Security monitoring method, device, equipment, storage medium and computer program product

Abstract

This application discloses a safety monitoring method, apparatus, equipment, storage medium, and computer program product to address the problem that existing safety monitoring schemes suffer from poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation. The method includes: acquiring real-time operating condition data of a locomotive and acquiring vibration and noise data corresponding to at least two test points using at least two sensors installed on the locomotive's drivetrain; determining a target diagnostic model corresponding to the locomotive's current operating condition from at least two pre-constructed diagnostic models based on the real-time operating condition data; performing feature extraction and analysis on the vibration and noise data according to the target diagnostic model to determine whether a fault exists in the drivetrain; when the determination result is yes, performing coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and generating a fault diagnosis result based on the coherence analysis results.

Description

Technical Field

[0001] This application relates to the field of safety control technology for transportation equipment, and in particular to a safety monitoring method, device, equipment, storage medium, and computer program product. Background Technology

[0002] Monitoring the health status of key rotating components of rail transit locomotives and rolling stock (such as traction motors, gearboxes, and bearings) is a crucial aspect of ensuring safe vehicle operation. Currently, the industry standard for monitoring this is to install vibration acceleration sensors on the surface of axle boxes or motor housings, triggering alarms based on locally preset fixed thresholds to achieve online identification of mechanical faults.

[0003] However, in practical applications, the above-mentioned existing technical solutions have the following drawbacks: First, when locomotives are running on actual tracks, traction power, speed, and track conditions change drastically, causing significant fluctuations in the vibration energy of the transmission chain. Using a fixed threshold discrimination mechanism can easily lead to numerous false alarms under high-energy conditions such as climbing slopes and crossing switches due to increased normal vibration. Conversely, under low-energy conditions such as coasting and low-speed station entry, the amplitude of fault characteristic signals such as early micro-pitting and tooth surface micro-cracks is weak and easily fails to reach the alarm threshold, resulting in missed alarms.

[0004] Second, existing systems mostly adopt a single measurement point acquisition mode. When an alarm occurs, it is difficult for maintenance personnel to determine whether the vibration source is from the deterioration of internal components or from external environmental interference such as wheel-rail impact. This results in insufficient fault source identification capability and affects the accuracy of subsequent maintenance decisions.

[0005] Third, existing systems rely heavily on analog signal transmission or point-to-point hard wiring to connect sensors and processing units. In harsh environments with strong electromagnetic interference, high humidity, and severe vibration under the vehicle, signal integrity is difficult to guarantee. Furthermore, the complex cabling increases the weight of the vehicle and the difficulty of installation. Loose or corroded connectors may also become new sources of failure.

[0006] Therefore, improving the ability to identify fault sources and the accuracy of identification for key locomotive components, and reducing false alarms and missed alarms, has become a technical problem that needs to be solved by existing technologies. Summary of the Invention

[0007] This application provides a safety monitoring method to address the problem that existing safety monitoring schemes have poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation.

[0008] This application also provides a safety monitoring device to address the problem that existing safety monitoring schemes have poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, which affects the safety of railway transportation.

[0009] This application also provides a safety monitoring device to address the problem that existing safety monitoring schemes have poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, which affects the safety of railway transportation.

[0010] This application also provides a computer-readable storage medium to address the problem that existing safety monitoring schemes have poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation.

[0011] A computer program product is provided to address the problem that existing safety monitoring schemes suffer from poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation.

[0012] The embodiments of this application adopt the following technical solutions: A safety monitoring method includes: acquiring real-time operating condition data of a locomotive, and acquiring vibration and noise data corresponding to at least two test points through at least two sensors installed on the locomotive's transmission chain; determining a target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-constructed diagnostic models based on the real-time operating condition data; performing feature extraction and analysis on the vibration and noise data based on the target diagnostic model to determine whether there is a fault in the transmission chain; when the determination result is yes, performing coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and generating a fault diagnosis result based on the coherence analysis results.

[0013] A safety monitoring device includes: a data acquisition unit for acquiring real-time operating condition data of a locomotive and acquiring vibration and noise data corresponding to at least two test points through at least two sensors installed on the locomotive's transmission chain; a diagnostic model determination unit for determining a target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-constructed diagnostic models based on the real-time operating condition data; a fault identification unit for performing feature extraction and analysis on the vibration and noise data based on the target diagnostic model to determine whether a fault exists in the transmission chain; and a fault diagnosis unit for performing coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain a coherence analysis result when the judgment result obtained by the fault identification unit is yes, and generating a fault diagnosis result based on the coherence analysis result.

[0014] A safety monitoring device, comprising: The system includes a processor and a memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: acquire real-time operating condition data of the locomotive and acquire vibration and noise data corresponding to at least two test points using at least two sensors mounted on the locomotive's drivetrain; determine a target diagnostic model corresponding to the locomotive's current operating condition from at least two pre-built diagnostic models based on the real-time operating condition data; perform feature extraction and analysis on the vibration and noise data based on the target diagnostic model to determine whether the drivetrain has a fault; when the determination result is yes, perform coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and generate a fault diagnosis result based on the coherence analysis results.

[0015] A computer-readable storage medium stores one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the following operations: acquire real-time operating condition data of a locomotive and acquire vibration and noise data corresponding to at least two test points using at least two sensors disposed on the locomotive's drivetrain; determine a target diagnostic model corresponding to the locomotive's current operating condition from at least two pre-constructed diagnostic models based on the real-time operating condition data; perform feature extraction and analysis on the vibration and noise data based on the target diagnostic model to determine whether a fault exists in the drivetrain; when the determination result is yes, perform coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain a coherence analysis result, and generate a fault diagnosis result based on the coherence analysis result.

[0016] A computer program product includes a computer program that, when executed by a processor, performs the following: acquiring real-time operating condition data of a locomotive, and acquiring vibration and noise data corresponding to at least two test points using at least two sensors installed on the locomotive's drivetrain; determining a target diagnostic model corresponding to the locomotive's current operating condition from at least two pre-built diagnostic models based on the real-time operating condition data; performing feature extraction and analysis on the vibration and noise data based on the target diagnostic model to determine whether a fault exists in the drivetrain; when the determination result is yes, performing coherence analysis on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and generating a fault diagnosis result based on the coherence analysis results.

[0017] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: The safety monitoring method provided in this application allows for the acquisition of real-time locomotive operating condition data during locomotive operation safety monitoring. Vibration and noise data corresponding to at least two test points are acquired using at least two sensors installed on the locomotive's transmission chain. Based on the real-time operating condition data, a target diagnostic model corresponding to the locomotive's current operating condition is determined from at least two pre-built diagnostic models. Features are extracted and analyzed from the vibration and noise data using the target diagnostic model to determine if a fault exists in the transmission chain. If the determination is yes, coherence analysis is performed on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and a fault diagnosis result is generated based on the coherence analysis results. The safety monitoring method provided in this application has several advantages. First, the diagnostic model can dynamically switch according to changes in the vehicle's operating conditions (such as traction, coasting, and braking), avoiding the drawbacks of using a single fixed threshold or fixed feature extraction method for uniform judgment under all operating conditions. Under high-energy operating conditions, a highly adaptable diagnostic model with a higher threshold can be selected to prevent false alarms caused by normal vibration fluctuations. Under low-energy operating conditions, a highly sensitive diagnostic model with a lower threshold can be selected to capture early weak fault features and prevent missed alarms. Second, after determining that a fault exists, coherence analysis can be further performed based on the vibration and noise data corresponding to at least two test points, and a fault diagnosis result can be generated based on the coherence analysis results. By setting multiple test points at different positions in the transmission chain and utilizing the coherence differences between the signals at each test point, it is possible to effectively distinguish whether the vibration source comes from the deterioration of internal mechanical components or from external environmental interference such as wheel-rail impact, thereby providing maintenance personnel with more accurate fault source information. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of the specific structure of a security monitoring system provided in an embodiment of this application; Figure 2 A schematic diagram showing the arrangement of a MEMS acoustic-vibration composite sensor on a locomotive bogie drive unit, provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating a specific process of a security monitoring method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the specific structure of a safety monitoring device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the specific structure of a safety monitoring device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides a safety monitoring method to address the problem that existing safety monitoring schemes have poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation.

[0021] For ease of description, the following description uses a safety monitoring system installed on a locomotive as an example to illustrate the implementation of this method. It should be understood that using a safety monitoring system as the implementing entity is merely an illustrative example and should not be construed as a limitation of the method.

[0022] In this embodiment of the application, the specific structure of the security monitoring system is as follows: Figure 1 As shown, it mainly includes a micro-electro-mechanical systems (MEMS) acoustic and vibration composite sensor array arranged on the locomotive bogie drive unit, an on-board edge computing gateway, and a data interaction interface module that communicates with the locomotive central control unit (CCU).

[0023] In this embodiment, at least two MEMS acoustic-vibration composite sensors can be installed at each locomotive bogie drive unit to monitor vibration and noise data at at least two test points on the locomotive bogie drive unit.

[0024] In one implementation, such as Figure 2As shown, the following section uses the example of setting two MEMS acoustic-vibration composite sensors at each locomotive bogie drive unit to monitor vibration and noise data at test points A and B, respectively, to introduce the safety monitoring method provided in this application embodiment. The MEMS acoustic-vibration composite sensor at test point A can be fixedly installed on the outside of the non-drive end cover of the traction motor. The sensitive axis of the MEMS acoustic-vibration composite sensor can be arranged radially along the motor to collect vibration and structural noise signals generated by the traction motor bearings and rotor assembly during operation. The MEMS acoustic-vibration composite sensor at test point B is fixedly installed on the outer wall of the gearbox housing near the input shaft or the meshing area of ​​the large gear. The sensitive axis of this MEMS acoustic-vibration composite sensor can be arranged along the normal direction of the gear meshing line to collect impact, friction, and modulation vibration and noise signals generated by the gear pair during power transmission. By setting MEMS acoustic-vibration composite sensors at the above two test points, a spatial layout can be formed on the mechanical energy transmission path from the output end of the traction motor to the input end of the gearbox, creating an "input" of the sensor. The output "dual-point beam monitoring structure" provides data support for subsequent fault source location.

[0025] It should be noted that, in the embodiments of this application, all MEMS acoustic-vibration composite sensors adopt an industrial-grade Power over Ethernet (PoE) integrated power supply and communication design compliant with the IEEE 802.3af / at standard, and internally integrate a 16-bit Σ The system includes a delta-type analog-to-digital converter, a digital signal preprocessing unit, and an Ethernet physical layer transceiver. Each sensor is connected in series via shielded twisted-pair (STP) Cat5e Ethernet cable, forming a single-ring topology. The first and last ends of the ring are connected to two independent Ethernet ports of the vehicle-mounted edge computing gateway.

[0026] The vehicle-mounted edge computing gateway incorporates a ring network redundancy protocol processing module, supporting the IEEE 802.1D spanning tree protocol or a proprietary fast ring network recovery mechanism. It automatically reconstructs the data path when any single physical link is interrupted, ensuring communication continuity for the remaining nodes. This ring network, while providing 48V DC power, transmits raw vibration acceleration time-series data with a sampling rate of 10.24kHz and a quantization precision of 16 bits in full-duplex mode at 100Mbps, along with synchronous acoustic signal data.

[0027] In this embodiment, the on-board edge computing gateway further polls and reads the train status data frame broadcast by the CCU at a fixed period of 200ms via a Multifunction Vehicle Bus (MVB) or Wire Train Bus (WTB) interface module. This data frame contains the following deterministic fields: current train speed v (unit: km / h, resolution 0.1 km / h), traction handle level L (integer, range 0~100%, corresponding to the main controller output power percentage), and brake cylinder pressure P. b (Unit: kPa, resolution 1 kPa), actual traction motor speed n m (Unit: rpm, resolution 1 rpm) and current wheel diameter correction value D w (Unit: mm, output by the wheel diameter automatic correction algorithm). The above five-dimensional parameters constitute the real-time operating condition state vector S = [v, L, P] b , n m D w The vehicle-mounted edge computing gateway is equipped with a high-precision hardware timestamp unit. Its clock source is synchronized with the sensor sampling clock through the IEEE 1588 Precision Time Protocol (PTP) to ensure that the time stamp of the state vector S and the timestamp of the corresponding vibration waveform data do not deviate from each other by more than ±2ms, thereby achieving strict alignment of multi-source heterogeneous data in the time domain.

[0028] In this embodiment of the application, the vehicle edge computing gateway can determine the target diagnostic model corresponding to the current operating condition in the "three-dimensional operating condition-fingerprint matrix database" in the local memory according to the real-time acquired state vector S, and determine whether the locomotive has a fault based on the target diagnostic model. When the determination result is yes, it outputs an alarm notification to the dynamic diagnostic logic module, and then generates the final fault diagnosis result through the dynamic diagnostic logic module.

[0029] In this embodiment of the application, the "three-dimensional working condition" The specific construction process of the "fingerprint matrix database" is as follows: Before the locomotive leaves the factory or during advanced maintenance, select no fewer than 10 healthy locomotives of the same model, and perform full-level traction (L=10%, 30%, 50%, 70%, 90%), coasting (L=0, P_b=0), electric braking (L=0, regenerative braking activated), and air braking (L=0, P_b=0) according to the preset procedures during test line or main line operation. b=100~500kPa) combined operating condition test. Simultaneous vibration, acoustic, and TCMS data were continuously collected for no less than 30 minutes under each operating condition. Each data segment was sliced ​​into 200ms windows, resulting in 9000 sample windows. A 128-dimensional feature vector was extracted from each window, including but not limited to: vibration RMS, peak factor, kurtosis, spectral centroid, spectral entropy, envelope peak value, GMF energy ratio, BPFO / BPFI band energy, 1~5kHz acoustic energy, and coherence mean. All feature vectors were bound to their corresponding S-vectors and stored in the database. The boundary conditions of each operating condition subspace were determined using the K-means clustering algorithm (cluster number K=24), and the feature distribution of healthy samples within each subspace was fitted using a Gaussian Mixture Model (GMM). The alarm threshold was set to mean ± 3 times standard deviation, covering 99.7% of healthy operating scenarios. The final deterministic mapping table is stored in binary format in the read-only memory (ROM) of the vehicle edge computing gateway, thus obtaining the "three-dimensional working condition". Fingerprint matrix database.

[0030] Based on the aforementioned security monitoring system, a schematic diagram illustrating the specific implementation process of the security monitoring method provided in this application is shown below. Figure 3 As shown, the main steps include the following: Step 11: Obtain real-time operating condition data of the locomotive, and obtain vibration and noise data corresponding to at least two test points through at least two sensors set on the locomotive transmission chain; In this embodiment, real-time operating condition data may include traction handle position L, locomotive speed v, and brake cylinder pressure P. b traction motor speed n m and the current wheel diameter correction value D w .

[0031] The traction handle position, a crucial parameter reflecting the driver's intentions, can be measured by an encoder or potentiometer mounted on the driver's cab control panel and transmitted as a digital signal to the Central Processing Unit (CCU). Locomotive speed is acquired via speed sensors mounted on the wheel axles. These sensors utilize electromagnetic induction to convert wheel rotation speed into pulse signals, which are then converted to the actual operating speed. Brake cylinder pressure is monitored by pressure sensors installed in the brake lines; the output signal is amplified and converted from analog to digital before being uploaded to the CCU. Furthermore, traction motor speed data is obtained via an encoder directly connected to the motor shaft, while the current wheel diameter correction value can be dynamically updated based on historical operating data and wheel wear models to ensure accurate speed calculations. The data acquisition frequency must meet real-time requirements, typically set at over 100 times per second, to ensure comprehensive and accurate perception of the locomotive's operating status.

[0032] In this embodiment, vibration and noise data can be acquired by multiple MEMS acoustic-vibration composite sensors installed on the locomotive transmission chain. Specifically, in this embodiment, a first sensor can be arranged at the non-transmission end of the locomotive's traction motor, mainly for collecting vibration signals of the motor bearing and rotor. At the same time, a second sensor is installed on the gearbox housing to focus on monitoring the changes in vibration and noise during gear meshing. It should be noted that the specific arrangement and location of the MEMS acoustic-vibration composite sensors are detailed above and will not be repeated here.

[0033] It should be noted that, since piezoelectric accelerometers have the characteristics of good high-frequency response, high sensitivity and strong anti-interference ability, they are suitable for vibration signal acquisition under complex working conditions. Therefore, in this embodiment of the application, a piezoelectric accelerometer can be selected as a MEMS acoustic-vibration composite sensor.

[0034] Step 12: Based on the real-time operating condition data obtained by performing Step 11, determine the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models. In this embodiment of the application, the safety monitoring system can determine the following three target diagnostic models corresponding to the current operating condition of the locomotive, based on the current operating condition of the locomotive: 1. Determination of the target diagnostic model corresponding to strong traction conditions: When the traction handle level is greater than the first threshold and the current braking state is determined to be no braking based on the brake cylinder pressure, the locomotive is determined to be in a strong traction condition. At this time, the first diagnostic model can be selected as the target diagnostic model.

[0035] In this embodiment, the first diagnostic model is designed to identify gear wear faults by analyzing the energy distribution characteristics of gear meshing frequencies. Specifically, under heavy traction conditions, the gearbox bears a large load, and the energy proportion of the gear meshing frequency and its harmonics in the vibration signal increases significantly. Therefore, in this embodiment, the first diagnostic model can perform spectral analysis on the vibration noise data, extract energy characteristics related to the gear meshing frequency, and compare them with a preset first alarm threshold to achieve early warning of faults. In this embodiment, the first diagnostic model is suitable for high-speed, heavy-load operation scenarios and can quickly detect typical fault modes such as gear surface fatigue spalling and tooth surface scuffing, providing assurance for locomotive operation safety.

[0036] 2. Determination of the target diagnostic model corresponding to coasting condition: When the traction handle position is zero and the current braking state is determined to be no braking based on the brake cylinder pressure, it can be determined that the locomotive is currently in coasting condition. At this time, the second diagnostic model can be selected as the target diagnostic model.

[0037] In this embodiment, the second diagnostic model is designed to process vibration signals based on envelope demodulation technology to identify bearing damage-related faults. Under coasting conditions, the main excitation source of the locomotive drivetrain is impact vibration caused by internal bearing defects. These vibration signals are often drowned out by strong background noise. Therefore, in this embodiment, the second diagnostic model first performs a Hilbert transform on the vibration noise data to generate an analytical signal and extract its envelope spectrum. Then, by comparing the energy distribution of the bearing's outer ring fault characteristic frequencies and inner ring fault characteristic frequencies, it can be determined whether the bearing is damaged. Since the drivetrain load is low under coasting conditions, bearing fault characteristics are more easily revealed. Therefore, the second diagnostic model exhibits high fault identification sensitivity and accuracy under this condition.

[0038] 3. Determination of the target diagnostic model corresponding to electric braking conditions: When the traction handle position is zero and the current braking state is determined to be braking based on the brake cylinder pressure, it can be determined that the locomotive is currently in electric braking condition. At this time, the third diagnostic model can be selected as the target diagnostic model.

[0039] In this embodiment, the third diagnostic model is designed to identify subtle fault features hidden within complex signals by performing refined analysis of the energy distribution characteristics of vibration and noise signals, thereby enabling the identification of faults such as abnormal gear backlash or tooth back damage. Under electric braking conditions, changes in the interaction forces between gear pairs inside the gearbox may lead to stress concentration at the tooth back contact points, resulting in tooth back damage or abnormal expansion of gear backlash. The third diagnostic model calculates the energy distribution parameters of vibration and noise data within a preset frequency band and compares them with benchmark values ​​under normal operating conditions to determine whether the drivetrain exhibits the aforementioned fault types.

[0040] Step 13: Based on the target diagnostic model determined by executing Step 12, feature extraction and analysis are performed on the vibration and noise data to determine whether there is a fault in the transmission chain; Specifically, when the target diagnostic model is the first diagnostic model, the following process can be followed to determine whether there is a fault in the transmission chain, including: Step 1-1: Determine the current gear meshing frequency based on the traction motor speed and gearbox transmission ratio; Specifically, it can be based on the traction motor speed n m Based on the gearbox transmission ratio i, the current gear mesh frequency (GMF) is determined according to the following formula [1]: GMF = (n m / 60) × Z p [1] Among them, Z p n is the number of teeth on the pinion. m The actual speed of the traction motor (unit: rpm).

[0041] Step 1-2, based on the first diagnostic model, determines the energy ratio of vibration noise data to gear meshing frequency: Specifically, based on the first diagnostic model, a narrowband fast Fourier transform (FFT) can be performed on the vibration noise data collected by the MEMS acoustic-vibration composite sensor set at test point B, with a spectral resolution of 1 Hz and an analysis bandwidth of 0~5 kHz. The GMF and its energy proportion E at its 2nd and 3rd harmonics are determined according to the following formula [2]. k : [2] Where k = 1, 2, 3; X(f) are FFT coefficients; the numerator represents the sum of energy within the GMF×k±1Hz bandwidth, and the denominator represents the sum of energy across the entire frequency band from 0 to 5000Hz.

[0042] Steps 1-3: Based on the energy percentage obtained by executing steps 1-2 and the first alarm threshold, determine whether there is a fault in the gears in the transmission chain; If any E k If the first alarm threshold is exceeded, for example, the first alarm threshold can be set to 15%, then it is determined that there is an early wear fault in the gears in the transmission chain, triggering an early wear warning for the gears.

[0043] Meanwhile, under the first diagnostic model, the alarm threshold of the effective value of vibration acceleration (RMS) can be dynamically increased from the baseline value of 50 m / s² to 80 m / s² to avoid false alarms caused by normal vibration energy fluctuations under strong traction conditions.

[0044] Specifically, when the target diagnostic model is the second diagnostic model, the following process can be followed to determine whether there is a fault in the transmission chain, including: Step 2-1: Perform envelope demodulation on the vibration noise data to obtain the envelope spectrum; Specifically, a high-frequency carrier can be removed by using an FIR low-pass filter with a cutoff frequency of 8kHz, and then an analytic signal can be obtained by performing a Hilbert transform on the absolute value signal. The real part is taken as the envelope, and finally, an FFT analysis is performed on the envelope with a spectral resolution of 0.5Hz and an analysis bandwidth of 0~1kHz.

[0045] Step 2-2: Based on the envelope spectrum and bearing geometric parameters, determine the characteristic frequencies of bearing outer ring faults and bearing inner ring faults in the transmission chain. Specifically, this can be determined based on the bearing's geometric parameters (inner diameter d, outer diameter D, rolling element diameter b, contact angle α) and the traction motor's speed n. m The outer ring fault characteristic frequency (Ball Pass Frequency Outer, BPFO) and inner ring fault characteristic frequency (Ball Pass Frequency Inner, BPFI) of the bearing are calculated according to the following formulas [3]~[4]: [3] [4] Among them, Z b Where d is the number of rolling elements, D is the bearing inner diameter, and α is the contact angle; these parameters are all known constants for the bearing model.

[0046] Step 2-3: Based on the bearing outer ring fault characteristic frequency, the bearing inner ring fault characteristic frequency, and the second alarm threshold, determine whether there is a fault in the bearing in the transmission chain.

[0047] Specifically, if a significant peak is detected within the ±2Hz bandwidth of BPFO or BPFI and its harmonics (2 times, 3 times) (in this embodiment, the significant peak can be defined as a local maximum value with a signal-to-noise ratio ≥6dB), then the corresponding bearing is determined to have early pitting or microcracks, triggering a bearing damage warning.

[0048] Additionally, it should be noted that under the second diagnostic model, the alarm threshold for the effective value of vibration acceleration (RMS) can be lowered to 15 m / s² to improve the sensitivity to weak fault signals.

[0049] Specifically, when the target diagnostic model is the third diagnostic model, the following process can be followed to determine whether there is a fault in the transmission chain, including: The energy distribution parameters of vibration and noise data within a preset frequency band are determined. In this embodiment, the safety monitoring system can focus on analyzing the energy distribution characteristics within the 1kHz~5kHz frequency band of the acoustic signal spectrum collected by the MEMS acoustic-vibration composite sensor set at test point B. Since the gear's force-bearing surface switches from the working tooth surface to the non-working tooth surface (backlash side) during braking, the energy in this frequency band should remain stable under normal conditions, with a fluctuation standard deviation σ ≤ 3dB. If a sudden increase in energy in this frequency band is detected (ΔE ≥ 8dB) accompanied by periodic modulation sidebands (sideband spacing equal to GMF, sideband amplitude ≥ 4dB higher than the main peak), it is determined that the gear backlash is abnormally increased or there is tooth back damage.

[0050] Step 14: When the judgment result obtained by executing step 13 is yes, perform coherence analysis based on the vibration and noise data corresponding to at least two test points to obtain the coherence analysis result, and generate the fault diagnosis result based on the coherence analysis result.

[0051] When a fault is determined in the transmission chain through step 13, to further improve the accuracy of fault source identification, the safety monitoring system can perform coherence analysis on the vibration and noise data corresponding to at least two test points to determine the specific location and type of the fault. Coherence analysis is a signal correlation-based analysis method that evaluates the similarity of signals in the frequency domain by calculating the coherence function between vibration signals at different test points.

[0052] In this embodiment of the application, the safety monitoring system can perform coherence analysis according to the following sub-steps to obtain coherence analysis results, and generate fault diagnosis results based on the coherence analysis results, including: Sub-step 1401: The vibration signal x collected by the MEMS acoustic-vibration composite sensor located at test point A within the same time window... A(t) The vibration signal x collected by the MEMS acoustic-vibration composite sensor set at measurement point B B(t) Perform cross power spectral density G AB(f) With their respective power spectral density G AA(f) G BB(f) The calculation was performed using the Welch average periodogram method, with a segment overlap rate of 50% and a Hanning window function.

[0053] Sub-step 1402: Calculate the frequency correlation function γ²(f); In this embodiment of the application, the frequency correlation function can be calculated according to the following formula [5]: [5] The range of the frequency correlation function γ²(f) is [0,1].

[0054] Sub-step 1403: The fault diagnosis result is obtained by executing the γ²(f) value obtained in sub-step 1402; Specifically, if ²(f) ≥ 0.85 within the 0~2kHz main frequency band, the vibration source is determined to be external excitation, wheel-rail impact or track irregularity, and the fault diagnosis result can be marked as "environmental interference".

[0055] If γ²(f) < 0.4 in the 0~2kHz main frequency band, and the amplitude of the vibration signal collected by the MEMS acoustic-vibration composite sensor set only at test point B exceeds the limit, then it is determined to be an internal fault of the gearbox.

[0056] If γ²(f) < 0.4 in the 0~2kHz main frequency band, and the amplitude of the vibration signal collected by the MEMS acoustic-vibration composite sensor set only at test point A exceeds the limit, it is determined to be a motor bearing or rotor imbalance fault.

[0057] The safety monitoring method provided in this application allows for the acquisition of real-time locomotive operating condition data during locomotive operation safety monitoring. Vibration and noise data corresponding to at least two test points are acquired using at least two sensors installed on the locomotive's transmission chain. Based on the real-time operating condition data, a target diagnostic model corresponding to the locomotive's current operating condition is determined from at least two pre-built diagnostic models. Features are extracted and analyzed from the vibration and noise data using the target diagnostic model to determine if a fault exists in the transmission chain. If the determination is yes, coherence analysis is performed on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and a fault diagnosis result is generated based on the coherence analysis results. The safety monitoring method provided in this application has several advantages. First, the diagnostic model can dynamically switch according to changes in the vehicle's operating conditions (such as traction, coasting, and braking), avoiding the drawbacks of using a single fixed threshold or fixed feature extraction method for uniform judgment under all operating conditions. Under high-energy operating conditions, a highly adaptable diagnostic model with a higher threshold can be selected to prevent false alarms caused by normal vibration fluctuations. Under low-energy operating conditions, a highly sensitive diagnostic model with a lower threshold can be selected to capture early weak fault features and prevent missed alarms. Second, after determining that a fault exists, coherence analysis can be further performed based on the vibration and noise data corresponding to at least two test points, and a fault diagnosis result can be generated based on the coherence analysis results. By setting multiple test points at different positions in the transmission chain and utilizing the coherence differences between the signals at each test point, it is possible to effectively distinguish whether the vibration source comes from the deterioration of internal mechanical components or from external environmental interference such as wheel-rail impact, thereby providing maintenance personnel with more accurate fault source information.

[0058] In one embodiment, this application also provides a safety monitoring device to address the problem that existing safety monitoring schemes suffer from poor monitoring accuracy and are prone to false alarms and missed alarms in complex operating environments, thus affecting the safety of railway transportation. A schematic diagram of the specific structure of this safety monitoring device is shown below. Figure 4 As shown, it includes: a data acquisition unit 41, a diagnostic model determination unit 42, a fault identification unit 43, and a fault diagnosis unit 44.

[0059] The data acquisition unit 41 is used to acquire real-time operating condition data of the locomotive and acquire vibration and noise data corresponding to at least two test points through at least two sensors set on the transmission chain of the locomotive. The diagnostic model determination unit 42 is used to determine the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models based on the real-time operating condition data. Fault identification unit 43 is used to extract and analyze the vibration and noise data according to the target diagnosis model to determine whether there is a fault in the transmission chain; The fault diagnosis unit 44 is used to perform coherence analysis based on the vibration and noise data corresponding to the at least two test points when the judgment result obtained by the fault identification unit is yes, to obtain the coherence analysis result, and to generate a fault diagnosis result based on the coherence analysis result.

[0060] In one embodiment, the real-time operating condition data includes at least one of the following: traction handle level, locomotive speed, brake cylinder pressure, traction motor speed, and current wheel diameter correction value. The diagnostic model determination unit 42 is specifically used for: when the traction handle level is greater than a first threshold, and the current braking state is determined to be no braking based on the brake cylinder pressure, determining the current locomotive operating condition as a strong traction condition and determining the first diagnostic model as the target diagnostic model; when the traction handle level is zero, and the current braking state is determined to be no braking based on the brake cylinder pressure, determining the current locomotive operating condition as a coasting condition and determining the second diagnostic model as the target diagnostic model; when the traction handle level is zero, and the current braking state is determined to be braking based on the brake cylinder pressure, determining the current locomotive operating condition as an electric braking condition and determining the third diagnostic model as the target diagnostic model; wherein, the first alarm threshold corresponding to the first diagnostic model is higher than the second alarm threshold corresponding to the second diagnostic model, the first diagnostic model is used to identify gear wear faults, the second diagnostic model is used to identify bearing damage, and the third diagnostic model is used to identify abnormal gear backlash or tooth back damage.

[0061] In one embodiment, the fault identification unit 43 is specifically used to: determine the current gear meshing frequency based on the traction motor speed and gearbox transmission ratio; determine the energy ratio of the vibration noise data to the gear meshing frequency based on the first diagnostic model; and determine whether there is a fault in the gears of the transmission chain based on the energy ratio and the first alarm threshold.

[0062] In one embodiment, the fault identification unit 43 is specifically used for: performing envelope demodulation processing on the vibration noise data to obtain an envelope spectrum; determining the bearing outer ring fault characteristic frequency and bearing inner ring fault characteristic frequency corresponding to the bearing in the transmission chain based on the envelope spectrum and bearing geometric parameters; and determining whether there is a fault in the bearing in the transmission chain based on the bearing outer ring fault characteristic frequency, the bearing inner ring fault characteristic frequency, and the second alarm threshold.

[0063] In one embodiment, the fault identification unit 43 is specifically used to: determine the energy distribution parameters of the vibration noise data within a preset frequency band; and determine whether there is abnormal gear backlash or tooth back damage in the transmission chain based on the energy distribution parameters.

[0064] In one embodiment, the system further includes a first sensor disposed at the non-drive end of the traction motor of the locomotive, the sensitive axis of the first sensor being arranged radially along the traction motor, for collecting vibration and noise data of the bearings and rotor of the traction motor; and a second sensor disposed in the gearbox housing of the locomotive, the sensitive axis of the second sensor being arranged along the normal direction of the gear meshing line in the gearbox, for collecting vibration and noise data of the gearbox.

[0065] Using the safety monitoring device provided in this application embodiment, when monitoring locomotive operation safety, real-time operating condition data of the locomotive can be acquired. Vibration and noise data corresponding to at least two test points can be acquired through at least two sensors installed on the locomotive drivetrain. Then, based on the real-time operating condition data, a target diagnostic model corresponding to the current operating condition of the locomotive can be determined from at least two pre-built diagnostic models. Feature extraction and analysis of the vibration and noise data are performed according to the target diagnostic model to determine whether there is a fault in the drivetrain. When the determination result is yes, coherence analysis is performed based on the vibration and noise data corresponding to at least two test points to obtain the coherence analysis result, and a fault diagnosis result is generated based on the coherence analysis result. The safety monitoring device provided in this application has several advantages. First, the diagnostic model can dynamically switch according to changes in the vehicle's operating conditions (such as traction, coasting, and braking), avoiding the drawbacks of using a single fixed threshold or fixed feature extraction method for uniform judgment under all operating conditions. Under high-energy conditions, a highly adaptable diagnostic model with a higher threshold can be selected to prevent false alarms caused by normal vibration fluctuations. Under low-energy conditions, a highly sensitive diagnostic model with a lower threshold can be selected to capture early weak fault features and prevent missed alarms. Second, after determining that a fault exists, coherence analysis can be performed on the vibration and noise data corresponding to at least two test points, and a fault diagnosis result can be generated based on the coherence analysis results. By setting multiple test points at different positions in the transmission chain and utilizing the coherence differences between the signals at each test point, it is possible to effectively distinguish whether the vibration source comes from the deterioration of internal mechanical components or from external environmental interference such as wheel-rail impact, thereby providing maintenance personnel with more accurate fault source information.

[0066] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 5At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and memory. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0067] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0068] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0069] The processor reads the corresponding computer program from non-volatile memory into main memory and then runs it, forming a security monitoring device at the logical level. The processor executes the program stored in memory and specifically performs the following operations: The system acquires real-time operating condition data of the locomotive and obtains vibration and noise data corresponding to at least two test points using at least two sensors installed on the locomotive's drivetrain. Based on the real-time operating condition data, a target diagnostic model corresponding to the current operating condition of the locomotive is determined from at least two pre-built diagnostic models. Feature extraction and analysis are performed on the vibration and noise data based on the target diagnostic model to determine whether there is a fault in the drivetrain. When the determination result is yes, coherence analysis is performed on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and a fault diagnosis result is generated based on the coherence analysis results.

[0070] The above is as stated in this application. Figure 5The methods performed by the security monitoring electronic equipment disclosed in the illustrated embodiments can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0071] Of course, in addition to software implementation, the electronic device of this application does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. In other words, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0072] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by a portable electronic device including multiple applications, enable the portable electronic device to perform... Figure 3 The security monitoring method shown in the embodiment is specifically used to perform the following operations: The system acquires real-time operating condition data of the locomotive and obtains vibration and noise data corresponding to at least two test points using at least two sensors installed on the locomotive's drivetrain. Based on the real-time operating condition data, a target diagnostic model corresponding to the current operating condition of the locomotive is determined from at least two pre-built diagnostic models. Feature extraction and analysis are performed on the vibration and noise data based on the target diagnostic model to determine whether there is a fault in the drivetrain. When the determination result is yes, coherence analysis is performed on the vibration and noise data corresponding to the at least two test points to obtain coherence analysis results, and a fault diagnosis result is generated based on the coherence analysis results.

[0073] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0076] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0079] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0081] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A safety monitoring method, characterized by, include: The locomotive's real-time operating condition data is acquired, and vibration and noise data corresponding to at least two test points are acquired through at least two sensors installed on the locomotive's drive train. Based on the real-time operating condition data, determine the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models; Based on the target diagnostic model, feature extraction and analysis are performed on the vibration and noise data to determine whether there is a fault in the transmission chain; When the judgment result is yes, coherence analysis is performed based on the vibration and noise data corresponding to the at least two test points to obtain the coherence analysis result, and a fault diagnosis result is generated based on the coherence analysis result.

2. The method of claim 1, wherein, The real-time operating condition data includes at least one of the following: traction handle position, locomotive speed, brake cylinder pressure, traction motor speed, and current wheel diameter correction value. The step of determining the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models based on the real-time operating condition data specifically includes: When the traction handle level is greater than the first threshold, and the current braking state is determined to be no braking based on the brake cylinder pressure, the current operating condition of the locomotive is determined to be a strong traction operating condition, and the first diagnostic model is determined as the target diagnostic model. When the traction handle position is zero and the current braking state is determined to be no braking based on the brake cylinder pressure, the current operating condition of the locomotive is determined to be coasting, and the second diagnostic model is determined as the target diagnostic model. When the traction handle position is zero, and the current braking state is determined to be braking based on the brake cylinder pressure, the current operating condition of the locomotive is determined to be electric braking condition, and the third diagnostic model is determined as the target diagnostic model. Wherein, the first alarm threshold corresponding to the first diagnostic model is higher than the second alarm threshold corresponding to the second diagnostic model, the first diagnostic model is used to identify gear wear faults, the second diagnostic model is used to identify bearing damage, and the third diagnostic model is used to identify abnormal gear backlash or tooth back damage.

3. The method of claim 2, wherein, When the target diagnostic model is the first diagnostic model, the step of extracting and analyzing features from the vibration and noise data based on the target diagnostic model to determine whether the transmission chain has a fault specifically includes: The current gear meshing frequency is determined based on the traction motor speed and the gearbox transmission ratio; Based on the first diagnostic model, the energy ratio of the vibration noise data to the gear meshing frequency is determined; Based on the energy percentage and the first alarm threshold, it is determined whether there is a fault in the gears of the transmission chain.

4. The method of claim 2, wherein, When the target diagnostic model is the second diagnostic model, the step of extracting and analyzing features from the vibration and noise data based on the target diagnostic model to determine whether the transmission chain has a fault specifically includes: The vibration noise data is subjected to envelope demodulation processing to obtain the envelope spectrum; Based on the envelope spectrum and bearing geometric parameters, determine the bearing outer ring fault characteristic frequency and bearing inner ring fault characteristic frequency corresponding to the bearing in the transmission chain; Based on the bearing outer ring fault characteristic frequency, the bearing inner ring fault characteristic frequency, and the second alarm threshold, it is determined whether there is a fault in the bearing in the transmission chain.

5. The method of claim 2, wherein, When the target diagnostic model is a third diagnostic model, the step of extracting and analyzing features from the vibration and noise data based on the target diagnostic model to determine whether the transmission chain has a fault specifically includes: Determine the energy distribution parameters of the vibration noise data within the preset frequency band; Based on the energy distribution parameters, determine whether there is abnormal gear backlash or tooth back damage in the transmission chain.

6. The method of claim 1, wherein, The at least two sensors specifically include: A first sensor is installed at the non-drive end of the traction motor of the locomotive. The sensitive shaft of the first sensor is arranged radially along the traction motor and is used to collect vibration and noise data of the bearing and rotor of the traction motor. A second sensor is installed in the gearbox housing of the locomotive. The sensitive axis of the second sensor is arranged along the normal direction of the gear meshing line in the gearbox, and is used to collect vibration and noise data of the gearbox.

7. A safety monitoring device, characterized by include: The data acquisition unit is used to acquire real-time operating condition data of the locomotive and to acquire vibration and noise data corresponding to at least two test points through at least two sensors installed on the locomotive's transmission chain. The diagnostic model determination unit is used to determine the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models based on the real-time operating condition data. The fault identification unit is used to extract and analyze the vibration and noise data according to the target diagnosis model to determine whether there is a fault in the transmission chain. The fault diagnosis unit is used to perform coherence analysis on the vibration and noise data corresponding to the at least two test points when the judgment result obtained by the fault identification unit is yes, to obtain the coherence analysis result, and to generate a fault diagnosis result based on the coherence analysis result.

8. A safety monitoring device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the following operations: The locomotive's real-time operating condition data is acquired, and vibration and noise data corresponding to at least two test points are acquired through at least two sensors installed on the locomotive's drive train. Based on the real-time operating condition data, determine the target diagnostic model corresponding to the current operating condition of the locomotive from at least two pre-built diagnostic models; Based on the target diagnostic model, feature extraction and analysis are performed on the vibration and noise data to determine whether there is a fault in the transmission chain; When the judgment result is yes, coherence analysis is performed based on the vibration and noise data corresponding to the at least two test points to obtain the coherence analysis result, and a fault diagnosis result is generated based on the coherence analysis result.

9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of applications, cause the electronic device to perform the security monitoring method as described in any one of claims 1-6.

10. A computer program product, characterised in that, It includes a computer program that, when executed by a processor, implements the security monitoring method as described in any one of claims 1-6.

Images