Pressure vessel safety intelligent supervision system based on Internet of Things

Abstract

The invention relates to the technical field of pressure vessel supervision, in particular to a pressure vessel safety intelligent supervision system based on the Internet of Things, which comprises a safety supervision platform, an information acquisition unit, a performance damage unit, a graphical evaluation unit, a safety evaluation analysis, management adjustment unit and a management response unit. According to the invention, analysis is carried out from the two angles of historical use and appearance image of the target pressure vessel to know the state risk condition of the target pressure vessel, and the state data of the target pressure vessel is analyzed through information feedback and information fusion, so that the target pressure vessel is managed in time, and the management efficiency is improved. According to the method, the operation fault risk and the explosion risk of the target pressure vessel are reduced, and early warning supervision adjustment demand analysis is performed from the early warning perspective, so that reasonable adjustment is performed by reasonably setting early warning parameters according to the use and damage conditions of the target pressure vessel, and the early warning timeliness and the early warning sensitivity of the target pressure vessel are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure vessel supervision, and in particular to a pressure vessel safety intelligent supervision system based on the Internet of Things. Background Art

[0002] Pressure vessels are common equipment in industry and are widely used in petrochemical, chemical, pharmaceutical, food and other industries. They store or transport substances by compressing gas or liquid and are under great pressure. Therefore, the safety of pressure vessels is very critical. Once an accident occurs, it may cause serious casualties and property losses. Therefore, the research on intelligent monitoring and control technology of pressure vessels is of great significance. However, in the prior art, it is impossible to safely supervise the operating status of the pressure vessel, thereby reducing the timeliness of the early warning and the rationality of the management of the pressure vessel, and it is impossible to analyze the use and damage of the pressure vessel, thereby reducing the operating safety of the pressure vessel. At the same time, reasonable early warning parameters are set according to the use and early warning of the pressure vessel, thereby reducing the timeliness and sensitivity of the early warning of the pressure vessel, resulting in an increase in the risk of explosion of the pressure vessel; In view of the above technical defects, a solution is now proposed. Summary of the invention

[0003] The purpose of the present invention is to provide a pressure vessel safety intelligent supervision system based on the Internet of Things to solve the above-mentioned technical defects. The present invention analyzes the target pressure vessel from two perspectives: the historical use and the appearance image to understand the state risk of the target pressure vessel, so as to manage and adjust the early warning of the target pressure vessel to improve the operation safety of the target pressure vessel. The state data of the target pressure vessel is analyzed by information feedback and information fusion to timely manage the target pressure vessel to reduce the operation failure risk and explosion risk of the target pressure vessel. From the perspective of early warning, the early warning supervision adjustment demand analysis is performed to make reasonable early warning parameter settings and make reasonable adjustments according to the use and damage of the target pressure vessel to improve the early warning timeliness and early warning sensitivity of the target pressure vessel, thereby helping to improve the operation safety and early warning reliability of the target pressure vessel.

[0004] The object of the present invention can be achieved by the following technical solutions: A pressure vessel safety intelligent supervision system based on the Internet of Things, including a safety supervision platform, an information collection unit, a performance damage unit, a graphic evaluation unit, a safety assessment analysis, a management adjustment unit and a management response unit; The information collection unit is used to collect the historical use data and image data of the pressure vessel, and send the historical use data and image data to the performance damage unit and the graphic evaluation unit respectively. After receiving the historical use data, the performance damage unit immediately performs a use performance safety supervision analysis on the historical use data, analyzes the obtained use damage evaluation coefficient S, and obtains the state impact level ZJ; After receiving the image data, the graphic evaluation unit immediately performs a graphic difference division analysis on the image data, compares and analyzes the obtained appearance difference index and inner wall difference index, and obtains a difference risk index CZ; The safety assessment analysis is used to collect the state data of the target pressure vessel, and at the same time, combine the state impact level ZJ and the difference risk index CZ of the target pressure vessel to perform a fusion state safety feedback analysis, compare and analyze the obtained safety risk assessment coefficient R, and obtain an alarm signal; The management and adjustment unit is used to collect the early warning information of the target pressure vessel, and perform early warning supervision and adjustment demand analysis on the early warning information, and compare and analyze the obtained early warning control evaluation coefficient H to obtain a control signal.

[0005] Preferably, the performance safety supervision and analysis process of the performance impairment unit is as follows: The working period of the pressure vessel is collected and set as a time threshold, the pressure vessel is set as a target pressure vessel, and the historical usage data of the target pressure vessel within the time threshold is obtained. The historical usage data includes an operation value and a potential risk value. The operation value and the potential risk value are labeled YZ and QF, respectively. The operation value YZ and the potential risk value QF are substituted into the formula to obtain a use damage assessment coefficient S, and the use damage assessment coefficient S is compared and analyzed with the preset use damage assessment coefficient range stored internally: If the damage assessment coefficient S is greater than the maximum value in the preset damage assessment coefficient range, it is determined to be a third-level status impact; if the damage assessment coefficient S belongs to the preset damage assessment coefficient range, it is determined to be a second-level status impact; if the damage assessment coefficient S is less than the minimum value in the preset damage assessment coefficient range, it is determined to be a first-level status impact, and the first-level status impact, the second-level status impact and the third-level status impact are set as status impact levels ZJ, ZJ=1, 2, 3.

[0006] Preferably, the operating value represents the time between the time when the target pressure vessel starts to be put into use and the current time; the potential risk value represents the product of the proportion of the number of delayed maintenance times in the total number of maintenance times within the operating value of the target pressure vessel and the total delayed maintenance time after data normalization.

[0007] Preferably, the diagram difference division analysis process of the diagram evaluation unit is as follows: The image data of the target pressure vessel within the time threshold is obtained, the image data including the appearance feature image and the inner wall feature image, the target pressure vessel is divided into g sub-region blocks, g is a natural number greater than zero, and the appearance feature image and the inner wall feature image of each sub-region are compared and analyzed with the standard appearance feature image and the standard inner wall feature image inside thereof, and the difference value between the appearance feature image and the standard appearance feature image and the difference value between the inner wall feature image and the standard inner wall feature image are respectively obtained, and they are set as the appearance difference index and the inner wall difference index respectively; The sub-region blocks corresponding to the appearance difference index within the sub-region block being greater than the preset appearance difference index threshold and the inner wall difference index being greater than the preset inner wall difference index threshold are obtained, and are set as defective regions. The ratio of the corresponding number of defective regions to the total number of sub-region blocks is set as the difference risk index CZ.

[0008] Preferably, the fusion state safety feedback analysis process of the safety assessment analysis is as follows: T1: Divide the time threshold into i sub-time periods, where i is a natural number greater than zero, obtain the state data of the target pressure vessel in each sub-time period, the state data including the pressure offset value and the mechanical risk value, compare and analyze the pressure offset value and the mechanical risk value with the preset pressure offset value threshold and the preset mechanical risk value threshold stored in the internal input, and set the ratio between the number of sub-time periods corresponding to the pressure offset value being greater than or equal to the preset pressure offset value threshold, or the mechanical risk value being greater than or equal to the preset mechanical risk value threshold, and the total number of sub-time periods as the state risk coefficient Z; T2: The pressure deviation value indicates the maximum value of the pressure change inside the target pressure vessel; the mechanical risk value indicates the total duration corresponding to any mechanical parameter of the target pressure vessel exceeding a preset threshold, and the mechanical parameters include vibration amplitude and mechanical abnormal sound.

[0009] Preferably, the state impact level ZJ, the difference risk index CZ and the state risk coefficient Z of the target pressure vessel are retrieved and substituted into the formula to obtain the safety risk assessment coefficient R, and the safety risk assessment coefficient R is compared and analyzed with the preset safety risk assessment coefficient threshold value stored in the internal input: If the ratio between the security risk assessment coefficient R and the preset security risk assessment coefficient threshold is less than 1, no signal is generated; if the ratio between the security risk assessment coefficient R and the preset security risk assessment coefficient threshold is greater than or equal to 1, an alarm signal is generated.

[0010] Preferably, the early warning supervision adjustment demand analysis process of the management adjustment unit is as follows: The warning information of the target pressure vessel within the time threshold is obtained. The warning information includes the warning efficiency coefficient and the fault assessment value. The warning efficiency coefficient represents the proportion of the delayed warning times in the total warning times of the target pressure vessel. The fault assessment value represents the product of the total number of failures of the target pressure vessel and the total number of parts replacements after data normalization. The warning efficiency coefficient and the fault assessment value are labeled as YJ and GP, respectively. The early warning control evaluation coefficient H is obtained according to the formula, where v1 and v2 are the preset weight factor coefficients of the early warning efficiency coefficient and the fault evaluation value respectively, and v3 is the preset error correction coefficient. v1, v2 and v3 are all greater than zero. The early warning control evaluation coefficient H is compared and analyzed with the preset early warning control evaluation coefficient threshold value stored in the internal input: If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is less than 1, no signal is generated; If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is greater than or equal to 1, a control signal is generated.

[0011] The beneficial effects of the present invention are as follows: (1) The present invention analyzes the target pressure vessel from two perspectives: historical use and appearance image, to understand the state risk of the target pressure vessel, so as to manage and adjust the target pressure vessel in an early warning manner, so as to improve the operational safety of the target pressure vessel. That is, the historical use data is analyzed for use performance safety supervision, so as to understand the aging risk of the pressure vessel from the two perspectives of time and maintenance, and the image data is analyzed for graphical difference division, so as to understand the difference in use change of the target pressure vessel from the two perspectives of internal and external, thereby facilitating the comprehensiveness of subsequent analysis data and the accuracy of analysis results. (2) The present invention analyzes the status data of the target pressure vessel by means of information feedback and information fusion, so as to timely manage the target pressure vessel and reduce the risk of operational failure and explosion of the target pressure vessel. From the perspective of early warning, the present invention conducts an early warning supervision adjustment demand analysis, so as to reasonably adjust the early warning parameters according to the use and damage of the target pressure vessel, so as to improve the early warning timeliness and early warning sensitivity of the target pressure vessel, thereby helping to improve the operational safety and early warning reliability of the target pressure vessel. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The present invention will be further described below in conjunction with the accompanying drawings; Figure 1 It is a flowchart of the system of the present invention; Figure 2 This is a local analysis diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] Embodiment 1: See also Figure 1 to Figure 2 As shown, the present invention is a pressure vessel safety intelligent supervision system based on the Internet of Things, including a safety supervision platform, an information collection unit, a performance damage unit, a graphic evaluation unit, a safety assessment analysis, a management adjustment unit and a management response unit, the safety supervision platform and the information collection unit are in a two-way communication connection, the safety supervision platform and the graphic evaluation unit are in a one-way communication connection, the graphic evaluation unit and the performance damage unit are in a one-way communication connection, the performance damage unit and the graphic evaluation unit are both in a one-way communication connection with the safety assessment analysis and management adjustment unit, and the safety assessment analysis and management adjustment unit are both in a one-way communication connection with the management response unit; In the embodiment of the present invention, the data (historical use data and image data) of the target pressure vessel are collected by the information collection unit, and the aging risk of the pressure vessel is understood from the two points of time and maintenance by the performance damage unit. At the same time, the difference in the use change of the target pressure vessel is understood from the two points of internal and external by means of images, and the level of classification is performed, which is helpful to provide the accuracy of the analysis result, and to carry out in-depth information fusion to understand the failure risk of the target pressure vessel, so as to timely manage the target pressure vessel, so as to improve the operation safety of the target pressure vessel, and to analyze the early warning information of the management adjustment unit, so as to make reasonable early warning supervision settings according to the use and damage of the target pressure vessel, so as to improve the early warning timeliness and supervision reliability of the target pressure vessel; When the safety supervision platform monitors the operation of any pressure vessel, a supervision instruction is generated and sent to the information collection unit. After receiving the supervision instruction, the information collection unit immediately collects the historical use data and image data of the pressure vessel, and sends the historical use data and image data to the performance damage unit and the graphic evaluation unit respectively through the safety supervision platform. After receiving the historical use data, the performance damage unit immediately performs a use performance safety supervision analysis on the historical use data, so as to understand the aging risk of the pressure vessel from the two points of time and maintenance. The specific use performance safety supervision analysis process is as follows: The working period of the pressure vessel is collected and set as the time threshold, the pressure vessel is set as the target pressure vessel, and the historical usage data of the target pressure vessel within the time threshold is obtained. The historical usage data includes the operation value and the potential risk value. The operation value and the potential risk value are marked as YZ and QF respectively. The operation value YZ and the potential risk value QF are substituted into the formula The damage assessment coefficient is obtained, where a1 and a2 are the preset proportional factor coefficients of the operating value and the potential risk value respectively. The proportional factor coefficient is used to correct the deviation of various parameters in the calculation process of the formula, so as to make the calculation result more accurate. Both a1 and a2 are greater than zero. S is the damage assessment coefficient. The damage assessment coefficient S is compared with the preset damage assessment coefficient range stored in the internal input: If the use damage assessment coefficient S is greater than the maximum value in the preset use damage assessment coefficient range, it is determined to be a level 3 state impact; If the use damage assessment coefficient S falls within the preset use damage assessment coefficient range, it is determined to be a secondary state impact; If the damage assessment coefficient S is less than the minimum value in the preset damage assessment coefficient range, it is determined to be a primary state impact, wherein the impact degrees corresponding to the primary state impact, the secondary state impact and the tertiary state impact are increased in sequence, and the primary state impact, the secondary state impact and the tertiary state impact are set as state impact levels ZJ, ZJ=1, 2, 3, that is, when the state impact level ZJ=1, it indicates a primary state impact, when the state impact level ZJ=2, it indicates a secondary state impact, and when the state impact level ZJ=3, it indicates a tertiary state impact; In the embodiment of the present invention, the operation value indicates the time between the time when the target pressure vessel starts to be put into use and the current time. It should be noted that the aging risk of the target pressure vessel is determined from the perspective of time. In the embodiment of the present invention, the potential risk value represents the product value obtained by multiplying the proportion of the number of delayed maintenance times in the total number of maintenance times within the operation value of the target pressure vessel by the total delayed maintenance duration after data normalization. It should be noted that the analysis is performed from the perspective of historical maintenance to understand the potential risk situation of the target pressure vessel; After receiving the image data, the graphic evaluation unit immediately performs a graphic difference division analysis on the image data, so as to understand the usage change differences of the target pressure vessel from both internal and external points, so as to provide data support for subsequent analysis. The specific graphic difference division analysis process is as follows: The image data of the target pressure vessel within the time threshold is obtained, the image data including the appearance feature image and the inner wall feature image, the target pressure vessel is divided into g sub-region blocks, g is a natural number greater than zero, and the appearance feature image and the inner wall feature image of each sub-region are compared and analyzed with the internal standard appearance feature image and the standard inner wall feature image, and the difference value between the appearance feature image and the standard appearance feature image and the difference value between the inner wall feature image and the standard inner wall feature image are respectively obtained, and they are set as the appearance difference index and the inner wall difference index respectively. It should be noted that the use risk of the target pressure vessel can be understood by analyzing from the perspective of the difference between the appearance and the inner wall; The sub-region block corresponding to the appearance difference index within the sub-region block is obtained to be greater than the preset appearance difference index threshold, and the inner wall difference index is greater than the preset inner wall difference index threshold, and is set as a defective area, and the ratio of the corresponding number of defective areas to the total number of sub-region blocks is set as the difference risk index CZ. It should be noted that the difference between the target pressure vessel image and the standard image is understood through image analysis, so as to provide data support for the subsequent safe use analysis of the target pressure vessel.

[0015] Implementation 2: Safety assessment analysis is used to collect the status data of the target pressure vessel, and at the same time, combine the status impact level ZJ and the difference risk index CZ of the target pressure vessel to perform a fusion status safety feedback analysis to understand the failure risk of the target pressure vessel, so as to manage the target pressure vessel in a timely manner, improve the operating safety of the target pressure vessel, and reduce the operating failure risk and explosion risk of the target pressure vessel. The specific fusion status safety feedback analysis process is as follows: The time threshold is divided into i sub-time periods, where i is a natural number greater than zero, and the state data of the target pressure vessel in each sub-time period is obtained, the state data including the pressure offset value and the mechanical risk value, and the pressure offset value and the mechanical risk value are compared and analyzed with the preset pressure offset value threshold and the preset mechanical risk value threshold that are internally entered and stored, and the ratio between the number of sub-time periods corresponding to the pressure offset value being greater than or equal to the preset pressure offset value threshold, or the mechanical risk value being greater than or equal to the preset mechanical risk value threshold, and the total number of sub-time periods is set as the state risk coefficient Z; In the embodiment of the present invention, the pressure offset value represents the maximum value of the pressure change inside the target pressure vessel. It should be noted that the failure risk of the target pressure vessel is understood by analyzing the pressure change of the target pressure vessel. In the embodiment of the present invention, the mechanical risk value indicates the total time duration corresponding to any mechanical parameter of the target pressure vessel exceeding a preset threshold value. The mechanical parameters include vibration amplitude, mechanical abnormal sound, etc. It should be noted that the analysis is performed from the perspective of mechanical performance in order to effectively analyze the state of the target pressure vessel. Retrieve the state impact level ZJ, difference risk index CZ and state risk coefficient Z of the target pressure vessel and substitute them into the formula The safety risk assessment coefficient is obtained, where a1, a2 and a3 are the preset weight factor coefficients of the state impact level ZJ, the difference risk index CZ and the state risk coefficient Z respectively, a1, a2 and a3 are all greater than zero, a4 is the preset fault tolerance factor coefficient, and the value is 2.641, R is the safety risk assessment coefficient, and the safety risk assessment coefficient R is compared and analyzed with the preset safety risk assessment coefficient threshold value stored in the internal input: If the ratio between the security risk assessment coefficient R and the preset security risk assessment coefficient threshold is less than 1, no signal is generated; If the ratio between the safety risk assessment coefficient R and the preset safety risk assessment coefficient threshold is greater than or equal to 1, an alarm signal is generated and sent to the management response unit. After receiving the alarm signal, the management response unit immediately performs the preset early warning operation corresponding to the alarm signal, so as to manage the target pressure vessel in time, so as to improve the operation safety of the target pressure vessel and reduce the operation failure risk and explosion risk of the target pressure vessel; The management adjustment unit is used to collect the early warning information of the target pressure vessel and analyze the early warning supervision adjustment needs of the early warning information, so as to make reasonable early warning supervision settings according to the use and damage of the target pressure vessel, so as to improve the early warning timeliness and supervision reliability of the target pressure vessel. The specific early warning supervision adjustment needs analysis process is as follows: The warning information of the target pressure vessel within the time threshold is obtained. The warning information includes the warning efficiency coefficient and the fault assessment value. The warning efficiency coefficient represents the proportion of the delayed warning times in the total warning times of the target pressure vessel. The fault assessment value represents the product of the total number of failures of the target pressure vessel and the total number of parts replacements after data normalization. The warning efficiency coefficient and the fault assessment value are labeled as YJ and GP, respectively. According to the formula The early warning control evaluation coefficient is obtained, where v1 and v2 are the preset weight factor coefficients of the early warning efficiency coefficient and the fault evaluation value respectively, v3 is the preset error correction coefficient, v1, v2 and v3 are all greater than zero, and H is the early warning control evaluation coefficient. The early warning control evaluation coefficient H is compared with the preset early warning control evaluation coefficient threshold value stored in the internal input: If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is less than 1, no signal is generated; If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is greater than or equal to 1, a control signal is generated and sent to the management response unit. After receiving the control signal, the management response unit immediately displays the preset early warning text corresponding to the control signal, so as to rationally adjust the early warning parameter setting of the target pressure vessel according to the information feedback, so as to improve the early warning timeliness and early warning sensitivity of the target pressure vessel, thereby helping to improve the operation safety and early warning reliability of the target pressure vessel; In summary, the present invention analyzes the target pressure vessel from two perspectives: historical use and appearance image, to understand the state risk of the target pressure vessel, so as to manage and adjust the early warning of the target pressure vessel, so as to improve the operational safety of the target pressure vessel, that is, to perform a performance safety supervision analysis on the historical use data, so as to understand the aging risk of the pressure vessel from the two points of time and maintenance, to perform a graphical difference division analysis on the image data, so as to understand the usage change differences of the target pressure vessel from the two points of internal and external, thereby facilitating the comprehensiveness of the subsequent analysis data and the accuracy of the analysis results, to analyze the state data of the target pressure vessel through information feedback and information fusion, so as to manage the target pressure vessel in time, so as to reduce the operational failure risk and explosion risk of the target pressure vessel, and to perform an early warning supervision adjustment demand analysis from the perspective of early warning, so as to make reasonable early warning parameter settings and make reasonable adjustments according to the use and damage of the target pressure vessel, so as to improve the early warning timeliness and early warning sensitivity of the target pressure vessel, thereby helping to improve the operational safety and early warning reliability of the target pressure vessel.

[0016] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0017] The above formulas are obtained by collecting a large amount of data for software simulation and selecting a formula that is close to the actual value. The coefficients in the formula are set by technical personnel in this field according to actual conditions. The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited to this. Any technical personnel familiar with the technical field within the technical scope disclosed by the present invention, according to the technical solution and the inventive concept of the present invention, make equivalent replacement or change, which should be covered within the protection scope of the present invention.

Claims

1. A pressure vessel safety intelligent supervision system based on the Internet of Things, characterized in that: It includes a safety supervision platform, an information collection unit, a performance impairment unit, a graphic evaluation unit, a safety assessment analysis unit, a management adjustment unit, and a management response unit; The information collection unit is used to collect the historical use data and image data of the pressure vessel, and send the historical use data and image data to the performance damage unit and the graphic evaluation unit respectively. After receiving the historical use data, the performance damage unit immediately performs a use performance safety supervision analysis on the historical use data, analyzes the obtained use damage evaluation coefficient S, and obtains the state impact level ZJ; After receiving the image data, the graphic evaluation unit immediately performs a graphic difference division analysis on the image data, compares and analyzes the obtained appearance difference index and inner wall difference index, and obtains a difference risk index CZ; The safety assessment analysis is used to collect the state data of the target pressure vessel, and at the same time, combine the state impact level ZJ and the difference risk index CZ of the target pressure vessel to perform a fusion state safety feedback analysis, compare and analyze the obtained safety risk assessment coefficient R, and obtain an alarm signal; The management and adjustment unit is used to collect the early warning information of the target pressure vessel, and perform early warning supervision and adjustment demand analysis on the early warning information, and compare and analyze the obtained early warning control evaluation coefficient H to obtain a control signal.

2. According to the Internet of Things-based pressure vessel safety intelligent supervision system according to claim 1, it is characterized in that: The performance safety supervision and analysis process of the performance impairment unit is as follows: The working period of the pressure vessel is collected and set as a time threshold, the pressure vessel is set as a target pressure vessel, and the historical usage data of the target pressure vessel within the time threshold is obtained. The historical usage data includes an operation value and a potential risk value. The operation value and the potential risk value are labeled YZ and QF, respectively. The operation value YZ and the potential risk value QF are substituted into the formula to obtain a use damage assessment coefficient S, and the use damage assessment coefficient S is compared and analyzed with the preset use damage assessment coefficient range stored internally: If the use damage assessment coefficient S is greater than the maximum value in the preset use damage assessment coefficient range, it is determined to be a third-level state impact; if the use damage assessment coefficient S is within the preset use damage assessment coefficient range, it is determined to be a second-level state impact; If the damage assessment coefficient S is less than the minimum value in the preset damage assessment coefficient range, it is determined to be a first-level state impact, and the first-level state impact, the second-level state impact and the third-level state impact are set as the state impact level ZJ, ZJ=1, 2, 3.

3. According to claim 2, a pressure vessel safety intelligent supervision system based on the Internet of Things is characterized in that: The operating value represents the duration between the time when the target pressure vessel starts to be put into use and the current time; the potential risk value represents the product of the proportion of the number of delayed maintenance times in the total number of maintenance times within the operating value of the target pressure vessel and the total delayed maintenance duration after data normalization.

4. According to the Internet of Things-based pressure vessel safety intelligent supervision system of claim 1, it is characterized in that: The diagram difference division analysis process of the diagram evaluation unit is as follows: The image data of the target pressure vessel within the time threshold is obtained, the image data including the appearance feature image and the inner wall feature image, the target pressure vessel is divided into g sub-region blocks, g is a natural number greater than zero, and the appearance feature image and the inner wall feature image of each sub-region are compared and analyzed with the standard appearance feature image and the standard inner wall feature image inside thereof, and the difference value between the appearance feature image and the standard appearance feature image and the difference value between the inner wall feature image and the standard inner wall feature image are respectively obtained, and they are set as the appearance difference index and the inner wall difference index respectively; The sub-region blocks corresponding to the appearance difference index within the sub-region block being greater than the preset appearance difference index threshold and the inner wall difference index being greater than the preset inner wall difference index threshold are obtained, and are set as defective regions. The ratio of the corresponding number of defective regions to the total number of sub-region blocks is set as the difference risk index CZ.

5. According to the Internet of Things-based pressure vessel safety intelligent supervision system of claim 1, it is characterized in that: The fusion state safety feedback analysis process of the safety assessment analysis is as follows: T1: Divide the time threshold into i sub-time periods, where i is a natural number greater than zero, obtain the state data of the target pressure vessel in each sub-time period, the state data including the pressure offset value and the mechanical risk value, compare and analyze the pressure offset value and the mechanical risk value with the preset pressure offset value threshold and the preset mechanical risk value threshold stored in the internal input, and set the ratio between the number of sub-time periods corresponding to the pressure offset value being greater than or equal to the preset pressure offset value threshold, or the mechanical risk value being greater than or equal to the preset mechanical risk value threshold, and the total number of sub-time periods as the state risk coefficient Z; T2: The pressure deviation value indicates the maximum value of the pressure change inside the target pressure vessel; the mechanical risk value indicates the total duration corresponding to any mechanical parameter of the target pressure vessel exceeding a preset threshold, and the mechanical parameters include vibration amplitude and mechanical abnormal sound.

6. The pressure vessel safety intelligent supervision system based on the Internet of Things according to claim 5 is characterized in that: The state impact level ZJ, differential risk index CZ and state risk coefficient Z of the target pressure vessel are retrieved and substituted into the formula to obtain the safety risk assessment coefficient R, and the safety risk assessment coefficient R is compared and analyzed with the preset safety risk assessment coefficient threshold value stored in the internal input: If the ratio between the security risk assessment coefficient R and the preset security risk assessment coefficient threshold is less than 1, no signal is generated; if the ratio between the security risk assessment coefficient R and the preset security risk assessment coefficient threshold is greater than or equal to 1, an alarm signal is generated.

7. The pressure vessel safety intelligent supervision system based on the Internet of Things according to claim 1 is characterized in that: The early warning supervision adjustment demand analysis process of the management adjustment unit is as follows: The warning information of the target pressure vessel within the time threshold is obtained. The warning information includes the warning efficiency coefficient and the fault assessment value. The warning efficiency coefficient represents the proportion of the delayed warning times in the total warning times of the target pressure vessel. The fault assessment value represents the product of the total number of failures of the target pressure vessel and the total number of parts replacements after data normalization. The warning efficiency coefficient and the fault assessment value are labeled as YJ and GP, respectively. The early warning control evaluation coefficient H is obtained according to the formula, where v1 and v2 are the preset weight factor coefficients of the early warning efficiency coefficient and the fault evaluation value respectively, and v3 is the preset error correction coefficient. v1, v2 and v3 are all greater than zero. The early warning control evaluation coefficient H is compared and analyzed with the preset early warning control evaluation coefficient threshold value stored in the internal input: If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is less than 1, no signal is generated; If the ratio between the early warning control evaluation coefficient H and the preset early warning control evaluation coefficient threshold is greater than or equal to 1, a control signal is generated.

Images