CN112468988A - Hazardous chemical substance monitoring method and device - Google Patents
Hazardous chemical substance monitoring method and device Download PDFInfo
- Publication number
- CN112468988A CN112468988A CN202011206134.0A CN202011206134A CN112468988A CN 112468988 A CN112468988 A CN 112468988A CN 202011206134 A CN202011206134 A CN 202011206134A CN 112468988 A CN112468988 A CN 112468988A
- Authority
- CN
- China
- Prior art keywords
- hazardous chemical
- real
- chemical substance
- monitoring data
- data
- 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
- 239000000126 substance Substances 0.000 title claims abstract description 136
- 238000012544 monitoring process Methods 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000000383 hazardous chemical Substances 0.000 title claims description 108
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims abstract description 46
- 238000003062 neural network model Methods 0.000 claims abstract description 32
- 238000012806 monitoring device Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 18
- 230000005540 biological transmission Effects 0.000 description 34
- 230000015654 memory Effects 0.000 description 24
- 238000005516 engineering process Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 230000006854 communication Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 14
- 238000004590 computer program Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012795 verification Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 239000007789 gas Substances 0.000 description 6
- 238000004880 explosion Methods 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 239000002360 explosive Substances 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000005507 spraying Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000002087 whitening effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/50—Safety; Security of things, users, data or systems
Abstract
The application discloses a dangerous chemical monitoring method, which comprises the following steps: acquiring real-time monitoring data of at least one type of sensor for dangerous chemicals based on an LoRa network; acquiring a monitoring value based on the real-time monitoring data and a preset neural network model; and determining the safety state of the dangerous chemicals based on the monitoring value. The embodiment of the application also provides a monitoring device for the dangerous chemical plant, which can comprehensively and accurately monitor the dangerous chemical.
Description
Technical Field
The invention relates to the field of hazardous chemical sensing monitoring, in particular to a hazardous chemical monitoring method and device.
Background
The dangerous chemical varieties of chemical plants are various, the production lines are widely distributed, and the production field environment is complex. In order to standardize the safety production management of a chemical plant, ensure the regional safety of chemical devices, orderly control the safety production of the chemical plant and quickly carry out the emergency treatment of safety emergencies, dangerous chemicals are necessarily monitored. Therefore, how to monitor hazardous chemicals comprehensively and accurately is a constantly pursued goal.
Disclosure of Invention
The embodiment of the invention provides a method and a device for monitoring a hazardous chemical substance plant, which can comprehensively and accurately monitor hazardous chemical substances.
The embodiment of the invention provides the following specific technical scheme:
the embodiment of the invention provides a monitoring method for a hazardous chemical substance plant, which comprises the following steps:
acquiring real-time monitoring data of at least one type of sensor for dangerous chemicals based on an LoRa network;
acquiring a monitoring value based on the real-time monitoring data and a preset neural network model;
and determining the safety state of the dangerous chemicals based on the monitoring value.
In some embodiments, the real-time monitoring data of at least one type of sensor for hazardous chemical substances is acquired based on an LoRa network, and the real-time monitoring data of the hazardous chemical substances sent by an LoRa gateway is received; the real-time monitoring data of the hazardous chemical substances are collected by at least one type of sensor and are sent to the LoRa gateway.
In some embodiments, based on the real-time monitoring data and a preset neural network model, inputting the real-time monitoring data into the neural network model to obtain the monitoring value; and the neural network model is obtained by training based on the historical monitoring data of the dangerous chemicals.
In some embodiments, said determining a safety state of said hazardous chemical based on said monitored value comprises: determining that the state of the dangerous chemicals is unsafe under the condition that the monitoring value is within an early warning range; and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
In some embodiments, in the case that the state of the hazardous chemical substance is determined to be unsafe, triggering an in-plant alarm system of the hazardous chemical substance and/or sending a first alarm message to an out-plant alarm system of the hazardous chemical substance.
In some embodiments, when the state of the hazardous chemical substance is determined to be unsafe based on at least two monitoring values obtained from real-time monitoring data of at least two types of sensors, triggering an in-plant alarm system of the hazardous chemical substance and/or sending second alarm information to an out-of-plant alarm system of the hazardous chemical substance, wherein the urgency degree of the second alarm information is higher than that of the first alarm information.
The embodiment of the application still provides a dangerization article monitoring device, dangerization article monitoring device includes:
the acquisition unit is used for acquiring real-time monitoring data of at least one type of sensor for dangerous chemicals based on the LoRa network; and acquiring a monitoring value based on the real-time monitoring data and a preset neural network model.
And the determining unit is used for determining the safety state of the dangerous chemicals based on the monitoring value.
In some embodiments, the obtaining unit is further configured to receive real-time monitoring data of the hazardous chemical substance sent by the LoRa gateway; the real-time monitoring data of the hazardous chemical substances are collected by at least one type of sensor and are sent to the LoRa gateway.
In some embodiments, the obtaining unit is further configured to input the real-time monitoring data into the neural network model to obtain the monitoring value; and the neural network model is obtained by training based on historical monitoring data of the dangerous chemicals.
In some embodiments, the determining unit is further configured to determine that the state of the hazardous chemical substance is unsafe if the monitored value is within an early warning range; and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
In some embodiments, the apparatus further comprises: the first sending unit is used for sending first alarm information to an in-plant alarm system of the hazardous chemical substance and/or an out-plant alarm system of the hazardous chemical substance under the condition that the state of the hazardous chemical substance is determined to be unsafe.
In some embodiments, the apparatus further comprises: and the second sending unit is used for sending second alarm information to an in-plant alarm system of the hazardous chemical substance and/or an out-of-plant alarm system of the hazardous chemical substance under the condition that the state of the hazardous chemical substance is determined to be unsafe on the basis of at least two monitoring values obtained by real-time monitoring data of at least two types of sensors, and the emergency degree of the second alarm information is higher than that of the first alarm information.
According to the hazardous chemical substance monitoring method and device provided by the embodiment of the invention, the hazardous chemical substance monitoring device acquires real-time monitoring data of at least one type of sensor for the hazardous chemical substance based on the LoRa network; acquiring a monitoring value based on the real-time monitoring data and a preset neural network model; and determining the safety state of the dangerous chemicals based on the monitoring value. Therefore, the problem that the safety state of the hazardous chemical substance cannot be timely acquired due to poor network signals of the hazardous chemical substance factory in the prior art is solved by acquiring real-time monitoring data based on the LoRa network; because the acquired real-time monitoring data can be acquired by a plurality of sensors, hazardous chemical substances can be monitored from different dimensions, and the monitoring data is fully mined and analyzed to form accurate and effective accident prediction.
Drawings
Fig. 1 is a system architecture diagram in an embodiment of the invention.
Fig. 2 is a schematic view of an alternative flow of a hazardous chemical monitoring method according to an embodiment of the present invention.
Fig. 3 is a flow chart of an AI neural network prediction service in an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a hazardous chemical substance monitoring device provided in an embodiment of the present application.
Fig. 5 is a schematic diagram of a hardware composition structure of the hazardous chemical substance monitoring device according to the embodiment of the present application.
Detailed Description
The present application will be described in further detail below with reference to the accompanying drawings and examples. 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.
Before the embodiments of the present application are described in detail, information related to hazardous chemical substances is briefly described. In the processes of chemical production, processing, transportation and storage in hazardous chemical plants, various flammable and explosive gases, liquids, various dusts and fibers may be leaked and dispersed. The substances and air are moderate and become mixture which is easy to generate explosion danger, and the surrounding place is also a place with different explosion danger. When the concentration of explosive reaches the critical point of explosion, once an explosion source appears, serious accidents such as explosion, fire and the like can be caused. The explosion-proof application monitoring equipment is necessary to be correctly installed and used in each explosion-proof area, so that various potential safety hazards can be effectively reduced. However, the existing part of hazardous chemical plant areas have poor wireless signals, which may cause loss in the data transmission process, and the geographical positions of part of plant areas are far away, which may cause network coverage of operators to be unavailable; the network data transmission mode of the existing part of dangerous chemical plant is single, the construction difficulty of the sensor is high, and the cost of the whole network amortization is high; the current monitoring content of the existing part of dangerous chemical plant is not comprehensive, and the whole content of the dangerous chemical plant to be monitored cannot be covered; moreover, the multi-sensor data fusion technology of the hazardous chemical plant is rare, and the data value cannot be effectively and fully mined, so that an effective accident prediction function is formed; finally, the existing part of dangerous chemical plants have the problems of single early warning form and unspecific content.
Fig. 1 is a system architecture diagram in an embodiment of the present invention, and as shown in fig. 1, the system architecture is divided into three layers, namely a data sensing layer, a data transmission layer, and a platform management layer.
The data perception layer is used for gathering danger article data through the sensor, and the kind of sensor covers the sensor that is used for the monitoring to easily fire explosive gas concentration, humiture monitoring sensor, flame monitoring sensor, tank field liquid level monitoring sensor, hydraulic monitoring sensor etc. and the monitoring dimension is comprehensive.
And the data transmission layer is used for transmitting the data acquired by the sensor to a server or a cloud platform. Adopt the wireless sensor based on loRa module, perhaps traditional serial port sensor passes through the cooperation with DTU, realizes that the wireless data of loRa passes through. The wireless sensor network integrates computer technology, sensor technology, embedded technology and wireless communication technology. The LoRa technology is a low-power-consumption wide-area communication technology and supports long-time work of a disposable power supply; the transmission distance is long, and the point-to-point transmission distance can reach 20km under the condition of no obstruction; the security is high, and the LoRaWAN protocol carries out double encryption on the data packet; the stability is high, and data directly sends to wherein through the single hop, and the model of LoRa gateway can be G200 or G500 etc.. The wireless sensor network based on the LoRa utilizes the effective long-distance transmission of the LoRa communication technology and a star network topological structure, thereby improving the coverage area of the wireless sensor network. The serial interface sensor is a serial interface for short, and is an extended interface adopting a serial communication mode. The serial interface means that data is sequentially transferred one bit by one bit (parallel port is to transmit 8-bit data at the same time). The serial port communication line is simple, two-way communication can be realized only by one pair of transmission lines, although one bit of data is transmitted at one time, mutual interference among different data channels during parallel port transmission can be avoided, and the work is more stable. RS232 is a standard serial port and is used most, the maximum transmission distance is 15 meters, and the maximum speed is 20 kb/s; RS422 is a serial port having a master-slave function, and allows a plurality of receiving nodes (up to 10) to be connected to the same transmission line, that is, one master device and a plurality of slave devices, the master device can communicate with any slave device, and the slave devices cannot communicate with each other. The transmission performance is improved compared with that of RS232, the maximum transmission distance is 1219 m, and the maximum transmission speed is 10 Mb/s; RS485 is an optimized serial interface based on RS422, and can connect up to 32 slave devices, and the maximum transmission distance and the maximum transmission rate of the interface are the same as those of RS 422. The core of the data transmission layer is an LoRa gateway, the LoRa gateway is in a star networking mode, the transmission distance of the data transmission layer is related to the type of the LoRa gateway, the minimum value of the transmission distance can be 2KM to 3KM, and the maximum value of the transmission distance can reach more than 10 KM.
The core of the platform management layer may be a LinkOS cloud platform. After receiving the data acquired by the sensor, the Lora gateway can transmit the data to the LinkOS cloud platform; the LinkOS cloud platform can be deployed for public clouds or private clouds. The LinkOS cloud platform carries out maintenance management on the sensor and forwards data acquired by the sensor to an Internet of things host of a hazardous chemical substance factory. Based on historical data and real-time data, the LinkOS cloud platform monitors and warns safety state trends of hazardous chemicals and provides scheduling suggestions through an Artificial Intelligence network (AI). The host of the internet of things directly reports the information to an emergency management early warning system of the local government through an emergency special line.
In some embodiments, the platform management layer may be based on: and performing model training on historical data by using a Long Short-Term Memory network (LSTM) to obtain a neural network model for determining the safety state of the hazardous chemical substance, and monitoring and early warning the safety state trend of the hazardous chemical substance based on the real-time data and the neural network model. Meanwhile, the background is fused with data collected by various sensors, such as temperature data collected by a temperature sensor and combustible gas concentration data, and early warning is carried out by the cloud platform according to the monitoring value. If the temperature continuously exceeds the set value and the concentration exceeds the set value, strong early warning is carried out.
An optional processing flow of the hazardous chemical substance monitoring method provided in the embodiment of the present application is shown in fig. 2, and includes:
step S201, real-time monitoring data of at least one type of sensor for dangerous chemicals is obtained based on the LoRa network.
In some embodiments, the LinkOS cloud platform obtains real-time monitoring data of at least one type of sensor for hazardous chemicals based on the LoRa network. For example, the LinkOS cloud platform receives real-time monitoring data of at least one type of sensor for dangerous chemicals through the LoRa gateway.
In some embodiments, the real-time monitoring data of the hazardous chemical may be collected by one or more types of sensors. Such as: the temperature sensor collects the temperature of the hazardous chemical substance, the liquid level sensor collects the liquid level of the hazardous chemical substance in the tank area, the gas concentration sensor collects the concentration of combustible or toxic gas in the hazardous chemical substance, the humidity sensor collects the humidity of the hazardous chemical substance and the like.
In some embodiments, adopt the wireless sensor based on loRa module, perhaps traditional serial port sensor passes through the cooperation with DTU, realizes that the wireless data of loRa passes through. The wireless sensor network integrates computer technology, sensor technology, embedded technology and wireless communication technology. The LoRa technology is a low-power-consumption wide-area communication technology and supports long-time work of a disposable power supply; the transmission distance is long, and the point-to-point transmission distance can reach 20km under the condition of no obstruction; the security is high, and the LoRaWAN protocol carries out double encryption on the data packet; the stability is high, the data is directly sent to the Lora gateway through a single hop, and the model of the Lora gateway can be G200 or G500. The wireless sensor network based on the LoRa utilizes the effective long-distance transmission of the LoRa communication technology and a star network topological structure, thereby improving the coverage area of the wireless sensor network. The LoRa technology essentially provides an end-to-end communication connection pipeline, the applications of the LoRa technology also need to be connected with sensing terminals, and each sensing terminal supports local data analysis and a custom algorithm.
Based on the LoRa module, the serial port sensor adopts an expansion interface in a serial communication mode. The serial interface means that data is sequentially transferred one bit by one bit (parallel port is to transmit 8-bit data at the same time). The serial port has simple communication line, and can realize bidirectional communication by only one pair of transmission lines, thereby reducing the cost and being particularly suitable for remote communication. Although only one bit of data is transmitted at a time, the data transmission method is not interfered by the mutual interference among different data channels during parallel port transmission, and the work is more stable. RS232 is a standard serial port and is used most, the maximum transmission distance is 15 meters, and the maximum speed is 20 kb/s; RS422 is a serial port having a master-slave function, and allows a plurality of receiving nodes (up to 10) to be connected to the same transmission line, that is, one master device and a plurality of slave devices, the master device can communicate with any slave device, and the slave devices cannot communicate with each other. The transmission performance is improved compared with that of RS232, the maximum transmission distance is 1219 m, and the maximum transmission speed is 10 Mb/s; RS485 is an optimized serial interface based on RS422, and can connect up to 32 slave devices, and the maximum transmission distance and the maximum transmission rate of the interface are the same as those of RS 422.
And step S202, acquiring a monitoring value based on the real-time monitoring data and a preset neural network model.
In some embodiments, the LinkOS cloud platform obtains a monitoring value based on the real-time monitoring data and a preset neural network model.
In specific implementation, the LinkOS cloud platform inputs the real-time monitoring data into the neural network model to obtain the monitoring value.
And the neural network model is obtained by training based on historical monitoring data of the dangerous chemicals. Such as:
the LinkOS cloud platform determines a training set neural network model, such as a training LSTM model, by taking historical monitoring data as a training sample; the trained neural network model can determine the safety state of the dangerous chemicals based on the input current monitoring data of the dangerous chemicals. And if the current monitoring data is input into the neural network model, obtaining a monitoring value. And determining the safety state of the dangerous chemical according to the monitoring value, and if the state of the dangerous chemical is determined to be unsafe, sending an early warning by the LinkOS cloud platform and reporting early warning information to a server, wherein the early warning information can be first warning information or second warning information.
And step S203, determining the safety state of the dangerous chemicals based on the monitoring value.
In some embodiments, the LinkOS cloud platform determines the safety status of the hazardous chemical based on the monitored value.
In some embodiments, determining that the state of the hazardous chemical is unsafe if the monitored value is within an early warning range; and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe. The early warning range may be set to different concentration limits, different temperature limits, different humidity limits, or the like.
In some embodiments, the method may further comprise:
and step S204, under the condition that the state of the dangerous chemicals is determined to be unsafe, triggering an in-plant alarm system of the dangerous chemicals and/or sending first alarm information to an out-plant alarm system of the dangerous chemicals.
In some embodiments, if the state of the hazardous chemical substance is determined to be unsafe according to the neural network model, the LinkOS cloud platform triggers an in-plant alarm system of the hazardous chemical substance; such as starting the exhaust fan, starting the spraying system, sending acousto-optic information or sending short messages to inform relevant responsible persons, or stopping production.
Wherein, alarm information can divide according to the safety degree of dangerization article, if the security of dangerization article is low, then start first-level alarm information. And if the safety of the dangerous chemicals is extremely low, starting secondary alarm information. Namely, the emergency degree of the second alarm information is higher than that of the first alarm information.
The first-level alarm information and the second-level alarm information have different alarm modes. For example, the first-level alarm information may be to start an exhaust fan and start a spraying system, and the second-level alarm information may be to send audible and visual information or short messages to notify a relevant person in charge, or to stop production, etc.
In some embodiments, the method may further comprise:
step S205, when the LinkOS cloud platform determines that the state of the hazardous chemical substance is unsafe based on at least two monitoring values obtained by real-time monitoring data of at least two types of sensors, triggering an in-plant alarm system of the hazardous chemical substance and/or sending second alarm information to an out-plant alarm system of the hazardous chemical substance, wherein the emergency degree of the second alarm information is higher than that of the first alarm information.
In some embodiments, when the LinkOS cloud platform determines that the states of two or more hazardous chemicals are unsafe according to the neural network model, the LinkOS cloud platform triggers an alarm system of the hazardous chemicals, and sends second alarm information to an in-plant alarm system of the hazardous chemicals and/or an out-plant alarm system of the hazardous chemicals.
Specifically, the server performs model training on the historical data by using an LSTM model to obtain a neural network model for determining the safety state of the hazardous chemical substance, and then monitors and warns the safety state trend of the hazardous chemical substance based on the real-time data and the neural network model. Meanwhile, the background fuses data collected by various sensors, such as temperature data collected by a temperature sensor and combustible gas concentration data, to jointly monitor, and if the temperature continuously exceeds a set value and the concentration exceeds the set value, strong early warning is performed. The strong early warning mode comprises the modes of responding sound and light, system reminding, short message reminding and the like.
The embodiment of the present application further provides a detailed flow diagram of a hazardous chemical substance monitoring method, as shown in fig. 3, the method may include the following steps:
and S301, acquiring and storing historical chemical plant hazardous chemical sensor monitoring data by the LinkOS cloud platform based on the Lora network.
In some embodiments, the sensor monitoring data is monitoring data for hazardous chemicals based on at least one type of sensor acquired by a Lora network.
Step S302, the server classifies and preprocesses the sensor monitoring data.
In some embodiments, the sensor data may be classified as gas concentration data, temperature data, humidity data, and the like.
In some embodiments, the server preprocesses the sensor data, which may be zero mean, normalization, Principal Components Analysis (PCA), whitening, etc. of the sensor data. The zero mean value is obtained by subtracting the average value of each dimension of data from each dimension of original data and replacing the original data with the result; normalization is to normalize original data to the same scale, and there are two normalization methods at present, the first one is to carry on the zero mean value to the original data first, and then divide the data of each dimension by the standard deviation of the data of each dimension, the second one is to normalize the data of different dimensions to the same numerical value interval; PCA and whitening are to change data into zero mean value, then calculate the covariance matrix of the data to get the correlation between different dimensions of the data, and reduce the dimensions of the data by selecting the first few eigenvectors.
Step S303, the server can divide the sensor monitoring data into a training set and a verification set by using an algorithm, wherein the training set is used for fitting a model (training pattern recognition system), and the classification model is trained by setting parameters of the classifier. When the effect of the verification set is subsequently combined, different values of the same parameter are selected, and a plurality of classifiers are fitted; the verification set has the functions that after a plurality of models are trained through the training set, in order to find out the model with the best effect, the data of the verification set are predicted by using each model, and the accuracy of the model is recorded. And selecting the parameters corresponding to the model with the best effect, namely adjusting the model parameters. After the system is trained on the training set, some parameters are not learnable and need to be set artificially, such as the hyperparameter relaxation parameter C in the support vector machine SVM. However, the above-mentioned artificial setting may not be the optimal parameter, so the role of the validation set is to find the optimal parameter.
And step S304, training the LSTM model by the training data and the verification data, and optimizing the model parameters. The above-mentioned artificially set hyper-parameters are continuously debugged on the verification set until the result obtained on the verification set meets the requirements, and the optimal hyper-parameters are usually determined by adopting cross-validation on the verification set. After the hyper-parameters which need to be set artificially are determined, all the parameters of the system are determined, and then the effect of the system on the test set is determined.
In step S305, the server obtains the trained LSTM model based on step S304.
In some embodiments, the server updates the LSTM model at a preset period based on updated historical plant hazardous chemical sensor monitoring data.
The preset period can be flexibly set according to practical application, such as one week, two weeks, or one month.
Step S306, the server acquires current sensor monitoring data, wherein the current sensor monitoring data are real-time monitoring data of at least one type of sensor for dangerous chemicals acquired based on the Lora network.
And step S307, the server inputs the current sensor monitoring data into the LSTM model to obtain a predicted value.
Step S308, the server judges whether the predicted value is in the early warning range.
Wherein, the early warning range can be preset.
And step S309, if the predicted value is within the early warning range, the cloud platform starts an early warning system and reports information.
Specifically, the LinkOS cloud platform determines the safety state of the hazardous chemical substance according to the monitoring value, and if the state of the hazardous chemical substance is determined to be unsafe, the LinkOS cloud platform sends out an early warning and reports early warning information to the server, wherein the early warning information can be first warning information or second warning information.
In order to implement the hazardous chemical substance monitoring method, the embodiment of the application further provides a hazardous chemical substance monitoring device. The hazardous chemical substance monitoring device is schematically shown in the structural diagram, as shown in fig. 4:
hazardous chemical substance monitoring device 400 includes: an acquisition unit 401 and a determination unit 402.
The hazardous chemical substance monitoring device 400 includes:
the acquiring unit 401 is configured to acquire real-time monitoring data of at least one type of sensor for hazardous chemical substances based on a Lora network; and acquiring a monitoring value based on the real-time monitoring data and a preset neural network model.
A determining unit 402, configured to determine a safety state of the hazardous chemical based on the monitored value.
In some embodiments, the obtaining unit 401 is further configured to receive real-time monitoring data of the hazardous chemical substance sent by the Lora gateway; and the real-time monitoring data of the dangerous chemicals are collected by at least one type of sensor and are sent to the Lora gateway.
The obtaining unit 401 is further configured to input the real-time monitoring data into the neural network model to obtain the monitoring value; and the neural network model is obtained by training based on historical monitoring data of the dangerous chemicals.
In some embodiments, the determining unit 402 is configured to determine that the state of the hazardous chemical substance is unsafe if the monitored value is within an early warning range; and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
In some embodiments, the hazardous chemical monitoring device 400 further comprises: a first sending unit 403, configured to send first alarm information to an in-plant alarm system of the hazardous chemical substance and/or an out-of-plant alarm system of the hazardous chemical substance, when it is determined that the state of the hazardous chemical substance is unsafe.
In some embodiments, the hazardous chemical monitoring device 400 further comprises: the second sending unit 404 is configured to send second alarm information to an in-plant alarm system of the hazardous chemical substance and/or an out-of-plant alarm system of the hazardous chemical substance under the condition that the state of the hazardous chemical substance is determined to be unsafe based on at least two monitoring values obtained based on real-time monitoring data of at least two types of sensors, where an emergency degree of the second alarm information is higher than that of the first alarm information.
And under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
Fig. 5 is a schematic diagram of a hardware composition structure of the hazardous chemical substance monitoring device according to the embodiment of the present application. The apparatus 800 comprises: at least one processor 801, memory 802, and at least one network interface 804. The various components in the device 800 are coupled together by a bus system 805. It is understood that the bus system 805 is used to enable communications among the components connected. The bus system 805 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 805 in fig. 5.
It will be appreciated that the memory 802 can be either volatile memory or nonvolatile memory, and can include both volatile and nonvolatile memory. The nonvolatile Memory may be ROM, Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), magnetic Random Access Memory (FRAM), Flash Memory (Flash Memory), magnetic surface Memory, optical Disc, or Compact Disc Read-Only Memory (CD-ROM); the magnetic surface storage may be disk storage or tape storage. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (Enhanced Synchronous DRAM), Direct Memory Access (DRAM), and Direct Memory Access (DRDRU). The memory 802 described in connection with the embodiments of the invention is intended to comprise, without being limited to, these and any other suitable types of memory.
The memory 802 in embodiments of the present invention is used to store various types of data to support the operation of the device 800. Examples of such data include: any computer program for operation on device 800, such as application 8022. A program implementing a method according to an embodiment of the present invention may be included in application program 8022.
The methods disclosed in the embodiments of the present invention described above may be implemented in the processor 801 or implemented by the processor 801. The processor 801 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 801. The Processor 801 may be a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Processor 801 may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the method disclosed by the embodiment of the invention can be directly implemented by a hardware decoding processor, or can be implemented by combining hardware and software modules in the decoding processor. The software modules may be located in a storage medium that is located in the memory 802, and the processor 801 reads the information in the memory 802 to perform the steps of the aforementioned methods in conjunction with its hardware.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), FPGAs, general purpose processors, controllers, MCUs, MPUs, or other electronic components for performing the foregoing methods.
The embodiment of the application also provides a storage medium for storing the computer program.
Optionally, the storage medium may be applied to the terminal device in the embodiment of the present application, and the computer program enables the computer to execute corresponding processes in each method in the embodiment of the present application, which is not described herein again for brevity.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (12)
1. A method for monitoring hazardous chemicals, the method comprising:
acquiring real-time monitoring data of at least one type of sensor for dangerous chemicals based on an LoRa network;
acquiring a monitoring value based on the real-time monitoring data and a preset neural network model;
and determining the safety state of the dangerous chemicals based on the monitoring value.
2. The method according to claim 1, wherein the obtaining of real-time monitoring data of at least one type of sensor for hazardous chemical substances based on the LoRa network comprises:
receiving real-time monitoring data of the hazardous chemical substances sent by the LoRa gateway;
the real-time monitoring data of the hazardous chemical substances are collected by at least one type of sensor and are sent to the LoRa gateway.
3. The method of claim 1, wherein obtaining the monitored values based on the real-time monitoring data and a preset neural network model comprises:
inputting the real-time monitoring data into the neural network model to obtain the monitoring value;
and the neural network model is obtained by training based on historical monitoring data of the dangerous chemicals.
4. The method of claim 1, wherein the determining the safety status of the hazardous chemical based on the monitored value comprises:
determining that the state of the dangerous chemicals is unsafe under the condition that the monitoring value is within an early warning range;
and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
5. The method according to any one of claims 1 to 4, further comprising:
and triggering the in-plant alarm system of the hazardous chemical substance and/or sending first alarm information to the out-of-plant alarm system of the hazardous chemical substance.
6. The method according to any one of claims 1 to 4, further comprising:
and under the condition that the state of the hazardous chemical substance is determined to be unsafe based on at least two monitoring values obtained by real-time monitoring data of at least two types of sensors, triggering an in-plant alarm system of the hazardous chemical substance and/or sending second alarm information to an out-of-plant alarm system of the hazardous chemical substance, wherein the emergency degree of the second alarm information is higher than that of the first alarm information.
7. A hazardous chemical monitoring device, the device comprising:
the acquisition unit is used for acquiring real-time monitoring data of at least one type of sensor for dangerous chemicals based on the LoRa network; acquiring a monitoring value based on the real-time monitoring data and a preset neural network model;
and the determining unit is used for determining the safety state of the dangerous chemicals based on the monitoring value.
8. The device according to claim 7, wherein the obtaining unit is configured to receive real-time monitoring data of the hazardous chemical substance sent by an LoRa gateway;
the real-time monitoring data of the hazardous chemical substances are collected by at least one type of sensor and are sent to the LoRa gateway.
9. The device according to claim 7, wherein the obtaining unit is configured to input the real-time monitoring data into the neural network model to obtain the monitoring value;
and the neural network model is obtained by training based on historical monitoring data of the dangerous chemicals.
10. The device of claim 7, wherein the determining unit is configured to determine that the state of the hazardous chemical substance is unsafe if the monitored value is within an early warning range;
and under the condition that the monitoring value is not within the early warning range, determining that the state of the dangerous chemicals is safe.
11. The apparatus of any one of claims 7 to 10, further comprising:
the first sending unit is used for triggering an in-plant alarm system of the hazardous chemical substance and/or sending first alarm information to an out-of-plant alarm system of the hazardous chemical substance under the condition that the state of the hazardous chemical substance is determined to be unsafe.
12. The apparatus of any one of claims 7 to 10, further comprising:
the second sending unit is used for triggering an in-plant alarm system of the hazardous chemical substance and/or sending second alarm information to an out-of-plant alarm system of the hazardous chemical substance under the condition that the state of the hazardous chemical substance is determined to be unsafe on the basis of at least two monitoring values obtained by real-time monitoring data of at least two types of sensors, and the emergency degree of the second alarm information is higher than that of the first alarm information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011206134.0A CN112468988A (en) | 2020-11-02 | 2020-11-02 | Hazardous chemical substance monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011206134.0A CN112468988A (en) | 2020-11-02 | 2020-11-02 | Hazardous chemical substance monitoring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112468988A true CN112468988A (en) | 2021-03-09 |
Family
ID=74835348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011206134.0A Pending CN112468988A (en) | 2020-11-02 | 2020-11-02 | Hazardous chemical substance monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112468988A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990706A (en) * | 2021-03-15 | 2021-06-18 | 上海应用技术大学 | Dangerous chemical storage environment risk early warning method |
| CN117555279A (en) * | 2024-01-11 | 2024-02-13 | 杭州企茏电子科技有限公司 | Remote instant monitoring system and method for dangerous chemical storage warehouse |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080236275A1 (en) * | 2002-06-11 | 2008-10-02 | Intelligent Technologies International, Inc. | Remote Monitoring of Fluid Storage Tanks |
| CN109993344A (en) * | 2019-01-09 | 2019-07-09 | 淮阴工学院 | Harmful influence tank car operating status prediction technique and system based on multisource data fusion |
| CN209280033U (en) * | 2018-12-28 | 2019-08-20 | 广东石油化工学院 | A kind of dangerous goods store danger monitoring system based on the base station LORA |
| CN111220202A (en) * | 2018-11-23 | 2020-06-02 | 中国科学院大连化学物理研究所 | Dangerous chemical solution safety early warning remote monitoring system and method based on Internet of things |
-
2020
- 2020-11-02 CN CN202011206134.0A patent/CN112468988A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080236275A1 (en) * | 2002-06-11 | 2008-10-02 | Intelligent Technologies International, Inc. | Remote Monitoring of Fluid Storage Tanks |
| CN111220202A (en) * | 2018-11-23 | 2020-06-02 | 中国科学院大连化学物理研究所 | Dangerous chemical solution safety early warning remote monitoring system and method based on Internet of things |
| CN209280033U (en) * | 2018-12-28 | 2019-08-20 | 广东石油化工学院 | A kind of dangerous goods store danger monitoring system based on the base station LORA |
| CN109993344A (en) * | 2019-01-09 | 2019-07-09 | 淮阴工学院 | Harmful influence tank car operating status prediction technique and system based on multisource data fusion |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990706A (en) * | 2021-03-15 | 2021-06-18 | 上海应用技术大学 | Dangerous chemical storage environment risk early warning method |
| CN117555279A (en) * | 2024-01-11 | 2024-02-13 | 杭州企茏电子科技有限公司 | Remote instant monitoring system and method for dangerous chemical storage warehouse |
| CN117555279B (en) * | 2024-01-11 | 2024-04-05 | 杭州企茏电子科技有限公司 | Remote instant monitoring system and method for dangerous chemical storage warehouse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103456136B (en) | Internet of Things framework type system for monitoring and early warning of major accident potential safety hazards of water conservancy and hydropower project | |
| CN109139115B (en) | Underground data acquisition terminal, processing system and processing method | |
| CN112468988A (en) | Hazardous chemical substance monitoring method and device | |
| CN110159929B (en) | Intelligent control big data processing method for underground drainage pipe network | |
| KR20210051376A (en) | Bigdata based building fire prevention response system and method | |
| CN104777762A (en) | Vehicle-mounted system monitoring method and terminal thereof | |
| KR20160085033A (en) | Learning type emergency detection system with multi-sensor and that method | |
| CN209055532U (en) | A kind of multinode closed area monitoring of hazardous gas device | |
| CN112379621A (en) | Power station house environment monitoring system and method | |
| CN111668927A (en) | Substation intelligent inspection system based on ubiquitous power Internet of things and control method thereof | |
| CN107204105A (en) | Dangerous monitoring and early warning method and device | |
| CN115903973A (en) | Fire detection and emergency linkage control system based on Internet of things | |
| Li et al. | Developing a fire monitoring and control system based on IoT | |
| Ehsan et al. | Internet of things-based fire alarm navigation system: A fire-rescue department perspective | |
| KR102296568B1 (en) | Swithchboard Management And Control System based on Machine Learning | |
| Krishnamoorthy et al. | A design and development of the smart forest alert monitoring system using IoT | |
| CN114527717A (en) | Chemical safety production early warning system and safety early warning method thereof | |
| CN116754022B (en) | On-line detection emergency early warning method and system for cable tunnel | |
| CN204376958U (en) | Based on Big Dipper location and the railway Landslide Forecast System of Minimal routing jumping figure agreement | |
| CN117133107A (en) | Fire security monitoring method and system | |
| CN208077386U (en) | Equipment working state monitors system | |
| KR101918591B1 (en) | Gas-related Accident Prediction System for the Area of Dense Energy Consumption | |
| CN110033594A (en) | Substation safety monitors system and method | |
| CN108263310A (en) | A kind of power battery dynamic security information sharing and communication alarm device | |
| RU2736624C1 (en) | Method and system for prediction of consequences of accidents involving hazardous substances on hazardous production facilities in real time |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210309 |