Safety management method and system for hot work of dangerous goods
Through combined temperature and pressure sensors with artificial intelligence analysis, the status of fire operation equipment is monitored in real time and warning prompts are generated, which solves the problems of low frequency and insufficient accuracy of traditional monitoring management and improves safety.
Patent Information
- Application Number
- CN202410604487.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-15
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-05-15
AI Technical Summary
The monitoring and management of traditional fire operation equipment relies on manual inspection, which has low monitoring frequency and low accuracy, and cannot be warned of potential problems in real time, resulting in the occurrence of safety accidents.
The temperature sensor and pressure sensor are used to collect data in real time, and through the timing correlation response and multi-scale feature analysis algorithm based on artificial intelligence, the device status is automatically judged and the acousto-optical warning prompt signal is generated.
It improves the continuity and real-time nature of equipment status monitoring, reduces the dependence of manual monitoring, reduces the incidence of safety accidents, and enhances operational safety.
Smart Images

Figure CN118469782B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent management, and more specifically, to a method and system for safe management of hot work operations involving dangerous goods. Background Art
[0002] Dangerous goods hot work refers to unconventional work that may produce open flames, sparks or hot surfaces during the loading, unloading, storage and transportation of flammable and explosive dangerous goods, such as electric welding, gas welding and cutting, blowtorches, electric drills, grinding wheels, etc. Due to their particularity, this type of work has a high safety risk, so it is necessary to strictly abide by the relevant safety management system and operating procedures to ensure the safety of the work.
[0003] Hot work equipment refers to all equipment and tools used in hot work. These equipment may produce flames, sparks or hot surfaces during the operation, so special safety management measures are required to ensure the safety of the operation. By monitoring and managing hot work equipment, abnormal conditions in the working environment can be discovered in time, so that preventive measures can be taken to avoid safety accidents such as fire and explosion.
[0004] However, traditional monitoring and management of hot work equipment usually relies on manual inspections and regular maintenance, which has problems such as low monitoring frequency and low monitoring accuracy, and cannot fully and real-time monitor the equipment status. In addition, traditional monitoring and management can often only be discovered when equipment fails or has problems, and cannot warn of potential problems in advance, resulting in slow response to fault handling and affecting equipment safety.
[0005] Therefore, an optimized safety management method for hot work operations involving dangerous goods is desired. Summary of the invention
[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a method and system for the safety management of hot work operations on dangerous goods, which uses a temperature sensor and a pressure sensor to collect the temperature value and pressure value of the hot work equipment in the hot work process in real time, and adopts a data processing and analysis algorithm based on artificial intelligence technology to perform a time-series correlation response and multi-scale feature analysis of the temperature value and the pressure value, so as to automatically judge whether there is an abnormality in the working state of the hot work equipment according to the real-time changes and coordinated responses of the working parameters of the hot work equipment in the hot work process, and generate an audible and visual early warning prompt signal in response to the state monitoring result that the working state of the hot work equipment is abnormal. In this way, the system can more accurately judge the working state of the equipment, ensure the continuity and real-time nature of monitoring, so as to timely discover potential dangerous situations, while reducing the dependence on manual monitoring, and correspondingly reducing safety accidents caused by human factors, thereby improving the safety of operations.
[0007] According to one aspect of the present application, a dangerous goods hot work safety management system is provided, which includes:
[0008] The work permit application and management module is used to allow the work applicant to apply for a hot work permit and confirm the validity of the hot work personnel qualification certificate;
[0009] The personnel positioning and monitoring module is used to ensure that the monitoring personnel arrive at the hot work site by linking the personnel positioning system;
[0010] Operation monitoring and recording module, used to record the entire process of hot work construction;
[0011] Intelligent perception and early warning module, used for real-time monitoring, intelligent perception and risk early warning of hot work equipment.
[0012] In the above-mentioned dangerous goods hot work safety management system, the intelligent perception and warning module includes: a hot work process parameter acquisition unit, which is used to collect the time series of temperature values and the time series of pressure values of the hot work equipment during the hot work process through a temperature sensor and a pressure sensor; a time dimension arrangement unit, which is used to arrange the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector according to the time dimension respectively; a responsiveness fusion unit, which is used to fuse the temperature time series input vector and the pressure time series input vector through a responsiveness gamma correction fusion module to obtain a temperature-pressure time series responsiveness input vector; a multi-scale time domain correlation unit, which is used to perform multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain correlation feature vector as a temperature-pressure responsiveness multi-scale time domain correlation feature; and a state monitoring result generation unit, which is used to obtain a state monitoring result based on the temperature-pressure responsiveness multi-scale time domain correlation feature, and determine whether to generate an audible and visual warning prompt signal.
[0013] In the above-mentioned dangerous goods hot work operation safety management system, the responsiveness fusion unit includes: a position-by-position response calculation subunit, used to calculate the position-by-position response between the temperature time series input vector and the pressure time series input vector to obtain a temperature-pressure position-by-position response characteristic vector; a first nonlinear response factor construction subunit, used to construct a first nonlinear response factor for each position in the temperature-pressure response characteristic vector; a second nonlinear response factor construction subunit, used to construct a second nonlinear response factor for each position in the temperature-pressure response characteristic vector; and a position-by-position feature calculation subunit, used to divide the first nonlinear response factor by the second nonlinear response factor to obtain a feature value for each position in the temperature-pressure time series responsiveness input vector.
[0014] In the above-mentioned dangerous goods hot work safety management system, the multi-scale time domain association unit is used to: pass the temperature-pressure time series responsiveness input vector through a multi-scale feature capture network comprising a first convolutional layer and a second convolutional layer to obtain the temperature-pressure responsiveness multi-scale time domain association feature vector.
[0015] In the above-mentioned dangerous goods hot work safety management system, the state monitoring result generating unit includes: a working state abnormality judging subunit, used for passing the temperature-pressure responsive multi-scale time-domain correlation feature vector through a classifier-based state monitor to obtain a state monitoring result, wherein the state monitoring result is used to indicate whether there is an abnormality in the working state of the hot work equipment; and, a warning prompt signal generating subunit, used for generating an audible and visual warning prompt signal in response to the state monitoring result indicating that there is an abnormality in the working state of the hot work equipment.
[0016] In the above-mentioned dangerous goods hot work operation safety management system, it also includes a training step: a training module for training the responsive gamma correction fusion module, the multi-scale feature capture network including the first convolution layer and the second convolution layer, and the classifier-based state monitor.
[0017] In the above-mentioned dangerous goods hot work safety management system, the training module includes: a training data acquisition unit, used to acquire training data, the training data including the time series of training temperature values and the time series of training pressure values collected by the temperature sensor and the pressure sensor during the hot work process of the hot work equipment, and the real value of whether the working state of the hot work equipment is abnormal; a training data arrangement unit, used to arrange the time series of the training temperature values and the time series of the training pressure values into training temperature time series input vectors and training pressure time series input vectors according to the time dimension respectively; a training time series responsiveness unit, used to pass the training temperature time series input vector and the training pressure time series input vector through the responsiveness gamma correction fusion module to obtain a training temperature-pressure time series responsiveness input vector; a training multi-scale feature capture unit, used to pass the training temperature-pressure time series responsiveness input vector through the multi-scale feature capture network including the first convolutional layer and the second convolutional layer to obtain a training first-scale temperature-pressure responsiveness time domain correlation feature vector and a training second-scale A temperature-pressure responsiveness time-domain correlation feature vector; a training multi-scale fusion unit, used to fuse the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector to obtain a training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; a feature correction unit, used to correct the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector to obtain a corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; a classification loss function value calculation unit, used to pass the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector through the classifier-based state monitor to obtain a classification loss function value; and a model training unit, used to train the responsiveness gamma correction fusion module, the multi-scale feature capture network including the first convolutional layer and the second convolutional layer, and the classifier-based state monitor based on the classification loss function value and through back propagation of gradient descent, wherein the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector is corrected at each model iteration.
[0018] In the above-mentioned dangerous goods hot work safety management system, the feature correction unit includes: a correction feature calculation subunit, used to calculate a correction feature vector based on the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector; and a correction subunit, used to correct the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector based on the correction feature vector to obtain the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector.
[0019] According to another aspect of the present application, a method for safety management of hot work operations involving dangerous goods is provided, comprising:
[0020] The time series of temperature values and pressure values of the hot work equipment during the hot work process are collected by a temperature sensor and a pressure sensor;
[0021] Arrange the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector respectively according to the time dimension;
[0022] The temperature time series input vector and the pressure time series input vector are fused through a responsive gamma correction module to obtain a temperature-pressure time series responsiveness input vector;
[0023] Performing multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain correlation feature vector as a temperature-pressure responsiveness multi-scale time domain correlation feature;
[0024] Based on the temperature-pressure responsiveness multi-scale time domain correlation characteristics, a state monitoring result is obtained, and it is determined whether to generate an acoustic and visual early warning prompt signal.
[0025] In the above-mentioned dangerous goods hot work operation safety management method, based on the temperature-pressure responsive multi-scale time-domain correlation characteristics, a state monitoring result is obtained, and it is determined whether to generate an acoustic and visual warning prompt signal, including: passing the temperature-pressure responsive multi-scale time-domain correlation feature vector through a classifier-based state monitor to obtain a state monitoring result, and the state monitoring result is used to indicate whether there is an abnormality in the working state of the hot work equipment; and, in response to the state monitoring result indicating that the working state of the hot work equipment is abnormal, generating an acoustic and visual warning prompt signal.
[0026] Compared with the prior art, the present application provides a method and system for the safety management of hot work operations on dangerous goods, which uses temperature sensors and pressure sensors to collect the temperature and pressure values of the hot work equipment in the hot work process in real time, and uses data processing and analysis algorithms based on artificial intelligence technology to perform time-series correlation response and multi-scale feature analysis of the temperature and pressure values, so as to automatically judge whether there is an abnormality in the working state of the hot work equipment according to the real-time changes and coordinated responses of the working parameters of the hot work equipment in the hot work process, and generate an audible and visual early warning prompt signal in response to the status monitoring result that the working state of the hot work equipment is abnormal. In this way, the system can more accurately judge the working state of the equipment, ensure the continuity and real-time nature of monitoring, so as to timely discover potential dangerous situations, while reducing the reliance on manual monitoring, and correspondingly reducing safety accidents caused by human factors, thereby improving the safety of operations. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0028] Figure 1 It is a block diagram of a dangerous goods hot work safety management system according to an embodiment of the present application.
[0029] Figure 2 It is a block diagram of the intelligent perception and warning module in the dangerous goods hot work operation safety management system according to the embodiment of the present application.
[0030] Figure 3 Schematic diagram of the architecture of the intelligent perception and warning module in the dangerous goods hot work operation safety management system according to an embodiment of the present application.
[0031] Figure 4 It is a block diagram of a responsive fusion unit in a dangerous goods hot work operation safety management system according to an embodiment of the present application.
[0032] Figure 5 It is a block diagram of a training module in a dangerous goods hot work safety management system according to an embodiment of the present application.
[0033] Figure 6 Flow chart of a method for safe management of hot work operations involving dangerous goods according to an embodiment of the present application. DETAILED DESCRIPTION
[0034] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0035] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0036] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.
[0037] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0038] Dangerous goods hot work refers to unconventional work that may produce open flames, sparks or hot surfaces during the loading, unloading, storage and transportation of flammable and explosive dangerous goods, such as electric welding, gas welding and cutting, blowtorches, electric drills, grinding wheels, etc. Due to their particularity, this type of work has a high safety risk, so it is necessary to strictly abide by the relevant safety management system and operating procedures to ensure the safety of the work.
[0039] Hot work equipment refers to all equipment and tools used in hot work. These equipment may produce flames, sparks or hot surfaces during the operation, so special safety management measures are required to ensure the safety of the operation. By monitoring and managing hot work equipment, abnormal conditions in the working environment can be discovered in time, so that preventive measures can be taken to avoid safety accidents such as fire and explosion.
[0040] However, traditional monitoring and management of hot work equipment usually relies on manual inspections and regular maintenance, which has problems such as low monitoring frequency and low monitoring accuracy, and cannot fully and real-time monitor the equipment status. In addition, traditional monitoring and management can often only be discovered when equipment fails or has problems, and cannot warn of potential problems in advance, resulting in slow response to fault handling and affecting equipment safety.
[0041] Based on this, in response to the above technical problems, the present application proposes a dangerous goods hot work safety management system, which includes: a work ticket application and management module, which is used to allow work applicants to apply for hot work tickets and confirm the validity of the hot work personnel's qualification certificate; a personnel positioning and monitoring module, which is used to ensure that the monitoring personnel arrive at the hot work site through the linkage personnel positioning system; an operation monitoring and recording module, which is used to record the entire process of hot work construction; and an intelligent perception and early warning module, which is used to perform real-time monitoring, intelligent perception and risk early warning of hot work equipment.
[0042] Accordingly, the technical concept of the present application is to collect the temperature and pressure values of the hot work equipment in the process of hot work in real time through temperature sensors and pressure sensors, and use data processing and analysis algorithms based on artificial intelligence technology to perform time-series correlation response and multi-scale feature analysis of the temperature and pressure values, so as to automatically judge whether there is any abnormality in the working state of the hot work equipment according to the real-time changes and coordinated responses of the working parameters of the hot work equipment in the process of hot work, and generate an audible and visual early warning prompt signal in response to the status monitoring result that the working state of the hot work equipment is abnormal. In this way, the system can more accurately judge the working state of the equipment, ensure the continuity and real-time nature of monitoring, so as to timely discover potential dangerous situations, while reducing the reliance on manual monitoring, and correspondingly reducing safety accidents caused by human factors, thereby improving the safety of operations.
[0043] Figure 1 FIG. 1 is a block diagram of a dangerous goods hot work safety management system according to an embodiment of the present application. Figure 1 As shown, according to the embodiment of the present application, the dangerous goods hot work safety management system 100 includes: a work ticket application and management module 110, which is used to allow the work applicant to apply for a hot work ticket and confirm the validity of the hot work personnel qualification certificate; a personnel positioning and monitoring module 120, which is used to ensure that the monitoring personnel arrive at the hot work site through the linkage personnel positioning system; an operation monitoring and recording module 130, which is used to record the entire process of the hot work construction; and an intelligent perception and early warning module 140, which is used to perform real-time monitoring, intelligent perception and risk early warning of hot work equipment.
[0044] Figure 2 It is a block diagram of the intelligent perception and warning module in the dangerous goods hot work operation safety management system according to the embodiment of the present application. Figure 3 FIG. 1 is a schematic diagram of the architecture of the intelligent perception and warning module in the dangerous goods hot work safety management system according to an embodiment of the present application. Figure 2 and Figure 3As shown, the intelligent perception and warning module 140 includes: a hot work process parameter acquisition unit 141, which is used to collect the time series of temperature values and the time series of pressure values of the hot work equipment during the hot work process through a temperature sensor and a pressure sensor; a time dimension arrangement unit 142, which is used to arrange the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector according to the time dimension respectively; a responsiveness fusion unit 143, which is used to fuse the temperature time series input vector and the pressure time series input vector through a responsiveness gamma correction fusion module to obtain a temperature-pressure time series responsiveness input vector; a multi-scale time domain association unit 144, which is used to perform multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain association feature vector as a temperature-pressure responsiveness multi-scale time domain association feature; and a state monitoring result generation unit 145, which is used to obtain a state monitoring result based on the temperature-pressure responsiveness multi-scale time domain association feature, and determine whether to generate an acoustic and visual warning prompt signal.
[0045] In an embodiment of the present application, the hot work process parameter acquisition unit 141 is used to collect the time series of temperature values and the time series of pressure values of the hot work equipment during the hot work process through temperature sensors and pressure sensors. It should be understood that, considering that in hot work, temperature and pressure are two key physical parameters, they can express and reflect the operating status and potential safety risks of the operating equipment. Specifically, the measured values of temperature and pressure can intuitively reflect whether the operating status of the equipment is normal. For example, if the temperature or pressure exceeds the safety range designed for the equipment, this may mean that the equipment is overloaded or has a fault. Based on this, in order to ensure the safety of equipment during hot work to improve operating efficiency and prevent accidents, in the technical solution of the present application, the time series of temperature values and the time series of pressure values of the hot work equipment during the hot work process are collected through temperature sensors and pressure sensors.
[0046] In the embodiment of the present application, the time dimension arrangement unit 142 is used to arrange the time series of the temperature value and the time series of the pressure value into a temperature time series input vector and a pressure time series input vector according to the time dimension. Accordingly, considering that in the process of hot work, the temperature value and the pressure value have certain correlation and sequence in the time series as they change over time, that is, the temperature value and the pressure value have certain characteristic information on the time scale, such as the change trend of temperature, the periodic change of pressure, etc. Based on this, in order to retain the correlation of the temperature value and the pressure value in time, it is helpful for the model to better understand and utilize the time dynamic characteristic information in the temperature value and the pressure value. In the technical solution of the present application, the time series of the temperature value and the time series of the pressure value are arranged into a temperature time series input vector and a pressure time series input vector according to the time dimension, respectively, so that the change pattern and structural trend of the temperature value and the pressure value in the time series can be captured and mined, so as to better understand the process and change law of the temperature value and the pressure value in the time series of the temperature value and the pressure value in the time series of the pressure value.
[0047] In the embodiment of the present application, the responsiveness fusion unit 143 is used to obtain a temperature-pressure time series responsiveness input vector by fusing the temperature time series input vector and the pressure time series input vector through a responsiveness gamma correction fusion module. Figure 4 is a block diagram of a responsive fusion unit in a dangerous goods hot work safety management system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 4As shown, the responsiveness fusion unit 143 includes: a position-by-position response calculation subunit 1431, which is used to calculate the position-by-position response between the temperature time series input vector and the pressure time series input vector to obtain the temperature-pressure position-by-position response characteristic vector; a first nonlinear response factor construction subunit 1432, which is used to construct the first nonlinear response factor of each position in the temperature-pressure response characteristic vector; a second nonlinear response factor construction subunit 1433, which is used to construct the second nonlinear response factor of each position in the temperature-pressure response characteristic vector; and a position-by-position characteristic calculation subunit 1434, which is used to divide the first nonlinear response factor by the second nonlinear response factor to obtain the characteristic value of each position in the temperature-pressure time series responsiveness input vector. It should be understood that, considering that in hot work, the temperature sensor and the pressure sensor may have a response curve mismatch, and there is a time-series mutual responsiveness correlation relationship between the temperature time series input vector and the pressure time series input vector, for example, under certain operating conditions of hot work, such as boiling point or condensation point, a slight change in temperature may cause a phase change of the material, thereby causing a significant change in pressure. Therefore, in order to eliminate the corresponding mismatch between the temperature time series input vector and the pressure time series input vector, and at the same time capture and mine the responsive correlation relationship between the temperature and the pressure in the time dimension, in the technical solution of the present application, the temperature time series input vector and the pressure time series input vector are fused through a responsive gamma correction module to obtain a temperature-pressure time series responsive input vector. It is worth mentioning that the responsive gamma correction fusion module is a technology for adjusting the sensor response curve, which can correct the nonlinear response of the sensor and improve the accuracy and reliability of the sensor data. Specifically, the responsive gamma correction fusion module can ensure that the temperature and pressure collected by the temperature sensor and the pressure sensor can be effectively responded to and combined, thereby improving the consistency and comparability of the temperature-pressure time series responsive input vector, and helping the model to better analyze and understand the time series correlation response changes of the temperature and pressure of the hot work equipment during the hot work process.
[0048] Preferably, in an embodiment of the present application, the responsiveness fusion unit is used to: use the responsiveness gamma correction fusion module to process the temperature time series input vector and the pressure time series input vector with the following responsiveness fusion formula to obtain the temperature-pressure time series responsiveness input vector; wherein the responsiveness fusion formula is:
[0049]
[0050] in, and are the temperature time series input vector and the pressure time series input vector. The eigenvalues at the positions, is the first one in the temperature-pressure time series responsiveness input vector The eigenvalues at the positions, , , , , and are the corresponding adjustment parameters.
[0051] In the embodiment of the present application, the multi-scale time domain association unit 144 is used to perform multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain association feature vector as a temperature-pressure responsiveness multi-scale time domain association feature. Specifically, in the embodiment of the present application, the multi-scale time domain association unit is used to: pass the temperature-pressure time series responsiveness input vector through a multi-scale feature capture network including a first convolution layer and a second convolution layer to obtain the temperature-pressure responsiveness multi-scale time domain association feature vector. Accordingly, considering that the temperature-pressure time series responsiveness input vector contains feature information of different time scales about the temperature-pressure time series response relationship, such as instantaneous changes, fluctuations or noises of temperature and pressure; long-term periodic changes of temperature and pressure, etc. In addition, the temperature and pressure data may have complex time series correlations in the time domain. Based on this, in the technical solution of the present application, the temperature-pressure time series responsiveness input vector is passed through a multi-scale feature capture network including a first convolution layer and a second convolution layer to obtain a temperature-pressure responsiveness multi-scale time domain association feature vector. It should be understood that the multi-scale feature capture network including the first convolutional layer and the second convolutional layer captures the time series feature information of different time domain scales of the temperature-pressure time series responsiveness input vector through the first convolutional layer and the second convolutional layer respectively, and can effectively capture the correlation feature information between temperature and pressure in the time domain, helping the model to better understand the time series feature information of different time domain scales in the temperature-pressure time series responsiveness input vector, so as to more comprehensively characterize the full time domain correlation characteristics of temperature and pressure, so as to obtain a temperature-pressure responsive multi-scale time domain correlation feature vector that integrates different time domain timing information.
[0052] In the embodiment of the present application, the state monitoring result generating unit 145 is used to obtain the state monitoring result based on the temperature-pressure responsive multi-scale time domain correlation feature, and determine whether to generate an acoustic and optical warning prompt signal. Specifically, in the embodiment of the present application, the state monitoring result generating unit includes: a working state abnormality judgment subunit, which is used to pass the temperature-pressure responsive multi-scale time domain correlation feature vector through a classifier-based state monitor to obtain a state monitoring result, and the state monitoring result is used to indicate whether the working state of the hot work equipment is abnormal; and a warning prompt signal generating subunit, which is used to generate an acoustic and optical warning prompt signal in response to the state monitoring result that the working state of the hot work equipment is abnormal. That is, the temperature-pressure responsive multi-scale time domain correlation feature obtained by extracting the scale feature using the temperature-pressure time series responsiveness input vector is classified and processed, so as to automatically judge whether the working state of the hot work equipment is abnormal according to the real-time change and coordinated response of the working parameters of the hot work equipment during the hot work process, and generate an acoustic and optical warning prompt signal in response to the state monitoring result that the working state of the hot work equipment is abnormal. In this way, the system can more accurately judge the working status of the equipment and ensure the continuity and real-time nature of monitoring so as to promptly detect potential dangerous situations. At the same time, it reduces dependence on manual monitoring, and correspondingly reduces safety accidents caused by human factors, thereby improving the safety of operations.
[0053] It is worth mentioning that those skilled in the art should be aware that before applying a deep neural network model for inference, the deep neural network model must be trained so that the deep neural network can implement specific functional capabilities.
[0054] Specifically, in the technical solution of the present application, the dangerous goods hot work operation safety management system also includes a training module for training the responsive gamma correction fusion module, the multi-scale feature capture network including the first convolutional layer and the second convolutional layer, and the classifier-based state monitor.
[0055] Figure 5 is a block diagram of a training module in a dangerous goods hot work safety management system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 5As shown, the training module 200 includes: a training data acquisition unit 210, which is used to acquire training data, and the training data includes a time series of training temperature values and a time series of training pressure values collected by the temperature sensor and the pressure sensor during the hot work operation, and a real value of whether the working state of the hot work operation equipment is abnormal; a training data arrangement unit 220, which is used to arrange the time series of the training temperature values and the time series of the training pressure values into a training temperature time series input vector and a training pressure time series input vector according to the time dimension respectively; a training time series responsiveness unit 230, which is used to pass the training temperature time series input vector and the training pressure time series input vector through the responsiveness gamma correction fusion module to obtain a training temperature-pressure time series responsiveness input vector; a training multi-scale feature capture unit 240, which is used to pass the training temperature-pressure time series responsiveness input vector through the multi-scale feature capture network including the first convolution layer and the second convolution layer to obtain a training first-scale temperature-pressure responsiveness time domain correlation feature vector and a training second-scale temperature-pressure responsiveness time domain correlation feature vector. a training multi-scale fusion unit 250 for fusing the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector to obtain a training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; a feature correction unit 260 for correcting the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector to obtain a corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; a classification loss function value calculation unit 270 for passing the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector through the classifier-based state monitor to obtain a classification loss function value; and a model training unit 280 for training the responsiveness gamma correction fusion module, the multi-scale feature capture network including the first convolutional layer and the second convolutional layer, and the classifier-based state monitor based on the classification loss function value and through back propagation of gradient descent, wherein the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector is corrected at each model iteration.
[0056] Specifically, the model training unit 280 is used to train the responsive gamma correction fusion module, the multi-scale feature capture network including the first convolution layer and the second convolution layer, and the classifier-based state monitor based on the classification loss function value and through the back propagation of gradient descent, wherein the training temperature-pressure responsive multi-scale time domain correlation feature vector is corrected at each model iteration. It should be understood that in the technical solution described above, when the training temperature-pressure time series responsiveness input vector passes through the multi-scale feature capture network including the first convolution layer and the second convolution layer, the obtained training first scale temperature-pressure responsiveness time domain correlation feature vector and the training second scale temperature-pressure responsiveness time domain correlation feature vector respectively represent the local time series implicit correlation features of the temperature-pressure responsiveness time series distribution based on different time domain scales. Thus, the training first scale temperature-pressure responsiveness time domain correlation feature vector and the training second scale temperature-pressure responsiveness time domain correlation feature vector have feature representation modes based on different time domain correlation scales.
[0057] Taking into account the parallel model branch structure of the first convolutional layer and the second convolutional layer of the multi-scale feature capture network, based on the feature correspondence between the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector, if the multi-dimensional feature representation can be fused on the basis of maintaining the class regression discrimination of the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector in different dimensions, it will be beneficial to improve the generalization of regression through the decoupled fusion of regression information of different dimensions, thereby improving the accuracy of the state monitoring results during model inference. Based on this, in the technical solution of the present application, the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector is corrected at each model iteration.
[0058] Specifically, in an embodiment of the present application, the feature correction unit includes: a correction feature calculation subunit, used to calculate a correction feature vector based on the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector; and a correction subunit, used to correct the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector based on the correction feature vector to obtain the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector.
[0059] More specifically, in the embodiment of the present application, the correction feature calculation subunit is used to: calculate the correction feature vector based on the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector using the following correction formula; wherein the correction formula is:
[0060]
[0061] in, is the time domain correlation feature vector of the first scale temperature-pressure responsiveness of the training and the training second scale temperature-pressure responsiveness time domain correlation feature vector The mean eigenvector of and are respectively the time domain correlation feature vectors of the classifier for the first scale temperature-pressure responsiveness of the training and the training second scale temperature-pressure responsiveness time domain correlation feature vector The weight matrix of represents an exponential function with the natural constant e as the base, represents matrix multiplication, It means adding by position. represents the corrected feature vector.
[0062] That is, in order to train the first scale temperature-pressure responsiveness time domain correlation feature vector and the training second scale temperature-pressure responsiveness time domain correlation feature vector The class-specific features on the independent pipelines learn their high-order fusion representation while maintaining their discriminability, and the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second scale temperature-pressure responsiveness time domain correlation feature vector The mean vector between is used as the intermediate vector, and the corresponding weight matrix of the classifier is and Perform query-support matching, thereby strengthening the distinguishing degree learning of sequence correspondence enrichment under the model branch structure through the class association of feature sequences. Then, use the correction feature vector By correcting the training temperature-pressure responsive multi-scale time-domain correlation feature vector, the generalization of the training temperature-pressure responsive multi-scale time-domain correlation feature vector during regression can be improved, thereby improving the accuracy of the state monitoring results during model inference. In this way, the system can more accurately judge the working status of the equipment, ensure the continuity and real-time nature of monitoring, so as to timely discover potential dangerous situations, while reducing the reliance on manual monitoring, and correspondingly reducing safety accidents caused by human factors, thereby improving the safety of operations.
[0063] In summary, the dangerous goods hot work safety management system 100 based on the embodiment of the present application is explained, which uses temperature sensors and pressure sensors to collect the temperature value and pressure value of the hot work equipment in the hot work process in real time, and uses data processing and analysis algorithms based on artificial intelligence technology to perform time-series correlation response and multi-scale feature analysis of the temperature value and the pressure value, so as to automatically judge whether there is an abnormality in the working state of the hot work equipment according to the real-time changes and coordinated responses of the working parameters of the hot work equipment in the hot work process, and generate an audible and visual early warning prompt signal in response to the status monitoring result that the working state of the hot work equipment is abnormal. In this way, the system can more accurately judge the working state of the equipment, ensure the continuity and real-time nature of monitoring, so as to timely discover potential dangerous situations, while reducing the reliance on manual monitoring, and correspondingly reducing safety accidents caused by human factors, thereby improving the safety of operations.
[0064] As described above, the dangerous goods hot work operation safety management system 100 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a dangerous goods hot work operation safety management algorithm. In a possible implementation, the dangerous goods hot work operation safety management system 100 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the dangerous goods hot work operation safety management system 100 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the dangerous goods hot work operation safety management system 100 can also be one of the many hardware modules of the wireless terminal.
[0065] Alternatively, in another example, the dangerous goods hot work operation safety management system 100 and the wireless terminal may also be separate devices, and the dangerous goods hot work operation safety management system 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.
[0066] Figure 6 Flow chart of the method for safe management of dangerous goods hot work operations according to an embodiment of the present application. Figure 6As shown, according to the embodiment of the present application, the method for safe management of hot work operations on dangerous goods includes: S110, collecting the time series of temperature values and the time series of pressure values of the hot work operation equipment during the hot work operation through a temperature sensor and a pressure sensor; S120, arranging the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector according to the time dimension respectively; S130, fusing the temperature time series input vector and the pressure time series input vector through a responsive gamma correction fusion module to obtain a temperature-pressure time series responsiveness input vector; S140, performing multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain correlation feature vector as a temperature-pressure responsiveness multi-scale time domain correlation feature; and, S150, obtaining a status monitoring result based on the temperature-pressure responsiveness multi-scale time domain correlation feature, and determining whether to generate an audible and visual warning prompt signal.
[0067] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned dangerous goods hot work safety management method have been referred to above. Figures 1 to 5 The description of the dangerous goods hot work safety management system has been introduced in detail, and therefore, its repeated description will be omitted.
[0068] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A dangerous goods hot work safety management system, characterized in that: include: The work permit application and management module is used to allow the work applicant to apply for a hot work permit and confirm the validity of the hot work personnel qualification certificate; The personnel positioning and monitoring module is used to ensure that the monitoring personnel arrive at the hot work site by linking the personnel positioning system; Operation monitoring and recording module, used to record the entire process of hot work construction; Intelligent perception and early warning module, used for real-time monitoring, intelligent perception and risk early warning of hot work equipment; The intelligent perception and early warning module includes: A hot work process parameter collection unit, used to collect the time series of temperature values and pressure values of the hot work equipment during the hot work process through a temperature sensor and a pressure sensor; A time dimension arrangement unit, used for arranging the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector respectively according to the time dimension; A responsiveness fusion unit, used for fusing the temperature time series input vector and the pressure time series input vector through a responsiveness gamma correction fusion module to obtain a temperature-pressure time series responsiveness input vector; A multi-scale time domain correlation unit, used for performing multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain correlation feature vector as a temperature-pressure responsiveness multi-scale time domain correlation feature; A state monitoring result generating unit, used to obtain a state monitoring result based on the temperature-pressure responsiveness multi-scale time domain correlation characteristics, and determine whether to generate an acoustic and visual early warning prompt signal; The responsive fusion unit comprises: A position-by-position response calculation subunit, used for calculating the position-by-position response between the temperature time series input vector and the pressure time series input vector to obtain a temperature-pressure position-by-position response characteristic vector; A first nonlinear response factor construction subunit, used to construct a first nonlinear response factor at each position in the temperature-pressure response characteristic vector; A second nonlinear response factor construction subunit, used to construct a second nonlinear response factor for each position in the temperature-pressure response characteristic vector; The position-by-position characteristic calculation subunit is used to divide the first nonlinear response factor by the second nonlinear response factor to obtain the characteristic value of each position in the temperature-pressure time series responsiveness input vector.
2. The dangerous goods hot work safety management system according to claim 1 is characterized in that: The multi-scale time domain association unit is used to: pass the temperature-pressure time series responsiveness input vector through a multi-scale feature capture network including a first convolutional layer and a second convolutional layer to obtain the temperature-pressure responsiveness multi-scale time domain association feature vector.
3. The dangerous goods hot work safety management system according to claim 2 is characterized in that: The state monitoring result generating unit comprises: A working state abnormality judgment subunit, used for passing the temperature-pressure responsive multi-scale time-domain correlation feature vector through a classifier-based state monitor to obtain a state monitoring result, wherein the state monitoring result is used to indicate whether the working state of the hot work equipment is abnormal; The early warning signal generating subunit is used to generate an audible and visual early warning signal in response to the status monitoring result indicating that the working status of the hot work equipment is abnormal.
4. The dangerous goods hot work safety management system according to claim 3 is characterized in that: It also includes a training step: a training module for training the responsive gamma correction fusion module, the multi-scale feature capture network including the first convolution layer and the second convolution layer, and the classifier-based state monitor.
5. The dangerous goods hot work safety management system according to claim 4 is characterized in that: The training module comprises: A training data acquisition unit, used to acquire training data, wherein the training data includes a time series of training temperature values and a time series of training pressure values of the hot work equipment collected during the hot work process by a temperature sensor and a pressure sensor, and a real value of whether there is an abnormality in the working state of the hot work equipment; A training data arrangement unit, used for arranging the time series of the training temperature values and the time series of the training pressure values into a training temperature time series input vector and a training pressure time series input vector respectively according to the time dimension; A training timing responsiveness unit, used for fusing the training temperature timing input vector and the training pressure timing input vector through the responsiveness gamma correction fusion module to obtain a training temperature-pressure timing responsiveness input vector; A training multi-scale feature capture unit, used for passing the training temperature-pressure time series responsiveness input vector through the multi-scale feature capture network comprising the first convolution layer and the second convolution layer to obtain a training first-scale temperature-pressure responsiveness time domain correlation feature vector and a training second-scale temperature-pressure responsiveness time domain correlation feature vector; A training multi-scale fusion unit, used for fusing the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector to obtain a training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; A feature correction unit, used for correcting the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector to obtain a corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector; A classification loss function value calculation unit, used for passing the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector through the classifier-based state monitor to obtain a classification loss function value; A model training unit is used to train the responsive gamma correction fusion module, the multi-scale feature capture network including the first convolutional layer and the second convolutional layer, and the classifier-based state monitor based on the classification loss function value and through back propagation of gradient descent, wherein the training temperature-pressure responsive multi-scale time-domain correlation feature vector is corrected at each model iteration.
6. The dangerous goods hot work safety management system according to claim 5 is characterized in that: The feature correction unit comprises: A correction feature calculation subunit, used to calculate a correction feature vector based on the training first-scale temperature-pressure responsiveness time-domain correlation feature vector and the training second-scale temperature-pressure responsiveness time-domain correlation feature vector; A correction subunit is used to correct the training temperature-pressure responsiveness multi-scale time-domain correlation feature vector based on the correction feature vector to obtain the corrected training temperature-pressure responsiveness multi-scale time-domain correlation feature vector.
7. A method for safety management of hot work operations involving dangerous goods, characterized in that: include: The time series of temperature values and pressure values of the hot work equipment during the hot work process are collected through the temperature sensor and the pressure sensor; Arrange the time series of the temperature values and the time series of the pressure values into a temperature time series input vector and a pressure time series input vector respectively according to the time dimension; The temperature time series input vector and the pressure time series input vector are fused through a responsive gamma correction module to obtain a temperature-pressure time series responsiveness input vector; Performing multi-scale feature capture on the temperature-pressure time series responsiveness input vector to obtain a temperature-pressure responsiveness multi-scale time domain correlation feature vector as a temperature-pressure responsiveness multi-scale time domain correlation feature; Based on the multi-scale time-domain correlation characteristics of the temperature-pressure responsiveness, a state monitoring result is obtained, and it is determined whether to generate an acoustic and optical early warning prompt signal; The step of fusing the temperature time series input vector and the pressure time series input vector through a responsive gamma correction module to obtain a temperature-pressure time series responsiveness input vector includes: Calculating the position-by-position response between the temperature time series input vector and the pressure time series input vector to obtain a temperature-pressure position-by-position response characteristic vector; Constructing a first nonlinear response factor for each position in the temperature-pressure response characteristic vector; Constructing a second nonlinear response factor for each position in the temperature-pressure response characteristic vector; The first nonlinear response factor is divided by the second nonlinear response factor to obtain a characteristic value of each position in the temperature-pressure time series responsiveness input vector.
8. The method for safety management of hot work operations involving dangerous goods according to claim 7 is characterized in that: Based on the multi-scale time domain correlation characteristics of the temperature-pressure responsiveness, a state monitoring result is obtained, and it is determined whether to generate an acoustic and visual early warning prompt signal, including: The temperature-pressure responsive multi-scale time-domain correlation feature vector is passed through a classifier-based state monitor to obtain a state monitoring result, wherein the state monitoring result is used to indicate whether the working state of the hot work equipment is abnormal; In response to the status monitoring result indicating that the working status of the hot work equipment is abnormal, an audible and visual warning prompt signal is generated.
Citation Information
Patent Citations
Dangerous operation early warning method and system, storage medium and processing terminal
CN112991669A
Fire operation process compliance detection method based on video monitoring
CN113343854A
Hybrid deep learning model and Stacking-based time series data prediction method and system
CN114548591A
Underground fire operation risk early warning method and system
CN116050852A
Intelligent power distribution room equipment operation maintenance management system and method thereof
CN116934304A
