System and method for monitoring, detecting and alarming air leakage of working cylinder of railway large machine

Abstract

The invention discloses an air leakage monitoring, detecting and alarming system and method for a working air cylinder of a railway large machine. The system comprises a sensor module, a data collecting and processing module and an alarming module. The sensor module is installed on each working air cylinder and used for collecting all parameter data in the air cylinders in real time. The data collecting and processing module is connected with the sensor module and the alarm module and used for analyzing and processing original data collected by the sensor module, obtaining air leakage quantitative data of the working air cylinder and sending a corresponding instruction to the alarm module. And the alarm module sends out an alarm signal after receiving the instruction of the data acquisition and processing module. Compared with the prior art, the air leakage fault of the air cylinder can be accurately recognized, the air leakage degree can be quantitatively evaluated, data support is provided for a maintainer to formulate a scientific and reasonable maintenance strategy, the detection accuracy and reliability are remarkably improved, and the misjudgment rate and the missed judgment rate are effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of rail transit technology, and in particular to a system and method for monitoring and detecting air leakage in the working cylinder of a large railway locomotive. Background Art

[0002] Under the operating conditions of large-scale railway maintenance machinery (hereinafter referred to as railway large machinery), working cylinder leakage failures occur frequently, and it is difficult to achieve real-time monitoring and early warning. This failure will not only cause the equipment output power to decrease and the fuel consumption rate to increase, but in severe cases it will also cause functional failure of the equipment, which will have a significant impact on the routine maintenance of the railway line and even endanger the safety of railway driving.

[0003] At present, the detection of cylinder leakage of railway large machinery mainly relies on manual regular inspections, and maintenance personnel make qualitative judgments on the cylinder status by means of experience such as hearing and touch. This method has many limitations: first, the detection efficiency is low, and it is impossible to achieve real-time monitoring of all time periods and all working conditions; second, the detection results are significantly affected by the technical level and subjective judgment of maintenance personnel, and it is very easy to make misjudgments and missed judgments; third, for early minor leakage faults, manual detection methods are not sensitive enough and it is difficult to detect potential fault hazards. As time accumulates, it may cause equipment failures to further deteriorate.

[0004] Therefore, the industry currently lacks a monitoring, detection and alarm system with high timeliness and precision. It is unable to conduct real-time dynamic monitoring of cylinder leakage status and trigger alarms in a timely manner, resulting in slow maintenance response, increased equipment downtime, and a significant increase in maintenance costs. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide a railway large locomotive working cylinder leakage monitoring detection alarm system and method which can improve the detection accuracy and reliability.

[0006] The technical solution provided by the present invention is as follows: A railway large locomotive working cylinder air leakage monitoring detection alarm system comprises a sensor module, a data acquisition and processing module, and an alarm module; the sensor module is installed on each working cylinder and is used for real-time acquisition of various parameter data in the cylinder; the data acquisition and processing module is connected to the sensor module and the alarm module, and is used for analyzing and processing the original data collected by the sensor module, obtaining the quantitative data of the air leakage of the working cylinder, and sending the corresponding instructions to the alarm module; the alarm module sends an alarm signal after receiving the instruction from the data acquisition and processing module.

[0007] Preferably, it also includes a display module, which is connected to the data acquisition and processing module and is used to display the working status of each cylinder. The display of the working status of each cylinder includes displaying normal operation, slight leakage, and severe leakage conditions, and quantifying the degree of leakage.

[0008] Preferably, the parameters collected by the sensor module include pressure, temperature, gas flow, and voltage.

[0009] Preferably, the data acquisition and processing module includes an integrated analysis of pressure, temperature, gas flow, and voltage, and a cylinder working state evaluation model obtained using a machine learning algorithm.

[0010] Preferably, the machine learning algorithm is support vector regression.

[0011] Preferably, the input parameters of the cylinder working state evaluation model are the effective value of current, the pressure change rate, and the temperature, and the output parameters are the leakage rate and the confidence level.

[0012] A method for monitoring, detecting and alarming air leakage in the working cylinder of a railway large locomotive adopts the above-mentioned monitoring, detecting and alarming system for monitoring, detecting and alarming air leakage in the working cylinder of a railway large locomotive, and the method comprises: using a sensor module to collect real-time data; preprocessing the collected voltage signal to extract the characteristics of the voltage signal; comparing the extracted characteristics with the existing characteristic library under normal / leakage state to determine whether there is a leakage phenomenon; if so, obtaining the leakage rate by using a cylinder working state evaluation model; and performing multi-level alarm according to different leakage rates.

[0013] Preferably, the preprocessing of the collected voltage signal to extract the characteristics of the voltage signal includes: performing sliding average filtering on the voltage signal collected by the ADC; calculating the time domain characteristics of the signal, wherein the time domain characteristics include effective value, peak value, and kurtosis.

[0014] Preferably, comparing the extracted features with an existing feature library in normal / leakage states to determine whether there is leakage includes: using the Mahalanobis distance method to calculate the similarity between the real-time signal and the feature library, and introducing physical model correction in the determination process.

[0015] Preferably, the method for obtaining the cylinder working state evaluation model includes: establishing a leakage rate prediction model based on support vector regression; data collection, including collecting multiple groups of samples in a bench test, and then marking the leakage rate by a flow method; model training, including using 70% of the data for training and 30% for verification, and using grid search to optimize SVR parameters, introducing transfer learning to deal with differences between different models, and obtaining the cylinder working state evaluation model after training and verification are completed.

[0016] Compared with the prior art, the railway large locomotive working cylinder leakage monitoring detection alarm system and method of the present invention obtains the quantitative leakage data of the working cylinder by setting up a data acquisition and processing module. It can not only accurately identify the cylinder leakage fault, but also quantitatively evaluate the degree of leakage, and provide data support for maintenance personnel to formulate scientific and reasonable maintenance strategies, which significantly improves the accuracy and reliability of detection and effectively reduces the misjudgment and missed judgment rates. DETAILED DESCRIPTION

[0017] In order 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. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] In the embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely schematic. For example, the division of units and modules is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or modules can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0019] In addition, all functional units in the embodiments of the present application may be integrated into one processor, or each unit may be a separate device, or two or more units may be integrated into one device; each functional unit in the embodiments of the present application may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0020] A person skilled in the art can understand that all or part of the steps of the following method embodiments can be completed by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, the steps of the following method embodiments are executed; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a magnetic disk or an optical disk, and other media that can store program codes.

[0021] It should be understood that if "system", "device", "unit" and / or "module" are used in this application, it is only a method for distinguishing different units, elements, components, parts or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0022] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "multiple" and "several" mean two or more, unless otherwise clearly and specifically defined.

[0023] It should also be noted that, in this article, terms such as "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that an article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the article or device including the above elements.

[0024] The embodiment of the present invention provides a railway locomotive working cylinder leakage monitoring detection alarm system, including a sensor module, a data acquisition and processing module, an alarm module, and a display module. The data acquisition and processing module connects the sensor module, the alarm module, and the display module. The modules can work together through standardized data interfaces and communication protocols (such as RS485 and CAN bus). In terms of hardware, the sensor module can be embodied as a plurality of sensors installed on each working cylinder, the data acquisition and processing module can be integrated on the control motherboard of the railway locomotive, including related chips and other electronic components, the alarm module can be an audible and visual alarm or a voice player, and the display module can be a display screen on the railway locomotive. The modules are connected by communication cables.

[0025] The sensor module is installed on each working cylinder to collect various parameter data in the cylinder in real time. In this embodiment, the parameters collected by the sensor module include pressure, temperature, gas flow, and voltage, and the corresponding parameters may include a pressure sensor, a temperature sensor, a gas flow sensor, and a voltage sensor.

[0026] The data acquisition and processing module is used to analyze and process the raw data collected by the sensor module, obtain the quantitative data of the air leakage of the working cylinder (the air leakage rate in this embodiment), and send the corresponding instructions to the alarm module. In this embodiment, the data acquisition and processing module includes an integrated analysis of pressure, temperature, gas flow, and voltage, and a cylinder working state evaluation model obtained by a machine learning algorithm. The machine learning algorithm is preferably support vector regression. The input parameters of the cylinder working state evaluation model are the effective value of the current, the pressure change rate, and the temperature, and the output parameters are the air leakage rate and the confidence level. The effective value of the current can be obtained by converting the voltage value.

[0027] The effective value of current is usually the current required when the heating device on the sampling sensor is heated to 80 degrees. In this system, the reference current effective value is set to the current measurement value collected by the sensor in real time when there is no leakage (i.e. normal operation). When the actual ambient temperature is used and there is a weak leakage flow, the sensor temperature will be lowered, resulting in an increase in current. The leakage amount can be obtained by comparing it with the reference current effective value and then converting it into a 16-bit digital signal through PID conversion.

[0028] After receiving the instruction from the data acquisition and processing module, the alarm module sends out an alarm signal. The alarm signal can be an audible and visual alarm or / and a voice prompt. Multiple levels of alarm can be performed according to different leakage rates.

[0029] The display module is connected to the data acquisition and processing module, and is used to display the working status of each cylinder, including normal operation, slight leakage, and severe leakage, and quantitatively display the degree of leakage. Of course, in other embodiments, the display module may not be provided.

[0030] This embodiment also provides a method for monitoring, detecting and alarming air leakage in the working cylinder of a large railway locomotive, which adopts the above-mentioned monitoring, detecting and alarming system for monitoring, detecting and alarming air leakage in the working cylinder of a large railway locomotive.

[0031] The method comprises the following steps.

[0032] The sensor module is used to collect real-time data, including data on parameters such as pressure, temperature, gas flow, and voltage.

[0033] The collected voltage signal is preprocessed to extract the characteristics of the voltage signal, specifically including: performing sliding average filtering on the voltage signal collected by the ADC (analog-to-digital converter); calculating the time domain characteristics of the signal, which include effective value, peak value, and kurtosis.

[0034] The extracted features are compared with the existing feature library under normal / leakage conditions to determine whether there is leakage. Specifically, the feature library under normal / leakage conditions is first established, and then the Mahalanobis distance method is used to calculate the similarity between the real-time signal and the feature library. Physical model correction is introduced in the judgment process (considering cylinder pressure and temperature compensation).

[0035] If so, the leakage rate is obtained using the cylinder working state assessment model. The cylinder working state assessment model is obtained by: establishing a leakage rate prediction model based on support vector regression; data collection, including collecting multiple groups of samples (generally more than 1,000 groups, including normal and different degrees of leakage samples) in the bench test, and then marking the leakage rate by the flow method; model training, including using 70% of the data for training and 30% for verification, and using grid search to optimize SVR (support vector machine) parameters, introducing transfer learning to deal with differences in different models, and obtaining the cylinder working state assessment model after training and verification. Input the effective value of current, pressure change rate, and temperature into the cylinder working state assessment model to obtain the leakage rate data.

[0036] Multi-level alarm is provided according to different leakage rates.

[0037] Compared with the prior art, this embodiment has the following effects: Real-time and accurate monitoring: It can realize the full-time and high-precision real-time monitoring of the leakage status of the working cylinder of the railway large machine, and can timely capture the potential fault hazards in the early stage, providing strong support for the preventive maintenance of the equipment. Make the line smoother and more stable; Improve equipment reliability: effectively avoid equipment failures caused by cylinder leakage, improve the stability and reliability of equipment operation, reduce equipment failure rate, and extend equipment service life; Reduce maintenance costs: Through timely alarm and accurate fault diagnosis, equipment downtime is shortened, unnecessary maintenance work is reduced, maintenance costs are reduced, and equipment availability and operational efficiency are improved; Ensure railway operation safety: Ensure the normal operation of railway locomotives and provide technical support for high-quality maintenance of railway lines, thereby effectively improving the safety and reliability of railway operation.

[0038] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A railway locomotive working cylinder leakage monitoring detection alarm system, characterized in that: It includes a sensor module, a data acquisition and processing module, and an alarm module; the sensor module is installed on each working cylinder and is used to collect various parameter data in the cylinder in real time; the data acquisition and processing module is connected to the sensor module and the alarm module, and is used to analyze and process the original data collected by the sensor module, obtain the quantitative data of the leakage of the working cylinder, and send corresponding instructions to the alarm module; the alarm module sends an alarm signal after receiving the instruction from the data acquisition and processing module.

2. The railway locomotive working cylinder leakage monitoring detection alarm system according to claim 1, characterized in that: It also includes a display module, which is connected to the data acquisition and processing module and is used to display the working status of each cylinder. The display of the working status of each cylinder includes displaying normal operation, slight leakage, and severe leakage conditions, and quantifying the degree of leakage.

3. The railway locomotive working cylinder leakage monitoring detection alarm system according to claim 1, characterized in that: The parameters collected by the sensor module include pressure, temperature, gas flow, and voltage.

4. The railway locomotive working cylinder leakage monitoring detection alarm system as claimed in claim 3, characterized in that: The data acquisition and processing module includes integrated analysis of pressure, temperature, gas flow, and voltage, and a cylinder working status evaluation model obtained using a machine learning algorithm.

5. The railway locomotive working cylinder air leakage monitoring detection alarm system as claimed in claim 4, characterized in that: The machine learning algorithm is support vector regression.

6. The railway locomotive working cylinder leakage monitoring detection alarm system as claimed in claim 4, characterized in that: The input parameters of the cylinder working state evaluation model are the effective value of current, the pressure change rate, and the temperature, and the output parameters are the leakage rate and the confidence level.

7. A method for monitoring, detecting and alarming air leakage in a working cylinder of a railway locomotive, characterized in that: A railway locomotive working cylinder leakage monitoring, detection and alarm system as described in any one of claims 4 to 6 is used, and the method includes: using a sensor module to collect real-time data; preprocessing the collected voltage signal to extract the characteristics of the voltage signal; comparing the extracted characteristics with the existing feature library under normal / leakage conditions to determine whether there is a leakage phenomenon; if so, using a cylinder working state evaluation model to obtain the leakage rate; and performing multi-level alarms according to different leakage rates.

8. The method for monitoring, detecting and alarming air leakage in the working cylinder of a railway locomotive as claimed in claim 7, characterized in that: The preprocessing of the collected voltage signal to extract the characteristics of the voltage signal includes: performing sliding average filtering on the voltage signal collected by the ADC; and calculating the time domain characteristics of the signal, wherein the time domain characteristics include effective value, peak value, and kurtosis.

9. The method for monitoring, detecting and alarming air leakage in the working cylinder of a railway locomotive as claimed in claim 8, characterized in that: The comparing the extracted features with the existing feature library under normal / leakage state to determine whether there is leakage includes: using Mahalanobis distance method to calculate the similarity between the real-time signal and the feature library, and introducing physical model correction in the determination process.

10. The method for monitoring, detecting and alarming air leakage in the working cylinder of a railway locomotive according to claim 7, 8 or 9, characterized in that: The method for obtaining the cylinder working state evaluation model includes: establishing a leakage rate prediction model based on support vector regression; data collection, including collecting multiple groups of samples in a bench test, and then marking the leakage rate through a flow method; model training, including using 70% of the data for training and 30% for verification, and using grid search to optimize SVR parameters, introducing transfer learning to deal with differences between different models, and obtaining the cylinder working state evaluation model after training and verification are completed.