CN111506043A - Fault prediction system for key components of naval gun - Google Patents
Fault prediction system for key components of naval gun Download PDFInfo
- Publication number
- CN111506043A CN111506043A CN202010273166.6A CN202010273166A CN111506043A CN 111506043 A CN111506043 A CN 111506043A CN 202010273166 A CN202010273166 A CN 202010273166A CN 111506043 A CN111506043 A CN 111506043A
- Authority
- CN
- China
- Prior art keywords
- data
- signal
- gun
- module
- fault
- 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.)
- Granted
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
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a system for predicting faults of key components of a naval gun, and relates to the technical field of naval guns. The system comprises: the processing subsystem is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of key components of the ship cannon; and the control subsystem is used for carrying out parameter configuration, data management and historical data analysis on the processing subsystem, and displaying a historical data analysis result and a fault prediction result. The method can simultaneously acquire the vibration, temperature, pressure, current and voltage signals of the key components of the gun, the acquired gun data is more comprehensive, the signals can be processed, stored and subjected to fault prediction, and the problems that the fault prediction cannot be performed on the key components of the gun system at present, the acquired data is single in type, and the condition for performing fault prediction on the key components is lacked are solved.
Description
Technical Field
The invention relates to the technical field of naval cannons, in particular to a system for predicting faults of key components of naval cannons.
Background
From the composition structure, the naval gun is a complex weapon integrating light, machine, electricity and liquid, and a naval gun system can be generally divided into an artillery and an electrical system, and specifically comprises an automaton, a gun rack, an artillery control cabinet, a follow-up motor, a follow-up frequency converter, a power supply cabinet and other key components. At present, the maintenance and guarantee mode of the gun system is mainly 'after maintenance' and 'regular maintenance', the working state of key components of the gun cannot be judged in real time, the fault occurrence time cannot be accurately predicted, and the reliability and the safety of the gun when the gun performs training or combat tasks are difficult to guarantee. Along with the improvement of the demand of a battlefield on the performance of the gun, the risks caused by the performance degradation and the failure of the gun are increased, and the maintenance cost is also greatly improved. The failure prediction technology provides a new means for solving the problems and improving the reliability and the maintenance guarantee capability of the gun system. The fault prediction technology further introduces prediction capability on the basis of traditional built-in test and state monitoring, monitors, diagnoses and predicts key components of the ship and cannon system by using various advanced sensors and intelligent algorithms, and realizes state-based maintenance and autonomous guarantee of the ship and cannon system. However, the existing gun state monitoring and fault diagnosis system basically mainly monitors and diagnoses, and lacks fault prediction capability and conditions for performing fault prediction on key components.
Disclosure of Invention
The invention aims to provide a failure prediction system for a gun key component, which solves the problem that the existing gun key component cannot predict failures.
In order to achieve the purpose, the invention provides the following scheme:
a failure prediction system for critical components of a naval gun comprises:
the processing subsystem is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of key components of the ship cannon;
and the control subsystem is used for carrying out parameter configuration, data management and historical data analysis on the processing subsystem, and displaying a historical data analysis result and a fault prediction result.
Optionally, the processing subsystem specifically includes:
a data acquisition module for acquiring a first signal, the first signal comprising: the pressure signal of the naval gun automaton, the vibration signal of the gun carrier and the temperature signal of the follow-up frequency converter of the electrical system;
a bus data acquisition module for acquiring a second signal, the second signal comprising: voltage and current signals of a naval gun control cabinet, temperature signals of an electric system servo motor and voltage signals of a power supply cabinet;
the signal preprocessing module is used for preprocessing the first signal to obtain a third signal;
the controller module is used for performing feature extraction, state identification and fault prediction on the third signal and the second signal to obtain feature data, a state identification result and a fault prediction result;
a data storage module for storing the first signal, the second signal and the characteristic data;
and the Ethernet module is used for transmitting the state identification result and the fault prediction result to the control subsystem.
Optionally, the controller module specifically includes:
the function configuration unit is used for receiving a parameter configuration instruction of the control subsystem and setting the sampling rate, the sampling channel and the fault prediction model parameters of the processing subsystem according to the parameter configuration instruction;
the data analysis unit is used for analyzing the data frame of the second signal to obtain a fourth signal and transmitting the fourth signal to the feature extraction unit;
the characteristic extraction unit is used for extracting characteristic data of the vibration signal and the pressure signal in the third signal by adopting a wavelet transform method to obtain fifth data; extracting characteristic data of a temperature signal in the third signal and characteristic data of a temperature signal, a voltage signal and a current signal in the fourth signal by adopting time-frequency domain analysis to obtain sixth data; acquiring a preset characteristic condition, judging whether the fifth data and the sixth data meet the preset characteristic condition, and determining data meeting the preset characteristic condition in the fifth data and the sixth data as characteristic data;
the state identification unit is used for identifying the running state of the key components of the gun system by adopting the feature data and the support vector machine classification algorithm to obtain a state identification result;
the fault prediction unit is used for constructing a fault prediction model by using the characteristic data and obtaining a fault prediction result;
and the data storage unit is used for transmitting the third signal, the fourth signal and the characteristic data to the data storage module for storage.
Optionally, the failure prediction unit specifically includes:
the diversity subunit is used for acquiring historical fault data and dividing the historical fault data into a training data set and a verification data set; the historical fault data comprises fault data of various fault modes of key components of the ship cannon system;
the off-line data prediction model subunit is used for constructing an off-line support vector machine regression prediction model by utilizing the training data set and the verification data set to obtain an off-line data prediction model;
the online prediction model subunit is used for monitoring the real-time characteristic data, and when the data volume of the real-time characteristic data reaches a preset modeling threshold value, an online support vector machine regression prediction model is constructed by using the real-time characteristic data to obtain an online prediction model; the real-time feature data includes: the feature extraction unit extracts feature data in real time;
the prediction value subunit is used for respectively predicting the real-time characteristic data by utilizing the offline data prediction model and the online prediction model to obtain an offline prediction value and an online prediction value;
the weight value subunit is used for respectively calculating an offline weight value of the offline predicted value and an online weight value of the online predicted value by using an adaptive weight algorithm;
and the fault prediction result subunit is used for calculating the fault prediction result by utilizing the offline prediction value, the online prediction value, the offline weight value and the online weight value.
Optionally, the control subsystem specifically includes:
the parameter configuration module is used for configuring parameters of the data acquisition module and the bus data acquisition module according to monitoring parameters of different gun system key components;
the data management module is used for associating the data stored by the data storage module;
the historical data analysis module is used for calling the stored data through the data management module, carrying out historical data analysis on the stored data and transmitting an analysis result to the data display module for displaying;
and the data display module is used for acquiring and displaying the real-time sampling data of the data acquisition module and the bus data acquisition module, the characteristic data in the controller module and the analysis result of the historical data analysis module.
Optionally, the data acquisition module acquires a pressure signal of the firing spring of the gun automaton through a pressure sensor installed on the firing spring of the automaton.
Optionally, the data acquisition module acquires the vibration signal of the gun rack through vibration sensors installed on the gun rack bracket and the gun bed.
Optionally, the data acquisition module acquires the temperature signal of the electric system follow-up frequency converter through a temperature sensor installed on the electric system follow-up frequency converter.
Optionally, the bus data acquisition module acquires the second signal through an in-aircraft self-inspection system of the gun.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a failure prediction system for a key component of a naval gun. The system comprises: the processing subsystem is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of key components of the ship cannon; and the control subsystem is used for carrying out parameter configuration, data management and historical data analysis on the processing subsystem, and displaying a historical data analysis result and a fault prediction result. The method can simultaneously acquire the vibration, temperature, pressure, current and voltage signals of the key components of the gun, the acquired gun data are more comprehensive, the signals can be processed, stored, transmitted and subjected to fault prediction, and the problems that the current gun key components cannot be subjected to fault prediction, the acquired data types are single, and effective historical data cannot be accumulated are solved. In addition, the failure prediction system for the key components of the naval gun does not influence the conventional built-in self-inspection system (BIT system) of the naval gun system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a structural diagram of a failure prediction system for a critical component of a gun carrier according to an embodiment of the present invention;
fig. 2 is a structural diagram of a controller module according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a failure prediction system for a gun key component, and solves the problems that the existing gun key component cannot perform failure prediction, the type of acquired data is single, and effective historical data cannot be accumulated.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
The embodiment provides a failure prediction system for a key component of a naval gun, which is applied to a failure prediction device for a key component of a naval gun, and comprises: the device comprises a vibration sensor, a pressure sensor, a temperature sensor, a built-in self-test (BIT) system, a lower computer and an upper computer. The upper computer adopts a computer.
The vibration sensor, the pressure sensor, the temperature sensor and the BIT system are all connected with a lower computer, and the lower computer is connected with an upper computer.
The vibration sensor is arranged at the bracket and the gun bed of the gun rack of the ship gun system and is used for acquiring vibration signals of the gun rack.
The pressure sensor is arranged on an automatic firing spring of the naval gun system and is used for acquiring a pressure signal of the automatic firing spring of the naval gun.
The temperature sensor is arranged on a follow-up frequency converter of an electrical system of the naval gun system and is used for acquiring a temperature signal of the follow-up frequency converter of the electrical system.
The BIT system is used for acquiring voltage and current signals of a gun control cabinet of the gun system, temperature signals of an electric system servo motor and voltage signals of a power supply cabinet of the gun system.
The lower computer is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of the critical components of the ship cannon.
The upper computer is used for carrying out parameter configuration, data management and historical data analysis on the processing subsystem and displaying a historical data analysis result and a fault prediction result.
The key parts of the naval gun of the embodiment comprise: gun carrier, automaton, electrical system, switch board and power rack of naval gun.
The lower computer is also provided with an external interface and a plurality of interfaces applying Python, Math-Script and a Dynamic link library, the external interface is used for realizing software function expansion in the iterative process of the fault prediction algorithm of the gun-warship key components, the Python, the Math-Script, the Dynamic link library (D LL) and other interfaces are used for externally connecting a data processing algorithm, the software function expansion in the iterative process of the algorithm can be realized, the algorithm compatibility of the software is strong, the Python is a cross-platform computer program design language, the Math-Script is a text-based and mathematic-oriented programming language, and the integration of a data analysis algorithm can be realized through the external interface and the interfaces.
Fig. 1 is a structural diagram of a system for predicting failure of a critical component of a gun carrier according to an embodiment of the present invention. Referring to fig. 1, the system for predicting the failure of the critical components of the naval gun comprises:
and the processing subsystem 101 is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of key components of the ship cannon.
The processing subsystem 101 specifically includes:
a data acquisition module 1011 configured to acquire a first signal, where the first signal includes: the pressure signal of the naval gun automaton, the vibration signal of the gun carrier and the temperature signal of the follow-up frequency converter of the electrical system.
The data acquisition module acquires pressure signals of the automatic firing spring of the gun carrier through a pressure sensor arranged on the automatic firing spring of the gun carrier system, acquires vibration signals of the gun carrier through a gun carrier bracket arranged on the gun carrier system and a vibration sensor arranged on a gun carrier, and acquires temperature signals of a follow-up frequency converter of an electrical system through a temperature sensor arranged on the follow-up frequency converter of the electrical system of the gun carrier system.
A bus data acquisition module 1012 for acquiring a second signal, the second signal comprising: voltage and current signals of a naval gun control cabinet, temperature signals of an electric system servo motor and voltage signals of a power supply cabinet; the bus data acquisition module is connected with an in-aircraft self-checking system of the gun through a wiring terminal to acquire a second signal.
The data acquisition module and the bus data acquisition module can simultaneously acquire vibration signals, temperature signals, pressure signals, voltage signals and current signals of critical components of the gun. The sampling channels of the vibration signal, the temperature signal, the pressure signal, the voltage signal and the current signal are isolated from each other and work independently.
The signal preprocessing module 1013 is configured to preprocess the first signal to obtain a third signal. The signal preprocessing module 1013 is specifically configured to convert an analog quantity of the first signal into a digital quantity, and sequentially perform data interpretation, deburring, outlier removal, time alignment, noise reduction and filtering on the first signal converted into the digital quantity to obtain a third signal.
And the controller module 1014 is configured to perform feature extraction, state identification and fault prediction on the third signal and the second signal to obtain feature data, a state identification result and a fault prediction result, transmit the feature data, the state identification result and the fault prediction result to the data storage module for storage, and transmit the state identification result and the fault prediction result to the data display module of the control subsystem through the ethernet module for display.
The controller module 1014 completes most of data processing work of the failure prediction system of the key components of the gun, including feature extraction, state recognition and failure prediction, and only uploads data processing results, namely feature data, state recognition results and failure prediction results, so that the requirement of the network bandwidth of the failure prediction system of the key components of the gun is reduced, the problem of large data transmission quantity can be solved, and the real-time performance of data processing is improved.
Fig. 2 is a structural diagram of a controller module according to an embodiment of the present invention, and referring to fig. 2, the controller module 1014 specifically includes:
and the function configuration unit 10141 is configured to receive a parameter configuration instruction of the control subsystem, and set a sampling rate and a sampling channel of the data acquisition module in the processing subsystem, a fault prediction model parameter of the fault prediction unit in the controller module, and the like according to the parameter configuration instruction. The sampling rate is preferably 102.4kHz and 51.2kHz, and the fault prediction model parameters refer to parameters required for establishing an offline data prediction model and an online prediction model.
The data parsing unit 10142 is configured to parse the data frame of the second signal to obtain a fourth signal, and transmit the fourth signal to the feature extraction unit.
The feature extraction unit 10143 is configured to extract feature data of the vibration signal and the pressure signal in the third signal respectively by using a wavelet transform method to obtain fifth data; respectively extracting the temperature signal in the third signal and the characteristic data of the temperature signal, the voltage signal and the current signal in the fourth signal by adopting time-frequency domain analysis to obtain sixth data; and acquiring a preset characteristic condition, judging whether the fifth data and the sixth data accord with the preset characteristic condition, and determining the data which accords with the preset characteristic condition in the fifth data and the sixth data as the characteristic data. The fifth data includes: the vibration signal characteristic data of the third signal, and the pressure signal characteristic data of the third signal. The sixth data includes: the time-frequency domain characteristic data of the temperature signal of the third signal, the time-frequency domain characteristic data of the temperature signal of the fourth signal, the time-frequency domain characteristic data of the voltage signal, and the time-frequency domain characteristic data of the current signal. The temperature signal comprises a temperature signal of the electric system follow-up frequency converter in the third signal and a temperature signal of the electric system follow-up motor in the fourth signal.
And the state identification unit 10144 is used for identifying the running state of the key components of the gun system by using the feature data and the support vector machine classification algorithm to obtain a state identification result. The state recognition unit 10144 is specifically configured to use the feature data of the feature extraction unit 10143 as input, and perform operation state recognition on the naval gun system key component by using a support vector machine classification algorithm to obtain a state recognition result.
And the failure prediction unit 10145 is used for constructing a failure prediction model by using the characteristic data and calculating to obtain a failure prediction result. The fault prediction unit can also be used for training, updating and managing the fault prediction model according to the real-time characteristic data, so that the effectiveness of the fault prediction model is ensured. The real-time feature data includes: and the feature extraction unit extracts feature data in real time.
The failure prediction unit specifically comprises:
the diversity subunit is used for acquiring historical fault data and extracting fault feature data containing fault features in the historical fault data; all historical fault data are randomly divided into two parts, wherein one part is used as a training data set, and the other part is used as a verification data set. The historical fault data comprises fault data of various fault modes of key components of the gun system; and the fault characteristic data is used for constructing a characteristic vector and is input into a support vector machine, so that an offline data prediction model is constructed.
And the offline data prediction model subunit is used for constructing an offline support vector machine regression prediction model by utilizing the training data set and the verification data set to obtain an offline data prediction model. And (3) constructing an off-line support vector machine regression prediction model, namely an off-line data prediction model.
And the online prediction model subunit is used for monitoring the real-time characteristic data, and when the data volume of the real-time characteristic data reaches a preset modeling threshold, constructing an online support vector machine regression prediction model by using the real-time characteristic data before the real-time characteristic data reaches the preset modeling threshold to obtain the online prediction model. And (3) constructing an online support vector machine regression prediction model, namely an online prediction model. The method for constructing the regression prediction model of the online support vector machine by utilizing the real-time characteristic data before reaching the preset modeling threshold value comprises the following steps: and constructing a real-time feature vector by using the real-time feature data, and constructing an online support vector machine regression prediction model by using the real-time feature vector as the input of the support vector machine.
A prediction value subunit, configured to use the offline data prediction model and the online prediction model to respectively predict the real-time feature data to obtain an offline prediction value P1And on-line predicted value P2。
And the weight value subunit is used for respectively calculating the offline weight value of the offline predicted value and the online weight value of the online predicted value by using an adaptive weight algorithm.
And the fault prediction result subunit is used for calculating to obtain a fault prediction result by utilizing the offline prediction value, the online prediction value, the offline weight value and the online weight value. The failure prediction result subunit is specifically configured to, according to a formula: and calculating the failure prediction result by the offline prediction value and the online prediction value as the failure prediction result.
The data storage unit 10146 is configured to transmit the third signal, the fourth signal and the feature data to the data storage module for storage.
The data storage module 1015 is configured to store the first signal, the second signal, the third signal, the fourth signal, and the feature data. The data stored in the data storage module includes the first signal, the second signal, the third signal, the fourth signal and the characteristic data which are stored in history, namely historical data, and the first signal, the second signal, the third signal, the fourth signal and the characteristic data which are collected and processed in real time, namely real-time data.
An ethernet module 1016 for transmitting the status identification result and the failure prediction result to the control subsystem. The Ethernet module is also used for receiving a parameter configuration instruction of the control subsystem and transmitting the parameter configuration instruction to the function configuration unit of the controller module.
The processing subsystem further includes: the power, the power is connected with the controller module electricity, and the power is used for supplying power to the controller module, prevents that the power supply of controller module is unstable.
And the control subsystem 102 is used for performing parameter configuration, data management and historical data analysis on the processing subsystem, and displaying a historical data analysis result and a fault prediction result.
The control subsystem 102 specifically includes:
the parameter configuration module 1021 is used for performing parameter configuration on sampling channels and sampling frequencies of the data acquisition module and the bus data acquisition module according to monitoring parameters of key components of different gun systems; the system and the method are particularly used for outputting parameter configuration instructions to the processing subsystem according to different monitoring parameters of key components of different gun systems, and performing parameter configuration on the data acquisition module and the bus data acquisition module. The parameter configuration instruction comprises parameters for reconfiguring sampling channels and sampling frequencies of the data acquisition module and the bus data acquisition module. The parameter configuration module is also used for acquiring the configuration parameters of the processing subsystem, judging whether the parameter configuration instruction is the same as the configuration parameters of the current processing subsystem or not, and if the parameter configuration instruction is the same as the configuration parameters of the current processing subsystem, not outputting the parameter configuration instruction; if the bus data acquisition module is different from the data acquisition module, a parameter configuration instruction is output, and parameter configuration is carried out on the data acquisition module and the bus data acquisition module. The parameter configuration module is connected with the controller module through the Ethernet module, and is further used for sending a self-checking request instruction to the controller module through the Ethernet module, detecting the sampling channels of the controller module, acquiring self-checking results of the sampling channels of the controller module, and sending the self-checking results to the data display module for displaying.
The data management module 1022 is configured to associate data stored by the data storage module. The data management module realizes data management in a WebDAV mode, namely, the data stored by the data storage module is associated and managed, including the selection, deletion and uploading of the data. The data management module is connected with the controller module through the Ethernet module.
And the historical data analysis module 1023 is used for calling the stored data through the data management module, performing historical data analysis on the historical data in the stored data, and transmitting the analysis result to the data display module for displaying.
And the data display module 1024 is used for acquiring and displaying real-time sampling data of the data acquisition module and the bus data acquisition module, characteristic data in the controller module and an analysis result of the historical data analysis module. The data display module is used for displaying the signal waveform and the frequency spectrum of the real-time sampling data. The data display module displays the received data, so that a user can conveniently check the real-time state of the key components of the gun system, the abnormity of the vibration, temperature, pressure, current and voltage signals of the key components of the gun system can be found in time, and the work task of the gun system can be adjusted if necessary. The data display module is connected with the controller module through the Ethernet module.
The method can simultaneously acquire the vibration, temperature, pressure, current and voltage signals of the key components of the gun, the acquired gun data is more comprehensive, the signals can be processed, stored and subjected to fault prediction, the problem of low prediction precision caused by single gun data used in the current gun fault prediction method is solved, and the unplanned maintenance times of the gun system can be reduced, the inspection cost is reduced and the downtime is shortened according to the fault prediction result. In addition, the failure prediction system for the key components of the gun carrier does not influence the existing built-in self-inspection system (BIT system) of the gun carrier system; all modules support a real-time continuous synchronous acquisition working mode, and are suitable for occasions with high requirements on data instantaneity and synchronism; a plurality of sampling channels are supported, at most, 36 channels including 12 vibration sampling channels, 8 temperature sampling channels and 16 current and voltage sampling channels can be simultaneously accessed, and the number of the channels can be expanded according to actual needs; the integrity of the failure prediction system of the key components of the ship cannon is high, and vibration monitoring, temperature monitoring, pressure monitoring, voltage monitoring and current monitoring are integrated in the failure prediction system of the key components of the ship cannon; because each sampling channel is independently collected and the host machine processes data in a centralized manner, the host machine of the ship cannon key component fault prediction system has the characteristics of low coupling and high cohesion; the offline data prediction model subunit and the online prediction model subunit of the fault prediction unit can simultaneously meet the requirements of data acquisition, storage, observation and analysis under field online signals and an offline state (without supervision); the state identification unit and the fault prediction unit of the controller module of the ship cannon key component fault prediction system adopt algorithms with high identification degree and prediction capability. The failure prediction system for the key components of the naval gun adopts the latest edge computing technical architecture, namely, most data processing work is completed in the controller module, the requirement of the failure prediction system for the key components of the naval gun on network bandwidth is lowered, and the problems of data blockage and untimely data processing caused by uploading of a large amount of data can be solved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (9)
1. A naval gun key component fault prediction system is characterized by comprising:
the processing subsystem is used for respectively acquiring, processing, storing and predicting faults of vibration, temperature, pressure, current and voltage signals of key components of the ship cannon;
and the control subsystem is used for carrying out parameter configuration, data management and historical data analysis on the processing subsystem, and displaying a historical data analysis result and a fault prediction result.
2. The system for predicting the failure of the critical components of the naval gun according to claim 1, wherein the processing subsystem specifically comprises:
a data acquisition module for acquiring a first signal, the first signal comprising: the pressure signal of the naval gun automaton, the vibration signal of the gun carrier and the temperature signal of the follow-up frequency converter of the electrical system;
a bus data acquisition module for acquiring a second signal, the second signal comprising: voltage and current signals of a naval gun control cabinet, temperature signals of an electric system servo motor and voltage signals of a power supply cabinet;
the signal preprocessing module is used for preprocessing the first signal to obtain a third signal;
the controller module is used for performing feature extraction, state identification and fault prediction on the third signal and the second signal to obtain feature data, a state identification result and a fault prediction result;
a data storage module for storing the first signal, the second signal and the characteristic data;
and the Ethernet module is used for transmitting the state identification result and the fault prediction result to the control subsystem.
3. The system of claim 2, wherein the controller module specifically comprises:
the function configuration unit is used for receiving a parameter configuration instruction of the control subsystem and setting the sampling rate, the sampling channel and the fault prediction model parameters of the processing subsystem according to the parameter configuration instruction;
the data analysis unit is used for analyzing the data frame of the second signal to obtain a fourth signal and transmitting the fourth signal to the feature extraction unit;
the characteristic extraction unit is used for extracting characteristic data of the vibration signal and the pressure signal in the third signal by adopting a wavelet transform method to obtain fifth data; extracting characteristic data of a temperature signal in the third signal and characteristic data of a temperature signal, a voltage signal and a current signal in the fourth signal by adopting time-frequency domain analysis to obtain sixth data; acquiring a preset characteristic condition, judging whether the fifth data and the sixth data meet the preset characteristic condition, and determining data meeting the preset characteristic condition in the fifth data and the sixth data as characteristic data;
the state identification unit is used for identifying the running state of the key components of the gun system by adopting the feature data and the support vector machine classification algorithm to obtain a state identification result;
the fault prediction unit is used for constructing a fault prediction model by using the characteristic data and obtaining a fault prediction result;
and the data storage unit is used for transmitting the third signal, the fourth signal and the characteristic data to the data storage module for storage.
4. The system for predicting the fault of the critical component of the naval gun according to claim 3, wherein the fault prediction unit specifically comprises:
the diversity subunit is used for acquiring historical fault data and dividing the historical fault data into a training data set and a verification data set; the historical fault data comprises fault data of various fault modes of key components of the ship cannon system;
the off-line data prediction model subunit is used for constructing an off-line support vector machine regression prediction model by utilizing the training data set and the verification data set to obtain an off-line data prediction model;
the online prediction model subunit is used for monitoring the real-time characteristic data, and when the data volume of the real-time characteristic data reaches a preset modeling threshold value, an online support vector machine regression prediction model is constructed by using the real-time characteristic data to obtain an online prediction model; the real-time feature data includes: the feature extraction unit extracts feature data in real time;
the prediction value subunit is used for respectively predicting the real-time characteristic data by utilizing the offline data prediction model and the online prediction model to obtain an offline prediction value and an online prediction value;
the weight value subunit is used for respectively calculating an offline weight value of the offline predicted value and an online weight value of the online predicted value by using an adaptive weight algorithm;
and the fault prediction result subunit is used for calculating the fault prediction result by utilizing the offline prediction value, the online prediction value, the offline weight value and the online weight value.
5. The system of claim 3, wherein the control subsystem specifically comprises:
the parameter configuration module is used for configuring parameters of the data acquisition module and the bus data acquisition module according to monitoring parameters of different gun system key components;
the data management module is used for associating the data stored by the data storage module;
the historical data analysis module is used for calling the stored data through the data management module, carrying out historical data analysis on the stored data and transmitting an analysis result to the data display module for displaying;
and the data display module is used for acquiring and displaying the real-time sampling data of the data acquisition module and the bus data acquisition module, the characteristic data in the controller module and the analysis result of the historical data analysis module.
6. The system of claim 2, wherein the data acquisition module acquires pressure signals of firing springs of the automatic gun firing spring via pressure sensors mounted on the automatic gun firing spring.
7. The system of claim 2, wherein the data acquisition module acquires vibration signals of the gun carrier through vibration sensors mounted on a gun carrier bracket and a gun bed.
8. The system of claim 2, wherein the data acquisition module acquires the temperature signal of the electrical system follow-up frequency converter through a temperature sensor mounted on the electrical system follow-up frequency converter.
9. The system of claim 2, wherein the bus data acquisition module is configured to acquire the second signal via a self-test system of the vessel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010273166.6A CN111506043B (en) | 2020-04-09 | 2020-04-09 | Fault prediction system for key components of naval gun |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010273166.6A CN111506043B (en) | 2020-04-09 | 2020-04-09 | Fault prediction system for key components of naval gun |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111506043A true CN111506043A (en) | 2020-08-07 |
| CN111506043B CN111506043B (en) | 2021-04-09 |
Family
ID=71864538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010273166.6A Active CN111506043B (en) | 2020-04-09 | 2020-04-09 | Fault prediction system for key components of naval gun |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111506043B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112346893A (en) * | 2020-11-10 | 2021-02-09 | 深圳市康必达控制技术有限公司 | Fault prediction method, device, terminal and storage medium |
| CN112415303A (en) * | 2020-10-30 | 2021-02-26 | 桂林电子科技大学 | Air compressor life prediction system and method considering fault accumulation effect |
| CN112858872A (en) * | 2020-12-31 | 2021-05-28 | 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） | Circuit board health management circuit, device, control method and circuit board health manager |
| CN113091809A (en) * | 2021-03-26 | 2021-07-09 | 中国船舶重工集团公司第七一三研究所 | Detection system capable of automatically identifying equipment state |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243133A (en) * | 2011-04-02 | 2011-11-16 | 中北大学 | High-speed automaton fault diagnosis method based on movement patterns and impact signal analysis |
| CN107024141A (en) * | 2017-05-23 | 2017-08-08 | 中北大学 | Sound and vibration monitoring and the defect positioning method of quality are assembled for Ramming Device |
| CN207408818U (en) * | 2017-08-10 | 2018-05-25 | 黄河交通学院 | A kind of numerically-controlled machine tool with failure predication and diagnostic function |
| CN109934358A (en) * | 2019-01-30 | 2019-06-25 | 中国人民解放军32181部队 | Equipment failure prediction and health evaluating method, system and terminal device |
-
2020
- 2020-04-09 CN CN202010273166.6A patent/CN111506043B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243133A (en) * | 2011-04-02 | 2011-11-16 | 中北大学 | High-speed automaton fault diagnosis method based on movement patterns and impact signal analysis |
| CN107024141A (en) * | 2017-05-23 | 2017-08-08 | 中北大学 | Sound and vibration monitoring and the defect positioning method of quality are assembled for Ramming Device |
| CN207408818U (en) * | 2017-08-10 | 2018-05-25 | 黄河交通学院 | A kind of numerically-controlled machine tool with failure predication and diagnostic function |
| CN109934358A (en) * | 2019-01-30 | 2019-06-25 | 中国人民解放军32181部队 | Equipment failure prediction and health evaluating method, system and terminal device |
Non-Patent Citations (2)
| Title |
|---|
| 孙涛等: "舰炮故障本体建模技术研究", 《船舶电子工程》 * |
| 王凯等: "舰炮健康管理技术研究", 《舰船电子工程》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112415303A (en) * | 2020-10-30 | 2021-02-26 | 桂林电子科技大学 | Air compressor life prediction system and method considering fault accumulation effect |
| CN112415303B (en) * | 2020-10-30 | 2022-07-12 | 桂林电子科技大学 | Air compressor life prediction system and method considering fault accumulation effect |
| CN112346893A (en) * | 2020-11-10 | 2021-02-09 | 深圳市康必达控制技术有限公司 | Fault prediction method, device, terminal and storage medium |
| CN112858872A (en) * | 2020-12-31 | 2021-05-28 | 华中光电技术研究所（中国船舶重工集团公司第七一七研究所） | Circuit board health management circuit, device, control method and circuit board health manager |
| CN113091809A (en) * | 2021-03-26 | 2021-07-09 | 中国船舶重工集团公司第七一三研究所 | Detection system capable of automatically identifying equipment state |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111506043B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111506043B (en) | Fault prediction system for key components of naval gun | |
| CN106844775B (en) | Spacecraft fault rapid detection system | |
| WO2011073613A1 (en) | A method, apparatus and computer program for diagnosing a mode of operation of a machine | |
| CN110884687A (en) | Semi-physical real-time simulation verification platform for PHM technology of electromechanical system | |
| CN107991900B (en) | Simulation and self-healing method for latent and hidden faults of Antarctic telescope on semi-physical simulation platform | |
| CN113009845B (en) | Simulation test system and method for satellite software | |
| CN113776794B (en) | Fault diagnosis method, device and system for embedded edge calculation | |
| CN109491341A (en) | Monitoring and data analysis system for oil field operation equipment | |
| CN109696883B (en) | Numerical control machine tool state monitoring and early warning system based on cloud storage | |
| CN110749462A (en) | Industrial equipment fault detection method and system based on edge calculation | |
| CN115437339A (en) | Remote diagnosis method and device, electronic equipment and storage medium | |
| CN109643087B (en) | System and method for selecting controllable parameters for operational safety of a device | |
| CN109901470A (en) | A kind of servo motor test equipment control system and application method | |
| CN115877198A (en) | Primary and secondary fusion switch fault diagnosis early warning system based on edge calculation | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN101776724B (en) | Control method, device and system for inquiring test result of submarine cable line | |
| CN113537652A (en) | Equipment health monitoring and early warning method, system, storage medium and equipment | |
| CN113487182B (en) | Device health state evaluation method, device, computer device and medium | |
| CN114648212A (en) | Cloud computing-based ship equipment performance intelligent management system and method | |
| CN109507986A (en) | Long-distance monitoring method for oil field operation equipment | |
| CN110146756B (en) | Event inversion driven relay protection test analysis system and method | |
| CN115508749A (en) | Intermittent fault acquisition and test device and method for aviation assembly connector | |
| US20130234699A1 (en) | Power supply monitoring system and method thereof | |
| CN107682177B (en) | Communication fault monitoring system and method | |
| CN105346244A (en) | Silk-screen printing online monitoring system for solar cell panel |
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 |