Coastal inland ship condition-based maintenance system and method based on ship-shore cooperation

Abstract

The invention relates to a coastal inland ship condition-based maintenance system and method based on ship-shore cooperation. The invention relates to the technical field of condition-based maintenance of coastal inland ships. The system comprises a ship-end condition-based maintenance system, a shore-end auxiliary decision-making system and a ship-shore communication system, the ship-end condition-based maintenance system performs data acquisition, data storage and management, data processing, intelligent analysis, fault trend prediction, residual life prediction and maintenance plan making; the shore-end auxiliary decision-making system comprises a shore-end remote support system and a handheld wireless terminal and is used for performing expert auxiliary decision-making; and the ship-shore communication system comprises ship-end communication equipment and shore-end communication equipment for data communication. The ship condition-based maintenance process is digitalized and intelligent, so that the condition-based maintenance process is more intuitive and efficient, and the use method is simpler and easier to learn.

Description

Technical Field

[0001] The present invention relates to the technical field of coastal inland river vessel condition-based maintenance, and is a coastal inland river vessel condition-based maintenance system and method based on ship-shore collaboration. Background Art

[0002] Inland waterway shipping is not only an important part of my country's comprehensive transportation system and comprehensive utilization of water resources, but also an important strategic resource for achieving sustainable economic and social development. It plays a vital role in promoting economic development, cultural dissemination, social progress, etc. Since modern times, as an important carrier connecting the development of the Yangtze River Economic Belt, Shanghai's urban construction, and coastal city trade, its economic activity unit, the role of coastal inland river ships, is crucial, playing an important role in deepening and safeguarding major national strategies, promoting the development of the Yangtze River Delta, and the construction of river-sea transport.

[0003] With the development of shipping and the improvement of modern ship design, production and manufacturing, modern ships are becoming more and more intelligent and integrated, and their structural functions and mission requirements are becoming more complex and diverse. Therefore, more stringent requirements are put forward for their safety and reliability, and their maintenance and guarantee costs are increasing. At the same time, due to the time-varying nature of the system itself, the harsh operating environment and the influence of many external factors, the probability of failure is also increasing. Once an accident occurs in the ship's systems, it will cause huge personal and property losses.

[0004] With the rapid development of detection technology, communication technology and operational decision-making theory, engineering systems in various fields such as aviation, aerospace, and navigation are becoming increasingly complex, and the cost of R&D, production, and manufacturing, especially operation and maintenance management, is increasing. At the same time, due to the increase in components and influencing factors, the probability of system failure is gradually increasing. Therefore, the condition-based maintenance and health management of high-end equipment have gradually become the focus of attention in the field of shipping. The condition-based maintenance system can detect fault information early, reduce operation and maintenance costs, and ensure safe and efficient operation of equipment by collecting and monitoring equipment operation information and environmental information in real time.

[0005] However, most of the existing situation-based maintenance systems have problems such as insufficient intelligence and low prediction accuracy. Therefore, it is urgent to propose a situation-based maintenance system for coastal inland ships based on ship-shore collaboration, reduce the labor intensity of crew members according to the operating environment and characteristics of coastal inland ships, study and build a digital and intelligent technology system for coastal inland ships, and break through key technologies such as "ship-shore-cloud" human-machine co-driving, equipment operation performance decay prediction and situation-based maintenance decision-making in the inland shipping environment. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention aims at the above-mentioned coastal and inland waterway shipping development needs, and provides a coastal and inland waterway vessel situation-based maintenance system and method based on ship-shore collaboration.

[0007] The present invention provides the following technical solutions:

[0008] A coastal inland river vessel situation maintenance system based on ship-shore collaboration, the system comprising: a ship-side situation maintenance system, a shore-side auxiliary decision-making system and a ship-shore communication system;

[0009] The ship-side condition-based maintenance system performs data collection, data storage and management, data processing, intelligent analysis, fault trend prediction, remaining life prediction, and maintenance plan formulation;

[0010] The shore-side decision-making support system includes the shore-side remote support system and handheld wireless terminals for expert-assisted decision-making; the ship-shore communication system includes ship-side communication equipment and shore-side communication equipment for data communication.

[0011] Preferably, the ship-side situation-based maintenance system includes a data acquisition module, a data processing module, an intelligent analysis module, a prediction and decision-making module, and a maintenance execution module;

[0012] The data acquisition module collects the operating data of the ship equipment in real time, including temperature, pressure, and vibration parameters, through sensors installed on the ship equipment, and transmits these data to the data processing module;

[0013] The data processing module processes missing values, outlier filtering, smoothing and other data cleaning processes to improve data quality so that the processed data can better reflect the performance status of the equipment. At the same time, the processed data is sent to the server and the intelligent analysis module respectively;

[0014] The intelligent analysis module uses deep learning algorithms such as two-dimensional convolutional neural networks to intelligently analyze the processed data and predict the failure trend and remaining life of the equipment;

[0015] The predictive decision module combines the results of the intelligent analysis module with the maintenance decision library to develop an optimal maintenance plan, including maintenance time, maintenance location, and maintenance content; the maintenance execution module automatically or manually adjusts the ship's operating status and performs maintenance operations according to the plan of the predictive decision module to ensure that the equipment is in the best operating state.

[0016] Preferably, the data processing method is based on the Hampel filtering principle and performs time series anomaly processing according to the characteristics of the ship navigation data, thereby eliminating invalid parameters and improving data quality.

[0017] Preferably, the shore-side remote support system obtains the ship's operating information in real time, and when the ship generates a situation-based maintenance plan, the expert-assisted decision-making function is realized through real-time remote connection dialogue.

[0018] Preferably, the ship-shore communication system includes a ship-side communication module and a shore-side communication module; the ship-side communication module communicates through multiple frequency bands and supports multiple communication frequency bands at the same time to ensure the stability and reliability of communication and realize remote transmission of data;

[0019] The shore communication module receives the data sent by the ship, restores it to the original data through decoding, and sends it to the shore auxiliary decision-making system.

[0020] A method for condition-based maintenance of coastal inland waterway vessels based on ship-shore collaboration, the method comprising the following steps:

[0021] The data processing module removes irrelevant data, duplicate data, and smoothes noise data from the original data set, filters out data that is irrelevant to the mining topic, processes missing values, outliers, and other filtering and smoothing data cleaning processes to improve data quality;

[0022] The intelligent analysis module realizes adaptive extraction of equipment operation characteristic values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks, performs intelligent analysis on the processed data, calculates the equipment health, predicts the equipment's failure trend and remaining life, and evaluates the equipment's health status through remaining life prediction to determine whether maintenance is needed.

[0023] Preferably, the operation data of a device received by the collection module is divided into a group of data with a length of n, the length of the sliding window is set to k, and the data to be identified x i ;

[0024] Calculate the median m of the data to be identified i , the calculation range is x i-k ,x i-k+1 ,x i-k+2 ,L,x i ,L,x i+k-2 ,x i+k-1 ,x i+k ;

[0025] Calculate the median absolute value of the deviation mad i , the calculation range is |x i-k -m i |,L,|x i+k -m i |;

[0026] Calculate the standard deviation σ i , σ i =κ×mad i ,in

[0027] Identify data x i , if |x i -m i |>n σ σ i , then use m i Replace x i Output, n σ Set the threshold for Hampel.

[0028] Preferably, the data is input into the trained two-dimensional convolution model through forward propagation, and the model will automatically learn and extract the features of the input data; in the convolution layer, the convolution kernel is convolved with the local area of ​​the input data to obtain the feature representation of the area; according to the obtained equipment operation characteristics, the Winner degradation process is used to obtain the performance degradation model of the equipment, and the health of the monitoring equipment is calculated to predict the failure trend and remaining life of the ship equipment:

[0029] The health calculation formula is expressed as follows:

[0030]

[0031] in, is the weighted distance between the monitoring data and the optimal solution, is the weighted distance between the monitoring data and the worst solution;

[0032] The health degree is displayed in percentage form. The further away from 100%, the unhealthier it is. The closer to 100%, the closer the monitoring data is to the optimal solution, and the healthier it is.

[0033] A computer-readable storage medium stores a computer program, which is executed by a processor to implement a condition-based maintenance method for coastal and inland vessels based on ship-shore collaboration.

[0034] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a condition-based maintenance method for coastal and inland river vessels based on ship-shore collaboration is implemented.

[0035] The present invention has the following beneficial effects:

[0036] Compared with the prior art, the present invention has the following advantages:

[0037] The present invention is composed of a ship-side situation-based maintenance system, a shore-side decision-making support system, and a ship-shore communication system. The ship-side situation-based maintenance system achieves accurate maintenance of equipment through real-time data collection, intelligent analysis and prediction, reduces maintenance costs, and improves equipment utilization. The shore-side decision-making support system improves the reliability of situation-based operation and maintenance decisions through real-time monitoring and expert support. The ship-shore communication system ensures coordinated maintenance between the ship and the shore, and improves the efficiency of situation-based maintenance.

[0038] The present invention digitizes and intelligentizes the ship's condition-based maintenance process, making the condition-based maintenance process more intuitive and efficient, and the method of use is simpler and easier to learn. Through real-time data collection and intelligent analysis, accurate maintenance of equipment is achieved, maintenance costs are reduced, equipment utilization is improved, potential equipment failure hazards are discovered in advance, and major accidents are avoided. The condition-based maintenance system makes full use of modern information processing technology to analyze ship data and mine its characteristic information, thereby depicting the operating characteristics and laws of the operation and maintenance subject, building an information knowledge base, and making intelligent decisions based on the monitoring data obtained through real-time transmission, thereby reducing the workload of maintenance staff. The present invention realizes the "ship-shore-cloud" human-machine co-driving system in the inland shipping environment through the ship-shore communication system, thereby improving the reliability of condition-based operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 Schematic diagram of the system framework of the present invention. DETAILED DESCRIPTION

[0041] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0043] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0045] The present invention is described in detail below in conjunction with specific embodiments. Specific embodiment one:

[0047] according to Figure 1 As shown, the specific optimization technical solution adopted by the present invention to solve the above technical problems is: the present invention relates to a situation-based maintenance system and method for coastal inland ships based on ship-shore collaboration.

[0048] The present invention provides a situation-based maintenance system for coastal inland waterways vessels based on ship-shore collaboration, the system comprising: a ship-side situation-based maintenance system, a shore-side auxiliary decision-making system and a ship-shore communication system;

[0049] The ship-side condition-based maintenance system performs data collection, data storage and management, data processing, intelligent analysis, fault trend prediction, remaining life prediction, and maintenance plan formulation;

[0050] The shore-side decision-making support system includes the shore-side remote support system and handheld wireless terminals for expert-assisted decision-making; the ship-shore communication system includes ship-side communication equipment and shore-side communication equipment for data communication. Specific embodiment 2:

[0052] The difference between the second embodiment of the present invention and the first embodiment is that:

[0053] The ship-side situation-based maintenance system includes data acquisition module, data processing module, intelligent analysis module, prediction and decision-making module, and maintenance execution module;

[0054] The data acquisition module collects the operating data of the ship equipment in real time, including temperature, pressure, and vibration parameters, through sensors installed on the ship equipment, and transmits these data to the data processing module;

[0055] The data processing module processes missing values, outlier filtering, smoothing and other data cleaning processes to improve data quality so that the processed data can better reflect the performance status of the equipment. At the same time, the processed data is sent to the server and the intelligent analysis module respectively;

[0056] The intelligent analysis module uses deep learning algorithms such as two-dimensional convolutional neural networks to intelligently analyze the processed data and predict the failure trend and remaining life of the equipment;

[0057] The predictive decision module combines the results of the intelligent analysis module with the maintenance decision library to develop an optimal maintenance plan, including maintenance time, maintenance location, and maintenance content; the maintenance execution module automatically or manually adjusts the ship's operating status and performs maintenance operations according to the plan of the predictive decision module to ensure that the equipment is in the best operating state. Specific embodiment three:

[0059] The difference between the third embodiment of the present invention and the second embodiment is that:

[0060] The data processing method is based on the Hampel filtering principle and performs time series anomaly processing according to the characteristics of ship navigation data, thereby eliminating invalid parameters and improving data quality. Specific embodiment four:

[0062] The difference between the fourth embodiment of the present invention and the third embodiment is that:

[0063] The shore-side remote support system obtains the ship's operating information in real time. When the ship generates a situation-based maintenance plan, the expert-assisted decision-making function is realized through real-time remote connection dialogue. Specific embodiment five:

[0065] The difference between the fifth embodiment of the present invention and the fourth embodiment is that:

[0066] The ship-shore communication system includes a ship-side communication module and a shore-side communication module; the ship-side communication module uses multi-band communication and supports multiple communication bands to ensure the stability and reliability of communication and realize remote data transmission;

[0067] The shore communication module receives the data sent by the ship, restores it to the original data through decoding, and sends it to the shore auxiliary decision-making system. Specific embodiment six:

[0069] The difference between the sixth embodiment of the present invention and the fifth embodiment is that:

[0070] The present invention provides a condition-based maintenance method for coastal inland river vessels based on ship-shore collaboration, the method comprising the following steps:

[0071] The data processing module removes irrelevant data, duplicate data, and smoothes noise data from the original data set, filters out data that is irrelevant to the mining topic, processes missing values, outliers, and other filtering and smoothing data cleaning processes to improve data quality;

[0072] The intelligent analysis module realizes adaptive extraction of equipment operation characteristic values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks, performs intelligent analysis on the processed data, calculates the equipment health, predicts the equipment's failure trend and remaining life, and evaluates the equipment's health status through remaining life prediction to determine whether maintenance is needed. Specific embodiment seven:

[0074] The difference between the seventh embodiment of the present invention and the sixth embodiment is that:

[0075] The data of a device running in the receiving acquisition module is divided into a group of data with a length of n. The length of the sliding window is set to k. The data to be identified x i ;

[0076] Calculate the median m of the data to be identified i , the calculation range is x i-k ,x i-k+1 ,x i-k+2 ,L,x i ,L,x i+k-2 ,x i+k-1 ,x i+k ;

[0077] Calculate the median absolute value of the deviation mad i , the calculation range is |x i-k -m i |,L,|x i+k -m i |;

[0078] Calculate the standard deviation σ i , σ i =κ×mad i ,in

[0079] Identify data x i , if |x i -m i |>n σ σ i , then use mi Replace x i Output, n σ Set the threshold for Hampel. Specific embodiment eight:

[0081] The difference between the eighth embodiment of the present invention and the seventh embodiment is that:

[0082] The data is input into the trained two-dimensional convolution model through forward propagation, and the model will automatically learn and extract the features of the input data; in the convolution layer, the convolution kernel performs convolution operation with the local area of ​​the input data to obtain the feature representation of the area; based on the obtained equipment operation characteristics, the Winner degradation process is used to obtain the performance degradation model of the equipment, and the health of the monitoring equipment is calculated to predict the failure trend and remaining life of the ship equipment:

[0083] The health calculation formula is expressed as follows:

[0084]

[0085] in, is the weighted distance between the monitoring data and the optimal solution, is the weighted distance between the monitoring data and the worst solution.

[0086] The health degree is displayed in percentage form. The further away from 100%, the unhealthier it is. The closer to 100%, the closer the monitoring data is to the optimal solution, and the healthier it is. Specific embodiment nine:

[0088] The difference between the ninth embodiment of the present invention and the eighth embodiment is that:

[0089] The present invention provides a computer-readable storage medium on which a computer program is stored. The program is executed by a processor to implement a method for condition-based maintenance of coastal and inland vessels based on ship-shore collaboration.

[0090] The method comprises the following steps:

[0091] The data processing module removes irrelevant data, duplicate data, and smoothes noise data from the original data set, filters out data that is irrelevant to the mining topic, processes missing values, outliers, and other filtering and smoothing data cleaning processes to improve data quality;

[0092] The intelligent analysis module realizes adaptive extraction of equipment operation characteristic values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks, performs intelligent analysis on the processed data, calculates the equipment health, predicts the equipment's failure trend and remaining life, and evaluates the equipment's health status through remaining life prediction to determine whether maintenance is needed. Specific embodiment ten:

[0094] The difference between the tenth embodiment of the present invention and the ninth embodiment is that:

[0095] The present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a condition-based maintenance method for coastal and inland vessels based on ship-shore collaboration is implemented.

[0096] The method comprises the following steps:

[0097] The data processing module removes irrelevant data, duplicate data, and smoothes noise data from the original data set, filters out data that is irrelevant to the mining topic, processes missing values, outliers, and other filtering and smoothing data cleaning processes to improve data quality;

[0098] The intelligent analysis module realizes adaptive extraction of equipment operation characteristic values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks, performs intelligent analysis on the processed data, calculates the equipment health, predicts the equipment's failure trend and remaining life, and evaluates the equipment's health status through remaining life prediction to determine whether maintenance is needed. Specific embodiment eleven:

[0100] The difference between the eleventh embodiment of the present invention and the tenth embodiment is that:

[0101] like Figure 1 As shown, the present invention provides a situation-based maintenance system for coastal and inland vessels based on ship-shore collaboration, including a ship-side situation-based maintenance system, a shore-side auxiliary decision-making system, and a ship-shore communication system.

[0102] The ship-side condition-based maintenance system consists of a data acquisition module, a data processing module, an intelligent analysis module, a prediction and decision module, and a maintenance execution module. It has the functions of data acquisition, data storage and management, data processing, intelligent analysis, fault trend prediction, remaining life prediction, and maintenance plan formulation.

[0103] The data acquisition module monitors the parameters of the operating ship equipment in real time through sensors installed on the ship equipment. At the same time, it collects the operating data of the ship equipment in real time, including temperature, pressure, vibration and other parameters, and transmits these data to the data processing module.

[0104] The data processing module improves data quality by deleting irrelevant data, duplicate data, and smoothing noise data in the original data set, filtering out data that is not related to the mining topic, and processing missing values, outliers, and other data cleaning processes such as filtering and smoothing. This allows the processed data to better reflect the performance status of the equipment, and at the same time sends the processed data to the server and intelligent analysis module respectively.

[0105] Specifically: in the process of building the data collection and data processing module, it has five different types of data storage types, namely: automatic storage of real-time data, storage of external input data, storage of system operation data, storage of model library parameters and storage of knowledge base.

[0106] The steps of data processing are:

[0107] The data of a device running in the receiving acquisition module is divided into a group of data with a length of n. The length of the sliding window is set to k. The data to be identified x i ;

[0108] Calculate the median m of the data to be identified i , the calculation range is x i-k ,x i-k+1 ,x i-k+2 ,L,x i ,L,x i+k-2 ,x i+k-1 ,x i+k ;

[0109] Calculate the median absolute value of the deviation mad i , the calculation range is |x i-k -m i |,L,|x i+k -m i |;

[0110] Calculate the standard deviation σ i , σ i =κ×mad i ,in

[0111] Identify data x i , if |x i -m i |>n σ σ i , then use m i Replace x i Output, n σ Set the threshold for Hampel.

[0112] The intelligent analysis module realizes adaptive extraction of equipment operation feature values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks. It no longer relies on manual selection and is easier for operators to use. The module performs intelligent analysis on the processed data, calculates the health of the equipment, predicts the failure trend and remaining life of the equipment, and evaluates the health of the equipment through remaining life prediction to determine whether maintenance is needed.

[0113] Specifically: input the data into the trained two-dimensional convolution model through forward propagation, and the model will automatically learn and extract the features of the input data. In the convolution layer, the convolution kernel performs convolution operation with the local area of ​​the input data to obtain the feature representation of the area. As the number of network layers increases, the model can learn higher-level feature representations. According to the obtained equipment operation characteristics, the winner degradation process can be used to obtain the performance degradation model of the equipment, and the health of the monitoring equipment can be calculated to predict the failure trend and remaining life of the ship equipment. The health calculation formula is: in is the weighted distance between the monitoring data and the optimal solution, is the weighted distance between the monitoring data and the worst solution.

[0114] The prediction and decision module will judge the results of the intelligent analysis module. When the results show that maintenance is needed, the decision module will evaluate the results. When the equipment only needs routine maintenance, the prediction and decision module will formulate the optimal maintenance plan based on the maintenance decision library to facilitate maintenance personnel to perform maintenance operations. When it is impossible to make a maintenance plan based on the existing decision maintenance database, the module will automatically send a request for auxiliary decision signal to the shore-side auxiliary decision system to obtain technical support from shore-side experts, and add the maintenance plan to the maintenance decision library.

[0115] The maintenance decision module automatically or manually performs maintenance operations according to the plan of the prediction decision module to ensure that the equipment is in the best operating condition.

[0116] It is worth noting that when the performance of ship equipment drops sharply due to an unexpected situation during the operation of the ship and maintenance is not enough to solve the problem, the operation and maintenance decision module will directly determine that the ship equipment has failed and skip the maintenance plan stage and enter the emergency processing mode. At this time, the operation and maintenance decision module will give priority to the automatic repair mode and send out a warning signal, indicating that the ship maintenance personnel will arrive at the scene as soon as possible.

[0117] The shore-side decision-making assistance system includes a shore-side remote support system and a handheld wireless terminal. The shore-side remote support system monitors the operating status of ship equipment in real time by receiving signals from the ship side, and realizes data visualization of ship operation. At the same time, it periodically stores received data, which is convenient for calling historical ship operation data for analysis.

[0118] The handheld wireless terminal can be a mobile phone, tablet computer or other device. The handheld wireless terminal can access the shore remote support system through a specific IP address to obtain real-time operation data and warning information of the ship, so that experts can provide technical support anytime and anywhere.

[0119] Specifically: the shore-side decision-making support system will have one or more administrators, who will assign corresponding permissions to wireless terminal operators, and the wireless terminal system will be automatically updated regularly. When accessing the shore-side decision-making support system with a wireless terminal, you need to log in with your personal registered account.

[0120] The ship-to-shore communication system includes a ship-side communication module and a shore-side communication module. The ship-borne communication module adopts multi-band communication technology, can support multiple communication bands at the same time, and sends the processing results to the shore-side communication module to achieve efficient and stable communication. The shore-side communication module receives the data sent by the ship-side communication module and forwards it to the shore-side auxiliary decision-making system, so that it analyzes the received data and generates a ship navigation status report and maintenance information. Specific embodiment twelve:

[0122] The coastal and inland river vessel situation-based maintenance system based on ship-shore collaboration includes a ship-side situation-based maintenance system, a shore-side decision support system, and a ship-shore communication system; the ship-side situation-based maintenance system has the following functions including data collection, data storage and management, data processing, intelligent analysis, fault trend prediction, remaining life prediction, and maintenance plan formulation; the shore-side decision support system includes a shore-side remote support system and a handheld wireless terminal, and has the function of expert decision support; the ship-shore communication system includes ship-side communication equipment and shore-side communication equipment.

[0123] The ship-side situation-based maintenance system includes a data acquisition module, a data processing module, an intelligent analysis module, a prediction and decision module, and a maintenance execution module; the data acquisition module collects the operating data of the ship equipment in real time, including parameters such as temperature, pressure, and vibration, through sensors installed on the ship equipment, and transmits these data to the data processing module; the data processing module processes missing values, outliers, and other data cleaning processes such as filtering and smoothing to improve data quality, so that the processed data can better reflect the performance status of the equipment, and at the same time sends the processed data to the server and the intelligent analysis module respectively; the intelligent analysis module performs intelligent analysis on the processed data based on deep learning algorithms such as two-dimensional convolutional neural networks to predict the failure trend and remaining life of the equipment; the prediction and decision module combines the results of the intelligent analysis module with the maintenance decision library to formulate the optimal maintenance plan, including maintenance time, maintenance location, maintenance content, etc.; the maintenance execution module automatically or manually adjusts the operating status of the ship and performs maintenance operations according to the plan of the prediction and decision module to ensure that the equipment is in the best operating state.

[0124] The data processing method is based on the Hampel filtering principle and performs time series anomaly processing according to the characteristics of ship navigation data, thereby eliminating invalid parameters and improving data quality.

[0125] The shore-side remote support system can obtain ship operation information in real time. When the ship generates a situation-based maintenance plan, the expert assistance decision-making function is realized through real-time remote connection dialogue.

[0126] The handheld wireless terminal can remotely access the shore remote support system to obtain ship operation data.

[0127] The ship-shore communication system includes a ship-side communication module and a shore-side communication module; the ship-side communication module uses multi-band communication technology to simultaneously support multiple communication bands to ensure the stability and reliability of communication and realize remote transmission of data; the shore-side communication module receives the data sent by the ship, restores it to the original data through decoding, and sends it to the shore-side auxiliary decision-making system.

[0128] In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction. In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. Any process or method description in the flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code including one or more executable instructions for implementing the steps of a custom logic function or process, and the scope of the preferred embodiment of the present invention includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the art to which the embodiments of the present invention belong. The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as a sequenced list of executable instructions for implementing the logic function, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection having one or N wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM).In addition, the computer readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, then editing, interpreting or processing in other suitable ways as necessary, and then storing it in a computer memory. It should be understood that the various parts of the present invention can be implemented with hardware, software, firmware, or a combination thereof. In the above-mentioned embodiment, N steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented with hardware, as in another embodiment, any one of the following technologies known in the art or their combination can be used to implement: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0129] The above is only a preferred implementation of a coastal inland river vessel condition-based maintenance system and method based on ship-shore collaboration. The protection scope of a coastal inland river vessel condition-based maintenance system and method based on ship-shore collaboration is not limited to the above embodiments. All technical solutions under this idea belong to the protection scope of the present invention. It should be pointed out that for those skilled in the art, several improvements and changes without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A coastal and inland river vessel situation-based maintenance system based on ship-shore collaboration, characterized by: The system includes: a ship-side situation maintenance system, a shore-side auxiliary decision-making system and a ship-shore communication system; The ship-side condition-based maintenance system performs data collection, data storage and management, data processing, intelligent analysis, fault trend prediction, remaining life prediction, and maintenance plan formulation; The shore-side decision-making support system includes the shore-side remote support system and handheld wireless terminals for expert-assisted decision-making; the ship-shore communication system includes ship-side communication equipment and shore-side communication equipment for data communication.

2. The system according to claim 1, characterized in that: The ship-side situation-based maintenance system includes data acquisition module, data processing module, intelligent analysis module, prediction and decision-making module, and maintenance execution module; The data acquisition module collects the operating data of the ship equipment in real time, including temperature, pressure, and vibration parameters, through sensors installed on the ship equipment, and transmits these data to the data processing module; The data processing module processes missing values, outlier filtering, smoothing and other data cleaning processes to improve data quality so that the processed data can better reflect the performance status of the equipment. At the same time, the processed data is sent to the server and the intelligent analysis module respectively; The intelligent analysis module uses deep learning algorithms such as two-dimensional convolutional neural networks to intelligently analyze the processed data and predict the failure trend and remaining life of the equipment; The prediction decision module combines the results of the intelligent analysis module with the maintenance decision library to develop the optimal maintenance plan, including maintenance time, maintenance location, and maintenance content; The maintenance execution module automatically or manually adjusts the ship's operating status and performs maintenance operations according to the plan of the prediction decision module to ensure that the equipment is in the best operating condition.

3. The system according to claim 2, characterized in that: The data processing method is based on the Hampel filtering principle and performs time series anomaly processing according to the characteristics of ship navigation data, thereby eliminating invalid parameters and improving data quality.

4. The system according to claim 3, characterized in that: The shore-side remote support system obtains the ship's operating information in real time. When the ship generates a situation-based maintenance plan, the expert-assisted decision-making function is realized through real-time remote connection dialogue.

5. The system according to claim 4, characterized in that: The ship-shore communication system includes a ship-side communication module and a shore-side communication module; the ship-side communication module uses multi-band communication and supports multiple communication bands to ensure the stability and reliability of communication and realize remote data transmission; The shore communication module receives the data sent by the ship, restores it to the original data through decoding, and sends it to the shore auxiliary decision-making system.

6. A situation-based maintenance method for coastal and inland river vessels based on ship-shore collaboration, characterized by: The method comprises the following steps: The data processing module removes irrelevant data, duplicate data, and smoothes noise data from the original data set, filters out data that is irrelevant to the mining topic, processes missing values, outliers, and other filtering and smoothing data cleaning processes to improve data quality; The intelligent analysis module realizes adaptive extraction of equipment operation characteristic values ​​based on deep learning algorithms such as two-dimensional convolutional neural networks, performs intelligent analysis on the processed data, calculates the equipment health, predicts the equipment's failure trend and remaining life, and evaluates the equipment's health status through remaining life prediction to determine whether maintenance is needed.

7. The method according to claim 6, characterized in that: The data of a device running in the receiving acquisition module is divided into a group of data with a length of n. The length of the sliding window is set to k. The data to be identified x i ; Calculate the median m of the data to be identified i , the calculation range is x i-k ,x i-k+1 ,x i-k+2 ,…,x i ,…,x i+k-2 ,x i+k-1 ,x i+k ; Calculate the median absolute value of the deviation mad i , the calculation range is |x i-k -m i |,…,|x i+k -m i |; Calculate the standard deviation σ i , σ i =κ×mad i ,in Identify data x i , if |x i -m i |>n σ σ i , then use m i Replace x i Output, n σ Set a threshold for Hampel.

8. The method according to claim 7, characterized in that: The data is input into the trained two-dimensional convolution model through forward propagation, and the model will automatically learn and extract the features of the input data; in the convolution layer, the convolution kernel performs convolution operation with the local area of ​​the input data to obtain the feature representation of the area; based on the obtained equipment operation characteristics, the Winner degradation process is used to obtain the performance degradation model of the equipment, and the health of the monitoring equipment is calculated to predict the failure trend and remaining life of the ship equipment: The health calculation formula is expressed as follows: in, is the weighted distance between the monitoring data and the optimal solution, is the weighted distance between the monitoring data and the worst solution.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to claims 6 to 8.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method of claims 6-8 is implemented.

Images