Injection Subsystems Research Articles

Application of Machine Learning to Classify the Technical Condition of Marine Engine Injectors Based on Experimental Vibration Displacement Parameters

The article presents the possibility of using machine learning (ML) in artificial intelligence to classify the technical state of marine engine injectors. The technical condition of the internal combustion engine and injection apparatus significantly determines the composition of the outlet gases. For this purpose, an analytical package using modern technology assigns experimental test scores to appropriate classes. The graded changes in the value of diagnostic parameters were measured on the injection subsystem bench outside the engine. The influence of the operating conditions of the fuel injection subsystem and injector condition features on the injector needle vibration displacement waveforms was subjected to a neural network (NN) ML process and then tested. Diagnostic parameters analyzed in the amplitude, frequency, and time–frequency domains were subjected after a learning process to recognize simulated various regulatory and technical states of suitability and unfitness with single and complex damage of new and worn injector nozzles. Classification results were satisfactory in testing single damage and multiple changes in technical state characteristics for unfitness states with random wear injectors. Testing quality reached above 90% using selected NNs of Statistica 13.3 and MATLAB R2022a environments.

Framework for fault-tolerant speed tracking control of gasoline engines using the first principle-based engine model

ABSTRACT Optimal engine torque management, a fundamental objective, depends predominantly on engine speed tracking performance. It ensures to attain desired speed profile in the presence of uncertainties, disturbances and malfunctions. On the other hand, certain requirements such as emissions control, fuel efficiency and drivability are degraded in case of poor speed tracking. Furthermore, constraints on engine speed tracking performance are even more stringent for hybrid power-train architecture as crankshaft speed and engine torque are the basic variables for coordinated control. Speed tracking is also considered essential for gear shift control of the automatic transmission. In this research work, a framework for fault-tolerant speed tracking of the gasoline engine is proposed using the First Principle-based Engine Model (FPEM). A high-fidelity direct relationship between fuel injection input and engine speed is derived by the transformation of FPEM. Fault is induced in the fuel injection subsystem to generate the torque imbalance. Using the proposed framework, a second-order sliding mode-based control technique is applied to track desired speed profile by mitigating the faults in the fuel injection subsystem. Reference data acquired from the engine test rig is used to demonstrate the offline validity and fault tolerance capabilities of the proposed framework in MATLAB/Simulink.

Model-Based Unified Framework for Detection and Mitigation of Cyclic Torque Imbalance in a Gasoline Engine

Abstract Torque produced by the internal combustion (IC) engine is desired to be of similar value for consecutive combustion cycles; nevertheless, difference occurs in the cyclic torque due to uncertainties in its generation. Variations between output work of successive combustion cycles are considered as the main cause of imbalance in the cyclic torque. Such variations are displayed in engine output torque and affect the engine performance. In this paper, a novel model-based unified framework is proposed for the detection and mitigation of cyclic torque imbalance in a gasoline engine by employing the first principle-based engine model (FPEM). Engine speed dynamics in the model are transformed to develop the direct relationship between engine speed dynamics and fuel input. Fault in fuel injection subsystem is induced to generate imbalance in the cyclic torque. FPEM-based uniform second-order sliding mode (USOSM) observer is applied for estimation of the unknown input, i.e., net piston force (fn) from engine speed dynamics to detect imbalance in the cyclic torque. Estimated net piston force (f⁁n) is utilized to design the control law for certainty equivalence super twisting algorithm (CESTA) based fault tolerant control (FTC) technique to mitigate the torque imbalance. The results of numerical simulation demonstrated that the desired objective is achieved by the proposed unified framework.

Physical simulation and compatibility evaluation of multi-seam CBM co-production: Implications for the development of stacked CBM systems

Multi-layer co-production is a mainstream method for efficient development of coalbed methane (CBM) and coal series gas under multi-seam conditions. However, interlayer interferences during CBM co-production caused by differences in reservoir properties (especially permeability and pressure) between stacked CBM systems severely restrict the output of CBM from the production layers. The identification of interlayer interferences and optimization of production layer combinations are important scientific issues that need to be explored to achieve high CBM production. Physical simulation is an effective means of accomplishing this research objective. Physical simulations of CBM co-production were performed under designed permeability and pressure combinations based on self-developed experimental equipment, which is mainly composed of an injection subsystem, a vacuum subsystem, the model body subsystem, and a separation and metering subsystem. Coal samples were collected from three CBM basins in China to form a series of five permeability levels, specifically 0.2, 2, 10, 50, and 100 mD. We focused our analysis on the contribution of gas production from each production layer using the gas flow data obtained from the physical simulation experiments. The co-mining compatibility of the production layers is divided into four types based on the grading evaluation of gas contribution: Grade I, II, and III compatible, and incompatible, which represent gas production contribution of the weak seam ≥37.5%, 25%–37.5%, 12.5%–25%, and ≤12.5%, respectively. On this basis, a template for discriminating CBM co-production compatibility is constructed using the permeability ratio and pressure difference as basic parameters. The gas and water production data of representative CBM wells in the Bide-Santang basin were used to verify the reliability of the template, and the compatibility discrimination results show consistency with the production data. The average daily gas production per unit of coal thickness presents a decreasing trend with deteriorating compatibility of co-producing seams. Finally, an integrated technical process for the development of stacked CBM systems is proposed, including the hierarchical optimization of production layer combinations, identification of interlayer interferences and sources of produced water, and selection of suitable development methods and technology. We divided the production layer combinations into four types representing different development potentials based on the hierarchical method: most favorable, favorable, sub-favorable, and unfavorable. Suggestions are made for the key geological constraints (weak water-bearing reservoir, compatibility of CBM systems, shallow groundwater interference, and deep CBM condition) and specific development strategies for different types of production layer combinations. This study will enrich the geological understanding of CBM co-production and provide theoretical and technical support for the efficient development of stacked CBM systems.

Diagnosing Marine Piston Engines Driving Generators at Different Operational Loads

Loads at which diagnostic research should be carried out were selected of operational investigation and preliminary diagnostic tests. It is difficult to keep the load constant during operational tests, so there is a need to apply the theory of the experiment. Operational investigation determined, the average and representative loads of tested engines driving generators. In preliminary diagnostic tests, the effects of loading on values of diagnostic parameters in various domains of signals analysis were checked and used to reduce the range the diagnostic research. Besides, the most useful symptoms were selected based on the correlation with the load. The diagnostic of pressure in the injection subsystem and in-cylinder pressure signals were subjected to time frequency analysis. In the principal studies, attempts were made to investigate the value of diagnostic symptoms while maintaining a constant load. For operating marine combustion engines, it is difficult to obtain repeatable test conditions because it is dependent on the principles of engine control and consumption of electricity by shipboard receivers. In operational tests on sea-going vessels, a wireless load measurement system and a system for processing and analyzing the parameters of working and residual processes were used. The wireless simultaneous load measurement system was effective in cases where load indicators and meters were away from the diagnosed objects. A wireless load and selected signals transmission system was used in tests on the ship. The aim of the article is to develop diagnostic models for bringing different test conditions to the common representative and reliable diagnostic decision. The article presents how to adjust diagnostic parameters of the working process, recorded at slightly different loads, to the value of common and equal load. This was done based on the best-fitted approximation model.

Development and research the electronic control system for gas engines converted on the basis of diesels

The object of research is an electronic microprocessor control system for gas internal combustion engines with spark ignition for operation on liquefied petroleum gas. The system consists of two main subsystems, the accumulative power supply common rail LPG injection subsystem and the contactless electronic ignition subsystem with a movable voltage distributor. In addition, the control system also includes a subsystem for controlling the filling of the cylinders with the charge of the working mixture, consisting of a throttle valve and an idle speed regulator with a conical damper. The control system, depending on the software version, is capable of providing group or sequential injection of liquefied petroleum gas into the inlet pipe of each cylinder in the area close to the inlet valve. Such a control system can be used when converting (re-equipping) both new diesel engines into spark-ignition gas engines, and those that are in operation. The feasibility of such a conversion is to reduce operating costs with powerful vehicles for diesel fuel, by replacing it with cheaper and environmentally friendly liquefied petroleum gas.To test the efficiency of the control system, a D-240-LPG-«B» model gas engine was developed and manufactured to operate on liquefied petroleum gas. The gas engine was converted on the basis of the D-240 transport diesel engine (atmospheric, four-stroke, liquid-cooled, 4-cylinder engine with a piston diameter of 110 mm and a stroke of 125 mm). Reducing the compression ratio of the diesel engine was achieved by modifying a semi-closed diesel combustion chamber of the TsNIDI type into an open combustion chamber in the form of an axisymmetric «truncated cone». For efficient control of three subsystems of the D-240-LPG-«B» model gas engine, an electronic microprocessor control unit of the Avenir Gaz 37 «B» model was developed and manufactured. The tests carried out on the D-240-LPG-«B» gas engine with the Avenir Gaz 37 «B» control unit showed the efficiency of using the electronic microprocessor control system.

Simulation research on passive safety injection system of marine nuclear power plant based on compressed gas

In case of a large or medium LOCA accident of marine nuclear power plant, the loop pressure drops rapidly. In case of power failure of the whole ship at this time, the active safety injection system will lose its function because the safety injection pump needs AC power, and the core is at risk of melting. A passive marine safety injection system based on high-pressure compressed gas is designed for the superposition of large and medium LOCA accidents and the whole ship's power failure accidents, including the safety injection subsystem of medium and low pressure and the safety injection subsystem of recirculation. The energy required for safety injection is provided by the potential energy of compressed gas, the pressure head is provided by the technology of gas-liquid booster pump, and the collection signals and valves are controlled by the technology of intelligent fluid control unit with small power consumption. The power supply used in the system is provided by DC 24 V battery. The mathematical and physical models of accumulator, gas storage tank, gas-liquid booster pump, reactor body and its pipeline are established for the designed passive safety injection system. The operation and safety characteristics of medium pressure safety injection, low pressure safety injection and recycling safety injection under LOCA accident conditions are simulated. The safety injection time and flow rate of three safety injection pressures are simulated by medium pressure safety injection, the safety injection time and peak temperature are simulated by low pressure safety injection, and the pressure and system temperature are simulated by recirculation safety injection. The simulation results show that the marine passive safety injection system designed under LOCA accident conditions can meet the requirements of core cooling.

Selection of Diagnostic Symptoms and Injection Subsystems of Marine Reciprocating Internal Combustion Engines

This paper presents the planning of an experiment aimed at determining the scope of scientific research. It has been demonstrated in the conducted reliability investigations that main and auxiliary combustion engines, chosen as the objects of marine vessels, are the most unreliable components of injection apparatus as a weak link of a fuel feed functional system. The author seeks to use the minimum number of diagnostic parameters to obtain the maximum amount of information about the state of the test object. Reliability indexes, theoretical research and preliminary diagnostic tests were used to select the diagnostic signal reception points. In the initial determination of the measured quantities, the following methods were used: decomposition of the combustion engine on a functional systems, significant assemblies and elements, analysis of working and residual processes. Preliminary tests of the injection subsystem were carried out outside the internal combustion engine, as well as tests on real objects in laboratory conditions and in the conditions of marine vessels. To obtain a lot of information about the research object, a lot of diagnostic parameters were used at the beginning. On this basis, the preliminary selection of signals and diagnostic parameters related to the technical state was carried out, conducting the analysis in the various domains. Methodical and experimental diagnostic models were elaborated.

DEVELOPMENT OF AN ELECTRONIC CONTROL SYSTEM FOR GAS-ENGINES, CONVERTED ON THE BASIS OF TRANSPORT DIESELS TO WORK FOR ON LIQUEFIED PETROLEUM GAS

The expediency and advantage of using gas motor fuels on a relation to traditional liquid motor fuels is shown. Technical solutions for the use of gas motor fuels by diesel engines are presented and analyzed. On the basis of the analysis, the expediency of converting diesel engines into gas engines with forced ignition is justified.An electronic microprocessor control system for gas internal combustion engines with forced ignition has been developed, which has a modular structure consisting of two main and a number of additional subsystems. The structures are described and the principle of operation of the main subsystems is described, including LPG injection subsystem, as well as the ignition control subsystem. An experienced ECU was developed and created. A structural scheme of the electronic control system of a gas engine with an experienced ECU is given. The out motorized tests of the experienced ECU were carried out, which confirmed his operability.

A probabilistic sedimentation analysis for predicting reservoir lifetime

This paper describes a melding of an established set of hydrological component processes to obtain a full-scale model for reservoir sedimentation. The goal is to achieve a probabilistic system relating reservoir sedimentation to standard injection, river flow, particle transport, and dam storage subsystems. In the conclucing section, it is found that for a certain assembly of process components, the sedimentation process is Poisson, with parameters interpretable in terms of physical variables. Moreover, for the resulting parameters, a Gaussian approximation can confidently be adopted.

Electronic Cell-Volume Analysis by Use of the AMAC I Transducer

Abstract A new potential-sensing transducer has been developed that produces short 5- to 10-µs pulses suitable for rapid cell counting and pulse height volume analysis rates. The use of a bridge circuit, where potential-sensing rather than current-carrying electrodes are connected to a differential amplifier with a high common-mode rejection ratio, permitted accurate determination of both pulse width and shapes from the short pulses generated with the transducer. A new sample injection subsystem permits small samples of constant volume to be continuously mixed at a variable rate with a constant flow of diluent. The counting rate can be optimized to 250,000 cells per minute at a 2% coincidence level. Polystyrene latex spheres produced pulses having the five basic shapes predicted by Grover et al. [Biophys. J. 9, 1398 (1969)]. Human erythrocytes produced, in addition to these shapes, a sixth, castle-shaped pulse, presumably caused by rotation or distortion of the erythrocyte as it passes through the orifice. A shape factor has been calculated from the latter pulses. The electronic cell-volume pulses from the tranducer trigger an pulsed-ion laser. The 5-W peak power beam is focused through the orifice. Illumination of the cells with this intense but economical light source permits the combined measurement of electronic cell volume, fluorescence, and light scattering.