CN111127825A - Environment prediction method and device and electronic equipment - Google Patents
Environment prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN111127825A CN111127825A CN201911357901.5A CN201911357901A CN111127825A CN 111127825 A CN111127825 A CN 111127825A CN 201911357901 A CN201911357901 A CN 201911357901A CN 111127825 A CN111127825 A CN 111127825A
- Authority
- CN
- China
- Prior art keywords
- environment
- environmental
- abnormal
- parameters
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002159 abnormal effect Effects 0.000 claims abstract description 148
- 230000007613 environmental effect Effects 0.000 claims abstract description 143
- 230000000306 recurrent effect Effects 0.000 claims abstract description 67
- 238000003062 neural network model Methods 0.000 claims abstract description 53
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 230000006378 damage Effects 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 18
- 238000003331 infrared imaging Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003384 imaging method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 21
- 239000007789 gas Substances 0.000 description 37
- 238000010586 diagram Methods 0.000 description 7
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000008034 disappearance Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000012260 Accidental injury Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/12—Alarms for ensuring the safety of persons responsive to undesired emission of substances, e.g. pollution alarms
- G08B21/14—Toxic gas alarms
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/20—Status alarms responsive to moisture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Toxicology (AREA)
- Environmental & Geological Engineering (AREA)
- Multimedia (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The application provides an environment prediction method and device, an electronic device and a computer readable storage medium, which are applied to an environment detection system, wherein the method comprises the following steps: acquiring environmental parameters in the cable trench by using a detection sensing module; inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: an LSTM network layer; and when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. According to the method and the device, the environmental parameters in the cable trench are obtained by the detection sensing module, the environmental parameters are input into the prediction model constructed by the recurrent neural network to obtain the environmental prediction information, and when the environmental prediction information comprises the environmental abnormal information, the corresponding avoidance strategy is obtained. The prediction model constructed by the recurrent neural network is utilized, so that the accuracy is ensured, the efficiency of environment information prediction is improved, and the probability of environment abnormity can be effectively reduced.
Description
Technical Field
The present disclosure relates to the field of power detection, and in particular, to an environment prediction method and apparatus, an electronic device, and a computer-readable storage medium.
Background
In recent years, 10kV cable trenches have frequent fire incidents, the operating environment in the cable trenches is poor, part of the cable trenches are over-capacity, and the temperature in the cable trenches is high due to unsmooth ventilation and no air circulation; and sewage exists in cable ducts of some sections, so that toxic and flammable gases such as methane and the like are easily generated, and a fire disaster is easily caused.
The existing cable trench is covered by a cover plate, and when patrolling personnel patrol, the cover plate of the cable trench needs to be opened for detection or a sensor with multiple physical parameters is used for detection in order to solve the running condition in the cable trench. When a fault is detected, the fault is processed again, and the method for reprocessing the abnormal environment often causes a lot of property loss and accidental injury.
Disclosure of Invention
The embodiment of the application provides an environment prediction method, an environment prediction device, electronic equipment and a computer readable storage medium, which can reduce the probability of occurrence of environment difference.
An environment prediction method is applied to an environment detection system, and comprises the following steps:
utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters;
inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: an LSTM network layer;
and when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information.
In one embodiment, before inputting the environmental parameter into the prediction model to obtain the environmental prediction information, the method further includes:
acquiring an environment parameter training set, wherein the environment parameter training set comprises a plurality of environment parameters carrying recording time information;
constructing the recurrent neural network model;
and training the recurrent neural network model by using the environmental parameter training set to obtain the prediction model.
In one embodiment, the training the recurrent neural network model with the training set of environmental parameters to obtain the prediction model includes:
determining a loss function of the recurrent neural network model according to the environmental parameters of each recording moment in the environmental parameter training set;
inputting the environmental parameter training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the loss function is smaller than a preset threshold value;
and taking the recurrent neural network model corresponding to the loss function with the output value smaller than a preset threshold value as the prediction model.
In one embodiment, before determining the corresponding abnormal avoidance maneuver according to the environmental abnormal information, the method further includes:
comparing the environment prediction information with environment reference information to obtain environment abnormal information, wherein the environment abnormal information comprises an abnormal identifier;
the determining the corresponding abnormal avoidance strategy according to the environment abnormal information comprises the following steps:
and acquiring a corresponding abnormal avoidance strategy according to the abnormal identifier of the environment abnormal information.
In one embodiment, the obtaining of the corresponding exception avoidance maneuver according to the exception identifier of the environment exception information includes:
searching the abnormal identification in a preset list, wherein the abnormal identification of the abnormal information of the conventional environment and a corresponding abnormal avoidance strategy are stored in the preset list;
when the abnormal identifier of the environment abnormal information is in the preset list, acquiring an abnormal avoidance strategy corresponding to the abnormal identifier stored in the preset list;
and when the abnormal identifier of the environment abnormal information is not in the preset list, taking an emergency processing strategy as an abnormal avoidance strategy corresponding to the abnormal identifier.
In one embodiment, the detecting and sensing module further includes an infrared imaging unit and a millimeter wave imaging unit, and the acquiring environmental parameters in the cable trench by using the detecting and sensing module includes:
acquiring a first image of a target field of view by using an infrared imaging unit, and acquiring a second image of the target field of view by using the infrared imaging unit;
and carrying out image fusion on the first image and the second image to obtain a target image, and acquiring the environmental parameters according to the target image.
In one embodiment, the detection sensing module includes at least: position sensor, temperature sensor, humidity transducer and gas sensor, utilize and survey sensing module and acquire the environmental parameter in the cable pit, include:
acquiring the positioning parameters by using the position sensor; acquiring damage parameters of the cable by using the cable flaw detection sensor; the temperature sensor is used for acquiring the space temperature parameter, the humidity sensor is used for acquiring the space humidity parameter, and the gas sensor is used for acquiring the harmful gas content parameter.
An environmental exception handling device applied to an environmental detection system, the device comprising:
the detection module is used for acquiring environmental parameters in the cable trench by using the detection sensing module, and the environmental parameters at least comprise: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters;
a prediction module, configured to input the environmental parameter into a prediction model to obtain environmental prediction information, where the prediction model is a trained recurrent neural network model, and the recurrent neural network model includes: an LSTM network layer;
and the processing module is used for determining a corresponding abnormal avoidance strategy according to the environment abnormal information when the environment prediction information comprises the environment abnormal information.
An electronic device comprising a memory and a processor, the memory having stored thereon a computer program that, when executed by the processor, causes the processor to perform the steps of the environment prediction method.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method.
The environment prediction method and device, the electronic equipment and the computer-readable storage medium are applied to an environment detection system, and the method comprises the following steps: utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters; inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: an LSTM network layer; and when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. According to the method and the device, the environmental parameters in the cable trench are obtained by the detection sensing module, the environmental parameters are input into the prediction model constructed by the recurrent neural network to obtain the environmental prediction information, and when the environmental prediction information comprises the environmental abnormal information, the corresponding avoidance strategy is obtained. The prediction model constructed by the recurrent neural network is utilized, the accuracy is ensured, meanwhile, the efficiency of environment information prediction is improved, an abnormality avoidance strategy is obtained according to the predicted environment abnormality information, and the probability of environment abnormality occurrence can be effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application 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, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of an environment in which the environment prediction method is applied according to an embodiment;
FIG. 2 is a flow diagram of a method for environment prediction in one embodiment;
FIG. 3 is a flowchart illustrating steps performed in one embodiment to train a recurrent neural network model to obtain a predictive model using an environmental parameter training set;
FIG. 4 is a flowchart illustrating steps performed in an embodiment to obtain corresponding exception avoidance maneuvers based on exception identifications of environmental exception information;
FIG. 5 is a flow diagram of steps in one embodiment for acquiring environmental parameters in a cable trench using a detection sensing module;
FIG. 6 is a block diagram showing the configuration of an environment prediction apparatus according to an embodiment;
fig. 7 is a schematic diagram illustrating an internal structure of the environment detection system according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first image may be referred to as a second image, and similarly, a second image may be referred to as a first image, without departing from the scope of the present application. The first image and the second image are both images, but they are not the same image.
FIG. 1 is a diagram of an environment in which the environmental method is applied in one embodiment. As shown in fig. 1, the application environment includes an environment detection system 10, which includes: the sensing module 110 is detected. By utilizing the detection sensing module 110 to obtain the environmental parameters in the cable trench, the environmental parameters at least include: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter. Inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: the LSTM network layer. And when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. The prediction model constructed by the recurrent neural network is utilized, the accuracy of environment prediction information is guaranteed, meanwhile, the prediction efficiency is improved, the abnormity avoidance strategy is obtained according to the predicted environment abnormity information, and the probability of environment abnormity can be effectively reduced.
Fig. 2 is a flowchart of an environment prediction method in an embodiment, as shown in fig. 2, the environment prediction method includes: step 202 to step 206.
Specifically, the environmental parameters at least include: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters. The process of obtaining the environmental parameters is as follows: the positioning information can be acquired by using a GPS sensor, the space temperature parameter can be acquired by using a temperature sensor, the space humidity parameter can be acquired by using a humidity sensor, the harmful gas content parameter can be acquired by using a gas sensor, and the cable damage parameter can be acquired by detecting a flaw by using a multi-parameter sensor integrated with the temperature sensor, the humidity sensor and the gas sensor; the detection sensing module can also comprise an infrared imaging unit and a millimeter wave imaging unit, the infrared imaging unit is used for collecting infrared rays radiated outwards by each device, two-dimensional or three-dimensional modeling is carried out to reproduce a first image corresponding to the environment of the cable trench, the millimeter wave imaging unit can transmit millimeter wave signals to a target view field in the cable trench, the devices, cables, channels and the like in the target view field are modulated and reflect the millimeter wave signals to form echo signals, the millimeter wave imaging unit captures the echo signals reflected by the target view field, a two-dimensional or three-dimensional scene of the cable channel is obtained according to the echo signal modeling, the first image is identified to obtain first environment parameters, the second image is identified to obtain second environment parameters, and the first environment parameters and the second environment parameters are mutually supplemented to obtain the environment parameters.
Among them, the Long Short Term Memory network (LSTM) is a recurrent neural network with a complex structure. A fully connected recurrent neural network typically includes: input layer, hidden layer and output layer. The input layer is an input layer, the hidden layer is a hidden layer, the hidden layer can have multiple layers, and the output layer is an output layer. In a standard LSTM network structure, 4 values are required for input, and 1 value is output, wherein there are 3 forgetting gate concepts, i.e., input gate, forgetgate, and output gate, and since there are 4 parameters for input, the number of parameters is usually 4 times that of a general neural network. LSTM can effectively prevent the gradient disappearance problem by gating control.
Specifically, the prediction model may include a plurality of recurrent neural network models, each parameter corresponds to one network model, and for example, the prediction model may include a model for predicting a cable damage parameter, a model for predicting a space temperature parameter, a model for predicting a space humidity parameter, and a model for predicting a harmful gas content parameter, where the positioning parameter may be used as a label of the environment parameter. Each environment parameter corresponds to one piece of positioning information, a circulating neural network model is trained by utilizing a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter which are recorded at different moments and are at the same position, the cable damage parameter, the space temperature parameter, the space humidity parameter and the harmful gas content parameter are respectively predicted, the predicted results are collected, and the environment prediction information is obtained by combining the positioning parameters.
And step 206, when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information.
Specifically, the environment prediction information is detected, and when parameters which do not match the environment reference information exist in the environment prediction information, the environment abnormal information is obtained according to the parameters which do not match in the environment prediction information. An abnormal avoidance strategy corresponding to the environmental abnormal information is stored in the environment detection system, if the fact that the temperature of the equipment B at the coordinate A is higher than a threshold value is predicted, and the equipment B at the coordinate A is identified to possibly cause a fire phenomenon, the abnormal avoidance strategy corresponding to the equipment B is searched in the environment detection system, and the abnormal avoidance strategy can be used for powering off the equipment B and carrying out software maintenance and hardware maintenance.
The environment prediction method comprises the following steps: utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter. Inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: the LSTM network layer. And when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. According to the method and the device, the environmental parameters in the cable trench are obtained by the detection sensing module, the environmental parameters are input into the prediction model constructed by the recurrent neural network to obtain the environmental prediction information, and when the environmental prediction information comprises the environmental abnormal information, the corresponding avoidance strategy is obtained. The prediction model constructed by the recurrent neural network is utilized, the accuracy of environment prediction information is guaranteed, meanwhile, the prediction efficiency is improved, the abnormity avoidance strategy is obtained according to the predicted environment abnormity information, and the probability of environment abnormity can be effectively reduced.
In one embodiment, before the step of inputting the environmental parameter into the prediction model to obtain the environmental prediction information, the environmental prediction method further includes: and acquiring an environment parameter training set, wherein the environment parameter training set comprises a plurality of environment parameters carrying recording time information. And constructing a cyclic neural network model, and training the cyclic neural network model by using an environment parameter training set to obtain a prediction model.
Specifically, before obtaining the environmental prediction information by using the prediction model, a large number of historical environmental parameters are collected as a training set, for example, 500 environmental parameters are collected for the location a, and each environmental parameter at least includes: recording time, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters. And inputting 500 environment parameters into the recurrent neural network model according to the sequence of the recording time to train the recurrent neural network. And encoding 500 environmental parameters into data matrixes required by the recurrent neural network according to the sequence of the recording time, inputting the data matrixes corresponding to 400 environmental parameters into the recurrent neural network according to the sequence of the recording time for training, using the data matrixes corresponding to the remaining 100 environmental parameters as a check set, and using the trained recurrent neural network model as a prediction model.
In one embodiment, as shown in fig. 3, the step of training the recurrent neural network model with the environmental parameter training set to obtain the prediction model includes: step 302 to step 306. And step 302, determining a loss function of the recurrent neural network model according to the environmental parameters of each recording moment in the environmental parameter training set. And step 304, inputting the environment parameter training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the loss function is smaller than a preset threshold value. And step 306, taking the recurrent neural network model corresponding to the loss function with the output value smaller than the preset threshold value as a prediction model.
Specifically, the loss function is an index for measuring the performance of the expected result predicted by the prediction model. And obtaining a loss function of the recurrent neural network model according to the difference value between the actual value and the predicted value of the environmental parameter at different recording moments in the environmental parameter training set, wherein the loss function can be a Mean Squared Error (MSE) function. And inputting the environment parameter training set into a recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the loss function is smaller than a preset threshold value. And in the process, continuously detecting the output value of the loss function, and determining a prediction model according to the weight of the LSTM network layer corresponding to the output value of the loss function smaller than the preset value when the output value of the loss function is smaller than the preset value.
In one embodiment, before determining the corresponding abnormal avoidance maneuver according to the environmental abnormal information, the environmental prediction method further includes: and comparing the environment prediction information with the environment reference information to obtain environment abnormal information, wherein the environment abnormal information comprises an abnormal identifier. Determining a corresponding abnormal avoidance strategy according to the environment abnormal information, comprising the following steps: and acquiring a corresponding abnormal avoidance strategy according to the abnormal identifier of the environment abnormal information.
Specifically, the environmental prediction information is compared with environmental reference information, and the environmental reference information is an environmental parameter when the environmental state is not abnormal. And when the parameters which are not matched with the environmental reference information exist in the environmental prediction information, acquiring the environmental abnormal information according to the parameters which are not matched in the environmental prediction information. The environment abnormal information carries abnormal identifications, abnormal avoidance strategies corresponding to the abnormal identifications can be stored in the environment detection system, if the predicted abnormal identification is 001 and the B equipment at the coordinate position of the identification A possibly catches fire, the abnormal avoidance strategies corresponding to the abnormal identification 001 are searched in the environment detection system, and the abnormal avoidance strategies can be used for powering off the B equipment and carrying out software maintenance and hardware maintenance.
In one embodiment, as shown in fig. 4, the step of obtaining a corresponding abnormal avoidance maneuver according to the abnormal identifier of the environmental abnormal information includes: step 402 to step 406. Step 402, searching an abnormal identifier in a preset list, wherein the abnormal identifier of the abnormal information of the conventional environment and a corresponding abnormal avoidance strategy are stored in the preset list. And step 404, when the abnormal identifier of the environment abnormal information is in the preset list, acquiring an abnormal avoidance strategy corresponding to the abnormal identifier stored in the preset list. And 406, when the abnormal identifier of the environment abnormal information is not in the preset list, taking the emergency processing strategy as an abnormal avoidance strategy corresponding to the abnormal identifier.
Specifically, an abnormal identifier corresponding to conventional abnormal information and a corresponding fault handling strategy are stored in the environment detection system in advance, for example, a first identifier corresponding to cable fire, a first handling strategy, a second identifier corresponding to equipment fire, a second handling strategy, and a third identifier corresponding to too high methane concentration, and a third handling strategy. And the environment abnormal information comprises an abnormal identifier, whether the abnormal identifier exists in the hand is searched in a preset list, and if the abnormal identifier exists in the preset list, an abnormal evasion strategy corresponding to the abnormal identifier of the environment abnormal information is obtained. If the abnormal information does not exist in the cable trench, the complex environment in the cable trench corresponding to the abnormal environment information is represented, multiple faults or faults which cannot be identified are possibly included, an alarm signal can be generated at the moment to prompt a worker to carry out manual inspection, an emergency processing strategy can be used as an abnormal avoidance strategy corresponding to the abnormal identifier, and the emergency processing strategy can be manual repair and fault removal.
In one embodiment, the detecting and sensing module further includes an infrared imaging unit and a millimeter wave imaging unit, and the step of acquiring the environmental parameter in the cable trench by using the detecting and sensing module includes: step 502 and step 504. Step 502, a first image of a target field of view is acquired using an infrared imaging unit, and a second image of the target field of view is acquired using the infrared imaging unit. And step 504, carrying out image fusion on the first image and the second image to obtain a target image, and acquiring environmental parameters according to the target image.
Specifically, each device in the target field of view radiates infrared outwards, the infrared imaging unit is used for collecting the infrared radiated outwards by each device, and two-dimensional or three-dimensional modeling is carried out to reproduce a first image corresponding to the cable trench environment. The millimeter wave imaging unit can transmit millimeter wave signals to a target view field in the cable trench, and equipment, cables, channels and the like in the target view field modulate and reflect the millimeter wave signals to form echo signals and capture the echo signals reflected by the target view field. And modeling according to the echo signal to obtain a two-dimensional or three-dimensional scene of the cable channel to obtain a second image. And fusing the first image and the second image to obtain a target image, and then performing image recognition on the target image, such as recognizing by using a neural network, a feature extraction method and the like to obtain an environment abnormal parameter.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, the detection sensing module comprises at least: position sensor, temperature sensor, humidity transducer and gas sensor, step utilize and survey sensing module and acquire the environmental parameter in the cable pit, include: and acquiring positioning parameters by using the position sensor. And acquiring damage parameters of the cable by using a cable flaw detection sensor. The temperature sensor is used for acquiring space temperature parameters, the humidity sensor is used for acquiring space humidity parameters, and the gas sensor is used for acquiring harmful gas content parameters.
Specifically, the temperature sensor can be used for collecting space temperature parameters, the humidity sensor is used for collecting space humidity parameters, the gas sensor is used for collecting harmful gas content parameters, the multi-parameter sensor integrated with the temperature sensor, the humidity sensor and the gas sensor can be used for carrying out flaw detection on the cable to obtain cable damage parameters, and the GPS positioning sensor is used for obtaining positioning parameters. The positioning parameters can be used as label information of cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters in the environment parameters, and the cable damage parameters, the space temperature parameters, the space humidity parameters and the harmful gas content parameters at the same position are packaged together to be used as one environment parameter.
An environmental exception handling apparatus according to an embodiment of the present application is applied to an environmental detection system, and as shown in fig. 6, the environmental exception handling apparatus includes: a detection module 602, a prediction module 604, and a processing module 606.
The detection module 602 is configured to acquire an environmental parameter in the cable trench by using the detection sensing module, where the environmental parameter at least includes: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter.
Specifically, the environmental parameters at least include: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters. The process of obtaining the environmental parameters is as follows: the positioning information can be acquired by using a GPS sensor, the space temperature parameter can be acquired by using a temperature sensor, the space humidity parameter can be acquired by using a humidity sensor, the harmful gas content parameter can be acquired by using a gas sensor, and the cable damage parameter can be acquired by detecting a flaw by using a multi-parameter sensor integrated with the temperature sensor, the humidity sensor and the gas sensor; the detection sensing module can also comprise an infrared imaging unit and a millimeter wave imaging unit, the infrared imaging unit is used for collecting infrared rays radiated outwards by each device, two-dimensional or three-dimensional modeling is carried out to reproduce a first image corresponding to the environment of the cable trench, the millimeter wave imaging unit can transmit millimeter wave signals to a target view field in the cable trench, the devices, cables, channels and the like in the target view field are modulated and reflect the millimeter wave signals to form echo signals, the millimeter wave imaging unit captures the echo signals reflected by the target view field, a two-dimensional or three-dimensional scene of the cable channel is obtained according to the echo signal modeling, the first image is identified to obtain first environment parameters, the second image is identified to obtain second environment parameters, and the first environment parameters and the second environment parameters are mutually supplemented to obtain the environment parameters.
A prediction module 604, configured to input the environmental parameter into a prediction model to obtain environmental prediction information, where the prediction model is a trained recurrent neural network model, and the recurrent neural network model includes: the LSTM network layer.
Among them, the Long Short Term Memory network (LSTM) is a recurrent neural network with a complex structure. A fully connected recurrent neural network typically includes: input layer, hidden layer and output layer. The input layer is an input layer, the hidden layer is a hidden layer, the hidden layer can have multiple layers, and the output layer is an output layer. In a standard LSTM network structure, 4 values are required for input, and 1 value is output, wherein there are 3 forgetting gate concepts, i.e., input gate, forgetgate, and output gate, and since there are 4 parameters for input, the number of parameters is usually 4 times that of a general neural network. LSTM can effectively prevent the gradient disappearance problem by gating control.
Specifically, the prediction model may include a plurality of recurrent neural network models, each parameter corresponds to one network model, and for example, the prediction model may include a model for predicting a cable damage parameter, a model for predicting a space temperature parameter, a model for predicting a space humidity parameter, and a model for predicting a harmful gas content parameter, where the positioning parameter may be used as a label of the environment parameter. Each environment parameter corresponds to one piece of positioning information, a circulating neural network model is trained by utilizing a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter which are recorded at different moments and are at the same position, the cable damage parameter, the space temperature parameter, the space humidity parameter and the harmful gas content parameter are respectively predicted, the predicted results are collected, and the environment prediction information is obtained by combining the positioning parameters.
And the processing module 606 is configured to determine, when the environment prediction information includes environment abnormal information, a corresponding abnormal avoidance policy according to the environment abnormal information.
Specifically, the environment prediction information is detected, and when parameters which do not match the environment reference information exist in the environment prediction information, the environment abnormal information is obtained according to the parameters which do not match in the environment prediction information. An abnormal avoidance strategy corresponding to the environmental abnormal information is stored in the environment detection system, if the fact that the temperature of the equipment B at the coordinate A is higher than a threshold value is predicted, and the equipment B at the coordinate A is identified to possibly cause a fire phenomenon, the abnormal avoidance strategy corresponding to the equipment B is searched in the environment detection system, and the abnormal avoidance strategy can be used for powering off the equipment B and carrying out software maintenance and hardware maintenance.
The environment prediction method and device, the electronic equipment and the computer-readable storage medium are applied to an environment detection system, and the method comprises the following steps: utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter. Inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: the LSTM network layer. And when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. According to the method and the device, the environmental parameters in the cable trench are obtained by the detection sensing module, the environmental parameters are input into the prediction model constructed by the recurrent neural network to obtain the environmental prediction information, and when the environmental prediction information comprises the environmental abnormal information, the corresponding avoidance strategy is obtained. The prediction model constructed by the recurrent neural network is utilized, the accuracy of environment prediction information is guaranteed, meanwhile, the prediction efficiency is improved, the abnormity avoidance strategy is obtained according to the predicted environment abnormity information, and the probability of environment abnormity can be effectively reduced.
The environment prediction device utilizes the detection sensing module to obtain the environment parameters in the cable trench, and the environment parameters at least comprise: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter. Inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: the LSTM network layer. And when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information. According to the method and the device, the environmental parameters in the cable trench are obtained by the detection sensing module, the environmental parameters are input into the prediction model constructed by the recurrent neural network to obtain the environmental prediction information, and when the environmental prediction information comprises the environmental abnormal information, the corresponding avoidance strategy is obtained. The prediction model constructed by the recurrent neural network is utilized, the accuracy of environment prediction information is guaranteed, meanwhile, the prediction efficiency is improved, the abnormity avoidance strategy is obtained according to the predicted environment abnormity information, and the probability of environment abnormity can be effectively reduced.
The division of the modules in the environment prediction apparatus is only used for illustration, and in other embodiments, the environment prediction apparatus may be divided into different modules as needed to complete all or part of the functions of the environment prediction apparatus.
For the specific definition of the environment prediction device, reference may be made to the above definition of the environment prediction method, which is not described herein again. The modules in the environment prediction device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Fig. 7 is a schematic diagram of the internal structure of the environment detection system in one embodiment. As shown in fig. 7, the environment detection system includes a processor, a memory, and a network interface connected by a system bus. Wherein, the processor is used for providing calculation and control capability and supporting the operation of the whole electronic equipment. The memory is used for storing data, programs and the like, and the memory stores at least one computer program which can be executed by the processor to realize the wireless network communication method suitable for the electronic device provided by the embodiment of the application. The memory may include a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The computer program can be executed by a processor for implementing an environment prediction method provided in the following embodiments. The internal memory provides a cached execution environment for the operating system computer programs in the non-volatile storage medium. The network interface may be an ethernet card or a wireless network card, etc. for communicating with an external electronic device.
The respective modules in the environment prediction apparatus provided in the embodiments of the present application may be implemented in the form of a computer program. The computer program may be run on a terminal or a server. The program modules constituted by the computer program may be stored on the memory of the terminal or the server. Which when executed by a processor, performs the steps of the method described in the embodiments of the present application.
The embodiment of the application also provides a computer readable storage medium. One or more non-transitory computer-readable storage media containing computer-executable instructions that, when executed by one or more processors, cause the processors to perform the steps of the environment prediction method of:
utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: the system comprises a positioning parameter, a cable damage parameter, a space temperature parameter, a space humidity parameter and a harmful gas content parameter.
Inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: the LSTM network layer.
And when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information.
A computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of environment prediction.
Any reference to memory, storage, database, or other medium used herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and bus dynamic RAM (RDRAM).
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An environment prediction method is applied to an environment detection system, and the method comprises the following steps:
utilize and survey sensing module and acquire the environmental parameter in the cable pit, the environmental parameter includes at least: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters;
inputting the environmental parameters into a prediction model to obtain environmental prediction information, wherein the prediction model is a trained recurrent neural network model, and the recurrent neural network model comprises: an LSTM network layer;
and when the environment prediction information comprises environment abnormal information, determining a corresponding abnormal avoidance strategy according to the environment abnormal information.
2. The method of claim 1, wherein prior to entering the environmental parameters into a predictive model to obtain environmental predictive information, the method further comprises:
acquiring an environment parameter training set, wherein the environment parameter training set comprises a plurality of environment parameters carrying recording time information;
constructing the recurrent neural network model;
and training the recurrent neural network model by using the environmental parameter training set to obtain the prediction model.
3. The method of claim 2, wherein training the recurrent neural network model using the training set of environmental parameters to obtain the predictive model comprises:
determining a loss function of the recurrent neural network model according to the environmental parameters of each recording moment in the environmental parameter training set;
inputting the environmental parameter training set into the recurrent neural network model to optimize the weight of the LSTM network layer until the output value of the loss function is smaller than a preset threshold value;
and taking the recurrent neural network model corresponding to the loss function with the output value smaller than a preset threshold value as the prediction model.
4. The method of claim 1,
before determining the corresponding abnormal avoidance strategy according to the environment abnormal information, the method further comprises the following steps:
comparing the environment prediction information with environment reference information to obtain environment abnormal information, wherein the environment abnormal information comprises an abnormal identifier;
the determining the corresponding abnormal avoidance strategy according to the environment abnormal information comprises the following steps:
and acquiring a corresponding abnormal avoidance strategy according to the abnormal identifier of the environment abnormal information.
5. The method according to claim 4, wherein the obtaining of the corresponding anomaly avoidance strategy according to the anomaly identification of the environmental anomaly information includes:
searching the abnormal identification in a preset list, wherein the abnormal identification of the abnormal information of the conventional environment and a corresponding abnormal avoidance strategy are stored in the preset list;
when the abnormal identifier of the environment abnormal information is in the preset list, acquiring an abnormal avoidance strategy corresponding to the abnormal identifier stored in the preset list;
and when the abnormal identifier of the environment abnormal information is not in the preset list, taking an emergency processing strategy as an abnormal avoidance strategy corresponding to the abnormal identifier.
6. The method of claim 1, wherein the detection sensing module further comprises an infrared imaging unit and a millimeter wave imaging unit, and the acquiring the environmental parameter in the cable trench by using the detection sensing module comprises:
acquiring a first image of a target field of view by using an infrared imaging unit, and acquiring a second image of the target field of view by using the infrared imaging unit;
and carrying out image fusion on the first image and the second image to obtain a target image, and acquiring the environmental parameters according to the target image.
7. The method of claim 1, wherein the detection sensing module comprises at least: position sensor, temperature sensor, humidity transducer and gas sensor, utilize and survey sensing module and acquire the environmental parameter in the cable pit, include:
acquiring the positioning parameters by using the position sensor; acquiring damage parameters of the cable by using the cable flaw detection sensor; the temperature sensor is used for acquiring the space temperature parameter, the humidity sensor is used for acquiring the space humidity parameter, and the gas sensor is used for acquiring the harmful gas content parameter.
8. An environmental exception handling apparatus, applied to an environmental detection system, the apparatus comprising:
the detection module is used for acquiring environmental parameters in the cable trench by using the detection sensing module, and the environmental parameters at least comprise: positioning parameters, cable damage parameters, space temperature parameters, space humidity parameters and harmful gas content parameters;
a prediction module, configured to input the environmental parameter into a prediction model to obtain environmental prediction information, where the prediction model is a trained recurrent neural network model, and the recurrent neural network model includes: an LSTM network layer;
and the processing module is used for determining a corresponding abnormal avoidance strategy according to the environment abnormal information when the environment prediction information comprises the environment abnormal information.
9. An electronic device comprising a memory and a processor, the memory having stored therein a computer program that, when executed by the processor, causes the processor to perform the steps of the environment prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357901.5A CN111127825A (en) | 2019-12-25 | 2019-12-25 | Environment prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357901.5A CN111127825A (en) | 2019-12-25 | 2019-12-25 | Environment prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111127825A true CN111127825A (en) | 2020-05-08 |
Family
ID=70502257
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911357901.5A Pending CN111127825A (en) | 2019-12-25 | 2019-12-25 | Environment prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111127825A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611991A (en) * | 2020-05-23 | 2020-09-01 | 中南大学 | Fault processing method and device, electronic equipment and computer readable storage medium |
| CN112216055A (en) * | 2020-09-24 | 2021-01-12 | 佛山市天然气高压管网有限公司 | Fire early warning detection method and system for gas field station |
| CN113469243A (en) * | 2021-06-30 | 2021-10-01 | 国网浙江宁波市鄞州区供电有限公司 | Method for predicting cable performance in extreme environment |
| CN113884130A (en) * | 2021-09-16 | 2022-01-04 | 广州番禺电缆集团有限公司 | Cable aging prediction method, device and equipment based on cable well environment monitoring |
| CN114047303A (en) * | 2022-01-04 | 2022-02-15 | 南京天创电子技术有限公司 | Cable scorching smell continuous detection method based on inspection robot |
| CN114777959A (en) * | 2022-06-22 | 2022-07-22 | 国网山东省电力公司兰陵县供电公司 | Cable trench state monitoring method and device, storage medium and terminal |
| CN115346345A (en) * | 2022-07-28 | 2022-11-15 | 福建省杭氟电子材料有限公司 | Intelligent toxic and harmful gas alarm system for preparing hexafluorobutadiene |
| CN115563622A (en) * | 2022-09-29 | 2023-01-03 | 国网山西省电力公司 | Method, device and system for detecting operating environment |
| CN115758226A (en) * | 2023-01-06 | 2023-03-07 | 之江实验室 | Method and device for anomaly detection, storage medium and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070044979A1 (en) * | 2005-08-30 | 2007-03-01 | Federal Express Corporation | Fire sensor, fire detection system, fire suppression system, and combinations thereof |
| CN106017560A (en) * | 2016-06-14 | 2016-10-12 | 上海君世电气科技有限公司 | Cable well state comprehensive monitoring and early warning system |
| CN106441423A (en) * | 2016-08-31 | 2017-02-22 | 国网河南省电力公司南阳供电公司 | Online monitoring platform for underground cable channels of urban power grids |
| CN107491508A (en) * | 2017-08-01 | 2017-12-19 | 浙江大学 | A kind of data base querying time forecasting methods based on Recognition with Recurrent Neural Network |
| CN109165727A (en) * | 2018-09-04 | 2019-01-08 | 成都品果科技有限公司 | A kind of data predication method based on Recognition with Recurrent Neural Network |
| CN109509327A (en) * | 2018-10-31 | 2019-03-22 | 武汉烽火众智数字技术有限责任公司 | A kind of abnormal behaviour method for early warning and device |
-
2019
- 2019-12-25 CN CN201911357901.5A patent/CN111127825A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070044979A1 (en) * | 2005-08-30 | 2007-03-01 | Federal Express Corporation | Fire sensor, fire detection system, fire suppression system, and combinations thereof |
| CN106017560A (en) * | 2016-06-14 | 2016-10-12 | 上海君世电气科技有限公司 | Cable well state comprehensive monitoring and early warning system |
| CN106441423A (en) * | 2016-08-31 | 2017-02-22 | 国网河南省电力公司南阳供电公司 | Online monitoring platform for underground cable channels of urban power grids |
| CN107491508A (en) * | 2017-08-01 | 2017-12-19 | 浙江大学 | A kind of data base querying time forecasting methods based on Recognition with Recurrent Neural Network |
| CN109165727A (en) * | 2018-09-04 | 2019-01-08 | 成都品果科技有限公司 | A kind of data predication method based on Recognition with Recurrent Neural Network |
| CN109509327A (en) * | 2018-10-31 | 2019-03-22 | 武汉烽火众智数字技术有限责任公司 | A kind of abnormal behaviour method for early warning and device |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611991A (en) * | 2020-05-23 | 2020-09-01 | 中南大学 | Fault processing method and device, electronic equipment and computer readable storage medium |
| CN112216055A (en) * | 2020-09-24 | 2021-01-12 | 佛山市天然气高压管网有限公司 | Fire early warning detection method and system for gas field station |
| CN112216055B (en) * | 2020-09-24 | 2021-05-11 | 佛山市天然气高压管网有限公司 | Fire early warning detection method and system for gas field station |
| CN113469243A (en) * | 2021-06-30 | 2021-10-01 | 国网浙江宁波市鄞州区供电有限公司 | Method for predicting cable performance in extreme environment |
| CN113884130A (en) * | 2021-09-16 | 2022-01-04 | 广州番禺电缆集团有限公司 | Cable aging prediction method, device and equipment based on cable well environment monitoring |
| CN114047303B (en) * | 2022-01-04 | 2022-04-12 | 南京天创电子技术有限公司 | Cable scorching smell continuous detection method based on inspection robot |
| CN114047303A (en) * | 2022-01-04 | 2022-02-15 | 南京天创电子技术有限公司 | Cable scorching smell continuous detection method based on inspection robot |
| CN114777959A (en) * | 2022-06-22 | 2022-07-22 | 国网山东省电力公司兰陵县供电公司 | Cable trench state monitoring method and device, storage medium and terminal |
| CN115346345A (en) * | 2022-07-28 | 2022-11-15 | 福建省杭氟电子材料有限公司 | Intelligent toxic and harmful gas alarm system for preparing hexafluorobutadiene |
| WO2024021253A1 (en) * | 2022-07-28 | 2024-02-01 | 福建省杭氟电子材料有限公司 | Intelligent toxic and harmful gas alarm system for preparing hexafluorobutadiene |
| CN115563622A (en) * | 2022-09-29 | 2023-01-03 | 国网山西省电力公司 | Method, device and system for detecting operating environment |
| CN115563622B (en) * | 2022-09-29 | 2024-03-12 | 国网山西省电力公司 | Method, device and system for detecting operation environment |
| CN115758226A (en) * | 2023-01-06 | 2023-03-07 | 之江实验室 | Method and device for anomaly detection, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111127825A (en) | Environment prediction method and device and electronic equipment | |
| CN112669316B (en) | Power production abnormality monitoring method, device, computer equipment and storage medium | |
| RU2573735C2 (en) | Method and system for analysis of flight data recorded during aircraft flight | |
| CN111209980A (en) | Environment detection method and device, electronic equipment and computer readable storage medium | |
| BR112018072687B1 (en) | STRUCTURAL HEALTH SYSTEM ACCORDING TO IDENTIFICATION OF DAMAGE THROUGH A DEVICE BASED ON AUGMENTED REALITY TECHNOLOGY | |
| US20090273479A1 (en) | Hazard Dectection And Mitigation System And Method | |
| CN111611991A (en) | Fault processing method and device, electronic equipment and computer readable storage medium | |
| CN105787581A (en) | Apparatus And Method For Early Detection Of Abnormality | |
| Bektash et al. | Automated emergency landing system for drones: SafeEYE project | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN116754022B (en) | On-line detection emergency early warning method and system for cable tunnel | |
| Naddaf-Sh et al. | Real‐Time Explainable Multiclass Object Detection for Quality Assessment in 2‐Dimensional Radiography Images | |
| KR102279039B1 (en) | Vessel maintenance support method by vessel maintenance support system including mobile device and maintenance support server | |
| CN111105582B (en) | Forest fire prevention monitoring method and system, computer equipment and readable storage medium | |
| CN116050807B (en) | Feed production equipment defect identification method and system based on video monitoring inspection | |
| CN117058630A (en) | Coast ship identification method, system, equipment and storage medium | |
| CN117214598A (en) | Cable monitoring system and method based on inspection image | |
| KR20210115121A (en) | Deeep learning-based disaster safety building custom 3D modeling dataset construction method | |
| CN115861364A (en) | AI identification-based field personnel management and control method and system | |
| KR20220107540A (en) | Apparatus for artificial intelligence based safety diagnosis through 3d model and method thereof | |
| CN113515993A (en) | Video anomaly detection method, video anomaly model training method, video anomaly detection equipment, video anomaly model and storage medium | |
| US20240053287A1 (en) | Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography | |
| CN117668737B (en) | Pipeline detection data fault early warning checking method and related device | |
| EP4092315A1 (en) | System and method for inspecting stability of heat transfer pipe by using drone | |
| KR102332699B1 (en) | Event processing system for detecting changes in spatial environment conditions using image model-based AI algorithms |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200508 |
|
| RJ01 | Rejection of invention patent application after publication |