CN116432082A - Ship fault feature analysis method, system and storage medium - Google Patents
Ship fault feature analysis method, system and storage medium Download PDFInfo
- Publication number
- CN116432082A CN116432082A CN202310316586.1A CN202310316586A CN116432082A CN 116432082 A CN116432082 A CN 116432082A CN 202310316586 A CN202310316586 A CN 202310316586A CN 116432082 A CN116432082 A CN 116432082A
- Authority
- CN
- China
- Prior art keywords
- ship
- fault
- analysis
- mode
- ship 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 285
- 238000000034 method Methods 0.000 claims abstract description 38
- 238000004891 communication Methods 0.000 claims description 16
- 238000013138 pruning Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000003068 static effect Effects 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 abstract description 27
- 230000008569 process Effects 0.000 abstract description 17
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000013135 deep learning Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000010705 motor oil Substances 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 208000027697 autoimmune lymphoproliferative syndrome due to CTLA4 haploinsuffiency Diseases 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of ship fault analysis, and provides a ship fault feature analysis method, a system and a storage medium, wherein the method comprises the following steps: when a ship fault code is received, determining a ship fault analysis mode based on the acquired current first resource information of the ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system; based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model; taking the ship fault characteristic information corresponding to the ship fault code as input of a target ship fault analysis model; and outputting the analysis result of the current ship fault by the target ship fault analysis model. According to the invention, fault analysis of the corresponding mode and a selection result output mode can be adaptively carried out according to the current resource availability condition of the ship control system, so that the fault diagnosis process is ensured to be matched with the actual resource, and the occurrence of clamping or resource waste is avoided.
Description
Technical Field
The invention relates to the technical field of ship fault analysis, in particular to a ship fault feature analysis method, a ship fault feature analysis system and a storage medium.
Background
The ships are complex systems which are 'independent' sailing on the sea, and once the critical components are out of order, the normal operation of the ships is seriously affected if the ships are not processed in time, and even serious loss and disastrous results are caused. The traditional fault diagnosis is to conduct diagnosis guidance according to expert experience or priori knowledge of specific components, and simple fault diagnosis work can be completed by observing the frequency spectrum change of the fault frequency. With the development of data mining technology, deep learning provides a new technical route for intelligent fault diagnosis. The deep learning network can get rid of the dependence on a large number of signal processing technologies and diagnostic experience, and directly adaptively extract fault characteristics from the frequency domain signals.
New generation ships are rapidly developing towards intelligentization, automation and unmanned directions, so that research on intelligent, efficient and rapid fault diagnosis and risk prediction technologies is important to guarantee safe and stable operation of the ships.
The retrieved Chinese patent application with the application number of CN202210580880.9 provides a ship part fault diagnosis method and device, wherein the method comprises the following steps: obtaining vibration acceleration signal data of parts in the running state process of ship equipment, preprocessing the data, labeling fault types aiming at different faults, taking the labeled data as a one-dimensional data set, and dividing the labeled data into a training set and a testing set; constructing a feature extractor of a deep learning fault diagnosis model for ship parts; constructing a classifier of a deep learning fault diagnosis model for ship parts; and constructing a deep learning fault diagnosis model for the ship parts through the feature extractor and the classifier. The method is suitable for diagnosing the fault of the ship part; the Chinese patent application with the application number of CN202210805948.9 provides a ship body structure fault prediction method using a convolutional neural network, which comprises the following steps: data preprocessing, constructing a convolutional neural network model, establishing a category information database, and establishing a fault prediction result database and fault prediction. The method utilizes the deep learning capability of a computer, carries out fault classification (comprising cracks, corrosion and deformation) on signals through a convolutional neural network, can further judge the severity of the structural fault of the ship body on the classification result, can predict the occurrence time of the fault, can find the fault position according to the prediction result and the classification information, and then carries out repair treatment in a period of time before the fault is about to occur, thereby ensuring the timely maintenance and normal use of the ship.
However, in practical application, the common PC of the ship engine room is used as a server, and the software and hardware resources are limited, so that long-period big data processing and analysis cannot be performed; at the same time, ocean vessels often do not have enough time and external technical assistance in the event of an ocean-going accident; in addition, the ship control system itself needs to use limited software and hardware resources to perform other control operations besides fault diagnosis, and the fault diagnosis process cannot call enough resources of the system in most cases.
Therefore, how to timely and effectively complete the fault identification, classification and diagnosis processes and output analysis results when the ship is likely to be in fault under the condition of limited software and hardware resources, and meanwhile, normal operation control of the ship is not affected, so that the method is one of the technical problems to be solved in the field.
Disclosure of Invention
The invention provides a ship fault characteristic analysis method, a system and a storage medium, which can adaptively carry out fault analysis of a corresponding mode and select a result output mode according to the current resource availability condition of a ship control system, ensure that a fault diagnosis process is matched with actual resources, avoid the occurrence of clamping or resource waste, thereby completing fault identification, classification and diagnosis processes and outputting analysis results without influencing the normal operation control of a ship.
In one aspect, the invention provides a method for analyzing fault characteristics of a ship, the method comprising:
when a ship fault code is received, current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system are obtained;
determining a ship fault analysis mode based on the first resource information and the second resource information;
based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model;
taking the ship fault characteristic information corresponding to the ship fault code as input of the target ship fault analysis model;
and the target ship fault analysis model outputs the analysis result of the current ship fault.
Further, the first resource information includes a first remaining memory resource, a first remaining video memory resource, and a first remaining broadband resource of the ship control system;
the second resource information includes a second available computing resource and a second available communication resource for each of the edge terminals.
Further, the ship fault analysis mode includes any selected combination of one of the first modes and one of the second modes: the first mode comprises a local analysis mode and a cloud analysis mode, and the second mode comprises an abbreviated analysis mode, a standard analysis mode and a detailed analysis mode.
Further, after performing parameter configuration on at least one candidate ship fault analysis model based on the ship fault analysis mode, obtaining a target ship fault analysis model, including:
determining at least one candidate ship fault analysis model from among the existing plurality of available ship fault analysis models based on the ship fault analysis mode;
and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
Further, the target ship fault analysis model outputs an analysis result of the current ship fault, including:
based on the ship fault analysis mode, determining an output mode of the analysis result of the current ship fault, wherein the output mode comprises the following steps: plain text output, static teletext output or dynamic multimedia output.
Further, the candidate ship fault analysis model is a deep learning model or a neural network model.
On the other hand, the invention also provides a ship fault characteristic analysis system, which comprises a ship control system and a plurality of edge terminals which are cooperated with the ship control system, wherein the ship fault characteristic analysis system also comprises a resource information acquisition unit, a fault analysis mode determination unit, a model parameter configuration unit and a fault analysis result output unit;
the resource information acquisition unit is used for acquiring current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system when receiving a ship fault code;
the fault analysis mode determining unit is used for determining a ship fault analysis mode based on the first resource information and the second resource information;
the model parameter configuration unit is used for obtaining a target ship fault analysis model after parameter configuration is carried out on at least one candidate ship fault analysis model based on the ship fault analysis mode; the ship fault characteristic information corresponding to the ship fault code is used as input of the target ship fault analysis model;
the fault analysis result output unit is used for determining an output mode of an analysis result output by the target ship fault analysis model based on the ship fault analysis mode.
Further, the first resource information includes a first remaining memory resource, a first remaining video memory resource, and a first remaining broadband resource of the ship control system;
the second resource information comprises second available computing power resources and second available communication resources of each edge terminal;
the marine vessel failure analysis mode comprises any selected combination of one of the first modes and one of the second modes: the first mode comprises a local analysis mode and a cloud analysis mode, and the second mode comprises an abbreviated analysis mode, a standard analysis mode and a detailed analysis mode.
Further, the model parameter configuration unit is configured to obtain a target ship fault analysis model after performing parameter configuration on at least one candidate ship fault analysis model based on the ship fault analysis mode, and includes:
the model parameter configuration unit determines at least one candidate ship fault analysis model from the existing plurality of available ship fault analysis models based on the ship fault analysis mode;
and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
The present invention also provides a computer readable storage medium having a computer program stored thereon, characterized in that the storage medium has a computer program stored thereon, which when executed by a processor causes the processor to implement a ship fault signature analysis method as described in any one of the above.
In addition, the present invention may also provide a portable electronic device including a memory and a processor, the electronic device being accessible to a computer-readable storage medium (e.g., an optical disk, a USB flash disk, or other external storage device) as described above.
According to the ship fault feature analysis method and system, firstly, when a ship fault code is received, a ship fault analysis mode is determined according to the acquired current first resource information of a ship control system and the acquired second resource information of a plurality of edge terminals cooperated with the ship control system; then, based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model; taking the ship fault characteristic information corresponding to the ship fault code as input of a target ship fault analysis model; and finally, outputting an analysis result of the current ship fault by the target ship fault analysis model. Therefore, the invention can adaptively carry out fault analysis of the corresponding mode and select a result output mode according to the current resource availability condition of the ship control system, ensure that the fault diagnosis process is matched with the actual resource, and avoid the occurrence of clamping or resource waste.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow diagram of a method for analyzing a fault signature of a ship according to an embodiment of the present invention;
FIG. 2 is a flow chart of determining a failure analysis mode of a ship in a failure signature analysis method of an embodiment of the present invention;
FIG. 3 is a schematic plan view of a ship control system to which the ship fault signature analysis method of the present invention is applied;
FIG. 4 is a schematic diagram of the components of a portion of the functional units of a marine fault signature system implementing the marine fault signature method of FIG. 1;
fig. 5 is a schematic structural view of a computer storage medium and an electronic device implementing the ship fault signature analysis method of fig. 1.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The ship fault signature analysis method of the present invention is described below with reference to fig. 1 to 2.
Fig. 1 is a schematic flow chart of a ship fault feature analysis method provided by the invention.
As shown in fig. 1, the method for analyzing the fault characteristics of the ship according to the present embodiment may be executed by a ship fault characteristic analysis system, and at least includes the following steps:
s100, when a ship fault code is received, acquiring current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system;
s200, determining a ship fault analysis mode based on the first resource information and the second resource information;
s300, carrying out parameter configuration on at least one candidate ship fault analysis model based on the ship fault analysis mode to obtain a target ship fault analysis model;
s400, taking the ship fault characteristic information corresponding to the ship fault code as input of the target ship fault analysis model;
s500, outputting analysis results of the ship faults by the target ship fault analysis model.
The detailed embodiments of the steps described above and the corresponding improvements and innovations will be further described, step by step or in conjunction with other figures.
The execution triggering time of the step S100 is "when a ship fault code is received". Unlike the prior art, which generally requires periodic or uninterrupted acquisition of characteristic parameters to perform the fault diagnosis process, the method of the present embodiment is performed with a trigger timing, and is only started when a ship fault code is received.
The fault code is a fault identifier which can be visually prompted by the current intelligent ship navigation control system. Taking a diesel powered vessel as an example, in one particular embodiment, the marine diesel data acquisition and communication system is divided into 3 parts, namely a data acquisition module, a wireless data transmission module and a marine shore-based client. The data acquisition module can continuously and autonomously acquire ship data including longitude, latitude, ground speed, storage battery voltage, ambient temperature, instantaneous oil consumption rate, accumulated oil consumption, accelerator opening, current fault code, historical fault code and the like.
It should be understood that the ship fault code is merely a "possible" and "potential" fault outcome indication, and does not confirm whether the fault and the specific type of fault, and the process does not have access to a fault diagnostic model.
And in response to receiving the ship fault code, activating the ship fault characteristic analysis method.
Specifically, at this time, current first resource information of the ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system need to be acquired.
Illustratively, the first resource information includes a first remaining memory resource M, a first remaining video memory resource V, and a first remaining broadband resource N of the ship control system;
the second resource information includes a second available computing resource a and a second available communication resource E of each of the edge terminals.
As an advantage, aiming at the problems that a common PC (personal computer) of a ship engine room is used as a server, the software and hardware resources are limited, and long-period big data processing and analysis cannot be performed, the invention adopts the cooperative computing of the edge cloud.
Specifically, the edge terminal can process and infer real-time short-period data, but the edge terminal can provide limited computing power and needs interaction between a terminal control system and a cloud computing terminal; the cloud computing end has sufficient computing power, can perform non-real-time long-period big data analysis and model training, but has delay in communication.
Specifically, when the cloud mode or the local mode is started, the following embodiments will be further described.
Specifically, step S200 is further described in conjunction with fig. 2.
In the step S200, a ship fault analysis mode is determined based on the first resource information and the second resource information.
The marine vessel failure analysis mode comprises any selected combination of one of the first modes and one of the second modes: the first mode comprises a local analysis mode and a cloud analysis mode, and the second mode comprises an abbreviated analysis mode, a standard analysis mode and a detailed analysis mode.
It can be seen that there are two alternatives for the first mode and three alternatives for the second mode, and therefore the ship fault analysis mode comprises at least 2×3=6 analysis modes.
Firstly, the present embodiment selects an option from the first modes, i.e. a local analysis mode or a cloud analysis mode, based on the first remaining broadband resource N and the second available communication resource E;
it can be understood that the local analysis mode refers to that in the subsequent fault analysis process, the fault analysis model does not need to interact with the cloud database, and fault diagnosis is performed only by using the existing local data and data models; in the cloud analysis mode, interaction with a cloud database is required, and besides the local data, the cloud also needs to preprocess the data and adaptively update the model.
As an example, the size of the first remaining wideband resource N is represented by a value m, and in particular, may be represented by a downlink download rate (MB/S); the size of the second available communication resource E is represented by a percentage Er, that is, the ratio of the remaining available communication resources of the edge terminal to the total communication resources of the edge terminal is determined, where the total communication resources of the edge terminal include one of broadband resources, the number of data transmission channels, the number of data buffering channels, or any combination thereof. For ease of understanding and consistent with the foregoing resource scaling expressions, the following takes the total communication resources of the edge terminal as broadband resources as an example.
Preferably, in one embodiment, if m and Er satisfy the following condition (a), then a cloud analysis mode is selected from the first modes:
wherein Mt is a preset first remaining wideband resource size threshold, et is a preset second available communication resource percentage threshold;
in one embodiment, if m and Er satisfy the following condition (B), then a local analysis mode is selected from the first modes:
the MEDif is a preset broadband difference value, and the MEDif is 0.25< (1+Er).
If neither condition (A) nor condition (B) is satisfied by m and Er, the method selects from the first modes based on the history, e.g., selects the most selected mode of the first modes up to the current point in time.
Secondly, the present embodiment selects an option, i.e., a glance analysis mode, a standard analysis mode, or a detailed analysis mode, from the second mode based on the first remaining memory resource M and the second available computing power resource a;
specifically, the size of the first remaining memory resource M is denoted by Nm, the second available computing power resource a may be determined by the memory remaining capacity a and the buffer remaining size b of the current edge terminal and the remaining memory size c,
in particular, the method comprises the steps of,
wherein w is i (i=1, 2, 3) is a weight coefficient,
0＜w i ＜1。
obviously, the size index of the available computing resource A integrates the respective numerical values of the memory residual capacity a, the buffer residual size b and the residual memory size c of the current edge terminal and the balance of the mutual paper, and simultaneously, the weight preference of different indexes is regulated through the weight coefficient. For example, if better buffer performance is desired, w can be reduced 3 (in this case, greater A would be used when b is forced to be greater).
Preferably, in one embodiment, the detailed analysis mode is selected from the second mode if Nm and a satisfy the following condition (C):
nm is greater than a first preset standard value and a is greater than a second preset standard value … … (C).
It can be understood that at this time, the first remaining memory resource M and the second available computing resource a are both very sufficient and enough to perform a detailed analysis mode of fault diagnosis;
preferably, in one embodiment, the abbreviated analysis mode is selected from the second mode if Nm and a satisfy the following condition (D):
nm is less than the third preset standard value and a is less than the fourth preset standard value … … (D).
It can be understood that at this time, the first remaining memory resource M and the second available computing resource a are insufficient, and a abbreviated analysis mode for performing fault diagnosis is selected;
preferably, the third preset standard value is smaller than the first preset standard value; the fourth preset standard value is smaller than the second preset standard value.
Outside conditions (C) and (D), a standard analysis mode may be selected from the second modes.
It can be understood that the abbreviated analysis mode, the standard analysis mode and the detailed analysis mode determine the subsequent processing strategies of the corresponding fault analysis model, and after the subsequent processing strategies are determined, the output mode of the analysis result corresponds to the analysis mode.
Specifically, step S300 is performed: based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model;
specifically, step S300 is performed as follows: determining at least one candidate ship fault analysis model from the existing plurality of available ship fault analysis models based on the ship fault analysis model;
and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
Specifically, if the ship fault analysis mode does not include the cloud analysis mode, determining at least one candidate ship fault analysis model from a plurality of available ship fault analysis models existing locally; if the ship fault analysis mode does not comprise the local analysis mode, determining at least one candidate ship fault analysis model from a plurality of available ship fault analysis models existing in the cloud;
specifically, if the ship fault analysis mode is a shorthand analysis mode, pruning operation is carried out on the candidate ship fault analysis model to obtain the target ship fault analysis model; if the ship fault analysis mode is a detailed analysis mode and a cloud analysis mode, performing cloud updating operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
Of course, if the model is the standard analysis model, no operation is required, and the model itself for analyzing the ship fault candidate calling the standard is executed.
In one embodiment, the candidate ship fault analysis model is a deep learning model or a neural network model. The pruning operation of the deep learning model or the neural network model belongs to the prior art, such as ' Lin Jingdong, wu Xinyi, chai Yi and the like '. Convolutional neural network structure optimization overview [ J ]. Automation journal 2020,46 (01): 24-37 ' teaches that ' the network pruning method has been proposed in the popularity of deep learning, which has been widely used for the optimization problem of the network in nineties of the last century '; this embodiment is not specifically developed.
Next, step S400 takes the ship fault characteristic information corresponding to the ship fault code as input of the target ship fault analysis model; in step S500, the target ship fault analysis model outputs an analysis result of the present ship fault.
The target ship fault analysis model outputs the analysis result of the current ship fault, and specifically comprises the following steps:
based on the ship fault analysis mode, determining an output mode of the analysis result of the current ship fault, wherein the output mode comprises the following steps: plain text output, static teletext output or dynamic multimedia output.
As an example, if the first remaining video memory resource V is insufficient, or the current ship fault analysis mode includes a glance analysis mode, a plain text output mode is adopted;
if the first residual video memory resource V is sufficient and the current ship fault analysis mode comprises a detailed analysis mode, adopting a dynamic multimedia output mode;
and if the first residual video memory resource V is sufficient and the current ship fault analysis mode comprises a standard analysis mode, adopting a static image-text output mode.
In the above embodiment, as a specific expression form of the ship fault characteristic information corresponding to the ship fault code, the specific expression form includes a battery voltage, an ambient temperature, a relative humidity, an atmospheric pressure, a rotation speed, a torque, a cooling water temperature, an after-cooling temperature, an engine oil temperature, an exhaust temperature, an engine oil pressure, an after-cooling pressure, an instantaneous fuel consumption rate, an accumulated fuel consumption amount, an accelerator opening degree, and the like; of course, the type of information may also be selected as the ship fault signature information.
It is known to those skilled in the art how to select the ship fault characteristic information and how to perform fault diagnosis using a deep learning model or a neural network model, which is not specifically developed in this embodiment, and particularly, reference may be made to other prior arts including the background art, for example, reference may be made to "golden's, liu Pengpeng. A ship diesel fault diagnosis technique [ J ] based on an improved deep learning algorithm, ship science technique, 2021,043 (007): 131-134" or "Xu Lijun. A ship diesel fault diagnosis technique [ D ] based on a neural network, university of Jiangsu science and the like.
The above-described prior art is incorporated as part of the present embodiment to facilitate a better understanding of the prior art foundation and improved differentiation of the present invention by those skilled in the art.
See fig. 3 based on fig. 1-2. Fig. 3 is a schematic plan view of a ship control system to which the ship fault signature analysis method according to the present invention is applied.
Fig. 3 shows a plan view structure of a ship sailing in a water area, which includes a ship control system, a plurality of edge terminals cooperatively controlled with the ship control system and performing fault diagnosis, a cloud communication module for exchanging data with a cloud database, and a plurality of information storage units for storing related programs and data. The technical scheme of the invention can be specifically applied to the ship control process shown in fig. 3.
Fig. 4 is a schematic diagram showing the components of a part of functional units of a ship fault signature analysis system for implementing the ship fault signature analysis method of fig. 1.
The ship fault signature analysis system of fig. 4 comprises a ship control system and a plurality of edge terminals cooperated with the ship control system;
the ship fault characteristic analysis system further comprises a resource information acquisition unit, a fault analysis mode determination unit, a model parameter configuration unit and a fault analysis result output unit;
the resource information acquisition unit is used for acquiring current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system when receiving a ship fault code; the first resource information comprises a first residual memory resource, a first residual video memory resource and a first residual broadband resource of the ship control system; the second resource information comprises second available computing power resources and second available communication resources of each edge terminal;
the fault analysis mode determining unit is used for determining a ship fault analysis mode based on the first resource information and the second resource information; the ship fault analysis mode comprises any selected combination of one of the following first modes and one of the following second modes:
first mode: a local analysis mode and a cloud analysis mode;
second mode: a glance analysis mode, a standard analysis mode, and a detailed analysis mode;
the model parameter configuration unit is used for obtaining a target ship fault analysis model after parameter configuration is carried out on at least one candidate ship fault analysis model based on the ship fault analysis mode; the ship fault characteristic information corresponding to the ship fault code is used as input of the target ship fault analysis model;
the fault analysis result output unit is used for determining an output mode of an analysis result output by the target ship fault analysis model based on the ship fault analysis mode. The output mode comprises the following steps: plain text output, static teletext output or dynamic multimedia output.
The model parameter configuration unit obtains a target ship fault analysis model after performing parameter configuration on at least one candidate ship fault analysis model based on the ship fault analysis mode, and specifically includes: determining at least one candidate ship fault analysis model from the existing plurality of available ship fault analysis models based on the ship fault analysis model; and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
It is to be understood that the specific process of determining the failure analysis mode of the ship by the failure analysis mode determining unit according to fig. 4 based on the first resource information and the second resource information corresponds to the embodiment according to fig. 1, which is not specifically developed in this embodiment.
The specific process of determining the output mode of the analysis result output by the target ship fault analysis model by the fault analysis result output unit according to fig. 4 based on the ship fault analysis mode corresponds to the embodiment according to fig. 2.
Specifically, if the first residual video memory resource V is insufficient, or the current ship fault analysis mode comprises a glance analysis mode, adopting a plain text output mode;
if the first residual video memory resource V is sufficient and the current ship fault analysis mode comprises a detailed analysis mode, adopting a dynamic multimedia output mode;
and if the first residual video memory resource V is sufficient and the current ship fault analysis mode comprises a standard analysis mode, adopting a static image-text output mode.
The above technical solution of the present invention may also be implemented as computer program instructions, implemented by a portable electronic device.
In particular, referring to fig. 5, the portable electronic device includes a memory and a processor, and the electronic device has access to a computer readable storage medium (e.g., an optical disc, a usb disk, or other external storage device) storing a computer program that, when executed by the processor, causes the processor to implement a method of analyzing a marine fault signature as described in fig. 1.
According to the technical scheme, when the ship fault code is received, a ship fault analysis mode is determined according to the acquired current first resource information of the ship control system and the acquired second resource information of a plurality of edge terminals cooperated with the ship control system; based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model; taking the ship fault characteristic information corresponding to the ship fault code as input of a target ship fault analysis model; and outputting the analysis result of the current ship fault by the target ship fault analysis model. Therefore, the invention can adaptively carry out fault analysis of the corresponding mode and select a result output mode according to the current resource availability condition of the ship control system, ensure that the fault diagnosis process is matched with the actual resource, and avoid the occurrence of clamping or resource waste.
Therefore, the technical scheme of the invention can adaptively carry out fault analysis of the corresponding mode and select a result output mode according to the current resource availability condition of the ship control system, ensure that the fault diagnosis process is matched with the actual resource, avoid the occurrence of clamping or resource waste, thereby completing the fault identification, classification and diagnosis processes and outputting the analysis result without affecting the normal operation control of the ship.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of analyzing a marine fault signature, comprising:
when a ship fault code is received, current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system are obtained;
determining a ship fault analysis mode based on the first resource information and the second resource information;
based on the ship fault analysis mode, carrying out parameter configuration on at least one candidate ship fault analysis model to obtain a target ship fault analysis model;
taking the ship fault characteristic information corresponding to the ship fault code as input of the target ship fault analysis model;
and the target ship fault analysis model outputs the analysis result of the current ship fault.
2. The marine vessel fault signature analysis method of claim 1, wherein the first resource information comprises a first remaining memory resource, a first remaining video memory resource, and a first remaining broadband resource of the marine vessel control system;
the second resource information includes a second available computing resource and a second available communication resource for each of the edge terminals.
3. The marine vessel fault signature analysis method of claim 1, wherein the marine vessel fault analysis mode comprises any selected combination of one of the first modes and one of the second modes: the first mode comprises a local analysis mode and a cloud analysis mode, and the second mode comprises an abbreviated analysis mode, a standard analysis mode and a detailed analysis mode.
4. The ship fault signature analysis method according to claim 1, wherein the obtaining a target ship fault analysis model after parameter configuration of at least one candidate ship fault analysis model based on the ship fault analysis mode comprises:
determining at least one candidate ship fault analysis model from among the existing plurality of available ship fault analysis models based on the ship fault analysis mode;
and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
5. The ship fault signature analysis method according to claim 1, wherein the target ship fault analysis model outputs an analysis result of the present ship fault, comprising:
based on the ship fault analysis mode, determining an output mode of the analysis result of the current ship fault, wherein the output mode comprises the following steps: plain text output, static teletext output or dynamic multimedia output.
6. The ship fault signature analysis method according to any one of claims 1 to 5, wherein the candidate ship fault analysis model is a deep learning model or a neural network model.
7. The ship fault characteristic analysis system comprises a ship control system and a plurality of edge terminals which are cooperated with the ship control system, and is characterized by further comprising a resource information acquisition unit, a fault analysis mode determination unit, a model parameter configuration unit and a fault analysis result output unit;
the resource information acquisition unit is used for acquiring current first resource information of a ship control system and second resource information of a plurality of edge terminals cooperated with the ship control system when receiving a ship fault code;
the fault analysis mode determining unit is used for determining a ship fault analysis mode based on the first resource information and the second resource information;
the model parameter configuration unit is used for obtaining a target ship fault analysis model after parameter configuration is carried out on at least one candidate ship fault analysis model based on the ship fault analysis mode; the ship fault characteristic information corresponding to the ship fault code is used as input of the target ship fault analysis model;
the fault analysis result output unit is used for determining an output mode of an analysis result output by the target ship fault analysis model based on the ship fault analysis mode.
8. The marine vessel fault signature analysis system of claim 7, wherein the first resource information comprises a first remaining memory resource, a first remaining video memory resource, and a first remaining broadband resource of the marine vessel control system;
the second resource information comprises second available computing power resources and second available communication resources of each edge terminal;
the marine vessel failure analysis mode comprises any selected combination of one of the first modes and one of the second modes: the first mode comprises a local analysis mode and a cloud analysis mode, and the second mode comprises an abbreviated analysis mode, a standard analysis mode and a detailed analysis mode.
9. The ship fault signature analysis system according to claim 7, wherein the model parameter configuration unit is configured to obtain a target ship fault analysis model after parameter configuration of at least one candidate ship fault analysis model based on the ship fault analysis mode, and includes:
the model parameter configuration unit determines at least one candidate ship fault analysis model from the existing plurality of available ship fault analysis models based on the ship fault analysis mode;
and carrying out cloud updating or pruning operation on the candidate ship fault analysis model to obtain the target ship fault analysis model.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the storage medium stores a computer program, which, when being executed by a processor, causes the processor to implement a ship fault signature analysis method as claimed in any one of the preceding claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310316586.1A CN116432082B (en) | 2023-03-29 | 2023-03-29 | Ship fault feature analysis method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310316586.1A CN116432082B (en) | 2023-03-29 | 2023-03-29 | Ship fault feature analysis method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116432082A true CN116432082A (en) | 2023-07-14 |
| CN116432082B CN116432082B (en) | 2024-01-09 |
Family
ID=87080778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310316586.1A Active CN116432082B (en) | 2023-03-29 | 2023-03-29 | Ship fault feature analysis method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116432082B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2109323A1 (en) * | 2008-04-08 | 2009-10-14 | Tieto Oyj | Dynamic fault analysis for a centrally managed network element in a telecommunications system |
| CN102404860A (en) * | 2010-09-14 | 2012-04-04 | 中兴通讯股份有限公司 | Downlink resource allocation method and device in long term evolution (LTE) system |
| CN104639451A (en) * | 2013-11-14 | 2015-05-20 | 中兴通讯股份有限公司 | Data flow distribution method and controller |
| CN110334844A (en) * | 2019-04-23 | 2019-10-15 | 武汉理工大学 | Utilize the ship optimized use method of the main promotion diesel engine operating status of ship |
| CN110740473A (en) * | 2019-10-22 | 2020-01-31 | 中国科学院计算技术研究所 | management method for mobile edge calculation and edge server |
| CN111611085A (en) * | 2020-05-28 | 2020-09-01 | 中国科学院自动化研究所 | Man-machine hybrid enhanced intelligent system, method and device based on cloud edge collaboration |
| CN111638458A (en) * | 2020-06-23 | 2020-09-08 | 广州小鹏汽车科技有限公司 | Method and device for analyzing battery cell fault |
| CN112001116A (en) * | 2020-07-17 | 2020-11-27 | 新华三大数据技术有限公司 | Cloud resource capacity prediction method and device |
| CN111999088A (en) * | 2020-08-29 | 2020-11-27 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
| WO2021127640A1 (en) * | 2019-12-20 | 2021-06-24 | Cresance Inc. | Modeling cloud inefficiencies using domain-specific templates |
| CN113074979A (en) * | 2021-05-12 | 2021-07-06 | 江苏海事职业技术学院 | Fault locking method based on ship data monitoring |
| CN113485841A (en) * | 2021-07-28 | 2021-10-08 | 腾讯科技（深圳）有限公司 | Data processing method and device based on edge calculation and readable storage medium |
| CN115099264A (en) * | 2022-05-26 | 2022-09-23 | 哈尔滨工程大学 | Ship part fault diagnosis method and device, computer and computer storage medium |
| KR20220129733A (en) * | 2021-03-17 | 2022-09-26 | 삼성중공업 주식회사 | Ship having fault diagnosis system |
| CN115374961A (en) * | 2022-07-11 | 2022-11-22 | 江苏科技大学 | Ship power operation and maintenance system and operation and maintenance method |
| KR20220167008A (en) * | 2021-06-11 | 2022-12-20 | 강병석 | A system for predicting equipment failure in ship and a method of predicting thereof |
-
2023
- 2023-03-29 CN CN202310316586.1A patent/CN116432082B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2109323A1 (en) * | 2008-04-08 | 2009-10-14 | Tieto Oyj | Dynamic fault analysis for a centrally managed network element in a telecommunications system |
| CN102404860A (en) * | 2010-09-14 | 2012-04-04 | 中兴通讯股份有限公司 | Downlink resource allocation method and device in long term evolution (LTE) system |
| CN104639451A (en) * | 2013-11-14 | 2015-05-20 | 中兴通讯股份有限公司 | Data flow distribution method and controller |
| CN110334844A (en) * | 2019-04-23 | 2019-10-15 | 武汉理工大学 | Utilize the ship optimized use method of the main promotion diesel engine operating status of ship |
| CN110740473A (en) * | 2019-10-22 | 2020-01-31 | 中国科学院计算技术研究所 | management method for mobile edge calculation and edge server |
| WO2021127640A1 (en) * | 2019-12-20 | 2021-06-24 | Cresance Inc. | Modeling cloud inefficiencies using domain-specific templates |
| CN111611085A (en) * | 2020-05-28 | 2020-09-01 | 中国科学院自动化研究所 | Man-machine hybrid enhanced intelligent system, method and device based on cloud edge collaboration |
| CN111638458A (en) * | 2020-06-23 | 2020-09-08 | 广州小鹏汽车科技有限公司 | Method and device for analyzing battery cell fault |
| CN112001116A (en) * | 2020-07-17 | 2020-11-27 | 新华三大数据技术有限公司 | Cloud resource capacity prediction method and device |
| CN111999088A (en) * | 2020-08-29 | 2020-11-27 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
| KR20220129733A (en) * | 2021-03-17 | 2022-09-26 | 삼성중공업 주식회사 | Ship having fault diagnosis system |
| CN113074979A (en) * | 2021-05-12 | 2021-07-06 | 江苏海事职业技术学院 | Fault locking method based on ship data monitoring |
| KR20220167008A (en) * | 2021-06-11 | 2022-12-20 | 강병석 | A system for predicting equipment failure in ship and a method of predicting thereof |
| CN113485841A (en) * | 2021-07-28 | 2021-10-08 | 腾讯科技（深圳）有限公司 | Data processing method and device based on edge calculation and readable storage medium |
| CN115099264A (en) * | 2022-05-26 | 2022-09-23 | 哈尔滨工程大学 | Ship part fault diagnosis method and device, computer and computer storage medium |
| CN115374961A (en) * | 2022-07-11 | 2022-11-22 | 江苏科技大学 | Ship power operation and maintenance system and operation and maintenance method |
Non-Patent Citations (3)
| Title |
|---|
| M.BLANKE AND T.F. LOOTSMA: "Adaptive observer for diesel fault detection in ship propulsion benchmark", EUROPEAN CONTROL CONFERENCE * |
| 张孝勇: "基于PCI的船舶动力装置监测与故障诊断系统设计", 硕士电子期刊, no. 4 * |
| 黎锌;: "船舶设备故障诊断技术及其应用研究", 内燃机与配件, no. 08 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116432082B (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944648B (en) | Large ship speed and oil consumption rate prediction method | |
| CN112287986B (en) | Image processing method, device, equipment and readable storage medium | |
| Soner et al. | Statistical modelling of ship operational performance monitoring problem | |
| EP3380903A1 (en) | Marine vessel performance monitoring | |
| CN112088122B (en) | Method and system for evaluating actual sea area propulsion performance of ship and computer readable storage medium | |
| CN113847950A (en) | Intelligent ship equipment state monitoring system based on cloud computing and information interaction method | |
| CN116643517A (en) | Accident prevention equipment for underwater manned submersible vehicle | |
| CN116432082B (en) | Ship fault feature analysis method, system and storage medium | |
| CN114418930A (en) | Underwater whale target detection method based on light YOLOv4 | |
| CN116089787B (en) | Ship subsystem running state analysis method and system based on analytic hierarchy process | |
| Gupta et al. | Big data analytics as a tool to monitor hydrodynamic performance of a ship | |
| CN115984084B (en) | Remote sensing distributed data processing method based on dynamic detachable network | |
| KR20210116798A (en) | Wave information collecting device for economic operation of ship using digital twin | |
| CN116401522A (en) | Financial service dynamic recommendation method and device | |
| CN116074380A (en) | Method and system for self-management of Internet of things gateway in offline environment | |
| CN116136926A (en) | Underwater robot health management system based on Bayesian network | |
| CN111897730A (en) | AI algorithm evaluation method, system, equipment and medium in urban brain construction | |
| CN116703001A (en) | Oil consumption prediction method and system of intelligent ship, intelligent ship and medium | |
| CN116395105B (en) | Automatic lifting compensation method and system for unmanned ship | |
| CN114638152B (en) | Deep sea Argo profile buoy energy management method based on HGP-MPC | |
| EP4102366B1 (en) | Method and device for optimising the sensor resources of a multi-sensor system | |
| CN112801380B (en) | Load prediction method for data annotation cloud server | |
| CN112560347B (en) | Method and system for predicting remaining service life of aero-engine and electronic equipment | |
| US20240104336A1 (en) | Guided dialogue using language generation neural networks and search | |
| CN115081751A (en) | Method for predicting residual service life of equipment based on data preprocessing and deep learning |
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 |