CN110647133B - Rail transit equipment state detection maintenance method and system - Google Patents
Rail transit equipment state detection maintenance method and system Download PDFInfo
- Publication number
- CN110647133B CN110647133B CN201910849412.5A CN201910849412A CN110647133B CN 110647133 B CN110647133 B CN 110647133B CN 201910849412 A CN201910849412 A CN 201910849412A CN 110647133 B CN110647133 B CN 110647133B
- Authority
- CN
- China
- Prior art keywords
- equipment
- component
- data
- fault
- life cycle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0267—Fault communication, e.g. human machine interface [HMI]
- G05B23/027—Alarm generation, e.g. communication protocol; Forms of alarm
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a rail transit equipment state detection and maintenance method and a system, wherein the method comprises the following steps: acquiring the fault condition of equipment or each component and the influence factors influencing the service life of the equipment or each component, simulating the application scene under the influence of the influence factors and acquiring the full life cycle data of the equipment or each component to form a full life cycle database, establishing a dynamic model according to the full life cycle database, analyzing and collecting main influencing factors and characteristics influencing the faults, hidden dangers and service lives of the current equipment or each component, receiving the main influencing factors and characteristics to obtain operation state data, analyzing the operation state data and judging whether potential faults exist or not, failure prediction and failure diagnosis are carried out on equipment or each part, a maintenance plan is generated according to a failure analysis result and is sent to a terminal, operation data is obtained by establishing a life database for a detection object and then monitoring, and performing fault prediction and making a maintenance plan according to the operation data so as to ensure that the traffic equipment can normally operate.
Description
Technical Field
The invention relates to the technical field of traffic equipment, in particular to a rail traffic equipment state detection maintenance method and a rail traffic equipment state detection maintenance system.
Background
The maintenance schedule of the rail transit system mainly comprises daily inspection, monthly inspection, frame maintenance, overhaul and the like, and the phenomena of excessive maintenance and insufficient maintenance are easy to occur mainly according to the operation mileage and fault information of a rail transit train and the service hidden danger information of related equipment and facilities. When equipment and facilities have fault hidden trouble, the maintenance is easy to cause late time and machine breakage, and the train operation order is influenced. From the maintenance technology, a large number of vehicle-mounted sensors with redundant functions, complex networking, different interfaces and complex installation are too limited to acquire information in real time, difficulty of returned data in fusion processing analysis is increased, safety detection mainly focuses on passive detection in an empirical fault mode, analysis detection under a physical mechanism rule and discrete detection under a fracture coupling relation due to the lack of a non-stop and non-contact data acquisition mode, and problems of inherent human subjective factor interference, equipment product principle closure and the like cause safety evaluation to be more limited to academic scientific research.
At present, serious obstacles are faced by adopting a predictive maintenance means, the lack of industrial field fault data and operation state data, few data samples, low model precision and the like, so that the correlation between the actual effect and the expectation is large. The greatest difficulty in doing predictive maintenance is the lack of industrial field data. At least two types of historical data, fault data and equipment operating status data, are required to build and train a model for predictive maintenance. And the quantity of the two types of data is large enough, so that the trained model and the reference library are more accurate. On the one hand, however, many devices have a low probability of failure due to downtime, possibly not several times a year, and therefore, the online collection of such data takes a long time. On the other hand, many industrial fields do not have perfect equipment data acquisition systems, or even some systems such as SCADA (supervisory control and data acquisition) systems are also used for completing real-time state monitoring, and for the state data of equipment operation, the storage time is short, and the long-term storage of the equipment data is lacked, so that the maintenance of traffic equipment and facilities is difficult to realize.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art. Therefore, the invention aims to provide a rail transit equipment state detection and maintenance method which can accurately predict faults of the transit equipment and appoint a maintenance plan so as to ensure the normal operation of the transit equipment.
Therefore, the invention has a second purpose of providing a rail transit equipment state detection and maintenance system.
The technical scheme adopted by the invention is as follows:
in a first aspect, the invention provides a rail transit equipment state detection and maintenance method, which is characterized by comprising the following steps:
step S1: acquiring the fault condition of the equipment or each component and influence factors influencing the service life of the equipment or each component according to the basic condition of the equipment or each component, simulating an application scene under the influence of the influence factors of the equipment or each component and acquiring full life cycle data of the equipment or each component to form a full life cycle database, and establishing a dynamic model of the equipment or each component according to the full life cycle database;
step S2: analyzing and collecting main influence factors and characteristics influencing the faults, hidden dangers and service lives of the current equipment or each part according to the current different equipment or each part;
step S3: receiving data of main influence factors and characteristics of current equipment or each part to acquire operation state data, analyzing the operation state data and judging whether the equipment or each part has potential faults or not;
step S4: and performing fault prediction and fault diagnosis on the equipment or each part, generating a maintenance plan according to a fault analysis result and sending the maintenance plan to the terminal.
Further, step S1 includes the steps of:
step S11: analyzing the structure, material, electric control and logic of the equipment or each component by using the operation characteristics;
step S12: acquiring the fault condition of equipment and each part and influence factors influencing the service life of the equipment or each part;
step S13: reproducing the application scene of the equipment or each component, and performing hardware-in-the-loop test simulation under the excitation of the same influence factors according to the relation between the same frequency spectrum and the time-space ratio compression so as to acquire the full life cycle data of the equipment or each component;
step S14: and forming a full life cycle database according to the full life cycle data of the equipment or each component, and establishing a dynamic model of the equipment or each component according to the full life cycle database, wherein the dynamic model comprises a health degree model, a health degradation model and a fault prediction model.
Further, step S2 includes the steps of:
step S21: aiming at different current equipment or each part, analyzing main influence factors and characteristics which influence the faults, hidden dangers and service life of the equipment or each part;
step S22: and collecting analog quantity of main influencing factors and characteristics, converting the analog quantity into a data signal and uploading the data signal to a controller.
Further, step S3 includes the steps of:
step S31: receiving data signals of main influencing factors and characteristics and converting the data signals into running state data of equipment or each part;
step S32: the monitoring software carries out preliminary analysis, filtration and correction on the running state data;
step S33: and presetting an alarm threshold, and comparing the processed running state data with the alarm threshold to judge whether the equipment has potential faults.
Further, step S4 includes the steps of:
s41: performing fault prediction and fault diagnosis on corresponding equipment or components by adopting a fault prediction technology based on a model and a data drive according to the alarm signal;
s42: and performing maintenance feasibility analysis according to the results of fault diagnosis and fault prediction, generating a maintenance plan and sending the maintenance plan to the terminal.
In a second aspect, the present invention provides a method and a system for detecting and maintaining a state of a rail transit device, including:
the acquisition module is used for analyzing the equipment or each part to acquire the fault condition and the influence factor of the equipment or each part;
the model establishing module is used for acquiring life cycle data of the equipment or each component under the application scene of simulating influence factors and establishing a dynamic model;
the analysis module is used for analyzing and collecting main influence factors and characteristics which influence the faults, hidden dangers and service lives of equipment or each component aiming at different current detection objects;
the processing and judging module is used for receiving and processing the running state data of main influencing factors and characteristics of the equipment or each component, and comparing the running state data with a preset alarm threshold value to judge whether a potential fault exists;
the fault diagnosis and prediction module is used for carrying out fault prediction and fault diagnosis on corresponding equipment or each component according to the alarm information;
and the maintenance decision module is used for making a corresponding maintenance plan according to the fault prediction and fault diagnosis result and sending the maintenance plan to the terminal.
Further, the obtaining module comprises:
the analysis unit is used for analyzing the characteristics of the structure, the material, the electric control, the logic, the operation and the like of equipment or each part;
and the acquisition unit is used for acquiring the fault condition and the influence factors of the equipment or each component according to the analysis result of the analysis unit.
Further, the model building module comprises:
the acquisition unit is used for simulating an application scene of the equipment or each component and carrying out hardware-in-the-loop test simulation according to the relation between the same frequency spectrum and space-time same-ratio compression so as to obtain full life cycle data of the equipment or each component;
and the model establishing unit is used for establishing a dynamic model of the equipment or each part according to a full life cycle database formed by the full life cycle data.
Further, the processing and judging module comprises:
the receiving unit is used for receiving factors influencing the normal work of the equipment or each component, the type and the expression form of the fault and converting the factors into operation state data influencing the equipment or each component;
the processing unit is used for analyzing, filtering and correcting the running state data of the equipment or each part;
and the comparison and judgment unit is used for presetting an alarm threshold value, and judging whether a potential fault exists or not when the operation state data is compared with the alarm threshold value.
Further, the fault diagnosis and prediction module comprises:
the model fault prediction unit is used for establishing a physical model or a random process modeling and evaluating the residual service life of the equipment or each component by calculating the functional damage of the equipment or each component and evaluating the damage degree of the components;
and the data driving fault prediction unit is used for mining the implicit information in each data analysis processing method to carry out evaluation, diagnosis and prediction operation.
The invention has the beneficial effects that:
the invention adopts the technical means of firstly detecting the fault condition and the influence factor of the equipment or each part, then acquiring the life cycle of the equipment or each part, monitoring to acquire the operation data, alarming the operation data exceeding the alarm threshold, predicting the fault of the equipment or each part to be alarmed and making the maintenance plan, overcomes the technical problem that the residual service life of machine parts is difficult to predict in the prior art, and realizes the aims of real-time online fault diagnosis, trend prediction and full-life management of the traffic equipment facilities or the parts.
Drawings
FIG. 1 is a schematic structural diagram of a system of an embodiment of a rail transit equipment state detection and maintenance system of the present invention;
FIG. 2 is a flowchart of an embodiment of a rail transit device status detection and maintenance method according to the present invention;
fig. 3 is a detailed flowchart of an embodiment of a rail transit device state detection and maintenance method according to the present invention.
Reference numerals: 10. an acquisition module; 11. an analysis unit; 12. an acquisition unit; 20. a model building module; 21. a collection unit; 22. a model building unit; 30. an analysis module; 31. a monitoring unit; 32. a signal acquisition unit; 40. a processing and judging module; 41. a receiving unit; 42. a processing unit; 43. a comparison and judgment unit; 50. a fault diagnosis and prediction module; 51. a model failure prediction unit; 52. a data driven failure prediction unit; 60. a maintenance decision module; 61. a predictive maintenance model unit; 62. and a maintenance plan making unit.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The first embodiment is as follows: referring to fig. 1; the invention discloses a rail transit equipment state detection and maintenance system, which comprises: the system comprises an acquisition module 10, a model building module 20, an analysis module 30, a processing and judging module 40, a fault diagnosis and prediction module 50 and a maintenance decision module 60. The acquisition module 10 is used for analyzing the equipment or each component to acquire the fault condition and the influence factor of the equipment or each component; the model establishing module 20 is used for simulating to obtain life cycle data of the equipment or each component under the condition that the influence factors influence the application scene of the equipment or each component and establishing a dynamic model; the analysis module 30 is used for analyzing main influence factors and characteristics of faults, hidden dangers and service lives of different devices or components aiming at different detection objects; the processing and judging module 40 is used for receiving main influence factors and characteristics of the equipment or each component, converting the main influence factors and characteristics into operation state data, processing and analyzing the operation state data, and comparing the operation state data with a preset alarm threshold value to judge whether a potential fault exists; the fault diagnosis and prediction module 50 is used for performing fault prediction and fault diagnosis on corresponding equipment or each component according to the alarm information; and the maintenance decision module 60 is used for making a corresponding maintenance plan according to the fault prediction and fault diagnosis result and sending the maintenance plan to the terminal.
The acquisition module 10 analyzes the equipment or each component to acquire the influence factors and fault conditions of the equipment or each component, the hardware acquires the whole life cycle data of the equipment or each component under the influence of the influence factors acquired by the acquisition module 10 in the ring test, and meanwhile, a dynamic model of the equipment or each component is established. The analysis module 30 performs tests on the different devices or components to analyze the main influencing factors and characteristics affecting the failure and life of the devices or components. The processing and judging module 40 collects the operation states of the equipment or each component under the main influence factors, the processing and judging module 40 presets an alarm threshold value and compares the preset alarm threshold value with the operation states of the equipment or each component, if the preset alarm threshold value exceeds the alarm threshold value, the equipment or each component is considered to have a potential fault, and the processing and judging module 40 triggers an alarm. The fault diagnosis and prediction module 50 performs fault diagnosis and prediction on the equipment or each component according to the alarm signal, and when the remaining service life of the equipment or each component is small, the maintenance decision module 60 makes a corresponding maintenance plan for the equipment or each component according to the diagnosis result, so that the service life of the equipment or each component can be accurately predicted, the equipment or each component can be maintained as soon as possible, and the normal operation of the traffic equipment is further ensured.
The obtaining module 10 includes an analyzing unit 11 and an obtaining unit 12, the analyzing unit 11 is used for analyzing the structure, material, electric control, logic, operation and other characteristics of the equipment or each component, and the obtaining unit 12 is used for obtaining the fault condition and the influencing factor of the equipment or each component according to the analysis result of the analyzing unit 11. There are many factors that affect the service life of the equipment or components, such as during manufacturing, assembly, testing, transportation, installation, and debugging, any link may affect the reliability of the components. The operating and maintenance environment, such as the size of the production load of the equipment, the operating environment, the maintenance level, the personnel responsibility, etc., can affect the remaining life of the equipment or components. Therefore, before the equipment or each part operates, the analysis unit 11 is used for carrying out object analysis on the equipment or each part, the structure, the material, the electric control, the logic, the operation characteristics, the environment and the like of an object are deeply known, the fault form and the performance of the equipment or each part are determined, and the acquisition unit 12 is used for mastering influence factors such as internal causes, external causes and the like which influence the service life of the equipment or each part so as to determine the monitoring signals and the excitation signals of the equipment or each part, wherein the influence factors comprise types and numbers and are used for monitoring the recession and the loss conditions of the equipment or each part.
The model building module 20 comprises a collecting unit 21 and a model building unit 22, the model building module 20 is used for simulating application scenes of equipment or each component, hardware-in-the-loop test simulation is carried out according to the relation of the same frequency spectrum and space-time geometric compression to obtain full life cycle data of the equipment or each component, and the model building unit 22 is used for forming a life cycle database according to the full life cycle data and building a health degree model, health degradation and fault prediction. The application scenes of test equipment or each component are reproduced in an on-line real laboratory, data are excited off the line, and hardware-in-the-loop test simulation, health degradation and fault prediction with the same frequency spectrum relationship and space-time geometric compression are performed. It should be noted that failure data may not exist yet, but the operation data may show a trend that the performance of the device or each component deteriorates over time, so the acquisition unit 21 obtains the life cycle data of the device or each component by simulating the application scene of the device or each component, and the model establishing unit 22 establishes a health model of the device or each component according to the life cycle data of the device or each component, so that the health deterioration condition of the device or each component and the failure prediction can be obtained according to the use time and the influence factors of the device or each component.
The analysis module 30 comprises a monitoring unit 31 and a signal acquisition unit 32, the monitoring unit 31 is used for detecting the state of the equipment or parts to be detected in an omnibearing manner, the system mainly monitors objects which can be divided into physical materials, mechanical structures and electronic electrics according to types, wherein the physical materials comprise steel rails, cable sheaths, couplers and the like, the mechanical structures comprise bogies and the like, and the electronic electrics comprise inverters, motors and the like and are specific to different equipment or parts. The monitoring unit 31 needs to analyze the influence factors and characteristics of the faults, hidden dangers and service lives of the equipment or each component, the monitoring unit 31 is a sensor for direct or indirect measurement of various contact/non-contact, the monitoring unit 31 comprehensively senses the state of the equipment or each component from various angles such as sound, light, electricity, magnetism, force, heat, gas and flow, the angles required to be sensed for different equipment or each component are different, and therefore the detection content for different equipment or each component is different. The signal acquisition unit 32 is a data acquisition device, the signal acquisition unit 32 is used for acquiring operation state data affecting normal operation of equipment or each component, and the signal acquisition unit 32 can be a PLC, a remote I/O, an acquisition card, an acquisition module and the like, and converts an original signal into a digital signal to be uploaded or provided to a local controller.
The processing determination module 40 includes: the device comprises a receiving unit 41, a processing unit 42 and a comparison and judgment unit 43, wherein the receiving unit 41 is used for receiving factors influencing the normal operation of the device or each component, the type and the expression form of the fault and converting the factors into operation state data, the processing unit 42 is used for analyzing, filtering and correcting the operation state data of the device or each component, and the comparison and judgment unit 43 is used for presetting an alarm threshold value, judging that the device or each component has a potential fault when the operation state data exceeds the alarm threshold value, and giving an alarm when the device or each component has the potential fault. The processing and judging module 40 is close to the equipment to be tested or each part belongs to the remote monitoring end of the system so as to carry out preliminary processing and analysis on the monitoring data and realize the local field monitoring functions of measuring, storing, alarming and the like of the state data of the object. The processing and judging module 40 is a monitoring host in various forms such as an industrial personal computer, an edge server, a personal computer and the like, is internally provided with data monitoring software, is communicated with a data acquisition device of a signal sensing layer through an industrial field bus interface, and can also be directly connected with an intelligent sensor. The receiving unit 41 receives influencing factors, fault types and expression forms of normal operation of the equipment or each component, and the receiving unit 41 receives state signals of noise, vibration, temperature, humidity, pressure, speed, illumination, flow, voltage, current and the like with high fidelity of the equipment or each component and monitors decline and loss trends of the equipment or each component in real time. The monitoring software built in the monitoring host integrates modules such as data acquisition, storage, feature extraction, waveform capture, self-checking, alarm engine and the like, namely a processing unit 42, the processing unit 42 performs preliminary analysis, filtration and correction on the measured data, a comparison and judgment unit 43 presets an alarm threshold value, when the data is detected to exceed the alarm threshold value, an alarm is triggered, and then on-site state monitoring is realized, real-time monitoring on equipment or each component is facilitated, and the condition that the equipment or each component is damaged and difficult to maintain in time is prevented. In addition, the processing and determining module 40 also implements data networking, and converts various industrial field buses such as Modbus, FF, Profibus, etc. into common network protocols such as HTTP, MQTT, 5G/4G, etc. for transmission by using devices such as a monitoring host or an edge gateway.
The fault diagnosis and prediction module 50 comprises a model fault prediction unit 51 and a data driving fault prediction unit 52, wherein the model fault prediction unit 51 is used for evaluating the damage degree of the parts through calculation of the functional damage of the equipment or each part, establishing a physical model or random process modeling and evaluating the residual life of the equipment or each part, and the data driving fault prediction unit 52 is used for mining implicit information in the equipment or each part through each data analysis processing method to carry out evaluation, diagnosis and prediction operations. The failure prediction methods are classified into a plurality of types, the two types of the most common failure prediction methods are a failure prediction technology based on a model and a failure prediction technology based on data driving, and the two technologies are integrated in the embodiment to carry out diagnosis and prediction to form a hybrid failure prediction technology which combines a physical model and intelligent data analysis and can process data information and symbolic information, so that the predictive maintenance is more effective.
The model fault prediction unit 51 obtains an accurate mathematical model of the object through an under-line excitation compression test, estimates the damage degree of the key parts through calculation of functional damage, establishes a physical model or a random process modeling, and evaluates the residual life of the parts. Generally, the fault characteristics of the equipment system are closely related to the parameters of the used model, and as the equipment or system fault firework incentive research is carried out, the model can be gradually corrected and adjusted to improve the prediction accuracy. That is, according to the influence factors of different components and their own damage degrees, the remaining life of the component is calculated by referring to the health model established by the life cycle data, so that the maintenance decision module 60 can make corresponding maintenance measures for the component or the equipment according to the calculation result.
The data-driven fault prediction unit 52 uses current and historical data for statistical and probabilistic analysis, does not need prior knowledge of equipment or each component system, and mines implicit information therein through various data analysis processing methods for evaluation, diagnosis and prediction operations on the basis of the acquired data, thereby avoiding the defects of the fault prediction technology based on models and knowledge. The method has wide application range and strong adaptability, and is suitable for occasions where accurate models are difficult to establish. The residual service life of the equipment or the components is deduced through the measurement data obtained by measuring the equipment or the components, so that the service life is easy to calculate.
The maintenance decision module 60 includes a predictive maintenance model unit 61 and a maintenance plan making unit 62, and the predictive maintenance model unit 61 constructs a predictive maintenance model by using the result of the predictive analysis. The predictive maintenance model unit 61 establishes an expert knowledge base by using the maintenance interval, the maintenance threshold, the component threshold, and the like as optimization variables and the lowest total cost of the plant maintenance cycle as an optimization target, and thereby provides a maintenance decision suggestion. The maintenance plan making unit 62 performs maintenance feasibility analysis from various aspects and angles such as personnel, resources, time, cost, benefit and the like according to the results obtained by the processing and judging module 40 and the fault diagnosis and state prediction module, makes a maintenance plan, determines maintenance guarantee resources, and makes time, place, task and content of maintenance activities. The method for the maintenance plan making unit 62 to make the maintenance plan is generally a fault tree reasoning method, a mathematical model analysis method, a bayesian network method, an intelligent maintenance decision method, etc., and the bayesian network method is suitable for expressing and analyzing uncertain and probabilistic things.
And displaying the maintenance plan through an intelligent terminal after the maintenance plan is formulated, wherein the intelligent terminal comprises a tablet personal computer, a mobile phone, a central large screen and the like, so that related personnel can formulate corresponding maintenance actions according to the maintenance plan on the mobile terminal, and normal operation of traffic equipment facilities is ensured.
Example two: referring to fig. 2, an embodiment of the invention discloses a rail transit equipment state detection and maintenance method, which includes the following steps:
step S1: acquiring the fault condition of the equipment or each component and influence factors influencing the service life of the equipment or each component according to the basic condition of the equipment or each component, simulating an application scene under the influence of the influence factors of the equipment or each component and acquiring full life cycle data of the equipment or each component to form a full life cycle database, and establishing a dynamic model of the equipment or each component according to the full life cycle database;
step S2: analyzing and collecting main influence factors and characteristics influencing the faults, hidden dangers and service lives of the current equipment or each part according to the current different equipment or each part;
step S3: receiving data of main influence factors and characteristics of current equipment or each part to acquire operation state data, analyzing the operation state data and judging whether the equipment or each part has potential faults or not;
step S4: and performing fault prediction and fault diagnosis on the equipment or each part, generating a maintenance plan according to a fault analysis result and sending the maintenance plan to the terminal.
Firstly, analyzing equipment or each part of the rail transit to obtain the fault condition and the influence factor of the equipment or each part, simultaneously simulating the application scene of the equipment or each part, stimulating and compressing the test to obtain the life cycle data of the equipment or each part, establishing a life cycle database, establishing a dynamic model of the equipment or each part according to the life cycle database, wherein the dynamic model is a health degree model, a health degradation model and a fault prediction module of the equipment or each part, then detecting the main influence factor and the characteristic of each equipment or each part, adopting the running state data of the equipment and each part in the running state according to the main influence factor and the characteristic, analyzing whether the equipment or each part has a potential fault according to the running state data, simultaneously carrying out fault prediction and fault diagnosis according to the equipment or each part with the potential fault, and finally generating a corresponding maintenance plan according to the prediction and diagnosis result and sending the maintenance plan to a terminal, so that the relevant personnel can obtain the maintenance guidance required to be carried out from the terminal, and carry out maintenance or replacement measures on the equipment or each part so as to ensure the normal operation of the traffic equipment or facilities.
Step S1 includes the following steps:
step S11: analyzing the structure, material, electric control and logic of the equipment or each component by using the operation characteristics;
step S12: acquiring the fault condition of equipment and each part and influence factors influencing the service life of the equipment or each part;
step S13: reproducing the application scene of the equipment or each component, and performing hardware-in-the-loop test simulation under the excitation of the same influence factors according to the relation between the same frequency spectrum and the time-space ratio compression so as to acquire the full life cycle data of the equipment or each component;
step S14: and forming a full life cycle database according to the full life cycle data of the equipment or each component, and establishing a dynamic model of the equipment or each component according to the full life cycle database, wherein the dynamic model comprises a health degree model, a health degradation model and a fault prediction model.
Analyzing the equipment or each component before monitoring, deeply knowing the structure, material, electric control, logic, operation characteristics, environment and the like of the equipment or each component, so as to clarify the fault form and performance of the equipment or each component, master influence factors such as external factors and internal factors influencing the service life of the equipment or each component, further determine monitoring signals and excitation signals of the equipment or each component, reappear the application scene of the test equipment or each component in a laboratory according to the excitation signals on line, perform hardware-in-the-loop test simulation according to the same frequency spectrum and space-time same-ratio compression relationship by applying the same influence factors to deactivate, perform the same-ratio speed inspection on the use of the equipment or each component to obtain the life cycle data of the equipment or each component, establish a life cycle database and establish a health degree model of the equipment or each component according to the life cycle database, in order to calculate health degradation and failure prediction of the equipment or components.
Step S2 includes the following steps:
step S21: aiming at different current equipment or each part, analyzing main influence factors and characteristics which influence the faults, hidden dangers and service life of the equipment or each part;
step S22: and collecting analog quantity of main influencing factors and characteristics, converting the analog quantity into a data signal and uploading the data signal to a controller.
Because the types of the monitored equipment or components are different and can be divided into physical materials, mechanical structures and electronic and electrical types, the influence factors and characteristics of faults, hidden dangers and service lives which need to be detected aiming at different types of components are different, so that the equipment types need to be firstly determined, then the states of the equipment and the components are comprehensively sensed from various angles such as sound, light, electricity, magnetism, force, heat, gas, flow and the like, and then original analog signals are converted into digital signals through a collecting device and uploaded to a local controller so as to be convenient for the targeted detection aiming at the different equipment or components.
Step S3 includes the following steps:
step S31: receiving data signals of main influencing factors and characteristics and converting the data signals into running state data of equipment or each part;
step S32: the monitoring software carries out preliminary analysis, filtration and correction on the running state data;
step S33: and presetting an alarm threshold, and comparing the processed running state data with the alarm threshold to judge whether the equipment has potential faults.
The receiving and collecting device collects the operating state data of the equipment or each component, wherein the collected operating data needs to be measured, namely the operating data is in another form of measuring data. The method mainly measures state signals of noise, vibration, temperature, humidity, pressure, speed, illumination, flow, voltage, current and the like of the fidelity of equipment or each component, monitors decline and loss trend of the equipment or each component in real time, then carries out preliminary analysis, filtration and correction on measured data, presets an alarm threshold value, triggers an alarm when the detected measured data exceeds the alarm threshold value, converts various industrial field buses such as Modbus, FF, Profibus and the like into common network protocols such as HTTP, MQTT, 5G/4G and the like by utilizing equipment such as a monitoring host or an edge gateway and the like on the processed measured data, so as to conveniently carry out real-time monitoring on the operation of the equipment or each component and prevent traffic paralysis caused by direct damage of the equipment or each component.
Step S4 includes the following steps:
s41: performing fault prediction and fault diagnosis on corresponding equipment or components by adopting a fault prediction technology based on a model and a data drive according to the alarm signal;
s42: and performing maintenance feasibility analysis according to the results of fault diagnosis and fault prediction, generating a maintenance plan and sending the maintenance plan to the terminal.
The fault prediction method for the equipment or each component is classified into a plurality of categories, a model-based fault prediction technology and a data-driven fault prediction technology are common, the fault prediction for the equipment and each component is carried out by combining the two technologies, wherein the model-based fault prediction technology obtains an accurate mathematical model of an object, namely a health degree model, the damage degree of key components is evaluated by calculating functional damage, a physical model or a random process modeling is established to evaluate the residual service life of the component, under the condition of the fault characteristic of the object system is generally closely related to the parameters of all models, the model can be gradually corrected and adjusted to improve the prediction precision of the component along with the gradual deep research on the equipment or each component, so that the residual service life of the equipment or each component can be accurately calculated, so as to make a corresponding maintenance plan. The statistical and probabilistic analysis is performed based on a data-driven method and by using current and historical data, prior knowledge of an object system is not needed, the acquired data is used as a basis, and evaluation, diagnosis and prediction operations are performed by mining implicit information in the acquired data through various data analysis and processing methods, so that the prediction of equipment or each component is simple.
By using the results of the predictive analysis, a predictive maintenance model is constructed. And establishing an expert knowledge base by taking the maintenance interval, the maintenance threshold, the part threshold and the like as optimization variables and taking the lowest total cost of the equipment and facility maintenance period as an optimization target, and providing a maintenance decision suggestion according to the expert knowledge base. The maintenance decision is based on multiple aspects and multiple angles such as personnel, resources, time, cost, benefit and the like, maintenance feasibility analysis is carried out according to the results of state monitoring, fault diagnosis and state prediction, a maintenance plan is set, the maintenance guarantee resources are determined, and the time, the place, the personnel and the content of maintenance activities are given. And a maintenance plan corresponding to the results of the state monitoring, the fault diagnosis and the state prediction is made through multiple aspects and multiple angles of consideration and is sent to the terminal, so that related personnel can conveniently develop maintenance actions according to the indication of the terminal.
Example three: as shown in fig. 3, after analyzing the fault condition and the influence factor of the equipment or each component, simulating a real application scene, adopting excitation to test the equipment or each component, then establishing a dynamic model of the equipment or each component, continuously improving the dynamic model of the equipment or each component through repeated simulation and test, simultaneously collecting a reference database of the equipment or each component, namely a temperature alarm threshold, a voltage alarm threshold and the like of the equipment or each component in continuous simulation and test, then measuring the equipment or each component in the current system to collect corresponding measurement data, comparing the measurement data with the alarm threshold in the database of the equipment or each component, starting to judge the fault condition of the equipment or each component if the measurement data exceeds the alarm threshold, carrying out fault diagnosis according to a diagnosis scale, and judging the damage level of the equipment or each component through the fault diagnosis, and establishing a health decline model according to the damage level so as to obtain the fault prediction of the equipment or each part according to the health decline model.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A rail transit equipment state detection maintenance method is characterized by comprising the following steps:
step S1: acquiring the fault condition of the equipment or each component and influence factors influencing the service life of the equipment or each component according to the basic condition of the equipment or each component, simulating an application scene under the influence of the influence factors of the equipment or each component and acquiring full life cycle data of the equipment or each component to form a full life cycle database, and establishing a dynamic model of the equipment or each component according to the full life cycle database;
step S2: analyzing and collecting main influence factors and characteristics influencing the faults, hidden dangers and service lives of the current equipment or each part according to the current different equipment or each part;
step S3: receiving data of main influence factors and characteristics of current equipment or each part to acquire operation state data, analyzing the operation state data and judging whether the equipment or each part has potential faults or not;
step S4: and performing fault prediction and fault diagnosis on the equipment or each part by using a dynamic model, generating a maintenance plan according to a fault analysis result and sending the maintenance plan to the terminal.
2. The rail transit equipment state detection maintenance method according to claim 1, wherein the step S1 includes the steps of:
step S11: analyzing the structure, material, electric control and logic of the equipment or each component by using the operation characteristics;
step S12: acquiring the fault condition of equipment and each part and influence factors influencing the service life of the equipment or each part;
step S13: reproducing the application scene of the equipment or each component, and performing hardware-in-the-loop test simulation under the excitation of the same influence factors according to the relation between the same frequency spectrum and the time-space ratio compression so as to acquire the full life cycle data of the equipment or each component;
step S14: and forming a full life cycle database according to the full life cycle data of the equipment or each component, and establishing a dynamic model of the equipment or each component according to the full life cycle database, wherein the dynamic model comprises a health degree model, a health degradation model and a fault prediction model.
3. The rail transit equipment state detection maintenance method according to claim 1 or 2, wherein the step S2 includes the steps of:
step S21: aiming at different current equipment or each part, analyzing main influence factors and characteristics which influence the faults, hidden dangers and service life of the equipment or each part;
step S22: and collecting analog quantity of main influencing factors and characteristics, converting the analog quantity into a data signal and uploading the data signal to a controller.
4. The rail transit equipment state detection maintenance method according to claim 1 or 2, wherein the step S3 includes the steps of:
step S31: receiving data signals of main influencing factors and characteristics and converting the data signals into running state data of equipment or each part;
step S32: the monitoring software carries out preliminary analysis, filtration and correction on the running state data;
step S33: and presetting an alarm threshold, and comparing the processed running state data with the alarm threshold to judge whether the equipment has potential faults.
5. The rail transit equipment state detection maintenance method according to claim 1 or 2, wherein the step S4 includes the steps of:
s41: performing fault prediction and fault diagnosis on corresponding equipment or components by adopting a fault prediction technology based on a model and a data drive according to the alarm signal;
s42: and performing maintenance feasibility analysis according to the results of fault diagnosis and fault prediction, generating a maintenance plan and sending the maintenance plan to the terminal.
6. A rail transit equipment state detection maintenance system characterized by comprising:
the acquisition module is used for analyzing the equipment or each part to acquire the fault condition and the influence factor of the equipment or each part;
the model establishing module is used for acquiring life cycle data of the equipment or each component under the application scene of simulating influence factors and establishing a dynamic model;
the analysis module is used for analyzing and collecting main influence factors and characteristics which influence the faults, hidden dangers and service lives of equipment or each component aiming at different current detection objects;
the processing and judging module is used for receiving and processing the running state data of main influencing factors and characteristics of the equipment or each component, and comparing the running state data with a preset alarm threshold value to judge whether a potential fault exists;
the fault diagnosis and prediction module is used for carrying out fault prediction and fault diagnosis on corresponding equipment or each component by using a dynamic model according to the alarm information;
and the maintenance decision module is used for making a corresponding maintenance plan according to the fault prediction and fault diagnosis result and sending the maintenance plan to the terminal.
7. The rail transit equipment state detection maintenance system of claim 6, wherein the acquisition module comprises:
the analysis unit is used for analyzing the characteristics of the structure, the material, the electric control, the logic, the operation and the like of equipment or each part;
and the acquisition unit is used for acquiring the fault condition and the influence factors of the equipment or each component according to the analysis result of the analysis unit.
8. The rail transit equipment state detection maintenance system of claim 6 or 7, wherein the model building module comprises:
the acquisition unit is used for simulating an application scene of the equipment or each component and carrying out hardware-in-the-loop test simulation according to the relation between the same frequency spectrum and space-time same-ratio compression so as to obtain full life cycle data of the equipment or each component;
and the model establishing unit is used for establishing a dynamic model of the equipment or each part according to a full life cycle database formed by the full life cycle data.
9. The rail transit equipment state detection maintenance system of claim 6 or 7, wherein the processing and judgment module comprises:
the receiving unit is used for receiving factors influencing the normal work of the equipment or each component, the type and the expression form of the fault and converting the factors into operation state data influencing the equipment or each component;
the processing unit is used for analyzing, filtering and correcting the running state data of the equipment or each part;
and the comparison and judgment unit is used for presetting an alarm threshold value, and judging whether a potential fault exists or not when the operation state data is compared with the alarm threshold value.
10. The rail transit equipment state detection maintenance system of claim 6 or 7, wherein the fault diagnosis and prediction module comprises:
the model fault prediction unit is used for establishing a physical model or a random process modeling and evaluating the residual service life of the equipment or each component by calculating the functional damage of the equipment or each component and evaluating the damage degree of the components;
and the data driving fault prediction unit is used for mining the implicit information in each data analysis processing method to carry out evaluation, diagnosis and prediction operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910849412.5A CN110647133B (en) | 2019-09-09 | 2019-09-09 | Rail transit equipment state detection maintenance method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910849412.5A CN110647133B (en) | 2019-09-09 | 2019-09-09 | Rail transit equipment state detection maintenance method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110647133A CN110647133A (en) | 2020-01-03 |
| CN110647133B true CN110647133B (en) | 2022-03-15 |
Family
ID=68991839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910849412.5A Active CN110647133B (en) | 2019-09-09 | 2019-09-09 | Rail transit equipment state detection maintenance method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647133B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111240300A (en) * | 2020-01-07 | 2020-06-05 | 国电南瑞科技股份有限公司 | Vehicle health state evaluation model construction method based on big data |
| CN111239529A (en) * | 2020-03-05 | 2020-06-05 | 西南交通大学 | Excitation test method and system supporting predictive maintenance of electromechanical equipment |
| CN111624958A (en) * | 2020-04-14 | 2020-09-04 | 吉利汽车研究院（宁波）有限公司 | Equipment state information monitoring method and device and storage medium |
| CN111472410A (en) * | 2020-05-13 | 2020-07-31 | 雷沃工程机械集团有限公司 | Excavator electrical element fault warning method and system |
| CN111597637A (en) * | 2020-05-19 | 2020-08-28 | 北京铁道工程机电技术研究所股份有限公司 | Fault detection method, device, server and system for field parts of bullet train |
| CN111768113A (en) * | 2020-07-03 | 2020-10-13 | 许艳杰 | Public cloud-based hydraulic engineering management system and method |
| CN112305959A (en) * | 2020-10-14 | 2021-02-02 | 北京市地铁运营有限公司地铁运营技术研发中心 | Equipment monitoring and maintaining method and system in subway system |
| CN112465684A (en) * | 2020-11-09 | 2021-03-09 | 覃强 | Full life cycle management system of track |
| CN112668840A (en) * | 2020-12-11 | 2021-04-16 | 广州致新电力科技有限公司 | Method for evaluating service life of high-voltage electrical equipment of rail transit |
| CN112561352B (en) * | 2020-12-21 | 2022-07-26 | 卡斯柯信号有限公司 | Rail transit signal system health assessment method and device |
| CN112561096A (en) * | 2020-12-23 | 2021-03-26 | 上海地铁维护保障有限公司 | Full-life maintenance method for subway vehicle equipment |
| CN113221324B (en) * | 2021-04-13 | 2022-07-19 | 厦门路桥信息股份有限公司 | Life cycle prediction method and life cycle prediction system for parking lot equipment |
| CN113409556A (en) * | 2021-06-10 | 2021-09-17 | 通号(北京)轨道工业集团有限公司轨道交通技术研究院 | LEU monitoring and early warning method and system |
| CN113505476B (en) * | 2021-06-28 | 2022-08-30 | 东风汽车集团股份有限公司 | Prediction method and prediction system for improving prediction accuracy of impact scratches |
| CN113688027B (en) * | 2021-10-26 | 2022-02-22 | 深圳市永达电子信息股份有限公司 | Detection data processing method and system for industrial control equipment |
| CN114429249B (en) * | 2022-04-06 | 2022-08-16 | 杭州未名信科科技有限公司 | Method, system, equipment and storage medium for predicting service life of steel pipe bundle production equipment |
| CN114880839B (en) * | 2022-04-15 | 2024-05-07 | 东风汽车股份有限公司 | Method for resolving problematic faults of automobile spare parts |
| CN116205636B (en) * | 2023-05-04 | 2023-07-18 | 天津三号线轨道交通运营有限公司 | Subway facility maintenance management method and system based on Internet of things technology |
| CN116776653B (en) * | 2023-08-24 | 2023-12-26 | 国网浙江省电力有限公司宁波供电公司 | Full life cycle tracking method and device for power cable |
| CN117111589B (en) * | 2023-10-23 | 2024-01-02 | 中国机械总院集团云南分院有限公司 | Fault diagnosis method for numerical control machine tool control system based on Petri network |
| CN117168865B (en) * | 2023-11-03 | 2024-04-12 | 南通宝佳精密机械有限公司 | Electromechanical device protection system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063551A (en) * | 2014-07-03 | 2014-09-24 | 北京索为高科***技术有限公司 | Avionics system full-life-cycle unified model modeling method |
| CN105809255A (en) * | 2016-03-07 | 2016-07-27 | 大唐淮南洛河发电厂 | IoT-based heat-engine plantrotary machine health management method and system |
| CN108446864A (en) * | 2018-04-10 | 2018-08-24 | 广州新科佳都科技有限公司 | The fault early warning system and method for Transit Equipment based on big data analysis |
| CN109445406A (en) * | 2018-10-18 | 2019-03-08 | 西南交通大学 | Industrial control system safety detection method based on scrnario testing and affairs search |
| CN109814529A (en) * | 2019-01-23 | 2019-05-28 | 北京博得交通设备有限公司 | A kind of train door prognostic and health management system |
-
2019
- 2019-09-09 CN CN201910849412.5A patent/CN110647133B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104063551A (en) * | 2014-07-03 | 2014-09-24 | 北京索为高科***技术有限公司 | Avionics system full-life-cycle unified model modeling method |
| CN105809255A (en) * | 2016-03-07 | 2016-07-27 | 大唐淮南洛河发电厂 | IoT-based heat-engine plantrotary machine health management method and system |
| CN108446864A (en) * | 2018-04-10 | 2018-08-24 | 广州新科佳都科技有限公司 | The fault early warning system and method for Transit Equipment based on big data analysis |
| CN109445406A (en) * | 2018-10-18 | 2019-03-08 | 西南交通大学 | Industrial control system safety detection method based on scrnario testing and affairs search |
| CN109814529A (en) * | 2019-01-23 | 2019-05-28 | 北京博得交通设备有限公司 | A kind of train door prognostic and health management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110647133A (en) | 2020-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| US20210241544A1 (en) | Platform for analyzing health of heavy electric machine and analysis method using the same | |
| US6694286B2 (en) | Method and system for monitoring the condition of an individual machine | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| CN102495320A (en) | Dynamic monitoring system and on-line monitoring method of transformer operation exception | |
| CN112232405B (en) | Fault prediction, monitoring and diagnosis method of gearbox and corresponding device | |
| CN117134503B (en) | State monitoring method and system for large-scale power supply device | |
| CN108921305B (en) | Component life period monitoring method | |
| CN113763667A (en) | Fire early warning and state monitoring device and method based on 5G edge calculation | |
| CN111931849A (en) | Hydroelectric generating set operation data trend early warning method | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN114510979A (en) | Underwater equipment inspection system and method based on edge calculation | |
| CN116861369A (en) | Air compressor health assessment method and system for industrial internet heterogeneous data fusion | |
| CN116756909A (en) | Early warning diagnosis system of thermal power plant based on data model and mechanism model | |
| CN116754022B (en) | On-line detection emergency early warning method and system for cable tunnel | |
| CN113483815A (en) | Mechanical fault monitoring system based on industrial big data | |
| CN117330948A (en) | Online monitoring method and system for mechanical characteristics of circuit breaker | |
| Davari et al. | A fault detection framework based on lstm autoencoder: A case study for volvo bus data set | |
| Chen et al. | BIM-and IoT-Based Data-Driven Decision Support System for Predictive Maintenance of Building Facilities | |
| RU2735296C1 (en) | Method for multi-parameter monitoring of complex electrotechnical objects state | |
| CN115249387A (en) | Intelligent rail transit monitoring and management system | |
| CN114063601A (en) | Equipment state diagnosis system and method based on artificial intelligence | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| CN202433448U (en) | Transformer-operation anomalous dynamic monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |