Leak detection system, method and locomotive

Abstract

The embodiment of the present application provides a leakage detection system, a method and a locomotive, the leakage detection system comprises a sensor unit and a signal processing unit; the sensor unit comprises, from bottom to top, a base, a transduction layer for converting mechanical vibration into an electric signal, and a gas-sensitive material layer; the transduction layer can output a first vibration signal, the gas-sensitive material layer can output a raw mixed signal comprising an effective target gas signal and vibration interference, and the sensor unit is arranged at a target area of the locomotive; the signal processing unit is used for determining the effective target gas signal in the target area according to the first vibration signal and the raw mixed signal, and determining that target gas leakage occurs in the target area when the effective target gas signal meets a first preset condition.

Description

Technical Field

[0001] This application relates to the field of electric locomotive technology, and in particular to leakage detection systems, methods and locomotives. Background Technology

[0002] As a core subsystem ensuring the reliability of hydrogen-powered locomotives, the performance of the hydrogen leak safety detection system directly affects the overall vehicle safety level and operational efficiency.

[0003] In related technologies, gas sensors are used to detect hydrogen leaks. However, when deployed on railway locomotives, the mechanical vibrations caused by track irregularities are efficiently transmitted through the car body's steel structure to the gas sensor's installation location. This causes disturbances at the electrolyte interface and micro-displacements of the electrodes within the sensor's sensitive element, resulting in significant non-gas-related fluctuations superimposed on the output signal, leading to a high false alarm rate for hydrogen leak detection. Summary of the Invention

[0004] The purpose of this application is to provide a leak detection system, method, and locomotive that can solve the problem of high false alarm rate caused by vibration in leak detection sensors in related technologies.

[0005] To solve the above-mentioned technical problems, the embodiments of this application are implemented through the following aspects.

[0006] In a first aspect, embodiments of this application provide a leak detection system, including a sensor unit and a signal processing unit; the sensor unit, from bottom to top, includes: a base, a transducer layer that converts mechanical vibration into an electrical signal, and a gas-sensitive material layer; the transducer layer is capable of outputting a first vibration signal, and the gas-sensitive material layer is capable of outputting a raw mixed signal including an effective target gas signal and vibration interference; the sensor unit is disposed in a target area of ​​a locomotive; the signal processing unit is used to determine an effective target gas signal in the target area based on the first vibration signal and the raw mixed signal, and to determine that a target gas leak has occurred in the target area if the effective target gas signal meets a first preset condition.

[0007] Secondly, embodiments of this application provide a leak detection method executed by a leak detection system. The leak detection system includes a sensor unit and a signal processing unit. The sensor unit, from bottom to top, includes: a base, a transducer layer that converts mechanical vibration into an electrical signal, and a gas-sensitive material layer. The transducer layer can output a first vibration signal, and the gas-sensitive material layer can output a raw mixed signal including an effective target gas signal and vibration interference. The sensor unit is disposed in a target area of ​​a locomotive. The leak detection method includes: determining an effective target gas signal in the target area based on the first vibration signal and the raw mixed signal; and determining that a target gas leak has occurred in the target area when the effective target gas signal meets a first preset condition.

[0008] Thirdly, embodiments of this application provide a locomotive including the leakage detection system described in the first aspect above.

[0009] In this embodiment, the leak detection system includes a sensor unit and a signal processing unit. The sensor unit, from bottom to top, includes: a base, a transducer layer that converts mechanical vibration into an electrical signal, and a gas-sensitive material layer. The transducer layer outputs a first vibration signal, and the gas-sensitive material layer outputs a raw mixed signal including an effective target gas signal and vibration interference. The sensor unit is positioned in the target area of ​​the locomotive. The signal processing unit determines the effective target gas signal in the target area based on the first vibration signal and the raw mixed signal, and determines that a target gas leak has occurred in the target area if the effective target gas signal meets a first preset condition. The non-gas-related fluctuations in the effective target gas signal are significantly reduced compared to the raw mixed signal, enabling a more accurate characterization of the target gas concentration in the target area. Therefore, the leak detection system can reduce the false alarm rate caused by vibration. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This illustration shows a schematic diagram of a leak detection system provided in an embodiment of this application; Figure 2 Show Figure 1 An exploded view of the structure of the sensor unit and piezoelectric actuator; Figure 3 This illustration shows a flowchart of a leakage detection method provided in an embodiment of this application; Figure 4 A schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0012] Figure label: 100 - Leak Detection System; 110 - Sensor unit; 111 - Base; 112 - Transducer layer; 113 - Gas-sensitive material layer; 114 - Housing; 115 - Electrode layer; 116 - Electrical pins; 120 - Signal Processing Unit; 130 - Piezoelectric actuator. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0014] As a core subsystem ensuring the reliability of hydrogen-powered locomotives, the performance of the hydrogen leak safety detection system directly affects the overall vehicle safety level and operational efficiency. Typically, gas sensors are installed in critical areas such as the outer wall of the hydrogen storage tank, the hydrogen pipeline support, and the fuel cell stack inlet to detect hydrogen leaks.

[0015] In related technologies, gas sensors can be used to detect hydrogen leaks. However, when deployed on railway locomotives, the mechanical vibrations caused by track irregularities are efficiently transmitted through the car body's steel structure to the gas sensor's installation location. This causes disturbances at the electrolyte interface and micro-displacements of the electrodes within the sensor's sensitive element, resulting in significant non-gas-related fluctuations superimposed on the output signal. Consequently, the signal-to-noise ratio of the output signal is low, leading to a high false alarm rate for hydrogen leak detection.

[0016] To solve this technical problem, the inventors of this application propose a leakage detection system, method, and locomotive.

[0017] In this embodiment of the application, "locomotive" can refer to a train locomotive, which is a type of railway equipment.

[0018] Figure 1It illustrates a structural schematic diagram of a leak detection system 100 provided in an embodiment of the present application. The leak detection system 100 may include a connected sensor unit 110 and a signal processing unit 120. The sensor unit 110 is disposed in a target area of a locomotive, and the signal processing unit 120 acquires signals collected by the sensor unit 110, and determines whether a target gas leak occurs in the target area of the locomotive according to the signals.

[0019] Referring Figure 2 , in the sensor unit 110, a base 111, a transducing layer 112 and a gas-sensitive material layer 113 may be arranged in a stacked manner. From the bottom layer to the top layer, the sensor unit 110 may sequentially comprise: the base 111, the transducing layer 112 that converts mechanical vibration into electrical signals, and the gas-sensitive material layer 113. The transducing layer 112 can sense mechanical vibration and output a first vibration signal, and the gas-sensitive material layer 113 can output an original mixed signal including an effective target gas signal and vibration interference (or noise). After the signal processing unit 120 acquires the first vibration signal and the original mixed signal, it determines the effective target gas signal in the target area according to the first vibration signal and the original mixed signal, and determines that a target gas leak occurs in the target area when the effective target gas signal meets a first preset condition.

[0020] Compared with the related art, where whether a target gas leak occurs is determined based on a signal with significant non-gas-related fluctuations superimposed output from the gas-sensitive material layer 113 of a gas-sensitive sensor, that is, whether a target gas leak occurs is directly determined based on the original mixed signal mixed with a large amount of vibration interference (or noise), in the embodiments of the present application, the effective target gas signal is decoupled from the vibration interference from the original mixed signal according to the first vibration signal, so as to obtain the effective target gas signal. Non-gas-related fluctuations in the obtained effective target gas signal are significantly reduced compared with those in the original mixed signal, therefore the signal-to-noise ratio of the obtained effective target gas signal is relatively higher, which can more accurately characterize the concentration of the target gas in the target area, thereby reducing the false alarm rate caused by vibration.

[0021] Referring Figure 2 , the sensor unit 110 of the present application may further include a housing 114, an electrode layer 115, and an electrical pin 116.

[0022] The housing 114 can accommodate a gas-sensitive material layer 113, an electrode layer 115, a transducer layer 112, and a portion of a base 111. The housing 114 has openings to allow gas to flow into the surface of the gas-sensitive material layer 113. The electrode layer 115 can be disposed between the transducer layer 112 and the gas-sensitive material layer 113. To improve the sensitivity and response speed of the sensor unit 110, the electrode layer 15 can be an interdigitated electrode; and to improve the stability of the sensor unit 110, the electrode layer 15 can be a micro-heating electrode. The electrode layer 15 can be both an interdigitated electrode and a micro-heating electrode. The electrical pin 116 can connect the signal processing unit 120 and the electrode layer 15 to transmit the first vibration signal and the original mixed signal acquired by the sensor unit 110 to the signal processing unit 120. Furthermore, the first vibration signal and the original mixed signal output by the sensor unit 110 are physically decoupled.

[0023] In this embodiment, at certain locomotive speeds, the first vibration signal output by the transducer layer 112 is consistent with or very close to the vibration interference in the original mixed signal output by the gas-sensitive material layer 113. In this case, the signal processing unit 120 can directly subtract the first vibration signal from the original mixed signal to determine the effective target gas signal. However, in other cases, the vibration interference in the first vibration signal output by the transducer layer 112 differs significantly from that in the original mixed signal output by the gas-sensitive material layer 113. Even after subtracting the first vibration signal from the original mixed signal, the resulting effective target gas signal still has considerable vibration interference. Therefore, in one embodiment, the signal processing unit 120 is used to determine the effective target gas signal in the target region based on the first vibration signal and the original mixed signal, including: filtering the original mixed signal according to a preset filtering algorithm, the first vibration signal, and the current locomotive speed to determine the effective target gas signal in the target region.

[0024] In this embodiment, the preset filtering algorithm can be an adaptive Kalman filter algorithm. The signal processing unit 120 is used to filter the original mixed signal according to the preset filtering algorithm, the first vibration signal, and the current speed of the locomotive to determine the effective target gas signal in the target area. This can include: determining the gas concentration signal of the gas-sensitive material layer 113 according to the original mixed signal and the first vibration signal; determining the measurement noise covariance R of the adaptive Kalman filter algorithm according to the current speed of the locomotive; and determining the effective target gas signal according to the gas concentration signal and the measurement noise covariance R. Therefore, accurate effective target gas signals can be obtained at different locomotive speeds, reducing the false alarm rate for gas leaks.

[0025] In one possible implementation, the preset filtering algorithm may not be the adaptive Kalman filter algorithm, and other filtering algorithms, such as particle filtering, H∞ filtering or wavelet transform denoising, are all signal processing algorithms that can estimate the true state from noisy signals.

[0026] In this embodiment, a mapping relationship between locomotive speed and the measurement noise covariance R in the adaptive Kalman filter algorithm can be pre-established. Then, based on the current locomotive speed, the measurement noise covariance R of the adaptive Kalman filter algorithm is dynamically adjusted. For example, when the speed is between 30-80 km / h, the R value is its original value; when the speed is greater than 80 km / h, the R value is updated to 1.3 times its original value; when the speed is less than 30 km / h, the R value is updated to 0.8 times its original value. The update period for the R value can be fixed at 500 milliseconds to avoid system instability caused by frequent switching. In the adaptive Kalman filter algorithm, when the R value is large (vehicle speed is high, such as exceeding 80 km / h), the signal processing unit 120 can reduce its sensitivity to the current signal in the sensor unit 110 to avoid false alarms caused by continuous, high-frequency vibrations. Conversely, when the R value is small (vehicle speed is slow, such as less than 30 km / h), the signal processing unit 120 can increase its sensitivity to the current signal in the sensor unit 110 to avoid misjudging some gas signals as vibration interference and deleting them. The original value of the measurement noise covariance R can be 0.5.

[0027] In one possible implementation, when the R value is large, the adaptive Kalman filter algorithm in the signal processing unit 120 can predict based on historical data, i.e., increase the confidence in the prediction model in the adaptive Kalman filter algorithm, so as to predict the current effective target gas signal based on the historically stored effective target gas signals. Conversely, when the R value is small, the adaptive Kalman filter algorithm in the signal processing unit 120 can determine the current effective target gas signal based on the current signal in the sensor unit 110.

[0028] During prolonged testing, vibration interference in the gas-sensitive material layer 113 and the first vibration signal of the transducer layer 112 may accumulate continuously, resulting in the accumulation of previous signals in both the first vibration signal and the original mixed signal input to the signal processing unit 120 each time. For example, the transducer layer 112 may have deformed in previous cycles. The deformation caused by mechanical vibration detected in the current cycle is superimposed on the deformation of the previous cycles. Therefore, the first vibration signal output in the current cycle is superimposed with previous vibration signals, which leads to the inaccuracy of the first vibration signal and the original mixed signal obtained by the signal processing unit 120 due to accumulated errors.

[0029] Therefore, in this embodiment, the leak detection system 100 may further include a compensation actuator, which may include a piezoelectric actuator 130. The piezoelectric actuator 130 may be located below the base 111 on the side opposite to the transducer layer 112, and both the base 111 and the transducer layer 112 are made of deformable materials. The piezoelectric actuator 130 is used to generate reverse deformation to compensate for the deformation of the sensor unit 110, including compensating for the deformation of the transducer layer 112 and the gas-sensitive material layer 113. The piezoelectric actuator 130 is disposed below the base 111, and its small deformation can drive small deformations of the base 111, the transducer layer 112, and the gas-sensitive material layer 113. For example, the base 111 is made of silicone rubber, and the transducer layer 112 is made of piezoelectric material. The piezoelectric actuator 130 can undergo reverse deformation to compensate for the deformation of the transducer layer 112 and the gas-sensitive material layer 113 in the previous cycle or several previous cycles, thereby keeping the transducer layer 112 and the gas-sensitive material layer 113 relatively stationary so as to acquire real-time signals more accurately in the next cycle or subsequent cycles.

[0030] Figure 2 The piezoelectric driver 130 shown also has electrical pins (unlabeled) that can be connected to the signal processing unit 120.

[0031] After determining the effective gas signal in the target area, the signal processing unit 120 can also be used to: determine the vibration residual signal of the previous cycle based on the difference between the original mixed signal and the effective target gas signal; input a driving electrical signal to the piezoelectric actuator 130 based on the vibration residual signal, the driving electrical signal causing the piezoelectric actuator 130 to generate reverse deformation, the reverse deformation compensating for the deformation of the transducer layer 112 and the gas-sensitive material layer 113 in the sensor unit 110, so as to reduce the cumulative error of the transducer layer 112 and the gas-sensitive material layer 113 in the next cycle, so that the real-time signal can be obtained more accurately in the next cycle, thereby reducing the false alarm rate of the leak detection system 100.

[0032] To ensure that the reverse deformation of the piezoelectric actuator 130 can completely compensate for the deformation of the transducer layer 112, the piezoelectric actuator 130 and the transducer layer 112 in the sensor unit 110 are manufactured using the same materials and processes to ensure consistency in electromechanical response characteristics. For example, when the transducer layer 112 is a piezoelectric ceramic sheet, the piezoelectric actuator 130 also uses a piezoelectric ceramic sheet, and both are manufactured using the same process.

[0033] The piezoelectric actuator 130 can be mounted below the base 111 of the sensor unit 110 and can generate a reverse displacement of less than 5 micrometers after receiving a drive command, with a response delay of no more than 50 milliseconds.

[0034] In one possible implementation, the compensation actuator may also exclude the piezoelectric actuator 130 and instead employ other precision micro-displacement actuators, such as voice coil motors, magnetostrictive actuators, or super magnetostrictive actuators.

[0035] In this embodiment, the transducer layer 112 and the gas-sensitive material layer 113 are respectively connected to independent signal channels, thereby achieving physical decoupling of the first vibration signal and the original mixed signal.

[0036] In this embodiment of the application, the signal processing unit 120 can also be used to: issue a prompt after determining that a target gas leak has occurred in the target area, which may be an alarm prompt.

[0037] In this embodiment, the first preset condition may include at least one of the following: the effective target gas signal exceeds a preset concentration threshold; the effective target gas signal exceeds the preset concentration threshold and the duration exceeds a preset duration. The preset concentration threshold may be a threshold set according to safety requirements, and the preset duration may be 2 seconds, 1 second, 3 seconds, etc.

[0038] In this embodiment of the application, the target area can be an area where it is necessary to carefully detect whether the concentration of the target gas exceeds a preset concentration threshold, such as the area around a hydrogen storage tank, the area around a hydrogen pipeline, or the area near the inlet of a hydrogen fuel cell stack. Therefore, the target area includes at least one of the following: the outer wall of the hydrogen storage tank, the support of the hydrogen pipeline, and the inlet of the fuel cell stack.

[0039] Of course, in this embodiment, the target gas monitored by the leak detection system 100 is hydrogen, therefore, the target area is mainly set in the area associated with hydrogen. It should be understood that when the target gas monitored by the leak detection system is other gases, the location of the target area can also be flexibly adjusted as needed.

[0040] In this embodiment, multiple sensor units 110 can be arranged in a distributed array in the target area to fully detect whether a target gas leak has occurred in the target area, and all multiple sensor units 110 are connected to the signal processing unit 120. For example, the multiple sensor units 110 can be deployed in the target area in the form of a triangular grid, which can be arranged in a 1.2m × 1.2m triangular grid.

[0041] To facilitate quick and easy placement of the sensor unit 110 in the target area, a magnetic connection can be established between the sensor unit 110 and the mounting surface of the target area. The magnetic structure between the sensor unit 110 and the target area may include a combination of a permanent magnet and a soft iron pad to ensure reliable fixation even under vibration conditions with a maximum acceleration of 1.5g.

[0042] In this embodiment, to further reduce the impact of vibration on the sensor unit 110, the base 111 of the sensor unit 110 can be a vibration damping base 111 to absorb some of the vibration energy, preventing all locomotive vibration from acting on the transducer layer 112 and the gas-sensitive material layer 113, thereby reducing the computational load of the signal processing unit 120. The vibration damping base 111 can be a silicone rubber vibration damping base 111, which can be made of a material with a hardness of Shore A 30 and a thickness of 8 mm, used to absorb low-frequency vibration energy with frequencies below 50 Hz.

[0043] In the sensor unit 110, the damping base 111 mainly absorbs low-frequency oscillation energy, while high-frequency vibration energy can be absorbed and detected by the transducer layer 112.

[0044] In this embodiment, the transducer layer 112 can be a piezoelectric material layer, such as a piezoelectric ceramic sheet, and the polarization direction of the piezoelectric ceramic sheet is perpendicular to the mounting plane of the target area to improve its sensitivity. The piezoelectric material layer can also be a piezoelectric thin film; of course, the transducer layer 112 can also be a MEMS accelerometer layer, magnetostrictive sensing layer, etc., preferably capable of sensing mechanical vibrations and converting them into electrical signals. Furthermore, the transducer layer 112 may include other materials after the piezoelectric material.

[0045] In one possible implementation, the piezoelectric ceramic sheet can be made of PZT-5A type piezoelectric material, with dimensions of 20 mm × 20 mm × 0.2 mm, and its polarization direction is perpendicular to the mounting plane.

[0046] In this embodiment, the gas-sensitive material layer 113 can be a nanoporous graphene sensitive membrane, which can be prepared by chemical vapor deposition. The pore size is controlled within the range of 7 nm ± 1 nm, the sheet resistance is 50 ohms per square meter, and it exhibits selective adsorption response only to hydrogen molecules with a response time of 50 milliseconds. Of course, the gas-sensitive material layer 113 can be made of gas-sensitive materials, such as carbon nanotubes, metal oxides (e.g., SnO2), or palladium alloy films. These materials can all change electrical properties (resistance, capacitance, etc.) by adsorbing gases. The gas-sensitive material layer 113 can include other gas-sensitive materials after incorporating the nanoporous graphene sensitive membrane.

[0047] In one embodiment, the first vibration signal output by the transducer layer 112 can be pre-amplified and bandpass filtered before being sent to the field programmable gate array accelerator as an auxiliary observation input to participate in the state correction process of the adaptive Kalman filter algorithm.

[0048] The signal processing unit 120 may include an ARM Cortex-M7 main control chip, a 24-bit Σ-Δ analog-to-digital converter module, and a field-programmable gate array (FPGA) accelerator. The 24-bit Σ-Δ ADC module has a sampling rate of 100 kHz and receives analog signals from each sensor unit 110 via shielded twisted-pair cable. The shielding layer of the twisted-pair cable is grounded at a single point with a grounding resistance of 0.08 ohms. The FPGA accelerator internally includes dedicated hardware logic circuitry for executing an adaptive Kalman filter algorithm and a circular buffer for storing historical vibration data from the most recent 10 seconds.

[0049] The signal processing unit 120 can be installed in a central control cabinet with an IP67 protection rating.

[0050] In one embodiment, the signal processing unit 120 may also be configured with a fault self-diagnosis module, which monitors the operating status of each sensor unit 110 and automatically switches to a redundant channel when abnormal signal drift or communication interruption is detected. The fault self-diagnosis module can periodically inject standard test signals to verify the consistency of sensor responses, with a test period of 10 seconds.

[0051] The leak detection method of this application has been improved at both the physical structure and algorithm levels, thereby achieving stable hydrogen leak identification with high signal-to-noise ratio and low false alarm rate across the entire speed domain, meeting the dual requirements of safety and economy for hydrogen-powered rail transit equipment. Specifically, the sensor unit is improved in terms of physical structure. The transducer layer of the sensor unit acquires the first vibration signal, and the gas-sensitive material layer acquires the original mixed signal. The effective target gas signal can then be obtained based on the original mixed signal and the first vibration signal; that is, the physical structure can decouple the vibration signal and the effective target gas signal. At the algorithm level, an adaptive Kalman filter algorithm is used to measure the noise covariance matrix R based on the current speed of the locomotive, and this is used to filter the original mixed signal, thereby achieving stable hydrogen leak identification with high signal-to-noise ratio and low false alarm rate across the entire speed domain.

[0052] Figure 3 This diagram illustrates a flowchart of a leakage detection method provided in an embodiment of this application. The method can be executed by a leakage detection system or by an electronic device including a leakage detection system, such as a terminal device or a server device. In other words, the method can be executed by a leakage detection system located on a locomotive, and the method can be executed by software or hardware installed on a terminal device or server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. Figure 3 As shown, the method may include the following steps.

[0053] Step S302: Determine the effective target gas signal in the target region based on the first vibration signal and the original mixed signal.

[0054] Step S304: Under the condition that the effective target gas signal meets the first preset condition, it is determined that a target gas leak has occurred in the target area.

[0055] The leak detection method of this application does not directly determine the target gas leak based on the original mixed signal with a low signal-to-noise ratio output by the gas-sensitive material layer, but instead obtains an effective target gas signal with a high signal-to-noise ratio based on the original mixed signal to determine the target gas leak. Therefore, it can detect the target gas leak more accurately and reduce the false alarm rate of leak detection.

[0056] In one embodiment, step S302 may include: filtering the original mixed signal according to a preset filtering algorithm, the first vibration signal and the current speed of the locomotive, to determine the effective target gas signal in the target area.

[0057] In one embodiment, the preset filtering algorithm includes an adaptive Kalman filter algorithm. Step S302 may include: determining the gas concentration signal of the gas-sensitive material layer based on the original mixed signal and the first vibration signal; determining the measurement noise covariance R of the adaptive Kalman filter algorithm based on the current locomotive speed; and determining the effective target gas signal based on the gas concentration signal and the measurement noise covariance R.

[0058] In one embodiment, the leak detection system further includes a compensation actuator comprising a piezoelectric actuator located below the base on a side opposite to the transducer layer, the base and the transducer layer being made of a deformable material, the piezoelectric actuator being used to generate reverse deformation to compensate for the deformation of the sensor unit.

[0059] The above-mentioned leakage detection method may further include step S306: determining the vibration residual signal of the previous cycle based on the difference between the original mixed signal and the effective target gas signal; inputting a driving electrical signal to the piezoelectric actuator based on the vibration residual signal to cause the piezoelectric actuator to generate reverse deformation, the reverse deformation compensating for the deformation of the transducer layer and the gas-sensitive material layer in the sensor unit.

[0060] In this embodiment, the leakage detection method can achieve the technical effects of the above-mentioned leakage detection system, which will not be elaborated here.

[0061] This application also provides a locomotive that can include the above-mentioned leakage detection system and achieve the technical effects of the leakage detection system, which will not be described in detail here.

[0062] Figure 4 The diagram illustrates the hardware structure of an electronic device implementing the embodiments of this application. Referring to the diagram, at the hardware level, the electronic device includes a processor and optionally, an internal bus, a network interface, and a memory. The memory may include RAM, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0063] The processor, network interface, and memory can be interconnected via an internal bus, which can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be categorized as an address bus, data bus, control bus, etc. For ease of illustration, only a single bidirectional arrow is used in this diagram, but this does not imply that there is only one bus or one type of bus.

[0064] 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.

[0065] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming a device at the logical level that locates the target user. The processor executes the program stored in memory and specifically performs the following: Figure 3 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0066] The above is as stated in this application. Figure 3The methods disclosed in the illustrated embodiments can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above methods 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 embodied in the execution of 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.

[0067] The electronic device can also execute the methods described in the preceding method embodiments and achieve the functions and beneficial effects of the methods described in the preceding method embodiments, which will not be repeated here.

[0068] 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.

[0069] This application also proposes a computer-readable storage medium that stores one or more programs, which, when executed by an electronic device including multiple applications, cause the electronic device to perform... Figure 3 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0070] The computer-readable storage medium mentioned above includes read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, etc.

[0071] Furthermore, embodiments of this application also provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, implement the following process: Figure 3 The methods disclosed in the embodiments shown achieve the functions and beneficial effects of the methods described in the preceding method embodiments, and will not be repeated here.

[0072] In summary, the above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

[0073] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0074] 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.

[0075] 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.

[0076] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

Claims

1. A leak detection system, characterized in that, Includes sensor units and signal processing units; The sensor unit, from bottom to top, includes: a base, a transducer layer that converts mechanical vibration into electrical signals, and a gas-sensitive material layer; the transducer layer can output a first vibration signal, and the gas-sensitive material layer can output a raw mixed signal including an effective target gas signal and vibration interference; the sensor unit is disposed in the target area of ​​the locomotive. The signal processing unit is configured to determine the effective target gas signal in the target area based on the first vibration signal and the original mixed signal, and determine that a target gas leak has occurred in the target area if the effective target gas signal meets a first preset condition.

2. The detection system according to claim 1, characterized in that, The signal processing unit is used to determine the effective target gas signal in the target area based on the first vibration signal and the original mixed signal, including: filtering the original mixed signal according to a preset filtering algorithm, the first vibration signal and the current speed of the locomotive, to determine the effective target gas signal in the target area.

3. The detection system according to claim 2, characterized in that, The preset filtering algorithm includes the adaptive Kalman filtering algorithm; In the signal processing unit, the original mixed signal is filtered according to a preset filtering algorithm, the first vibration signal, and the current speed of the locomotive to determine the effective target gas signal in the target area, including: The gas concentration signal of the gas-sensitive material layer is determined based on the original mixed signal and the first vibration signal. Based on the current speed of the locomotive, determine the measurement noise covariance of the adaptive Kalman filter algorithm; The effective target gas signal is determined based on the gas concentration signal and the measurement noise covariance.

4. The detection system according to claim 1, characterized in that, The leakage detection system further includes a compensation actuator, which includes a piezoelectric actuator located below the base on the side opposite to the transducer layer. The base and the transducer layer are made of a deformable material. The piezoelectric actuator is used to generate reverse deformation to compensate for the deformation of the sensor unit. After determining the valid target gas signal in the target region, the signal processing unit is further used for: The vibration residual signal of the previous cycle is determined based on the difference between the original mixed signal and the effective target gas signal. Based on the vibration residual signal, a driving electrical signal is input to the piezoelectric actuator to cause the piezoelectric actuator to generate reverse deformation, which is used to compensate for the deformation of the sensor unit.

5. The detection system according to claim 1, characterized in that, Multiple sensor units are arranged in a distributed array in the target area; the sensor units are magnetically connected to the mounting plane of the target area.

6. The detection system according to claim 1, characterized in that, The base is a shock-absorbing base; and / or, the transducer layer includes a piezoelectric ceramic sheet, the polarization direction of which is perpendicular to the mounting plane of the target area; and / or, the gas-sensitive material layer includes nanoporous graphene.

7. The detection system according to claim 4, characterized in that, The transducer layer is made of the same material and manufactured using the same process as the piezoelectric actuator.

8. The detection system according to claim 1, characterized in that, The target area includes at least one of the following: the outer wall of a hydrogen storage tank, a hydrogen pipeline support, and a fuel cell stack inlet.

9. A leak detection method, characterized in that, Performed by a leak detection system, the leak detection system includes a sensor unit and a signal processing unit. The sensor unit, from bottom to top, includes: a base, a transducer layer that converts mechanical vibration into an electrical signal, and a gas-sensitive material layer. The transducer layer can output a first vibration signal, and the gas-sensitive material layer can output a raw mixed signal including an effective target gas signal and vibration interference. The sensor unit is disposed in the target area of ​​the locomotive. The leak detection method includes: determining an effective target gas signal in the target area based on the first vibration signal and the original mixed signal; and determining that a target gas leak has occurred in the target area when the effective target gas signal meets a first preset condition.

10. A locomotive, characterized in that, The locomotive includes a leak detection system as described in any one of claims 1-8.

Images