A method for detecting seal failure of an explosion-proof box of an offshore platform

Abstract

The application discloses a kind of offshore platform explosion-proof box sealing fault detection method, this method is through temperature and humidity sensor and pressure sensor to the temperature, humidity and pressure data inside the box body after explosion-proof box sealing are carried out real-time acquisition, and by constructing based on temperature, humidity and pressure explosion-proof box sealing fault monitoring early warning model, determine the safety and sealing performance of explosion-proof box.Explosion-proof box is sealed after through air hole to carry out low-pressure nitrogen pressure regulating, temperature and humidity sensor and pressure sensor are configured in the box, collect temperature, humidity and pressure data in the box, construct based on temperature, humidity and pressure explosion-proof box sealing fault model, real-time monitoring explosion-proof box sealing performance, when at least one data in temperature, humidity and pressure data is above specified specific time length exceeds the corresponding data threshold set in advance, judge that explosion-proof box inside occurs sealing failure.The application establishes data acquisition and prediction method, ensures the real-time monitoring and fault prediction of explosion-proof box sealing performance, provides guarantee for the safe operation of offshore equipment.

Description

Technical Field

[0001] This invention relates to a method for detecting sealing failures in explosion-proof boxes on offshore platforms, applicable to the monitoring of the safety and sealing performance of intelligent explosion-proof boxes in marine environments. Background Technology

[0002] With the rapid development of offshore oil and gas extraction and other marine engineering, the safety and stability of offshore equipment have become critical issues. Explosion-proof enclosures, as key components protecting electrical equipment, directly affect their explosion-proof effectiveness through their sealing performance. Poor sealing can allow harmful external gases to enter, increasing the risk of explosion. Due to the complexity of the marine environment, characterized by high humidity, pressure fluctuations, and temperature variations, traditional explosion-proof enclosures struggle to achieve real-time monitoring of safety and sealing performance. Once a sealing failure or abnormal internal temperature occurs within the explosion-proof enclosure, it can lead to equipment damage or safety hazards. With the development of intelligent technologies, developing an intelligent explosion-proof enclosure detection method capable of real-time monitoring of temperature, humidity, and pressure, and using model analysis to determine equipment status, is of significant practical importance. Summary of the Invention

[0003] The purpose of this invention is to provide a method for detecting sealing failures in explosion-proof boxes for offshore platforms. This method can achieve real-time monitoring of the internal environment of the explosion-proof box, and promptly detect and warn of potential faults and sealing performance failures.

[0004] This invention proposes a novel method for detecting sealing failures, applicable to explosion-proof containers on offshore platforms. It aims to improve the safety and reliability of explosion-proof containers in marine environments. The method includes the following steps: Low-pressure nitrogen is introduced into the explosion-proof container through a vent, and the internal pressure is adjusted to 0.1 MPa to ensure a stable internal environment. Multiple sensors within the explosion-proof container transmit collected data to a data processing system via a wireless network or wired connection, ensuring a data acquisition frequency of once per second. Based on regression analysis of real-time and historical sensor data, a sealing failure monitoring and early warning model for the explosion-proof container, based on temperature, humidity, and pressure, is constructed. When at least one of the temperature, humidity, and pressure data exceeds a pre-set threshold for a specified time period, a sealing failure is determined to have occurred inside the explosion-proof container. When a failure or sealing performance failure is detected, a fault indicator light illuminates and an alarm sounds, alerting personnel to perform repairs. Simultaneously, detection data and fault information are recorded in real time.

[0005] Among them, the explosion-proof enclosure sealing failure monitoring and early warning model based on temperature, humidity and pressure judgment includes:

[0006] S301. Due to the complex environment of offshore platforms, in order to improve the accuracy of temperature judgment inside the explosion-proof enclosure, considering environmental influences and historical data, the formula for calculating the enclosure temperature after real-time correction by the sensor is as follows:

[0007] T a (t)=T m (t)-β·(T env (t)-T r )

[0008] In the formula, t is the current time, T a (t) represents the chamber temperature after environmental correction, T m (t) represents the real-time temperature inside the chamber, T env (t) represents the external ambient temperature, T r The reference temperature is the temperature under normal operating conditions, and β is the influence coefficient of ambient temperature on the internal temperature of the chamber. a (t)>T S If the temperature is abnormal inside the box, the data processing system will issue an alarm signal, where T... S It is the set maximum threshold temperature.

[0009] S302. To improve the accuracy of the model, multivariate linear regression analysis is performed on the temperature data to establish a historical temperature change trend model, capture the dynamic change characteristics of temperature, and improve the reliability of prediction. The specific formula is as follows:

[0010] T pred (t+1)=α1T m (t)+α2T m (t-1)+α3T env (t)+∈

[0011] Where t is the current time, T pred (t+1) represents the predicted temperature at the next moment, α1, α2, and α3 are regression coefficients derived from historical data fitting, and ∈ represents the error term.

[0012] The invented sealing model based on humidity and pressure data includes:

[0013]

[0014] Where t is the current time, S(t) is the sealing performance index, H(t) and P(t) are the real-time values ​​of humidity and pressure, respectively. r This is the reference humidity, P r The reference pressure value is γ1, γ2, and γ3, which are weighting coefficients, and δ1, δ2, and δ3 are nonlinear adjustment coefficients. When S(t) > S max If the sealing performance is determined to be compromised, the data processing system will issue an alarm signal.

[0015] Data and early warning information can be displayed to staff in real time through the data processing system's visual interface, showing changes in temperature, humidity, and pressure, as well as alarm status, to facilitate rapid decision-making.

[0016] The beneficial effects of this invention are as follows:

[0017] 1. The present invention proposes a method for detecting sealing failures in explosion-proof boxes for offshore platforms. Through real-time data acquisition from multiple sensors, it can monitor the temperature, humidity, and pressure conditions inside the explosion-proof box at any time, ensuring that the equipment operates within a safe range.

[0018] 2. The present invention proposes a method for detecting sealing failures in explosion-proof boxes for offshore platforms. By utilizing temperature failure models and sealing performance models, it can issue early warnings before failures occur, thereby reducing losses caused by equipment failures and improving equipment safety.

[0019] 3. The invention proposes a method for detecting sealing failures in explosion-proof boxes for offshore platforms. By analyzing the relationship between temperature, humidity, and pressure, it achieves a comprehensive evaluation of sealing performance, providing strong protection for the safe operation of equipment, extending the service life of explosion-proof boxes in harsh marine environments, reducing equipment failure rates, and providing reliable technical means for ensuring the safety of offshore operations.

[0020] 4. The present invention proposes a method for detecting sealing failures in explosion-proof boxes for offshore platforms. The system has a fault recording function, which can automatically record the time, type and duration of the fault, and display the monitoring results to the staff in real time through a visual interface, which facilitates rapid decision-making and maintenance. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the method for testing the safety and sealing performance of explosion-proof boxes for offshore platforms according to an embodiment of the present invention.

[0022] Figure 2 This is a schematic diagram of the temperature fault model structure constructed according to the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0024] This invention proposes a method for detecting sealing failures in explosion-proof boxes on offshore platforms. Figure 1 This is a flowchart illustrating the safety and sealing performance testing method for explosion-proof containers on offshore platforms. The process includes the following six steps:

[0025] S100: Low-pressure nitrogen gas is introduced into the explosion-proof box through the vent, and the pressure inside the box is adjusted to 0.1 MPa;

[0026] S200, the multiple sensors inside the explosion-proof enclosure transmit the collected data to the data processing system via a wireless network or wired connection, and the temperature sensor collects the internal temperature T of the explosion-proof enclosure. m The humidity sensor collects the internal humidity H m The pressure sensor collects the internal air pressure P. m The data collection frequency for each data point is 1 time per second;

[0027] S300: Based on the regression analysis of real-time and historical data from the multiple sensors, a monitoring and early warning model for sealing failure of the explosion-proof box based on temperature, humidity and pressure is constructed. When at least one of the temperature, humidity and pressure data exceeds the corresponding preset data threshold for more than a specified period of time, it is determined that a sealing failure has occurred inside the explosion-proof box.

[0028] S400, when a malfunction occurs inside the explosion-proof box or the sealing performance fails, the malfunction light of the explosion-proof box will light up and an alarm will be sounded to remind the staff to carry out maintenance;

[0029] The S500 records real-time collected data and faults or failures in the data processing system and displays them on the web page in real time.

[0030] In the S300 process, the explosion-proof enclosure sealing failure monitoring and early warning model, based on temperature, humidity, and pressure assessments, is implemented as follows: Figure 2 As shown:

[0031] S301. Due to the complex environment of offshore platforms, explosion-proof enclosures are often exposed. Changes in the external ambient temperature directly affect the temperature measurement inside the enclosure. Without correction, the real-time temperature may not accurately reflect the equipment's operating status. In explosion-proof environments, temperature monitoring is crucial; therefore, temperature correction helps ensure the equipment operates within safe limits and prevents accidents. To improve the accuracy of temperature judgment inside the explosion-proof enclosure, considering environmental influences and historical data, the formula for calculating the real-time corrected internal temperature of the enclosure is as follows:

[0032] T a (t)=T m (t)-β·(T env (t)-T r )

[0033] t is the current time, T a (t) represents the chamber temperature after environmental correction, T m (t) represents the real-time temperature inside the chamber, T env (t) represents the external ambient temperature, T r The reference temperature is the temperature under normal operating conditions, and β is the influence coefficient of ambient temperature on the internal temperature of the chamber. a (t)>TS If the temperature is abnormal inside the box, the data processing system will issue an alarm signal, where T... S It is the set maximum threshold temperature.

[0034] After correction, T a (t) It can more realistically reflect the actual temperature changes inside the explosion-proof box in the complex environment of the offshore platform, eliminate the interference of external environmental fluctuations on temperature monitoring, provide a more reliable data foundation, facilitate subsequent analysis and decision-making, and optimize the operation process;

[0035] S302. To improve the accuracy of the model, multivariate linear regression analysis was performed on the temperature data to establish a historical temperature change trend model. The specific formula is as follows:

[0036] T pred (t+1)=α1T m (t)+α2T m (t-1)+α3T env (t)+∈

[0037] t is the current time, T pred (t+1) represents the predicted temperature at the next moment, α1, α2, and α3 are regression coefficients derived from historical data fitting, and ∈ represents the error term.

[0038] By using multivariate linear regression, historical temperature trend models can predict temperature changes at the next moment using historical temperature data from the current moment and previous moments. This comprehensive consideration of time-series temperature trends helps the system identify abnormal temperature trends in advance, avoiding fluctuation errors caused by data from a single moment. Early prediction of temperature data provides the system with warning time, enabling maintenance personnel to take timely intervention measures before sealing failures or temperature anomalies occur, reducing the impact of failures on equipment and personnel.

[0039] To improve the accuracy of sealing performance assessment, when constructing a monitoring and early warning model for explosion-proof enclosure sealing failures based on temperature, humidity, and pressure, not only are independent changes in humidity and pressure considered, but the coupling relationship between them is also analyzed, using the following nonlinear correlation model:

[0040]

[0041] Where t is the current time, S(t) is the sealing performance index, H(t) and P(t) are the real-time values ​​of humidity and pressure, respectively. r This is the reference humidity, P r The reference pressure value is γ1, γ2, and γ3, which are weighting coefficients, and δ1, δ2, and δ3 are nonlinear adjustment coefficients. When S(t) > S max If the sealing performance is determined to be compromised, the data processing system will issue an alarm signal.

[0042] Relying solely on data from temperature, humidity, or pressure may not be sufficient to accurately diagnose sealing failures. By combining parameters such as humidity and pressure for comprehensive analysis, and through different weighting coefficients and nonlinear adjustment coefficients, the sealing model can be adjusted according to the importance of each parameter, thereby improving the accuracy and sensitivity of sealing failure monitoring.

[0043] Data and early warning information can be displayed to staff in real time through the data processing system's visual interface, showing changes in temperature, humidity, and pressure, as well as alarm status, to facilitate rapid decision-making.

Claims

1. A method for detecting sealing failures in explosion-proof boxes for offshore platforms, characterized in that, The explosion-proof enclosure is equipped with multiple sensors, including a temperature sensor, a humidity sensor, and a pressure sensor. These sensors are used to monitor real-time changes in temperature, humidity, and pressure inside the explosion-proof enclosure. The method includes the following steps: S100: Low-pressure nitrogen gas is introduced into the explosion-proof box through the vent, and the pressure inside the box is adjusted to 0.1 MPa; S200, the multiple sensors inside the explosion-proof enclosure transmit the collected data to the data processing system via a wireless network or wired connection, and the temperature sensor collects the internal temperature T of the explosion-proof enclosure. m The humidity sensor collects the internal humidity H m The pressure sensor collects the internal air pressure P. m The data collection frequency for each data point is 1 time per second; S300: Based on the regression analysis of real-time and historical data from the multiple sensors, a monitoring and early warning model for sealing failure of the explosion-proof box based on temperature, humidity and pressure is constructed. When at least one of the temperature, humidity and pressure data exceeds the corresponding preset data threshold for more than a specified period of time, it is determined that a sealing failure has occurred inside the explosion-proof box. S400, when a malfunction occurs inside the explosion-proof box or the sealing performance fails, the malfunction light of the explosion-proof box will light up and an alarm will be sounded to remind the staff to carry out maintenance; The S500 records real-time collected data and faults or failures in the data processing system and displays them on the web page in real time. Among them, regression analysis based on real-time and historical data from sensors is used to construct a monitoring and early warning model for explosion-proof enclosure sealing failures based on temperature, humidity, and pressure. Specifically, this includes... S301, Calculate the real-time corrected value of the sensor's internal temperature, using the following formula: in, For the current time, a ( The temperature inside the chamber is the environmentally corrected temperature. m ( (This refers to the real-time temperature inside the chamber.) env ( ( ) represents the external ambient temperature. r This is the reference temperature under normal operating conditions. The coefficient representing the influence of ambient temperature on the internal temperature of the chamber is given when... a ( )> S If an abnormal temperature is detected inside the explosion-proof enclosure, the data processing system will issue an alarm signal. S It is the set maximum threshold temperature; S302, perform multivariate linear regression analysis on temperature data to establish a historical temperature change trend model. The specific formula is as follows: in, For the current time, pred (t+1) represents the predicted temperature at the next moment, and α1, α2, and α3 are regression coefficients obtained by fitting historical data. This is the error term.

2. The method according to claim 1, characterized in that, The explosion-proof enclosure sealing failure monitoring and early warning model based on temperature, humidity, and pressure adopts the following nonlinear correlation model: in, For the current time, S( H( ) is a sealing performance indicator. ) and P( ) represent the real-time values ​​of humidity and pressure, respectively. H r This is the reference humidity, P r The reference pressure value is γ1, γ2, and γ3, which are weighting coefficients, and δ1, δ2, and δ3 are nonlinear adjustment coefficients. When S(t) > S max If the sealing performance is determined to be compromised, the data processing system will issue an alarm signal.

3. The method according to claim 1, characterized in that, The data processing system displays real-time temperature, humidity, and pressure changes, as well as alarm status, to staff through a visual interface, facilitating rapid decision-making.

4. The method according to claim 1, characterized in that, The temperature and humidity sensors and pressure sensors are made of corrosion-resistant materials.

5. The method according to claim 1, characterized in that, The data processing system has a fault recording function, which records the time of excessive temperature and the time of sealing performance failure in the database to provide reference data for subsequent maintenance.

Images