WO2023005467A1 - 一种定子绕组温度预警方法 - Google Patents
一种定子绕组温度预警方法 Download PDFInfo
- Publication number
- WO2023005467A1 WO2023005467A1 PCT/CN2022/098498 CN2022098498W WO2023005467A1 WO 2023005467 A1 WO2023005467 A1 WO 2023005467A1 CN 2022098498 W CN2022098498 W CN 2022098498W WO 2023005467 A1 WO2023005467 A1 WO 2023005467A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- stator winding
- winding temperature
- value
- measuring point
- time
- Prior art date
Links
- 238000004804 winding Methods 0.000 title claims abstract description 219
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000013598 vector Substances 0.000 claims description 70
- 238000004364 calculation method Methods 0.000 claims description 34
- 230000002159 abnormal effect Effects 0.000 claims description 33
- 230000005856 abnormality Effects 0.000 claims description 25
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 230000002542 deteriorative effect Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000002547 anomalous effect Effects 0.000 abstract 2
- 230000009191 jumping Effects 0.000 abstract 1
- 238000011156 evaluation Methods 0.000 description 6
- 238000002347 injection Methods 0.000 description 3
- 239000007924 injection Substances 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K1/00—Details of thermometers not specially adapted for particular types of thermometer
- G01K1/02—Means for indicating or recording specially adapted for thermometers
- G01K1/024—Means for indicating or recording specially adapted for thermometers for remote indication
Definitions
- the invention relates to the technical field of generators, in particular to a stator winding temperature early warning method.
- stator winding of a large generator is placed in the slot of the stator core, and the straight part is in the rotating main magnetic field, which induces high voltage and high current and transmits it to the grid.
- the stator winding is a key part of the generator energy conversion and output electric energy, and its operating status directly affects whether the entire unit can operate safely and stably. Because the stator winding current of a large generator is very large, the stator current of the turbogenerator with a power of 300MW and 600MW exceeds 10000A and 20000A respectively, so the stator winding is one of the components with the largest loss and heat generation of the generator.
- stator thermal failure is a common failure of generators.
- stator winding temperature is a key symptom of this type of failure
- each power plant pays special attention to the temperature of the stator winding.
- Large steam turbines with internal water cooling are used to generate electricity Taking the machine as an example, the water inlet and outlet ends of the stator winding are equipped with temperature detectors, and at the same time, there are also temperature detectors buried between the upper and lower wire rods of each groove.
- a limit value alarm mechanism that is, set a temperature limit value. Once the temperature measurement point data arranged on the stator winding exceeds this value, an alarm signal will be sent to remind the power plant monitoring personnel to confirm and deal with it.
- the temperature limit alarm value is general. Set according to the design or related standards. For large water-cooled turbogenerators, the temperature alarm value at the outlet end of the stator winding is 85°C, and the alarm value in the tank is 90°C. This alarm mechanism only alarms when the stator winding of the generator has obvious faults and reaches the limit. However, in order to meet the requirements of the power grid, the operation mode of large generator sets is more flexible than before, with frequent deep peak regulation and long-term low-load operation.
- stator current is much lower than the rated current.
- temperature of the outlet end of the stator winding and the tank is much lower than the normal rated working condition.
- the fixed The monitoring function of the limit alarm is greatly weakened, and the early symptoms of the stator thermal failure cannot be found effectively and timely.
- the publication number is CN 108847799A, and the Chinese patent literature published on November 20, 2018 discloses a method for online detection of PMSM stator winding temperature based on signal injection.
- the online detection method of PMSM stator winding temperature based on signal injection disclosed in this patent document can monitor the health status of the motor and prevent overheating by estimating the stator winding temperature of the permanent magnet synchronous motor online. It can also be used in the optimal control of active thermal management motors , which is conducive to improving the performance of the electric drive system. However, abnormal temperature data cannot be identified in time, and the accuracy of early warning is low.
- the present invention provides a stator winding temperature early warning method.
- the present invention is based on a self-assessment and alarm mechanism based on online temperature calculation, and uses the dynamically changing theoretical normal value of temperature as the evaluation standard.
- the evaluation standard is related to the operation of the generator Working conditions are closely related, and it can identify abnormal temperature data in time, find early thermal faults, combine counter counting, and when the number of overruns accumulates to a certain value, an abnormal alarm will be issued, and it has a certain degree of fault tolerance for temperature data drift in non-abnormal conditions Ability, temperature warning is more accurate.
- the present invention realizes through following technical scheme:
- ⁇ ' t is the predicted value of stator winding temperature measuring point operation at time t
- ⁇ tn is the actual operating value of stator winding temperature measuring point before time t
- ⁇ 1 , ⁇ 2 ... ⁇ n is the weighting coefficient vector
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of the stator winding temperature measuring point at ti time
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ t+1-i is the actual operation of stator winding temperature measuring point at time t+1-i value, is the disturbance amount
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of stator winding temperature measuring point at time ti, is the disturbance amount
- step S5 If the value of the abnormality counter is less than the total number of early warnings N 0 , and the value of the judgment counter is less than the total number of judgment intervals N, move back one moment and jump to step S2;
- the abnormal counter is less than the total number of early warnings N 0 , and the value of the judgment counter is greater than or equal to the total number of judgment intervals N, it is considered that the actual operating values of the stator winding temperature measuring points with a total of N judgment intervals are normal, and the abnormality calculator and judgment counter Set all to zero, move back one moment, jump to step S2, and start the next round of judgment;
- identifying the coefficient vector required for the online calculation of the stator winding temperature specifically refers to the total n value of the selected coefficient vector, selecting the continuous operation data of the stator winding temperature measuring point for a period of time, setting the initial value of the coefficient vector iteration, and passing The least squares method or neural network identification coefficient vector, after the calculation error is stable in the statistical identification process, judge whether the ratio of the number whose error is smaller than the convergence error value to the total is up to the standard, if not, reselect the total number n of the coefficient vector, and adjust the parameters Continue to identify; if so, output the coefficient vector.
- ⁇ is the absolute deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point operating at time t.
- ⁇ is the relative deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point at time t.
- the threshold K is inversely proportional to the actual operating value ⁇ t of the stator winding temperature measuring point at time t, the larger the actual operating value ⁇ t of the stator winding temperature measuring point at time t, the smaller the threshold K.
- the total number N of early warnings is less than or equal to the total number N of judgment intervals.
- the theoretical normal value of the temperature of each measuring point of the stator winding under any load is obtained.
- the theoretical normal value of the temperature is obtained through in-depth research on the mechanism and structure of the generator and repeated verification, and then the measured operating value of the generator and the theoretical normal temperature Value comparison, real-time evaluation of generator operating status, when the operating data of the measuring point of the unit deviates from a certain threshold compared with the theoretical normal value of temperature, it will be counted, and when the count reaches a certain value within a certain period of time, an alarm will be issued.
- the self-evaluation alarm mechanism based on online temperature calculation uses the dynamically changing theoretical normal value of temperature as the judgment standard, which is closely related to the operating conditions of the generator, and can identify abnormalities in time Temperature data, early thermal faults are found, combined with counter counting, when the number of overruns accumulates to a certain value, an abnormal alarm is issued, and the temperature data drifts under non-abnormal conditions, with a certain fault tolerance capability, and the temperature early warning is more accurate.
- the present invention according to the operating temperature characteristics of the stator winding, only introduces the recent temperature operating value and a set of coefficient vectors to describe the normal operating characteristics of the part where the temperature measurement point of the stator winding is located, and obtains the local temperature of the stator winding through real-time online calculation, instead of The average temperature of the stator windings and thus better validity for generator health assessment.
- the present invention is applicable to different load conditions of flexible operation of generators. It can model the temperature measuring points of the stator windings separately, and extract coefficient vectors that meet their respective operating characteristics, so as to build a high-precision calculation model to ensure calculation accuracy. .
- the present invention by introducing the normal operating value of the temperature in the past, does not need to inject high-frequency signals, avoids the risk of safe operation of the generator, is suitable for different load conditions, has high adaptability to each temperature measuring point of the stator winding, and can Satisfying the individualized operating characteristics of each measuring point, the local temperature of the stator winding can be calculated online in real time, and the calculation accuracy is high, which greatly improves the effect of generator health assessment.
- Fig. 1 is a flowchart of the present invention.
- a stator winding temperature early warning method includes the following steps:
- ⁇ ' t is the predicted value of stator winding temperature measuring point operation at time t
- ⁇ tn is the actual operating value of stator winding temperature measuring point before time t
- ⁇ 1 , ⁇ 2 ... ⁇ n is the weighting coefficient vector
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of the stator winding temperature measuring point at ti time
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ t+1-i is the actual operation of stator winding temperature measuring point at time t+1-i value, is the disturbance amount
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of stator winding temperature measuring point at time ti, is the disturbance amount
- step S5 If the value of the abnormality counter is less than the total number of early warnings N 0 , and the value of the judgment counter is less than the total number of judgment intervals N, move back one moment and jump to step S2;
- the abnormal counter is less than the total number of early warnings N 0 , and the value of the judgment counter is greater than or equal to the total number of judgment intervals N, it is considered that the actual operating values of the stator winding temperature measuring points with a total of N judgment intervals are normal, and the abnormality calculator and judgment counter Set all to zero, move back one moment, jump to step S2, and start the next round of judgment;
- This embodiment is the most basic implementation mode.
- the self-assessment alarm mechanism based on online temperature calculation uses the dynamically changing theoretical normal value of temperature as the evaluation standard, and the evaluation standard is closely related to the operating conditions of the generator. , can identify abnormal temperature data in time, find early thermal faults, combined with counter counting, when the number of overruns accumulates to a certain value, an abnormal alarm will be issued, and the temperature data will drift under non-abnormal conditions, with certain fault tolerance and temperature early warning more acurrate.
- a stator winding temperature early warning method includes the following steps:
- ⁇ ' t is the predicted value of stator winding temperature measuring point operation at time t
- ⁇ tn is the actual operating value of stator winding temperature measuring point before time t
- ⁇ 1 , ⁇ 2 ... ⁇ n is the weighting coefficient vector
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of the stator winding temperature measuring point at ti time
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ t+1-i is the actual operation of stator winding temperature measuring point at time t+1-i value, is the disturbance amount
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of stator winding temperature measuring point at time ti, is the disturbance amount
- step S5 If the value of the abnormality counter is less than the total number of early warnings N 0 , and the value of the judgment counter is less than the total number of judgment intervals N, move back one moment and jump to step S2;
- the abnormal counter is less than the total number of early warnings N 0 , and the value of the judgment counter is greater than or equal to the total number of judgment intervals N, it is considered that the actual operating values of the stator winding temperature measuring points with a total of N judgment intervals are normal, and the abnormality calculator and judgment counter Set all to zero, move back one moment, jump to step S2, and start the next round of judgment;
- identifying the coefficient vector required for the online calculation of the stator winding temperature specifically refers to the total n value of the selected coefficient vector, selecting the continuous operation data of the stator winding temperature measuring point for a period of time, setting the initial value of the coefficient vector iteration, and passing The least squares method or neural network identification coefficient vector, after the calculation error is stable in the statistical identification process, judge whether the ratio of the number whose error is smaller than the convergence error value to the total is up to the standard, if not, reselect the total number n of the coefficient vector, and adjust the parameters Continue to identify; if so, output the coefficient vector.
- This embodiment is a better implementation mode. According to the operating temperature characteristics of the stator winding, only the recent temperature operating value and a set of coefficient vectors can be introduced to describe the normal operating characteristics of the part where the temperature measurement point of the stator winding is located, and the stator winding can be obtained by real-time online calculation. The local temperature, rather than the average temperature of the stator winding, is therefore more valid for generator health assessment.
- a stator winding temperature early warning method includes the following steps:
- ⁇ ' t is the predicted value of stator winding temperature measuring point operation at time t
- ⁇ tn is the actual operating value of stator winding temperature measuring point before time t
- ⁇ 1 , ⁇ 2 ... ⁇ n is the weighting coefficient vector
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of the stator winding temperature measuring point at ti time
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ t+1-i is the actual operation of stator winding temperature measuring point at time t+1-i value, is the disturbance amount
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of stator winding temperature measuring point at time ti, is the disturbance amount
- step S5 If the value of the abnormality counter is less than the total number of early warnings N 0 , and the value of the judgment counter is less than the total number of judgment intervals N, move back one moment and jump to step S2;
- the abnormal counter is less than the total number of early warnings N 0 , and the value of the judgment counter is greater than or equal to the total number of judgment intervals N, it is considered that the actual operating values of the stator winding temperature measuring points with a total of N judgment intervals are normal, and the abnormality calculator and judgment counter Set all to zero, move back one moment, jump to step S2, and start the next round of judgment;
- ⁇ is the absolute deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point operating at time t.
- ⁇ is the relative deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point at time t.
- This embodiment is another preferred implementation mode, which is suitable for different load conditions of generator flexible operation, and can model the temperature measurement points of the stator winding separately, and extract coefficient vectors that meet the respective operating characteristics, so as to construct high-precision Calculation model to ensure calculation accuracy.
- a stator winding temperature early warning method includes the following steps:
- ⁇ ' t is the predicted value of stator winding temperature measuring point operation at time t
- ⁇ tn is the actual operating value of stator winding temperature measuring point before time t
- ⁇ 1 , ⁇ 2 ... ⁇ n is the weighting coefficient vector
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of the stator winding temperature measuring point at ti time
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ t+1-i is the actual operation of stator winding temperature measuring point at time t+1-i value, is the disturbance amount
- ⁇ ' t+1 is the predicted value of stator winding temperature measuring point operation at time t+1
- ⁇ i is the weighting coefficient vector
- ⁇ ti is the actual operating value of stator winding temperature measuring point at time ti, is the disturbance amount
- step S5 If the value of the abnormality counter is less than the total number of early warnings N 0 , and the value of the judgment counter is less than the total number of judgment intervals N, move back one moment and jump to step S2;
- the abnormal counter is less than the total number of early warnings N 0 , and the value of the judgment counter is greater than or equal to the total number of judgment intervals N, it is considered that the actual operating values of the stator winding temperature measuring points with a total of N judgment intervals are normal, and the abnormality calculator and judgment counter Set all to zero, move back one moment, jump to step S2, and start the next round of judgment;
- identifying the coefficient vector required for the online calculation of the stator winding temperature specifically refers to the total n value of the selected coefficient vector, selecting the continuous operation data of the stator winding temperature measuring point for a period of time, setting the initial value of the coefficient vector iteration, and passing The least squares method or neural network identification coefficient vector, after the calculation error is stable in the statistical identification process, judge whether the ratio of the number whose error is smaller than the convergence error value to the total is up to the standard, if not, reselect the total number n of the coefficient vector, and adjust the parameters Continue to identify; if so, output the coefficient vector.
- ⁇ is the absolute deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point operating at time t.
- ⁇ is the relative deviation
- ⁇ t is the actual operating value of the stator winding temperature measuring point at time t
- ⁇ ' t is the predicted value of the stator winding temperature measuring point at time t.
- the threshold K is inversely proportional to the actual operating value ⁇ t of the stator winding temperature measuring point at time t, the larger the actual operating value ⁇ t of the stator winding temperature measuring point at time t, the smaller the threshold K.
- the total number N of early warnings is less than or equal to the total number N of judgment intervals.
- This embodiment is the best implementation mode.
- By introducing the normal operating value of the temperature in the past there is no need to inject high-frequency signals, which avoids the risk of safe operation of the generator. It is suitable for different load conditions and adapts to the temperature measurement points of the stator winding. High performance, can meet the personalized operation characteristics of each measuring point, real-time online calculation to obtain the local temperature of the stator winding, and the calculation accuracy is high, which greatly improves the effect of generator health assessment.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
- Protection Of Generators And Motors (AREA)
Abstract
本发明公开了一种定子绕组温度预警方法，属于发电机领域，其特征在于，包括以下步骤：S1、设置门槛阈值K、判断区间总数N和预警总数N 0；S2、计算θ' t；S3、若θ' t与θ t的偏差在K内，判定θ t正常，判断计数器加1，异常计数器不变；S4、若θ' t与θ t的偏差超出K，判定θ t异常，判断计数器加1，且异常计数器加1；S5、若异常计数器的值小于N 0，且判断计数器的值小于N，跳转步骤S2；S6、异常计算器与判断计数器均置零；S7、若异常计数器的值大于或等于N 0，则发出预警信号。本发明能识别异常温度数据，发现早期热故障，结合计数器计数，当超限次数累积一定值时，才发出异常报警，温度预警更准确。
Description
本发明涉及到发电机技术领域，尤其涉及一种定子绕组温度预警方法。
大型发电机的定子绕组放在定子铁芯的槽内，直线部分处于旋转的主磁场中，感应出高电压与大电流，输向电网。定子绕组作为发电机能量转换及输出电能的关键部件，其运行状态的优劣直接影响整个机组能否安全稳定运行。由于大型发电机的定子绕组电流很大，功率在300MW和600MW的汽轮发电机定子电流分别超过10000A和20000A，因此定子绕组是发电机损耗发热最大的部件之一。统计数据表明，定子热故障是发电机的常见故障，由于定子绕组温度是该类故障的关键性征兆，因此，每个电厂对定子绕组温度给予格外的关注，以水内冷的大型汽轮发电机为例，定子绕组的进出水端都装有温度检测计，同时，在每个槽的上下层线棒之间也都埋有槽内检温计。
目前电厂普遍采用固定极限值报警机制，即设置一个温度极限值，一旦布置在定子绕组上的温度测点数据超过该值，就发出报警信号，提醒电厂监控人员确认与处理，温度极限报警值一般根据设计或相关标准来进行设定，对于大型水内冷汽轮发电机，定子绕组出水端温度报警值是85℃，槽内报警值是90℃。这种报警机制是在发电机定子绕组出现明显故障并达到极限时才报警，然而为满足电网要求，大型发电机组的运行方式较以往更为灵活，频繁地深度调峰，长时间低负荷运行，使得定子电流远低于额定电流，相应地，定子绕组出水端与槽内温度对比正常额定工况也低得多，在这种情况下，当出现早期热故障但并没超过极限值时，固定极限报警的监控作用就大大减弱了，不能有效及时地发现定子热故障的早期征兆。
公开号为CN 108847799A，公开日为2018年11月20日的中国专利文献公开了一种基于信号注入的PMSM定子绕组温度在线检测的方法，其特征在于，包括以下步骤：步骤一，建立永磁同步电机定子绕组的实时温度观测方法；步骤二，在步骤一的温度观测方法中加入最优注入信号策略。
该专利文献公开的基于信号注入的PMSM定子绕组温度在线检测的方法，通过在线估计永磁同步电机定子绕组温度，能够监测电机健康状况，防止过温发生，还可用于主动热管理电机优化控制中，有利于提高电驱动 系统性能。但是，不能及时识别异常温度数据，预警准确度低。
发明内容
本发明为了克服上述现有技术的缺陷，提供一种定子绕组温度预警方法，本发明基于温度在线计算的自评估报警机制，以动态变化的温度理论正常值作为评判标准，评判标准与发电机运行工况紧密相关，能够及时识别异常温度数据，发现早期热故障，结合计数器计数，当超限次数累积一定值时，才发出异常报警，对温度数据在非异常情况下发生漂移，具备一定的容错能力，温度预警更准确。
本发明通过下述技术方案实现：
一种定子绕组温度预警方法，其特征在于，包括以下步骤：
S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N
0；
S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’
t；
其中，θ’
t为t时刻的定子绕组温度测点运行预测值，θ
t-1,θ
t-2…θ
t-n为t时刻以前的定子绕组温度测点实际运行值，α
1,α
2…α
n为加权系数向量，
为扰动量，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ
t正常，判断计数器加1，异常计数器不变，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式2计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,
为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ
t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ
t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式3计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值，
为扰动量；
S5、若异常计数器的值小于预警总数N
0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；
S6、若异常计数器的值小于预警总数N
0，且判断计数器的值大于或等于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；
S7、若异常计数器的值大于或等于预警总数N
0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断。
所述步骤S1中，辨识定子绕组温度在线计算所需的系数向量具体是指选定系数向量总数n值，选取一段时间定子绕组温度测点的连续运行数据，设定系数向量迭代初始值，通过最小二乘法或神经网络辨识系数向量，统计辨识过程中计算误差稳定后，判断误差小于收敛误差值的数量占总数的 比例值是否达标，若否，则重新选定系数向量总数n值，调整参数继续辨识；若是，则输出系数向量。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用绝对偏差σ，绝对偏差σ通过式4计算；
σ＝|θ
t-θ’
t| 式4
其中，σ为绝对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用相对偏差λ，相对偏差λ通过式5计算；
λ＝|θ
t-θ’
t|/θ
t 式5
其中，λ为相对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
所述门槛阈值K与t时刻的定子绕组温度测点实际运行值θ
t呈反比，t时刻的定子绕组温度测点实际运行值θ
t越大，门槛阈值K越小。
所述预警总数N
0小于或等于判断区间总数N。
本发明的基本原理如下：
通过研究得出在任意负载下定子绕组各个测点的温度理论正常值，温度理论正常值是通过对发电机机理及结构的深入研究及反复验证获取，然后通过发电机实测运行值与温度理论正常值的比较，实时对发电机运行状况进行评估，当该机组测点运行数据对比温度理论正常值偏离一定阈值时，予以计数，当一定时间内，计数达到一定值，则发出报警。
本发明的有益效果主要表现在以下方面：
一、本发明，与固定极限值报警相比，基于温度在线计算的自评估报警机制，以动态变化的温度理论正常值作为评判标准，评判标准与发电机运行工况紧密相关，能够及时识别异常温度数据，发现早期热故障，结合计数器计数，当超限次数累积一定值时，才发出异常报警，对温度数据在 非异常情况下发生漂移，具备一定的容错能力，温度预警更准确。
二、本发明，依据定子绕组运行温度特性，仅引入近期温度运行值及一组系数向量就能够描述定子绕组温度测点所在局部的正常运行特征，实时在线计算得出定子绕组局部温度，而不是定子绕组的平均温度，因而对发电机健康评估的有效性更好。
三、本发明，适用于发电机灵活性运行的不同负载工况，可对定子绕组各温度测点分别建模，提取出符合各自运行特征的系数向量，以此构建高精度计算模型，确保计算精度。
四、本发明，通过引入以往时刻温度的正常运行值，无需注入高频信号，避免了发电机安全运行风险，适用于不同负载工况，对定子绕组各个温度测点的适配性高，能够满足各测点个性化的运行特征，实时在线计算得出定子绕组局部温度，且计算精度高，极大的提高了对发电机健康评估的效果。
下面将结合说明书附图和具体实施方式对本发明作进一步的具体说明：
图1为本发明的流程框图。
实施例1
参见图1，一种定子绕组温度预警方法，包括以下步骤：
S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N
0；
S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’
t；
其中，θ’
t为t时刻的定子绕组温度测点运行预测值，θ
t-1,θ
t-2…θ
t-n为t时刻以前的定子绕组温度测点实际运行值，α
1,α
2…α
n为加权系数向量，
为扰动量，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ
t正常，判断计数器加1，异常计数器不变，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式2计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,
为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ
t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ
t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式3计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值，
为扰动量；
S5、若异常计数器的值小于预警总数N
0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；
S6、若异常计数器的值小于预警总数N
0，且判断计数器的值大于或等 于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；
S7、若异常计数器的值大于或等于预警总数N
0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断。
本实施例为最基本的实施方式，与固定极限值报警相比，基于温度在线计算的自评估报警机制，以动态变化的温度理论正常值作为评判标准，评判标准与发电机运行工况紧密相关，能够及时识别异常温度数据，发现早期热故障，结合计数器计数，当超限次数累积一定值时，才发出异常报警，对温度数据在非异常情况下发生漂移，具备一定的容错能力，温度预警更准确。
实施例2
参见图1，一种定子绕组温度预警方法，包括以下步骤：
S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N
0；
S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’
t；
其中，θ’
t为t时刻的定子绕组温度测点运行预测值，θ
t-1,θ
t-2…θ
t-n为t时刻以前的定子绕组温度测点实际运行值，α
1,α
2…α
n为加权系数向量，
为扰动量，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ
t正常，判断计数器加1，异常计数器不变，则 t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式2计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,
为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ
t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ
t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式3计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值，
为扰动量；
S5、若异常计数器的值小于预警总数N
0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；
S6、若异常计数器的值小于预警总数N
0，且判断计数器的值大于或等于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；
S7、若异常计数器的值大于或等于预警总数N
0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始 下一轮判断。
所述步骤S1中，辨识定子绕组温度在线计算所需的系数向量具体是指选定系数向量总数n值，选取一段时间定子绕组温度测点的连续运行数据，设定系数向量迭代初始值，通过最小二乘法或神经网络辨识系数向量，统计辨识过程中计算误差稳定后，判断误差小于收敛误差值的数量占总数的比例值是否达标，若否，则重新选定系数向量总数n值，调整参数继续辨识；若是，则输出系数向量。
本实施例为一较佳实施方式，依据定子绕组运行温度特性，仅引入近期温度运行值及一组系数向量就能够描述定子绕组温度测点所在局部的正常运行特征，实时在线计算得出定子绕组局部温度，而不是定子绕组的平均温度，因而对发电机健康评估的有效性更好。
实施例3
参见图1，一种定子绕组温度预警方法，包括以下步骤：
S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N
0；
S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’
t；
其中，θ’
t为t时刻的定子绕组温度测点运行预测值，θ
t-1,θ
t-2…θ
t-n为t时刻以前的定子绕组温度测点实际运行值，α
1,α
2…α
n为加权系数向量，
为扰动量，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ
t正常，判断计数器加1，异常计数器不变，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式2计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,
为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ
t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ
t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式3计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值，
为扰动量；
S5、若异常计数器的值小于预警总数N
0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；
S6、若异常计数器的值小于预警总数N
0，且判断计数器的值大于或等于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；
S7、若异常计数器的值大于或等于预警总数N
0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断。
所述步骤S1中，辨识定子绕组温度在线计算所需的系数向量具体是指 选定系数向量总数n值，选取一段时间定子绕组温度测点的连续运行数据，设定系数向量迭代初始值，通过最小二乘法或神经网络辨识系数向量，统计辨识过程中计算误差稳定后，判断误差小于收敛误差值的数量占总数的比例值是否达标，若否，则重新选定系数向量总数n值，调整参数继续辨识；若是，则输出系数向量。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用绝对偏差σ，绝对偏差σ通过式4计算；
σ＝|θ
t-θ’
t| 式4
其中，σ为绝对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用相对偏差λ，相对偏差λ通过式5计算；
λ＝|θ
t-θ’
t|/θ
t 式5
其中，λ为相对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
本实施例为又一较佳实施方式，适用于发电机灵活性运行的不同负载工况，可对定子绕组各温度测点分别建模，提取出符合各自运行特征的系数向量，以此构建高精度计算模型，确保计算精度。
实施例4
参见图1，一种定子绕组温度预警方法，包括以下步骤：
S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N
0；
S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’
t；
其中，θ’
t为t时刻的定子绕组温度测点运行预测值，θ
t-1,θ
t-2…θ
t-n为t时刻以前的定子绕组温度测点实际运行值，α
1,α
2…α
n为加权系数向量，
为扰动量，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ
t正常，判断计数器加1，异常计数器不变，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式2计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,
为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ
t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ
t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’
t+1通过式3计算确定；
其中，θ’
t+1为t+1时刻的定子绕组温度测点运行预测值，α
i为加权系数向量，θ
t-i为t-i时刻的定子绕组温度测点实际运行值，
为扰动量；
S5、若异常计数器的值小于预警总数N
0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；
S6、若异常计数器的值小于预警总数N
0，且判断计数器的值大于或等于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；
S7、若异常计数器的值大于或等于预警总数N
0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断。
所述步骤S1中，辨识定子绕组温度在线计算所需的系数向量具体是指选定系数向量总数n值，选取一段时间定子绕组温度测点的连续运行数据，设定系数向量迭代初始值，通过最小二乘法或神经网络辨识系数向量，统计辨识过程中计算误差稳定后，判断误差小于收敛误差值的数量占总数的比例值是否达标，若否，则重新选定系数向量总数n值，调整参数继续辨识；若是，则输出系数向量。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用绝对偏差σ，绝对偏差σ通过式4计算；
σ＝|θ
t-θ’
t| 式4
其中，σ为绝对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
所述t时刻的定子绕组温度测点运行预测值θ’
t与t时刻的定子绕组温度测点实际运行值θ
t的偏差采用相对偏差λ，相对偏差λ通过式5计算；
λ＝|θ
t-θ'
t|/θ
t 式5
其中，λ为相对偏差，θ
t为t时刻的定子绕组温度测点实际运行值，θ’
t为t时刻的定子绕组温度测点运行预测值。
所述门槛阈值K与t时刻的定子绕组温度测点实际运行值θ
t呈反比，t时刻的定子绕组温度测点实际运行值θ
t越大，门槛阈值K越小。
所述预警总数N
0小于或等于判断区间总数N。
本实施例为最佳实施方式，通过引入以往时刻温度的正常运行值，无需注入高频信号，避免了发电机安全运行风险，适用于不同负载工况，对定子绕组各个温度测点的适配性高，能够满足各测点个性化的运行特征，实时在线计算得出定子绕组局部温度，且计算精度高，极大的提高了对发电机健康评估的效果。
Claims (6)
- 一种定子绕组温度预警方法，其特征在于，包括以下步骤：S1、设定辨识收敛误差值和占比值，辨识定子绕组温度在线计算所需的系数向量，设置门槛阈值K、判断区间总数N和预警总数N 0；S2、提取n个定子绕组温度连续运行值，根据系数向量通过式1计算t时刻的定子绕组温度测点运行预测值θ’ t；
其中，θ’ t为t时刻的定子绕组温度测点运行预测值，θ t-1,θ t-2…θ t-n为t时刻以前的定子绕组温度测点实际运行值，α 1,α 2…α n为加权系数向量，为扰动量，α i为加权系数向量，θ t-i为t-i时刻的定子绕组温度测点实际运行值；
S3、若t时刻的定子绕组温度测点运行预测值θ’ t与t时刻的定子绕组温度测点实际运行值θ t的偏差在门槛阈值K以内时，判定为t时刻的定子绕组温度测点实际运行值θ t正常，判断计数器加1，异常计数器不变，则t+1时刻的定子绕组温度测点运行预测值θ’ t+1通过式2计算确定；
其中，θ’ t+1为t+1时刻的定子绕组温度测点运行预测值，α i为加权系数向量，θ t+1-i为t+1-i时刻的定子绕组温度测点实际运行值,为扰动量；
S4、若t时刻的定子绕组温度测点运行预测值θ’ t与t时刻的定子绕组 温度测点实际运行值θ t的偏差超出门槛阈值K时，判定为t时刻的定子绕组温度测点实际运行值θ t不符合正常特征，为异常数据，判断计数器加1，且异常计数器加1，并剔除t时刻的定子绕组温度测点实际运行值θ t，不参与后续计算，则t+1时刻的定子绕组温度测点运行预测值θ’ t+1通过式3计算确定；
其中，θ’ t+1为t+1时刻的定子绕组温度测点运行预测值，α i为加权系数向量，θ t-i为t-i时刻的定子绕组温度测点实际运行值，为扰动量；
S5、若异常计数器的值小于预警总数N 0，且判断计数器的值小于判断区间总数N，往后移动一个时刻，跳转步骤S2；S6、若异常计数器的值小于预警总数N 0，且判断计数器的值大于或等于判断区间总数N，则认为判断区间总数N个的定子绕组温度测点实际运行值正常，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断；S7、若异常计数器的值大于或等于预警总数N 0，则认为判断计数器所包含的区间的定子绕组温度测点实际运行值出现劣化趋势，发出预警信号，异常计算器与判断计数器均置零，往后移动一个时刻，跳转步骤S2，开始下一轮判断。 - 根据权利要求1所述的一种定子绕组温度预警方法，其特征在于：所述步骤S1中，辨识定子绕组温度在线计算所需的系数向量具体是指选定系数向量总数n值，选取一段时间定子绕组温度测点的连续运行数据，设定系数向量迭代初始值，通过最小二乘法或神经网络辨识系数向量，统计辨识过程中计算误差稳定后，判断误差小于收敛误差值的数量占总数的比例值是否达标，若否，则重新选定系数向量总数n值，调整参数继续辨识；若是，则输出系数向量。
- 根据权利要求1所述的一种定子绕组温度预警方法，其特征在于：所述t时刻的定子绕组温度测点运行预测值θ’ t与t时刻的定子绕组温度测 点实际运行值θ t的偏差采用绝对偏差σ，绝对偏差σ通过式4计算；σ＝|θ t-θ’ t| 式4其中，σ为绝对偏差，θ t为t时刻的定子绕组温度测点实际运行值，θ’ t为t时刻的定子绕组温度测点运行预测值。
- 根据权利要求1所述的一种定子绕组温度预警方法，其特征在于：所述t时刻的定子绕组温度测点运行预测值θ’ t与t时刻的定子绕组温度测点实际运行值θ t的偏差采用相对偏差λ，相对偏差λ通过式5计算；λ＝|θ t-θ’ t|/θ t 式5其中，λ为相对偏差，θ t为t时刻的定子绕组温度测点实际运行值，θ’ t为t时刻的定子绕组温度测点运行预测值。
- 根据权利要求1所述的一种定子绕组温度预警方法，其特征在于：所述门槛阈值K与t时刻的定子绕组温度测点实际运行值θ t呈反比，t时刻的定子绕组温度测点实际运行值θ t越大，门槛阈值K越小。
- 根据权利要求1所述的一种定子绕组温度预警方法，其特征在于：所述预警总数N 0小于或等于判断区间总数N。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110865263.9 | 2021-07-29 | ||
| CN202110865263.9A CN113588123B (zh) | 2021-07-29 | 2021-07-29 | 一种定子绕组温度预警方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023005467A1 true WO2023005467A1 (zh) | 2023-02-02 |
Family
ID=78252026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/098498 WO2023005467A1 (zh) | 2021-07-29 | 2022-06-14 | 一种定子绕组温度预警方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113588123B (zh) |
| WO (1) | WO2023005467A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688834A (zh) * | 2023-12-11 | 2024-03-12 | 北京京能能源技术研究有限责任公司 | 一种水氢氢汽轮发电机线圈绝缘过热故障预警方法 |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588123B (zh) * | 2021-07-29 | 2023-01-06 | 东方电气集团东方电机有限公司 | 一种定子绕组温度预警方法 |
| CN114199505B (zh) * | 2021-11-29 | 2024-04-09 | 中电华创(苏州)电力技术研究有限公司 | 一种基于相关性分析的发电机定子线棒流通性评价方法 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004021842A (ja) * | 2002-06-19 | 2004-01-22 | Japan Research Institute Ltd | 回転機の熱解析方法、回転機の熱解析装置、コンピュータプログラム、及び記録媒体 |
| CN110414155A (zh) * | 2019-07-31 | 2019-11-05 | 北京天泽智云科技有限公司 | 一种带有单测点的风机部件温度异常检测和报警方法 |
| CN112504511A (zh) * | 2020-12-15 | 2021-03-16 | 润电能源科学技术有限公司 | 一种发电机定子温度监测方法、装置及介质 |
| CN112711832A (zh) * | 2020-12-08 | 2021-04-27 | 重庆理工大学 | 同步发电机定子绕组温度预警与故障识别的方法与系统 |
| CN113588123A (zh) * | 2021-07-29 | 2021-11-02 | 东方电气集团东方电机有限公司 | 一种定子绕组温度预警方法 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108897954A (zh) * | 2018-06-29 | 2018-11-27 | 龙源（北京）风电工程技术有限公司 | 基于BootStrap置信度计算的风电机组温度预警方法及其系统 |
| CN111016946A (zh) * | 2019-12-25 | 2020-04-17 | 新誉轨道交通科技有限公司 | 轨道车辆及其空调用温度传感器故障检测系统 |
-
2021
- 2021-07-29 CN CN202110865263.9A patent/CN113588123B/zh active Active
-
2022
- 2022-06-14 WO PCT/CN2022/098498 patent/WO2023005467A1/zh unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004021842A (ja) * | 2002-06-19 | 2004-01-22 | Japan Research Institute Ltd | 回転機の熱解析方法、回転機の熱解析装置、コンピュータプログラム、及び記録媒体 |
| CN110414155A (zh) * | 2019-07-31 | 2019-11-05 | 北京天泽智云科技有限公司 | 一种带有单测点的风机部件温度异常检测和报警方法 |
| CN112711832A (zh) * | 2020-12-08 | 2021-04-27 | 重庆理工大学 | 同步发电机定子绕组温度预警与故障识别的方法与系统 |
| CN112504511A (zh) * | 2020-12-15 | 2021-03-16 | 润电能源科学技术有限公司 | 一种发电机定子温度监测方法、装置及介质 |
| CN113588123A (zh) * | 2021-07-29 | 2021-11-02 | 东方电气集团东方电机有限公司 | 一种定子绕组温度预警方法 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117688834A (zh) * | 2023-12-11 | 2024-03-12 | 北京京能能源技术研究有限责任公司 | 一种水氢氢汽轮发电机线圈绝缘过热故障预警方法 |
| CN117688834B (zh) * | 2023-12-11 | 2024-05-24 | 北京京能能源技术研究有限责任公司 | 一种水氢氢汽轮发电机线圈绝缘过热故障预警方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113588123A (zh) | 2021-11-02 |
| CN113588123B (zh) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023005467A1 (zh) | 一种定子绕组温度预警方法 | |
| CN104020370B (zh) | 基于虚拟参数变化监视的变压器内部故障诊断方法 | |
| RU2323512C2 (ru) | Электрическая машина | |
| CN106771835A (zh) | 基于检测线圈的汽轮发电机转子匝间短路诊断装置及方法 | |
| CN109490726A (zh) | 基于云理论的电力变压器绝缘状态评估方法 | |
| CN103399241A (zh) | 基于温升与负荷关系的配电变压器故障诊断系统及方法 | |
| CN109827679B (zh) | 配电变压器绕组温升在线监测系统以及在线监测方法 | |
| CN110456270A (zh) | 一种电机绝缘在线监测方法及装置 | |
| CN109100608A (zh) | 一种基于d-s信息融合算法的双馈风机定子匝间短路故障的诊断方法 | |
| CN109239523A (zh) | 基于改进Karrenbauer变换的有源配电网故障定位方法 | |
| CN106091515B (zh) | 火电机组海水直流冷却循环水系统在线运行优化的方法 | |
| CN115859092B (zh) | 一种基于主成分分解的发电机绕组温度预警方法及装置 | |
| CN113344428B (zh) | 一种风电变流器igbt功率模块散热系统健康度评价方法 | |
| CN110082623A (zh) | 一种开关柜健康状态评价方法及系统 | |
| CN109899118A (zh) | 一种汽轮机组启停的控制方法 | |
| CN112526306B (zh) | 一种发电机出口侧电压互感器绝缘状态监测系统 | |
| CN116338451A (zh) | 一种深度调峰工况下汽轮发电机安全评价诊断系统及方法 | |
| CN205945494U (zh) | 智能功率模块及包含其的变频器 | |
| CN104330690A (zh) | 基于等值电阻的变压器绕组状态估计方法 | |
| Hu et al. | Risk assessment of cascading failure in power systems based on uncertainty theory | |
| CN113591029B (zh) | 一种定子绕组温度在线计算方法 | |
| Xu et al. | Research of practical expert system for transformer fault diagnosis based on multidimensional data fusion | |
| Bian et al. | Influence of Waterway Blockage Fault on Temperature Distribution of Stator Transposition Winding | |
| CN110136914B (zh) | 一种混合磁体联锁安全保护方法 | |
| KR101478658B1 (ko) | Pcm 진단장치 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22848075 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |