CN114565162A - Aircraft transportation state monitoring and safety protection method and system - Google Patents
Aircraft transportation state monitoring and safety protection method and system Download PDFInfo
- Publication number
- CN114565162A CN114565162A CN202210194936.7A CN202210194936A CN114565162A CN 114565162 A CN114565162 A CN 114565162A CN 202210194936 A CN202210194936 A CN 202210194936A CN 114565162 A CN114565162 A CN 114565162A
- Authority
- CN
- China
- Prior art keywords
- parameter
- state
- aircraft
- data
- parameters
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 89
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 230000002159 abnormal effect Effects 0.000 claims abstract description 43
- 230000008569 process Effects 0.000 claims abstract description 36
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 9
- 238000010219 correlation analysis Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims description 31
- 238000011156 evaluation Methods 0.000 claims description 30
- 238000007405 data analysis Methods 0.000 claims description 20
- 238000007418 data mining Methods 0.000 claims description 20
- 238000013500 data storage Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000008878 coupling Effects 0.000 claims description 17
- 238000010168 coupling process Methods 0.000 claims description 17
- 238000005859 coupling reaction Methods 0.000 claims description 17
- 238000013210 evaluation model Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000001133 acceleration Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 4
- 230000006353 environmental stress Effects 0.000 abstract description 5
- 239000002360 explosive Substances 0.000 abstract description 4
- 230000000977 initiatory effect Effects 0.000 abstract description 4
- 230000005855 radiation Effects 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 9
- 239000011159 matrix material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for monitoring and protecting the transportation state of an aircraft, which are used for collecting the transportation environment parameters of the aircraft; analyzing the correlation among the parameters based on a correlation analysis theory; subjective combination weight assignment is carried out based on an analytic hierarchy process, objective combination weight assignment is carried out based on an entropy method, a combination weight coefficient is determined based on a level difference maximization combination weight method, and the state of the aircraft is evaluated based on a principal component analysis method; based on LSTM network prediction, comparing residual errors between predicted values and true values, and judging whether parameters are abnormal or not; and based on knowledge reasoning, providing a safety protection decision suggestion for the detected abnormal state. The problem of monitoring the state and protecting the safety of the transportation process is solved, and the transportation safety is greatly improved aiming at the condition that the environment stress such as temperature, humidity, vibration, impact, radiation and the like in the transportation process of the aircraft is variable to accelerate the damage of parts such as precision machinery, electrons, initiating explosive devices and the like in the aircraft.
Description
Technical Field
The invention relates to the technical field of aircraft transportation safety monitoring, in particular to an aircraft transportation state monitoring and safety protection method and system.
Background
At present, in the process of boxing and transporting aircraft weapons, environmental stresses such as temperature, humidity, vibration, impact and radiation are variable, the damage of parts such as precise machinery, electronics and initiating explosive devices in the aircraft is accelerated, and potential safety hazards are increased. Once the fire, explosion and the like occur in the transportation process, the residents, animals, plants and ecological environment around the line can cause great damage, even cause the leakage of technical parameters of weaponry, and cause great loss to countries and armies.
At present, the transportation management of dangerous and equipment products is highly regarded by people. The related scholars use advanced technological means to monitor the transport vehicles in real time, but the monitoring only tracks the vehicles and does not relate to monitoring of the state of the equipment. The position tracking of the equipment is mainly carried out on the equipment transportation, but the safety problem of the weapon transportation process can be solved by collecting and analyzing the state information of the weapon equipment.
However, the current anomaly monitoring technologies mainly include a proximity-based method, a probability-based method, a prediction-based method, and a deep learning-based method. In the proximity-based method, the condition that the data points are sparse is defined as abnormal according to the different positions of the normal data and the abnormal data and the consideration that the abnormal data is sparse. Proximity-based methods include distance-based methods, density-based methods, and cluster-based methods. In a probabilistic model-based approach, a reasonable fluctuation range of current data is determined by the distribution of historical contemporaneous data. In a predictive model-based approach, the deviation of a data point from its predicted value is used to define an anomaly. The abnormal detection algorithm based on the prediction model firstly establishes a prediction model through training data, and then defines abnormal data by using the deviation between a data point and a predicted value. The methods based on deep learning are basically developed from the perspective of reconstruction errors, and in consideration of the characteristic that abnormal data in time series data are rare, a 'normal' model is firstly learned by using a training data set, and then an abnormal score of each sequence relative to the model is calculated.
The current multi-parameter coupled state evaluation technology mainly includes a neural network method, a fuzzy evaluation method, a Bayesian network method and the like. The neural network method utilizes the state information of the equipment to train an evaluation model, and has the defects that input samples are difficult to obtain, and the convergence of the algorithm is influenced; the fuzzy evaluation method is an evaluation method applying fuzzy theory according to fuzzy mathematics, a proper membership function is constructed by distributing corresponding weight, and the membership and the weight are combined to calculate a result; and the Bayesian network method is used for continuously correcting and perfecting sample data and an evaluation system, and the health grade state evaluation of the equipment is obtained through artificial intelligence judgment, needs to be continuously corrected and perfected, and is difficult to apply to a large-scale actual system with large data.
Therefore, how to provide a transportation state monitoring and safety protection method and system based on multi-parameter data coupling driving. The method is based on multi-parameter coupling analysis and signal anomaly detection, and aims to detect the influence of environmental stress on the performance of an aircraft, research the state monitoring and safety protection technology in the transportation process, and form a state evaluation model and a safety protection strategy based on multi-parameter coupling drive.
Disclosure of Invention
In view of the above, the present invention provides a method and system for monitoring and protecting the transportation state of an aircraft; the method and the system for monitoring the transport state and protecting the safety of the aircraft are used for overcoming the difficult problems of monitoring the state and protecting the safety of the transport process, aiming at the condition that the damage of parts such as precision machinery, electrons and initiating explosive devices in the aircraft is accelerated due to variable environmental stresses such as temperature, humidity, vibration, impact and radiation in the transport process of the aircraft, and realizing the great improvement of the transport safety.
In order to achieve the purpose, the invention adopts the following technical scheme:
an aircraft transportation state monitoring and safety protection method comprises the following steps:
s1, collecting aircraft transportation environment parameters;
s2, analyzing the correlation among the parameters based on the correlation analysis theory;
s3, carrying out subjective combination weight assignment based on an analytic hierarchy process, carrying out objective combination weight assignment based on an entropy method, determining a combination weight coefficient based on a level difference maximization combination weight method, and evaluating the state of the aircraft based on a principal component analysis method;
s4, comparing residual errors between the predicted values and the true values based on LSTM network prediction, and judging whether the parameters are abnormal or not;
and S5, based on knowledge reasoning, providing a safety protection decision suggestion for the detected abnormal state.
Preferably, the step S3 specifically includes:
subjective weight assignment is carried out according to expert experience by adopting an analytic hierarchy process, the relative importance degree between all parameters is judged and measured through the expert experience, and the weight of each parameter is given;
an entropy value method is adopted to carry out objective weight assignment, the dispersion degree of a parameter is judged by calculating the information entropy, the smaller the information entropy is, the larger the dispersion degree of the parameter is, the larger the influence of the parameter on comprehensive evaluation is, and the larger the weight is;
determining a combination weight coefficient by adopting a step difference maximization combination weight method, and determining a reasonable value interval of the combination weight according to the main and objective weights of each parameter; establishing an optimization model by taking the maximum discrimination of the evaluation result as an objective function and the reasonable value interval of the parameter weight as a constraint condition, and solving the combined weight of the evaluation index;
and reducing the dimension of the environmental parameter data containing the weight by adopting a principal component analysis method, and evaluating the state of the aircraft in the transportation process through the one-dimensional principal components after dimension reduction.
Preferably, the step S4 specifically includes:
acquiring the correlation among the parameters and preprocessing the correlation;
establishing an LSTM network prediction model and training parameters according to historical time sequence data of each parameter, and inputting characteristic data which has strong correlation with the parameter and is characterized by the parameter to be predicted and selected by parameter coupling analysis;
calculating residual errors between the predicted values and the true values of the parameters, and fitting residual error data into a Gaussian model;
and predicting the parameter variation trend, and judging whether the parameter state is abnormal according to a 3 sigma rule.
Preferably, the step S5 specifically includes:
establishing a safety protection knowledge base, providing protection knowledge for dealing with various abnormal conditions by experts or users, and expressing the protection knowledge by a production formula rule, namely IF state and THEN strategy to be adopted;
and (3) searching a rule matched with the abnormal state obtained by monitoring the state in a knowledge base by using an inference mechanism as a precondition, and inferring to obtain a corresponding safety protection strategy.
An aircraft transportation condition monitoring and safety protection system comprising: the system comprises an environmental parameter acquisition module, a data storage module, a data analysis and mining module, a state monitoring module and a safety protection decision-making module;
the environment parameter acquisition module consists of a sensor and data transmission equipment and is used for realizing the acquisition and transmission of environment parameters; the sensor collects key environmental parameters in the transportation of the aircraft, and the data transmission equipment transmits the collected parameter data to the data storage module;
the data storage module realizes parameter storage; the data storage module transmits the real-time data to the state monitoring module, continuously collects historical data, and applies the historical data to the data analysis and mining module;
the data analysis and mining module comprises multi-parameter coupling analysis, state evaluation model establishment and parameter anomaly detection model establishment and is used for supporting aircraft state evaluation and parameter anomaly detection;
the state monitoring module is used for realizing real-time parameter monitoring, evaluating the real-time state of the aircraft based on the state evaluation model, detecting whether the parameters are abnormal based on the parameter abnormality detection model and sending an alarm signal to the abnormal state;
and the safety protection decision module deduces to obtain a corresponding safety protection strategy according to the knowledge in the protection decision knowledge base based on the monitored parameter real-time state.
Preferably, the environmental parameter acquisition module comprises a temperature and humidity sensor, a vibration sensor, an acceleration sensor and an inclination angle sensor, and acquires parameters which directly influence the state of the aircraft in the transportation process of the aircraft, wherein the parameters comprise temperature and humidity, vibration, acceleration and inclination angle; and the data transmission equipment transmits the obtained real-time parameter data to the data storage module for analysis and processing by the data analysis and mining module and the state monitoring module.
Preferably, the state monitoring module carries out real-time monitoring, state evaluation, abnormal detection and alarm on the parameters. And the real-time parameter input data analysis and mining module establishes a parameter anomaly detection model and a state evaluation model to realize parameter anomaly detection and aircraft state evaluation, and gives an alarm signal under the condition of parameter anomaly and state anomaly.
Through the technical scheme, compared with the prior art, the invention discloses and provides a method and a system for monitoring the transportation state of an aircraft and protecting the safety; the method and the system for monitoring the transport state and protecting the safety of the aircraft are used for overcoming the difficult problems of monitoring the state and protecting the safety of the transport process, aiming at the condition that the damage of parts such as precision machinery, electrons and initiating explosive devices in the aircraft is accelerated due to variable environmental stresses such as temperature, humidity, vibration, impact and radiation in the transport process of the aircraft, and realizing the great improvement of the transport safety.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic view of the general flow of the method of the present invention.
Fig. 2 is a schematic view of an implementation flow of aircraft state evaluation provided by the present invention.
Fig. 3 is a schematic view of a parameter anomaly detection process provided by the present invention.
Fig. 4 is a schematic structural diagram of a parameter prediction network model provided by the present invention.
Fig. 5 is a schematic diagram of the overall composition structure of the system provided by the present invention.
Fig. 6 is a schematic view of a flow chart of a state detection module according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses an aircraft transportation state monitoring and safety protection method, which comprises the following steps:
s1, collecting aircraft transportation environment parameters;
s2, analyzing the correlation among the parameters based on a correlation analysis theory;
s3, carrying out subjective combination weight assignment based on an analytic hierarchy process, carrying out objective combination weight assignment based on an entropy method, determining a combination weight coefficient based on a level difference maximization combination weight method, and evaluating the state of the aircraft based on a principal component analysis method;
s4, comparing residual errors between the predicted values and the true values based on LSTM network prediction, and judging whether the parameters are abnormal or not;
and S5, based on knowledge reasoning, providing a safety protection decision suggestion for the detected abnormal state.
To further optimize the above technical solution, step S3 specifically includes:
subjective weight assignment is carried out according to expert experience by adopting an analytic hierarchy process, relative importance degree among all parameters is judged and measured through the experience of experts, and the weight of each parameter is given;
an entropy value method is adopted to carry out objective weight assignment, the dispersion degree of a parameter is judged by calculating the information entropy, the smaller the information entropy is, the larger the dispersion degree of the parameter is, the larger the influence of the parameter on comprehensive evaluation is, and the larger the weight is;
determining a combination weight coefficient by adopting a step difference maximization combination weight method, and determining a reasonable value interval of the combination weight according to the main and objective weights of each parameter; establishing an optimization model by taking the maximum discrimination of the evaluation result as an objective function and the reasonable value interval of the parameter weight as a constraint condition, and solving the combined weight of the evaluation index;
and reducing the dimension of the environmental parameter data containing the weight by adopting a principal component analysis method, and evaluating the state of the aircraft in the transportation process through the one-dimensional principal components after dimension reduction.
To further optimize the above technical solution, step S4 specifically includes:
acquiring the correlation among the parameters and preprocessing the correlation;
establishing an LSTM network prediction model and training parameters according to historical time sequence data of each parameter, and inputting characteristic data which has strong correlation with the parameter and is characterized by the parameter to be predicted and selected by parameter coupling analysis;
calculating residual errors between the predicted values and the true values of the parameters, and fitting residual error data into a Gaussian model;
and predicting the parameter variation trend, and judging whether the parameter state is abnormal according to a 3 sigma rule.
To further optimize the above technical solution, step S5 specifically includes:
establishing a safety protection knowledge base, providing protection knowledge for dealing with various abnormal conditions by experts or users, and expressing the protection knowledge by a production formula rule, namely IF state and THEN strategy to be adopted;
and (3) searching a rule matched with the abnormal state obtained by monitoring the state in a knowledge base by using an inference mechanism as a precondition, and inferring to obtain a corresponding safety protection strategy.
An aircraft transportation condition monitoring and safety protection system comprising: the system comprises an environmental parameter acquisition module, a data storage module, a data analysis and mining module, a state monitoring module and a safety protection decision-making module;
the environment parameter acquisition module consists of a sensor and data transmission equipment and is used for realizing the acquisition and transmission of environment parameters; the sensor collects key environmental parameters in the transportation of the aircraft, and the data transmission equipment transmits the collected parameter data to the data storage module;
the data storage module realizes parameter storage; the data storage module transmits the real-time data to the state monitoring module, continuously collects historical data, and applies the historical data to the data analysis and mining module;
the data analysis and mining module comprises multi-parameter coupling analysis, state evaluation model establishment and parameter anomaly detection model establishment and is used for supporting aircraft state evaluation and parameter anomaly detection;
the state monitoring module is used for realizing real-time parameter monitoring, evaluating the real-time state of the aircraft based on the state evaluation model, detecting whether the parameters are abnormal based on the parameter abnormality detection model and sending an alarm signal to the abnormal state;
and the safety protection decision module deduces to obtain a corresponding safety protection strategy according to the knowledge in the protection decision knowledge base based on the monitored parameter real-time state.
In order to further optimize the technical scheme, the environmental parameter acquisition module comprises a temperature and humidity sensor, a vibration sensor, an acceleration sensor and an inclination angle sensor, and acquires parameters which directly influence the state of the aircraft in the transportation process of the aircraft, wherein the parameters comprise temperature and humidity, vibration, acceleration and inclination angle; and the data transmission equipment transmits the obtained real-time parameter data to the data storage module for analysis and processing by the data analysis and mining module and the state monitoring module.
In order to further optimize the technical scheme, the state monitoring module carries out real-time monitoring, state evaluation, anomaly detection and alarm on the parameters. And the real-time parameter input data analysis and mining module establishes a parameter anomaly detection model and a state evaluation model to realize parameter anomaly detection and aircraft state evaluation, and gives an alarm signal under the condition of parameter anomaly and state anomaly.
As shown in fig. 1, the invention provides a transportation state monitoring and safety protection method based on multi-parameter data coupling driving, which comprises the following steps:
step 1, a data acquisition sensor acquires key environmental parameter data of the aircraft in the transportation process, and the measured parameters comprise important data of temperature, humidity, vibration, acceleration, inclination angle and the like which influence the state of the aircraft in the transportation process. The quality and the danger of the aircraft are affected by the change of the temperature and the humidity, the vibration signal reflects the bumping condition in the transportation process, and the inclination angle and the acceleration parameter reflect the running state of the transportation vehicle.
Step 2, multi-parameter coupling analysis: correlation among different parameters is researched by utilizing a correlation analysis theory based on the Pearson coefficient, and reference is provided for establishing a state evaluation model and a parameter anomaly detection model. The correlation analysis adopts an analysis method based on Pearson correlation coefficient, and the formula is
Wherein, Xi,YiDenotes the ith X variable and the ith Y variable,mean value of X, Y. r describes the degree of linear correlation between two variables. r takes on a value between-1 and +1, if r>0, indicating that the two variables are positively correlated, if r<0, indicating that the two variables are negatively correlated, a larger absolute value of r indicates a stronger correlation.
Step 3, the general scheme of aircraft state evaluation is shown in fig. 2: firstly, subjective weight assignment is carried out according to expert experience by adopting an analytic hierarchy process; secondly, performing objective weight assignment according to a multi-parameter coupling analysis result by adopting an entropy method; then determining a combined weight coefficient by a level difference maximization combined weight method; and finally, reducing the dimension of the environment parameter data containing the weight by adopting a principal component analysis method, and evaluating the state of the aircraft in the transportation process through the one-dimensional principal components after dimension reduction.
Specifically, the status evaluation steps are detailed as follows:
step 3.1, subjective weight assignment based on an analytic hierarchy process: by combining quantitative analysis and qualitative analysis, the relative importance degree of each parameter is judged and measured through the experience of experts, and the weight of each parameter is reasonably given. Because the influence degrees of all environment parameters on the state of the aircraft in the transportation process are different, the state is evaluated by firstly sequencing from high to low according to the importance among expert indexes, then quantifying the sequencing by an analytic hierarchy process to obtain the weight of each index, and then carrying out normalization processing on the subjective weight.
Step 3.2, the objective weight assignment process based on the entropy method is as follows:
(1) data matrix of environmental parameters: x ═ Xij](i is more than or equal to 1 and less than or equal to m, j is more than or equal to 1 and less than or equal to n) represents that m aircraft transport boxes are arranged in total, n environment parameters are arranged, and x isijThe value of the j environmental parameter of the ith aircraft transport case.
(3) calculating the weight of the ith aircraft transport case in the jth environmental parameter:
step 3.3, the process of determining the combined weight by the level difference maximization combined weight method is as follows:
(2) The maximum variance of the evaluated object scores under the combined weight is an objective function, and the reasonable interval of the attributes and the sum of the attribute weights are 1 as constraint conditions, so that a combined weighted optimization model is constructed:
wherein m aircraft transport bin number, w is weight vector w ═ w (w)1,...,wn)。
(3) And solving the combined weight of the evaluation indexes.
And 3.4, performing a state evaluation process based on a principal component analysis method as follows:
(1) constructing a standard matrix containing weights: t ═ wjxij)m×n。
(2) Calculating a covariance matrix: c ═ cov (T) ═ TTT。
(3) Calculating the eigenvalues λ of the matrix C1,...,λnAnd a feature vector d1,...,dn。
(4) Principal component projection vector of TWhere d is the eigenvector corresponding to the largest eigenvalue.
(5) Evaluating the rule: d vector contains the risk degree of m transport cases, DiLarger represents higher risk.
Step 4, the flow of the parameter anomaly detection method is shown in fig. 3: according to the historical time sequence data of each parameter, after preprocessing, according to the multi-parameter coupling analysis result, a parameter LSTM network prediction model is established, the parameter change trend is predicted, residual errors are calculated for the parameter prediction value and the true value, the residual error data are fitted into a Gaussian model, and whether the parameter state is abnormal or not is judged according to the 3 sigma rule.
Specifically, taking the abnormal detection of the temperature parameter as an example, the detailed implementation flow of the parameter abnormal detection is as follows:
step 4.2, building and training an LSTM network model of temperature parameters, inputting characteristic data with more than temperature, inputting other characteristic data which is selected by parameter coupling analysis and has strong correlation with temperature data, outputting the temperature parameters, wherein the schematic diagram of the network structure is shown in FIG. 4: wherein, Xi(i 1.. n.) is a vector composed of multidimensional features, and the future 1 time is predicted by multi-parameter data of historical n time stepsTemperature data of the step.
Step 4.3, inputting the training data into the well-trained LSTM network, and calculating the residual difference delta between the predicted value and the true value1,...,δi,., fitting a gaussian distribution with the residual data: t to N (mu, sigma)2)。
And 4.3, predicting and calculating a residual error: inputting historical data of n time steps before time t, and predicting temperature value of 1 time stepCalculating a predicted valueWith true value Tt+1The residual δ between.
Step 4.4, judging whether the parameters are abnormal according to the 3 sigma rule: when | δ - μ | > 3 σ, the residual δ is considered not to be within the normal range, i.e., the temperature data at this time is considered to be in an abnormal state.
And 5, safety protection decision based on knowledge reasoning: and (4) providing a safety protection strategy according to the abnormal state monitored in real time by combining expert knowledge and an inference mechanism.
Specifically, the safety protection decision flow is detailed as follows:
step 5.1, establishing a safety protection knowledge base: protection knowledge for dealing with various abnormal conditions is given by experts or users, and is input into a safety protection knowledge base. Knowledge is expressed by a production rule, namely an IF state and a strategy to be adopted by THEN (for example, an IF vibration signal or an acceleration signal is abnormal, THEN reminds a driver to reduce the vehicle speed, and an IF temperature and humidity signal is abnormal, THEN adopts corresponding measures to control the temperature and the humidity).
Step 5.2, knowledge reasoning: and (3) searching a rule matched with the abnormal state obtained by monitoring the state in a knowledge base by using an inference mechanism as a precondition, and inferring to obtain a corresponding safety protection strategy.
As shown in fig. 5, the present invention further provides a transportation state monitoring and safety protection system based on multi-parameter data coupling driving, which mainly includes: the system comprises an environmental parameter acquisition module, a data storage module, a data analysis and mining module, a state monitoring module and a safety protection decision-making module.
The environment parameter acquisition module is mainly used for acquiring real-time key parameters of the aircraft in the transportation process through a temperature and humidity sensor, a vibration sensor, an acceleration sensor, an inclination angle sensor and the like, and the data transmission equipment transmits the acquired real-time parameter data to the data storage module so as to be analyzed and processed by the data analysis and mining module and the state monitoring module.
And the data storage module is used for realizing the storage of environmental parameters, transmitting the real-time data to the state monitoring module, continuously collecting historical data and applying the historical data to the data analysis and mining module.
The main tasks of the data analysis and mining module include: multi-parameter coupling analysis, state evaluation model establishment and parameter anomaly detection model establishment. The parameter coupling analysis result can provide reference for establishing a state evaluation model and an abnormality detection model.
The main tasks of the state monitoring module are real-time monitoring, parameter anomaly detection and state evaluation. The specific process is as shown in fig. 6, based on the preprocessed real-time monitored environmental parameters, the real-time parameters are input into a parameter anomaly detection model and a state evaluation model which are established by the data analysis and mining module, parameter anomaly detection and aircraft state evaluation are realized, and an alarm signal is given out under the condition of parameter anomaly and state anomaly.
The main task of the security decision module is to present a security policy. The module mainly comprises a protection decision knowledge base and an inference engine. The knowledge base stores safety protection knowledge corresponding to various abnormal states, and the method for acquiring the knowledge is input by an expert and a user; and the inference machine infers a proper safety protection strategy according to the abnormal result of the state monitoring and the knowledge in the knowledge base.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. An aircraft transportation state monitoring and safety protection method is characterized by comprising the following steps:
s1, collecting aircraft transportation environment parameters;
s2, analyzing the correlation among the parameters based on a correlation analysis theory;
s3, carrying out subjective combination weight assignment based on an analytic hierarchy process, carrying out objective combination weight assignment based on an entropy method, determining a combination weight coefficient based on a level difference maximization combination weight method, and evaluating the state of the aircraft based on a principal component analysis method;
s4, comparing residual errors between the predicted values and the true values based on LSTM network prediction, and judging whether the parameters are abnormal or not;
and S5, based on knowledge reasoning, providing a safety protection decision suggestion for the detected abnormal state.
2. The aircraft transportation state monitoring and safety protection method according to claim 1, wherein the step S3 specifically includes:
subjective weight assignment is carried out according to expert experience by adopting an analytic hierarchy process, the relative importance degree between all parameters is judged and measured through the expert experience, and the weight of each parameter is given;
an entropy value method is adopted to carry out objective weight assignment, the dispersion degree of a parameter is judged by calculating the information entropy, the smaller the information entropy is, the larger the dispersion degree of the parameter is, the larger the influence of the parameter on comprehensive evaluation is, and the larger the weight is;
determining a combination weight coefficient by adopting a step maximum combination weight method, and determining a reasonable value interval of the combination weight according to the main and objective weights of each parameter; establishing an optimization model by taking the maximum discrimination of the evaluation result as an objective function and the reasonable value interval of the parameter weight as a constraint condition, and solving the combined weight of the evaluation index;
and reducing the dimension of the environment parameter data containing the weight by adopting a principal component analysis method, and evaluating the state of the aircraft in the transportation process by using the one-dimensional principal component after dimension reduction.
3. The aircraft transportation state monitoring and safety protection method according to claim 1, wherein the step S4 specifically includes:
acquiring the correlation among the parameters and preprocessing the correlation;
establishing an LSTM network prediction model and training parameters according to historical time sequence data of each parameter, and inputting characteristic data which has strong correlation with the parameter and is characterized by the parameter to be predicted and is selected by parameter coupling analysis;
calculating residual errors between the predicted values and the true values of the parameters, and fitting residual error data into a Gaussian model;
and predicting the parameter variation trend, and judging whether the parameter state is abnormal according to a 3 sigma rule.
4. The aircraft transportation state monitoring and safety protection method according to claim 1, wherein the step S5 specifically includes:
establishing a safety protection knowledge base, providing protection knowledge for dealing with various abnormal conditions by experts or users, and expressing the protection knowledge by a production formula rule, namely IF state and THEN strategy to be adopted;
and (3) searching a rule matched with the abnormal state obtained by monitoring the state in a knowledge base by using an inference mechanism as a precondition, and inferring to obtain a corresponding safety protection strategy.
5. An aircraft transportation state monitoring and safety protection system, comprising: the system comprises an environmental parameter acquisition module, a data storage module, a data analysis and mining module, a state monitoring module and a safety protection decision-making module;
the environment parameter acquisition module consists of a sensor and data transmission equipment and is used for realizing the acquisition and transmission of environment parameters; the sensor collects key environmental parameters in the transportation of the aircraft, and the data transmission equipment transmits the collected parameter data to the data storage module;
the data storage module realizes parameter storage; the data storage module transmits the real-time data to the state monitoring module, continuously collects historical data, and applies the historical data to the data analysis and mining module;
the data analysis and mining module comprises multi-parameter coupling analysis, state evaluation model establishment and parameter anomaly detection model establishment and is used for supporting aircraft state evaluation and parameter anomaly detection;
the state monitoring module is used for realizing real-time parameter monitoring, evaluating the real-time state of the aircraft based on the state evaluation model, detecting whether the parameters are abnormal based on the parameter abnormality detection model and sending an alarm signal to the abnormal state;
and the safety protection decision module deduces to obtain a corresponding safety protection strategy according to the knowledge in the protection decision knowledge base based on the monitored parameter real-time state.
6. The aircraft transportation state monitoring and safety protection system according to claim 5, wherein the environmental parameter acquisition module comprises a temperature and humidity sensor, a vibration sensor, an acceleration sensor and an inclination angle sensor, and acquires parameters directly influencing the aircraft state in the aircraft transportation process, such as temperature and humidity, vibration, acceleration and inclination angle; and the data transmission equipment transmits the obtained real-time parameter data to the data storage module for analysis and processing by the data analysis and mining module and the state monitoring module.
7. The aircraft transportation state monitoring and safety protection system according to claim 5, wherein the state monitoring module performs real-time monitoring, state evaluation, anomaly detection and alarm on the parameters. And the real-time parameter input data analysis and mining module establishes a parameter anomaly detection model and a state evaluation model to realize parameter anomaly detection and aircraft state evaluation, and gives an alarm signal under the condition of parameter anomaly and state anomaly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210194936.7A CN114565162A (en) | 2022-03-01 | 2022-03-01 | Aircraft transportation state monitoring and safety protection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210194936.7A CN114565162A (en) | 2022-03-01 | 2022-03-01 | Aircraft transportation state monitoring and safety protection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114565162A true CN114565162A (en) | 2022-05-31 |
Family
ID=81715006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210194936.7A Pending CN114565162A (en) | 2022-03-01 | 2022-03-01 | Aircraft transportation state monitoring and safety protection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114565162A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116502963A (en) * | 2023-06-29 | 2023-07-28 | 苏州鸿安机械股份有限公司 | Wafer transportation control method and system based on artificial intelligence |
CN117435964A (en) * | 2023-12-21 | 2024-01-23 | 江苏赫奕科技有限公司 | Equipment state evaluation method and system based on data diagnostic instrument |
CN117635009A (en) * | 2024-01-25 | 2024-03-01 | 四川汇利实业有限公司 | Intelligent monitoring method, system, equipment and storage medium for cold chain transportation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633855A (en) * | 2019-09-17 | 2019-12-31 | 江南大学 | Bridge health state detection and management decision making system and method |
CN111105153A (en) * | 2019-12-13 | 2020-05-05 | 西安交通大学 | Satellite health state multi-stage fuzzy evaluation method based on AHP-entropy weight method |
CN112966939A (en) * | 2021-03-05 | 2021-06-15 | 浙江理工大学 | Elevator safety assessment method based on combined weighted fuzzy comprehensive evaluation |
-
2022
- 2022-03-01 CN CN202210194936.7A patent/CN114565162A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110633855A (en) * | 2019-09-17 | 2019-12-31 | 江南大学 | Bridge health state detection and management decision making system and method |
CN111105153A (en) * | 2019-12-13 | 2020-05-05 | 西安交通大学 | Satellite health state multi-stage fuzzy evaluation method based on AHP-entropy weight method |
CN112966939A (en) * | 2021-03-05 | 2021-06-15 | 浙江理工大学 | Elevator safety assessment method based on combined weighted fuzzy comprehensive evaluation |
Non-Patent Citations (2)
Title |
---|
曾航 等: "基于改进LSTM模型的航空安全预测方法研究", 《***工程与电子技术》 * |
王奔驰 等: "基于主客观权重方法的某战机起飞阶段飞行品质评价", 《计算机测量与控制》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116502963A (en) * | 2023-06-29 | 2023-07-28 | 苏州鸿安机械股份有限公司 | Wafer transportation control method and system based on artificial intelligence |
CN116502963B (en) * | 2023-06-29 | 2023-09-15 | 苏州鸿安机械股份有限公司 | Wafer transportation control method and system based on artificial intelligence |
CN117435964A (en) * | 2023-12-21 | 2024-01-23 | 江苏赫奕科技有限公司 | Equipment state evaluation method and system based on data diagnostic instrument |
CN117435964B (en) * | 2023-12-21 | 2024-03-15 | 江苏赫奕科技有限公司 | Equipment state evaluation method and system based on data diagnostic instrument |
CN117635009A (en) * | 2024-01-25 | 2024-03-01 | 四川汇利实业有限公司 | Intelligent monitoring method, system, equipment and storage medium for cold chain transportation |
CN117635009B (en) * | 2024-01-25 | 2024-05-03 | 四川汇利实业有限公司 | Intelligent monitoring method, system, equipment and storage medium for cold chain transportation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114565162A (en) | Aircraft transportation state monitoring and safety protection method and system | |
CN111813084B (en) | Mechanical equipment fault diagnosis method based on deep learning | |
CN111539515B (en) | Complex equipment maintenance decision method based on fault prediction | |
CN111487991B (en) | Unmanned aerial vehicle cluster-oriented security level prediction method and system | |
CN109934358A (en) | Equipment failure prediction and health evaluating method, system and terminal device | |
CN109685366A (en) | Equipment health state evaluation method based on mutation data | |
CN110197282B (en) | Threat estimation and situation assessment method based on genetic fuzzy logic tree | |
CN110348752B (en) | Large industrial system structure safety assessment method considering environmental interference | |
CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
CN115169479A (en) | Remote monitoring method, system and storage medium for sewage treatment process | |
CN112884051B (en) | Data-driven multi-component online complex fault diagnosis method for lightweight unmanned aerial vehicle | |
CN109947898B (en) | Equipment fault testing method based on intellectualization | |
CN114004331A (en) | Fault analysis method based on key indexes and deep learning | |
CN111767657B (en) | Nuclear power system fault diagnosis method and system | |
CN117332347A (en) | Intelligent operation and maintenance method and system for power grid by integrating machine patrol and AI | |
CN116109039A (en) | Data-driven anomaly detection and early warning system | |
CN115146845A (en) | Equipment system level-oriented health state evaluation and fault prediction method and system | |
CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
CN116029220B (en) | Voltage transformer operation error assessment method, system, equipment and medium | |
CN112785074B (en) | Equipment maintenance and repair opportunity determination system and method based on deep learning | |
CN117252435B (en) | Factory production safety monitoring and early warning method and system based on industrial Internet | |
Gu et al. | A baseline modeling method for UAV condition monitoring based on multiple flight data | |
Minghua et al. | Rough Set Neural Network Evaluation Method for UAV Reconnaissance Effectiveness | |
EP4273752A1 (en) | Device and method for detecting anomalies in technical systems | |
CN114884694B (en) | Industrial control network security risk assessment method based on hierarchical modeling |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220531 |