Researched regimes of engine operation without load: 1 – test of the original engine; 2 – test with disconnection of four cylinders by stopping the fuel supply; 3 – test with the disconnection of four cylinders by simultaneously stopping the fuel supply and the absence of pumping losses of the cylinder-piston group (CPG) of the disconnected cylinders. It was established that when the crankshaft rotation frequency increases from 1400 min-1 to 2550 min-1 when the fuel supply to half of the cylinders is turned off, the fuel economy changes from 0 to 0.53 kg/h. When the fuel is turned off and there are no CPG pumping losses, the fuel economy changes from 1.2 kg/h to 3.88 kg/h. Recommendations have been developed that allow to increase the efficiency of wheeled vehicles by 11-26% by disconnecting a part of the cylinders.

The method of testing vehicles for dynamic position stability has been improved, which makes it possible to assesstheir lateral stability when driving on irregularities. The dynamic stability coefficient is proposed for use as an assessmentcriterion. The application of the developed method allows to obtain an assessment of stability in real time during theoperation of transport means.The structural scheme has been developed to ensure the reliability of the operation of wheeled vehicle, based onreducing the influence of the driver's qualifications as an element of the "driver-vehicle-road conditions" system on itsposition stability, taking into account the results of monitoring the technical condition.To conduct experiments and evaluate the results, the mobile registration and measurement complex (MRMC) wasused to assess and improve the safety of exploitation of wheeled vehicles, taking into account modern means andapproaches. A single-board computer Raspberry Pi version 3B + serves as a platform for the mobile registration andmeasurement complex. The architecture of MRMC is modular; it supports the installation of additional inertial sensors,photo and video fixation devices, GPS, as well as devices compatible with USB. Operating system – Raspbian based onDebian distribution (GNU / Linux).To further automate the process of controlling a wheeled vehicle, the promising scheme for the operation of theregistration and measuring complex with elements of artificial intelligence was developed, which allows, without theparticipation of the driver, to carry out the necessary actions to control it and ensure, including operational safety.The results can be used to assess the suitability and performance of wheeled vehicles.

The article proposes the use of neural network technology to solve the problems of diagnosing the automobile and tractor engines technical conditions. This allow to work with real data obtained for an individual and reference (average)  engine, as well as with data calculated using the mathematical model, based on the comparison of which researcher can take informed decisions about the nature and location of a particular defect. This improves the functional stability of the wheeled vehicle and improves the performance of its intelligent on-board systems. It has been proven that in order to reduce the redundancy of a neural network, it is necessary to reduce the number of neurons in the hidden layer for a given level of network training error. For diagnosing the automobile or tractor engine, the input signals are voltages received in an artificial neural network from sensors that are standard in the engine, and additionally indicate the technical conditions.

The method of testing vehicles for dynamic position stability has been improved, which makes it possible to assess their lateral stability when driving on irregularities. The dynamic stability coefficient is proposed for use as an assessment criterion. The application of the developed method allows to obtain an assessment of stability in real time during the operation of transport means. The structural scheme has been developed to ensure the reliability of the operation of wheeled vehicle, based on reducing the influence of the driver's qualifications as an element of the "driver-vehicle-road conditions" system on its position stability, taking into account the results of monitoring the technical condition. To conduct experiments and evaluate the results, the mobile registration and measurement complex (MRMC) was used to assess and improve the safety of exploitation of wheeled vehicles, taking into account modern means and approaches. A single-board computer Raspberry Pi version 3B + serves as a platform for the mobile registration and measurement complex. The architecture of MRMC is modular; it supports the installation of additional inertial sensors, photo and video fixation devices, GPS, as well as devices compatible with USB. Operating system – Raspbian based on Debian distribution (GNU / Linux). To further automate the process of controlling a wheeled vehicle, the promising scheme for the operation of the registration and measuring complex with elements of artificial intelligence was developed, which allows, without the participation of the driver, to carry out the necessary actions to control it and ensure, including operational safety. The results can be used to assess the suitability and performance of wheeled vehicles.