CN114239394A - Relay contact characteristic evaluation method based on contact resistance time sequence - Google Patents
Relay contact characteristic evaluation method based on contact resistance time sequence Download PDFInfo
- Publication number
- CN114239394A CN114239394A CN202111521997.1A CN202111521997A CN114239394A CN 114239394 A CN114239394 A CN 114239394A CN 202111521997 A CN202111521997 A CN 202111521997A CN 114239394 A CN114239394 A CN 114239394A
- Authority
- CN
- China
- Prior art keywords
- relay
- contact
- time sequence
- contact resistance
- resistance value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 24
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000009471 action Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000000750 progressive effect Effects 0.000 abstract description 2
- 230000009897 systematic effect Effects 0.000 abstract 1
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002679 ablation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01H—ELECTRIC SWITCHES; RELAYS; SELECTORS; EMERGENCY PROTECTIVE DEVICES
- H01H50/00—Details of electromagnetic relays
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01H—ELECTRIC SWITCHES; RELAYS; SELECTORS; EMERGENCY PROTECTIVE DEVICES
- H01H50/00—Details of electromagnetic relays
- H01H50/54—Contact arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Measurement Of Resistance Or Impedance (AREA)
Abstract
The invention discloses a relay contact characteristic evaluation method based on a contact resistance time sequence, which is used for building a relay contact characteristic test loop and obtaining a contact resistance time sequence of the first half life stage of a relay. And analyzing and modeling the time sequence by using an Elman neural network, iteratively predicting a future value of the contact resistance, and expanding the time sequence, thereby realizing the evaluation of the contact performance of the relay contact. The invention provides a method for evaluating the contact characteristics of the electromagnetic relay by modeling the contact resistance time sequence by using the Elman neural network, and the method has the advantages of complete structure, progressive test scheme, systematic and comprehensive test scheme and high result feasibility, and is suitable for popularization and application in a power system.
Description
Technical Field
The invention relates to the technical field of reliability evaluation of electromagnetic relays, in particular to a relay contact characteristic evaluation method based on a contact resistance time sequence.
Background
The electromagnetic relay is a low-voltage electrical appliance element widely used in the fields of aerospace, power system protection, automatic control and the like, plays a role in protection and control, and is particularly represented as automatic control, a conversion circuit, safety protection and the like in a power system. With the improvement of the requirement of society on the stability of a power grid and the continuous increase of the scale of a power system, the requirements on the performance and the reliability of switching appliances such as relays are also improved, and particularly, if the reliability of an electromagnetic relay is reduced, the reliability and the safety of the operation of the system are greatly reduced, serious faults of the system are caused, and irretrievable losses and damages are caused to equipment safety, personal safety, social production life and the like. The contact is used as an important component of the electromagnetic relay and takes the tasks of closing, opening and closing current or bearing current for a long time, and the contact performance of the contact is closely related to the working performance and the action reliability of the relay. Meanwhile, the contact is subjected to various effects such as arc ablation, mechanical stress, oxidation and the like in the relay operation process and is a weak link in each part of the relay. No matter what kind of factors cause the reliability to be reduced, the relay can finally show the degradation of the contact performance, such as the reduction of the contact pressure caused by the fault of an action mechanism or the increase of the contact resistance caused by the thickness reduction of a contact under the arc ablation or mechanical stress; therefore, the contact performance of the contact of the electromagnetic relay is evaluated, and the relay is found and replaced in time before the contact is completely failed, so that the method has great significance for improving the reliability of the relay and further ensuring the safe and stable operation of a power system.
The contact performance of a contact is determined by many factors, most of which present measurement difficulties, such as the tightness of the internal components of the relay, or difficulties in quantitative description, such as the surface state of the contact. It is difficult to infer the contact state by directly acquiring these factors. These factors all vary with the number of operations, i.e. with time, and these variations are combined to be regular in the contact resistance with time. The time series of contact resistances can thus be analyzed as an amount of time using the number of operations. In the existing research, the time series of the contact resistance of the relay is analyzed and modeled by using models such as fuzzy weighted prediction, exponential smooth prediction or Markov prediction, so as to predict the future contact resistance variation trend to complete the evaluation of the contact performance. However, relevant parameters in each model are determined by human subjective experience, and the universality and the objectivity are not strong. In the whole service life stage, the contact resistance presents different change characteristics in different stages, the error of a single prediction model is large, and the practicability is not high when different prediction models are used for modeling in each stage.
Disclosure of Invention
In order to solve the problems, the invention provides a relay contact characteristic evaluation method based on a contact resistance time sequence, which introduces an Elman neural network to analyze and model the contact resistance time sequence of the relay, and establishes the contact resistance time sequence in the full-life stage through partial contact resistance data, thereby achieving the prediction of the future contact resistance and realizing the evaluation of the contact performance of the relay.
In order to achieve the purpose, the technical scheme is as follows:
a relay contact characteristic evaluation method based on contact resistance time sequence comprises the following steps:
s1: a relay contact resistance measurement loop is built, the relay is controlled to continuously act, the resistance value of the contact resistance at one time is calculated every time the relay acts for a certain number of times until the action number reaches 50% of the specified action number of the service life of the relay; the contact resistance value comprises a relay normally open contact resistance value and a normally closed contact resistance value;
s2: generating a test time sequence according to the resistance value of the contact resistor;
s3: modeling by using an Elman neural network, and continuously iteratively expanding the length of the total time sequence;
s4: and solving the contact performance failure action times of the relay.
Further, the relay acts once, and the steps are as follows:
s110: a 100mA direct current constant current source with an open circuit protection function is connected with a normally closed contact of the relay;
s120: confirming that the relay is in a release state;
s130: starting a direct current constant current source, and outputting constant direct current to the normally closed contact;
s140: closing the direct current constant current source;
s150: a direct-current constant-voltage source is used for supplying power to a relay coil to enable the relay to act;
s160: the direct current constant current source is connected with a normally open contact of the relay;
s170: confirming that the relay is in an action holding state;
s180: starting a direct current constant current source, and outputting constant direct current to a normally open contact;
s190: and turning off the direct current constant current source.
Further, the step of calculating the resistance value of the normally closed contact resistor is as follows every ten thousand times of actions of the relay:
s131: recording the voltage at two ends of the normally closed contact;
s132: transmitting the current data and the voltage data to a computer;
s133: calculating to obtain the normally closed contact resistance through ohm's law;
the steps of calculating the resistance value of the normally open contact resistor are as follows:
s181: recording the voltage at two ends of the normally open contact;
s182: transmitting the current data and the voltage data to a computer;
s183: and calculating to obtain the contact resistance of the normally open contact through ohm's law.
Further, modeling by using an Elman neural network, and continuously iteratively expanding the length of the total time sequence; the method comprises the following steps:
s310: establishing an Elman neural network, setting the number of nodes of an input layer to be 4, the number of nodes of an output layer to be 1, the number of nodes of a hidden layer to be 10, and setting the upper limit of training iteration times to be 100;
s320: training an Elman neural network by using a test time sequence until the state of the neuron does not change or the upper limit of the iteration times is reached;
s330: drawing a prediction time sequence according to the training data;
s340: comparing the predicted time sequence with the test time sequence, and finishing model training if the predicted time sequence and the test time sequence have the same change trend; if the variation trend of the predicted time sequence is inconsistent with that of the test time sequence, changing the number of nodes of the hidden layer, and repeating S320 to S330;
s350: using the last four times of data of the test time sequence as Elman network input, and predicting the last time of data of the time sequence as Elman network output;
s360: repeating S350 to increase the total time sequence length.
Further, the step of solving the number of contact performance failure actions of the relay is as follows:
s410: when the contact resistance value in the data of the total time sequence continuously exceeds the contact resistance threshold value of the relay for 3 times, recording the serial number in the data of the time sequence when the contact resistance value first exceeds the threshold value;
s420: and multiplying the serial number by ten thousand to obtain the contact performance failure action number of the relay.
Compared with the prior art, the beneficial effects are:
the invention provides a method for predicting the time sequence of contact resistance of a relay by adopting an Elman neural network, which uses the time sequence of the contact resistance in the first half life stage and judges the action times when the contact performance of the contact fails by iteratively generating the contact resistance value in the residual life stage. The method for evaluating the contact characteristics of the electromagnetic relay of the contact resistance time sequence has clear evaluation process and is progressive, the Elman neural network intelligent prediction algorithm is adopted to process the existing data, the contact resistance value at the residual life stage can be predicted, and the method has important significance for evaluating the contact performance of the electromagnetic relay.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a relay contact characteristic evaluation method based on a contact resistance time series of the present invention;
FIG. 2 is a circuit diagram of the relay contact characteristic measurement of the present invention;
fig. 3 is an Elman neural network topology of the present invention.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
A relay contact characteristic evaluation method based on contact resistance time sequence is disclosed, as shown in FIG. 1, and comprises the following steps:
s1: a relay contact resistance measurement loop is built, the relay is controlled to continuously act, the resistance value of the contact resistance at one time is calculated every ten thousand times of the relay action until the action times reach 50% of the specified action times of the service life of the relay; the contact resistance value comprises a normally open contact resistance value and a normally closed contact resistance value of the relay.
S2: generating a test time sequence according to the resistance value of the contact resistor;
s3: modeling by using an Elman neural network, and continuously iteratively expanding the length of the total time sequence;
s4: and solving the contact performance failure action times of the relay.
According to the invention, a relay contact characteristic measurement loop is firstly established, the relay is controlled to continuously act, and the action frequency reaches 50% of the specified action frequency. And (3) carrying out contact resistance measurement on the normally closed contact and the normally open contact once every ten thousand times of action to form a test time sequence, namely obtaining the contact resistance time sequence of the first half life stage. Training an Elman neural network to model the time sequence, when the fitting error of the contact resistance time sequence in the first half life stage is small, continuously iterating and predicting a future value by using the network, expanding the length of the time sequence, and finding out the action times corresponding to the contact resistance exceeding a threshold value, thereby evaluating the contact performance of the relay contact. The invention has clear process, gradual progress and combination of theory and reality.
Specifically, as shown in the relay contact characteristic measurement circuit diagram of fig. 2, the relay contact resistance is measured based on the four-wire method, the influence of the conductor resistance and the measurement circuit contact resistance is eliminated, and a small resistance value with high accuracy can be obtained. A 100mA dc constant current power supply including an open circuit protection function was used to supply current to the contacts. In step S1, the relay operates once, and the steps are as follows:
s110: a 100mA direct current constant current source with an open circuit protection function is connected with a normally closed contact of the relay;
s120: confirming that the relay is in a release state;
s130: starting a direct current constant current source, and outputting constant direct current to the normally closed contact;
s140: closing the direct current constant current source;
s150: a direct-current constant-voltage source is used for supplying power to a relay coil to enable the relay to act;
s160: the direct current constant current source is connected with a normally open contact of the relay;
s170: confirming that the relay is in an action holding state;
s180: starting a direct current constant current source, and outputting constant direct current to a normally open contact;
s190: and turning off the direct current constant current source.
Specifically, the acquisition card is used for acquiring the voltage at two ends of the contact, the voltage and current signals are transmitted to the industrial computer through Bluetooth, and the contact resistance can be obtained through calculation according to ohm's law. The relay is controlled to continuously act, contact resistance measurement is carried out once every ten thousand times of actions until the action frequency reaches 50% of the specified action frequency.
The step of calculating the resistance value of the normally closed contact resistor comprises the following steps:
s131: recording the voltage at two ends of the normally closed contact by using an acquisition card;
s132: the current data and the voltage data are transmitted to the industrial computer using the bluetooth transmission module. (ii) a
S133: calculating to obtain the normally closed contact resistance through ohm's law;
the steps of calculating the resistance value of the normally open contact resistor are as follows:
s181: recording the voltage at two ends of the normally open contact by using a collection card;
s182: transmitting the current data and the voltage data to an industrial computer by using a Bluetooth transmission module;
s183: and calculating to obtain the contact resistance of the normally open contact through ohm's law.
Specifically, modeling is carried out by using an Elman neural network, and the total time sequence length is continuously expanded in an iterative mode; the method comprises the following steps:
s310: establishing an Elman neural network, setting the number of nodes of an input layer to be 4, the number of nodes of an output layer to be 1, the number of nodes of a hidden layer to be 10, and setting the upper limit of training iteration times to be 100;
s320: training an Elman neural network by using a test time sequence, taking the contact resistance value calculated every 4 times as a network input parameter, taking the contact resistance value calculated in the 5 th time as a network output, and training until the state of a neuron is not changed or the upper limit of iteration times is reached;
s330: drawing a prediction time sequence according to the training data;
s340: comparing the predicted time sequence with the test time sequence, and finishing model training if the predicted time sequence and the test time sequence have the same change trend; if the variation trend of the predicted time sequence is inconsistent with that of the test time sequence, changing the number of nodes of the hidden layer, and repeating S320 to S330;
s350: using the last four times of data of the test time sequence as Elman network input, and predicting the last time of data of the time sequence as Elman network output;
s360: repeating S350 to increase the total time sequence length.
Such as the Elman neural network topology shown in figure 3. The Elman network is composed of an input layer, a hidden layer, a receiving layer and an output layer. The input layer only plays a role in transmitting input parameters, the hidden layer is used for mining and storing the internal relation between the input parameters and the output parameters, the receiving layer plays a role in time delay, the output at the migration moment of the hidden layer is returned to be used as the input of a network, and the output layer linearly weights the output of the hidden layer and then outputs the output. The characteristics of the Elman network structure determine that the Elman network structure has sensitivity to data of a historical state, and meanwhile, the existence of the feedback link also strengthens the processing capacity of the network on time-varying information, so that the Elman network structure is suitable for analyzing and modeling a time sequence, and prediction of future values in the time sequence is realized.
And predicting to obtain 5 th time series data by using the first 4 data in the test time series, adding the predicted time series data into the total time series each time, and continuously iterating and expanding the time series. And when the variation trend of the prediction time sequence is consistent with that of the test time sequence, finishing the model training. And (4) continuously iterating by using the model, predicting the contact resistance value of the relay in 50% service life, namely predicting the contact performance failure action times of the relay.
Specifically, in step S4, the step of calculating the number of times of contact performance failure operation of the relay is as follows:
s410: when the resistance value of the normally closed contact resistor or the resistance value of the normally open contact resistor in the data of the total time sequence continuously exceeds the threshold value of the contact resistor of the relay for 3 times, recording the serial number in the data of the time sequence when the threshold value is exceeded for the first time;
s420: and multiplying the serial number by ten thousand to obtain the contact performance failure action number of the relay. Since the measurement is performed once every ten thousand times, the number multiplied by ten thousand is the number of times of the operation corresponding to the number.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (5)
1. A relay contact characteristic evaluation method based on contact resistance time series is characterized in that: the method comprises the following steps:
s1: a relay contact resistance measurement loop is built, the relay is controlled to continuously act, the resistance value of the contact resistance at one time is calculated every time the relay acts for a certain number of times until the action number reaches 50% of the specified action number of the service life of the relay; the contact resistance value comprises a relay normally open contact resistance value and a normally closed contact resistance value;
s2: generating a test time sequence according to the resistance value of the contact resistor;
s3: modeling by using an Elman neural network, and continuously iteratively expanding the length of the total time sequence;
s4: and solving the contact performance failure action times of the relay.
2. The relay contact characteristic evaluation method based on the contact resistance time series according to claim 1, characterized in that: the relay acts once and comprises the following steps:
s110: a 100mA direct current constant current source with an open circuit protection function is connected with a normally closed contact of the relay;
s120: confirming that the relay is in a release state;
s130: starting a direct current constant current source, and outputting constant direct current to the normally closed contact;
s140: closing the direct current constant current source;
s150: a direct-current constant-voltage source is used for supplying power to a relay coil to enable the relay to act;
s160: the direct current constant current source is connected with a normally open contact of the relay;
s170: confirming that the relay is in an action holding state;
s180: starting a direct current constant current source, and outputting constant direct current to a normally open contact;
s190: and turning off the direct current constant current source.
3. The relay contact characteristic evaluation method based on the contact resistance time series according to claim 2, characterized in that: the method comprises the following steps of calculating the resistance value of the normally closed contact resistor every ten thousand times of actions of the relay:
s131: recording the voltage at two ends of the normally closed contact;
s132: transmitting the current data and the voltage data to a computer;
s133: calculating to obtain the normally closed contact resistance through ohm's law;
the steps of calculating the resistance value of the normally open contact resistor are as follows:
s181: recording the voltage at two ends of the normally open contact;
s182: transmitting the current data and the voltage data to a computer;
s183: and calculating to obtain the contact resistance of the normally open contact through ohm's law.
4. The relay contact characteristic evaluation method based on the contact resistance time series according to claim 3, characterized in that: modeling by using an Elman neural network, and continuously iteratively expanding the length of the total time sequence; the method comprises the following steps:
s310: establishing an Elman neural network, setting the number of nodes of an input layer to be 4, the number of nodes of an output layer to be 1, the number of nodes of a hidden layer to be 10, and setting the upper limit of training iteration times to be 100;
s320: training an Elman neural network by using a test time sequence until the state of the neuron does not change or the upper limit of the iteration times is reached;
s330: drawing a prediction time sequence according to the training data;
s340: comparing the predicted time sequence with the test time sequence, and finishing model training if the predicted time sequence and the test time sequence have the same change trend; if the variation trend of the predicted time sequence is inconsistent with that of the test time sequence, changing the number of nodes of the hidden layer, and repeating S320 to S330;
s350: using the last four times of data of the test time sequence as Elman network input, and predicting the last time of data of the time sequence as Elman network output;
s360: repeating S350 to increase the total time sequence length.
5. The relay contact characteristic evaluation method based on the contact resistance time series according to claim 4, characterized in that: the step of solving the failure action times of the contact performance of the relay is as follows:
s410: when the contact resistance value in the data of the total time sequence continuously exceeds the contact resistance threshold value of the relay for 3 times, recording the serial number in the data of the time sequence when the contact resistance value first exceeds the threshold value;
s420: and multiplying the serial number by ten thousand to obtain the contact performance failure action number of the relay.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111521997.1A CN114239394A (en) | 2021-12-13 | 2021-12-13 | Relay contact characteristic evaluation method based on contact resistance time sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111521997.1A CN114239394A (en) | 2021-12-13 | 2021-12-13 | Relay contact characteristic evaluation method based on contact resistance time sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114239394A true CN114239394A (en) | 2022-03-25 |
Family
ID=80755423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111521997.1A Pending CN114239394A (en) | 2021-12-13 | 2021-12-13 | Relay contact characteristic evaluation method based on contact resistance time sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239394A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062453A (en) * | 2022-05-18 | 2022-09-16 | 河北工业大学 | Relay service life prediction method |
| CN115097296A (en) * | 2022-06-22 | 2022-09-23 | 云南电网有限责任公司电力科学研究院 | Relay reliability evaluation method and device |
| CN116776631A (en) * | 2023-07-05 | 2023-09-19 | 深圳市精微康投资发展有限公司 | Connector performance evaluation method and system based on data analysis |
-
2021
- 2021-12-13 CN CN202111521997.1A patent/CN114239394A/en active Pending
Non-Patent Citations (4)
| Title |
|---|
| 姚芳等: ""基于概率分布和时间序列的接触失效组合预测模型"", 《电工技术学报》, no. 09, 26 September 2004 (2004-09-26), pages 46 - 50 * |
| 孙立军: ""触点电接触失效预测理论的研究"", 《中国优秀博硕士学位论文全文数据库 (硕士)工程科技Ⅱ辑》, no. 02, 15 December 2002 (2002-12-15), pages 042 - 110 * |
| 张国强: ""基于DBN的汽车电磁继电器寿命预测方法研究"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 02, 15 February 2020 (2020-02-15), pages 035 - 259 * |
| 王佳炜等: ""继电器寿命预测方法综述"", 《电器与能效管理技术》, no. 04, 28 February 2018 (2018-02-28), pages 1 - 5 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062453A (en) * | 2022-05-18 | 2022-09-16 | 河北工业大学 | Relay service life prediction method |
| CN115097296A (en) * | 2022-06-22 | 2022-09-23 | 云南电网有限责任公司电力科学研究院 | Relay reliability evaluation method and device |
| CN116776631A (en) * | 2023-07-05 | 2023-09-19 | 深圳市精微康投资发展有限公司 | Connector performance evaluation method and system based on data analysis |
| CN116776631B (en) * | 2023-07-05 | 2024-02-02 | 深圳市精微康投资发展有限公司 | Connector performance evaluation method and system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114239394A (en) | Relay contact characteristic evaluation method based on contact resistance time sequence | |
| da Silva et al. | Composite reliability assessment based on Monte Carlo simulation and artificial neural networks | |
| CN108896926B (en) | Lithium battery health state assessment method and system and related components | |
| CN107423414B (en) | Information transfer model-based process industry complex electromechanical system fault tracing method | |
| US20160239592A1 (en) | Data-driven battery aging model using statistical analysis and artificial intelligence | |
| CN113125095B (en) | Universal circuit breaker contact system residual mechanical life prediction method based on deep learning | |
| CN109271741A (en) | A kind of prediction of buck DC-DC power module remaining life and health evaluating method | |
| CN110763997A (en) | Early fault early warning method for synchronous motor stator | |
| CN114252731B (en) | Relay action characteristic evaluation method and device based on multiple parameters | |
| CN113516310A (en) | Transformer fault early warning method and system | |
| CN117708669A (en) | Multi-source data-based adaptive probability neural network high-voltage cable state evaluation method | |
| CN114781875B (en) | Micro-grid economic operation state evaluation method based on deep convolution network | |
| CN117040048A (en) | Wind-solar power generation energy storage management method and system | |
| CN113919198A (en) | Electrical fire monitoring and early warning method based on generation of countermeasure network | |
| CN114330642A (en) | Building power load prediction method for multiple sampling times | |
| Kirschbaum et al. | Prognostics for electromagnetic relays using deep learning | |
| Shettar et al. | Blackout prediction in smart grids using machine learning | |
| Winkel et al. | Run-to-failure relay dataset for predictive maintenance research with machine learning | |
| CN114791537A (en) | Method and system for predicting residual service life of industrial equipment based on attribute self-adaption | |
| Agarwal et al. | Applicability of ANN for Reliability Analysis of Distribution Network | |
| Bu et al. | Life Prediction of Electronic Equipment Based on the Fusion of Simulation Data and Measurement Data | |
| Monteiro et al. | Determination of Renewable Generation Operation with the Aid of the ANN | |
| Ibrahim et al. | An adaptive fuzzy technique for learning power-quality signature waveforms | |
| Kejie et al. | A Multi-sensor Fusion Approach for Susceptibility Analysis in Smart Substation based on Deep Bayesian Network | |
| CN114252807B (en) | Transformer life prediction method based on life differentiation phenomenon |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |