CN116957366A - Port data acquisition and evaluation method and system based on Internet of things - Google Patents
Port data acquisition and evaluation method and system based on Internet of things Download PDFInfo
- Publication number
- CN116957366A CN116957366A CN202311217065.7A CN202311217065A CN116957366A CN 116957366 A CN116957366 A CN 116957366A CN 202311217065 A CN202311217065 A CN 202311217065A CN 116957366 A CN116957366 A CN 116957366A
- Authority
- CN
- China
- Prior art keywords
- data
- remote control
- shore bridge
- bridge equipment
- control shore
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 45
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 83
- 238000012549 training Methods 0.000 claims description 45
- 238000012545 processing Methods 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 30
- 238000012360 testing method Methods 0.000 claims description 22
- 238000011176 pooling Methods 0.000 claims description 19
- 239000000779 smoke Substances 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 14
- 238000001816 cooling Methods 0.000 claims description 10
- 238000013480 data collection Methods 0.000 claims description 10
- 238000002620 method output Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 3
- 239000003595 mist Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000007921 spray Substances 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 description 53
- 238000012544 monitoring process Methods 0.000 description 17
- 239000013535 sea water Substances 0.000 description 11
- 238000005461 lubrication Methods 0.000 description 6
- 230000009467 reduction Effects 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000011157 data evaluation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000003381 stabilizer Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/40—Transportation
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Accounting & Taxation (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a port data acquisition and evaluation method and system based on the Internet of things, comprising the following steps: real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the real-time data to obtain a preprocessed real-time acquisition data set; and carrying out data classification by a K nearest neighbor algorithm and an isolated forest algorithm to obtain automatic subsystem data, constructing a remote control shore bridge equipment work prediction model, obtaining abnormal working parameters based on the automatic subsystem, obtaining a debugging method with highest debugging efficiency based on the abnormal working parameters, and finally carrying out vibration debugging, temperature adjustment and intelligent security treatment on the debugged remote control shore bridge equipment.
Description
Technical Field
The invention relates to the field of data processing, in particular to a port data acquisition and evaluation method and system based on the Internet of things.
Background
Remote quay bridge equipment is a large mechanical device used in port container terminal loading and unloading operations, and is commonly used for loading and unloading containers on ships, lifting containers from ships to terminals, or lifting containers from terminals to ships. In the working process of the remote control shore bridge equipment, the mechanical connection part is easy to vibrate due to friction, and meanwhile, if the water level is too high on a wharf, the remote control shore bridge is impacted, and the remote control shore bridge is easy to vibrate, so that various working parameters of the remote control shore bridge equipment are required to be collected to judge whether the remote control shore bridge equipment has abnormal conditions or not, and intelligent regulation and control processing are carried out on the remote control shore bridge equipment.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a port data acquisition and evaluation method and system based on the Internet of things.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides a port data acquisition and evaluation method based on the Internet of things, which comprises the following steps:
real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
The debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
Further, in a preferred embodiment of the present invention, the real-time data acquisition is performed on the remote control shore bridge equipment of the port, and the data preprocessing is performed on the data acquired in real time, which specifically includes:
installing a sensor in an automation subsystem of the remote control shore bridge equipment of the port, and acquiring data in the sensor in real time to obtain real-time acquisition data of the automation subsystem of the remote control shore bridge equipment;
acquiring the data point density of real-time acquisition data, setting a sliding window based on the data point density, and fitting a polynomial in the sliding window by using a least square method to obtain a fitting polynomial and a polynomial coefficient;
calculating a smooth value of a central data point of the sliding window based on the fitting polynomial and the polynomial coefficient to obtain a smooth value, sliding the sliding window on the real-time acquired data, and performing polynomial fitting and smooth value calculation on the sliding window when the sliding window slides to a new data point until the sliding window slides to all the data points of the real-time acquired data to obtain filtered real-time acquired data;
And detecting abnormal values of the data by using a statistical method, removing the abnormal values, carrying out interpolation compensation processing on the missing values of the filtered real-time acquisition data, carrying out filtering processing on the repeated values, and finally carrying out data format standardization processing on the filtered real-time acquisition data to obtain the preprocessed real-time acquisition data.
Further, in a preferred embodiment of the present invention, the classification processing is performed on the preprocessed real-time collected data by using a K-nearest neighbor algorithm, and the outlier processing is performed on the classified preprocessed real-time collected data by using an isolated forest algorithm, so as to obtain automatic subsystem classification data, which specifically includes:
dividing the preprocessing real-time acquisition data into a training set and a testing set, determining the size of a K value, calculating the Euclidean distance between the K value and each data sample in the training set, presetting Euclidean distance intervals, classifying the data samples in the training set according to the difference of the Euclidean distance intervals, testing the accuracy and the precision of the classified training set by using the testing set, and stopping classifying when the accuracy and the precision of the classified training set reach preset values to obtain a preliminary classified data set;
Constructing an isolated forest by using an isolated forest algorithm, determining the maximum depth of binary trees and the number of binary trees in the isolated forest, and dividing the preliminary classification data set into subsets with the same number based on the number of binary trees;
randomly selecting a subset, applying the subset to nodes of a binary tree, acquiring characteristic values of the subset as node characteristic values of the current binary tree, and randomly selecting a node dividing value according to the node characteristic values;
based on the node characteristic values and the node classification values, binary tree construction is carried out on the preliminary classification data set, the preliminary classification data samples with the node characteristic values smaller than the node classification values are classified as a class of samples, and the preliminary classification data samples with the node characteristic values larger than the node classification values are classified as a class of samples;
if the depth value of the node is smaller than the maximum depth value and the number of the classified data points in the first class sample and the second class sample is not zero, the first class sample and the second class sample are used as new data sets, the steps are repeated, and when the depth value of the node reaches the maximum depth value, the current node is marked as a leaf node;
setting a node at the tree root part of the binary tree as a root node, calculating the distances between leaf nodes and root nodes of all binary trees, marking data samples with the distances between the leaf nodes and the root nodes not within a preset value range as outliers, and removing the outliers to obtain a final classification data set, wherein the final classification data set is automatic subsystem classification data.
Further, in a preferred embodiment of the present invention, a remote control shore bridge equipment operation prediction model is constructed according to historical operation data of the remote control shore bridge equipment, and automatic subsystem classification data is input into the remote control shore bridge equipment operation prediction model to generate abnormal operation parameters of abnormal sub-equipment of the remote control shore bridge equipment, specifically:
carrying out data statistics processing on historical working data of remote control shore bridge equipment to generate normal working parameters of the remote control shore bridge equipment, and dividing the normal working parameters of the remote control shore bridge equipment into a training data set and a testing data set;
based on a convolutional neural network algorithm, the training data set is imported into a convolutional layer in a neural network model in the neural network algorithm, various working parameters of remote control shore bridge equipment are defined by a convolutional kernel in the convolutional layer, and the convolutional kernel carries out convolutional operation on the training set in the data of the training set to obtain a convolutional value;
importing the convolution value into a pooling layer of a neural network model to carry out maximized pooling treatment to obtain a pooling characteristic value, generating a pooling characteristic diagram based on the pooling characteristic value, carrying out reverse training on the pooling characteristic diagram through a cross entropy loss function, stopping reverse training when an error value of the reverse training is converged to a preset value, outputting a reverse training result to the neural network model, carrying out data testing on the neural network model after reverse training through a test data set team, and generating a normal operation prediction model of the remote control shore bridge equipment if the test result meets a preset range;
The automatic subsystem classification data comprise working vibration frequency and vibration amplitude of remote control shore bridge equipment, the automatic subsystem classification data are imported into a normal working prediction model of the remote control shore bridge equipment to generate an abnormal working prediction model of the remote control shore bridge equipment, and prediction parameters are generated by the abnormal working prediction model of the remote control shore bridge equipment;
and carrying out parameter comparison on the predicted parameters and normal working parameters output by a normal working prediction model of the remote control shore bridge equipment to obtain parameter deviation values, carrying out data analysis on the parameter deviation values, importing the parameter deviation values into a Bayesian network, reversely deducing to obtain sub-equipment with abnormal working parameters, defining the sub-equipment as abnormal sub-equipment, acquiring the working parameters of the abnormal sub-equipment, and defining the sub-equipment as abnormal working parameters.
Further, in a preferred embodiment of the present invention, based on the abnormal working parameter, a remote control shore bridge device debugging method is retrieved in a big data network, and a debugging method output with the highest debugging efficiency is screened from the remote control shore bridge device debugging methods, which specifically includes:
importing the abnormal working parameters into a big data network for debugging method matching to obtain all debugging methods of the remote control quay bridge equipment, importing all the remote control quay bridge equipment debugging methods into a remote control quay bridge equipment abnormal working prediction model to obtain a debugging result;
Analyzing the debugging result, if the vibration amplitude and the vibration frequency of the remote control shore bridge in the debugging result are both larger than the preset value, eliminating the corresponding debugging method, and classifying the debugging method of which the vibration amplitude and the vibration frequency of the remote control shore bridge are both smaller than the preset value as a qualified debugging method;
and combining the vibration amplitude and the vibration frequency of the remote control shore bridge to obtain vibration state data of the remote control shore bridge, sequencing the debugging results of the qualified debugging methods based on the vibration state data of the remote control shore bridge to obtain a vibration state sequencing table, and selecting a debugging method with the minimum vibration state based on the vibration state sequencing table to output to remote control shore bridge equipment.
Further, in a preferred embodiment of the present invention, the remote control shore bridge device after debugging is connected to a remote control shore bridge device management system through the internet of things, and the remote control shore bridge device after debugging is intelligently regulated, specifically:
the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, wherein the remote control shore bridge equipment management system comprises a hydrologic detection system, a fire alarm system, a water management system and an intelligent regulation and control system;
If the vibration state data of the remote control shore bridge equipment after debugging is still larger than a preset value, connecting an intelligent regulation and control system with a hydrological detection system, wherein the hydrological detection system generates hydrological detection data, the hydrological detection data comprise water level parameters and flow velocity parameters of a water area where the remote control shore bridge equipment is located, combining the vibration state data and the hydrological detection data into a unified data set, and carrying out normalization processing on the data set to obtain a vibration state data-hydrological detection data comparison table;
setting a first preset value and a second preset value of a water level parameter and a flow rate parameter based on the vibration state data-hydrologic detection data comparison table, and controlling the remote control shore bridge equipment to stop working and sending out an alarm signal by the intelligent regulation and control system if the water level parameter and the flow rate parameter are larger than the first preset value;
if the water level parameter and the flow rate parameter are between the first preset value and the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to stop working, water diversion treatment and water storage treatment are carried out on the water area where the remote control shore bridge equipment is located, and when the water level parameter and the flow rate parameter are smaller than the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to continue working;
The fire alarm system and the water management system of the remote control shore bridge equipment are connected with the intelligent regulation and control system through the Internet of things, a temperature detection device of the fire alarm system automatically detects the working temperature of the remote control shore bridge equipment, a cooling threshold value is preset, if the working temperature of the remote control shore bridge equipment reaches the cooling threshold value, the fire alarm system sends out a fire early warning signal, the intelligent regulation and control system receives the fire early warning signal, and the water storage equipment of the water management system is controlled to spray water mist to cool the remote control shore bridge equipment;
the smoke sensor of the fire alarm system automatically detects the smoke concentration in the remote control shore bridge equipment, if the smoke sensor of the fire alarm system detects smoke, the fire alarm system sends out a fire fighting signal, the intelligent regulation and control system receives the fire fighting signal, controls the water storage equipment in the water management system to perform fire extinguishing treatment on the remote control shore bridge equipment, and adjusts the water pressure of outlet water according to the smoke concentration;
when the water level in the water storage equipment of the water management system is reduced to a preset value, the intelligent regulation and control system controls the water management system to extract water in the water area where the remote control shore bridge equipment is located to conduct fire extinguishing treatment on the remote control shore bridge equipment.
The invention also provides a port data acquisition and evaluation system based on the Internet of things, which comprises a memory and a processor, wherein the memory stores port data acquisition and evaluation programs, and when the port data acquisition and evaluation programs are executed by the processor, the port data acquisition and evaluation system realizes the following steps:
real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
The debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
The invention solves the technical defects in the background technology, and has the following beneficial effects: real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the real-time data to obtain a preprocessed real-time acquisition data set; and carrying out data classification by a K nearest neighbor algorithm and an isolated forest algorithm to obtain automatic subsystem data, constructing a remote control shore bridge equipment work prediction model, obtaining abnormal working parameters based on the automatic subsystem, obtaining a debugging method with highest debugging efficiency based on the abnormal working parameters, and finally carrying out vibration debugging, temperature adjustment and intelligent security treatment on the debugged remote control shore bridge equipment. The method can acquire and analyze data of the remote control shore bridge equipment of the port based on the Internet of things, and then an intelligent regulation and control method is obtained. The remote control shore bridge equipment can be regulated and controlled to maintain the normal operation of the remote control shore bridge equipment, so that the working efficiency is improved, and the economic benefit is met.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of a port data acquisition and evaluation method based on the Internet of things;
FIG. 2 shows a flow chart for acquiring automated subsystem classification data by a K-nearest neighbor algorithm and an orphan forest algorithm;
FIG. 3 shows a flow chart of a method for obtaining abnormal operating parameters and debugging of an abnormal sub-device of a remotely controlled quay bridge device;
fig. 4 shows a program diagram of a port data acquisition and evaluation system based on the internet of things.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a port data acquisition and evaluation method based on the internet of things, comprising the following steps:
S102: real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
s104: classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
s106: according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
s108: searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
s110: the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
Further, in a preferred embodiment of the present invention, the real-time data acquisition is performed on the remote control shore bridge equipment of the port, and the data preprocessing is performed on the data acquired in real time, which specifically includes:
Installing a sensor in an automation subsystem of the remote control shore bridge equipment of the port, and acquiring data in the sensor in real time to obtain real-time acquisition data of the automation subsystem of the remote control shore bridge equipment;
acquiring the data point density of real-time acquisition data, setting a sliding window based on the data point density, and fitting a polynomial in the sliding window by using a least square method to obtain a fitting polynomial and a polynomial coefficient;
calculating a smooth value of a central data point of the sliding window based on the fitting polynomial and the polynomial coefficient to obtain a smooth value, sliding the sliding window on the real-time acquired data, and performing polynomial fitting and smooth value calculation on the sliding window when the sliding window slides to a new data point until the sliding window slides to all the data points of the real-time acquired data to obtain filtered real-time acquired data;
and detecting abnormal values of the data by using a statistical method, removing the abnormal values, carrying out interpolation compensation processing on the missing values of the filtered real-time acquisition data, carrying out filtering processing on the repeated values, and finally carrying out data format standardization processing on the filtered real-time acquisition data to obtain the preprocessed real-time acquisition data.
It should be noted that, the sensor can collect various data in the automation subsystem in real time, and the automation subsystem includes but is not limited to a vibration detection system, and noise reduction and data cleaning are required to be performed on the real-time collected data of the automation subsystem because the collected data may have excessive noise and abnormal or repeated data. And the SG filtering is used for noise reduction, polynomial fitting is carried out in a sliding window, so that the smooth processing of data points can be realized, and high-frequency noise is effectively removed. The data may have abnormal data points and repeated data points, and the data needs to be removed and normalized, so that the data can be stored and processed in the next step. The invention can perform data preprocessing operation on the real-time acquisition data of the automation subsystem by using the SG filtering and data cleaning methods.
Further, in a preferred embodiment of the present invention, the remote control shore bridge device after debugging is connected to a remote control shore bridge device management system through the internet of things, and the remote control shore bridge device after debugging is intelligently regulated, specifically:
the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, wherein the remote control shore bridge equipment management system comprises a hydrologic detection system, a fire alarm system, a water management system and an intelligent regulation and control system;
If the vibration state data of the remote control shore bridge equipment after debugging is still larger than a preset value, connecting an intelligent regulation and control system with a hydrological detection system, wherein the hydrological detection system generates hydrological detection data, the hydrological detection data comprise water level parameters and flow velocity parameters of a water area where the remote control shore bridge equipment is located, combining the vibration state data and the hydrological detection data into a unified data set, and carrying out normalization processing on the data set to obtain a vibration state data-hydrological detection data comparison table;
setting a first preset value and a second preset value of a water level parameter and a flow rate parameter based on the vibration state data-hydrologic detection data comparison table, and controlling the remote control shore bridge equipment to stop working and sending out an alarm signal by the intelligent regulation and control system if the water level parameter and the flow rate parameter are larger than the first preset value;
if the water level parameter and the flow rate parameter are between the first preset value and the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to stop working, water diversion treatment and water storage treatment are carried out on the water area where the remote control shore bridge equipment is located, and when the water level parameter and the flow rate parameter are smaller than the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to continue working;
The fire alarm system and the water management system of the remote control shore bridge equipment are connected with the intelligent regulation and control system through the Internet of things, a temperature detection device of the fire alarm system automatically detects the working temperature of the remote control shore bridge equipment, a cooling threshold value is preset, if the working temperature of the remote control shore bridge equipment reaches the cooling threshold value, the fire alarm system sends out a fire early warning signal, the intelligent regulation and control system receives the fire early warning signal, and the water storage equipment of the water management system is controlled to spray water mist to cool the remote control shore bridge equipment;
the smoke sensor of the fire alarm system automatically detects the smoke concentration in the remote control shore bridge equipment, if the smoke sensor of the fire alarm system detects smoke, the fire alarm system sends out a fire fighting signal, the intelligent regulation and control system receives the fire fighting signal, controls the water storage equipment in the water management system to perform fire extinguishing treatment on the remote control shore bridge equipment, and adjusts the water pressure of outlet water according to the smoke concentration;
when the water level in the water storage equipment of the water management system is reduced to a preset value, the intelligent regulation and control system controls the water management system to extract water in the water area where the remote control shore bridge equipment is located to conduct fire extinguishing treatment on the remote control shore bridge equipment.
It should be noted that the remote control shore bridge equipment works at the port, is similar to the sea area, and is easily affected by sea water. When the water level of the seawater is higher and the flow velocity is larger, the seawater impacts the remote control shore bridge equipment, so that the remote control shore bridge equipment is easy to vibrate, and the normal operation of the remote control shore bridge equipment is influenced. The apparatus for detecting the water level and the flow rate of the seawater used in the hydrologic detection system comprises a bubble type water level meter and a flow rate meter. If the water level and the flow rate of the seawater at the detection position are larger than the first preset value, the fact that the water level and the flow rate of the seawater are too large at the moment seriously affects the normal operation of the remote control shore bridge equipment is proved, and the remote control shore bridge equipment is stopped immediately to prevent accidents; if the water level and the flow velocity of the seawater are between the first preset value and the second preset value, the normal operation of the remote control shore bridge equipment can be maintained through regulation and control, the seawater can be split by using objects such as a baffle plate, so that the contact surface and the contact time of the seawater and the remote control shore bridge equipment are reduced, and meanwhile, the split seawater is stored in a storage container of the remote control shore bridge equipment, so that the remote control shore bridge equipment normally operates.
In addition, during the working period of the remote control shore bridge equipment, friction is easily generated at the equipment connection part due to the fact that heavy objects are lifted, spontaneous combustion is easily caused by temperature rise in high-temperature weather, and cooling and even fire extinguishing treatment is needed to be carried out on the remote control shore bridge equipment for ensuring safety. The fire alarm system can detect the temperature and smoke concentration of the remote control shore bridge equipment, carries out corresponding cooling and fire extinguishing treatment on the remote control shore bridge equipment, extracts water for cooling and fire extinguishing from the storage container, realizes the maximum utilization of water resources, accords with economic benefit, and directly extracts seawater for cooling and fire extinguishing treatment after the water in the storage container is completely extracted. The invention can connect the debugged remote control shore bridge equipment with the remote control shore bridge equipment management system through the Internet of things, properly regulate and control the remote control shore bridge equipment and maintain the normal operation of the remote control shore bridge equipment.
Fig. 2 shows a flowchart for acquiring automation subsystem classification data by K-nearest neighbor algorithm and isolated forest algorithm, comprising the steps of:
s202: classifying the preprocessed real-time acquired data by using a K nearest neighbor algorithm to obtain a preliminary classified data set;
s204: dividing the preliminary classification data set into a class-one sample and a class-two sample by using an isolated forest algorithm;
s206: and calculating the distances between the leaf nodes and the root nodes of all binary trees to obtain the automatic subsystem classification data.
Further, in a preferred embodiment of the present invention, the classification processing is performed on the preprocessed real-time collected data by using a K-nearest neighbor algorithm to obtain a preliminary classification data set, which specifically includes:
dividing the preprocessing real-time acquisition data into a training set and a testing set, determining the size of a K value, calculating the Euclidean distance between the K value and each data sample in the training set, presetting Euclidean distance intervals, classifying the data samples in the training set according to the difference of the Euclidean distance intervals, testing the accuracy and the precision of the classified training set by using the testing set, and stopping classifying when the accuracy and the precision of the classified training set reach preset values, so as to obtain a preliminary classified data set.
It should be noted that, preprocessing real-time collected data is all data of the remote control shore bridge equipment, and data analysis is performed on the remote control shore bridge equipment, so that the preprocessed collected data needs to be subjected to data classification, and the analysis result is more accurate. The K nearest neighbor algorithm is an algorithm for classifying data based on the distance between the data. The Euclidean distance is the distance between the data, reflects the similarity between the data, and proves that the similarity between the data is higher when the Euclidean distance is smaller. And (3) performing Euclidean distance calculation on each data and each data sample in the training set, so that preliminary classification of the data can be realized. The invention can carry out preliminary classification on the data of the preprocessing real-time acquisition data through the K nearest neighbor algorithm, and provides preconditions for analyzing the working efficiency of the remote control shore bridge equipment.
Further, in a preferred embodiment of the present invention, the preliminary classification data set is divided into a first class of samples and a second class of samples by using an isolated forest algorithm, specifically:
constructing an isolated forest by using an isolated forest algorithm, determining the maximum depth of binary trees and the number of binary trees in the isolated forest, and dividing the preliminary classification data set into subsets with the same number based on the number of binary trees;
Randomly selecting a subset, applying the subset to nodes of a binary tree, acquiring characteristic values of the subset as node characteristic values of the current binary tree, and randomly selecting a node dividing value according to the node characteristic values;
and based on the node characteristic values and the node segmentation values, constructing a binary tree for the preliminary classification data set, classifying the preliminary classification data samples with the node characteristic values smaller than the node segmentation values as a class of samples, and classifying the preliminary classification data samples with the node characteristic values larger than the node segmentation values as a class of samples.
It should be noted that, after the preprocessing real-time collected data is classified into the preliminary classification data set, some data may have incomplete classification or wrong classification, which may cause the data to have an outlier, so that the accuracy of subsequent analysis of the remote control shore bridge equipment is reduced, and therefore, the outlier in the data needs to be removed. The isolated forest algorithm is an algorithm for detecting outliers of data, and in the preliminary classification dataset, various data may exist in outliers, resulting in incomplete classification of the data. The maximum depth of the binary tree means the number of nodes on the longest path of the root node of the binary tree to the furthest leaf node, and the nodes means the positions of the binary tree dividing the data set. The node characteristic value means a value of a characteristic dividing the preliminary classification data sample, and the node score value means a cut threshold point dividing the preliminary classification data sample. The method and the device can classify the preliminary classification data samples into a class sample and a class sample based on the node characteristic values and the node segmentation values.
Further, in a preferred embodiment of the present invention, the calculating the distances between the leaf nodes and the root nodes of all binary trees obtains the automation subsystem classification data, specifically:
if the depth value of the node is smaller than the maximum depth value and the number of the classified data points in the first class sample and the second class sample is not zero, the first class sample and the second class sample are used as new data sets, the steps are repeated, and when the depth value of the node reaches the maximum depth value, the current node is marked as a leaf node;
setting a node at the tree root part of the binary tree as a root node, calculating the distances between leaf nodes and root nodes of all binary trees, marking data samples with the distances between the leaf nodes and the root nodes not within a preset value range as outliers, and removing the outliers to obtain a final classification data set, wherein the final classification data set is automatic subsystem classification data.
If the depth value of the current node is smaller than the maximum depth value, the number of nodes of the binary tree is insufficient, and the outlier data of the preliminary classification data sample cannot be accurately obtained. Gradually increasing the depth value of the current node until the depth value of the current node is the maximum depth value, and defining the current node as a leaf node if the current node cannot continue dividing the first class and the second class of samples in the binary tree. And obtaining the path length from the leaf node to the root node, marking the preliminary classification data sample with the path length which is not in the preset value range of the preliminary classification data sample as an outlier, and eliminating the outlier to obtain the classification data of the automatic subsystem. The automatic subsystem classification data is accurate classification data, plays an important role in building models and other analysis, and provides a better premise for analysis of remote control shore bridge equipment. The method can obtain the automatic subsystem classification data by judging the path length of the preliminary classification data sample, screening to obtain outliers and removing.
Fig. 3 shows a flowchart of a method for acquiring abnormal operating parameters and debugging abnormal sub-equipment of a remote control quay bridge equipment, comprising the following steps:
s302: based on a convolutional neural network algorithm, constructing a normal working prediction model of the remote control shore bridge equipment;
s304: generating abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment based on the normal working prediction model of the remote control shore bridge equipment;
s306: and acquiring an optimal debugging method of the remote control quay crane equipment based on the abnormal working parameters.
Further, in a preferred embodiment of the present invention, the construction of the normal operation prediction model of the remote control quay bridge device based on the convolutional neural network algorithm specifically comprises:
carrying out data statistics processing on historical working data of remote control shore bridge equipment to generate normal working parameters of the remote control shore bridge equipment, and dividing the normal working parameters of the remote control shore bridge equipment into a training data set and a testing data set;
based on a convolutional neural network algorithm, the training data set is imported into a convolutional layer in a neural network model in the neural network algorithm, various working parameters of remote control shore bridge equipment are defined by a convolutional kernel in the convolutional layer, and the convolutional kernel carries out convolutional operation on the training set in the data of the training set to obtain a convolutional value;
And importing the convolution value into a pooling layer of the neural network model to carry out maximized pooling treatment to obtain a pooling characteristic value, generating a pooling characteristic diagram based on the pooling characteristic value, carrying out reverse training on the pooling characteristic diagram through a cross entropy loss function, stopping reverse training when an error value of the reverse training is converged to a preset value, outputting a reverse training result to the neural network model, carrying out data testing on the neural network model after reverse training through a test data set team, and generating a normal operation prediction model of the remote control shore bridge equipment if the test result meets a preset range.
It should be noted that, the convolution value can extract the multi-level feature of the input historical working data set, and the purpose of pooling the convolution value is to reduce the space dimension of the convolution feature, reduce the dimension and complexity of the data, and improve the performance of the convolution neural network model. The reverse training can enable the error to be converged to a preset value, and the data test is carried out on the neural network model after the reverse training, so that the normal working prediction model of the remote control shore bridge equipment is finally obtained. The remote control shore bridge equipment normal operation prediction model can predict future operating parameters of the remote control shore bridge equipment under normal operation. The invention can construct the normal operation prediction model of the remote control shore bridge equipment through a convolutional neural network algorithm.
Further, in a preferred embodiment of the present invention, the generating, based on the prediction model for normal operation of the remote control quay crane device, an abnormal operation parameter of an abnormal sub-device of the remote control quay crane device specifically includes:
the automatic subsystem classification data comprise working vibration frequency and vibration amplitude of remote control shore bridge equipment, the automatic subsystem classification data are imported into a normal working prediction model of the remote control shore bridge equipment to generate an abnormal working prediction model of the remote control shore bridge equipment, and prediction parameters are generated by the abnormal working prediction model of the remote control shore bridge equipment;
and carrying out parameter comparison on the predicted parameters and normal working parameters output by a normal working prediction model of the remote control shore bridge equipment to obtain parameter deviation values, carrying out data analysis on the parameter deviation values, importing the parameter deviation values into a Bayesian network, reversely deducing to obtain sub-equipment with abnormal working parameters, defining the sub-equipment as abnormal sub-equipment, acquiring the working parameters of the abnormal sub-equipment, and defining the sub-equipment as abnormal working parameters.
It should be noted that, when the equipment connection of the remote control shore bridge equipment is used for lifting heavy objects, vibration is easy to occur, and the vibration comprises vibration amplitude and vibration frequency, and when the vibration amplitude and the vibration frequency are large, the operation of the remote control shore bridge equipment is affected. And introducing the vibration amplitude and the vibration frequency into a normal operation prediction model of the remote control shore bridge equipment, applying a condition to the normal operation prediction model of the remote control shore bridge equipment, obtaining an abnormal operation prediction model of the remote control shore bridge equipment, and obtaining prediction parameters of the abnormal operation prediction model of the remote control shore bridge equipment. Based on the predicted parameters, parameter deviation values are obtained, and the parameter deviation values are analyzed by using a Bayesian network, wherein the Bayesian network is a probability model and can represent the dependency relationship among variables, and the positions causing vibration can be reversely deduced through the Bayesian network and are defined as abnormal sub-equipment, and abnormal working parameters are obtained. According to the method, the abnormal working parameters can be obtained through the reverse thrust of the predicted parameters of the remote control shore bridge equipment abnormal working prediction model.
Further, in a preferred embodiment of the present invention, the method for obtaining the optimal debugging of the remote control quay bridge device based on the abnormal working parameter specifically includes:
importing the abnormal working parameters into a big data network for debugging method matching to obtain all debugging methods of the remote control quay bridge equipment, importing all the remote control quay bridge equipment debugging methods into a remote control quay bridge equipment abnormal working prediction model to obtain a debugging result;
analyzing the debugging result, if the vibration amplitude and the vibration frequency of the remote control shore bridge in the debugging result are both larger than the preset value, eliminating the corresponding debugging method, and classifying the debugging method of which the vibration amplitude and the vibration frequency of the remote control shore bridge are both smaller than the preset value as a qualified debugging method;
and combining the vibration amplitude and the vibration frequency of the remote control shore bridge to obtain vibration state data of the remote control shore bridge, sequencing the debugging results of the qualified debugging methods based on the vibration state data of the remote control shore bridge to obtain a vibration state sequencing table, and selecting a debugging method with the minimum vibration state based on the vibration state sequencing table to output to remote control shore bridge equipment.
When the remote control shore bridge equipment vibrates, the abnormal sub-equipment fails, and equipment debugging is needed to be carried out on the abnormal sub-equipment, so that the problem of vibration is solved. There are various debugging methods, a debugging method with highest debugging efficiency needs to be selected for outputting, the debugging method with the debugging result not meeting the requirement is removed, and the debugging method output for enabling the vibration state of the remote control quay bridge equipment to be minimum is obtained according to the premise that the debugging time is minimum and the debugging result is optimal. The invention can carry out abnormal debugging on the abnormal sub-equipment through a screening debugging method.
In addition, the port data acquisition and evaluation method based on the Internet of things further comprises the following steps:
the method comprises the steps that a safety control system of remote control shore bridge equipment is connected with an intelligent security system through the Internet of things, and the safety control system comprises a video monitoring system, an intelligent access control system and a perimeter alarm system;
based on classified data of a safety control system, intelligent access control data of remote control shore bridge equipment are obtained, personal information of workers allowed to approach the remote control shore bridge equipment is contained in the intelligent access control data, and a video monitoring system monitors the remote control shore bridge equipment and the periphery in real time to obtain a monitoring image;
performing image graying treatment on the monitoring image to obtain a graying monitoring image, selecting a proper wavelet basis function to perform wavelet decomposition on the graying monitoring image to obtain wavelet coefficients with different frequencies, performing threshold segmentation on the wavelet coefficients with different frequencies, setting the wavelet coefficient with the frequency smaller than a preset frequency threshold to be zero, reserving the wavelet coefficient with the frequency larger than the preset frequency threshold, and continuing performing wavelet decomposition on the wavelet coefficient with the frequency larger than the preset frequency threshold until the graying monitoring image reaches the preset wavelet decomposition times, and performing inverse wavelet transformation on the wavelet coefficient subjected to the threshold segmentation treatment to obtain the noise reduction graying monitoring image;
Performing convolution calculation processing on the noise reduction graying monitoring image by using a Sobel operator to obtain a horizontal gradient value and a vertical gradient value of each pixel point in the image, obtaining a gradient image according to the horizontal gradient value and the vertical gradient value of each pixel point in the image, determining an edge pixel point based on the gradient image and the gradient direction, marking the edge pixel point as a figure pixel point, and marking the figure pixel point to obtain a figure feature image;
the intelligent access control system identifies the character feature map, performs data comparison with personal information of staff allowed to be close to the remote control shore bridge equipment in the intelligent access control system, and sends early warning information to the perimeter alarm system if the data comparison is inconsistent;
the perimeter alarm system is connected with the intelligent security system, when the perimeter alarm system receives early warning information and during the fire extinguishing treatment and water diversion treatment of the remote control shore bridge equipment, the perimeter alarm system controls the broadcasting of the remote control shore bridge equipment to carry out warning broadcasting at a port, and stores and processes personal characteristic information records and uploading values of illegally approaching persons in the intelligent security system, and the intelligent security system drives and alarms the illegally approaching persons based on the personal characteristic information of the illegally approaching persons.
It should be noted that, the goods in the harbour are numerous, need to hoist the goods in the long-distance control bank bridge equipment working process, and non-staff is close to and easily causes danger. Personal information of staff is stored in the intelligent access control system, the personal information comprises facial information, iris information and the like, and non-staff can refuse to enter through the intelligent access control system. The video monitoring system is used for monitoring the conditions around the remote control shore bridge equipment in real time, when people are detected in an area which is not accessible by a non-staff, the video monitoring system can send information to the intelligent access control system for information comparison, and if the information comparison results are inconsistent, the video monitoring system can control the perimeter alarm system to carry out port broadcasting and broadcasting, and is connected with the intelligent security system for alarm processing.
In addition, in the video monitoring period, the purpose of carrying out the graying treatment on the image is to make the image occupy less memory and make the image clearer; the purpose of noise reduction processing on the image is that noise exists in the image, the noise reduction processing can improve the definition of the image, and the Sobel operator can acquire the edge of the person according to the change degree of the gradient value, so that the person information is acquired, and the personal information is compared. The security control system and the intelligent security system of the remote control shore bridge equipment can be connected through the Internet of things, and people illegally approaching the remote control shore bridge equipment are driven based on classification data of the security control system.
In addition, the port data acquisition and evaluation method based on the Internet of things further comprises the following steps:
the video monitoring system is made to monitor the remote control shore bridge equipment, the working conditions of a slewing mechanism and a lifting mechanism of the remote control shore bridge equipment are observed, the working efficiencies of the slewing mechanism and the lifting mechanism are monitored and recorded in real time based on the weight and the quantity of cargoes, and a working efficiency table is manufactured;
based on historical data, acquiring standard working efficiency of the slewing mechanism and the lifting mechanism under the condition that the weight and the number of cargoes are the same, comparing the standard working efficiency with a working efficiency table, and presetting a normal working efficiency threshold;
when the working efficiency of the slewing mechanism and the lifting mechanism is lower than the normal working efficiency threshold, connecting an intelligent control system with an automatic lubrication system of the remote shore bridge equipment through the Internet of things, wherein the intelligent control system controls the automatic lubrication system to lubricate the slewing mechanism and the lifting mechanism, and continuously monitoring and recording the working efficiency of the slewing mechanism and the lifting mechanism after the lubrication treatment;
if the working efficiency of the slewing mechanism and the lifting mechanism is still lower than a normal threshold value after lubrication treatment, acquiring the power supply voltage of the slewing mechanism and the lifting mechanism, comparing the power supply voltage of the slewing mechanism and the lifting mechanism with the normal voltage, if the power supply voltage of the slewing mechanism and the lifting mechanism is not in a preset range, carrying out transformation treatment on the power supply voltage of the slewing mechanism and the lifting mechanism through a transformer and a voltage stabilizer, and recording the working efficiency of the slewing mechanism and the lifting mechanism after the power supply voltage is changed;
And if the working efficiency of the slewing mechanism and the lifting mechanism after the power supply voltage is changed is still lower than the normal threshold value, stopping the operation of the slewing mechanism and the lifting mechanism, and overhauling the slewing mechanism and the lifting mechanism.
The crane comprises a crane, a remote control shore bridge device, a crane, a lifting mechanism and a control system, wherein the crane can enable a bridge frame of the remote control shore bridge device to rotate in the horizontal direction, the crane consists of an electric driving device and a rotating shaft, and the crane is used for lifting and lowering a container and consists of components such as the electric driving device and a rolling device. After the slewing mechanism and the lifting mechanism work for many times, the joint of the slewing mechanism and the lifting mechanism can be worn, so that the rotation speed of the bridge frame and the lifting and reducing speed of the container are influenced, the working efficiency is influenced, and even the safety is influenced, so that the working efficiency of the slewing mechanism and the lifting mechanism is required to be obtained through video monitoring to formulate a corresponding solution. The joint of the slewing mechanism and the lifting mechanism is lubricated, so that the rotating effect caused by abrasion can be improved, and the working efficiency is improved. If the working efficiency of the slewing mechanism and the lifting mechanism is still low after the lubrication treatment, whether the electric driving device of the slewing mechanism and the lifting mechanism has a problem needs to be judged, and the working efficiency of the electric driving device is reduced due to insufficient voltage, so that the working efficiency of the slewing mechanism and the lifting mechanism is reduced, and the working voltage is regulated and maintained at the normal working voltage by using a transformer and a voltage stabilizer. If the working efficiency of the slewing mechanism and the lifting mechanism is still not within the normal threshold after the voltage is regulated, judging that the slewing mechanism and the lifting mechanism are likely to be in fault and are in need of maintenance. The invention can carry out lubrication and pressure transformation treatment on the slewing mechanism and the lifting mechanism, and can detect and optimize the working efficiency of the slewing mechanism and the lifting mechanism.
As shown in fig. 4, the second aspect of the present invention further provides a port data collection and evaluation system based on the internet of things, where the port data collection and evaluation system includes a memory 41 and a processor 42, where a port data collection and evaluation program is stored in the memory 41, and when the port data collection and evaluation program is executed by the processor 42, the following steps are implemented:
real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
The debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The port data acquisition and evaluation method based on the Internet of things is characterized by comprising the following steps of:
real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
Searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
2. The port data collection and evaluation method based on the internet of things according to claim 1, wherein the real-time data collection is performed on the remote control shore bridge equipment of the port, and the data preprocessing is performed on the data collected in real time, specifically:
installing a sensor in an automation subsystem of the remote control shore bridge equipment of the port, and acquiring data in the sensor in real time to obtain real-time acquisition data of the automation subsystem of the remote control shore bridge equipment;
acquiring the data point density of real-time acquisition data, setting a sliding window based on the data point density, and fitting a polynomial in the sliding window by using a least square method to obtain a fitting polynomial and a polynomial coefficient;
calculating a smooth value of a central data point of the sliding window based on the fitting polynomial and the polynomial coefficient to obtain a smooth value, sliding the sliding window on the real-time acquired data, and performing polynomial fitting and smooth value calculation on the sliding window when the sliding window slides to a new data point until the sliding window slides to all the data points of the real-time acquired data to obtain filtered real-time acquired data;
And detecting abnormal values of the data by using a statistical method, removing the abnormal values, carrying out interpolation compensation processing on the missing values of the filtered real-time acquisition data, carrying out filtering processing on the repeated values, and finally carrying out data format standardization processing on the filtered real-time acquisition data to obtain the preprocessed real-time acquisition data.
3. The port data collection and evaluation method based on the internet of things according to claim 1, wherein the classifying processing is performed on the preprocessed real-time collection data by using a K-nearest neighbor algorithm, and the outlier processing is performed on the classified preprocessed real-time collection data by using an isolated forest algorithm, so as to obtain automatic subsystem classification data, which specifically comprises:
dividing the preprocessing real-time acquisition data into a training set and a testing set, determining the size of a K value, calculating the Euclidean distance between the K value and each data sample in the training set, presetting Euclidean distance intervals, classifying the data samples in the training set according to the difference of the Euclidean distance intervals, testing the accuracy and the precision of the classified training set by using the testing set, and stopping classifying when the accuracy and the precision of the classified training set reach preset values to obtain a preliminary classified data set;
Constructing an isolated forest by using an isolated forest algorithm, determining the maximum depth of binary trees and the number of binary trees in the isolated forest, and dividing the preliminary classification data set into subsets with the same number based on the number of binary trees;
randomly selecting a subset, applying the subset to nodes of a binary tree, acquiring characteristic values of the subset as node characteristic values of the current binary tree, and randomly selecting a node dividing value according to the node characteristic values;
based on the node characteristic values and the node classification values, binary tree construction is carried out on the preliminary classification data set, the preliminary classification data samples with the node characteristic values smaller than the node classification values are classified as a class of samples, and the preliminary classification data samples with the node characteristic values larger than the node classification values are classified as a class of samples;
if the depth value of the node is smaller than the maximum depth value and the number of the classified data points in the first class sample and the second class sample is not zero, the first class sample and the second class sample are used as new data sets, the steps are repeated, and when the depth value of the node reaches the maximum depth value, the current node is marked as a leaf node;
setting a node at the tree root part of the binary tree as a root node, calculating the distances between leaf nodes and root nodes of all binary trees, marking data samples with the distances between the leaf nodes and the root nodes not within a preset value range as outliers, and removing the outliers to obtain a final classification data set, wherein the final classification data set is automatic subsystem classification data.
4. The port data collection and evaluation method based on the internet of things according to claim 1, wherein the construction of a remote control shore bridge equipment operation prediction model according to the remote control shore bridge equipment historical operation data, and the input of automatic subsystem classification data in the remote control shore bridge equipment operation prediction model, the generation of abnormal operation parameters of the remote control shore bridge equipment abnormal sub-equipment, specifically comprises:
carrying out data statistics processing on historical working data of remote control shore bridge equipment to generate normal working parameters of the remote control shore bridge equipment, and dividing the normal working parameters of the remote control shore bridge equipment into a training data set and a testing data set;
based on a convolutional neural network algorithm, the training data set is imported into a convolutional layer in a neural network model in the neural network algorithm, various working parameters of remote control shore bridge equipment are defined by a convolutional kernel in the convolutional layer, and the convolutional kernel carries out convolutional operation on the training set in the data of the training set to obtain a convolutional value;
importing the convolution value into a pooling layer of a neural network model to carry out maximized pooling treatment to obtain a pooling characteristic value, generating a pooling characteristic diagram based on the pooling characteristic value, carrying out reverse training on the pooling characteristic diagram through a cross entropy loss function, stopping reverse training when an error value of the reverse training is converged to a preset value, outputting a reverse training result to the neural network model, carrying out data testing on the neural network model after reverse training through a test data set team, and generating a normal operation prediction model of the remote control shore bridge equipment if the test result meets a preset range;
The automatic subsystem classification data comprise working vibration frequency and vibration amplitude of remote control shore bridge equipment, the automatic subsystem classification data are imported into a normal working prediction model of the remote control shore bridge equipment to generate an abnormal working prediction model of the remote control shore bridge equipment, and prediction parameters are generated by the abnormal working prediction model of the remote control shore bridge equipment;
and carrying out parameter comparison on the predicted parameters and normal working parameters output by a normal working prediction model of the remote control shore bridge equipment to obtain parameter deviation values, carrying out data analysis on the parameter deviation values, importing the parameter deviation values into a Bayesian network, reversely deducing to obtain sub-equipment with abnormal working parameters, defining the sub-equipment as abnormal sub-equipment, acquiring the working parameters of the abnormal sub-equipment, and defining the sub-equipment as abnormal working parameters.
5. The port data collection and evaluation method based on the internet of things according to claim 1, wherein the searching of the remote control shore bridge equipment debugging method in the big data network based on the abnormal working parameters, and the screening of the debugging method output with the highest debugging efficiency in the remote control shore bridge equipment debugging method are specifically as follows:
importing the abnormal working parameters into a big data network for debugging method matching to obtain all debugging methods of the remote control quay bridge equipment, importing all the remote control quay bridge equipment debugging methods into a remote control quay bridge equipment abnormal working prediction model to obtain a debugging result;
Analyzing the debugging result, if the vibration amplitude and the vibration frequency of the remote control shore bridge in the debugging result are both larger than the preset value, eliminating the corresponding debugging method, and classifying the debugging method of which the vibration amplitude and the vibration frequency of the remote control shore bridge are both smaller than the preset value as a qualified debugging method;
and combining the vibration amplitude and the vibration frequency of the remote control shore bridge to obtain vibration state data of the remote control shore bridge, sequencing the debugging results of the qualified debugging methods based on the vibration state data of the remote control shore bridge to obtain a vibration state sequencing table, and selecting a debugging method with the minimum vibration state based on the vibration state sequencing table to output to remote control shore bridge equipment.
6. The port data collection and evaluation method based on the internet of things according to claim 1, wherein the method is characterized in that the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the internet of things, and the debugged remote control shore bridge equipment is intelligently regulated and controlled, specifically:
the debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, wherein the remote control shore bridge equipment management system comprises a hydrologic detection system, a fire alarm system, a water management system and an intelligent regulation and control system;
If the vibration state data of the remote control shore bridge equipment after debugging is still larger than a preset value, connecting an intelligent regulation and control system with a hydrological detection system, wherein the hydrological detection system generates hydrological detection data, the hydrological detection data comprise water level parameters and flow velocity parameters of a water area where the remote control shore bridge equipment is located, combining the vibration state data and the hydrological detection data into a unified data set, and carrying out normalization processing on the data set to obtain a vibration state data-hydrological detection data comparison table;
setting a first preset value and a second preset value of a water level parameter and a flow rate parameter based on the vibration state data-hydrologic detection data comparison table, and controlling the remote control shore bridge equipment to stop working and sending out an alarm signal by the intelligent regulation and control system if the water level parameter and the flow rate parameter are larger than the first preset value;
if the water level parameter and the flow rate parameter are between the first preset value and the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to stop working, water diversion treatment and water storage treatment are carried out on the water area where the remote control shore bridge equipment is located, and when the water level parameter and the flow rate parameter are smaller than the second preset value, the intelligent regulation system controls the remote control shore bridge equipment to continue working;
The fire alarm system and the water management system of the remote control shore bridge equipment are connected with the intelligent regulation and control system through the Internet of things, a temperature detection device of the fire alarm system automatically detects the working temperature of the remote control shore bridge equipment, a cooling threshold value is preset, if the working temperature of the remote control shore bridge equipment reaches the cooling threshold value, the fire alarm system sends out a fire early warning signal, the intelligent regulation and control system receives the fire early warning signal, and the water storage equipment of the water management system is controlled to spray water mist to cool the remote control shore bridge equipment;
the smoke sensor of the fire alarm system automatically detects the smoke concentration in the remote control shore bridge equipment, if the smoke sensor of the fire alarm system detects smoke, the fire alarm system sends out a fire fighting signal, the intelligent regulation and control system receives the fire fighting signal, controls the water storage equipment in the water management system to perform fire extinguishing treatment on the remote control shore bridge equipment, and adjusts the water pressure of outlet water according to the smoke concentration;
when the water level in the water storage equipment of the water management system is reduced to a preset value, the intelligent regulation and control system controls the water management system to extract water in the water area where the remote control shore bridge equipment is located to conduct fire extinguishing treatment on the remote control shore bridge equipment.
7. The port data acquisition and evaluation system based on the Internet of things is characterized by comprising a memory and a processor, wherein port data acquisition and evaluation programs are stored in the memory, and when the port data acquisition and evaluation programs are executed by the processor, the following steps are realized:
real-time data acquisition is carried out on remote control shore bridge equipment of a port, and data preprocessing is carried out on the data acquired in real time to obtain preprocessed real-time acquisition data;
classifying the preprocessing real-time acquisition data by using a K nearest neighbor algorithm, and performing outlier processing on the classified preprocessing real-time acquisition data by using an isolated forest algorithm to obtain automatic subsystem classification data;
according to historical working data of the remote control shore bridge equipment, a remote control shore bridge equipment working prediction model is constructed, automatic subsystem classification data is input into the remote control shore bridge equipment working prediction model, and abnormal working parameters of abnormal sub-equipment of the remote control shore bridge equipment are generated;
searching a remote control shore bridge equipment debugging method in a big data network based on the abnormal working parameters, and screening a debugging method output with highest debugging efficiency from the remote control shore bridge equipment debugging methods;
The debugged remote control shore bridge equipment is connected with a remote control shore bridge equipment management system through the Internet of things, and intelligent regulation and control are carried out on the debugged remote control shore bridge equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311217065.7A CN116957366B (en) | 2023-09-20 | 2023-09-20 | Port data acquisition and evaluation method and system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311217065.7A CN116957366B (en) | 2023-09-20 | 2023-09-20 | Port data acquisition and evaluation method and system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116957366A true CN116957366A (en) | 2023-10-27 |
| CN116957366B CN116957366B (en) | 2024-01-16 |
Family
ID=88449589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311217065.7A Active CN116957366B (en) | 2023-09-20 | 2023-09-20 | Port data acquisition and evaluation method and system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116957366B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150084613A (en) * | 2014-01-14 | 2015-07-22 | 주식회사 트라콤 | Method For Predicting Disorder Of Tower Crane By Using Data Mining |
| CN108090608A (en) * | 2017-12-13 | 2018-05-29 | 上海海事大学 | A kind of gantry crane trend prediction method based on BP neural network |
| CN109977869A (en) * | 2019-03-27 | 2019-07-05 | 上海海事大学 | A kind of gantry crane operating mechanism state evaluating method based on deep learning |
| CN111242329A (en) * | 2020-03-06 | 2020-06-05 | 广州港集团有限公司 | Port crane transmission part big data monitoring system and monitoring method |
| CN111651530A (en) * | 2020-06-04 | 2020-09-11 | 广州港集团有限公司 | Intelligent port monitoring system |
| CN111860839A (en) * | 2020-07-28 | 2020-10-30 | 上海海事大学 | Shore bridge fault monitoring method based on multi-signal fusion and Adam optimization algorithm |
| KR102206658B1 (en) * | 2020-08-14 | 2021-01-22 | 아이티플래닛 주식회사 | Vision camera system to be communicated with Terminal Operating System through middleware in a port container terminal and method thereof |
| CN113511592A (en) * | 2021-06-30 | 2021-10-19 | 三一海洋重工有限公司 | Shore bridge monitoring method and system and shore bridge |
-
2023
- 2023-09-20 CN CN202311217065.7A patent/CN116957366B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20150084613A (en) * | 2014-01-14 | 2015-07-22 | 주식회사 트라콤 | Method For Predicting Disorder Of Tower Crane By Using Data Mining |
| CN108090608A (en) * | 2017-12-13 | 2018-05-29 | 上海海事大学 | A kind of gantry crane trend prediction method based on BP neural network |
| CN109977869A (en) * | 2019-03-27 | 2019-07-05 | 上海海事大学 | A kind of gantry crane operating mechanism state evaluating method based on deep learning |
| CN111242329A (en) * | 2020-03-06 | 2020-06-05 | 广州港集团有限公司 | Port crane transmission part big data monitoring system and monitoring method |
| CN111651530A (en) * | 2020-06-04 | 2020-09-11 | 广州港集团有限公司 | Intelligent port monitoring system |
| CN111860839A (en) * | 2020-07-28 | 2020-10-30 | 上海海事大学 | Shore bridge fault monitoring method based on multi-signal fusion and Adam optimization algorithm |
| KR102206658B1 (en) * | 2020-08-14 | 2021-01-22 | 아이티플래닛 주식회사 | Vision camera system to be communicated with Terminal Operating System through middleware in a port container terminal and method thereof |
| CN113511592A (en) * | 2021-06-30 | 2021-10-19 | 三一海洋重工有限公司 | Shore bridge monitoring method and system and shore bridge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116957366B (en) | 2024-01-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649755B (en) | Threshold value self-adaptive setting abnormity detection method for multi-dimensional real-time power transformation equipment data | |
| CN111223263A (en) | Full-automatic comprehensive fire early warning response system | |
| CN116224925B (en) | Intelligent processing management system | |
| CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN117235443A (en) | Electric power operation safety monitoring method and system based on edge AI | |
| CN112087604A (en) | Intelligent monitoring video management and control method based on image recognition | |
| CN116976865B (en) | Ship maintenance device allocation management system based on big data analysis | |
| CN103093197A (en) | Monitoring method and system for recognizing hanging behavior | |
| CN116957366B (en) | Port data acquisition and evaluation method and system based on Internet of things | |
| CN112232235B (en) | Intelligent factory remote monitoring method and system based on 5G sum algorithm | |
| CN110543809A (en) | Electric power operation site risk supervision intrusion video identification method | |
| CN114155472A (en) | Method, device and equipment for detecting abnormal state of factory scene empty face protection equipment | |
| CN106022977A (en) | Transformer substation job site safety analysis method | |
| CN117575334A (en) | Highway construction safety monitoring system | |
| CN116168019B (en) | Power grid fault detection method and system based on machine vision technology | |
| CN113095160A (en) | Power system personnel safety behavior identification method and system based on artificial intelligence and 5G | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN115328986A (en) | Power plant safety early warning data analysis processing method and system | |
| CN115629567A (en) | Multi-mode information management system, early warning method and storage medium for livestock and poultry farm | |
| CN113685166A (en) | Drilling accident early warning method and system | |
| CN112862019A (en) | Method for dynamically screening aperiodic anomaly | |
| CN115346140B (en) | Ground disaster early warning method and system based on real-time data monitoring | |
| CN117372723A (en) | Intelligent substation violation operation early warning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |