Abstract: A method for controlling a controlled system by a control device, the method may include transmitting multiple actuation signals to multiple degree of freedom (DOF) points of the controlled system; wherein the multiple actuation signals comprise multiple alternating current (AC) components that are mutually orthogonal, measuring at least one feedback signal from at least one probe point of the controlled system; wherein a number of DOF points exceeds a number of the at least one probe point; determining, based upon the at least one feedback signal, values of line search pulses to be sent to the multiple DOF points during at least one line search iteration; and performing the at least one line search iteration.

Abstract: Systems and methods are disclosed for enforcing at least one rule associated with a geofence. At least one device is constructed and configured in network communication with a server platform and a database. The server platform defines at least one geofence for a region of interest and specifies at least one rule associated with the at least one geofence, thereby creating a rule-space model for the region of interest. The at least one geofence comprises a multiplicity of geographic designators with each geographic designator assigned with a unique IPv6 address. The at least one device receives at least one notification signal regarding the at least one rule from the at least one server platform and implements the at least one rule when the at least one device is within a predetermined distance from the at least one geofence for the region of interest.

Abstract: Systems and methods are disclosed herein for optimizing harvester yield. In an embodiment, a controller receives a pre-harvest image from a front-facing camera of a harvester. The controller inputs the pre-harvest image into a model, and receives as output from the model a predicted harvest yield. The controller receives, from an interior camera of the harvester, a post-harvest image including the plants as harvested. The controller inputs the post-harvest image into a second model and receives, as output, an actual harvest yield of the plants as-harvested. The controller determines that the predicted harvest yield does not match the actual harvest yield, and outputs a control signal.

Abstract: A method for tagging entities in a building automation system (BAS), the method including identifying, by a processing circuit, a first entity of one or more entities in a system library in response to receiving an indication to add the one or more entities to the BAS, wherein the system library includes a number of relationships between a number of tags and a number of entities. The method further including determining, by the processing circuit, one or more tags associated with the first entity based on the system library, determining, by the processing circuit, a tag type for each of the one or more tags based on a tag dictionary, and adding, by the processing circuit, the one or more tags to the first entity based on the tag type of each of the one or more tags.

Abstract: Described embodiments provide systems and methods for inferring a network type and network conditions. The system includes a packet capturing engine configured to capture a plurality of network packets from a plurality of TCP network connections. The system includes a packet analyzer configured to analyze the plurality of network packets to generate a plurality of metrics. The system includes a network classifier configured to infer network types of the plurality of TCP connections based on the plurality of metrics and at least one classification model. The system also includes a conditions ranking engine configured to estimate a level of network congestion for each TCP connection based on the plurality of metrics and the network types.

Abstract: Systems and methods for a control system for controlling a machine including a first controller to generate a first control command according to an objective of control. A second controller to generate a control input as a combination of a second control command and a third control command. Wherein the second controller generates the second control command according to the objective of control, and generates the third control command using a product of a gain with a difference between the first control command and the second control command. A motor to control the machine according to the control input.

Abstract: An information processing method includes: a second device acquires identification information of a commodity in a video; the second device acquires corresponding advertisement information according to the identification information of the commodity; and the second device contains the advertisement information in a first read response, and sends the first read response to a fourth device. An information processing apparatus and a device are also disclosed.

Abstract: A method for controlling a controlled system by a control device, the method may include transmitting multiple actuation signals to multiple degree of freedom (DOF) points of the controlled system; wherein the multiple actuation signals comprise multiple alternating current (AC) components that are mutually orthogonal; measuring at least one feedback signal from at least one probe point of the controlled system; wherein a number of DOF points exceeds a number of the at least one probe point; determining, based upon the at least one feedback signal, values of line search pulses to be sent to the multiple DOF points during at least one line search iteration; and performing the at least one line search iteration.

Abstract: Various embodiments include methods for performing temperature calibration of a first temperature sensitive unit with an electronic device having a first processing unit that is thermally coupled to the first temperature sensitive unit. Various embodiments may include determining a current temperature of the first temperature sensitive unit, determining a processing load for the first processing unit based on the current temperature and a target temperature, applying the determined processing load to the first processing unit to vary a temperature of the first temperature sensitive unit, and determining a temperature bias for the first temperature sensitive unit at the temperature of the first temperature sensitive unit based on an output of the first temperature sensitive unit.

Abstract: Systems and methods for creating a data-driven attribution model are described. A processor identifies visits to a website. The processor identifies a path for each visitor identifier associated with the visits. The processor determines, for each path type associated with the identified paths, a path-type conversion probability based on a number of visits corresponding to the path type that resulted in a conversion. The processor calculates, for each of a plurality of the path types, a counterfactual gain for each event based on a conversion probability of the given path type and a conversion probability of a path type that does not include the event for which the counterfactual gain is calculated. The processor determines, for each event, an attribution credit based on the calculated counterfactual gain of the event. The processor then stores the attribution credits of each of the events.

Abstract: Aspects of the present disclosure are directed towards a method of electronic verification of motion data. This includes collecting a first set of motion data that corresponds to a first set of motion characteristics generated from physically moving a hardware element of a computer ending upon inserting the hardware element of the computer into a computer chassis. This can further include determining an approved set of motion data and comparing the first set of motion data to the approved set of motion data. This can further include determining a difference between the first set of motion data and the approved set of motion data. This can further include determining that the difference does not satisfy a threshold. This can further include executing a reaction sequence in the computer, in response to determining that the difference does not satisfy the threshold.

Abstract: The present invention is a system and method for performing ethnicity classification based on the facial images of people, using multi-category decomposition architecture of classifiers, which include a set of predefined auxiliary classifiers that are specialized to auxiliary features of the facial images. In the multi-category decomposition architecture, which is a hybrid multi-classifier architecture specialized to ethnicity classification, the task of learning the concept of ethnicity against significant within-class variations, is handled by decomposing the set of facial images into auxiliary demographics classes; the ethnicity classification is performed by an array of classifiers where each classifier, called an auxiliary class machine, is specialized to the given auxiliary class. The facial image data is annotated to assign the age and gender labels as well as the ethnicity labels.

Abstract: A controlling method for protecting an electronic apparatus, performed by the electronic apparatus to determine whether the system temperature thereof is overheated, so as to switch the electronic apparatus into a low-power operation mode when the system temperature is overheated. The controlling method is to monitor an electronic component of the electronic apparatus, so as to obtain the current temperature and the current working power of the electronic component and to determine whether the system temperature is overheated according to the current temperature and the current working power. When the system temperature is overheated, an overheating signal is generated to switch the electronic apparatus into the low-power operation mode.

Abstract: Specification of a time is received from a device that uses an in-home-presence probability calculation system, a probability that a person is at home at the specified time is calculated on the basis of a specified operation time and a specified correlation when the specified operation time is a time within a period of a certain time ending at the time at which the specification has been received, and information as to whether or not a person is at home is output to the device on the basis of the calculated probability.

Abstract: A fuzzy control method and apparatus for a signal receiving part in a high speed WDM system are provided, wherein, the method comprises the following steps: step A, obtaining related information of each device in a receiving system and working environment parameter information of the receiving system; step B, according to the related information of each device and the working environment parameter information, finding out fuzzy control parameters which best match the related information of each device and the working environment parameter information from a fuzzy control parameter table stored in the system, and controlling the parameters of each device in the receiving system according to the fuzzy control parameters to make the system reach the best receiving balancing point. The method and apparatus can simplify the adjusting steps of the receiver and save the adjusting time.

Abstract: This invention provides a system and method of Advanced Process Control for optimal operation of multi-unit plants in large scale processing and power generation industries. The invention framework includes the following components: continuous real time dynamic process simulation, automatic coefficient adjustment of dynamic and static process models, automatic construction of transfer functions, determination of globally optimal operating point specific to current conditions, provision of additional optimal operating scenarios through a variety of unit combinations, and calculation of operational forecasts in accordance with planned production.

Abstract: A path display apparatus includes a first position command acquiring unit that acquires first position command for motors, a first position feedback acquiring unit that acquires first position feedback of each of the motors, a correction data acquiring unit that acquires correction data generated for each of the motors, a second position command calculating unit that subtracts the correction data from the first position command to calculate a second position command, a second position feedback calculating unit that subtracts the correction data from the first position feedback to calculate second position feedback, a command path display unit that displays a command path of the tip point of the tool, based on the second position command; and a feedback path display unit that displays a feedback path of the tip point of the tool, based on the second position feedback.

Abstract: The disclosure provides an HVAC data processing and communication network and a method of manufacturing the same. In an embodiment, the HVAC data processing and communication network includes at least one environmental sensor, at least one subnet and a subnet controller. The subnet controller is configured to discover the at least one environmental sensor, the at least one subnet and at least one damper controller. The subnet controller is further configured to set up the network for zoned operation in the event that at least two of the at least one environmental sensor are discovered.

Abstract: A present invention relates to a novel hybrid intelligent control system and method for power generating apparatuses, in which the control system comprises: a fuzzy sliding mode speed controller, embedded with a fuzzy inference mechanism so as to be used for controlling the speed of a power generating apparatus; and a radial basis function network (RBFN) pitch controller, being embedded with an on-line training RBFN so as to be used for controlling the pitch angle of a turbine coupled to the power generating apparatus. In a variable-speed energy conversion system using the aforesaid control system, the turbine can be driven to operate at its maximum efficiency by adjusting its blade pitch angle in response to the variation of the input flowing into the turbine, while allowing the shaft speed of the power generating apparatus to be controlled by a fuzzy interference mechanism so as to achieve its maximum power output.

Abstract: The parallel kinematic machine (PKM) trajectory planning method is operable via a data-driven neuro-fuzzy multistage-based system. Offline planning based on robot kinematic and dynamic models, including actuators, is performed to generate a large dataset of trajectories, covering most of the robot workspace and minimizing time and energy, while avoiding singularities and limits on joint angles, rates, accelerations and torques. The method implements an augmented Lagrangian solver on a decoupled form of the PKM dynamics in order to solve the resulting non-linear constrained optimal control problem. Using outcomes of the offline-planning, the data-driven neuro-fuzzy inference system is built to learn, capture to and optimize the desired dynamic behavior of the PKM. The optimized system is used to achieve near-optimal online planning with a reasonable time complexity. The effectiveness of the method is illustrated through a set of simulation experiments proving the technique on a 2-degrees of freedom planar PKM.

Abstract: Metrics representing a combined measure of power used by a central processing unit (CPU) and power used by a graphics processing unit (GPU) are compared to a shared supply power and thermal power budgets. Power used by the CPU and power used by the GPU are regulated in tandem using a fuzzy logic control system that can implement fuzzy rules that describe the management within thermal and supply power design constraints of the platform.

Abstract: A computerized method of assigning a building automation system point type to a plurality of unclassified data points is provided. The method includes receiving unclassified data points and attributes for each data point. The method includes receiving classifications for a first subset of the unclassified data points. Each classification associates a data point with a building automation system point type. The method includes generating a term set containing substrings that appear in the attributes. The method includes generating a first matrix describing a frequency that the substrings appear in the attributes. The method includes calculating an indicator of a probability that the presence of the selected substring results in the data point belonging to the selected point type. The method includes assigning a point type to a second subset by finding the substring and potential point type pair having the greatest indication of probability.

Abstract: Anticipatory logistics is used to predict observable events and respond to the predictions of the observable events in the control of automated equipment that perform highly repetitive functions such as elevator cars. A set of table entries is obtained, and the table entries are metricized and stored as cell entries. All cell entries are normalized. Ten weighted values to the cell entries are initialized. An algorithmically defined subset of weighted values is normalized and an instruction is selected based on the computed dependency using an algorithm incorporating uniform chance selection for exploratory optimization, such as the Mersenne Twister algorithm. Here, the search space is delimited by careful selection of the salient variables as well as by the algorithm itself, which only relies on chance to find truly novel solutions as time (and space) permit.

Abstract: An industrial truck having height-adjustable load bearing means, lifting height controls in which a plurality of predetermined lifting heights are saved, a lifting height detection system for the load bearing means that detects an actual value of the lifting height and provides it to the lifting height controls, and a control unit that allows the lifting height of the load bearing means to be manually adjusted at different speeds, wherein the lifting height controls move the load bearing means to one of the predetermined lifting heights when the speed for adjusting the load bearing means specified by the control unit falls below a predetermined threshold, wherein the lifting height assumed by the lifting height controls corresponds to the lifting height of the predetermined lifting heights that most closely approximates the actual value of the lifting height in the direction in which the load bearing means is moving.

Abstract: A system and method are provided for integrated management of a biofuel distillation process and a biofuel dehydration process of a biofuel production process, comprising a dynamic multivariate model-based controller coupled to a dynamic multivariate predictive model. The model is executable to: receive distillation and dehydration process information including biofuel compositions, receive an objective for biofuel production output from the distillation and dehydration processes, e.g., target product composition, production rate, and/or feed rate, and generate model output comprising target values for a plurality of manipulated variables related to the distillation and dehydration processes in accordance with the objective. The controller is operable to dynamically control the biofuel production process by adjusting the plurality of manipulated variables to the model-determined target values in accordance with the objective for biofuel production.

Abstract: One or more techniques are provided for the sharing of variable trajectories between multiple controllers in a control system. In general, the present technique is based upon the sharing of predicted desired variable trajectories between multiple controllers requiring a common input variable. In one embodiment, a common input variable is shared between two controllers, wherein one controller is tuned to have dominant control with regard to the shared variable. Each controller determines and communicates their own desired trajectory for the shared variable to the other controller and in doing so, the constraints associated with each controller are shared and honored by the other controller. Based on the communicated trajectories, the dominant controller may exercise control over the shared variable, thus improving overall process control.

Abstract: The disclosure presents categorization of users into groups comprising expert users and novice users. A system and method analyzes the users' inputted data in helpdesk troubleshooting software to determine the deviation of novice users from expert users, or the deviation of novice users to a preconfigured behavior as determined by management policy. Other embodiments are also disclosed.

Abstract: A system for optimizing a power plant includes a chemical loop having an input for receiving an input parameter (270) and an output for outputting an output parameter (280), a control system operably connected to the chemical loop and having a multiple controller part (230) comprising a model-free controller. The control system receives the output parameter (280), optimizes the input parameter (270) based on the received output parameter (280), and outputs an optimized input parameter (270) to the input of the chemical loop to control a process of the chemical loop in an optimized manner.

Abstract: Real-time condition-based analysis is performed on a machine for providing diagnostic and prognostic outputs indicative of machine status includes a signal processor for receiving signals from sensors adapted for measuring machine performance parameters. The signal processor conditions and shapes at least some of the received signals into an input form for a neural network. A fuzzy adaptive resonance theory neural network receives at least some of the conditioned and shaped signals, and detects and classifies a state of the machine based upon the received conditioned and shaped signals, and upon a predetermined ontology of machine states, diagnostics, and prognostics. The neural network can also determine from the machine state a health status thereof, which can comprise an anomaly, and output a signal representative of the determined health status. A Bayesian intelligence network receives the machine state from the neural network and determines a fault probability at a future time.

Abstract: The present invention relates to a robot and a control method adapted for the robot. The method includes a) measuring time; b) performing a normal biological action when the time reaches a beginning time of a biological function; c) judging whether an instruction is received while during the biological function; d) if the instruction is received while during the biological function, fetching an action adjustment parameter of the biological function and performing an output; e) after the output is finished, resuming performing the normal biological action; and f) stopping the normal biological action when the time reaches an ending time of the biological function.

Abstract: An industrial process control transmitter includes a first input configured to couple to a first sensor, and a second input configured to couple to a second sensor. Measurement circuitry is configured to couple to the first and second sensors and provide an output related to a sensed process variable. A multiplexer is configured to selectively couple the first and second sensors to the measurement circuitry. An equalizer circuit is coupled to the first and second sensors and configured to equalize a voltage potential between the first sensor and the measurement circuitry.

Abstract: A multilevel semiotic and fuzzy logic user and metadata interface means includes: an interactive user interface means comprising at least one multilevel semiotic means addressable by a user and a fuzzy logic descriptor set module for storing multiple fuzzy logic descriptor sets; a metadata layer for linking said multilevel semiotic means to interactivity points present in content of the multimedia representation and defined by the metadata layer such that each level of each of the multilevel semiotic means identifies an interactivity point in the content and allows by selection of the interactivity point to perform a selectively varying content manipulation and to receive a resulting interactive presentation of content according to the selection: and a user control device for addressing the multilevel semiotic means.

Abstract: Methods and apparatuses to manage working states of a data processing system. At least one embodiment of the present invention includes a data processing system with one or more sensors (e.g., physical sensors such as tachometer and thermistors, and logical sensors such as CPU load) for fine grain control of one or more components (e.g., processor, fan, hard drive, optical drive) of the system for working conditions that balance various goals (e.g., user preferences, performance, power consumption, thermal constraints, acoustic noise). In one example, the clock frequency and core voltage for a processor are actively managed to balance performance and power consumption (heat generation) without a significant latency. In one example, the speed of a cooling fan is actively managed to balance cooling effort and noise (and/or power consumption).

Abstract: The control optimization method for helicopters carrying suspended loads during hover flight utilizes a controller based on time-delayed feedback of the load swing angles. The controller outputs include additional displacements, which are added to the helicopter trajectory in the longitudinal and lateral directions. This simple implementation requires only a small modification to the software of the helicopter position controller. Moreover, the implementation of this controller does not need rates of the swing angles. The parameters of the controllers are optimized using the method of particle swarms by minimizing an index that is a function of the history of the load swing. Simulation results show the effectiveness of the controller in suppressing the swing of the slung load while stabilizing the helicopter.

Abstract: A machine tool monitoring device of a machine tool for machining a work piece, includes a signal unit (24) provided for an ultra-broad-band operation. The signal unit (24) processes a signal (32, 34), which has a sequence (46) of pulses (48) and includes an arithmetic-logic unit (40) for associating a detected signal (34) with a use situation (52, 58) by means of a fuzzy logic-based and/or neural logic-based signal processing. The signal unit (24) preferably has a programmable data base (44) in which a use situation (52, 58) in a machining process is associated with a procedure (56, 60) for changing the machining process.

Abstract: The fuzzy logic-based control method for helicopters carrying suspended loads utilizes a controller based on fuzzy logic membership distributions of sets of load swing angles. The anti-swing controller is fuzzy-based and has controller outputs that include additional displacements added to the helicopter trajectory in the longitudinal and lateral directions. This simple implementation requires only a small modification to the software of the helicopter position controller. The membership functions govern control parameters that are optimized using a particle swarm algorithm. The rules of the anti-swing controller are derived to mimic the performance of a time-delayed feedback controller. A tracking controller stabilizes the helicopter and tracks the trajectory generated by the anti-swing controller.

Abstract: A process is proposed for continuously operating a plant for preparing acetylene from hydrocarbons by partial oxidation, cleavage in an arc or pyrolysis of hydrocarbons to obtain a reaction gas mixture which is conducted through one or more compressors, the pressure of the reaction gas mixture on the suction side of the compressor being controlled within a predefined range by means of a conventional controller, which comprises additionally using a higher-level model-supported predictive controller which reacts to abrupt changes in the mass flow rate of the reaction gas mixture.

Abstract: A control system (300) for optimizing a power plant includes a chemical loop having an input for receiving an input signal (369) and an output for outputting an output signal (367), and a hierarchical fuzzy control system (400) operably connected to the chemical loop. The hierarchical fuzzy control system (400) includes a plurality of fuzzy controllers (330). The hierarchical fuzzy control system (400) receives the output signal (367), optimizes the input signal (369) based on the received output signal (367), and outputs an optimized input signal (369) to the input of the chemical loop to control a process of the chemical loop in an optimized manner.

Abstract: The disclosure presents categorization of users into groups comprising expert users and novice users. A system and method analyzes the users' inputted data in helpdesk troubleshooting software to determine the deviation of novice users from expert users, or the deviation of novice users to a preconfigured behavior as determined by management policy. Other embodiments are also disclosed.

Abstract: Process control system for detecting abnormal events in a process having one or more independent variables and one or more dependent variables. The system includes a device for measuring values of the one or more independent and dependent variables, a process controller having a predictive model for calculating predicted values of the one or more dependent variables from the measured values of the one or more independent variables, a calculator for calculating residual values for the one or more dependent variables from the difference between the predicted and measured values of the one or more dependent variables, and an analyzer for performing a principal component analysis on the residual values. The process controller is a multivariable predictive control means and the principal component analysis results in the output of one or more scores values, T2 values and Q values.

Abstract: One or more techniques are provided for the sharing of variable trajectories between multiple controllers in a control system. In general, the present technique is based upon the sharing of predicted desired variable trajectories between multiple controllers requiring a common input variable. In one embodiment, a common input variable is shared between two controllers, wherein one controller is tuned to have dominant control with regard to the shared variable. Each controller determines and communicates their own desired trajectory for the shared variable to the other controller and in doing so, the constraints associated with each controller are shared and honored by the other controller. Based on the communicated trajectories, the dominant controller may exercise control over the shared variable, thus improving overall process control.

Abstract: A process is proposed for continuously operating a plant for preparing acetylene from hydrocarbons by partial oxidation, cleavage in an arc or pyrolysis of hydrocarbons to obtain a reaction gas mixture which is conducted through one or more compressors, the pressure of the reaction gas mixture on the suction side of the compressor being controlled within a predefined range by means of a conventional controller, which comprises additionally using a high-level model-supported predictive controller which reacts to abrupt changes in the mass flow rate of the reaction gas mixture.

Abstract: In a control loop for regulating a combustion process in a plant (e.g., a power-generating plant, a waste incineration plant or a cement works) having a controlled system for converting material by way of the combustion process while supplying air, with at least one flame body being formed, and having at least one observation device for imaging the flame body, other sensors for determining the input data, at least one adjustment device that can be controlled by output data for supplying at least material and/or air, and a computer for evaluating the input data in relation to target values and for determining the output data by using a current process model, the computer has a feature extraction module that extracts features from the input data using an information measure. The features are informative for the target values, and are for use in an alternative process model.

Abstract: A method of fuzzy control for adjusting a semiconductor machine comprising: providing measurement values from first the “parameter of a pre-semiconductor manufacturing process”, second the “parameter of the semiconductor manufacturing process”, and third the “operation parameter of the semiconductor manufacturing process”; performing a fuzzy control to define two inputs and one output corresponding to the measurement values, wherein the difference between the first and third values, and the difference between the second and third values, forms the two inputs, then from the two inputs one target output is calculated by fuzzy inference; finally, determining if the target output is in or out of an acceptable range. Whereby the target output is the “machine control parameter of the semiconductor manufacturing process” and when within an acceptable range is used for adjusting the semiconductor machine.

Abstract: A system and computer readable medium for discovering gene regulatory models using relational fuzzy models. A system is provided that includes a data selection system that clusters gene expression data into a set of clusters and identifies a representative subset of genes from the set of clusters; and a relational fuzzy modeling system that builds a relational fuzzy model using the representative subset.

Abstract: Systems and methods of adaptive control for uncertain nonlinear multi-input multi-output systems in the presence of significant unmatched uncertainty with assured performance are provided. The need for gain-scheduling is eliminated through the use of bandwidth-limited (low-pass) filtering in the control channel, which appropriately attenuates the high frequencies typically appearing in fast adaptation situations and preserves the robustness margins in the presence of fast adaptation.

Abstract: A PID controlling apparatus and method for providing a control value to a control object according to the difference between an output value of the control object and a target value are provided, in which an error calculator outputs an error value between the target value and the output value of the control object, a PID operator calculates a proportional value, an integral value, and a derivative value of the error value, calculates the control value using the proportional value, the integral value, and the derivative value, and outputs the control value to the control object, a first sampler samples the output value of the control object a plurality of times with respect to the target value and outputs a sampled output value, and a controller controls the PID operator to repeat a PID operation and output the control value according to a sampling period of the first sampler.

Abstract: A robot localization system is provided. The robot localization includes a robot, which moves within a predetermined space and performs predetermined tasks, and a docking station corresponding to a home position of the robot. The docking station includes a first transmitting unit, which transmits a sound wave to detect a position of the robot; and a second transmitting unit, which transmits a synchronizing signal right when the sound wave is transmitted.

Abstract: Metrics representing a combined measure of power used by a central processing unit (CPU) and power used by a graphics processing unit (GPU) are compared to a shared supply power and thermal power budgets. Power used by the CPU and power used by the GPU are regulated in tandem using a fuzzy logic control system that can implement fuzzy rules that describe the management within thermal and supply power design constraints of the platform.

Abstract: A multipurpose hemofiltration system and method are disclosed for the removal of fluid and/or soluble waste from the blood of a patient. The system continuously monitors the flow rates of drained fluid, blood, and infusate. When necessary, the pumping rates of the infusate, drained fluid and blood are adjusted to remove a preselected amount of fluid from the blood in a preselected time period. A supervisory controller can monitor patient parameters, such as heart rate and blood pressure, and adjust the pumping rates accordingly. The supervisory controller uses fuzzy logic to make expert decisions, based upon a set of supervisory rules, to control each pumping rate to achieve a desired flow rate and to respond to fault conditions. An adaptive controller corrects temporal variations in the flow rate based upon an adaptive law and a control law.