622 results about "Online evaluation" patented technology

The invention discloses an optimization method of a network variable structure with a distributed type power supply distribution system. The optimization method includes that basic static data of electric power network structure parameters, distributed type power supply distribution, load capacity, faulty lines and the like are extracted, under the condition of present line fault, the basic static data are utilized to perform islanding scheme calculation and correction, survivability indexes constructed by the method are combined to perform an online evaluation for islanding network safe operation performances and implement immediate control measures, finally, on account of residual network structure data after final islanding electric power network division is performed, by means of an ant colony algorithm, a reconfiguration optimal computation is performed for residual network with minimum network loss as a target, and finally the electric power network structure with high safe operation level is obtained. On the basis of the developed algorism and function modules, the invention further provides a large-scale power distribution network intelligent optimization decision system based on multi-stage computation correction and survivability evaluation, according to the technical scheme, the division and reconstruction of the network with the generalized model distributed type power supply distribution system are achieved, and accurate reference of network structure adjustment, schedule and operation can be excellently provided for regional electric power network schedule staffs.

The invention discloses online accuracy detection method and system of a current transformer. A standard current sensor is connected with a transmission line and collects a current signal on the transmission line; a current signal output by the current transformer and the current signal on the transmission line are collected by respective signal collectors and sent to a signal processor in sharingtime; and the signal processor synchronously sends the signals to a central processing system (CPU) which compares and processes the two signals received in the same clock and calculates the error conditions of the measured current transformer. The online accuracy detection system of the current transformer can be electrically connected or disconnected with a circuit of a transformer to be measured and can uninterruptedly carry out accuracy comparison measurement with the transformer to be measured under an electric operation condition for dozens of hours so as to estimate the current transformer under different operational working conditions and environmental characteristics, achieve the online accuracy estimation of the current transformer and have favorable effect.

The invention relates to a self-adaptive screening method for an anticipated fault set in power system security and stability on-line assessment, which is suitable for determining the anticipated fault set in the static, transient and dynamic security and stability on-line assessment of the power system. The method adopts the core concept that the fault set required to be recalculated in the security and stability on-line assessment is determined according to the mode of the security and stability margin of all anticipated faults given by the security and stability on-line assessment in the previous round of the power network. The invention takes the power network security and stability margin and the security and stability mode as the quantitative index of the power network security and stability degree, takes the security and stability margin as the index, and screens the anticipated fault subset required to be recalculated from the anticipated fault universal set by combining the security and stability mode and the degree of change of the running state of the power network as the dynamic anticipated fault set which meets the practical demands of the engineering and is changed along with the running state of the power network; the scale of the anticipated fault set used for the security and stability on-line assessment under the current time section can be reduced, and the computing speed for the security and stability on-line assessment is increased.

The invention discloses an online evaluation method of electric power system dynamic stability. The online evaluation method comprises the steps of step 1, carrying out high-frequency sampling by utilizing a PMU (Power Management Unit), and extracting an oscillation mode for sampling data by utilizing a matrix pencil identification method; step 2, detecting low-frequency oscillation, and emitting low-frequency oscillation warning if a damping ratio of the detected oscillation mode is lower than a set threshold value; step 3, carrying out small perturbation calculation on a system model in a current running mode through a frequency domain analysis method, and obtaining a characteristic value, a characteristic vector, a corresponding unit and participated factor information; and step 4, screening out information of a low-frequency oscillation mode from a small perturbation calculation result according to the low-frequency oscillation mode which is determined by the matrix pencil identification method, regulating a related electric power generator to output, and obtaining tide stability limit of call lines between related domains through time-domain simulation at the same time. According to the online evaluation method disclosed by the invention, the influence of noise is effectively avoided, the identification accuracy is improved, the calculating speed and the calculating efficiency are increased, and the online dynamic safety evaluation effect of the electric power system is obviously improved.

A method for evaluating software performance includes steps of: receiving a plurality of versions of code; selecting starting and stopping points for timing execution of the code versions; dispatching at least two of the plurality of code versions for execution; repeatedly executing the at least two code versions; recording execution times for the at least two code versions, according to the selected starting and stopping points; collecting the execution times; and processing the collected execution times. The method further includes steps of: performing a statistical analysis of the collected execution times for determining which code version is fastest; and invoking a confidence metric periodically to determine if a difference between means is statistically meaningful.

A system and method for facilitating on-line generation and assignment of evaluations for entities of a particular organization comprising: a web-based server device for generating web-based communications for delivery to web-enabled devices over a communications network, and receiving web-based communications via the network; an evaluation build module for initiating a web-based communication via the server device for receipt by a user device, the communication comprising a first interface for receiving user input to generate a customized evaluation for a particular organization including input for specifying a target audience (evaluator) for the evaluation, specifying a subject (evaluatee) of the evaluation, specifying associated evaluation questions for the target audience, and specifying potential answer choice types to be entered by evaluators when completing the evaluation; and, evaluation assignment module for generating an evaluations assignment interface via a web-based communication for receiving user input to selectively assign and schedule by date and date range the generated evaluations to one or more evaluators for receipt at web-enabled devices, wherein the assigned evaluations are capable of being viewed and completed on-line by the evaluators.

The invention discloses a distributed power supply, energy storage and flexible load combined scheduling method and device. The distributed power supply, energy storage, flexible load and other distributed resources are numerous in number, dispersed in layout and difficult to be directly scheduled by a power grid; and a resource aggregator can execute a power grid scheduling instruction by internally integrating various distributed resources. Based on the operation mode of the resource aggregator, a combined scheduling model combining large-capacity resource direct scheduling and small-capacity resource electricity price response indirect scheduling is established. On the basis, with the maximum profit of the resource aggregator as an optimization target, rolling online evaluation is carried out on the large-capacity resource scheduling performance difference, and a dynamic comprehensive scheduling priority is set; for the uncertainty of indirect scheduling of small-capacity resources,an opportunity scheduling constraint containing fuzzy parameters is provided; and an improved particle swarm algorithm is adopted to clarify the fuzzy opportunity constraint and solve the schedulingmodel. Based on an IEEE33 node power distribution network, the effectiveness and scientificity of the proposed model and algorithm are verified.

The invention relates to an online evaluation approach to evaluate the maximum power supply capacity of urban power network, belonging to the technical field of advanced application of electric power system dispatching. The method employs data base connection modes(ADO and ODBC), reads the relative network topology and network nodes in EMS and analyses the topology of the urban power network by means of an adjacency matrix to build up a model for calculating the maximum power supply capacity of the urban power network; the model is a linear programming model based on DC power flow and takes the maximum load of the network as the target function, and power balance, rated capacities of the branch lines and power restriction of the nodes as the constraint condition. In the program, the linear programming is worked out through improved simplex method and error analysis is carried out to the result. The model has the advantages of big calculation speed and small calculation error as for light load network and is suitable for power networks that require repeated optimization and adjustment. Results from a great amount of calculation with the program show that the method is of efficacy and applicability.

The invention provides a power battery health state online evaluation system and method based on internet of vehicles. The method comprises the following steps: realizing real-time collection and uploading of different frequencies on the CAN data through the internet of vehicles, through a power battery health state evaluation model established by the big data analysis platform, analyzing the influence degree on the battery health degree by various influence elements when the uploaded data satisfies a judgment condition for model running, and comprehensively evaluating multiple battery healthdegree influence elements. By online analyzing the battery health state, aftersales personnel of the enterprise can understand the market vehicle battery state in time, thereby quickly replying the market vehicle battery fault processing and spare parts supply; on the other hand, the relevancy analysis result data and suggestion are pushed to the user by analyzing the health degree influence relevancy, the user can directly understand the health status of the battery of the vehicle and the influence element of the battery health status conveniently, thereby reminding the user to correct the bad operation habits in time, and the service life of the battery is prolonged.

The invention provides an online evaluation method for compaction quality of an earth and rockfill dam material and provides an online evaluation method for compaction quality of a dam material, which is suitable for monitoring rolling parameters and compaction effect in real time and taking dam material property into consideration. The compaction quality of the earth and rockfill dam material is comprehensively evaluated in real time; and a technical scheme adopted in the method is that the online evaluation method for the compaction quality of the earth and rockfill dam material comprises the following steps: collecting field test pit experiment results by using a PDA (Personal Digital Assistant); establishing a compaction quality evaluation model; figuring out the compact quality of each grid of the current construction bin surface; next, obtaining the compaction quality in any position of the current full construction bin surface by using a spatial interpolation method; furthermore, analyzing a quality qualified or disqualified area according to a compaction quality control principle, figuring out qualified rate of the compaction quality of the current construction bin surface; and feeding back the qualified rate in time to instruct field construction so as to control construction quality. The online evaluation method for the compaction quality of the earth and rockfill dam material, provided by the invention, is mainly applied to online evaluation of the compaction quality of the earth and rockfill dam material.

The invention discloses a method and system for real-time online evaluation of off-site results of nuclear facility accidents, and belongs to the technical field of nuclear facility accident result analysis. The method comprises a wind field prediction method of a simulation area, a wind field diagnosis method, a Lagrange puff atmospheric diffusion simulation method, an estimation method of gaseous radionuclide-caused radiation dosages and prevention measures, and an airborne passing food chain radioactivity estimation method. Through the method and system provided by the invention, the wind field prediction and diagnosis, and the contaminant atmospheric diffusion simulation and radiation dosage estimation of a plurality of accident points from the happening of a nuclear facility accident to the end moment in a simulation area range which takes a nuclear facility as a center can be completed, so that result evaluation data basis is provided for the accident emergency command processing after the nuclear facility accident.

The invention discloses a method for evaluating an arterial green wave coordination effect based on a mobile terminal, and the method can output evaluation indexes on line in real time by adopting a green wave coordination effect evaluation algorithm and utilizing the intelligent mobile terminal. The method can obtain single-vehicle traveling data in real time through the intelligent terminal and realize real-time online evaluation of a green wave coordination effect of a single-vehicle test road segment in combination with a data processing algorithm and the green wave coordination control evaluation algorithm, and meanwhile, the evaluation method mainly has two evaluation modes which are drawing of a trajectory space-time diagram and output of the evaluation indexes respectively. Compared with existing common methods such as a manual research method, a single-vehicle test method, a floating vehicle method and the like, the method for evaluating the arterial green wave coordination effect based on the mobile terminal has the advantages of low manpower and material resource consumption, capability of giving out the effect evaluation indexes and optimization suggestions on line in real time, and the like, thereby having very high practicality and a wide application prospect.

The invention discloses a capacitive voltage transformer error state online monitoring method and a system thereof. The method comprises the steps of through synchronous triggering of a synchronous signal unit, acquiring and calibrating measurement data of an operation three-phase capacitive voltage transformer, establishing a threshold which represents a statistics characteristic parameter of thecapacitive voltage transformer error state and a statistics characteristic quantity of a standard normal operation state by means of a principal component analysis method; acquiring measurement dataof the three-phase capacitive voltage transformer in the operation state, according to a statistics characteristic parameter, representing a statistics characteristic quantity of the three-phase capacitive voltage transformer error state by means of an adaptive principal component analysis method, and comparing the statistics characteristic quantity with a statistics threshold for determining whether the error state of the capacitive voltage transformer is normal; and when the statistics characteristic quantity of the measured data exceeds the statistics threshold, performing diagnosis on theerror abnormity of the capacitive voltage transformer. The capacitive voltage transformer error state online monitoring method and the system thereof can realize real-time online evaluation on the error state of the capacitive voltage transformer.

The embodiment of the invention relates to a processing system for teaching data. The processing system comprises an educational terminal, a learning terminal and a shared platform, wherein the sharedplatform comprises a teaching live broadcasting module, a teaching recording module, a teaching on-demand broadcasting module and an online evaluation module; the teaching live broadcasting module comprises a live broadcasting establishing unit, a network connection unit, a video and audio receiving unit, a live broadcasting interaction unit and a content distributing unit; the teaching recordingmodule comprises a recording unit, an analyzing unit, an annotating unit and a storage unit; the teaching on-demand broadcasting module comprises an on-demand broadcasting receiving unit, an on-demand broadcasting querying unit and an on-demand broadcasting processing unit; the online evaluation module comprises a test question entering unit, a proofreading unit, a wrong topic analysis unit and aknowledge point pushing unit. When students view analysis for wrong questions tested on the platform, relevant explaining videos can be obtained according to knowledge points of the wrong questions and are pushed to the students to help the students to break through weak knowledge points and improve the learning efficiency; in addition, in the live broadcasting process, a teacher can monitor thelearning states of the students so as to guarantee the learning quality of the students and the teaching quality of the teacher.

The invention discloses a website bug online evaluation method and device. the method comprises receiving website bug information sent by bug detection webpage, wherein the website bug information comprises uniform resource locators with bug websites, bug test parameters and bug test results; obtaining classification identification of the bugs and the website access flow within the preset period according to the website bug information; determining bug risk evaluation levels of the bugs according to the classification identification of the bugs and the website access traffic. By the aid of the method and the device, the bug risk evaluation levels are determined by comprehensive considering of the bug classification identification and the bug website access traffic, so that the determined risk evaluation levels are in accordance with the actual website harm degree by the bugs, pertinence is provided for subsequent bug fixing schemes, and an effective precaution effect is provided.

The invention discloses online radiotherapy plan quality control software which comprises a DVH prewarning value template setting interface, a data read-in interface, a radiotherapy plan DVH prewarning value setting interface, a sketching and integration interface, a plant evaluation interface, an online adjustment interface, an image deformation registration algorithm, an online plan modification algorithm and a dosage calculation algorithm. A fusion image is generated through an original image and an online image, a target section is described, the endangered organ profile is subjected to online sketching, based on this, dosage calculation is conducted, DVH is generated, comparison with the DVH prewarning value set by a doctor is conducted, online evaluation and adjustment of a radiotherapy plan are achieved, and precise application of the radiotherapy plan is guaranteed.

The invention relates to a power system transient stability assessment method based on convolution neural network CNN, in particular to power system transient voltage stability online assessment. In order to solve the problem that the traditional transient voltage assessment methods cannot meet the accuracy and rapidity, CNN is introduced into the transient stability assessment of power system. The technical scheme is mainly divided into two parts. The first step is off-line training: pre-processing based on simulation data, obtaining 36-dimensional input feature quantities, forming training set and test set and inputting them into CNN, optimizing the structure and parameters of CNN truss, and generating off-line transient stability assessment model; the second step is to obtain the post-fault PMU measurement data and construct the 36-dimensional feature quantities, input the trained off-line transient stability assessment model, and evaluate the transient voltage online stability state. At present, the traditional transient voltage evaluation method cannot meet the problem of accuracy and rapidity, the error rate is low, and the test time is short.

The invention provides a method and a system for assessing the health of a fan, a storage and a controller. The method comprises the steps of acquiring historical data of a fan in normal operation and forming a working condition feature vector when the fan is working; dividing the historical working condition of the fan; recognizing the type of the working condition, and using a state feature vector to build a reference model for assessing the health of the fan on the line according to the type of the working condition; inputting the working condition feature vector at the current moment into a preset training model to acquire the probability the working condition of the fan at current moment belongs to the type of each working condition, and computing a mahalanobis distance between the state feature vector at the current moment and the reference model under each working condition; and acquiring a weighted average value of the working condition type probability and the mahalanobis distance with the reference model under each working condition, and converting the weighted average value into a health index for describing the degree the working condition deviates from normal operation at the current moment. According to the method and the system provided by the invention, a degradation process before the fan is failed can be recognized in advance, and health state variation of the fan in operation can be accurately assessed.

An online recommendation system based on collaborative filtering and a long-short memory network comprises a real-time module, a near-line module and an offline module; the real-time module receives auser request in real time and outputs the user request to an HDFS cluster distributed file system built by a plurality of terminals after preprocessing, and meanwhile real-time recommendation and online evaluation are conducted according to the request; The near-line module obtains user request data from the real-time module, distributes the requests to the distributed cache through the message queue in real time, carries out offline training on the recommendation model by using characteristics in the user requests, and carries out incremental updating on the data in the load cache of the recommendation model which is subjected to offline training; The offline module loads characteristics from the characteristic pool; and training in the training set by using the recommendation model, realizing collaborative filtering of the trained recommendation model through an autoencoder to mine the long-term preference of the user, thereby performing recommendation model estimation in the test set by combining with the long and short memory network, and finally performing offline evaluation on the effect of the recommendation model to obtain a final recommendation result.

The invention provides a system and method for fault prediction and on-line evaluation of health state of marine diesel generator, which includes a shell, a displayer, an alertor, a power supply and adata processing device, wherein the data processing device include a deep learning integration module, a full life cycle history database, and a fault multimodal expert system database. The deep learning integration module utilizes an integrated learning method, and includes multiple supervised and unsupervised deep learning network models. The fault multimodal expert system database includes allfault feature databases and corresponding fault category labels, and also comprises a memory, a GPU, a CPU, an external device control interface, a data acquisition module and a wireless signal transceiving device, and realizes automatic monitoring and evaluation of an equipment. The system has the advantages of more accurate and convenient fault prediction, state on-line monitoring and the health evaluation.

The present invention provides a least-square location method based on the communication distance estimation and online estimation thereof, and relates to the precision wireless location technology. The objective of the invention is to solve the problems that the communication distance estimation error is large and the location precision is low because of the influences of noise and measurement error in the wireless location environment. The method comprises: unknown nodes employ a distance measurement method based on nanoLOC to obtain the communication distance measurement value between anchor nodes, respectively perform online moving average processing and statistical calculation of the communication distance measurement values and obtain each communication distance estimation result and each quality estimation value; in the least-square location process, communication distance estimation results with high quality and the position information of the corresponding anchor nodes are selected to construct a least-square location equation group and perform resolving so as to realize precision location. The least-square location method based on the communication distance estimation and online estimation thereof is suitable for wireless and underwater environment high-precision distance estimation.

The invention relates to a transient voltage stable on-line assessment method based on a WAMS (Wide Area Measurement System) and an EMS, comprising: obtaining WAMS real-time power grid measurement information to determine whether a power grid is disturbed; obtaining the topological structure, parameters and power flow operation information of a current power grid from an EMS when the power grid is disturbed so as to calculate a full admittance matrix concerning load equivalent admittance; according to the WAMS measurement information, running statistics on nodes having a voltage dip exceeding a preset threshold value, obtaining Thevenin equivalent parameters of statistic nodes based on full admittance matrix inversion to be used as an initial value to track Thevenin equivalent parameter identification of the WAMS measurement information and static state voltage stable margin index calculation, and calculating a transient voltage dip acceptability area index; and running statistics on nodes having a power grid node voltage dip exceeding a preset threshold value and having a dip duration greater than a preset threshold value, and determining the occupancy of power grid disturbance transient voltage instability nodes. The method can rapidly and effectively realize the stable and rapid assessment of a transient voltage.

The invention discloses a method and a system for online detection of voltage transformer precision. The invention is characterized in that the system comprises a capacitive voltage dividing loop, a signal acquisition processor and a data processing system, the output end of the capacitive voltage dividing loop is connected with the input end of a first signal acquisition processor, the output end of the voltage transformer to be detected is connected with the input end of a second signal acquisition device, the output end of the first signal acquisition processor and the output end of a second signal acquisition processor are connected with the data processing system, voltage signal on a power transmission line and voltage signal of the voltage transformer to be detected are acquired, calculated and processed respectively by the signal acquisition processing system of the power transmission line and the signal acquisition processing system of the voltage transformer to be detected, and the error condition of the voltage transformer to be detected is obtained. Tens of hours of uninterrupted measurement can be conducted to the voltage transformer to be detected under the charged operation condition and no influence is caused to the grid during accessing and quitting, so the assessment of the voltage transformer under different operation conditions and environmental characteristics can be realized and the online evaluation of the voltage transformer precision is flexibly realized.

The invention discloses a meteorological-information-based photovoltaic power generation active power online evaluation method, which comprises the following steps of: 1, selecting a reference point, a reference direction and a sample photovoltaic panel, and setting a data acquisition moment t to be an initial moment 0; 2, acquiring the axial directions of the photovoltaic panel and photometric equipment; 3, acquiring the geographical position information and dip angle data of the photovoltaic panel and the photometric equipment; 4, acquiring solar irradiation sample data, prediction data and cloud cover monitoring data measured by the photometric equipment; 5, preprocessing the solar irradiation sample data and the prediction data; 6, preprocessing the cloud cover monitoring data; 7, computing the active power output of a photovoltaic component; and 8, obtaining a photovoltaic power generation active power characteristic curve. In the method, the data actually measured by the photometric equipment in the given time period of 1min is taken as a basis and the influence of a cloud cluster on a photovoltaic power station is comprehensively taken into account to obtain the photovoltaic power generation active power characteristic curve in the future 0 to 5min by approximately equal power processing and curve fitting, so active power characteristic analysis efficiency and accuracy are effectively improved, and the bases are provided for the formulation and regulation of complementary running policies and energy efficiency management policies of joint power generation systems utilizing a plurality of power supplies such as wind, sunlight and the like.

The invention relates to a service quality assurance system for a wireless sensor network. The service quality assurance system comprises a wireless sensor network, a user control server communicating and interacting with the wireless sensor network and a service quality assurance platform for implementing control and management to the network service quality. The service quality assurance platform is provided with three functional modules of service quality assessment, service quality control and service quality management, and a network interface and a human-computer interaction interface which connected with the wireless sensor network. The structure of the service quality assurance platform is simple, the platform is easy to realize and convenient for control, various performance parameters influencing the network service quality of the wireless sensor network are analyzed through the current service quality assessment system, the key factors are searched out, and the motion of the sensor network and the nodes is further controlled and adjusted. The service quality assurance system not only can be used for online assessment to the service quality of the wireless sensor network, but also can be used for the verification and the improvement of the protocol algorithm of the future wireless sensor network, thereby having very good promotion and application prospect.

The invention discloses a dual-inertial navigation combination spin modulation navigation and online relative performance assessment method for solving the problem of difficulty in assessing inertial navigation performance. By the steps of coordinate system defining, combination spin modulation strategy arrangement, combination system state equation determination, measurement equation determination and Kalman filtering, online assessment of the inertial navigation performance is realized, and an information fusion effect among multiple inertial navigation systems is improved. The assessment method can be used for assessment of the inertial navigation system relative performance under long-endurance and high-precision navigation conditions and inertial navigation system fault diagnosis, and has positive significance to ensuring navigation precision under the long-endurance condition.

Disclosed are improved methods, systems, and computer program products for lithographic simulation of an electronic circuit design. Various embodiments of the present invention identifies a mask pattern, performs offline precharacterization for the mask pattern by solving an equation which models a solution for the mask pattern and an interaction between the mask pattern and one or more effects, performs online evaluation based at least upon a parameterized form of the equation, determines a field around the mask pattern based at least upon the act of performing the online evaluation, and stores a result of the act of determining an electromagnetic field around the mask pattern in a tangible computer readable or usable medium

The invention discloses a method for online valuation of used cars. The method for online valuation of the used cars comprises the steps of (1) carrying out data capture in a timing mode on main vehicle circulation trading platform websites on the internet through a net crawler program, (2) carrying out discrimination on vehicle model information of various platforms, and corresponding prices to vehicle models, (3) carrying out statistical analysis on data through a linear regression method after a large number of price data are collected, obtaining a linear equation Y=a*X+b, wherein prices and mileages serve as the weight of the linear equation, the Y stands for the prices, and the X stands for the mileages, and (4) adopting an online evaluation method to apply to the linear equation on the websites, working out a fair price of a used car to be evaluated, helping a user to distinguish cost performance of the used car according to cost performance when car source search is carried out, and expressing the cost performance through a showing form. The method for online valuation of the used cars can rapidly provide vehicle evaluation values for ordinary consumers, serves as a barometer of a vehicle circulation market, reflects market price behavior, provides data information besides experience for professional users, and can serve as reference for professional vehicle evaluators.

The invention discloses a power battery recession situation analysis method and system based on big data. The method comprises the following steps of acquiring a charging voltage of a sample power storage battery in a charging state and corresponding charging capacity; computing a corresponding capacity increment value according to the charging voltage and the charging capacity corresponding to the charging voltage; drawing an original capacity increment curve according to the charging voltage and the capacity increment value; carrying out smooth processing and curve fitting on the original capacity increment curve in order to obtain a capacity increment curve; obtaining a capacity increment peak-valley value according to a high peak value and a valley value of the capacity increment curve; computing a corresponding health state value of the power storage battery according to the charging capacity; drawing a change curve of the capacity increment peak-valley value along with a batteryhealth state according to the capacity increment peak-valley value and the corresponding health state value; and estimating a real-time health state value of a to-be-detected power storage battery according to the change curve. Through the adoption of the method or the system, real-time online evaluation of the service life of the power storage battery can be achieved.

The invention relates to a method for evaluating the capacity attenuation degree of a lithium ion battery online. According to the method, the relationships of the capacity attenuation degree and accumulated processing energy of the battery under different charging and discharging depths are established through cyclic tests of the battery under the different charging and discharging depths, and the association relationships are applied to an energy storage monitoring system, and therefore, the on-line evaluation of the capacity attenuation degree of the lithium ion battery can be realized.