A filling device for dosed filling of a product from a product storage container into product dose receiving containers provided in a disposable isolator so to be protected against contamination. The device includes means for holding the product storage container together with the contents outside of the disposable isolator. The device includes a controllable product removal device for a dosed removal of the product from the product storage container. The device includes a product dispensing device for the dosed dispensing of the product to the product dose receiving containers. The device includes a line assembly interconnecting the product storage container and the product dispensing device to conduct the product to the product dispensing device. The device includes at least one ultrasonic flowmeter outside of the disposable isolator fixed to the outside of the line assembly to detect the flow rate. The device includes a controller for measuring the product dose.

Pumping and water distribution systems for pools/spas, and methods for control thereof are provided. A system includes a pump including a variable speed motor, a controller configured to control the speed of the motor, a plurality of pool/spa components, a plumbing subsystem placing the components in fluidic communication with the pump, and a plurality of control valves switchable between an open position and a closed position. Each of the control valves is associated with one of the components, positioned in the plumbing subsystem between the associated component and the pump to control the flow of fluid to the associated component, and is configured to provide a specific flow rate of fluid to the associated component based on a set system pressure when in the open position. The controller adjusts the speed of the motor to adjust the fluid pressure within the plumbing subsystem to match the set system pressure value.

A perfusion chamber for use in a phantom includes a waterproof housing containing a porous material defining fluid paths between pores and tubular channels within the porous material. A reservoir for use in a phantom, a pump mechanism for use within the bore of an MRI scanner, a phantom for use in an MRI scanner, and a method for calibrating a scanning device are disclosed. Also disclosed is apparatus for validating images of a phantom that includes: one or more sensors for coupling to a phantom to be imaged; a control/logging system configured to: collect sensor data during imaging of the phantom and pass this as input to a computer model; compare the image data with reference image data produced using the computer model; and return a pass score depending on the comparison. A system and method for verifying images of a phantom are also disclosed.

A motor of an electric submersible pump (ESP) is positioned in a wellbore. Measured data is received from one or more sensors. A first deep learning model running on a motor controller of the ESP determines first operating parameters or first operating conditions for the ESP based on the measured data. The motor controller sends the first operating parameters or first operating conditions to a centralized computer system. A second deep learning model running on the centralized computer system determines second operating parameters or second operating conditions associated with the ESP based on the first operating parameters or first operating conditions. The centralized computer system sends the second operating parameters or second operating conditions to the motor controller. The motor controller adjusts operation of the motor of the ESP based on the second operating parameters or second operating conditions.

In accordance with at least one aspect of this disclosure, a variable displacement pump system can include, a variable displacement pump disposed in a main line and configured to supply pressure to receive a low pressure fluid and to output a high pressure fluid. The main line can connect a hydraulic fluid source to a plurality of system actuators, where the variable displacement pump is disposed in the main line between the hydraulic fluid source and the plurality of system actuators to pressurize the hydraulic fluid.

A connecting device includes a substantially cylindrical or tubular body provided, at one of its ends, with an outer perimeter projection and co-operative with a duct of channel of a cylinder cap. The device is preferably producible with steel aluminum alloy, or another metal alloy with similar structural and thermal properties mainly due to the stresses it may suffer during use. The device is configured to be able to absorb tolerance variations and to have a resilience capable of providing resistance at the time when a connection undergoes mechanical stresses of performance, especially torsion.

A pumping system for fracking fluid is designed to provide nearly constant flow rate. The pumping system includes a set of linear actuator pumping units, each driven by at least one electric motor. Each pumping unit includes a hollow threaded shaft driven by the linear actuator, two hollow cylinders fixed to an interior of the hollow shaft, and hollow pistons in each of the hollow cylinders. The hollow cylinders and hollow pistons form two pumping chambers. A first pumping chamber expels fluid when the linear actuator is moving in a first direction and a second pumping chamber that expels fluid when the linear actuator is moving in an opposite direction. The speeds of the actuators are coordinated such that a total flow rate of the pumping system is substantially constant.

Embodiments provide functionality to control real-world mechanical systems through the creation and deployment of machine learning models. An embodiment creates the machine learning model by extracting (i) an indication of efficiency and (ii) values of operational characteristics of one or more devices from one or more characteristic curves. Each characteristic curve corresponds to a respective device of one or more devices, in a mechanical system, functioning at a given speed. A training data set is created by determining efficiency and values of the operational characteristics for the mechanical system functioning with multiple combinations of the one or more devices operating at each of a plurality of speeds using the extracted indication of efficiency and extracted values of the operational characteristics. In turn, the machine learning model is trained with the created training dataset. Training configures the machine learning model to predict efficiency of the mechanical system based on operating data.

A method for determining a current wear (w) of a hydrostatic pump, particularly of a radial piston pump, with a variable-speed drive, where the pump is connected to a fluid passage, in which a fluid is pumped by the pump to create a current actual volume flow in the fluid passage. A current actual volume flow (Q.sub.act) is determined, by measuring the volume flow in the fluid passage at a predetermined drive-vector, a computed volume flow (Q.sub.comp) is determined, by a first computational method, at the predetermined drive-vector, and the current wear (w) of the pump is determined, by a second computational method, which relates the current actual volume flow (Q.sub.act) to the computed volume flow (Q.sub.comp).

A fault control protects a pump-motor assembly from monitored faults. The pump-motor assembly includes an electrical motor mechanically coupled to a pump. The fault control determines a speed of the motor. If the speed is determined to be less than a minimum speed, the fault control generates a fault signal to affect the operation of the motor. The fault control can also determine if a phase of the power provided to the motor is missing based on vibrations sensed by a vibration transducer. The fault control can also determine temperature faults based on signals from two thermocouples, including determination of loss of inlet or discharge flow.