A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.

The subject matter of this specification can be embodied in, among other things, a controller apparatus that includes a digital controller configured to provide a digital position signal based on a setpoint and a differential analog feedback signal, and a converter circuit configured to provide a differential analog electrohydraulic servo valve position control signal based on the digital position signal, and provide the differential analog feedback signal based on the differential analog electrohydraulic servo valve position control signal.

Methods and apparatus to detect and/or recover from failures in valve control devices. An apparatus includes an input signal generator to provide a digital input signal to a first converter. The first converter corresponds to one of a supply converter or an exhaust converter. The supply converter controls actuation of a supply relay to deliver pressurized fluid to an actuator operatively coupled to a valve in a process control system. The exhaust converter to control actuation of an exhaust relay to exhaust the pressurized fluid from the actuator. The digital input signal triggers application of a current to the first converter to open the first converter. The apparatus further including a failure detector to: determine a difference in at least one of a pressure in the actuator or a position of a flow control member in the valve; and detect a failure when the difference satisfies a failure threshold.

Provided is a process including: receiving a tank-nearly-full message indicating that a tank at an oil or gas related facility is or will be ready for a truck to unload and transport fluid accumulating in the tank; in response to the tank-nearly-full message, creating a tank-run record; sending a description of the tank-run to a mobile device of a driver of an oilfield truck; receiving, from the mobile device of the driver of the oilfield truck, a tank-run claimed message indicating that the driver will drive to the oil or gas related facility and transport at least some of the fluid accumulating in the tank; and after the tank-run claimed message, performing steps including: confirming that the tank-run has not yet been claimed; after the confirmation, designating the tank-run as claimed by the driver; and sending confirmation to the mobile device of the driver.

Provided is a process including: receiving a tank-nearly-full message indicating that a tank at an oil or gas related facility is or will be ready for a truck to unload and transport fluid accumulating in the tank; in response to the tank-nearly-full message, creating a tank-run record; sending a description of the tank-run to a mobile device of a driver of an oilfield truck; receiving, from the mobile device of the driver of the oilfield truck, a tank-run claimed message indicating that the driver will drive to the oil or gas related facility and transport at least some of the fluid accumulating in the tank; and after the tank-run claimed message, performing steps including: confirming that the tank-run has not yet been claimed; after the confirmation, designating the tank-run as claimed by the driver; and sending confirmation to the mobile device of the driver.

A system is provided to automatically monitor and control the operation of a microfluidic device using machine learning technology. The system receives images of a channel of a microfluidic device collected by a camera during operation of the microfluidic device. Upon receiving an image, the system applies a classifier to the image to classify the operation of the microfluidic device as normal, in which no adjustment to the operation is needed, or as abnormal, in which an adjustment to the operation is needed. When an image is classified as normal, the system may make no adjustment to the microfluidic device. If, however, an image is classified as abnormal, the system may output an indication that the operation is abnormal, output an indication of a needed adjustment, or control the microfluidic device to make the needed adjustment.

A method of operating a sapling hydrating system for a planting apparatus. The method comprising determining a release pressure of hydrating fluid for a release valve to hydrate a sapling based on a target distribution rate of the hydrating fluid, wherein the target distribution rate is received via an input signal. The method further comprising controlling a supply pressure of the hydrating fluid from a pump to be greater than or equal to the release pressure, and controlling an unloading valve fluidly disposed between the pump and a hydrating fluid storage tank. The unloading valve regulating a maximum supply pressure. The method further includes controlling the release valve to provide a first portion of the hydraulic fluid to the release valve at an unloading pressure greater than or equal to the release pressure, and directing the remainder of the hydrating fluid back to the storage tank.

Provided is a process including: receiving a tank-nearly-full message indicating that a tank at an oil or gas related facility is or will be ready for a truck to unload and transport fluid accumulating in the tank; in response to the tank-nearly-full message, creating a tank-run record; sending a description of the tank-run to a mobile device of a driver of an oilfield truck; receiving, from the mobile device of the driver of the oilfield truck, a tank-run claimed message indicating that the driver will drive to the oil or gas related facility and transport at least some of the fluid accumulating in the tank; and after the tank-run claimed message, performing steps including: confirming that the tank-run has not yet been claimed; after the confirmation, designating the tank-run as claimed by the driver; and sending confirmation to the mobile device of the driver.

A system for controlling a plurality of actuators is disclosed. The system includes at least one device for operating the plurality of actuators, at least one processor in communication with the device, and a memory coupled the processor. The memory stores data comprising program code that, when executed by the at least one processor, causes the system to receive as input a profile number indicating a specific test being performed by the system and a profile row indicating a load exerted by the plurality of actuators. The system is further caused to select a predetermined gain output based on the profile number and the profile row from a gain array. The gain array is a matrix containing a plurality of gain values, and the predetermined gain output is selected based on the profile number and the profile row. The system is further caused to determine a control value.

Provided is an information processing device, etc., that provides information which is the basis for quick detection of abnormalities that occur in a device. An information processing device calculates a degree of suitability between observation information and prediction information, the observation information observed for a system suffering an effect from an certain device, the prediction information predicted in accordance with a model for a state of the system; and calculates a difference between manipulation amount to the certain device and predictive manipulation amount predicted for the manipulation amount based on the model, the difference being a difference in case that the degree satisfies a predetermined calculation condition.