2954 results about "Global optimal" patented technology

The present invention relates to a method for workforce scheduling in which workload and workload types vary during scheduling period. The method acquires agent and skill requirements for all periods and contact types; acquires the contact center information including agent skill groups, agent work groups, tour and shift scheduling rules, agent availability, objective criterion to be optimized and its parameters; develops a Mixed Integer Linear Programming (MILP) model for the scheduling environment; applied an optimization algorithm that uses the Branch and Bound algorithm with a Rounding Algorithm to improve performance; and locates a globally optimal or near optimal workforce schedule in total cost or paid time or agent satisfaction. Detailed schedules may be developed by assigning daily shifts to work patterns, and breaks scheduled to daily shifts.

An embodiment of the invention provides a method of managing a cluster of networked resources and resource groups using rule-based constraints. This method includes the step of building a globally optimal cluster configuration of the resources in accordance with the rule-based constraints and a current state of the resources, including identifying for each of the resources and resource groups an availability and quality of service, which are determined by dependencies among the resources and resource groups, resource equivalency, constraints on the resources and network policies. The method comprises the further steps of bringing the cluster of resources on-line in a systematic manner, given the current state of each of the resources and resource groups; and with the cluster of networked resources on-line, determining dynamic dependencies of and configuration infomration about the cluster of resources (i) statically at defined times and (ii) dynamically during cluster operation.

The invention discloses an ORB key frame closed-loop detection SLAM method capable of improving the consistency of the position and the pose of a robot. The ORB key frame closed-loop detection SLAM method comprises the following steps of, firstly, acquiring color information and depth information of the environment by adopting an RGB-D sensor, and extracting the image features by using the ORB features; then, estimating the position and the pose of the robot by an algorithm based on RANSAC-ICP interframe registration, and constructing an initial position and pose graph; and finally, constructing BoVW (bag of visual words) by extracting the ORB features in a Key Frame, carrying out similarity comparison on the current key frame and words in the BoVW to realize closed-loop key frame detection, adding constraint of the position and pose graph through key frame interframe registration detection, and obtaining the global optimal position and pose of the robot. The invention provides the ORB key frame closed-loop detection SLAM method with capability of improving the consistency of the position and the pose of the robot, higher constructing quality of an environmental map and high optimization efficiency.

Disclosed in the invention is an improved method of a RGB-D-based simultaneously localization and mapping (SLAM) algorithm. The method comprises two parts: a front-end part and a rear-end part. The front-end part is as follows: feature detection and descriptor extraction, feature matching, motion conversion estimation, and motion conversion optimization. And the rear-end part is as follows: a 6-D motion conversion relation initialization pose graph obtained by the front-end part is used for carrying out closed-loop detection to add a closed-loop constraint condition; a non-linear error function optimization method is used for carrying out pose graph optimization to obtain a global optimal camera pose and a camera motion track; and three-dimensional environment reconstruction is carried out. According to the invention, the feature detection and descriptor extraction are carried out by using an ORB method and feature points with illegal depth information are filtered; bidirectional feature matching is carried out by using a FLANN-based KNN method and a matching result is optimized by using homography matrix conversion; a precise inliners matching point pair is obtained by using an improved RANSAC motion conversion estimation method; and the speed and precision of point cloud registration are improved by using a GICP-based motion conversion optimization method.

Exemplary embodiments of the present disclosure relate generally to methods, computer-accessible medium and systems for assembling haplotype and / or genotype sequences of at least one genome, which can be based upon, e.g., consistent layouts of short sequence reads and long-range genome related data. For example, a processing arrangement can be configured to perform a procedure including, e.g., obtaining randomly located short sequence reads, using at least one score function in combination with constraints based on, e.g., the long range data, generating a layout of randomly located short sequence reads such that the layout is globally optimal with respect to the score function, obtained through searching coupled with score and constraint dependent pruning to determine the globally optimal layout substantially satisfying the constraints, generating a whole and / or a part of a genome wide haplotype sequence and / or genotype sequence, and converting a globally optimal layout into one or more consensus sequences.

Dynamical methods for obtaining the global optimal solution of general optimization problems having closed form or black box objective functions, including the steps of first finding, in a deterministic manner, one local optimal solution starting from an initial point, and then finding another local optimal solution starting from the previously found one until all the local optimal solutions starting from any initial point are found, and then finding from said points the global optimal solution.

The invention discloses an intelligent scheduling system for tail-end instant logistics. The intelligent scheduling system comprises an order receiving module, an order processing module, a deliveryman searching module, an order combination module, a merchant portrait module, a deliveryman portrait module, an order dispatching decision-making module, and a deliveryman examination module. On the basis of position information of a merchant and a user as well as positioning information generated by a deliveryman terminal APP, global optimal matching is carried out on an order and a deliveryman by considering the current position of the deliveryman, the order executed by the deliveryman, portrait image of the merchant and the deliveryman, and the requirement on allocation time by the user comprehensively and then an optimal deliveryman is determined finally to complete a delivery task. On the basis of the intelligent order dispatching way, optimal order distribution is carried out at a global angle to realize optimal utilization of the whole transport capacity; the need of instant logistics and the transport capacity supply can be balanced well; the logistics delivery efficiency can be improved; the logistics delivery cost can be lowered; and the service quality of the tail-end instant logistics can be improved.

The invention discloses a method for autonomously localizing robots on the basis of laser radar. The method includes randomly generating N particles to form particle swarms around initial locations ofthe robots, and updating the particle swarms according to robot real-time movement distances and real-time rotation angles measured by sensors of the robots at current operation moments of the robots; computing the superposition quantity of point cloud of the laser radar and obstacles of maps for each particle to use the superposition quantity as a score of the particle, computing weighted position and posture average values of the particle swarms by the aid of the score, which is used as a weight, of each particle and utilizing the weighted position and posture average values as AMCL (adaptive Monte Carlo localization) estimation positions and posture; utilizing the AMCL estimation positions and posture as initial values, acquiring scanned and matched positions and posture by the aid ofscanning and matching algorithms on the basis of Gauss-Newton iterative processes and utilizing the scanned and matched positions and posture as the optimal positions and posture of the robots at thecurrent operation moments; re-sampling the particle swarms by the aid of AMCL algorithms to ultimately obtain the global optimal positions and posture of the robots during operation. The global optimal positions and posture of the robots are used as localization results. The method has the advantage that the localization convergence rate can be greatly increased, and the localization precision andthe localization stability can be greatly enhanced.

The invention discloses a minimum equivalent fuel consumption-based hybrid electrical vehicle control method, which comprises the following steps of: acquiring a nominal equivalence factor offline; acquiring signals; identifying working conditions; performing adaptive regulation; and performing optimum control. Under the condition of meeting the requirement of dynamic property, the minimum equivalent fuel consumption-based hybrid electrical vehicle control method is adopted, adaptive regulation can be performed according to an actual working condition, and the electric quantity balance of a storage battery is ensured, so that the performance and service life of the storage battery are ensured. The nominal equivalence factor is acquired through simulation calculation in the offline state, and calculated quantity for real-time control of the whole vehicle is reduced. In addition, different from a global optimal control method in which a future vehicle running working condition is required to be known (the future vehicle running working condition is unpredictable actually), the method has high implementability; and by the method, the real-time optimal energy management decision can be provided, the fuel economy of the whole vehicle is further improved, and the emission is reduced.

The invention discloses a network text segmenting method based on the genetic algorithm, used for segmenting short network texts. The method comprises the following steps of: evaluating a Latent Dirichlet allocation (LDA) model corresponding to a corpus by using a Gibbs sampling method, inferring latent topic information using the model, representing texts by using the latent topic information; then transforming a text-segmenting process into a multi-target optimum process by using a parallel genetic algorithm, and calculating the coherency of segmented units, the divergence among the segmented units and fitness functions by using deeper semantic information; and carrying out the genetic iteration of the text segmenting process, and determining whether the segmenting process terminates based on the similarity among multi-iteration results or the upper limit of iterations to obtain the global optimal solution for segmenting the texts. Therefore, the invention improves the accuracy for segmenting the short network texts.

Packet communication networks for transmission to wireless subscriber devices utilize both wireline and wireless packet routing components. The routing elements of these two different types often implement different packet scheduling algorithms, typically a form of Weighted Fair Queuing (WFQ) in the wireline portion of the network and Proportional Fairness (PF) queuing in the wireless domain. To improve resource allocation and thus end to end quality of service for time sensitive communications, such as integrated multimedia services, the present disclosure suggests adding the notion of slack time into either one or both of the packet scheduling algorithms. By modifying one or more of these algorithms, e.g. to reorder or shuffle packets based on slack times, global optimal resource allocations are possible, at least in certain cases.

The invention discloses an inspection robot path planning method combining map grids with potential field method obstacle avoidance; the inspection robot path planning method comprises the following steps: 1, global grid method path planning: using the grid method to obtain the global optimal path from a start point to an object point; 2, moving to the object point: determining whether obstacles are encountered or not, moving to the object point is no obstacle is detected, planning a local obstacle avoidance path if an obstacle is detected until reaching the object point; 3, planning the local obstacle avoidance path, using the artificial potential field method with changeable parameters to carry out obstacle avoidance path planning, determining whether the object point is reached or not, returning to step 2 if not, and finishing the tour if the object point is reached. The inspection robot path planning method can solve the problems that the robot inspection path planning in the prior art is poor in efficiency, thus enlarging the robot inspection time.

The invention discloses a wind power plant parameter identification and dynamic equivalence method based on operation data, comprising the following steps of a) performing recognition on wind generation set control model parameters based on testing data, b) combining with operation data and choosing characteristic variables reflecting the wind generation set and the wind power plant under influence and utilizing the improved fuzzy K average value dynamic clustering algorithm to perform cluster division, c) performing network simplification and parameter optimizing to obtain a wind power plant dynamic equivalence model based on global optimal position mutation particle swarm algorithm, and d) under disturbance input, comparing the wind power dynamic equivalence model with the detailed model dynamic respond to verify the validity of the equivalence model. The wind field dynamic equivalence model constructed by the invention can accurately reflect the dynamic characteristics of grid-connection points of the wind plant and have important construction application values, and can be used in the analysis of the stability of the double-fed wind power plant access power system and provide theory support for the programming and operation scheduling of the wind power plant power system.

The present invention discloses a method and system for collaborative scheduling of production and transportation in supply chains based on improved particle swarm optimization. The method includes the following steps: 1. setting algorithm parameters; 2. randomly generating an initial population; 3. correcting codes; 4. calculating fitness values and updating the speed and the position of particles; 5. performing tournament selection; 6. performing crossover mutation; 7. updating the population; and 8. determining whether a termination condition is satisfied; if so, outputting a globally optimal solution; if not, returning to the step 3. In the present invention, an approximately optimal solution can be obtained in view of the collaborative scheduling problem of production and transportation considering distributed storage, so that the cost is reduced for supply chains and the service level of supply chains is enhanced.

The invention discloses an AGV (Automated Guided Vehicle) route planning method and system based on an ant colony algorithm and multi-intelligent agent Q learning, improving the global optimization ability, realizing a case that an AGV learns how to avoid an obstacle in the interaction process by introducing the multi-intelligent agent Q learning into a route planning research of the AGV, and canplay independence and learning capacity of the AGV better. The AGV route planning method and system is characterized in that according to a static environment, carrying out modeling on an AGV operation environment by utilizing a grid method, and setting an initial point and a target point; according to coordinates of the initial point and the target point of the AGV, generating a global optimal route by the ant colony algorithm; enabling the AGV to move towards the target point according to the global optimal route, and when detecting that a dynamic obstacle exists in a minimum distance, carrying out selection of an obstacle avoidance strategy by an environment state corresponding to the multi-intelligent agent Q learning so as to take a corresponding obstacle avoidance action, and after ending obstacle avoidance, returning to an original route to continuously move.

The invention provides a method and device for controlling multi-joint moving robot to avoid an obstacle. The method is characterized in that a vision guidance device and the infrared obstacle avoidance device are mutually coordinated to control the robot to move during the process that the robot moves from a starting point to a target point along a pre-planned global optimal route; when a vision system detects the obstacle in the preset distance, a robot base is stopped marching, the movement posture of each joint can be automatically adjusted by grade on the basis of a pre-constructed kinematic geometric model of each joint, and the joints can be swung, from a tail end performer to the base, within a feasible region of each joint, so as to avoid the obstacle by grade; a servo system can control the pose position of each joint and the chassis movement direction, so as to continuously control the robot to move toward the target point until the robot reaches the target point; the movement postures of each joint and the base can be synchronously adjusted during the infrared obstacle avoiding process, thereby avoiding subsequent repeated adjusting, and as a result, the obstacle avoiding efficiency of the multi-joint moving robot can be improved.

The present invention belongs to the technical field of digital manufacturing, and particularly relates to a three-dimensional measurement point cloud optimization registration method. The method comprises: obtaining the source point cloud and the target point cloud; performing denoising preprocessing on the three-dimensional measurement point cloud; using the Markov Monte Carlo-based simulated annealing registration algorithm to solve the global optimal registration transformation matrix; and finally, using the ICP registration method to iteratively complete precise registration. According tothe method provided by the present invention, the problem of convergence to the local optimal solution in the ICP registration method is solved, the global optimization solution of the transformationmatrix in the process of three-dimensional point cloud registration is realized, falling into the local optimum is avoided, the precision of three-dimensional point cloud registration is improved, and the method is superior to the traditional ICP registration; and parameter sampling is realized based on the Markov Monte Carlo method, the convergence speed of the algorithm is accelerated, the accuracy of point cloud registration is improved, the method has strong adaptability to the point cloud, and the algorithm has good robustness.

A method determines a global optimal solution of a system defined by a plurality of nonlinear equations by applying a metaheuristic method to cluster a plurality of search instances into at least one group, selecting a center point and a plurality of top points from the search instances in each group and applying a local method, starting from the center point and top points for each group, to find a local optimal solution for each group in a tier-by-tier manner. Then a TRUST-TECH methodology is applied to each local optimal solution to find a set of tier-1 local optimal solutions, and the TRUST-TECH methodology is applied to each tier-1 local optimal solution to find a set of tier-2 local optimal solutions. A best solution is identified among all the local optimal solutions as the global optimal solution. The heuristic method can be a particle swarm optimization method or a genetic algorithm method.

The invention provides a multi-neural network control planning method for a robot path in an intelligent environment. The method comprises the steps that 1 a global map three-dimensional coordinate system is constructed for the carrying area of a carrier robot to acquire a walkable area coordinate in the global map three-dimensional coordinate system; 2 a training sample set is acquired; 3 the global static path planning model of the carrier robot is constructed; and 4 starting and ending coordinates in a transportation task are input into the global static path planning model based on a fuzzy neural network to acquire the corresponding optimal planning path for the carrier robot. According to the invention, the global static path planning model and a local dynamic obstacle avoidance planning model are separately established; the nonlinear fitting property of the neural network is used to find the global optimal solution quickly; and the problem of falling into a local optimum in common path planning is avoided.

The invention provides a power distribution network fault positioning method based on improvement of a binary particle swarm algorithm, the conventional binary particle swarm algorithm is improved, and the method is applied to positioning of power distribution network faults. The method comprises following steps: firstly, determining parameters including the particle swarm scale and the maximum iteration frequency etc.; then forming an expectation function of a switch according to fault information of the switch, and constructing a fitness function of power distribution network fault positioning; initializing a particle swarm, setting particle positions, and setting the speed of the particles as 0; calculating the fitness values of the particles according to the fitness function, and setting an initial global extremum; updating an individual extremum and the initial global extremum; updating the speed and position of the particle swarm; and stopping calculation when reaching the maximum iteration frequency, and outputting the global optimal position of the particle swarm, namely the practical fault state of each feed line section of a target power distribution network. According to the method, the problem of premature convergence of the conventional method can be overcome, and the convergence and the stability of the algorithm can be further improved.

The invention belongs to the technical field of unmanned vehicle navigation, particularly relates to an unmanned vehicle path planning method based on an improved A * algorithm and deep reinforcementlearning. The method aims to give full play to the advantages of global optimization of global path planning and real-time obstacle avoidance of local planning, improve the rapid real-time performanceof an A * algorithm and the complex environment adaptability of a deep reinforcement learning algorithm, and rapidly plan a collision-free optimal path of an unmanned vehicle from a starting point toa target point. The planning method comprises the following steps: establishing an initialized grid cost map according to environmental information; planning a global path by using an improved A * algorithm; designing a sliding window based on the global path and the performance of the laser radar sensor, and taking the information detected by the window as the state input of the network; on thebasis of a deep reinforcement learning method, using an Actor-Critic architecture for designing a local planning network. According to the invention, knowledge and a data method are combined, an optimal path can be obtained through rapid planning, and the unmanned vehicle has higher autonomy.

The invention discloses a road detection method based on bimodal data fusion. The method comprises the following steps: transferring axes of laser radar three-dimensional points; obtaining a laser radar three-dimensional point set in a camera image range; setting a height threshold value, obtaining a subset of laser radar three-dimensional points of a barrier; obtaining a subset of laser radar three-dimensional points of a passable road area; obtaining color Gaussian mixture models of a non-road area and a passable road area; obtaining an area-of-interest of road detection on an image; structuring an energy function based on the Markov random field, calculating the minimum value of the energy function, and obtaining a global optimal image road detection result. By the adoption of the road detection method based on the bimodal data fusion, robust of complex environment is achieved, the detection result is not influenced by shadows of road surface, fine barriers in an environment sensed by a sensor can be distinguished from the passable road area; an area without laser radar data returning and the non-road can be judged, and the road detection method based on the bimodal data fusion is suitable for fields such as autonomous vehicle guidance.

The invention discloses application of deep learning based on fuzzy processing in fault diagnosis of hydraulic equipment. The application comprises the following steps of: (1) introducing a time label and fuzzy weight to pre-process operation monitoring data of the hydraulic equipment, and dividing the operation monitoring data into a training data set and a test data set; (2) taking the training data set as an input vector of a sparse self-coding network to carry out non-supervision pre-training; (3) taking label data and no-label data as an input vector training Softmax classifier of a Softmax classifier; (4) utilizing a BP algorithm to carry out fine adjustment on deep learning network parameters; and (5) carrying out intelligent diagnosis on a fault condition. According to the application disclosed by the invention, firstly, a method of introducing the time label and fuzzy weight is adopted to carry out pre-processing on data; then, sparse self-coding is used to complete high-level feature extraction of sample data, and the Softmax classifier is used to carry out classifying diagnosis on an equipment fault state to construct an ICM model; and finally, the BP algorithm is utilized to carry out fine adjustment on global optimal parameters of the whole network, so that intelligent diagnosis on the fault state is realized.

The invention discloses a PID controller parameter setting algorithm based on an improved PSO (particle swarm optimization) algorithm, and the algorithm comprises the following steps: 1, initializing the algorithm parameters; 2, switching to an iterative loop, and carrying out the updating of the position and speed of each particle; 3, randomly searching a new position in the neighborhood of a current position; 4, calculating the adaptability difference between two positions, and judging whether to accept the new position or not through a simulated annealing mechanism when the adaptability of the new position is inferior to the adaptability of an original position but is superior to the adaptability of a global optimal position; 5, updating the global optimal position of a population, carrying out the natural selection operation, carrying out the arrangement of all particles according to the adaptability values, and employing the information of a part of better particles to replace the information of the other half particles; 6, judging whether to stop the iteration or not; 7, outputting PID controller parameters or executing step 2 again. The method can achieve the automatic setting of control parameters, irons out a defect that a conventional PSO algorithm is very liable to be caught in local optimization, achieves the complementation of the simulated annealing operation and a natural selection strategy, improves the convergence precision of the algorithm under the condition that the number of convergence times of the algorithm is guaranteed, is higher in robustness and precision, and enables the PID controller to generate a more excellent control effect.

The invention discloses a combined positioning method for moving multi-station passive time difference and frequency difference, wherein the method belongs to the field of passive positioning technology. The method comprises the following steps of establishing a time different positioning model; establishing a frequency different positioning model; constructing a time difference and frequency difference observation matrix epsilicon1, and designing a fitness function; initiating a group and various parameters; evaluating the fitness function value of each particle; sequencing all particles; when the algorithm satisfies a terminating condition, outputting a current global optimal value; reconstructing the time difference and frequency difference matrix epsilicon2; obtaining a weighted least square solution theta2 and a covariance matrix cov(theta2); and calculating position and speed of a radiation source. The combined positioning method has advantages of performing optimal value solving on the fitness function which is obtained from the time difference and frequency difference observation matrix, combining a particle swarm optimization algorithm with a least square algorithm, and realizing high-precision target position on the condition of four base stations, and furthermore calculating speed information of the target. The combined positioning method can realize high-precision estimation to the position of the radiation source and is not limited by a station site layout. Furthermore relatively high positioning estimation precision is realized.

The invention relates to a method suitable for multi-view-angle automatic global registration of ground laser point cloud data. The method involves two key modules: a module for extracting semantic feature points and a module for feature matching. The method comprises: step 1, extracting the semantic feature points: obtaining the semantic feature points in a series of modes of data slicing, distance clustering, geometric element fitting and the like; step 2, matching the semantic feature points: matching the semantic feature points by constructing a triangular geometric constraint condition and a semantic constraint condition, and removing error matching in a geometric consistency clustering mode; and finally, constructing a weighted undirected graph by taking a reciprocal of a feature point number as a weight, and finally obtaining global registration parameters of all stations by taking a minimum spanning tree of the weighted undirected graph as a registration path, thereby realizing global optimal registration. According to the invention, the method suitable for multi-view-angle automatic global registration of the ground laser point cloud data is constructed; the method can effectively resist influences of noise, point density and coverage; and the method improves the laser scanning operation efficiency, thereby having very high practical values.

Disclosed is an improved technique for training a support vector machine using a distributed architecture. A training data set is divided into subsets, and the subsets are optimized in a first level of optimizations, with each optimization generating a support vector set. The support vector sets output from the first level optimizations are then combined and used as input to a second level of optimizations. This hierarchical processing continues for multiple levels, with the output of each prior level being fed into the next level of optimizations. In order to guarantee a global optimal solution, a final set of support vectors from a final level of optimization processing may be fed back into the first level of the optimization cascade so that the results may be processed along with each of the training data subsets. This feedback may continue in multiple iterations until the same final support vector set is generated during two sequential iterations through the cascade, thereby guaranteeing that the solution has converged to the global optimal solution. In various embodiments, various combinations of inputs may be used by the various optimizations. The individual optimizations may be processed in parallel.

The invention discloses a power system reactive power optimization method based on an individual optimal position self-adaptive variation disturbance particle swarm algorithm. The power system reactive power optimization method comprises the following steps: establishing a power system inactive optimization model; inputting power grid parameters to form an initial population, and calculating a grid damage value corresponding to all particles of the population; recording an individual optimal position and an individual optimal grid damage value as well as a global optimal position and a global optimal grid damage value of the initial population; updating the speeds and the positions of the particles; calculating a grid damage value corresponding to each particle of the population and updating the individual optimal position and the individual optimal grid damage value as well as the global optimal position and the global optimal grid damage value of the population; and judging whether to carry out the variation according to a self-adaptive criterion. The method is rapid in convergence rate, high in calculation precision and good in stability; the problem of inactive optimization of the power system can be solved effectively; and the method can be used for improving the electricity transmission efficiency of the power system and reducing the network loss configuration real-time operation control in the power system.

The present invention discloses a multi-parameter multi-object chaotic particle swarm parameter optimization method. The method comprises the steps of (1) determining a target function and a parameter to be optimized, (2) initializing an algorithm, (3) calculating the target function corresponding to each individual in a population, (4) updating an individual history optimal solution, (5) updating a particle velocity and position, (6) updating a global optimal solution set, (7) updating a global optimal solution, and (8) carrying out result judgment. Compared with a common random initialization method and an existing chaotic logistic mapping particle swarm initialization method, according to the method of the invention, the performance of global optimization is improved and the stability is good, compared with a common multi-object weighted optimization method, the Pareto optimal solution technology is employed by the method, and the problem of difficult weight selection in the multi-object method is solved.

The invention discloses a high-voltage circuit breaker fault diagnosis method based on an improved BP neural network. The method specifically comprises the steps of classifying collected samples, withclass tags, of a high-voltage circuit breaker into training samples and test samples, then building a BP neural network model based on a breeding algorithm and a particle swarm optimization algorithm, and after the training samples are used for performing training, performing decoding to generate new connection weight and threshold value; performing control by applying an iteration controller, enabling the two algorithms to carry out information interaction every multiple generations, and obtaining an optimal global parameter, wherein contents of the information interaction is relevant information of an optimal particle seed; and decoding an obtained global optimal solution, replacing all weight value and threshold value parameters of an original BP neural network, building an optimized high-voltage circuit breaker fault model, performing fault classification on the test samples, and outputting a result. According to the method, the BA and PSO algorithms are used for replacing an error back propagation-based network learning process to optimize the connection weight and the threshold value of the BP neural network, so that the fault diagnosis precision is effectively improved.