97 results about "Firefly algorithm" patented technology

The invention discloses a slope deformation monitoring and dynamic early warning method and system based on multi-sensor data, and relates to the technical field of slope monitoring, and the method comprises the steps: collecting multi-source sensor data by using pre-deployed multi-class sensors, constructing graph structure data according to the sensor distribution and the pre-processed multi-source sensor data, and carrying out the graph structure data; a graph convolutional network is used for modeling, and a slope deformation monitoring model is constructed; introducing a clustering federation learning strategy to carry out joint training on the slope deformation monitoring models of the plurality of sites, and carrying out risk grade division by using the trained slope deformation monitoring models; key influence factors of landslide disasters are extracted, an improved firefly algorithm is introduced to dynamically optimize an early warning threshold value, the optimized early warning threshold value and the current risk level are used for judgment, and early warning information is generated. According to the invention, the reliability of monitoring and the timeliness of early warning are improved through multi-source data fusion and intelligent analysis, and the crossing of slope deformation monitoring from single-point static state to networked intelligence is realized.

The invention provides a rolling quality parameter uncertainty quantification method based on mixed entropy-fuzzy clustering. The method comprises the following steps: S1, multi-source data fusion: integrating rolling compaction parameters, meteorological data and real-time monitoring data in an engineering construction process, and constructing a multi-dimensional feature matrix; s2, calculating mixed entropy, namely quantifying the randomness and fuzziness of parameter distribution in combination with information entropy and fuzzy entropy; s3, performing dynamic fuzzy clustering, namely, optimizing a clustering center based on an improved firefly algorithm, and dividing parameter uncertainty levels; step S4, uncertainty contribution degree analysis: quantifying the influence weight of each parameter on the rolling quality through an entropy weight-grey correlation method; according to the method, the information entropy and the fuzzy entropy are fused, and dynamic clustering and an intelligent optimization algorithm are combined, so that precise quantification and hierarchical management and control of the rolling parameter uncertainty are realized.

The invention relates to the technical field of automobile charging station load systems, in particular to a new energy automobile charging station dynamic load optimization integration system and method based on multi-source data collaboration and elastic compensation. According to the system, charging pile power, meteorological data and user behavior information are fused in real time through a multi-source time sequence data set construction module, an LSTM neural network optimized by an improved sparrow algorithm is adopted to predict the remaining power capacity of a charging station, and Bootstrap resampling is combined to generate a confidence interval to realize safety boundary control; the self-adaptive firefly algorithm dynamically adjusts the charging pile power, establishes a multi-dimensional priority queue including SOC emergency degree, compensation willingness and social value, and guides users to charge in a peak shifting manner; the system comprises a 5G communication gateway, an IGBT power control module and a three-level early warning mechanism, and millisecond-level flexible adjustment of charging power is realized. The utilization rate of the transformer is improved to 91%, the peak-valley load ratio is reduced to 1.7: 1, the user waiting time is shortened by 63.5%, and a dynamic load management system of power grid-station-user collaborative optimization is formed.

The invention discloses a multi-parameter identification method for a valve-controlled cylinder electro-hydraulic servo system, and belongs to the field of servo technology control. The method comprises the following steps: firstly, carrying out mathematical modeling according to components and a working principle of the valve-controlled cylinder electro-hydraulic servo system to obtain a system model and to-be-identified parameters; secondly, an improved multi-strategy firefly algorithm is provided, the randomness and uniformity of an initial solution are enhanced through an improved Chebyshev polynomial, the global search capability of the algorithm is improved, an updating algorithm is introduced to modify a step length factor of the firefly algorithm, and balance between local search and global exploration is achieved; finally, parameters of the established model are identified through an improved algorithm, simulation and experimental analysis are conducted, and according to the result, the accuracy of the model can be effectively improved, the robustness of the model can be improved, and reliable theoretical and practical support is provided for actual engineering application of the high-precision electro-hydraulic servo system.

The invention provides a cooperative scheduling method for an electric medical waste transfer vehicle and a mobile battery exchange vehicle, and relates to the field of scheduling optimization, and the method comprises the steps: obtaining client data, and initializing algorithm parameters; constructing an initial feasible solution, calculating the total cost and the infection risk of the path of each firefly, and selecting the firefly path with the minimum objective function value as a current global optimal solution; selecting mutation operation to generate a neighborhood solution, calculating a corresponding target function value, and comparing the target function value with the current globally optimal solution to update the globally optimal solution; and updating the position of each firefly in the population according to the attraction mechanism of the firefly algorithm, performing adjustment and feasibility test on the solution in combination with mutation operation in the position updating process, and performing iterative optimization until termination. According to the method, the firefly algorithm and the variable neighborhood search algorithm are combined to realize efficient path optimization and charging scheduling, so that balance between total cost minimization and infection risk minimization is achieved, the medical waste transfer efficiency is improved, and the operation cost is reduced.

The invention relates to an MPPT (Maximum Power Point Tracking) method, system and equipment based on distributed photovoltaic and a medium, and relates to the technical field of distributed photovoltaic power generation, and the method comprises the following steps: preprocessing photovoltaic array data, and obtaining irradiance, temperature and MPP voltage data sets; determining the optimal number of hidden layer nodes of the ElmanNN by adopting K-fold cross validation and RMSE evaluation, and dividing a data set into a training set, a validation set and a test set; inputting the training set to firefly algorithm global search and ant colony optimization algorithm local optimization, and defining a stable solution as an FA-EAS optimal parameter after convergence; updating an ElmanNN weight threshold based on the optimal parameter, and deploying a training model to carry out MPP voltage online prediction; and the difference value of the predicted voltage and the reference voltage is input into a PID controller, the control quantity is calculated through incremental PID, a PWM signal is generated to control the duty ratio of the Boost converter, and maximum power point tracking is achieved. According to the invention, the tracking speed, stability and success rate of MPPT can be improved.

The invention discloses an unmanned aerial vehicle path deception jamming method based on an intelligent optimization algorithm, belongs to the technical field of unmanned aerial vehicle path deception jamming, is used for unmanned aerial vehicle path deception jamming, and comprises the steps of establishing an unmanned aerial vehicle kinetic equation and a kinematics equation, and obtaining an expected flight trajectory of an unmanned aerial vehicle; a particle filtering method based on firefly algorithm optimization is introduced, and the state of the unmanned aerial vehicle is tracked and estimated; an improved particle swarm optimization algorithm is introduced to calculate the public delay amount in the forwarding interference, and the positioning information of the unmanned aerial vehicle is interfered and guided. Compared with the prior art, the real flight process and maneuvering change of the unmanned aerial vehicle are simulated, and the attitude change and dynamic response of the unmanned aerial vehicle are reflected; the problems of particle degradation and sample depletion are relieved, and the tracking stability and precision under noisy observation are improved; the deception positioning precision and the system robustness are improved, and the overall deception jamming effect is enhanced; and a technical support is provided for improving the deception jamming capability of a tail end defense system.

The invention discloses a load flow calculation method and device based on a hybrid wing optimization algorithm, and belongs to the technical field of power system operation and maintenance, and the method comprises the steps: employing an improved firefly algorithm to combine with k-means clustering to achieve power data cleaning and noise reduction; secondly, constructing a mixed rattan model, and capturing the output data correlation of photovoltaic power generation and wind power generation through rattan structure decomposition and a connection function; and finally, designing a hybrid wing optimization algorithm, and solving a power flow optimization problem through guidance of a leader and a Cauchy variation strategy. According to the method, the complex dependency relationship in power flow calculation of the power system can be effectively processed through the combination of the hybrid rattan model and the hybrid wing algorithm, the calculation precision and efficiency are remarkably improved, and the adaptability to a complex power network is enhanced.

The invention provides an error correction method suitable for a three-component magnetic sensor, and the method comprises the steps: building a comprehensive error model of a non-orthogonal error, a sensitivity error and a zero offset error, and solving an error parameter through an intelligent optimization strategy fusing a particle swarm optimization algorithm and a firefly algorithm, thereby achieving the error correction of the three-component magnetic sensor. The method specifically comprises the steps of using a magnetometer to synchronously measure a geomagnetic field module value as a reference standard, combining collected three-component magnetic field data to construct a fitness function, searching an optimal error parameter set by using a particle swarm optimization and firefly fusion algorithm, and compensating the magnetic field data; according to the method, an intelligent optimization strategy based on particle swarm optimization and firefly algorithm fusion is adopted, the magnetic field measurement precision can be effectively improved, and high-precision solving of error parameters and accurate compensation of magnetic field data are achieved.

The invention discloses a manufacturing process quality diagnosis method based on an adaptive multivariate control chart. The method comprises the following steps: step 1, constructing an adaptive multivariate exponential weighted moving average control chart; and step 2, constructing a fuzzy support vector machine diagnosis model of firefly algorithm collaborative optimization, and using the model to complete manufacturing process quality diagnosis. According to the method, normal fluctuation and abnormal fluctuation areas in the manufacturing process can be identified, and accurate tracing of abnormal modes is realized, so that quality diagnosis of the manufacturing process is completed.

The invention relates to the technical field of state prediction, in particular to an electric energy meter battery life prediction method for optimizing XGBoost through an improved firefly algorithm, and the method comprises the steps: collecting the temperature T, the voltage V and the use frequency F of an electric energy meter and the service life L of a battery, carrying out the normalization processing of collected data, dividing a data set into a training set and a test set, and carrying out the prediction of the service life of the electric energy meter. The method comprises the following steps: using a minimum square error (MSE) as a target function to evaluate the performance of a model, initializing firefly algorithm parameters, iteratively optimizing XGBoost, after executing all iterations, selecting the position xbest of a firefly with the optimal fitness as an optimal hyper-parameter combination, training a final XGBoost regression model by using the optimal hyper-parameter combination, and evaluating the performance of the model on a test set. Calculating MSE (mean square error); by predicting the remaining life of the battery, the battery can be replaced before failure, the situation of loss of a power-off reading is avoided, the labor cost is reduced, and the metering, operation and maintenance efficiency is improved.

The invention discloses a charging pile abnormity identification method based on deep learning. The method comprises the following steps: S1, obtaining operation data of a charging pile for preprocessing; s2, based on the preprocessed data, using a deep learning algorithm to construct a charging pile abnormity identification model; s3, adopting a firefly algorithm to optimize hyper-parameters of the model; s4, adjusting a model structure based on the optimized hyper-parameter; s5, collecting data of the charging pile in real time, inputting the data into the optimized model for abnormal state recognition, and generating abnormal alarm information; s6, according to the abnormal alarm information, automatically triggering an alarm and feeding back the alarm to maintenance personnel for processing; and S7, continuously collecting new charging pile data, and performing incremental learning and updating by using the optimized model. According to the invention, efficient and accurate identification of charging pile anomaly detection is realized, the fault processing speed and the system stability are improved, and the method is widely applied to charging pile management and maintenance.

The invention specifically discloses a compliance control method and device for a power transmission tower operation and maintenance robot and a medium, and the method comprises the steps: determining an impedance control model of a robot impedance controller, carrying out the adaptive optimization of impedance control parameters based on an improved firefly algorithm, and enabling the improved firefly algorithm to be based on a standard firefly algorithm, and a self-adaptive step length factor is adopted for fusion, meanwhile, an improved algorithm of an annealing mechanism is introduced, and finally, the robot is controlled based on optimized parameters. The dynamic response characteristic of the mechanical arm is continuously tracked, the improved firefly algorithm is used for updating impedance parameter configuration in real time, the improved firefly algorithm improves the global search capability and the convergence speed, the optimal control effect is achieved, the adaptive capacity of the system to diversified operation scenes is improved, and the system performance is improved. A parameter optimization strategy based on real-time data analysis successfully overcomes the adaptability problem caused by parameter solidification in conventional impedance control, and the stability and safety of the power transmission tower operation and maintenance robot in the movement process are improved.

This invention provides a pipeline leak location method based on tensor completion, comprising: collecting leakage vibration data of a leaking pipeline using wireless accelerometers, wherein the leakage vibration data includes data sampled by N wireless accelerometers over M time periods; constructing a tensor completion model using a truncated tensor weighted norm algorithm, and constructing an optimal three-dimensional tensor structure using the firefly algorithm based on the leakage vibration data of the leaking pipeline and the tensor completion model; inputting the optimal three-dimensional tensor structure into the tensor completion model for completion; and calculating the leakage location of the leaking pipeline based on the completed three-dimensional tensor. This invention utilizes a truncated tensor weighted norm to construct a tensor completion model, which efficiently preserves effective information in the missing data, improves the tensor completion accuracy, ensures effective recovery of effective feature information from the pipeline leak data, and improves location accuracy.

The invention provides an unmanned aerial vehicle countering decision control method based on multi-target identification distribution, relates to the technical field of unmanned aerial vehicle countering, and solves the limitation problems of low detection precision, unstable tracking, rigid task distribution and the like in the existing unmanned aerial vehicle countering technology. The method comprises the steps that firstly, an RF-DETR model is used for detecting and recognizing all target unmanned aerial vehicles invading a preset airspace, and initial parameters of targets are obtained; predicting and tracking a target trajectory by using a DeepSORT algorithm, generating dynamic labeling information with a unique ID for each target, and maintaining a tracking state; dynamic environment parameters are obtained, the threat degree of each target is corrected according to the dynamic environment parameters, and a countering task corresponding to each target is distributed to at least one countering unmanned aerial vehicle through an adaptive firefly algorithm; and according to the distribution result, applying a differential countering strategy to each target, and monitoring a countering effect in real time. According to the invention, efficient, rapid and highly intelligent unmanned aerial vehicle countering decision can be realized, and countering tasks can be assisted in real time.

The invention provides a sustainable earthwork optimization and allocation method based on DC-FACO, and relates to the technical field of optimization and scheduling. The method comprises the following steps: collecting site construction data of a navigation channel project, and constructing a multi-dimensional data matrix based on the site construction data; constructing a plurality of constraint conditions of earth-rock deployment based on earth-rock deployment logic and engineering characteristics of the navigation channel engineering, and constructing a collaborative optimization model based on the plurality of constraint conditions; and the collaborative optimization model is optimized based on a sustainable earthwork allocation model optimization mode of DC-FACO. According to the method, a core concept of sustainable construction can be met by constructing an economical efficiency and ecological benefit collaborative optimization model, a two-stage hybrid optimization framework is adopted, the global optimization ability is enhanced by improving an ant colony algorithm and fusing a dynamic pheromone updating mechanism and a firefly algorithm, and collaborative optimization of the global search ability and stability is achieved.

The invention discloses a data-driven production line layout intelligent optimization and reconstruction method, and relates to the field of intelligent manufacturing engineering. According to the method, the cuckoo search algorithm, the group collaborative search mechanism and the firefly algorithm are fused, and intelligent optimization and dynamic reconstruction of the production line layout are realized. According to the invention, the stability of layout optimization and the performability of the scheme can be improved.

The application discloses a network intrusion detection method and system, electronic equipment and a storage medium. The method inputs to-be-detected data into a plurality of trained classifiers to perform network intrusion detection, and obtains an intrusion detection result output by each trained classifier. A firefly algorithm is used to perform firefly position optimization on each first firefly population to obtain a target firefly individual. The target firefly individuals of each first firefly population are combined to form a new population, and a target firefly individual meeting a target condition in the new population is found out. The target firefly individual in the new population is added to each first firefly population as a second firefly population for next iteration until the firefly algorithm reaches a maximum iteration number, and the position of the target firefly individual is obtained. According to a plurality of weight coefficients and the intrusion detection result output by each trained classifier, a final intrusion detection result is calculated. The application can improve the accuracy of network intrusion detection.

Disclosed is a shield tail gap image two-dimensional Otsu threshold segmentation method based on an improved firefly algorithm, which comprises the following steps: generating a population randomly in the gray scale [0, 255] range of a pipe segment image; obtaining the optimal two-dimensional firefly position in the population through iteration, which comprises the following steps: calculating the maximum brightness of each firefly in the population; sorting the maximum brightness of the fireflies in the population; for each firefly, forming a local colony with several fireflies whose brightness is lower than that of the firefly; performing an attraction operation between the fireflies in the local colony; updating the position of the firefly, and introducing an attraction force weight to strengthen the connection between the local colonies when updating the position; updating the maximum brightness of the firefly according to the position of the firefly after movement; and outputting the optimal two-dimensional firefly position after multiple iterations, so as to perform threshold segmentation on the pipe segment gray scale image.

The application discloses a kind of gas boiler main steam temperature self-disturbance decoupling control methods, comprising: signal detection device measures various signal data involved in the present application, then data is processed;Using the data after processing, the system model of double-input double-output is established, and the system model is identified;The system model after identification is decoupled, and the system is decoupled into two single-input single-output systems;For system, design linear self-disturbance controller to realize boiler main steam temperature stable control;Firefly algorithm is used to optimize linear self-disturbance controller parameter, and the control quality of main steam temperature control system is improved, the present application is aimed at the problems, such as nonlinearity, multiple disturbance and the like existing in the process of gas power generation boiler main steam temperature control, adopts the control strategy that linear self-disturbance control and decoupling control are combined, and the mutual coupling action between furnace gas flow and low-temperature superheater, desuperheating water flow and high-temperature superheater outlet temperature is decoupled and eliminated using Gauss elimination method.

The invention provides a firefly algorithm-based mobile node path planning method in the Internet of Things, and the main research content is to balance the energy consumption of each mobile sensor node so as to prolong the life cycle of the network. Since the mobile sensor nodes cannot be charged, in order to support certain applications sensitive to time, a plurality of mobile sensors are used for collecting information of each node, so that the nodes complete information collection within specified time. The method mainly comprises the following steps of: (1) dividing a wireless sensor network area into a plurality of square grids according to a certain rule, and describing the structure of the whole network by using an incomplete graph model; and (2) according to the requirement of time sensitivity, the appropriate number of the mobile sensor nodes is set, so that the mobile sensor nodes can effectively complete data collection work within specified time. And (3) in order to balance the energy consumption of each mobile sensor, planning a reasonable data collection route for the mobile sensors by adopting multi-mobile sensor node path planning of a firefly algorithm.

The invention discloses an electric agricultural machine operation scheduling method, and belongs to the technical field of intelligent agriculture and agricultural machine automatic scheduling. In order to solve the problems of difficult scheduling, high operation cost, low electric quantity utilization rate and unreasonable path planning caused by electric quantity limitation in multi-field continuous operation of electric agricultural machinery, the method comprises the following steps: constructing an electric agricultural machinery operation scheduling model which comprises a target function and constraint conditions, wherein the objective function is total scheduling cost minimization and electric quantity utilization rate maximization, and the constraint conditions comprise path constraint, electric quantity constraint, task allocation constraint and cost constraint; solving the scheduling model based on a firefly algorithm to obtain an optimal operation path and a scheduling scheme of the electric agricultural machinery; and outputting the optimal path and the corresponding target function value. According to the invention, various kinds of electric agricultural equipment in a large-scale farm can operate in a multi-field continuous operation scene.

The invention discloses a Bayesian network structure learning method based on an improved MMHC algorithm, and relates to the technical field of Bayesian networks, the MMPC algorithm obtains a data set, determines a father-child node set of each variable through a conditional independence test and correlation judgment, and obtains an undirected graph; converting the undirected graph into a directed graph; performing random operation on the directed graphs to obtain a series of directed graphs and an initial population of a firefly algorithm; the fitness value of each firefly in the population is calculated, and the positions of the fireflies are updated; performing local optimization operation on the fireflies after position updating; and after multiple iterations, selecting the firefly with the highest fitness value in the population as a final Bayesian network structure. The improvement measures of the invention help to enhance the overall performance of the algorithm.

The present application discloses a method for generating an operation and maintenance strategy for a power transformer and a related device. The method comprises: respectively obtaining status data of different components of the power transformer and basic information of the transformer; extracting comprehensive data information of the power transformer based on the status data and basic information of the transformer, and constructing a two-dimensional image training data set based on the comprehensive data information and time series; using the two-dimensional image training data set to train a preset convolutional neural network model to obtain an optimized convolutional neural network model, wherein the optimized model parameters of the preset convolutional neural network model are obtained by optimization training based on the artificial fish swarm-firefly algorithm; inputting the currently obtained real-time comprehensive data information into the optimized convolutional neural network model to perform operation and maintenance strategy analysis to obtain an optimized operation and maintenance strategy. The present application can solve the technical problem that the existing technology cannot design an operation and maintenance strategy based on the health status of the components of the power transformer, resulting in the actual operation and maintenance strategy lacking pertinence and having poor effect.

The application discloses a garden path planning method based on an improved firefly algorithm, and comprises the following steps: obtaining a garden landscape design drawing, extracting spatial coordinate information of garden path nodes and road sections, and constructing a garden path network topology model; designing a firefly individual coding scheme, coding the garden path node coordinates and the topological connection relationship in the network topology model, and establishing a mapping relationship between the position of the firefly individual and the garden path spatial layout; according to the garden constraint conditions, the improved firefly algorithm is used to solve the garden path layout optimization; when the algorithm converges or reaches the preset maximum iteration number, the garden path layout scheme corresponding to the current optimal firefly individual is output. The application further discloses a garden path planning device, equipment and medium based on the improved firefly algorithm. The application can generate an optimized garden path layout scheme under the constraint conditions of terrain, vegetation, landscape partition and the like, and improve the garden landscape design efficiency and quality.

The present invention discloses a static vehicle path planning method based on the firefly algorithm. The method first discretizes the firefly algorithm (Glowworm Swarm Optimization, GSO), and by simulating the ant colony algorithm, converts the carriers of fluorescein from fireflies to edges, and then uses the fluorescein value and weight value on the edge to calculate the probability of the vehicle selecting the next node, thereby forming an access path. At the same time, considering that a large computational cost will be incurred when the problem scale is too large, the patent of the present invention redefines the neighborhood range and neighborhood set in the firefly algorithm. Through the method of the present invention, the solution effect of the vehicle path planning problem can be effectively improved, and the distribution cost in the logistics distribution process can be reduced, which has very important practical significance for vehicle path planning.

This invention discloses a method, apparatus, and storage medium for sub-pixel edge detection of battery cell images. The method includes: acquiring a preprocessed battery cell image; edge localization processing based on the Canny operator to obtain pixel-level edge point images; obtaining an optimal threshold using a maximum entropy multi-threshold segmentation algorithm based on the Firefly algorithm; calculating Zernike parameters for the pixel-level edge points using a Zernike moment sub-pixel edge detection algorithm; separating contour edge points, fine grid edge points, and main grid edge points based on the Zernike parameters and the optimal threshold; and performing least-squares fitting processing on these points to obtain the contour line, fine grid edge line, and main grid edge line of the battery cell. This invention, through the Zernike moment sub-pixel edge detection algorithm, reduces the edge detection accuracy to within one pixel and minimizes the impact of noise on detection accuracy.

The present application relates to the field of water pollution control and treatment, in particular to an ecological filter rural water purification system, which comprises a data acquisition module, an optimal state feedback module, a dynamic modeling module and an optimal control parameter output module. The data acquisition module collects water quality parameters through multiple sensors, generates water quality time series data through synchronization, anomaly identification and distortion data reconstruction, and simultaneously collects and standardizes structural parameters; the optimal state feedback module obtains relevant indexes based on the fuzzy PID algorithm, and then outputs them through firefly algorithm optimization; the dynamic modeling module respectively constructs ammonia nitrogen degradation models in the aerobic zone and COD degradation models in the anaerobic zone, correlates the two zones by hydraulic retention time, and incorporates environmental disturbance correction models; the optimal control parameter output module outputs control parameter intervals through a decision tree, and particle swarm optimization algorithm is used to search for optimal parameters in the intervals and output them; the system can efficiently purify rural water sources and provide precise control basis for the water purification process.

The invention discloses a spanning frame structure size optimization method and system based on a firefly algorithm, and relates to the technical field of electric power engineering construction, and the method comprises the steps: firstly building a parameterized finite element model, implementing normalized hierarchical loading, obtaining a tangent stiffness matrix evolved along with a load, calculating the modal participation degree of a component, and constructing a dynamic participation degree track; and according to the quantitative trajectory smoothing index, the modal dominance and the key component suppression index, constructing a brightness function with coupled rigidity and trajectory features. The firefly attraction degree is corrected by means of trajectory similarity based on modal energy fingerprints, and nonlinear search is executed through a characteristic resonance mechanism. The method solves the problem that traditional static optimization neglects geometric nonlinear evolution to cause modal abrupt change, and the dynamic stability and evolution robustness of the spanning frame in the full stress process are remarkably improved while the structural light weight is achieved.

The invention belongs to the technical field of feature selection, and discloses a feature selection method based on an improved firefly algorithm and a software defect prediction system. Carrying out complexity analysis on the MSAFA; and feature selection based on MSAFA. The invention provides an improved firefly algorithm variant, the variant adopts a simulated annealing (SA) algorithm to escape local traps, and a plurality of groups of strategies are utilized to enhance the global search capability of a firefly algorithm. When a database has the problems of class imbalance and high dimension, the performance of a space software defect prediction (SDP) model constructed by a basic classification algorithm is weak. The proposed firefly algorithm variant significantly improves the performance of the firefly algorithm, and applies the firefly algorithm variant to the SDP model to reduce redundant features and improve the efficiency of the SDP model.