237 results about "Damage analysis" patented technology

A solid structure deformation and damage analysis method based on a quasi-bond finite element method comprises: carrying out geometric modeling on a target structure body, and distribution and subdivision to generate a grid of a traditional finite element method; dividing the target structure body into a finite element region and a quasi-bond region, and calculating a finite element region system stiffness matrix and a quasi-bond region system stiffness matrix to obtain an overall stiffness matrix of the target structure body; setting a boundary condition for the target structure body, applying an external load, and calculating a system force matrix under current load and boundary state; and judging a quasi-bond breakage condition according to a node trial displacement, then calculating a node displacement of the structure body and an equivalent damage parameter at each node, and outputting cloud charts of a displacement field and an equivalent damage field.

The invention discloses a rotor surface magnetic field characteristic real-time monitoring and damage assessment system and method, and relates to the technical field of damage assessment. According to the method, a rotor surface magnetic field is monitored in real time under different rotating speed conditions, detailed magnetic field change data information is collected, the monitoring means can dynamically capture the magnetic field fluctuation condition, and the damage assessment accuracy is improved. According to the method, the damage prediction model is constructed by using the deep learning technology, the relevance between the damage prediction model and the rotating speed of the rotor is analyzed, early detection and classified evaluation of the unbalance condition are ensured, accurate data support is provided for further damage analysis, and accurate evaluation of the surface damage of the rotor is realized by using the deep learning technology to construct the damage prediction model and combining the unbalance type and the magnetic field change data. Meanwhile, the damage evaluation index is subjected to linear normalization processing, the influence between different data dimensions can be eliminated, and the evaluation result is more stable and reliable. And whether the damage state of the rotor surface is abnormal or not is judged in time by comparing and analyzing the damage evaluation index and a threshold value.

The invention discloses a fan blade state monitoring method based on multi-sensor fusion, relates to the technical field of wind power, and is suitable for wind energy prime mover equipment manufacturing and blade state monitoring technologies of onshore and offshore wind generating sets. The method comprises the following steps: acquiring operation data, a vibration signal, an acoustic signal and a pulse signal of a fan; the current working condition state of the fan is recognized, common-mode fault verification, local damage positioning and transient stress damage analysis are carried out on the vibration signals and the acoustic signals, and a fault analysis result and a first damage analysis result are obtained; performing phase-locked amplification analysis on the vibration signal and the acoustic signal through active excitation to obtain a second damage analysis result; and finally, a comprehensive state monitoring report of the fan blade is generated, so that the problems of difficulty in identification of weak damage and high false alarm rate of blades of land and offshore wind generating sets in wind energy prime mover equipment manufacturing under a non-stable working condition are solved, and the equipment operation and maintenance intelligent level in the wind energy prime mover equipment manufacturing industry is effectively improved.

The invention belongs to the field of damage state evaluation, and relates to a bridge local damage state evaluation method based on detection data, which comprises the following steps of: firstly, constructing a bridge model through a multi-angle image, and segmenting the bridge model into a plurality of regions by adopting a grid region division method; thirdly, analyzing the distance from each grid region to the supporting piece and the forward overlapping area, and determining an influence coefficient factor; then, calculating a static damage degree index by collecting data such as the number of internal and external cracks, the missing or cavity area and the foundation height change of each grid region; in the dynamic damage analysis, pressure is applied to each grid region, the damage condition of each grid region under the stress condition is evaluated, a dynamic damage degree index is obtained, the difference between the static damage index and the dynamic damage index is compared, and the damage degree of each grid region is comprehensively analyzed in combination with an influence coefficient factor. Finally, the damage grade is evaluated according to the comprehensive damage degree coefficient and marked with colors, and comprehensive evaluation of the health condition of the bridge is achieved.

The invention provides a high-pile wharf structure damage identification method and system, and relates to the technical field of wharf damage identification. According to the invention, through collaborative acquisition of multi-source data (strain, deformation and defect), a monitoring blind area of a single sensor is broken through, the multi-source data is integrated into multi-source heterogeneous data with time-space alignment, and high-dimensional input is provided for a deep learning model; and a damage feature vector output by the model is matched with a dynamic threshold library, so that a full-link closed loop from data acquisition to feature fusion to damage decision is realized. Specifically, the detection coverage is improved through multi-dimensional data collection, the anti-interference capability is enhanced through standardization and fusion processing, the damage analysis precision is improved through a deep learning model, and self-adaptive decision making is achieved through a dynamic threshold library.

The invention discloses an aero-engine gear damage analysis method and system based on image recognition, and relates to the technical field of image recognition, and the method comprises the steps: obtaining a gear surface image of a to-be-detected aero-engine gear at multiple angles; preprocessing the gear surface image; sequentially performing gear region segmentation, damage region positioning and damage feature quantification processing on the preprocessed gear surface image to obtain gear damage features; and performing damage analysis on each damage area based on the gear damage characteristics to obtain a damage analysis result which at least comprises a damage type judgment result, a damage severity grading result and a residual life estimation result. The technical problems that the aero-engine gear damage detection efficiency is low, the omission ratio is high, tooth surface damage is difficult to detect, damage evolution cannot be predicted, the remaining life cannot be evaluated, and the maintenance requirement of the aero-engine gear cannot be met can be solved.

The invention belongs to the technical field of fan damage detection, and particularly discloses an unmanned aerial vehicle-based offshore fan blade damage detection system, which comprises a detection partition determination module, an unmanned aerial vehicle acquisition control module, a damage image acquisition module, a fan damage analysis module and a fan damage feedback terminal. According to the method, the damage point and the blade area are positioned through preliminary cruising of the unmanned aerial vehicle, and the fan array is divided, so that the dilemma that a traditional detection mode is easily interfered in an offshore high-wind-speed environment is changed, and the complicated offshore environment can be flexibly coped with; meanwhile, the shooting distance and the shooting time point of the unmanned aerial vehicle are adjusted by combining the space coordinates of the damage point, the real-time blade rotating speed and the real-time offshore wind condition to generate a shooting parameter instruction, so that the limitation and the monitoring dead angle limitation of traditional fixed-view-angle monitoring are broken through; and finally, crack analysis of different depth layers is carried out on the optical image and the ray image, so that the damage degree can be evaluated more comprehensively and accurately.

The invention provides a chain ring fatigue damage calculation method and system considering wear conditions, under the conditions of multiple working conditions and multiple wear losses, fatigue load calculation and accumulated damage analysis are carried out on a suspension chain ring, and through time domain simulation, finite element calculation, rain flow counting and S-N curve combination, the fatigue damage of the chain ring is calculated. And a working condition-abrasion loss-fatigue damage database is established. According to the method and the system, accurate evaluation and early warning can be provided for safe service management of the anchor chain or the suspension chain in ship and ocean engineering, and the reliability and the economical efficiency of system operation are greatly improved. All the parts of the device can be independently implemented and can also be modularly combined.

The invention belongs to the technical field of computer simulation, and particularly discloses a method, a system and equipment for predicting the fatigue life of a composite material patching and repairing structure. The prediction method comprises the following steps: establishing a composite laminated plate fatigue damage analysis method in combination with an improved Hashin criterion, finite element analysis, a strength degradation model, a rigidity degradation model and a Camanho material parameter degradation model; fatigue life prediction analysis is carried out on the non-porous laminated plate and the porous laminated plate by using the method; and comparing a prediction result with a test result, and verifying the effectiveness of the established composite material laminated plate fatigue damage analysis method. On the basis, a composite material fatigue damage analysis method and a cohesion unit are combined, and a repair structure fatigue life prediction model is established. The fatigue life prediction method for the repair structure is provided by taking the composite material patching and repairing structure as a research object, and has certain engineering practical significance and better practical value.

The invention discloses a fan blade structure damage analysis method and device based on a sub-model, and is used for solving the technical problem that the existing fan blade structure damage and sub-model analysis efficiency is relatively low. The method comprises the following steps: constructing a fan blade finite element model according to obtained fan blade design parameters; performing stress calculation on the fan blade finite element model, and determining a fluid load and a Mises stress value at the Gaussian integral point of each blade unit in the fan blade finite element model at the current time; according to the fluid load, the comparison result between the Mises stress value at the Gaussian integral point of each blade unit at the current time and a preset stress threshold value and the fan blade finite element model, dynamic construction of a target fine mesh entity unit sub-model is completed; and combining a phase field model and a Lagrange-cohesion model to perform structural damage analysis on the target fine grid entity unit sub-model to generate a structural damage analysis result of the target fan blade.

The invention relates to the technical field of reliability evaluation of a composite material structure, and particularly discloses an evaluation method for vibration damage mechanical properties of a composite material. The method comprises the following steps: firstly, clamping a composite material test piece on a special test clamp which can be stable and durable in a vibration environment, and carrying out parameter-controllable vibration excitation on a vibration table to simulate damage; then carrying out mechanical property test on the damaged test piece; and finally, based on the vibration data and the mechanical property data, establishing a vibration parameter-performance degradation correlation model by calculating the performance degradation rate, and performing quantitative evaluation on the vibration damage state of the composite material in combination with microscopic damage analysis. According to the invention, the problem that the vibration test and the performance evaluation process are separated and cannot be quantitatively associated in the prior art is solved, the integrated and quantitative analysis from damage simulation to state evaluation is realized, and the environment temperature influence factor is introduced; accurate data support can be provided for safety design and life prediction of the composite material structure in a specific vibration environment.

The invention discloses a fiber laminate damage acoustic emission signal processing method, equipment and a medium, and relates to the technical field of signal processing.The method comprises the steps that a fiber laminate is fixed to a test device, signals are collected through an acoustic emission sensor, filtering and preprocessing are carried out, features are extracted through an improved ReliefF algorithm, and a fiber laminate damage acoustic emission signal is obtained; randomly selecting samples, comparing the samples with nearest neighbors, updating feature weights, and screening most relevant features. An expectation maximization algorithm and a Gaussian mixture model are combined to establish a damage identification model, different types of damage are automatically classified, and a Gaussian distribution model is obtained through iterative optimization. And by utilizing a clustering analysis and feature selection algorithm, the damage of the laminated plate with different layering angles is identified, and different damage types are accurately distinguished. According to the method, high-precision damage classification is realized through feature extraction in combination with an expectation maximization algorithm and a Gaussian mixture model, laminated plate damage analysis at different layering angles is dynamically adapted, and feature extraction efficiency, classification accuracy and model adaptability are remarkably improved.

The invention discloses a digitalization-based velvet flower product quality detection and evaluation method and system, and belongs to the field of product quality detection. Binding position abnormity analysis is performed based on binding position texture image data and position data corresponding to bound velvet flowers; and then, based on the image data of the stapled velvet flower product, carrying out stapling damage abnormity analysis, and carrying out velvet flower stapling quality analysis by integrating a stapling position abnormity analysis result and a stapling change abnormity analysis result. According to the method, the binding quality is accurately and efficiently evaluated, damage analysis on the appearance of the product in the binding process is considered while the binding quality is evaluated, and then the binding quality of the product is comprehensively analyzed.

The invention discloses a nuclear power plant reactor core fuel assembly damage analysis and calculation method and system. The method comprises the following steps: calculating a typical nuclide equivalent attenuation coefficient according to fission product source item characteristics; calculating a typical nuclide release rate according to the typical nuclide equivalent attenuation coefficient; according to the equivalent attenuation coefficient of the typical nuclide and the release rate of the typical nuclide, calculating the reachable equilibrium specific activity of the typical nuclide; by analyzing typical nuclides, equilibrium specific activity can be achieved, and reactor core fuel assembly damage analysis is carried out. According to the method, the equilibrium specific activity can be reached through typical nuclides to carry out reactor core fuel assembly damage analysis, and the operation reliability of the reactor core fuel assembly is analyzed.

The invention discloses a maritime work steel plate intelligent cutting path planning method based on multi-objective optimization, and belongs to the field of maritime work steel plate intelligent cutting path planning, the method comprises the following steps: collecting cutting damage data of maritime work steel plates of different materials and thicknesses, constructing a process damage feature library, and combining internal damage analysis to perfect data dimensions, so as to obtain a process damage feature library; and finally establishing a damage prediction model by using a machine learning algorithm. A comprehensive objective function containing the material utilization rate, the cutting efficiency and damage avoidance is constructed, initial layout and path planning of parts are conducted, and cutting of the first part is executed after an initial cutting sequence and track are generated; by collecting damage data to establish a prediction model, constructing a comprehensive objective function to plan an initial path, optimizing a subsequent path in combination with a damage thermodynamic diagram, and establishing an adaptive rule base to adjust parameters, intelligent planning of a cutting path is realized, and the qualified rate of parts and the production efficiency are improved.

A first parcel digital image associated with a first interaction point is received. The first parcel digital image may be associated with a first parcel being transported to or from the first interaction point. At least a second parcel digital image associated with at least a second interaction point is further be received. The second parcel digital image may be associated with the first parcel being transported to or from the second interaction point. A first parcel damage analysis is automatically generated based at least in part on analyzing the first parcel digital image and the at least second parcel image. The damage analysis can include determining whether the first parcel is damaged above or below a threshold.

The invention discloses a digital simulation checking calculation system and method for repairing and reinforcing an ancient building, and relates to the technical field of data processing, and the method comprises the steps: carrying out the damage analysis of a three-dimensional model of a first ancient building, and extracting the structure type, material, shape and size of a damaged region; indexing and matching the repairing process knowledge graph in the repairing process library, and inputting damaged data to update material consumption prediction; simulating repairing to generate a second three-dimensional model based on the repairing process number and the predicted material consumption; and comparing the first modeling with the second modeling, calculating the repairing and reinforcing feasibility, and if the repairing and reinforcing feasibility reaches a threshold value, recording a passing identifier and outputting a corresponding scheme, thereby achieving the technical effects of providing accurate and efficient repairing and reinforcing evaluation and improving the repairing accuracy and reliability.

The invention discloses a structure safety assessment method and system based on a robot holder image, and relates to the field of structure safety assessment. The method comprises the following steps: S1, controlling a robot carrying a holder and a multi-modal sensor group to collect a surface image, internal heat distribution and three-dimensional contour data of a target structure, constructing a model based on an improved deep learning network to identify and classify surface defects and internal hidden damages, quantifying the defects through an algorithm, and outputting the data; s2, constructing a digital twin based on the three-dimensional contour data, mapping design parameters, tracking a dynamic feature point displacement trajectory to calculate deformation parameters, and outputting a deformation damage analysis result through a correlation model; and S3, calling a pre-constructed reinforcement learning adaptive evaluation model, inputting defect quantitative data and a deformation damage analysis result, and outputting a safety level and a risk evaluation result combined with a preset specification. The method improves the evaluation precision and efficiency, and adapts to the evaluation requirements of different target structures.

The invention provides a door-shaped steel bar optimization method and system based on ballastless track interface damage analysis, and relates to the field of track traffic, the method comprises the following steps: determining track interlayer bonding parameters of a ballastless track based on interface comprehensive mechanical property test data of a concrete material composite test piece of the ballastless track, and establishing a finite element model of the ballastless track; a service temperature field of the ballastless track is calculated, and equivalent simulation of shrinkage of the self-compacting concrete layer is completed; on the basis of the multiple structure optimization variables, multiple door-shaped steel bar optimization schemes are determined, and the track interface damage area and distribution of the ballastless track under the combined action of shrinkage of the self-compacting concrete layer and the temperature load are calculated by utilizing a finite element analysis method based on a finite element model of the ballastless track corresponding to the door-shaped steel bar optimization schemes; the method has the advantages that the early-stage interface damage risk is reduced, and the durability and reliability of the track structure are improved.

The invention discloses a building material mechanical testing system based on multi-algorithm fusion, and belongs to the technical field of building material testing, and the system comprises an initial damage quantification module which is used for obtaining detection information of a tested material test piece before mechanical loading and generating a quantitative evaluation result; the loading and information acquisition module is used for applying a mechanical load to the tested material test piece with the generated quantitative evaluation result and acquiring a mechanical response signal and a microscopic state signal of the tested material test piece; the damage analysis module is used for calling a preset second data processing algorithm and analyzing and generating a dominant damage path; and the diagnosis and prediction module is used for integrating the associated data atlas and the dominant damage path information, generating a material performance diagnosis report and constructing a prediction model through a preset third data processing algorithm. According to the method, the initial damage of the tested material test piece is quantified, so that systematic deviation of a test result caused by neglecting the initial damage is corrected.

The invention relates to the technical field of surrounding rock damage analysis, in particular to a deep-buried tunnel circulating blasting excavation surrounding rock accumulated damage analysis method and a deep-buried tunnel circulating blasting excavation surrounding rock accumulated damage analysis system. Further determining the effect of blasting and ground stress on surrounding rock damage during blasting excavation of the deep tunnel; under the action of blasting and ground stress, the influence of single-cycle blasting excavation and multi-cycle blasting excavation on surrounding rock damage is considered, and the cumulative damage variable of the rock mass is calculated; and evaluating the stable state of the surrounding rock according to the calculated accumulated damage variable, and optimizing a blasting design scheme and a support time sequence. According to the method, on the basis of considering the comprehensive action of blasting and ground stress, accurate calculation of the accumulated damage of the surrounding rock during deep-buried tunnel circulating blasting excavation is realized by analyzing the influence of single-circulation multi-section blast hole delayed blasting and multi-circulation blasting on the damage of the surrounding rock, so that a blasting design scheme and a support time sequence are optimized; and the safety of tunnel engineering is improved.

The invention discloses an urban agglomeration anti-seismic damage prediction method and system based on an unmanned aerial vehicle technology and a deep learning model. The method comprises the following steps: constructing a typical building multi-angle aerial image database and a building earthquake damage database under different load coupling effects; training an urban building group identification model based on the aerial photo database to identify the type, geometry and texture information of the building; constructing and training horizontal and vertical seismic oscillation amplification coefficient prediction models for correcting seismic oscillation intensities under different topographic conditions; a typical building earthquake damage prediction model is constructed and trained, and the building damage grade is predicted in combination with the corrected earthquake vibration intensity; and finally, realizing three-dimensional visualization of the damage condition of the urban building group through a damage grade imaging module. According to the method, the problems of inaccurate urban building group modeling information, large earthquake damage analysis workload and low precision in the prior art are solved, and a scientific basis is provided for construction and evaluation of tough cities.

The invention discloses an optical fiber end-to-end coverage fault positioning system based on passive optical switch cascade, and relates to the related technical field of optical fiber communication fault detection, and the system comprises a mapping construction module which builds a mapping matrix of a switch state and an optical fiber segment based on a preset switch switching sequence; the first identification module is used for injecting probe pulses in different switching states, and inverting local time delay distortion of each section by using a time delay observation set to form a first type of structural characterization; the second identification module is used for collecting the amplitude and phase sequence of the end-to-end signal, calculating the statistical distance between the end-to-end signal and the reference and projecting the statistical distance to the segment-level space to form a second type of structural representation; and the early warning module is used for carrying out damage analysis under multi-source observation and reporting fault abnormity. The technical problem that in the prior art, multiple potential degradation sections in the whole end-to-end process cannot be subjected to synchronous fine fault sensing and positioning is solved, and the technical effects that the health condition of the optical fiber link is sensed in real time through the passive cascade switch network and the fault positioning accuracy is improved are achieved.

The invention provides an aero-engine damaged blade data restoration and modeling method, which comprises the following steps: processing finite element grid files of a prototype blade and a damaged blade, and extracting grid topology information and node information of the blade; comparing node information of the prototype blade and the damaged blade, and determining multiple types of damaged nodes in the damaged blade; estimating the correct node position of the damaged node through three-dimensional data interpolation, and repairing the damaged area; the intermediate state shape of the blade is reconstructed by setting a repair reduction coefficient; and carrying out secondary reconstruction on nodes of the front edge area and the tail edge area of the blade, arranging blade profile node coordinates, and outputting a blade surface blade profile geometric file supporting pneumatic simulation. According to the method, the automatic conversion process from the finite element simulation grid to the pneumatic simulation blade profile file can be efficiently achieved, the blade damage analysis and repair design efficiency is greatly improved, and subsequent pneumatic performance simulation is facilitated.

The invention discloses a small sample gear damage intelligent identification and evaluation system based on machine vision, and belongs to the technical field of gear damage evaluation. The system comprises a user interaction interface module, a damage type detection module, dynamic binding of damage types and subprograms, a multi-damage analysis module, a result visualization module and a gear parameter management module. A B / S framework is adopted in the platform, an interactive Web interface is developed based on a Streamline framework, and a machine vision algorithm and a damage analysis model are integrated at the rear end. The system aims to realize determination of a damage position, identification of a damage type and extraction of various damage characteristics by inputting a picture of a damaged gear under a small sample condition.

The embodiment of the invention discloses a material performance degradation testing method and device, electronic equipment and a medium. The method comprises the following steps: based on a Shokrieh criterion, generating a subprogram for carrying out numerical simulation on the Shokrieh criterion; finite element software is adopted to construct a three-dimensional progressive damage analysis model of the composite material connection structure, and load applying simulation is conducted on the three-dimensional progressive damage analysis model; and carrying out stress tensor calculation and failure judgment on the three-dimensional progressive damage analysis model based on the subprogram according to a load applied to the three-dimensional progressive damage analysis model, and carrying out simulation test on a performance degradation process of the three-dimensional progressive damage analysis model. According to the scheme, the symmetry and the influence of each stress component on each failure mode can be considered based on the Shokrieh criterion, the damage process of the composite material can be simulated more accurately, and the method is more suitable for the actual material performance degradation process.

The invention relates to the technical field of concrete damage identification, and provides a concrete damage spatio-temporal evolution identification method and related equipment, and the method comprises the steps: carrying out the damage mapping based on all damage information, and obtaining an initial damage label of each sub-region in each historical time period; performing quantitative separation on the damage information according to the initial damage label by utilizing a support vector machine to obtain a final damage label; for each historical time period, performing spatial damage analysis based on all damage information of the historical time period to obtain a damage gray matrix of each sub-region in the historical time period; and constructing a three-dimensional damage model of the target concrete area in each historical time period according to the damage gray matrix and the final damage label of all the sub-areas in each historical time period, and serializing all the three-dimensional damage models to obtain a spatio-temporal evolution damage model of the target concrete area. According to the method, the identification accuracy of concrete damage spatio-temporal evolution can be improved.

The invention discloses a method for predicting creep-fatigue interactive damage of a powder disc edge. The method comprises the following steps: S1, constructing a creep constitutive model of the powder disc edge; s2, acquiring load holding time; s3, creep stress analysis and creep fatigue weak position acquisition; s4, creep stress segmentation: establishing a creep stress relaxation model in which the stress sigma is related to the time t, and segmenting the creep stress by taking the logarithmic stress as the step length; s5, performing low-cycle fatigue damage analysis, and acquiring the low-cycle fatigue life and the low-cycle fatigue accumulated damage of the section by adopting a stress-life curve or a strain-life curve; s6, creep-stress fracture damage and total damage are analyzed, and creep-stress fracture accumulated damage and low cycle fatigue and creep-stress fracture total damage under corresponding cycles are obtained; s7, designing and verifying a powder disc edge simulation piece; and S8, verifying and improving a powder disc edge creep-fatigue damage prediction model. According to the method, the creep-fatigue prediction precision of the turbine disc edge is improved.

The invention relates to a bending test method, system and device for a flexible OLED screen and a storage medium, and the method comprises the following steps: obtaining preset bending data of a target flexible OLED screen, and carrying out the dynamic bending test of the target flexible OLED screen based on the preset bending data; in the dynamic bending test process, performing non-contact detection on the target flexible OLED screen to obtain a detection image; judging whether a damage area exists in the detection image or not, and if yes, inputting the detection image into a preset damage model to determine the damage level of the target flexible OLED screen; and if the damage level exceeds a preset damage level, performing damage analysis on the damage area to obtain a damage analysis result, and formulating an OLED screen production management strategy based on the damage area and the damage analysis result. The technical problems that the damage risk in the testing process is increased, and the testing efficiency and accuracy are limited are solved.

The invention relates to the technical field of salt rock damage analysis, and discloses a salt rock damage form reconstruction method and system based on acoustic emission parameter fusion, and the method comprises the steps: carrying out the damage state monitoring of a real salt rock sample set, obtaining a plurality of mark state feature groups, constructing a target damage index group, and obtaining a target damage index set; screening the plurality of marked state feature groups based on the target damage index group to obtain a plurality of target state feature groups, performing mechanical parameter detection on the to-be-evaluated salt rock sample to obtain a to-be-evaluated mechanical parameter group, acquiring a to-be-evaluated acoustic emission feature group based on the to-be-evaluated mechanical parameter group, generating a to-be-evaluated state feature group, and performing evaluation on the to-be-evaluated acoustic emission feature group. And querying the predicted storage duration in the plurality of target state feature group sets based on the to-be-evaluated state feature group. According to the method, accurate reconstruction of the rock salt damage state and reliable prediction of the life can be realized, and the accuracy of a damage evaluation result is improved.