CN109268692B - Heat supply pipe network well type compensator leakage monitoring system and monitoring method - Google Patents
Heat supply pipe network well type compensator leakage monitoring system and monitoring method Download PDFInfo
- Publication number
- CN109268692B CN109268692B CN201810961516.0A CN201810961516A CN109268692B CN 109268692 B CN109268692 B CN 109268692B CN 201810961516 A CN201810961516 A CN 201810961516A CN 109268692 B CN109268692 B CN 109268692B
- Authority
- CN
- China
- Prior art keywords
- matrix
- leakage
- heat supply
- supply pipe
- pipe network
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
Abstract
The invention discloses a leakage monitoring system for a well compensator of a heat supply pipe network, which comprises a main control unit, wherein the main control unit is connected with an A/D conversion module through a lead, the A/D conversion module is respectively connected with a temperature measuring module, a conductivity sensor and a liquid level sensor through leads, the main control unit is connected with a GPRS wireless module through leads, and the GPRS wireless module is connected with a remote monitoring center. The monitoring method comprises the steps of firstly establishing a sample input matrix, carrying out normalization processing, establishing a heat supply pipe network well type compensator leakage condition prediction model, and finally taking measurement parameters as input to obtain the heat supply pipe network well type compensator leakage condition. The leakage state analysis of the multi-parameter compensator based on the ELM extreme learning machine is embedded into a monitoring system, automatic, intelligent and scientific real-time online monitoring and leakage level assessment are carried out, the reliability and the safety of equipment can be guaranteed, and a large amount of manpower and material resources can be saved.
Description
Technical Field
The invention belongs to the technical field of heat supply pipe leakage monitoring, and particularly relates to a heat supply pipe network well type compensator leakage monitoring system and a monitoring method of the system.
Background
The heat supply pipeline compensator is a component of a heat supply pipeline network, the leakage monitoring mode of the heat supply pipeline compensator belongs to the leakage monitoring mode of a heating power pipeline network, and the leakage detection means of the heat supply pipeline compensator and the leakage monitoring mode have universality. As a heating system with complex and huge operation working conditions, during the operation process, due to the influence of various factors, pipeline damage and leakage accidents frequently occur, and the leakage is generally monitored according to the change of relevant parameters of the system after the leakage of a pipe network. The leakage monitoring of the heat supply pipe network is a system project, and the leakage monitoring must be carried out by using a multi-means and multi-disciplinary crossing method.
At present, scholars at home and abroad have less research on leakage monitoring methods of heat supply pipeline compensators, and mainly judge and position the leakage of the heat supply pipeline by using other types of pipeline network leakage monitoring methods for reference. The compensator is used as a part of a heat distribution pipeline, leakage accidents caused by damage of factors such as material aging, illegal operation and external interference account for most of the leakage accidents, and the safe and stable operation of a heat supply system is seriously influenced.
Disclosure of Invention
The invention aims to provide a leakage monitoring system for a heat supply pipe network well type compensator, which solves the problem of poor monitoring effect of the existing leakage monitoring system for the compensator.
Another object of the present invention is to provide a monitoring method of the above monitoring system.
The invention adopts the technical scheme that the leakage monitoring system of the well compensator of the heat supply pipe network comprises a main control unit, wherein the main control unit is connected with an A/D conversion module through a lead, the A/D conversion module is respectively connected with a temperature measuring module, a conductivity sensor and a liquid level sensor through leads, the main control unit is connected with a GPRS wireless module through leads, and the GPRS wireless module is connected with a remote monitoring center.
The present invention is also characterized in that,
the solar photovoltaic array is connected with a photovoltaic controller through a wire, the photovoltaic controller is connected with a storage battery, the storage battery is respectively connected with a first power supply converter, a second power supply converter and a third power supply converter through wires, the second power supply converter is connected with a voltage stabilizer through wires, and the voltage stabilizer is connected with the main control unit.
The temperature measurement module comprises a first temperature sensor, a second temperature sensor, a third temperature sensor and a fourth temperature sensor, and the first temperature sensor, the second temperature sensor, the third temperature sensor and the fourth temperature sensor are all PT100 platinum thermal resistance type temperature sensors.
The main control unit is an STM32F103RBT6 singlechip.
The GPRS wireless module is ATK-SIM 800C; the level sensor is model number WRT-136.
The invention adopts another technical scheme that a leakage monitoring method for a heat supply pipe network well type compensator comprises the following specific steps:
when the temperature differences between T2 and T1, between T3 and T1, and between T4 and T1 are all less than 20 ℃, and G and H are both 0, the heat supply pipe network well compensator belongs to a normal state; otherwise, the state is abnormal;
in the abnormal state, if H is less than or equal to 0.5 mm, the leakage state is smaller; if H is larger than 0.5 mm, the leakage state is large;
in the formula (1), xmaxAnd xminRespectively representing the maximum value and the minimum value of each column of parameters in each sample matrix; x is the number ofiFor each column of parameter values in each sample matrix before normalization; x'iThe parameter value of each column in each sample matrix after normalization;
step 4, after the step 3, establishing a heat supply pipe network well type compensator leakage condition prediction model, which comprises the following specific steps:
step 4.1, using the sample input matrix obtained in step 3 as a training sample and a test sample, wherein the data number ratio of the training sample to the test sample is 8: 2, as the input of the ELM classification model, establishing a heat supply pipe network well type compensator leakage condition prediction model, as shown in formula (2):
in the formula (2), ykIs the output value of the neuron; x is the number ofjInput signals transmitted from other neurons; w is akThe connection weight, i.e. the connection strength; bkA threshold value for a neuron;
in equation (2), the output matrix Φ of the hidden layer is represented by equation (3):
in the formula (3), phi () is an activation function of the neuron, and the activation function is a sig function;
the number K of the hidden layers is increased from 10 to 200, and 10 is increased each time;
step 4.2, establishing a connection matrix beta between the output layer and the hidden layer, as shown in formula (4):
β＝Φ+T＝(ΦTΦ)-1ΦTT (4)；
in the formula (4), T is the output matrix of the training sample, phiTPhi is a singular or non-singular matrix; phi+The generalized inverse matrix is a Moore-Penrose generalized inverse matrix of the hidden layer output matrix phi; phiTIs a transposed matrix of the hidden layer output matrix phi;
wherein, the output matrix T of the training sample is shown as formula (5):
in formula (5), M is the number of output classes, and M is 1, 2.
4.3, calculating a learning error Z of the extreme learning machine, and obtaining a heat supply pipe network well type compensator leakage condition prediction model by taking the number K of hidden layers and an activation function phi (.) with the minimum learning error as parameters, namely the accuracy is highest;
if the learning errors are the same, taking the number K of hidden layers and an activation function phi (.) when the number of neurons of the hidden layers is small as parameters;
the calculation formula of the learning error Z is shown in equation (6):
Z＝||Φβ-T|| (6)；
and 5, after the step 4, carrying out normalization processing on the sample data matrix acquired by the first temperature sensor, the second temperature sensor, the third temperature sensor, the fourth temperature sensor, the conductivity sensor and the liquid level sensor in the step 2, inputting the sample data matrix into the heat supply pipe network well compensator leakage condition prediction model obtained after the step 4 by taking the sample data matrix as the input of the ELM classification model, and outputting a state class by the model to obtain the leakage condition of the heat supply pipe network well compensator.
The beneficial effect of the invention is that,
this multisensor heating power pipe network well formula compensator leakage monitoring system is good to the leakage monitoring effect that the compensator leads to because of damaging, can in time send alarm signal when it takes place to leak the accident, for relevant personnel promptly salvage provides important foundation, reduces the influence that leaks and cause, has important meaning to the normal operating of guarantee heating system.
Drawings
FIG. 1 is a block diagram of a leakage monitoring system for a well compensator of a heat supply pipe network according to the present invention;
FIG. 2 is a comparison graph of a test sample and an actual output of a heat supply pipe network well compensator leakage condition prediction model in the method.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
The invention relates to a leakage monitoring system of a heat supply pipe network well type compensator, which comprises a main control unit 1, wherein the main control unit 1 is connected with an A/D conversion module 2 through a lead, the A/D conversion module 2 is respectively connected with a temperature measuring module 3, a conductivity sensor 4 and a liquid level sensor 5 through leads, the main control unit 1 is connected with a GPRS wireless module 6 through a lead, and the GPRS wireless module 6 is connected with a remote monitoring center 7;
the solar photovoltaic controller is connected with the storage battery through a lead, the output voltage of the photovoltaic controller is 12V, the storage battery is respectively connected with the first power converter, the second power converter and the third power converter through leads, the first power converter generates +12V and-12V voltages, the second power converter generates +5V and-5V voltages, the third power converter generates +24V voltages, the second power converter is connected with the voltage stabilizer through a lead, the voltage of +5V can be reduced to +3.3V, and the voltage stabilizer is connected with the main control unit 1; the model of the voltage stabilizer is ASM 1117;
the temperature measurement module 3 comprises a first temperature sensor, a second temperature sensor, a third temperature sensor and a fourth temperature sensor, the first temperature sensor is arranged right above the well type compensator, the second temperature sensor is arranged right below the well type compensator, the third temperature sensor and the fourth temperature sensor are respectively arranged at two sides of the well type compensator 1, the conductivity sensor 4 is arranged in a heat preservation layer right below the well type compensator, and the liquid level sensor 5 is arranged at the bottom of the well type compensator;
the first power converter is respectively connected with the first temperature sensor, the second temperature sensor, the third temperature sensor, the fourth temperature sensor and the conductivity sensor 4;
the second power converter is respectively connected with the first temperature sensor, the second temperature sensor, the third temperature sensor, the fourth temperature sensor, the liquid level sensor 5 and the A/D conversion module 2;
the third power converter is connected with the liquid level sensor 5;
wherein the generated +12V voltage is supplied to the temperature measuring module 3 and the conductivity sensor 4;
the generated-12V voltage is provided to the temperature measuring module 3;
the generated +5V voltage is provided for the temperature measuring module 3, the liquid level sensor 5 and the A/D conversion module 2;
the generated-5V voltage is provided for the A/D conversion module 2;
the generated +24V voltage is supplied to the liquid level sensor 5;
the models of the first power converter, the second power converter and the third power converter are VRA1212YMD-6WR3, VRA1205YMD-6WR3 and VRA1224YMD-6WR3 respectively; the first temperature sensor, the second temperature sensor, the third temperature sensor and the fourth temperature sensor are all PT100 platinum thermistor type temperature sensors;
the main control unit 1 is an STM32F103RBT6 singlechip;
the GPRS wireless module 6 is ATK-SIM 800C;
the model of the liquid level sensor 5 is WRT-136;
the A/D conversion module 2 carries out analog-to-digital conversion on the acquired parameters and consists of a 4-bit double-integration A/D chip ICL7135CN and an ICL8069 chip, an ICL8069 reference voltage source provides reference voltage for the AD conversion chip ICL7135CN, and acquisition of data of each sensor is achieved through control of an STM32F103RBT6 single chip microcomputer.
The invention relates to a leakage monitoring system of a heat supply pipe network well type compensator, which has the following specific working principle:
each sensor in the system is arranged on the well compensator to realize leakage monitoring of the well compensator; the temperature measuring module 3 is used for detecting the temperature around the well compensator at the same time, taking any one measured temperature arranged on the well compensator as a reference, comparing the measured temperature with the color temperatures measured by other three temperature sensors, if the temperature difference has a certain difference, preliminarily judging that the well compensator has a leakage accident, and sending out compensator leakage early warning information by a monitoring system; and simultaneously starting the liquid level sensor 5 and the conductivity sensor 4, starting to collect the bottom hole liquid level and the conductivity parameters in the heat insulation layer right below the well type compensator, further confirming the damage and leakage of the well type compensator if the conductivity G value is obviously increased or the bottom hole liquid level H is also obviously changed, sending the collected parameters of temperature, conductivity, liquid level and the like to a remote monitoring center through a GPRS wireless network, storing, processing and analyzing the collected parameters, comprehensively evaluating the working state of the monitored heat pipe network compensator, and alarming the abnormal operation state and evaluating the damage and leakage condition.
Solar photovoltaic array will gather solar energy daytime and convert the electric energy into, for compensator leakage monitoring system power supply, through photovoltaic controller protection circuit and protection battery not receive the overshoot damage, control output voltage is 12V to with unnecessary electric quantity storage in the battery, voltage conversion circuit converts the 12V voltage of battery output into the receivable direct current voltage of detection module, the battery passes through voltage conversion circuit independently and provides the power for compensator leakage monitoring system night.
The invention discloses a leakage monitoring method for a heat supply pipe network well type compensator, which comprises the following specific steps:
when the temperature differences between T2 and T1, between T3 and T1, and between T4 and T1 are all less than 20 ℃, and G and H are both 0, the heat supply pipe network well compensator belongs to a normal state; otherwise, the state is abnormal;
in the abnormal state, if H is less than or equal to 0.5 mm, the leakage state is smaller; if H is larger than 0.5 mm, the leakage state is large;
in the formula (1), xmaxAnd xminMaximum of each column parameter in each sample matrixValue and minimum value, xiIs the parameter value of each column in each sample matrix before normalization, x'iThe parameter value of each column in each sample matrix after normalization;
step 4, after the step 3, establishing a heat supply pipe network well type compensator leakage condition prediction model, which comprises the following specific steps:
step 4.1, using the sample input matrix obtained in step 3 as a training sample and a test sample, wherein the data number ratio of the training sample to the test sample is 8: 2, as the input of the ELM classification model, establishing a heat supply pipe network well type compensator leakage condition prediction model, as shown in formula (2):
in the formula (2), ykIs the output value of the neuron; x is the number ofjInput signals transmitted from other neurons; w is akThe connection weight, i.e. the connection strength; bkA threshold value for a neuron;
in equation (2), the output matrix Φ of the hidden layer is represented by equation (3):
in the formula (3), phi () is an activation function of the neuron, and the activation function is a sig function;
the number K of the hidden layers is increased from 10 to 200, and 10 is increased each time;
step 4.2, establishing a connection matrix beta between the output layer and the hidden layer, as shown in formula (4):
β＝Φ+T＝(ΦTΦ)-1ΦTT (4)；
in the formula (4), T is the output matrix of the training sample, phiTPhi is a singular or non-singular matrix; phi+The generalized inverse matrix is a Moore-Penrose generalized inverse matrix of the hidden layer output matrix phi; phiTIs a transposed matrix of the hidden layer output matrix phi;
wherein, the output matrix T of the training sample is shown as formula (5):
in formula (5), M is the number of output classes, and M is 1, 2.
4.3, calculating a learning error Z of the extreme learning machine, and obtaining a heat supply pipe network well type compensator leakage condition prediction model by taking the number K of hidden layers and an activation function phi (.) with the minimum learning error as parameters, namely the accuracy is highest;
if the learning errors are the same, taking the number K of hidden layers and an activation function phi (.) when the number of neurons of the hidden layers is small as parameters;
the calculation formula of the learning error Z is shown in equation (6):
Z＝||Φβ-T|| (6)；
and 5, after the step 4, carrying out normalization processing on the sample data matrix acquired by the first temperature sensor, the second temperature sensor, the third temperature sensor, the fourth temperature sensor, the conductivity sensor and the liquid level sensor in the step 2, inputting the sample data matrix into the heat supply pipe network well compensator leakage condition prediction model obtained after the step 4 by taking the sample data matrix as the input of the ELM classification model, and outputting a state class by the model to obtain the leakage condition of the heat supply pipe network well compensator.
In the method, the number K of the hidden layers is increased by 10 from an initial value of 10 to 200 each time, the learning accuracy (the accuracy is 1-error) of the model is calculated, the number of the neurons with the minimum error is determined as the final number K of the hidden layers of the model through comparison, and if the same accuracy occurs, the number of the neurons of the hidden layers is taken as a parameter to reduce the complexity of the model, so that the classification speed of the model is ensured.
According to the method, the acquired data of the test sample is input into a leakage condition prediction model of the heat supply pipe network well type compensator, and the calculated output matrix is compared with the actual output of the test sample, as shown in fig. 2, the experimental result of the classification model in the test set can be seen, the horizontal axis represents the data of the test set, the vertical axis represents the labels of 1 type, 2 type and 3 type (1-normal condition; 2-small leakage; 3-large leakage) of the test set, the hollow circle in the graph represents the original category of the data of the test set, and the star line represents the category calculated by the algorithm. As can be seen, the model has a high prediction result, so that the effectiveness of the heat supply pipe network well compensator leakage condition prediction model based on the ELM algorithm is verified.
Claims (2)
1. A leakage monitoring method for a heat supply pipe network well type compensator is characterized by comprising the following specific steps:
step 1, according to parameters T1, T2, T3, T4 and G, H which are respectively measured by a first temperature sensor, a second temperature sensor, a third temperature sensor, a fourth temperature sensor, a conductivity sensor and a liquid level sensor in an analog mode, performing analog classification on the leakage conditions of the heat supply pipe network well type compensator to respectively obtain a sample matrix m x 6 in a normal state, a small leakage state and a large leakage state;
when the temperature differences between T2 and T1, between T3 and T1, and between T4 and T1 are all less than 20 ℃, and G and H are both 0, the heat supply pipe network well compensator belongs to a normal state; otherwise, the state is abnormal;
in the abnormal state, if H is less than or equal to 0.5 mm, the leakage state is smaller; if H is larger than 0.5 mm, the leakage state is large;
step 2, normalizing each row of each sample matrix obtained in the step 1 to enable each row of parameter values x 'of each sample matrix'iAll fall into [0, 1 ]]The formula is shown as a formula (1);
in the formula (1), xmaxAnd xminRespectively representing the maximum value and the minimum value of each column of parameters in each sample matrix; x is the number ofiFor each column of parameter values in each sample matrix before normalization; x'iThe parameter value of each column in each sample matrix after normalization;
step 3, after the step 2, splicing the sample matrix m x 6 in a row-to-row connection mode to form a 3m x 6 matrix, then adding a column at the end of the matrix to distinguish data of three states, and sequentially representing a normal state, a small leakage state and a large leakage state of the simulated heat supply pipe network well compensator by 1,2 and 3 to obtain a sample input matrix 3m x 7;
step 4, after the step 3, establishing a heat supply pipe network well type compensator leakage condition prediction model;
and 5, after the step 4, carrying out normalization processing on the sample data matrix acquired by the first temperature sensor, the second temperature sensor, the third temperature sensor, the fourth temperature sensor, the conductivity sensor and the liquid level sensor in the step 2, inputting the sample data matrix into the heat supply pipe network well compensator leakage condition prediction model obtained after the step 4 by taking the sample data matrix as the input of the ELM classification model, and outputting a state class by the model to obtain the leakage condition of the heat supply pipe network well compensator.
2. The method for monitoring the leakage of the well compensator of the heat supply pipe network according to claim 1, wherein the step 4 comprises the following steps:
step 4.1, using the sample input matrix obtained in step 3 as a training sample and a test sample, wherein the data number ratio of the training sample to the test sample is 8: 2, as the input of the ELM classification model, establishing a heat supply pipe network well type compensator leakage condition prediction model, as shown in formula (2):
in the formula (2), ykIs the output value of the neuron; x is the number ofjInput signals transmitted from other neurons; w is akThe connection weight, i.e. the connection strength; bkA threshold value for a neuron;
in equation (2), the output matrix Φ of the hidden layer is represented by equation (3):
in the formula (3), phi () is an activation function of the neuron, and the activation function is a sig function;
the number K of the hidden layers is increased from 10 to 200, and 10 is increased each time;
step 4.2, establishing a connection matrix beta between the output layer and the hidden layer, as shown in formula (4):
β＝Φ+T＝(ΦTΦ)-1ΦTT (4)；
in the formula (4), T is the output matrix of the training sample, phiTPhi is a singular or non-singular matrix; phi+The generalized inverse matrix is a Moore-Penrose generalized inverse matrix of the hidden layer output matrix phi; phiTIs a transposed matrix of the hidden layer output matrix phi;
wherein, the output matrix T of the training sample is shown as formula (5):
in formula (5), M is the number of output classes, and M is 1, 2.
4.3, calculating a learning error Z of the extreme learning machine, and obtaining a heat supply pipe network well type compensator leakage condition prediction model by taking the number K of hidden layers and an activation function phi (.) with the minimum learning error as parameters, namely the accuracy is highest;
if the learning errors are the same, taking the number K of hidden layers and an activation function phi (.) when the number of neurons of the hidden layers is small as parameters;
the calculation formula of the learning error Z is shown in equation (6):
Z＝||Φβ-T|| (6)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810961516.0A CN109268692B (en) | 2018-08-22 | 2018-08-22 | Heat supply pipe network well type compensator leakage monitoring system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810961516.0A CN109268692B (en) | 2018-08-22 | 2018-08-22 | Heat supply pipe network well type compensator leakage monitoring system and monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109268692A CN109268692A (en) | 2019-01-25 |
| CN109268692B true CN109268692B (en) | 2021-02-19 |
Family
ID=65154235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810961516.0A Expired - Fee Related CN109268692B (en) | 2018-08-22 | 2018-08-22 | Heat supply pipe network well type compensator leakage monitoring system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109268692B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110009874A (en) * | 2019-04-12 | 2019-07-12 | 泰州职业技术学院 | A kind of flammable gas alarm, combustible gas alarm method and system |
| CN114811443B (en) * | 2021-01-22 | 2024-04-16 | 北京科益虹源光电技术有限公司 | Waterway state monitoring system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012107727B4 (en) * | 2012-03-23 | 2014-12-04 | Atlas Elektronik Gmbh | Navigation method, distance control method and method for inspecting a flooded tunnel therewith as well as navigation device, distance control device and underwater vehicle therewith |
| CN103914711B (en) * | 2014-03-26 | 2017-07-14 | 中国科学院计算技术研究所 | A kind of improved very fast learning device and its method for classifying modes |
| CN104654024A (en) * | 2015-02-12 | 2015-05-27 | 常州大学 | Method for locating and analyzing leakage of city gas pipeline based on GRNN (Generalized Regression Neural Network) |
| CN204512965U (en) * | 2015-04-01 | 2015-07-29 | 西安科技大学 | A kind of underground heating network expansion joint leakage monitoring system |
| CN204964141U (en) * | 2015-06-25 | 2016-01-13 | 中国大唐集团科学技术研究院有限公司西北分公司 | Direct burial expansion joint leak testing sensing device |
| CN204962303U (en) * | 2015-07-02 | 2016-01-13 | 中国大唐集团科学技术研究院有限公司西北分公司 | Pipe network expansion joint of portable secret heat supply damages test probe |
| CN107917341B (en) * | 2016-10-09 | 2020-01-07 | 中国石油天然气股份有限公司 | Oil pipeline leakage detection method and device |
-
2018
- 2018-08-22 CN CN201810961516.0A patent/CN109268692B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109268692A (en) | 2019-01-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103323703B (en) | Cable connector fault diagnosing method | |
| CN104767482B (en) | A kind of photovoltaic module is aging and short trouble inline diagnosis method | |
| EP3444944B1 (en) | Fault detection and positioning system for cell panel in large-scale photovoltaic array | |
| CN105846780A (en) | Decision tree model-based photovoltaic assembly fault diagnosis method | |
| CN109781268B (en) | Switch cabinet interior key part temperature monitoring system based on low-cost infrared hot-vision technology | |
| CN104579166A (en) | Distributed photovoltaic power station monitoring system and fault diagnosis method thereof | |
| CN111308355A (en) | Transformer substation storage battery state detection and analysis method based on deep learning | |
| CN102607643A (en) | Overheat fault diagnosis and early warning system and method for electrical equipment of traction substation of electrified railway | |
| CN109724646A (en) | A kind of power distribution network switchgear cable connector monitoring method, server and system | |
| CN109268692B (en) | Heat supply pipe network well type compensator leakage monitoring system and monitoring method | |
| CN105716664A (en) | Cable state monitoring multiparameter correlation analysis method based on per-unit algorithm | |
| CN115979349B (en) | Power station space environment monitoring method and system | |
| CN112711832B (en) | Method and system for early warning of temperature and fault identification of stator winding of synchronous generator | |
| CN105024644A (en) | Performance evaluation system and method of photovoltaic system | |
| CN108092623A (en) | A kind of photovoltaic array multisensor fault detecting and positioning method | |
| CN103528701A (en) | Online monitoring system for temperature and current carrying capacity of power cable | |
| CN103941138B (en) | OPGW line monitoring diagnosis system and monitoring, diagnosing method completely | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN212895016U (en) | Aluminum electrolysis cell condition diagnosis system based on LoRa wireless measurement and control technology | |
| WO2023033002A1 (en) | Failure diagnosis method for solar cell module, and program | |
| CN105676044A (en) | Online test method and system for lightning arrester and monitor thereof | |
| CN116468422A (en) | Method and device for predicting wire clamp temperature rise and residual life of power transmission line | |
| CN109633375A (en) | A kind of power distribution network safe distance recognition methods and device | |
| CN206656749U (en) | Heat-engine plant sensor fault diagnosis system | |
| CN113295961B (en) | Overhead transmission line clamp heating early warning and dynamic capacity-increasing edge calculation method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210219 Termination date: 20210822 |