Abstract: A system for reducing computational load for training machine learning models is provided. The system may provide an end-to-end-solution for automating development, testing and updating of machine learning models in various operational environments. The system may determine which machine learning models included in a computer program product need to be retrained in response to a change in training data. For a computer program product that includes multiple models, the system only retrains target models, resulting in significant savings in computing resources. The system may also reduce the number of machine learning models that need to be generated for testing environments, further reducing consumption of computational resources.

Abstract: External interaction with a mover in an independent cart system is allowed at known locations along the track. The mover is initially propelled along the track in a first operating state. When the mover arrives at a station, the controller generates a signal to alert the external actuator of the presence of a mover at the station. After waiting at the station for a first predefined time interval, the controller switches to a second operating state, in which the coils are de-energized or the controller is reconfigured to operate in a less responsive manner than in the first operating state. The controller remains in the second operating state for a second predefined interval, during which the external actuator interacts with the mover or a load on the mover. After the second predefined interval, the controller enters a third operating state, and the controller propels the mover away from the station.

Abstract: Some embodiments described herein relate to a method of operating a compression ignition engine. The method of operating the compression ignition engine includes opening an intake valve to draw a volume of air into a combustion chamber, closing an intake valve, and moving a piston from a bottom-dead-center (BDC) position to a top-dead-center (TDC) position in the combustion chamber at a compression ratio of at least about 15:1. The method further includes injecting a volume of fuel into the combustion chamber at an engine crank angle between about 330 degrees and about 365 degrees during a first time period. The fuel has a cetane number less than about 40. The method further includes combusting substantially all of the volume of fuel. In some embodiments, a delay between injecting the volume of fuel into the combustion chamber and initiation of combustion is less than about 2 ms.

Abstract: A vehicle includes a collision determination ECU determining whether a possibility of collision is present, based on a detection result of a detection sensor detecting outside of the vehicle, a motor, a boosting circuit and a battery supplying a high voltage to the motor, and an electric suspension control ECU controlling the boosting circuit and the motor, and in a case where the collision determination ECU determines that the possibility of collision is present, the electric suspension control ECU limits the supply of the high voltage to the motor.

Abstract: Embodiments described herein relate to systems and methods of operating internal combustion (IC) engines by combusting various fuel chemistries therein. Specifically, engines described herein can operate a wide range of fuel chemistries with varying molecular formulas. The chemical compositions of the fuels described herein make them more difficult to ignite than long chain hydrocarbons (i.e., fuels that include 6 or more carbon atoms in a molecule). In some embodiments, engines described herein can combust fuels that have the chemical properties of alcohols. In some embodiments, engines described herein can combust fuels that include hydroxide groups. Examples of such fuels include methanol and/or ethanol. In some embodiments, engines described herein can combust natural gas. These fuel chemistries are difficult to ignite, particularly at low temperatures and during initial engine startup. Systems and methods described herein address these ignition difficulties, particularly in diesel engine architectures.

Abstract: Some embodiments described herein relate to a method of operating a compression ignition engine. The method of operating the compression ignition engine includes opening an intake valve to draw a volume of air into a combustion chamber, closing an intake valve, and moving a piston from a bottom-dead-center (BDC) position to a top-dead-center (TDC) position in the combustion chamber at a compression ratio of at least about 15:1. The method further includes injecting a volume of fuel into the combustion chamber at an engine crank angle between about 330 degrees and about 365 degrees during a first time period. The fuel has a cetane number less than about 40. The method further includes combusting substantially all of the volume of fuel. In some embodiments, a delay between injecting the volume of fuel into the combustion chamber and initiation of combustion is less than about 2 ms.

Abstract: A method for operating an internal combustion engine, in particular of a motor vehicle, wherein fuel is injected in a fuel injection device in a plurality of time-spaced partial injections per duty cycle directly into a combustion chamber of the internal combustion engine.

Abstract: The learning system includes a data generation unit configured to generate learning data based on rehabilitation data and a learning unit configured to perform machine learning using the learning data. A sensor is provided to detect a plurality of motion amounts in a walking motion of a trainee, and it is evaluated that, when one of the motion amounts matches one of abnormal walking criteria, that the walking motion is an abnormal walking pattern that meets the matched abnormal walking criterion. The data generation unit generates each of the pieces of rehabilitation data before and after a change in the results of evaluation of the abnormal walking pattern as learning data. The learning unit sequentially inputs each of the pieces of rehabilitation data as one data set, thereby performing machine learning.

Abstract: An engine includes a single cylinder, at least one sensor, a fuel injector, and a controller. The at least one sensor is configured to generate sensor data for an engine condition. The controller is configured to perform a comparison of the engine condition to a threshold and in response to the comparison, generate a first command to deactivate the fuel injector after a first predetermined time period and a second command to reactivate the fuel injector after a second predetermined time period.

Abstract: A work machine that can discharge water collected inside a casing to the outside, reduce leakage of noise, and reduce entry of foreign matter from outside. The work machine includes a bottom portion cover forming a portion of a casing, and the bottom portion cover includes: at least two ribs and a bead (strengthening structure portions) that are formed substantially perpendicular to a bottom surface of the bottom portion cover; and a drain hole located in a connecting portion connecting the bottom surface of the bottom portion cover and a water-discharging rib among the at least two ribs. An upper portion of the water-discharging rib is located over the drain hole.

Abstract: Method for diagnosing at least one exhaust gas sensor (22;24;26) of an internal combustion engine (10) disposed in an exhaust duct (21), where ambient air (12) is actively introduced into the exhaust duct (21) by means of a device (27), when an operating state is present in which the internal combustion engine (10) does not produce an exhaust gas mass flow, and the diagnosis of the at least one exhaust gas sensor (22;24;26) disposed in the exhaust duct (21) is subsequently carried out.

Abstract: A vehicle brake system, including: a first-braking-force control mechanism configured to control a first braking force, a second-braking-force control mechanism configured to control a second braking force, an abnormal-state detecting device configured to detect whether the first-braking-force control mechanism is in an abnormal state, a pseudo-abnormal-state detecting device configured to detect whether the first-braking-force control mechanism is in a pseudo abnormal state in which the first-braking-force control mechanism is suspected to be in the abnormal state, and a controller including a pseudo abnormal state controller configured to control the second-braking-force control mechanism in an operating state of the first-braking-force control mechanism so as to control the second braking force when the pseudo-abnormal-state detecting device detects that the first-braking-force control mechanism is in the pseudo abnormal state.

Abstract: A vehicle control device that can appropriately recognize a direction of a vehicle is provided. The vehicle control device includes: an image acquirer configured to acquire an image obtained by imaging a space outside of a vehicle; an object detector configured to detect, through image processing, a plurality of types of objects including a road structure and a moving object shown in the image; a reference line setter configured to select one type of object from the plurality of types of objects and to set a reference line based on a direction of the selected type of object; and a vehicle direction estimator configured to estimate an angle which is formed by the reference line and a traveling direction line of the vehicle as a direction of the vehicle relative to a lane in which the vehicle is traveling or is scheduled to travel.

Abstract: To provide a simulation apparatus capable of simulating the performance of a vehicle according to the battery to be mounted. A simulation apparatus (100) includes a battery performance acquisition unit (111) that acquires performance information of a battery that can be mounted on a vehicle, a vehicle information acquisition unit (112) that acquires vehicle information of the vehicle, and a simulation unit (113) that simulates vehicle performance of the vehicle and battery characteristics of the battery based on the performance information of the battery and the vehicle information.

Abstract: A system for estimating an articulation angle of a vehicle combination comprises a motion sensor for sensing one or more linear and/or angular motion quantities of the vehicle combination and a dynamics-based estimator configured to estimate state variables, including the articulation angle on the basis of the sensed motion quantities, wherein the dynamics-based estimator is dependent on one or more masses and moments of inertia of the vehicle combination.

Abstract: A method to control a road vehicle provided with an internal combustion engine having a plurality of cylinders and with a servo-assisted transmission. The control method comprises the steps of: establishing a minimum spark advance which should not be exceeded in order to avoid the risk of knocking or spontaneous ignitions of the mixture; temporarily reducing, during a gear shift in the servo-assisted transmission, a torque generated by the internal combustion engine by setting an actual spark advance, which is smaller than the minimum spark advance, for one single thermodynamic cycle of each cylinder; and cancelling the injection of fuel into each cylinder in the thermodynamic cycle immediately following the thermodynamic cycle carried out with an actual spark advance smaller than the minimum spark advance.

Abstract: A method for situation-based processing of sensor data from a motor vehicle. Sensor data generated by sensors relating to the situation in the surroundings of the motor vehicle is transferred to a processing unit via a bus. The processing unit takes into account the transferred sensor data to determine an information requirement, and generates a request for additional sensor data on the basis of the determined information requirement and the load on the bus, and sends this request to the sensors. A corresponding device is also described.

Abstract: Apparatus, systems, articles of manufacture, and methods to generate acceptability criteria for autonomous systems plans are disclosed. An example apparatus includes a data compiler to compile data generated by the autonomous system into an autonomous system task dataset, a data encoder to encode the dataset for input into a rule distillation neural network architecture, a model trainer to train the rule distillation neural network architecture, an adaptor to adapt the trained rule distillation neural network architecture to a new input data domain using the autonomous system task dataset, a verifier to generate formally verified acceptability criteria, and an inferer to evaluate a control command, the evaluation resulting in an acceptance or rejection of the command.

Abstract: Methods and systems are presented for improving operation of an engine that includes an evaporative emissions system. In one example, the methods and systems adjust an amount of fuel that is delivered to a pre-chamber of an igniter in response to purging fuel vapors and/or an indication of hydrocarbon breakthrough of a carbon filled fuel vapor storage canister.

Abstract: A method for adjusting a fuel mass to be injected into an internal combustion engine. The internal combustion engine including an intake tract, at least one cylinder, and an exhaust tract. In the method, an air mass introduced into the internal combustion engine is ascertained and a fuel mass to be injected into the internal combustion engine is determined. An air-fuel ratio in the exhaust tract of the internal combustion engine is determined which is adjusted in time. Based on the time-adjusted air-fuel ratio and the calculated fuel mass to be injected, a first wall film fuel mass is calculated and the fuel mass to be injected is adjusted based on the first wall film fuel mass.