Automation in Petro-Chemical Industry

Research on protective layer strategy in high pressure string to low pressure reformation

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

The protective layer analysis (LOPA) method was used to identify the effectiveness of each protective layer in the dangerous scenario of high pressure string and low pressure in petrochemical plant. The LOPA method and its characteristics are introduced, and the failure data of various dangerous scenarios are compared according to the actual transformation cases. The total protection layer failure data is calculated according to the LOPA Settings in different series pressures. By exploring the better series pressure transformation scheme, the risk reduction in different scenarios can be identified effectively, and reasonable and effective improvement measures can be selected, which provides a theoretical basis for the high pressure series low pressure transformation of petrochemical equipment

Optimization of Anti Jamming Gas Circuit Design for In-service On-off Valves in Natural Gas Purification Plant

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

In a natural gas purification plant, an in-service reflux on-off valve located at the outlet of an HP Lean Sulfinol Pump has been found unable to be opened while it’s stuck in the closed position under conditions of large dP up & downstream of the valve. To address this issue, a new air supply system suitable for larger dP conditions to prevent valve sticking is proposed as an online upgrade by utilizing conventional general instrument accessories without stripping down the valve body and actuator, featuring lower costs and shorter time occupation. This will enable flexible opening and closing of the valve in larger dP scenarios, making it suitable for a wider range of applications.

Application And Analysis Of Safety Instrument System (SIS) In Finished Oil/Chemical Products Tank farm

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Abstract：The storage tank area of a company stores dangerous chemicals such as methanol, gasoline and diesel, which constitutes a major hazard source of grade one and grade two. There is no independent safety instrumented system ( SIS ) in the tank farm, nor is there an emergency cut-off system for storage tanks. After the hazard and operability analysis ( HAZOP ) method and safety integrity rating ( SIL ) grading, measures such as reforming the pneumatic cut-off valve of the storage tank and increasing the on-site emergency stop button were taken, and the liquid level and valve switching signals were introduced into the SIS system to realize the high and low liquid level alarm interlock cutting function of the storage tank. It solves the problem of major safety hazards in the tank area and ensures the smooth operation of the tank area.

Dynamic risk assessment of storage tank in station based on bow-Bayesian network

SHI haotong Chang-Jing LIANGLIANG

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Recurrent Neural Network-based Performance Prediction Model for Compressor Units

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

The operation of compressor units generates a substantial amount of monitoring data, with the monitoring values of key parameters being the primary factors for determining the normal operation of the units. However, at various compressor stations, these data are only stored as backup files for post-incident investigation purposes and are not effectively utilized. In this paper, we propose a compressor unit performance prediction model based on recurrent neural networks. We first discretize the monitoring data values using data nodes to reduce data redundancy. Then, we calculate the correlation coefficients to measure the correlation between different parameters at different time points. By mining neighboring nodes, we obtain a set of temporal neighboring nodes for the key parameters and use it as the training set for the recurrent neural network to predict the values of the key parameters, thus determining the operating status of the units. Experimental validation on the SCADA dataset demonstrates that the proposed model performs well in predicting the values of the outlet temperature. The evaluation metrics, MAE and RMSE, for a typical abnormal event in the outlet temperature are 0.88 and 0.92, respectively. These results further indicate that the proposed model exhibits strong generalization ability and predictive accuracy.

Design of control scheme for inner floating roof tank gas recovery system

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Abstract:The waste gas generated by the oil and gas recovery unit of the inner floating roof tank of a petrochemical enterprise is treated by the technology of "exhaust gas reduction of the inner floating roof tank with air bags" developed by Sinopec Dalian Petrochemical Research Institute. The unit mainly includes the oil and gas recovery unit of the inner floating roof tank. The control plan for the emission reduction of exhaust gas from the built-in air bag of the inner floating roof tank was mainly introduced. The automatic control of the large breathing exhaust process, large breathing inhalation process, small breathing exhaust process, and small breathing inhalation process of the inner floating roof tank was carried out by setting up a program. From a safety perspective, the device was designed to ensure safety and stability during operation.

Study on soft sensing technology of gas pipeline compressor flow based on random forest

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Abstract: Compressor is the main energy consuming equipment of gas transmission pipeline, and the accuracy of its flow measurement results is directly related to the management level of the whole pipeline line. On the basis of field test experiments, a data-driven soft sensing model based on random forest is constructed, and the hyperparameters that affect the accuracy of the model are optimized by grid search and cross-validation. Finally, the optimal prediction model is constructed, and the prediction results are compared with those of SVM, NB, GS-SVM and other models. The results show that the correlation between fuel gas consumption and atmospheric pressure on compressor flow is small, and its variables should be reduced. When the number of decision tree n is 300 and the number of split features m is 5, the prediction effect is the best. The RMSE and MAPE of the model in this paper are both the smallest, which indicates that the model in this paper has a good regression effect for complex nonlinear data sets such as compressor flow, and has certain advanced and scientific nature.

Condition monitoring of instrument and control equipment has an important impact on the long-term development of petrochemical enterprises

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Based on the needs of petrochemical enterprises to build the "industrial Internet + hazardous safety production" technical system and the construction of equipment integrity system, the instrument control status monitoring platform has emerged as The Times require, improving the safety production risk perception ability and the response and disposal ability of instrument control equipment defects, excavating potential equipment hidden dangers, and transforming the maintenance mode of instrument control equipment into a predictive maintenance party after maintenance. This paper introduces the construction and application difficulties of the instrument control condition monitoring platform, and focuses on the overall structure and key functions of the platform. Through the operation results of the instrument control status monitoring platform of an integrated refinery and an oil refinery, it is shown that the platform has automatic analysis functions such as defect identification, fault diagnosis, equipment status KPI and advanced application based on model algorithm, which can directly guide enterprises to carry out operation maintenance, inspection and repair work, and improve production safety of enterprises.

Applicability Analysis of Electronic Remote Sensor System (ERS) Differential Pressure Transmitter

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Differential pressure level transmitters are widely used in common instruments for measuring liquid levels in petrochemical processes. There are various forms of differential pressure level transmitters, including intelligent differential pressure level transmitters, remote seal (RS) double flange differential pressure level transmitters, and electronic remote sensor type (ERS) double flange differential pressure level transmitters. This article mainly analyzes the application sites where ERS differential pressure level transmitter is suitable to replace RS differential pressure level transmitter. Through comparative experiments, two types of transmitters are simulated under the same working conditions and their measurement performance is compared. The data shows that ERS differential pressure level transmitter has advantages over RS differential pressure level transmitter in certain working conditions such as long distance, large differential pressure, small static pressure, and large temperature difference. Finally, based on the data analysis results, the applicability range and application suggestions of ERS differential pressure transmitter are proposed.

Solutions to optimize False Alarms

pi yu

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Abstract: If a mount of false alarms is produced, The normal process operation will be greatly disturbed. Frequent Spurious shutdown will be effected or even danger will occur. The bad economic loss will be involved in. In some cases, false alarms may be developed to potential safety hazard. Elimination of all kinds of false alarms is the basis to proceed the execution of advanced alarm management. The impact Factors to false alarms are completely analyzed. The corresponding solutions and implementation details will be provided including reasonable alarm setting design, Static and dynamic alarm suppression, signal filter and de-bounce function, instrument accuracy and range design. When all false alarms are actually eliminated, the management level of refinery plants will be greatly improved. The intrinsic safety conception shall be actually achieved.

屋顶分布式光伏电站油田计量间的应用

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Research on Continuous Monitoring Technology for CO2 Concentration of Shale Oil Associated Natural Gas

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

During shale oil well fracturing a large amount of CO2 is injected. These CO2 will be produced with the production of crude oil and natural gas. In order to accurately understand the CO2 production situation, the research group has conducted research on online continuous monitoring technology of associated gas CO2 concentration. A continuous monitoring device for CO2 concentration based on infrared gas analysis method has been developed and applied in shale oil wells. Real time and continuous monitoring of CO2 concentration in shale oil associated gas has been achieved. The data accuracy performance meets the requirements of data acquisition and production management, and the detection results are fast, accurate, and efficient, greatly reducing the labor intensity of manual labor.

Exploration and Application of Methods to Increase Torque in Single-Acting Pneumatic Actuators

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

In single-acting pneumatic shut-off valves, the valve is reset by relying on a spring when there is a loss of air. However, for pneumatic shut-off valves with a ball valve body, if the torque selection is too conservative, it is easy to encounter valve sticking, which fails to provide the necessary safety protection and poses significant risks. This article analyzes the internal structure of pneumatic shut-off valves and summarizes the causes of valve sticking. With the principle of reducing costs and increasing efficiency, without changing the original design, innovative methods to increase torque are explored to improve the safety and reliability of shut-off valves.

Evaluation of Uncertainty in Verification Results of

Fei GAO

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

At present, in the process of crude oil transportation, the scraper flowmeter is often used, which is one of the most commonly used measuring instruments for dynamic crude oil measurement, and its measuring performance and accuracy will directly affect the economic interests of both sides of the crude oil trade. This paper introduces the verification principle of the scraper flowmeter, determines the source of the measurement uncertainty according to the theoretical calculation formula of the standard volumetric tube online verification of the scraper flowmeter, calculates the component of the uncertainty, analyzes and evaluates the uncertainty, analyzes the factors affecting the calibration of the scraper flowmeter according to the measurement uncertainty results, and puts forward the corresponding reasonable solutions and suggestions.

Current Situation and Countermeasures of Industrial Control System's Network Security in Petrochemical Enterprises

Zhen LI

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Industrial control system is widely used in the industrial production of refining and chemical enterprises and plays an important role. The deep integration of automation and information technology and the rapid development of the Internet of Things make the industrial control system network face increasing threats. By analyzing the network security of industrial control system in refining and chemical enterprises, proposes the method of constructing an effective security management system, gives the scheme of network security risk control.The deep defense framework of industrial control system is put forward, and the main defense measures are given.

Design and application of intelligent cloud platform for instrument control equipment based on chemical industry

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

At present, with the rapid development of the industrial Internet, the digital and intelligent transformation of instrument control equipment in the chemical industry has become very important. Aiming at the problems of heavy operation and maintenance workload of instrument control equipment in chemical industry, data "information island", data alarm overflow, data visualization, data lack of integrated management and so on, the design and implementation method of intelligent cloud platform of instrument control equipment based on supOS industrial interconnection platform was proposed. The platform proposed the "1+X" design scheme, "1" is an industrial Internet platform, "X" is a number of business industrial APP applications, namely, the location management of instrument control equipment, alarm management of instrument control equipment, intelligent inspection of instrument control equipment, high-frequency fault statistical analysis, instrument control equipment health status visualization and other extendable business applications. The platform has achieved good results in chemical industry enterprises, helping enterprises to efficiently and intelligently manage instrument control equipment, reduce enterprise management costs, and improve production efficiency. Under the background of the development of industrial Internet, this research has certain reference significance in the chemical industry.

Research on defect identification method of pipeline weld based on fusion machine learning

2024, 60(1): 0-0.

Asbtract ( )

Related Articles | Metrics

Abstract: In order to improve the automatic identification of different defect types in pipeline welds, based on the excavated X-ray welds images, the pooled layer operation of the traditional convolutional neural network was modified by using the square difference pooling method by comparing the variance information of the pooled domain and the feature map, and then the CNN model hyperparameters were selected by using the whale algorithm. Finally, a fusion machine learning model is formed for the classification of weld defects, and compared with other models. The results show that the whale algorithm can optimize parameters such as the number and size of convolutional nuclei, the number and size of pooled nuclei, the type of convolutional kernel activation function, and the learning rate in a short time. In the classification results of fusion machine learning model, the classification accuracy of unfused and unwelded defects is the highest, reaching 93%~100% under different training rounds, and the average classification accuracy of 5 defect types is between 90.6%~95.8%. The proposed model is superior to other CNN models and SVM models in classification accuracy, training time and stability. The research results can provide practical reference for the identification of weld defects in other pressure vessels or pressure pipelines, and have strong universality and expansibility.

Table of Content