square method and subtracted from the original signal; the digital signal after subtraction is decomposed into six intrinsic mode functions IMF, and the low-frequency components IMF1-IMF3 related to the preload force are extracted;

[0028] The preprocessed digital signal is decomposed into 16 sub-bands by performing 4-layer wavelet packet decomposition. The energy value of each sub-band signal is calculated, and the frequency bands with the top 3 energy proportions are selected to form the feature vector.

[0029] The mean, variance and peak factor of the time domain features and the frequency domain features are used to select the energy values ​​of three frequency bands and construct a 6-dimensional historical feature vector F:

[0030]

[0031] Where μ is the mean; δ is the standard deviation; and peak factor Energy value x i represents the energy of the sub-band signal, i represents the sub-band number, K takes the value [1, N], and N is the number of data points of each sub-band signal;

[0032] The training set and test set were divided into 7:3, and the hyperparameters of the support vector machine (SVM) model were optimized using 5-fold cross validation. The model was trained using the training set and evaluated using the test set: the accuracy was ≥ 98.5% and the diagonal proportion of the confusion matrix was > 97%;

[0033] The real-time feature vector is input into the trained support vector machine (SVM) model, and combined with the preset alarm threshold, the bolt preload state is judged and output;

[0034] When the preload drops by >15% of the rated value, the bolt preload state is loose;

[0035] When the preload force rises > 10% of the rated value, the bolt preload force state is overtightened;

[0036] For the rest, the bolt preload status is normal;

[0037] When the number of newly added data is ≥500 within a period of time, model fine-tuning is triggered and the support vector is updated; if the model accuracy is <95% for three consecutive tests, full retraining is started.

[0038] In a third aspect, the present invention provides a brake disc system, comprising:

[0039] Hub,

[0040] Friction disc,

[0041] Pressure ring,

[0042] and the passive wireless EMU brake disc bolt preload force real-time monitoring assembly as described in the first aspect, or the passive wireless EMU brake disc bolt preload force real-time monitoring device as described in any one of the second aspects;

[0043] The disc hub, friction disc and pressure ring are assembled through the monitoring component, gaskets and nuts matching the monitoring component, and are press-fitted onto the brake disc seat of the axle through interference fit.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1) The present invention uses direct measurement of bolt deformation to sense the brake disc bolt preload force signal, thereby avoiding the transmission error and environmental noise influence during indirect measurement.

[0046] 2) The control module in the brake disc bolt preload force monitoring device enters the timed wake-up mode through the trigger signal sent by the trigger circuit. When the disc brake device stops working, the brake disc bolt preload force monitoring device is in sleep mode and will not consume too much power when it is not necessary to collect and send the brake disc bolt preload force data; at the same time, as soon as the disc brake device enters the working state, the trigger circuit immediately sends a trigger signal to the control module, and then the brake disc bolt preload force monitoring device sends the brake disc bolt preload force data online in real time.

[0047] 3) The system power consumption of the present invention in sleep mode is only a few microamperes, which can effectively ensure that the power of the energy storage module of the brake disc bolt preload monitoring device is always maintained within the voltage range for the normal operation of the system. In the timed wake-up working state, the electric energy generated by the temperature difference power generation module converting vibration heat energy can continuously charge the energy storage module, so that the brake disc bolt preload monitoring device can work for a long time.

[0048] 4) This brake disc bolt preload monitoring device adopts wireless data transmission, is easy to disassemble and assemble, and has low maintenance cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of a relay network operation provided by an embodiment of the present invention.

[0050] Figure 2 A block diagram of a device for real-time monitoring of bolt preload provided in an embodiment of the present invention.

[0051] Figure 3 A flow chart of a brake disc bolt looseness signal processing provided by an embodiment of the present invention.

[0052] Figure 4 A structural diagram of a brake disc system provided in an embodiment of the present invention.

[0053] Figure 5 A structural diagram of a monitoring component provided in an embodiment of the present invention.

[0054] In the figure:

[0055] 1. Disc hub; 2. Friction disc; 3. Pressure ring; 4. Monitoring assembly; 5. Gasket; 6. Nut; 7. Protective cover; 8. Protective sleeve; 9. Signal processor; 10. Sensor; 11. Grease; 12. Mandrel; 13. Bolt body. DETAILED DESCRIPTION

[0056] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0057] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0058] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0059] Example

[0060] In order to detect the preload of the brake disc bolt, the elongation of the brake disc bolt is monitored in real time. When the elongation of the brake disc bolt changes, the bolt elongation can be collected by the sensor to obtain a corresponding electrical signal, which can represent the preload state of the bolt.

[0061] The monitoring component provided in the embodiment of the present invention directly monitors the preload state of the brake disc bolts through the elongation of the brake disc bolts, and can effectively distinguish the preload state of the brake disc bolts. The detection accuracy is not affected by mechanical vibration loads and braking thermal loads, thereby ensuring the reliability of the brake disc bolt preload detection and further ensuring the safe and stable operation of the EMU.

[0062] like Figure 1 As shown, the real-time monitoring device includes multiple monitoring components, a repeater and a display terminal.

[0063] When testing the brake disc bolt preload, the monitoring component is encapsulated in the bolt that fixes the brake disc to collect the bolt preload data in real time and send the bolt preload data to the corresponding repeater. The repeater receives the bolt preload data in the corresponding monitoring component, sends it through the remote sending module, and converges it to the display terminal. The display terminal is used to receive the bolt preload data transmitted by the repeater network and display it on the screen.

[0064] In this embodiment, a plurality of monitoring components are provided to collect the bolt elongation in real time and send the brake disc bolt elongation data to the corresponding repeater.

[0065] Among them, the repeater includes a temperature difference power generation module, an energy storage module, a control module and a remote transmission module.

[0066] The repeater network is used for data transmission and consists of multiple repeaters. Each repeater receives the bolt elongation data sent by the remote sending module in the corresponding monitoring component and then gathers it to the display terminal. Each repeater only communicates with the corresponding monitoring component, and the repeater uses STM32F103C8T6 as the main control.

[0067] In this embodiment, a response relationship is set between the repeater network and the display terminal. After the repeater N sends the brake disc bolt preload data to the display terminal, the display terminal will send a response instruction back to the repeater N to confirm that the brake disc bolt preload data has indeed been received and displayed. If the repeater N does not receive the response instruction, the repeater N will send the brake disc bolt preload data again.

[0068] The repeater network is composed of multiple repeaters connected to each other, and each repeater is interconnected. When repeater N receives the brake disc bolt preload data sent by the brake disc bolt preload monitoring device N, repeater N sends the brake disc bolt preload data to repeater N1, and repeater N1 then sends the brake disc bolt preload data to repeater N2 until repeater 1 receives the brake disc bolt preload data.

[0069] like Figure 2As shown, the bolt preload monitoring device generates electricity from the temperature difference power generation module and stores it in the energy storage module. When the system is working, it supplies power to the control module, monitoring component and remote transmission module. The working status of the monitoring component and the temperature difference power generation module is controlled according to the instructions of the control module.

[0070] In this embodiment, the temperature difference power generation module is installed on the brake disc pressure ring, connected to the energy storage module through a conversion circuit, and connected to the control module through a trigger circuit.

[0071] The trigger circuit includes a rectifier bridge, a voltage regulator tube, a front-end capacitor and a switch circuit connected in sequence. The switch circuit is connected to the control module. The trigger circuit determines whether the disc brake device is in a working state according to whether the temperature difference power generation module generates electricity. If it is in a working state, the temperature difference power generation module generates electric energy, and the trigger circuit sends a trigger signal to the control module.

[0072] The control module is connected with the energy storage module, the monitoring component and the remote sending module respectively.

[0073] The control module includes two working modes, specifically:

[0074] 1) Sleep mode

[0075] When the disc brake device is not in operation, the control unit is in a low-power sleep mode;

[0076] 2) Scheduled wake-up mode

[0077] When the disc brake device is in operation, the control unit is in acquisition mode, with T c It wakes up at time intervals and transmits acquisition control commands to the sensor. s The time interval wakes up the remote sending module to transmit the wake-up control command and the brake disc bolt preload data to be sent, where T s =nT c , n is a positive integer.

[0078] The energy storage module is connected with the monitoring component and the remote sending module respectively.

[0079] When the disc brake device is in a non-working state, the temperature difference power generation module does not generate electricity, and the control module and the remote transmission module are in a dormant mode. When the disc brake device enters a working state, the internal control process of the brake disc bolt preload monitoring device includes the following steps:

[0080] The disc brake device starts working, and the friction of the brake disc generates heat and produces a temperature difference; the temperature difference power generation module converts the temperature difference energy of the brake disc into electrical energy; part of the electrical energy converted by the temperature difference power generation module is stored in the energy storage module through the conversion circuit to power the remote transmission module, monitoring components and control module, and the other part of the electrical energy sends a trigger signal to the control module through the trigger circuit; the control module enters the timed wake-up mode after receiving the trigger signal sent by the trigger circuit. In the timed wake-up mode, the control module is still in sleep mode, but with T c The sensor is woken up at a time interval and transmits a collection control command to the sensor; after receiving the collection control command, the sensor collects the brake disc bolt preload data, and returns the bolt preload data to the control module after the collection is completed.

[0081] In the timed wake-up mode of the control module, T s The remote sending module is woken up at a time interval to transmit a wake-up control command and the brake disc bolt preload data to be sent; after receiving the wake-up control command, the remote sending module enters the sending mode from the sleep mode; after receiving the brake disc bolt preload data, the remote sending module sends the brake disc bolt preload data, and then enters the sleep mode again to wait for the next wake-up control command.

[0082] In this embodiment, the monitoring component is configured with a signal receiving unit and a signal processing unit.

[0083] The signal receiving unit is used to receive the bolt preload state signal collected after the brake disc bolt generates axial deformation;

[0084] like Figure 3 As shown, during the monitoring process of the brake disc bolt preload force status, the signal processing unit pre-trains the bolt preload force signal, screens out abnormal data, performs sequence correlation and decomposition processing, wavelet packet decomposition, and frequency band energy screening to obtain a historical feature vector; the historical feature vector is input into the support vector machine classification model for training to obtain the brake disc bolt status detection result.

[0085] In this embodiment, by combining wavelet packet decomposition with SVM, the classification accuracy is improved by more than 20%; the whole process processing time is less than 50ms, which meets the real-time monitoring requirements of EMU braking; the signal processor adopts dynamic voltage regulation (DVS) and the power consumption is less than 10mW.

[0086] In this embodiment, the brake disc bolt preload force signal processing unit preprocesses the bolt preload force signal and inputs the historical feature vector into the support vector machine classification model for training, including the following steps:

[0087] Step 1: Signal acquisition and preprocessing

[0088] According to the vibration characteristics of the EMU brake disc, the sampling frequency is set to 10kHz, and the appropriate sensor type is selected: MEMS piezoresistive sensor, and the parameters are set to sensitivity: 2mV / N, range: 0~20kN.

[0089] The sensor collects the resistance change signal caused by the axial deformation of the bolt in real time and converts it into a voltage signal (0-5V). The signal is amplified by an instrument amplifier (gain: 100 times); at the same time, a low-pass filter (cut-off frequency: 2kHz) is used to remove high-frequency noise.

[0090] A 16-bit ADC module is used to convert analog signals into digital signals with a resolution of 0.076mV / LSB.

[0091] Step 2: Screening out abnormal data

[0092] The sliding window detection method is used, with a window length of 1 second (including 10,000 data points), to calculate the mean (μ) and standard deviation (δ) of the data in the window; and the calculation results are judged as abnormal: if a data point exceeds the range of μ±3δ, it is marked as abnormal; linear interpolation is used to replace the abnormal value to ensure data continuity.

[0093] Step 3: Serial Correlation and Decomposition Processing

[0094] The linear trend term is fitted using the least squares method and subtracted from the original signal. The signal is decomposed into six intrinsic mode functions (IMFs) and the low-frequency components (IMF1-IMF3) related to the preload are extracted.

[0095] Step 4: Wavelet packet decomposition and frequency band energy screening

[0096] The parameters of wavelet packet decomposition are set as follows: db4 (Daubechies 4th order) of wavelet basis function; 4 decomposition layers, generating 16 frequency bands; the frequency band is selected as 1.5-3kHz. Experiments have verified that the energy of this frequency band is strongly correlated with the change of bolt preload.

[0097] The preprocessed signal is decomposed into 4 layers to obtain 16 sub-bands, and the energy value of each sub-band signal is calculated:

[0098]

[0099] The top three frequency bands with the highest energy share (such as sub-bands 5, 7, and 9) are selected to form a feature vector.

[0100] Step 5: Historical feature vector construction

[0101] Select time domain features: mean, variance, peak factor, total 3 dimensions; select frequency domain features: select 3 frequency band energy values, total 3 dimensions; construct a 6-dimensional historical feature vector F based on time domain features and frequency domain features:

[0102]

[0103] Where μ is the mean; δ is the standard deviation; and peak factor Energy value x i represents the energy of the sub-band signal, i represents the sub-band number, K is [1, N], N is the number of data points of each sub-band signal, and its value is 625.

[0104] Step 6: Support Vector Machine (SVM) model training

[0105] The parameters of the support vector machine (SVM) model are set to the radial basis function (RBF, γ = 0.1) of the kernel function; the regularization parameter is C = 0.1; where 0 in the classification label represents normal pre-tightening, 1 represents looseness, and 2 represents over-tightening.

[0106] The training set and test set are divided into 7:3 ratios. The training set accounts for 70%, including 3,000 sets of samples under different working conditions; the test set accounts for 30%, including 1,286 sets of samples.

[0107] Five-fold cross validation was used to optimize the model hyperparameters, and the model evaluation indicators were set as follows: accuracy ≥ 98.5% (test set) and the diagonal proportion of the confusion matrix > 97%.

[0108] Step 7: Real-time monitoring and feedback

[0109] Input the real-time feature vector into the trained SVM model and output the bolt preload status (normal / loose / overtightened). Make judgments based on the preset alarm threshold:

[0110] Looseness threshold: preload force drops > 15% of rated value;

[0111] Over-tightening threshold: preload force rises > 10% of rated value.

[0112] After obtaining the real-time monitoring results, the status data and alarm information are sent to the display terminal through the repeater network with a refresh rate of 1Hz.

[0113] Step 8: Model Update and Maintenance

[0114] When new data (≥500 groups) are added each month, model fine-tuning is triggered and support vectors are updated; if the model accuracy is <95% for three consecutive tests, full retraining is initiated.

[0115] like Figure 4 As shown, the brake disc system mainly includes a disc hub, a friction disc and a pressure ring.

[0116] The disc hub, friction disc and pressure ring are assembled, and then assembled into a brake disc system through the monitoring component, brake disc gasket and brake disc nut, and then pressed onto the brake disc seat of the axle through interference fit.

[0117] like Figure 5 As shown, the passive wireless EMU brake disc bolt preload real-time monitoring component provided by the embodiment of the present invention includes a brake disc bolt body, a core shaft arranged along the extension direction of the screw and used to sense the change of the preload of the brake disc bolt body is encapsulated in the screw rod of the bolt body, and a sensor connected to the core shaft and a signal processor connected to the sensor are encapsulated in the screw head of the bolt body.

[0118] A packaging groove and a core groove are sequentially opened from the screw head to the screw rod, which are interconnected and located on the same axis as the bolt body. The diameter of the packaging groove is larger than the diameter of the core groove, and a spacing is reserved between the bottom of the core groove and the top of the screw rod;

[0119] The sensor and signal processor are installed in the packaging groove from the inside to the outside in sequence. The core shaft is matched and embedded in the core groove with grease on all sides and connected to the sensor in the packaging groove. A protective cover that wraps the sensor and signal processor in an annular shape and a protective cover that matches the size of the notch of the packaging groove and is flush are installed circumferentially in the packaging groove.

[0120] Specifically, the core shaft undergoes tension and compression deformation along with the brake disc bolt body, senses the change in the preload force of the brake disc bolt body, and transmits it to the sensor, which is processed into a bolt preload force status signal by the signal processor and transmitted to the repeater.

[0121] In combination with the specific embodiment, the working process of the passive wireless EMU brake disc bolt preload real-time monitoring device provided by the embodiment of the present invention is as follows:

[0122] The brake disc bolts encapsulated with the monitoring components are installed in the brake disc. When the brake disc starts to run, the preload of the brake disc bolts changes due to the external load. The monitoring component transmits the measured bolt preload status signal to the repeater. After the support vector machine classification model training of the signal detection unit, signal receiving unit and signal processing unit of the repeater, the bolt preload status signal is obtained and displayed on the remote terminal.

[0123] The passive wireless brake disc bolt preload real-time monitoring component (including packaging slot, mandrel, sensor and signal processor) is installed in the EMU brake disc through precision assembly process. The specific steps are as follows:

[0124] Step 1: Bolt Packaging and Installation

[0125] A core groove (2.5mm in diameter) is opened along the axis line in the screw of the brake disc bolt body, and a packaging groove (5mm in diameter) extends from the screw head to the core groove, and the two are coaxially connected; the MEMS piezoresistive sensor (range 0-20kN) and the signal processor (power consumption <10mW) are successively embedded in the packaging groove, and the core shaft (material: 316L stainless steel) is coated with high-temperature resistant grease (model: XG-3000) on the surface and then inserted into the core groove for precise coupling with the sensor; a silicone protective cover (1.2mm in thickness) and a titanium alloy protective cover are installed in the packaging groove to ensure that the component is waterproof and dustproof up to IP67.

[0126] The monitoring bolt is interference fit with the disc hub, friction disc and pressure ring through high-strength gaskets (grade 8.8) and anti-loosening nuts (pre-tightening torque 120N·m), and then press-fitted to the axle brake disc seat with a matching tolerance of H7 / g6.

[0127] Step 2: Dynamic monitoring and signal transmission of preload force

[0128] When the brake disc is running, the friction of the brake pad generates a thermomechanical coupling load (temperature range -40 to 300°C), which causes the bolt to deform axially (deformation 0.01 to 0.2 mm); the core shaft moves with the deformation, triggering the sensor to output a resistance change signal (sensitivity 2mV / N), which is amplified and filtered by the signal processor and converted into a digital signal (sampling rate 10kHz, resolution 16bit).

[0129] The signal is sent to the corresponding repeater via the LoRa wireless protocol (frequency band 433MHz, transmission distance ≤50m); the repeater main control chip STM32F103C8T6 starts the temperature difference power generation module (power generation efficiency 12%), the energy storage module (supercapacitor, capacity 10F) is powered, and the trigger control module enters the timed wake-up mode (Tc = 1s, T s =5s).

[0130] Step 3. Signal processing and state classification

[0131] The sliding window method (window length 1s) is used to remove abnormal points outside the range of μ±3δ and interpolate and repair;

[0132] Extract the low-frequency components (0-500 Hz) of IMF1-IMF3 by EMD decomposition; select the top three subbands (E5, E7, E9) with the highest energy proportion in the 1.5-3 kHz frequency band by 4-layer decomposition of db4 wavelet packet; construct the 6-dimensional feature vectors μ,δ 2 ,C f ,E5,E7,E9(C f is the peak factor).

[0133] Input 3,000 sets of training data (70% training set, 30% test set), using RBF kernel function (γ=0.1, C=1.0);

[0134] Output classification labels: 0 (normal, preload fluctuation <5%), 1 (loose, preload decrease ≥15%), 2 (overtight, preload increase ≥10%);

[0135] Model test accuracy ≥98.5%, response time <50ms.

[0136] Step 4. Remote terminal display and alarm

[0137] 3,000 sets of training data (70% training set, 30% test set) were input, and the RBF kernel function (γ=0.1, C=1.0) was used; the repeater network uploaded the processed preload status data to the display terminal through the ZigBee protocol (transmission rate 250kbps); the terminal interface was refreshed in real time (frequency 1Hz), and the preload change trend of each bolt was displayed in a three-dimensional curve, and color codes were marked: 1) Green: normal state (Class 0); 2) Yellow: loosening warning (Class 1, triggering sound and light alarm); 3) Red: overtightening fault (Class 2, forced shutdown command).

[0138] Data is synchronously stored in the cloud server, supporting historical data backtracking and maintenance report generation.

[0139] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A passive wireless EMU brake disc bolt preload real-time monitoring component, characterized in that: It comprises a brake disc bolt body, wherein a core shaft arranged along the extension direction of the screw and used for sensing the change of the preload force of the brake disc bolt body is encapsulated in the screw rod of the bolt body, and a sensor connected to the core shaft and a signal processor connected to the sensor are encapsulated in the screw head of the bolt body.

2. The passive wireless EMU brake disc bolt preload real-time monitoring component according to claim 1 is characterized in that: A packaging groove and a core groove are sequentially opened from the screw head to the screw rod, which are interconnected and located on the same axis as the bolt body, the diameter of the packaging groove is larger than the diameter of the core groove, and a spacing is reserved between the bottom of the core groove and the top of the screw rod; The sensor and the signal processor are installed in the packaging groove from the inside to the outside in sequence, the core shaft is matched and embedded in the core groove coated with grease on all sides and connected to the sensor in the packaging groove, and a protective cover that is annularly wrapped around the sensor and the signal processor and a protective cover that matches the size of the notch of the packaging groove and is flush are installed circumferentially in the packaging groove.

3. A passive wireless EMU brake disc bolt preload real-time monitoring device, characterized in that: include: Display terminal, Multiple repeaters, each of which is interconnected; And multiple passive wireless EMU brake disc bolt preload real-time monitoring components as described in claim 1 or 2, and the repeaters and monitoring components are connected one-to-one, and each of the repeaters receives the bolt preload status signal sent by the corresponding monitoring component and converges it to the display terminal.

4. The passive wireless EMU brake disc bolt preload real-time monitoring device according to claim 3 is characterized in that: The repeater includes a temperature difference power generation module, an energy storage module, a control module and a remote transmission module; The temperature difference power generation module is connected to the energy storage module through a conversion circuit and is connected to the control module through a trigger circuit; the control module is respectively connected to the energy storage module, the monitoring component and the remote transmission module; the energy storage module is respectively connected to the monitoring component and the remote transmission module.

5. The passive wireless EMU brake disc bolt preload real-time monitoring device according to claim 4 is characterized in that: The trigger circuit determines whether the disc brake device is in a working state according to whether the temperature difference power generation module generates electricity. If it is in a working state, the temperature difference power generation module generates electrical energy, and the trigger circuit sends a trigger signal to the control module so that the control module responds and enters a timed wake-up mode.

6. The passive wireless EMU brake disc bolt preload real-time monitoring device according to claim 5 is characterized in that: When the disc brake device is in a non-working state, the temperature difference power generation module does not generate electric energy, and the control module and the remote transmission module are in a sleep mode; When the disc brake device is in working state, the control module is in timed wake-up mode with T c It wakes up at time intervals and transmits acquisition control commands to the sensor. s The time interval wakes up the remote sending module to transmit the wake-up control command and the brake disc bolt preload data to be sent, where T s =nT c , n is a positive integer; so that the remote sending module responds after receiving the wake-up control command and enters the sending mode from the sleep mode, and after receiving the brake disc bolt preload force data, sends the brake disc bolt preload force data out, and enters the sleep mode again to wait for the next wake-up control command.

7. The passive wireless EMU brake disc bolt preload real-time monitoring device according to claim 5 is characterized in that: The monitoring component is configured with a signal receiving unit and a signal processing unit; The signal receiving unit is used to receive a bolt preload state signal collected after the brake disc bolt is axially deformed; The signal processing unit pre-trains the bolt preload state signal, performs abnormal data screening, sequence correlation and decomposition processing, wavelet packet decomposition, and frequency band energy screening to obtain a historical feature vector; and inputs the historical feature vector into a support vector machine classification model for training to obtain a bolt state detection model, thereby obtaining a brake disc bolt preload monitoring signal.

8. The passive wireless EMU brake disc bolt preload real-time monitoring device according to claim 7 is characterized in that: Screening to obtain historical feature vectors and inputting the historical feature vectors into a support vector machine classification model for training to obtain a bolt state detection model includes the following steps: The sensor collects the resistance change signal caused by the axial deformation of the bolt in real time and converts it into a voltage signal of 0-5V. The instrument amplifier gain amplifies the signal by 100 times, and the low-pass filter is used to set the cutoff frequency to 2kHz to remove high-frequency noise. The 16-bit ADC module is used to convert the analog signal into a digital signal with a resolution of 0.076mV / LSB. The mean μ and standard deviation δ of 10,000 data points in the window are calculated with a window length of 1 second. If a data point is out of the range of μ±3δ, it is marked as an abnormality and the abnormal value is replaced by linear interpolation. The linear trend term is fitted using the least square method and subtracted from the original signal; the digital signal after subtraction is decomposed into six intrinsic mode functions IMF, and the low-frequency components IMF1-IMF3 related to the preload force are extracted; The preprocessed digital signal is decomposed into 16 sub-bands by performing 4-layer wavelet packet decomposition. The energy value of each sub-band signal is calculated, and the frequency bands with the top 3 energy proportions are selected to form the feature vector. The mean, variance and peak factor of the time domain features and the frequency domain features are used to select the energy values ​​of three frequency bands and construct a 6-dimensional historical feature vector F: Where μ is the mean; δ is the standard deviation; and peak factor Energy value x i represents the energy of the sub-band signal, i represents the sub-band number, K takes the value [1, N], and N is the number of data points for each sub-band signal; The training set and test set were divided into 7:3, and the hyperparameters of the support vector machine (SVM) model were optimized using 5-fold cross validation. The model was trained using the training set and evaluated using the test set: the accuracy was ≥ 98.5% and the diagonal proportion of the confusion matrix was > 97%; The real-time feature vector is input into the trained support vector machine (SVM) model, and combined with the preset alarm threshold, the bolt preload state is judged and output; When the preload drops by >15% of the rated value, the bolt preload state is loose; When the preload force rises > 10% of the rated value, the bolt preload force state is overtightened; For the rest, the bolt preload status is normal; When the number of newly added data is ≥500 within a period of time, model fine-tuning is triggered and the support vector is updated; if the model accuracy is <95% for three consecutive tests, full retraining is started.

9. A brake disc system, characterized in that: include: Hub, Friction disc, Pressure ring, And the passive wireless EMU brake disc bolt preload force real-time monitoring component as claimed in claim 1 or 2, or the passive wireless EMU brake disc bolt preload force real-time monitoring device as claimed in any one of claims 3 to 8; The disc hub, friction disc and pressure ring are assembled through the monitoring component, gaskets and nuts matching the monitoring component, and are press-fitted onto the brake disc seat of the axle through interference fit.

Images