32 results about "Combinatorial algorithms" patented technology

The invention relates to the technical field of test question generation, in particular to an intelligent test question generation method and system based on learning behavior analysis. The method comprises the following steps: acquiring interactive behavior data and score data of learners in a user online learning platform in real time; inputting the interactive behavior data and the score data into a pre-trained knowledge state analysis model to generate a user knowledge state matrix; based on the knowledge state matrix and in combination with a preset teaching target library, identifying a target knowledge point set which needs to be strengthened currently and a corresponding cognitive training type; according to the target knowledge point set needing to be strengthened and the corresponding cognitive training type, a test question element combination algorithm is called, question stems, interference items and question solving path prompts are dynamically assembled, and personalized test questions are generated. The method has the advantages that full-closed-loop intelligent teaching from behavior analysis of the user to targeted training is achieved, and personalized test questions adaptive to individual cognitive vulnerabilities are dynamically generated.

The invention belongs to the technical field of packaging jet printing, and discloses an external packaging carton two-dimensional code jet printing quality online monitoring and error correction process, which comprises the following steps: building a vision, laser, spectrum and pressure four-source sensing positioning system in a preprocessing stage, comprehensively collecting carton material and form related data, and forming a pre-calibration closed loop in cooperation with microsample jet printing verification; in the jet printing process, a high-speed imaging system of self-adaptive light supplement works synchronously, after an image is preprocessed through a combinatorial algorithm, various defects such as blooming and scratches are accurately recognized through a ResNet34-Transform-GAN fusion model, and then an LSTM neural network is used for predicting the development trend of the defects and conducting early warning; a three-level parameter configuration system of cloud decision, edge execution and twin simulation is utilized, an edge calculation unit uploads data such as materials, sizes and flatness collected in real time to the cloud, historical optimal parameters of the corresponding materials are called, and then dynamic adjustment is conducted in combination with the conveying speed.

The invention discloses an urban user power utilization efficiency collaborative optimization analysis method and system based on the Internet of Things, and relates to the technical field of power analysis, and the technical scheme is characterized in that a multi-source heterogeneous data pool containing timestamp alignment is constructed; generating a user electricity consumption characteristic matrix through a space-time dynamic weight fusion algorithm; calculating a frequency modulation potential value through an entropy-TOPSIS combinatorial algorithm based on the user power consumption characteristic matrix; inputting the frequency modulation potential value into an LSTM-GAN confrontation generative network, and dynamically generating a three-dimensional efficiency parameter vector containing a user optimization degree, a good power grid contribution degree and an environmental benefit index; and based on the three-dimensional efficiency parameter vector, an optimization target of a user and a power grid is coordinated through a Stackelberg game model, and a dynamic electricity price strategy and a load adjustment strategy are output. The method has the advantages of being low in response delay, high in energy efficiency optimization rate, good in environmental benefit and the like when being used for coping with complex power consumption scenes in urban areas.

The invention discloses a cable material diameter detection method based on an eddy current impedance effect, and particularly relates to the field of cable nondestructive testing, which comprises the following steps: S1, synchronously acquiring the resistance and inductance of a coil under a low-frequency signal and the resistance and inductance of the coil under a high-frequency signal by adopting a double-frequency excitation eddy current sensor; the environment temperature and the lift-off distance between the sensor and the cable are measured; s2, denoising is carried out through a combinatorial algorithm, and temperature compensation is carried out on the resistance and inductance of a sensor coil and the conductivity of a cable core wire; s3, calculating a material sensitive factor under low frequency, calculating a line diameter sensitive factor under high frequency, and correcting when the lift-off distance deviates; s4, calculating a material deviation rate to judge the material, fitting a linear regression model, and combining with conductivity to correct the skin depth to calculate the line diameter; and S5, according to the material and the wire diameter, comprehensively determining progressive output, and triggering a corresponding alarm in case of abnormality. The problems of parameter coupling and incomplete temperature compensation are solved, and the detection precision and the environmental adaptability are improved.

The invention discloses a 5G and Beidou fused vehicle positioning navigation system. The system comprises a multi-source heterogeneous positioning module; a high-precision map and a dynamic traffic information base; a self-adaptive multi-layer map matching module; the dynamic path planning module considers steering limitation and real-time position feedback; and a central information fusion and decision unit. According to the invention, multi-source heterogeneous positioning data such as Beidou / GPS, 5G positioning, high-precision IMU, a vehicle-mounted atomic clock and a barometric altimeter are fused, and a tight combination algorithm based on ESKF or a factor graph is adopted, so that the system can realize accurate positioning in an environment with good satellite signals, partial shielding and even serious loss. Continuous, smooth and high-precision vehicle state estimation can be output, particularly when the number of visible satellites is insufficient, double-satellite positioning can be achieved by using the vehicle-mounted atomic clock to predict the clock error and combining the elevation constraint of the barometric altimeter, and the usability and robustness of positioning are improved.

The invention provides an antenna automatic control method adaptive to different antenna deployment modes. The antenna automatic control method comprises the steps that S1, a remote information processor reads circuit level data of an external antenna; s2, the communication module diagnoses the circuit level data of the external antenna based on an antenna in-situ identification algorithm, and judges the working state of the external antenna; step S3, based on a single-pole double-throw switch combination algorithm, evaluating a judgment result in the step S2, calculating an optimal switching scheme, and sending a corresponding switching instruction; s4, the single-pole double-throw switch receives the switching instruction and executes switching operation, the communication module verifies the switching effect through the step S2, and if switching fails, the switching instruction is sent again; and S5, setting a signal instability threshold, and comparing the signal receiving intensities before and after switching. According to the invention, a plurality of TBOX parts do not need to be varied to adapt to the selection of different antenna deployment, the flexibility of antenna deployment is improved, and the platform compatibility difficulty is reduced.

The invention discloses a five-axis numerical control machine tool machining error on-line compensation system based on deep learning, relates to the technical field of machine tool error compensation, and solves the problems that position correction difference is caused by neglecting a complex coupling relation between rotating shafts and linear shafts of different types of machine tools, and the error compensation accuracy is high. And deep learning models for machine tools with different requirement types are not designed, so that the model prediction precision is influenced. Determining the coupling relation of each axis error through the HTM homogeneous transformation matrix of the machine tool kinematic chain; aiming at kinematic chain structure differences of different types of machine tools, a differential correction strategy is designed. And constructing a zero drift time sequence model in combination with a historical drift trend term and a random error term predicted by the LSTM. Geometric error terms strongly related to machining errors are screened through grey correlation analysis, then the weight of the geometric error terms is quantified through random forest, the accuracy of key error recognition through a combinatorial algorithm is improved, and the model prediction precision is improved by training fusion models for machine tools with different requirement types.

The invention relates to an osteoarthritis AI (osteoarthritis) prediction method based on NETs (neutrophile granulocyte extracellular traps) related key genes, and aims to develop a model universally applicable to gene diagnosis or molecular diagnosis by analyzing and disclosing a large sample data set through an advanced algorithm by utilizing ML (makeup language) to reveal genetic regulation of neutrophile granulocyte extracellular traps (NETs) in joint tissues. Therefore, the optimal algorithm needs to be compared and screened by using multiple algorithms during modeling, the gene (molecule) diagnosis efficiency is improved by combining the algorithms on the basis, key genes which can best reflect OA characteristics and are driven by NETs (key gene characteristics related to the NETs) are selected, and the disease-related genes and the relationship between the disease-related genes and disease phenotypes are identified, so that the disease-related genes are identified. Therefore, understanding of interaction of biological components is deepened, and diagnosis and treatment strategies are improved.

The application provides a special-shaped character detection and recognition method, system, device and storage medium, and relates to the field of special-shaped character detection and recognition.The method comprises the following steps: (1) constructing a training set based on an existing product image, and importing the training set into a rotating target detection model for training; (2) inputting a product image to be detected into the trained rotating target detection model to output string information M of different regions in the product image to be detected; and (3) based on the string information M of different regions, adopting an optimal combination algorithm to combine characters in front and back, and forming a plurality of independent strings.The application uses a rotating target detection model for character recognition, and adopts an optimal combination algorithm for character combination on the basis of character recognition, and then detects special-shaped strings on medical devices and other products.The application solves the problem of low character detection accuracy caused by irregular string shapes in a complex scene.

The invention discloses a mechanical arm scanning track planning method based on an improved ant colony algorithm, which comprises the following steps: step 1, dividing a to-be-measured workpiece into n primitives, setting n measuring points on the to-be-measured workpiece, and setting a complete set T of the measuring points as follows: T = {T1, T2, T3,..., Tm}; 2, solving a set coverage problem by using an improved greedy algorithm to obtain an optimal selection method of a scanning point position set; 3, solving a scanning track by using an improved ant colony algorithm and a combined algorithm based on a BFS strategy; step 4, optimizing the scanning track by using a particle swarm algorithm to obtain an overall scanning track with the shortest scanning time; and step 5, obtaining an overall scanning track with the shortest scanning time by using a particle swarm algorithm. According to the method, a scanning track is solved by using an improved ant colony algorithm and a BFS-based strategy, a larger area is selected to continue to carry out strategy path search, and a smaller area is solved by using the ant colony algorithm to obtain a loop. And opening the loop, combining the loop to an original path, and solving the whole path through the BFS to obtain an optimal path.

The application discloses a programmable Josephson quantum voltage standard AC output characteristic comparison test system and method. The application generates synchronous step waves through homologous triggering of two sets of PJVS systems, directly collects difference signals of the two step waves by using a differential sampler, and realizes high-precision comparison of AC output characteristics of the two sets of PJVS systems by combining difference correction and effective value calculation. The application saves a complex intermediate transmission standard, simplifies the comparison process, and improves test efficiency and result accuracy. The application considers theoretical differences caused by parameters such as a PJVS junction parameter, a step number, a bias combination algorithm and a working microwave frequency difference, and further improves test precision by correction, and is suitable for comparison scenes of quantum voltage standard systems of different manufacturers and different parameter configurations.

The invention discloses a regional photovoltaic output data enhancement and ultra-short-term power prediction method based on a dynamic graph attention network combinatorial algorithm, and the method comprises the following steps: firstly, decomposing a photovoltaic power sequence into a plurality of subsequences with stable trends through employing a variation mode decomposition model optimized by a Bayesian algorithm, combining and constructing a feature matrix; secondly, constructing a combined model based on a dynamic graph attention network and Transform, representing a space-time dynamic association relationship of a feature matrix, and then predicting and reconstructing each sub-sequence at a missing moment to obtain a complete photovoltaic data set; and finally, introducing a period-trend component decoupling prediction model based on a variational inference principle, decomposing the photovoltaic power into a periodic component and a trend component, respectively predicting the periodic component and the trend component, and reconstructing the periodic component and the trend component, thereby improving the photovoltaic prediction precision. According to the invention, the authenticity and prediction precision of photovoltaic data can be effectively improved, and powerful support is provided for new energy consumption and safe operation of a power system.

The invention discloses a foundation pit engineering emergency disposal system combined with safety system evaluation and a response method, the system comprises a multi-source data acquisition module, a safety system evaluation module, an intelligent emergency disposal module and a recovery optimization module, and each module forms a closed-loop architecture. The multi-source data acquisition module acquires full-cycle data; the safety system evaluation module calculates a comprehensive weight and a risk value through a combinatorial algorithm, and quantifies a safety level; the intelligent emergency disposal module starts a grading scheme based on an evaluation result and optimizes a decision based on a BIM model; and the recovery optimization module optimizes the parameters of the feedback system. According to the response method, efficient disposal is achieved through data collection, grade judgment, grading response and redisk updating. The method improves the risk identification efficiency and judgment accuracy, optimizes the resource allocation, reduces the disposal cost, adapts to a complex foundation pit scene, and guarantees the safety of construction and the surrounding environment.

The invention provides a collaborative optimization method for working parameters of a wheel loader, which comprises the following steps of: firstly, dividing the running distance of the loader in a stepping manner to ensure that the distance of each step is equal, then accurately calculating a single-stepping cost function and a stepping time length in each stepping state by adopting a dynamic programming-Brench combinatorial algorithm and combining an initial weight factor, and finally calculating the working parameters of the wheel loader according to the single-stepping cost function and the stepping time length. And accumulating and calculating the total running time of the loader. And if the time length is different from the preset time length, dynamically adjusting the weight factor through a rooting algorithm until a preset condition is met. According to the process, collaborative optimization of the driving speed and the energy management strategy is achieved, the charging and discharging rate and frequency of the battery are effectively reduced, and therefore battery aging is slowed down. Compared with an existing electro-hydraulic parallel hybrid drive system, the energy utilization efficiency is remarkably improved, the service life of a battery is greatly prolonged, and the overall economical efficiency and environmental protection performance of the loader are improved.

The invention discloses a precipitation prediction method based on a GRU and an LSTM neural network. The precipitation prediction method comprises the following steps: selecting meteorological station data continuously monitored for a long time; removing abnormal values of the meteorological station data, and complementing missing values; selecting first 85% of historical data for model parameter training, and selecting last 15% of recent data for model generalization ability test; normalizing the three precipitation index dimensions of the training set and the test set respectively; combining an algorithm model by using GRU and LSTM components; inputting the preprocessed training set data into the network, using a mean square error as a loss function, adopting an Adam algorithm to optimize the loss function, and iteratively updating network parameters until the model converges; data to be predicted are input into the trained model after being preprocessed in the first step, and a precipitation prediction result is output. Sequence data information is processed through multiple influence factor data and the superposed GRU and LSTM combination, the gradient disappearance problem is avoided, the prediction effect is good, precision is high, and applicability is good.

The invention discloses a lung adenocarcinoma prognosis prediction method based on machine learning. RNA transcription data and clinical information of a lung adenocarcinoma patient are collected from a database, and a data set is constructed; performing gene expression data preprocessing and difference analysis to obtain differential expression genes; sequencing the risk coefficients of the differential genes by using single-factor COX analysis; carrying out survival related feature recognition on the screened genes by virtue of eight machine learning algorithms related to survival analysis to obtain related genes with prognosis values; a machine learning combinatorial algorithm is utilized to train multiple prognosis models, C-index average values of the prognosis models are calculated and compared, and an optimal StepCox-RSF algorithm is selected to carry out patient layering and prognosis prediction model construction according to feature genes; according to the risk score of the patient, predicting the total survival rate and the risk grouping condition of the patient; according to the method, the reflecting capacity of the model to the immune microenvironment is remarkably improved, the prediction precision is optimized, and a scientific basis is provided for personalized treatment of lung adenocarcinoma patients.

The invention discloses a method for solving a feedback set of a network, which relates to the technical field of software engineering, logic circuit design and social networking services, and comprises the following steps of: for a graph G, searching a cut edge of the graph G by using a depth-first search algorithm, and if the graph G has the cut edge, deleting the cut edge; if the maximum degree of the graph G is 0, ending the process, and outputting a feedback set; if the B is an isolated point, deleting vertexes in the B, and if the maximum degree of the B is at least 2, firstly putting a vertex v with the maximum degree in the B into a feedback set; according to the method, the feedback set of the network is directly obtained by alternately deleting the vertex with the maximum degree of the network and deleting the cut edge by utilizing the structural characteristics of the graph, and compared with the traditional solving modes such as a linear programming algorithm and a polyhedron combination algorithm, the solving method does not need to construct an adjacent vector and a feedback set polyhedron firstly, so that the solving efficiency is improved. The problem is converted into a linear programming problem, a feedback set result is directly obtained, solving is simpler and more convenient, and the result is more visual.

This invention discloses a method for selecting characteristic wavelengths in the near-infrared spectrum of turmeric vinegar solution based on a combinatorial algorithm, belonging to the fields of chemometrics and online detection of explosives. This invention utilizes a differential algorithm to obtain an initial solution. After initialization, mutation, crossover, and selection operations, a set of characteristic wavelengths for the differential optimization algorithm is obtained, reducing the time spent blindly searching in the initial stage of the Cuckoo Algorithm due to the large amount of information, thus improving the efficiency of selecting characteristic wavelengths in the near-infrared spectrum of turmeric vinegar solution. This invention uses the preprocessed spectrum corresponding to the characteristic wavelength set of the differential optimization algorithm as the initial variable, and uses the Cuckoo Algorithm to select characteristic wavelengths for the initial variable, effectively reducing dimensionality while maximizing the provision of effective information. The near-infrared quantitative analysis model for hexamethylenetetramine concentration in turmeric vinegar solution established by this invention using characteristic wavelengths selected by the combinatorial algorithm can reduce model complexity and improve model prediction accuracy and robustness.

The application discloses a kind of based on multi-sensor fusion's monitoring equipment intelligent early warning and linkage control system, belong to the technical field of abnormal state alarm system.System includes sensing perception layer, data fusion processing layer, intelligent early warning layer, linkage control layer and operation and maintenance management platform;Sensing perception layer acquires multidimensional data and standardization processing;Data fusion processing layer realizes double-layer fusion of multi-source heterogeneous data by improving evidence theory and combination algorithm, exports equipment state evaluation and fault location result;Intelligent early warning layer is based on improved clustering algorithm and completes fault classification early warning;Linkage control layer is matched with repair strategy by fault repair decision tree algorithm intelligent;Operation and maintenance management platform carries ARIMA time series prediction algorithm and realizes fault prevention beforehand.This application realizes monitoring equipment whole state accurate perception, fault early warning, and is suitable for snow bright project, wisdom traffic, safe city and other scenes.

The application discloses a kind of pedestrian trajectory classification methods based on semi-supervised random neural network.The method includes constructing pedestrian trajectory data;Pedestrian trajectory data is preprocessed;Different trajectory patterns are established according to pedestrian trajectory data;Finally, the combination algorithm of quantifiable minimum error entropy criterion and semi-supervised random neural network algorithm is used to classify pedestrian behavior.The application uses quantifiable minimum error entropy criterion to replace traditional mean square error criterion, and is combined with semi-supervised random neural network algorithm, which can further improve the classification ability of existing semi-supervised learning model, and also improves the accuracy of pedestrian trajectory classification.

The invention discloses a gate opening degree control system and method based on a force-displacement time error algorithm, and relates to the technical field of gate control, and the system comprises the following modules: an actual comparison module used for collecting performance parameters of a structure, a transmission mechanism and a motor of a gate, and obtaining actually measured operation time; the core algorithm building module is used for building a function that the driving force changes along with the opening degree on the basis of a mechanics and kinematics relation, and building a theoretical time-opening degree digital model; the theoretical calculation module forms a to-be-calibrated fixed parameter combination and outputs theoretical operation time under different working conditions; the model correction module optimizes fixed parameters in the theoretical model so as to minimize errors between the theory and actual measurement and lock an optimal parameter combination; and the algorithm operation module inputs the target opening degree into the final control model, the gate operation time is calculated, gate positioning control is achieved, and the system can improve the accuracy and reliability of gate control.

The application relates to the technical field of municipal engineering construction progress management, and discloses a construction progress management method and system fusing an underground pipeline digital model, which is suitable for a city water supply network reconstruction project. The method comprises the following steps: constructing an underground pipeline digital model fusing pipeline, geology, pipe material and construction constraint parameters and verifying the precision; generating an initial progress plan based on the model in combination with an improved critical path method and Monte Carlo simulation; collecting data through a multi-source sensing terminal and dynamically updating the model by using an improved Kalman filtering algorithm; quantifying progress deviation and locating causes by using an entropy weight-TOPSIS combination algorithm; adjusting progress and resources and formulating an emergency plan based on a particle swarm optimization algorithm; and constructing a progress-quality-pipeline safety correlation database in an acceptance stage to realize closed-loop management. Six function modules are correspondingly arranged in the system. The application improves the digitization and scientific level of progress management, solves problems such as poor adaptability and inaccurate deviation positioning of traditional management, and is suitable for complex working conditions.

A method for measuring the rotation angle of a rigid body based on a visual-inertial combined algorithm belongs to the field of rigid body angular motion parameter measurement. The method involves constructing a rectangular target as a reference plane for an industrial camera; the target base is fixedly placed in front of the rotation axis of the rigid body being measured. A cross slide rail drives the rectangular target to achieve small-angle pitch rotation around a horizontal rotation axis. A rigid body connector is installed and fixed at the end of the rotating rigid body, connecting the rigid body to the measurement module. During the rotation of the rigid body, feature images, primarily of the target, are acquired at a preset frequency, and angle calculations are performed. An inertial measurement unit acquires inertial data during the rotation of the rigid body at a predetermined frequency and performs angle calculations. An optimization algorithm is used to fuse inertial and visual sampling data to correct the zero-point drift of the inertial measurement unit, improving the measurement accuracy of the rigid body rotation angle. This invention is applicable to the measurement of dual-axis angular motion.

The present application relates to the technical field of medical care intelligentization, and particularly relates to a safety hidden danger management system for clinical nursing in obstetrics and gynecology, comprising a heterogeneous system adaptation, a hidden danger intelligent perception, a risk quantitative evaluation, a hierarchical precise early warning, a hidden danger hierarchical treatment and a data intelligent analysis module, the system connects multiple systems of a hospital through a heterogeneous module, completes format conversion, semantic alignment and encrypted transmission of multi-source heterogeneous data, fuses structured business data and unstructured environmental equipment data, identifies hidden dangers through a combination algorithm, dynamically determines a risk level by constructing a multi-dimensional index system, implements differentiated early warning and full-process tracing, embeds a standardized process to treat hidden dangers, hybridly stores full-process data and mines hidden danger occurrence rules, and realizes accurate identification and alarm of hidden dangers, scientific hierarchical early warning and standardized treatment of risks, mining of hidden danger occurrence rules, and improvement of nursing safety control pre-control ability and scientificity of management decisions.

The application provides a kind of based on multi-beam depth finder tight combination topographic auxiliary navigation method, comprising: establishing a kind of topographic auxiliary navigation system carried on underwater autonomous vehicle, including strapdown inertial navigation system, Doppler log, multi-beam depth finder, the error of each type sensor is introduced into system model and is accurately modeled;Propose a kind of equal-angle multi-beam depth finder measurement modeling method based on two-step iteration method and apply it to navigation filtering;The DR system in traditional loose combination algorithm, topographic auxiliary navigation particle filter, system Kalman filter are integrated into core tight combination particle filter, and the original information of each sensor is directly input into particle filter to correct positioning information.The tight combination topographic auxiliary navigation method provided by the application can effectively improve the efficiency, accuracy and stability of the navigation positioning system.

The invention discloses a clinical prediction model construction method for traumatic stress liver injury based on a machine learning algorithm, and belongs to the technical field of clinical examination data analysis and processing. The method specifically comprises the following steps: collecting clinical examination data of a patient suffering from traumatic stress liver injury, cleaning and structuring the clinical examination data, introducing four machine learning algorithm models including Logistic regression, a decision tree, CatBoost and a random forest, screening clinically meaningful characteristic variables to participate in machine learning modeling, establishing a search combination algorithm, performing characteristic optimization, and finally obtaining a final result. A five-fold cross validation mode is adopted to evaluate the predictive ability of each model on HSI occurring after trauma, the model with the best performance is found out, finally, the guiding effect of model variables on clinical diagnosis is displayed through SHAP feature importance, and based on important variables of the first four models, an optimized logistic model and a column diagram are established to improve the clinical practicability of the model, so that the clinical diagnosis accuracy of the model is improved. And further model evaluation is carried out on the optimized logistic model by using a Calibration calibration curve and a DCA decision curve, so that the clinical effectiveness is improved.

The invention provides a public building low-carbon transformation optimization method and system, and the method comprises the steps: obtaining building information and historical data, building a reference model combining future climate and power grid carbon factors, and evaluating the energy-saving potential of each subsystem; candidate reconstruction measures are screened from the technology library according to the potential, and an effect matrix representing the collaborative or antagonistic effect between the measures is constructed; the full life cycle cost and the carbon emission reduction amount are taken as targets, a multi-target particle swarm algorithm is adopted to solve an optimal measure combination, the algorithm speed is updated, an effect matrix correction term is utilized to guide and search a high-collaboration combination, and a Pareto solution set is obtained; calculating neighborhood solution density of each solution in the solution set to set a scene number, and evaluating target value dispersion under a random scene to obtain a score; and in combination with the risk aversion coefficient, performing weighted summation on the normalized target value and the score to obtain a comprehensive evaluation value, and selecting an optimal solution as a scheme.

The invention provides an air route planning method for a civil aircraft flight management system. The air route planning method comprises the following steps: step 1, establishing a standard entry and departure program of an aircraft; step 2, establishing a limited waypoint of the aircraft; step 3, reading waypoint information; and 4, calculating an optimal route by adopting an ant colony and particle combination method according to all route point information read in the step 3. According to the method, the limitation conditions are set, the ant colony and particle swarm combinatorial algorithm is utilized, and the optimal route is calculated, so that the time of manually inputting the route by a pilot is shortened, the route planning efficiency is improved, a flight plan does not need to be compiled according to a chart, and the flexibility of route planning is greatly improved. By introducing the ant colony and particle swarm optimization combined algorithm, the route distance is shortest on the basis of ensuring that the route planned each time meets the limiting conditions, the flight path of the aircraft is reduced, and the operation cost is greatly saved.

The application provides a civil aircraft vertical flight path planning system and a planning method thereof, the planning system comprising an air traffic control center, a ground cloud service, an airborne installed EFB device, an airborne weather radar, an airborne information system, an interconnected information transmission and processing module, and an interconnected flight control system; the planning system and the planning method thereof adopt the interconnected flight control system to receive weather restrictions and air route air traffic control restrictions, and adopt an optimization model combined with an intelligent optimization algorithm to calculate a locally optimal vertical flight path or a globally optimal vertical flight path according to actual flight requirements, thereby greatly improving the flexibility of flight management vertical flight path planning and making it more in line with actual flight conditions. The planned vertical flight path meets the restriction conditions and achieves the shortest flight time, the highest fuel efficiency, or the most balanced cost, thereby greatly saving the actual operation cost.