Operating Conditions Research Articles

Modeling, optimization and operability analysis of Lurgi and Haldor Topsøe methanol synthesis reactors

Abstract In this research is focused on modeling, simulation and operability analysis of methanol synthesis reactors in the Lurgi and Haldor Topsøe methanol plants at steady state condition. In this regard, the tubular methanol synthesis reactors are mathematically modeled based on the laws of conservation of mass and energy considering interparticle resistance inside the commercial CuO–ZnO/Al2O3 catalyst. Then, the methanol productivity, carbon conversion, and thermal performance of both configurations are compared at the same weight hourly space velocity. The mole fraction of methanol in the outlet stream from Lurgi and Topsøe designed reactors are 9.08 and 9.71, respectively. In addition, the hotspot temperature in the Lurgi and Topsøe reactors are 278.8 and 267.7 °C based on the considered model, respectively. The carbon dioxide and carbon monoxide conversion in the Topsøe designed reactor are 8.95 and 4.89 % higher compared to the Lurgi reactor. Finally, a multi-objective optimization problem is programmed considering methanol production rate, carbon dioxide conversion and catalyst loading as objective functions and the optimal operating conditions and specifications of Topsøe reactor are obtained considering two different strategies. The simulation results show that applying the optimal conditions on the Topsøe designed reactor enhance the methanol productivity up to 16.04 %.

A Lightweight and Efficient Multimodal Feature Fusion Network for Bearing Fault Diagnosis in Industrial Applications.

To address the issues of single-structured feature input channels, insufficient feature learning capabilities in noisy environments, and large model parameter sizes in intelligent diagnostic models for mechanical equipment, a lightweight and efficient multimodal feature fusion convolutional neural network (LEMFN) method is proposed. Compared with existing models, LEMFN captures rich fault features at multiple scales by combining time-domain and frequency-domain signals, thereby enhancing the model's robustness to noise and improving data adaptability under varying operating conditions. Additionally, the convolutional block attention module (CBAM) and random overlapping sampling technology (ROST) are introduced, and through a feature fusion strategy, the accurate diagnosis of mechanical equipment faults is achieved. Experimental results demonstrate that the proposed method not only possesses high diagnostic accuracy and rapid convergence but also exhibits strong robustness in noisy environments. Finally, a graphical user interface (GUI)-based mechanical equipment fault detection system was developed to promote the practical application of intelligent fault diagnosis in mechanical equipment.

Do the sparser access points have less impact on arterial traffic? A microscopic simulation-based study

A dynamic microscopic traffic flow simulation within a ring arterial context was developed to investigate the effects of access point spacing on urban arterial flow under a right-in-right-out access management system. The microscopic traffic flow model, centered on car-following and lane-changing behaviors, was established based on vehicle interactions. The car-following aspect encompasses free driving, car-following behavior, and deceleration and braking states while lane-changing considerations include decision-making and acceptable gap assessment. Experimental scenarios account for arterial traffic density, access traffic demand intensity, average access point spacing, and variation coefficient of access point spacing. The traffic flow and speeds within the ring arterial were evaluated across 5040 operational conditions (equating to 5880 simulation hours). The traffic flow trends and speed variations with density across different access spacing scenarios were analyzed. We made an intriguing discovery: the impact on arterial traffic flow increases with larger average access point spacing, challenging conventional traffic planning recommendations that advocate for greater spacing. Additionally, access traffic minimally affects the overall arterial flow when arterial traffic volume is low. By highlighting these critical insights, this study introduces novel considerations for designing and managing access points.

Equivalence Ratio-Driven Flame Response of an Industrial Premixed Burner: Experiments and Modeling

Abstract This paper presents an analysis of the unsteady heat release rate response of premixed flames to equivalence ratio perturbations for an industrial premixed swirl-based burner. During this investigation, perfectly and technically premixed flames were acoustically forced via fuel/air mixture flow and air flow modulations, respectively, at the same operating conditions. From the resulting flame transfer functions (FTFs), measured using the multimicrophone method, the equivalence ratio driven FTF was isolated and extracted by removing the velocity driven component, i.e., the measured FTF from the perfectly premixed flame, from the technically premixed FTF with two novel extraction techniques. The results are compared with FTFs obtained directly in a previous experimental campaign where the fuel flow was acoustically forced, the resulting equivalence ratio fluctuations measured via an infrared absorption technique, and the heat release rate response to the forcing was quantified using chemiluminescence measurements. The results from both measurement approaches agreed well highlighting the validity of the techniques. Further, to understand the governing features of the equivalence ratio driven FTF, a physics-based analytical model following the G-equation approach was developed. The contributions from flame surface area, flame speed, and heat of reaction oscillations were modeled to describe the heat release rate dynamics. A limited number of physical parameters in the analytical model were anchored on one test condition, optimized and restricted to values, which were all physically reasonable, and were subsequently used for model predictions at other operating conditions. The FTF model predictions compared well with experimental data across a range of different operating conditions. Finally, the relative contributions from flame surface area, flame speed, and heat of reaction oscillations on the features of the FTFs were identified and explored.

Advanced Diagnostic Model for Gearbox Degradation Prediction Under Various Operating Conditions and Degradation Levels

This study introduces a novel three-stage diagnostic methodology aimed at enhancing the prediction and classification of gearbox degradation under various operating conditions and multiple degradation levels, addressing the complexities encountered in real-world industrial settings. Leveraging the latest advancements in data-driven approaches, from similarity-based methods to residual-based deep convolutional neural networks (CNNs) and pseudo-labeling techniques, our approach systematically classifies data into known, unknown, and undetermined categories, predicts known degradation levels, and refines classification models with augmented pseudo-label data. The efficacy of our methodology is demonstrated through its remarkable performance using the data from the PHM North America 2023 Conference Data Challenge. It achieves scores of 600 / 800 on the testing data and 574 / 813 on the validation data, significantly surpassing the first-place scores of 463.5 and 472 in the competition, respectively, setting a new benchmark in the field of gear fault diagnosis.

Optimizing Sodium Ion Adsorption Through Robust d–d Orbital Modulation for Efficient Capacitive Deionization

AbstractUnraveling the fundamental mechanisms of sodium ion adsorption behavior is crucial for guiding the design of electrode materials and enhancing the performance of capacitive deionization systems. Herein, the optimization of sodium ion adsorption is systematically investigated through the robust d–d orbital interactions within zinc‐doped iron carbide, facilitated by a novel liquid nitrogen quenching treatment. Liquid nitrogen quenching treatment can enhance the coordination number, strengthen d–d orbital interactions, promote electron transfer, and shift the d‐band center of Fe closer to the Fermi level, thereby enhancing sodium ions adsorption energy. Consequently, the obtained electrode material achieves a superior gravimetric adsorption capacity of 121.1 mg g−1 and attractive cyclic durability. The adsorption capacity is highly competitive compared to the vast majority of related research works in the field of capacitive deionization. Furthermore, sodium ion adsorption/desorption mechanisms are substantiated through ex situ techniques, revealing dynamic atomic and electronic structure evolutions under operational conditions. This work demonstrates that optimizing sodium ion adsorption via robust d–d orbital modulation enabled by liquid nitrogen quenching treatment is an effective approach for developing efficient capacitive deionization electrode materials.

Analysis and Optimization of Output Low-Pass Filter for Current-Source Single-Phase Grid-Connected PV Inverters

In this study, the design of output low-pass capacitive–inductive (CL) filters is analyzed and optimized for current-source single-phase grid-connected photovoltaic (PV) inverters. Four different CL filter configurations with varying damping resistor placements are examined, evaluating performance concerning the output current’s total harmonic distortion (THD), the power factor (PF), and power losses. High-frequency harmonics are effectively attenuated by a second-order CL filter with the damping resistor placed parallel to the filter inductor. In addition, this filter type achieves the best performance by minimizing power loss. A systematic design methodology using filter normalization techniques allows to determine the optimum filter parameters based on the specified cut-off frequency (500 Hz), power loss (5% of rated power), and target THD (<5%). The analysis, simulations, and experiments show that under various operating conditions, this approach meets the grid connection standards (current THD < 5%, power factor between 0.8 leading and 0.95 lagging) while improving efficiency.

The HVAC system engineering method for a new family of unified cabins of combine harvesters

BACKGROUND: Designing a combine harvester cabin climate system is a complex and multi-stage process that includes solving a set of tasks. To solve them, a design engineer must have knowledge and skills in various fields, starting with thermal engineering calculations and ending with experimental research methods and computer modeling, which requires a large amount of intellectual and time resources. Therefore, the task of creating a unified method of engineering of combine harvester cabin HVAC system is highly relevant. AIM: Development of the HVAC system for a unified cabin of a grain harvester and a forage harvester. The designed HVAC system is purposed to create a comfortable microclimate in the cabin of the combine for 2 people in summer and winter operating conditions. METHODS: The methodology of calculation and selection of the combine harvester cabin HVAC system, which includes the development of engineering calculation methods and mathematical modeling of thermodynamic and ventilation processes in the cabin, is considered. RESULTS: The main parameters were determined: heat intakes and heat losses for the grain harvester and forage harvester cabins, which amounted to 2.8 and 2.2 kW for the grain harvester, 2.9 and 2.35 kW for the forage harvester; the required air flow rate supplied to the cabin to ensure a comfortable temperature — 740 m3/h; the percentage of air recirculation regarding the conditions of absence of fogging and creation of excessive pressure in the cabin — 75%; the cooling and heating capacity of the HVAC system, taking into account the operating conditions of the combine, are 7.8 and 6.3 kW respectively. The selection of the main equipment of the HVAC system for a unified cabin for a new family of unified cabins of combines — the BUHLER 1000 MFWD evaporator-heater and the Valeo TM16 compressor are chosen. CONCLUSION: The HVAC system designed in accordance with the presented methodology is capable of ensuring a comfortable cabin air temperature in the range of 22–24 °C at various operating modes of the combine harvester in different regions. In addition, the HVAC system parameters eliminate fogging of the cabin windows and the penetration of dusty air inside due to the created excessive pressure.

Biomimetic low carbonization efficient solar-driven thermochemical energy storage reactor design inspired by the diatoms’ superior photosynthesis capacity

Photon is the energy source that drives solar thermochemistry. Photon-based radiative transfer in the reactor space is an essential mode of energy transfer. However, there often exists mismatch between the radiative and chemical fields in direct solar thermochemical processes, which can lead to ultra-high temperature gradients and high carbonization rates. While, the vicious cycle that exists between high temperature gradients and higher carbonization rates could severely limit the thermochemical efficiency. To improve the efficiency and reduce the temperature gradient and carbonization, inspired by the superior performance of diatom photosynthesis, a biomimetic radiation-regulated reactor is proposed. The paper establishes multi-field model of steam methane reforming, and analyzes the energy conversion processes at pore-scale. In numerical analyses, compared to the conventional reactor, the biomimetic reactor enhances the light forward scattering in fore-end and the backward scattering in rear-end, which increases the light absorption efficiency by 6.8% and reduces the temperature gradient by 41.3%. In experimental investigation, the methane conversion and the solar-fuel efficiency of the biomimetic reactor is 48.6% and 44.0%, which is increased by 11.5% and 10.7% respectively. It also demonstrates high efficiency and stability under long operating conditions. The biomimetic reactor provides a new strategy for industrial solar-driven methane conversion.

Transport of a Mixture of Sand and Water Through a Pump Characterized by Dual Inlets and a Double-Layered Impeller

A centrifugal pump incorporating two inlets and a double-layered impeller is proposed for transporting a mixture of sand and water. The double-layered impeller (primary impeller) encircles a secondary impeller. To reveal the operating and flow characteristics of such a pump, numerical work is conducted with a validated numerical method. The effects of the feed rate of sand and the rotational speed of the impeller are investigated. The results show that the pump efficiency is not monotonically related to the solid volume fraction. At a feed rate of sand of 2.10 m3/min and a rotational speed of 950 rpm, the lowest pump efficiency is reached. In the volute chamber, vortices of various sizes are evidenced. With increasing rotational speed, the overall solid volume fraction in the pump decreases. Meanwhile, when the solid volume fraction attains 0.28, sand particles tend to accumulate near the outer rim of the volute chamber. The axial force acting on the primary impeller increases with the rotational speed. Under different operating conditions, the radial forces point unanimously toward the third and fourth quadrants.

Influence of Dopants on Pt/Al2O3-Based Monolithic Catalysts for Autothermal Oxidative Coupling of Methane

Autothermal oxidative coupling of methane (OCM) is a highly attractive approach for methane utilization. If platinum-based catalysts are operated in short-contact-time reactors with high space velocities, high methane conversion can be achieved. Using a 1 wt.% Pt/Al2O3 catalyst as a benchmark, the present study elucidates how different dopants, namely Ni, Sn, and V2O5, affect the OCM reaction. Kinetic catalyst tests reveal that acetylene (C2H2) is the predominant C2 product, irrespective of the catalyst formulation or operation conditions. Furthermore, the use of bimetallic catalysts allows either for the maintenance or even the improvement of the C2 selectivity during OCM, which is attributed to synergistic effects that occur when expensive Pt is partially replaced by cheaper dopants. In particular, the 1 wt.% Pt/Al2O3 reference catalyst yielded a maximum C2 selectivity of 8.2%, whereas the best-performing doped sample 0.25 wt.% Pt 0.75 wt.% V2O5/Al2O3 yielded a total C2 selectivity of 11.3%.

Comparative numerical study of the energy performance of two different configurations of a hybrid photovoltaic/thermal air collector

Solar energy is a renewable alternative to fossil fuels. When solar energy is converted into electricity by photovoltaic (PV) solar modules, the heat generated increases the temperature of the PV solar cells and, as a result, reduces their electrical efficiency. Several techniques are used to cool PV solar cells in order to reduce their operating temperature. One technique is the use of hybrid photovoltaic/thermal (PVT) solar collectors, which simultaneously produce electricity and useful heat. In the airflow channel, the heat and mass transfer equations and those derived from the energy balance on the solid layers of the collector were discretized using the finite difference method with an implicit alternating directions (ADI) scheme. All the algebraic equations obtained after discretization were solved using the Thomas algorithm. The aim is to make a numerical comparison of the energy performance of the Verre-PV-Tedlar and Verre-PV-Verre flat-plate air PVT hybrid solar collectors in the climatic conditions of Lomé, Togo. Under the same operating conditions, the average electrical efficiencies of the Verre-PV-Verre and Verre-PV-Tedlar flat-plate air PVT hybrid collectors are 15.34% and 13.85% respectively. There is a 1.49% improvement in electrical efficiency for a Verre-PV-Verre air-source PVT hybrid collector compared with a Verre-PV-Tedlar PVT hybrid collector. The Verre-PV-Verre flat plate PVT air hybrid collector has an average daily electrical energy gain of 0.564 kWh and a thermal energy gain of 0.839 kWh, while the Verre-PV-Tedlar flat plate PVT air hybrid collector has an average daily electrical energy gain of 0.548 kWh and a thermal energy gain of 1.403 kWh.

Aromatic Poly(dithioacetal)s: Spanning Degradability, Thermostability, and High Refractive Index Towards Eco-friendly Optics.

In the quest for eco-friendly optics, high refractive index polymers (HRIPs) with degradability have been one of the desirable optical materials for realizing eco-friendly and efficient lighting technologies. However, it has been challenging for HRIPs to simultaneously realize thermostability, high refractive index (RI), visible transparency, and efficient degradability, all of which are essential for their practical use. In this context, we herein focus on aromatic poly(dithioacetal)s, composed of visible-transparent yet degradable dithioacetal moieties and rigid phenylene sulfide spacers, exhibiting moderately high Tg (> 60 °C), high RI (> 1.7), and colorless film features. In addition, poly(dithioacetal)s can balance (1) high stability under the operating conditions even upon heating and (2) quantitative degradability that can selectively yield cyclic low-molecular-weight products that can be further repolymerized upon further addition of an acid catalyst. These results provide a key concept for high refractive index polymers that allow on-demand degradability and recyclability without compromising their high potential thermal and optical properties.

Optimal expansion planning of a self-healing distribution system considering resiliency investment alternatives

This paper proposes a three-stage optimization framework for the expansion planning of a self-healing distribution system that determines the optimal characteristics of distributed generation, energy storage systems, electric vehicle charging stations, and sectionalizing switches for the planning horizon. The main contribution of this model is that the proposed model considers the resilient investment alternatives in the expansion planning exercise to reduce the system's vulnerability against external shocks. The mobile energy storage system commitment in contingent conditions is another contribution of this paper. In the first stage, the optimal location, capacity, and time of installation of the electricity facilities are calculated. Then, the optimal allocation of sectionalizing switches is performed in the second stage. The third stage consists of three levels. In the first and second levels, the optimal normal and contingent operational scheduling are determined, respectively. The system is sectionalized into multi-microgrid systems in contingent conditions. Finally, the resilient investment alternatives for the designed system are evaluated. The proposed model utilizes a self-healing index and resilient expansion planning index to assess the impacts of resilient investment alternatives on the operational scheduling conditions. The proposed model was evaluated using the IEEE 123-bus system. The proposed method reduced the estimated average value of the worst-case energy not supplied by 50.52 % for the 5th year of the planning horizon concerning the no-resiliency investment case. Further, the proposed resilience investment method increased the self-healing index by about 9.32 % concerning the no-resiliency investment case.

Evaluating the Influence of Thin Film of Water on the Frequency Dependences of Transmission Line S-Parameters at Positive and Negative Temperatures

Relevance. Provision of reliable and uninterrupted radio communication is critically important under changing climatic conditions of its operation. The combined effect of temperature and humidity can lead to changes in the electrical characteristics of transceiving devices and thereby disrupt the communication channel. In difficult climatic conditions of operation, due to constant temperature changes on the surface of the printed circuit boards, which are part of them, condensation can form, affecting the performance of the entire device. In this regard, the electrical characteristics change, which must be taken into account when designing critical REE. When designing transmission lines on printed circuit boards, it is reasonable to evaluate climatic impacts on it in a wide frequency range, which requires the development of new models and methods that allow taking into account these impacts.Goal of the work: to evaluate the influence of the temperature of a thin film of water on the surface of a microstrip transmission line on its frequency dependences of S-parameters. Finite element methods and laboratory experiment were used.Results. A methodology to account for the effects of ambient temperature and humidity on the electrical characteristics of a microstrip transmission line (MTL) is presented, which allows evaluating the variation of the S-parameters of the line over wide ranges of frequencies, air temperature and humidity, as well as the chemical composition of the environment. The S-parameters of water in a container placed inside a coaxial chamber are measured over the frequency and temperature ranges of 10 MHz to 12 GHz and minus 50 to 100℃, respectively. Using the presented model, the frequency dependences of the electrical conductivity of water at different temperatures are calculated. It is shown that at positive temperature, the electrical conductivity can reach 6.5 Sm/m and at negative temperature it can reach 1.3 Sm/m. Using the developed methodology, the influence of different water electrical conductivity on the S-parameters of MTLs is evaluated. The influence of water and ice layer thickness on the S-parameters of MTLs was shown. It is found that models describing the electrical conductivity of water have an excellent influence on the electrical parameters of the transmission line. Novelty. A method of accounting for the influence of ambient temperature and humidity on the S-parameters of the transmission line is presented, which is characterized by the use of a model of water conductivity based on insertion losses calculated from the measured S-parameters of a coaxial chamber with water in the container when its temperature is changed. Practical significance: a model and a methodology for taking into account the impact of temperature and humidity of the environment on the MTL characteristics are presented, allowing estimating the S-parameters of the line in a wide range of frequencies, air temperature and humidity, as well as the chemical composition of the environment.

An Assessment of the Catalytic and Adsorptive Performances of Cellulose Acetate-Based Composite Membranes for Oil/Water Emulsion Separation.

Cellulose acetate (CA) mixed-matrix membranes incorporating polyvinylpyrrolidone (PVP), bentonite (B or Ben), graphene oxide (GO), and titanium dioxide (TiO2) were prepared by the phase inversion separation technique for oil/water separation. An investigation was performed where the mixed-matrix membrane was tested for the separation performance of hydrophilic and hydrophobic surface properties. An ultrafiltration experiment at the laboratory scale was used to test dead-end ultrafiltration models developed for the treatment performances of oily wastewater under dynamic full-scale operating conditions. Artificial oily wastewater solutions were prepared from hexane, toluene, and engine oil with Tween80 emulsions for oil removal treatment using composite membranes. The impacts of material hydrophilicity, weight loss, permeability, and pore size were investigated, and it was found that the oil retention of membranes with larger pore sizes enabled much more sophisticated water flux. The CA-GO-, CA-B-, and CA-TiO2-incorporated membranes achieved pure water flux (PWF) values of 45.19, 53.41, and 100.25 L/m2h, respectively. The performance of CA-TiO2 in oil/water emulsion rejection was assessed, and the rejection of engine oil/water, toluene/water, and hexane/water mixtures was determined to be 95.21%, 90.33%, and 92.4%, respectively. The CA-based mixed-matrix membrane portrayed better antifouling properties due to enhanced hydrophilicity and water molecules. The CA-TiO2-incorporated membrane possessed the potential to provide high separation efficiency for oily wastewater treatment. This study demonstrates the potential of fine-tuning membrane performances through material hybridization to achieve efficient wastewater treatment.

The green footprint of anammox processes under simulated actual operating conditions: Focusing on the nitrous oxide and methane production

The anammox process has attracted increasing attention due to its advantages of low-carbon and energy-saving, nevertheless, greenhouse gas was still generated during its engineering applications process. Hence, it is vital to comprehensively understand the production characteristics and mechanisms of N2O and CH4 in anammox processes by responding to practical conditions including dissolved oxygen, temperature, and salinity. Results showed that N2O production increased by 192 %–358 %, while nitrogen removal efficiency (NRE) increased by 64.2 %–86.8 % with increasing temperature. The increased salinity inhibits 40.60 %–65.33 % N2O production with a decrease NRE of 7.85 %–18.2 %. CH4 production was the highest at 18–27 °C, reaching 3.07 ± 0.11–4.06 ± 0.16 mg·L−1, which were 1.59–2 and 1.29–1.38 times higher than that at 8–17 °C and 28–37 °C, respectively. Denitratisoma, Thauera, and Nitrosomonas were the main functional microbes for greenhouse gas production in anammox consortia. Notably, H2O2-induced intracellular Fenton reaction may be critical for the CH4 production in anammox consortia. This work provides valuable insights into achieving efficient nitrogen removal and minimizing carbon footprint in anammox systems and provides a theoretical basis for implementing the net-zero emission idea in wastewater treatment plants.

Evaluation of the Use of the Angular Domain and Order Domain in a Bearing Fault Detection Framework using Deep Learning

Bearing failures are very common in the industrial environment, requiring effective fault detection methods, which can be categorized into physics-based, knowledge-based and data-driven types. Data-driven methods are efficient in differentiating healthy conditions from faulty conditions by characterizing machine signals, involving stages of data acquisition, feature extraction, and condition determination. Traditionally, feature extraction and condition determination were manual, but advances in artificial intelligence and machine learning, especially deep learning, have automated this process. Although deep learning automatically learns the best features from the input data, the signal domain can influence the model's performance. Time and frequency domain representations are widely used in fault detection methodologies using vibration signals, while angular and order domains are more common in variable operating conditions, but direct use of these domains with deep learning is still rare in the literature. Considering this, this study evaluates a bearing fault detection methodology using vibration signals in different domains (time, frequency, angular, and order) under various rotational conditions. Three distinct approaches were tested to assess the effectiveness of these representations. The results indicated that the frequency domain representation had the best overall performance and the study concluded that the angular and order domains do not offer significant advantages compared to the frequency domain. Nonetheless, it is recommended to conduct a more in-depth analysis with more diverse datasets, especially those containing early-stage bearing fault signals.

Advancing Light Aircraft Health Monitoring with Flight Phase Clustering

This paper addresses the clustering of flight phases of a light aircraft for health monitoring using vibration data. The aim is to improve diagnostic and prognostic functions. Grouping condition monitoring data under similar operating conditions is significant for predictive maintenance. Clustering also supports advanced analytics for fault detection and estimation of remaining life. The proposed framework uses self-organizing maps for flight phase clustering. The findings show that the algorithm can recognize and classify flight phases in various operational domains. Additionally, visualization of cluster maps uncovers complex patterns and non-linear relationships in sensor data under different flight conditions. As a followup, analyzing the vibration properties within these estimated clusters (regimes) provides insights from condition monitoring data behavior during flight phases. The results confirm the effectiveness of the method, but also confirm that determining light aircraft regimes requires more focus due to their unique flight patterns that are absent in commercial airliners. In this context, this research has dealt with these unique patterns and provided the foundation for a new model for clustering with an attempt to contribute valuable insights into improving the reliability and efficiency of light aircrafts.

Pressure and Temperature Prediction of Oil Pipeline Networks Based on a Mechanism-Data Hybrid Driven Method

To ensure the operational safety of oil transportation stations, it is crucial to predict the impact of pressure and temperature before crude oil enters the pipeline network. Accurate predictions enable the assessment of the pipeline’s load-bearing capacity and the prevention of potential safety incidents. Most existing studies primarily focus on describing and modeling the mechanisms of the oil flow process. However, monitoring data can be skewed by factors such as instrument aging and pipeline friction, leading to inaccurate predictions when relying solely on mechanistic or data-driven approaches. To address these limitations, this paper proposes a Temporal-Spatial Three-stream Temporal Convolutional Network (TS-TTCN) model that integrates mechanistic knowledge with data-driven methods. Building upon Temporal Convolutional Networks (TCN), the TS-TTCN model synthesizes mechanistic insights into the oil transport process to establish a hybrid driving mechanism. In the temporal dimension, it incorporates real-time operating parameters and applies temporal convolution techniques to capture the time-series characteristics of the oil transportation pipeline network. In the spatial dimension, it constructs a directed topological map based on the pipeline network’s node structure to characterize spatial features. Data analysis and experimental results show that the Three-stream Temporal Convolutional Network (TTCN) model, which uses a Tanh activation function, achieves an error rate below 5%. By analyzing and validating real-time data from the Dongying oil transportation station, the proposed hybrid model proves to be more stable, reliable, and accurate under varying operating conditions.