Abstract: An energy-saving strategy formulation method for a semi-automatic production line based on model predictive control is performed as follows. max-plus algebra model is constructed, based on which an optimization objective function with the WIP products as discrete elements and sleep start moment and sleep end moment of the automated device as control variables is established. A first unoptimized WIP product is substituted into the optimization objective function, and the optimization objective function is solved to obtain an optimal sequence, in which a first set of values is output as optimization result. Whether all WIP products have been optimized is determined, and if yes, an energy-saving strategy is generated and used to control the automated device, otherwise, the optimization result is treated as disturbance information to be incorporated into the modeling. An energy-saving strategy formulation system is also provided.

Abstract: The present disclosure relates to a method, an electronic device, and a computer program product for monitoring a field device. For example, a method for monitoring a field device is provided. The method may include receiving facility information data associated with locations of a group of field devices and a sensing data set acquired by a sensing apparatus arranged near the group of field devices. The method may further include determining, according to a determination that sensing data associated with at least one field device in the group of field devices in the sensing data set is abnormal, a target location of the at least one field device based on the facility information data. In addition, the method may further include generating navigation information from a source location where a user is located to the target location.

Abstract: Techniques are provided for allocating resources for one or more workloads. One method comprises obtaining a current performance of a workload; determining an adjustment to a current allocation of a resource allocated to the workload by evaluating a representation of a relationship between: (i) the current allocation of the resource allocated to the workload, (ii) a performance metric, and (iii) the current performance of the workload; and initiating an application of the determined adjustment to the current allocation of the resource for the workload. The performance metric may comprise a nominal value of a predefined service metric and the current performance of the workload may comprise a current value of a variable that tracks a given predefined service metric of the workload. An amount (or percentage) of the adjustment permitted for each iteration may be controlled. A sum of allocated resources can be constrained to an amount of available resources.

Abstract: According to an embodiment of the present invention, an approach accurately detects anomalies or outliers of a time-series dataset. A method for identifying whether a particular data element of the time-series dataset is an outlier comprises predicting a value for that particular data element and obtaining a threshold value that defines, relative to the predicted value, whether an actual value of the data element is an outlier. In an aspect of a present invention embodiment, the threshold value is generated based on historic error values associated with data elements temporally preceding the particular data element of the time-series dataset.

Abstract: A system and method for managing all of the HVAC components of a building so they operate like one optimized ecosystem. The system and method optimize HVAC operations by predicting HVAC requirements based historical data, weather forecasts and/or occupancy rates. Historical data includes data obtained from an observation phase in which sensor data is collected from the building and used to train the algorithms utilized in the system and method and thereby providing for a more accurate prediction of HVAC requirements. In some embodiments, the systems and methods are configured to predict future required operational parameters using an artificial intelligence engine trained using historical data from the HVAC components.

Abstract: A computer-implemented method for determining a control trajectory for a robotic device. The method includes: performing an information theoretic model predictive control applying a control trajectory sample prior in each time step to obtain a control trajectory for a given time horizon; determining the control trajectory sample prior depending on a data-driven trajectory prediction model which is trained to output a control trajectory sample as the control trajectory sample prior based on an actual state of the robotic device.

Abstract: The invention is a method for detecting aberrant values of an incident wind field in a space located upstream of a lidar sensor. The method comprises acquiring and modelling a measurement rws(k) with the lidar sensor of an incident wind field, by estimating a median mr(k) and a mean absolute deviation dr(k) in real time of measurements of the incident wind field and detecting aberrant values in real time using the estimated median mr(k) and the mean absolute deviation dr(k).

Abstract: A method for predicting an operating anomaly comprises steps of (i) taking an assembly comprising at least a first and a second equipment item, each equipment item comprising a first operating parameter, (ii) recording and storing measurements over time of the first parameters for the first and the second equipment items, (iii) collecting the measurements during or after the completion of at least one part of an operating cycle, (iv) processing the collected measurements to detect a possible malfunction of the first and second equipment items by establishing a coefficient of determination, (v) emitting a first notification indicating the possible malfunction and/or triggering additional steps if the first coefficient of determination is less than a first threshold, and (vi) emitting a second notification and/or adjusting the first threshold if the first coefficient of determination is greater than or equal to the first threshold.

Abstract: A machine learning device that searches for a first parameter of a component of a servo control device that controls a servo motor includes: a solution detection unit that acquires a set of evaluation function values used during machine learning or after machine learning, plots the set of evaluation function values in a search range of the first parameter or a second parameter used for searching for the first parameter, and detects whether a search solution is at an edge of the search range or is in a predetermined range from the edge; and a range changing unit that changes the search range to a new search range of the first parameter or the second parameter based on the estimation made on evaluation function values of an evaluation function expression when the search solution is at the edge of the search range or is in the predetermined range.

Abstract: A method for controlling an energy production and distribution system includes identifying sources that supply input resources, subplants that produce output resources using the input resources, and sinks that consume the output resources. The method includes obtaining a cost function including a cost of producing the output resources and generating a transit time constraint that requires the input resources be sent from the sources to the subplants at a first departure time that occurs before a first arrival time at which the input resources are predicted to be used by the subplants. The method includes solving an optimization problem to determine an amount of the output resources to produce at each of multiple time steps within a time period. Solving the optimization problem includes performing an optimization of the cost function subject to the transit time constraint.

Abstract: A load control device for controlling the power delivered from an AC power source to an electrical load is able to receive radio-frequency (RF) signals from a Wi-Fi-enabled device, such as a smart phone, via a wireless local area network. The load control device comprises a controllably conductive device adapted to be coupled in series between the source and the load, a controller for rendering the controllably conductive device conductive and non-conductive, and a Wi-Fi module operable to receive the RF signals directly from the wireless network. The controller controls the controllably conductive device to adjust the power delivered to the load in response to the wireless signals received from the wireless network.

Abstract: A device for detecting a defect of a rotating arrangement is provided. The rotating arrangement further provides one or more rotating elements. The device includes a measuring unit for measuring a parameter of the rotating arrangement for a predefined time period, a calculation unit for calculating a mean value and a standard deviation of the parameter of the predefined time period and for calculating a threshold based on a sum of the mean value and the standard deviation during the predefined time period, and a detection unit for detecting a defect by comparing a current value of the parameter with the calculated threshold. The calculation unit is configured to adjust the calculated threshold using a stability factor. The stability factor is a variable function of the standard deviation and the mean value. A method for detecting a defect of a rotating arrangement is also provided.

Abstract: An apparatus for automatically tuning a fluid temperature PID (proportional-integral-differential) controller is provided. The apparatus for automatically tuning a fluid temperature PID controller includes: a setter configured to calculate an initial value of a gain of a controller configured to control a fluid temperature by deriving a physical property of the fluid temperature, and a tuner configured to tune the initial value of the gain of the controller using an artificial intelligence neural network algorithm according to a control target.

Abstract: A computer-implemented method of and a system for generating a prediction model and determining an accuracy parameter of a trained decision tree prediction model. The method comprises accessing the trained decision tree prediction model having been generated at least partially based on a set of training objects; generating a subset of random parameters of interest; associating the subset of random parameters of interests with a given leaf; determining a leaf accuracy parameter based on (i) the parameters of interest associated with the given leaf and (ii) the subset of random parameters of interest of the given leaf; and determining the accuracy parameter of the trained decision tree prediction model based on the determined leaf accuracy parameter for each of the leafs of the decision tree.

Abstract: Described herein are a system and techniques for detecting whether biometric data provided in an access request is genuine or a replay. In some embodiments, the system uses an machine learning model trained using genuine and replay sample data which is optimized in order to produce a result set in which results for the genuine samples are pulled closer to a genuine center and results for the replay samples are pushed away from the genuine center. Subjecting input biometric data (e.g., an audio sample) to the trained model results in a classification of the input biometric data as genuine or replay, which can then be used to determine whether or not to verify the input biometric data.

Abstract: There is disclosed a method of and a system for converting a categorical feature value into a numeric representation thereof, the categorical feature being associated with a training object used for training a Machine Learning Algorithm (MLA). The MLA is trained using several models, each model comprising a plurality of decision trees (an ensemble of decision trees). For each model, a respective set of training objects into an ordered list of training objects such that for each given training object there is at least one of: (i) a preceding training object that occurs before the given training object and (ii) a subsequent training object that occurs after the given training object. The method further comprises, for a given categorical feature, using a respective ordered set to generate numeric representation of values of the given categorical feature.

Abstract: The embodiments described herein include one embodiment that provides a control method that includes connecting a first controller to a control system; receiving control system configuration data from a database, in which the configuration data comprises holistic state data of a second controller in the control system; and configuring operation of the first controller based at least in part on the configuration data received.

Abstract: An example method comprises receiving event and alarm data from event logs, failure data, and asset data from SCADA system(s), retrieve patterns of events from the SCADA data, receiving historical sensor data from sensors of components of wind turbines, training a set of models to predict faults for each component using the patterns of events and historical sensor data, each model of a set having different observation time windows and lead time windows, evaluating each model of a set using standardized metrics, comparing evaluations of each model of a set to select a model with preferred lead time and accuracy, receive current sensor data from the sensors of the components, apply the selected model(s) to the current sensor data to generate a component failure prediction, compare the component failure prediction to a threshold, and generate an alert and report based on the comparison to the threshold.

Abstract: Systems and methods for constructing a scoring model and evaluating user credit. An example method for constructing a scoring model may comprise: collecting a plurality of sample datasets, each sample dataset comprising at least one characteristic variable and a corresponding characteristic value; for each characteristic variable, acquiring an interaction index of the characteristic variable with each of one or more other characteristic variables, and determining a clustering index of the characteristic variable according to the interaction indices; selecting a target characteristic variable from the at least one characteristic variable according to the clustering indices of the characteristic variables; dividing the plurality of sample datasets into a plurality of sample dataset subgroups according to the target characteristic variable and the corresponding characteristic value; and constructing a corresponding sub-scoring model for each of the sample dataset subgroups.

Abstract: A method for implementing artificial intelligence agents to perform machine learning tasks using predictive analytics to leverage ensemble policies for maximizing long-term returns includes obtaining a set of inputs including a set of ensemble policies and a meta-policy parameter, selecting an action for execution within the system environment using a meta-policy function determined based in part on the set of ensemble policies and the meta-policy function parameter, causing the artificial intelligence agent to execute the selected action within the system environment, and updating the meta-policy function parameter based on the execution of the selected action.

Abstract: An analytical model training method includes generating a modified set of machine repair records by associating a machine with at least one of i) one or more defects associated with the machine, ii) a repair of the one or more defects, and iii) one or more repair characteristics. An analytical model training system generates a training model based from the modified set of repair records and a set of survey records indicative of reported experience values. The system isolates at least one time-based machine operation parameter associated with machine operation from a set of machine operation records. A modified set of machine operation records is generated that includes a plurality of values associated with the at least one time-based machine operation parameter. An analytical model is configured to output an estimate of customer experience based at least partly on a second set of machine repair records.

Abstract: In an embodiment, a method for optimizing computer machine learning includes receiving an optimization goal. The optimization goal is used to search a database of base option candidates (BOC) to identify matching BOCs that at least in part matches the goal. A selection of a selected base option among the matching BOCs is received. Machine learning prediction model(s) are selected based at least in part on the goal to determine prediction values associated with alternative features for the selected base option, where the model(s) were trained using training data to at least identify weight values associated with the alternative features for models. Based on the prediction values, at least a portion of the alternative features is sorted to generate an ordered list. The ordered list is provided for use in manufacturing an alternative version of the selected base option with the alternative feature(s) in the ordered list.

Abstract: The embodiments relate to assigning data to processors of a file system. Metadata associated with respective blocks of data, and an initial batch of the blocks is assigned to nodes of a file system based on the metadata. Unassigned blocks are selectively assigned to one or more of the nodes. The selective assignment includes constructing a linear regression model based on node data, and determining a value for each node based on the linear regression model. Each value is associated with a predicted load corresponding to a new assignment of one or more unassigned blocks.

Abstract: Systems and methods for improved gas turbine engine performance are disclosed. The method can include receiving an error function for a wide range of fuels. The error function can provide lower heating value (LHV) corrections over the wide range of fuels. The method can include receiving gas turbine engine operation data for a first period of run time on the gas turbine from one or more sensors of the gas turbine engine. The engine operation data can include a performance data points. The method can include determining an optimum LHV based on the engine operation data for the first period of run time and the error function. The method can then include adjusting fuel consumption of the gas turbine engine based on the optimum LHV.

Abstract: A data analysis server holds base-point-added information, wherein the base-point-added information includes a value of an explanatory variable encrypted by first high-performance encryption, a value of a response variable encrypted by a predetermined encryption scheme, and a base point based on frequencies of the value of the explanatory variable in information for learning are associated with one another, wherein the data analysis server: executes decision tree generation processing for generating a decision tree having a leaf node associated with the value of the response variable encrypted by the predetermined encryption scheme, which is included in the base-point-added information; and execute branching rule determine processing in decision tree generation processing without decrypting the value of the explanatory variable and the base point corresponding.

Abstract: A control system for causing an output of a control target to follow a command includes: a first processing device which is a processing device having a first processor and a prediction model that defines a correlation between a state variable with respect to the predetermined control target and a control input to the predetermined control target in the form of a state equation, performs model predictive control using the first processor, and outputs a servo command corresponding to the control input at an initial time point of the prediction interval; and a second processing device which is a processing device having a second processor different from the first processor and a feedback system including controllers to which a feedback signal related to an operation of the predetermined control target is input and receiving the servo command from the first processing device, and performs feedback control using the second processor.

Abstract: Aspects of the present disclosure provide for operations of a key-value tree data structure that: merge key-value sets within a given node by merging and rewriting key blocks of the key-value sets while rewriting or deferring rewrite of value blocks of the merged key-value sets based on whether one or more child nodes of the given node comprise a leaf node; and move one or more portions of the merged key-value set into one or more child nodes of the given node.

Abstract: Systems, methods, and computer-readable medium storing instructions can be used to predict insurance information. One of the methods includes obtaining information about an insured entity. The method includes providing the information to a machine learning system, the machine learning system trained to provide insurance information based on the provided information. The method includes in response to providing the information, receiving a prediction of the insurance information. The method also includes adjusting an insurance premium based on the prediction.

Abstract: An environmental conditioning system for conditioning the environment of an occupiable region includes environmental conditioning hardware and a controller. The controller includes an occupancy module configured to receive ingress data associated with occupants entering the occupiable region for each of a first plurality of ingress iterations of a first prescribed time period. The controller further performs a first ingress rolling mean of the ingress data over the first plurality of ingress iterations, and compares at least the first ingress rolling mean to a first occupancy threshold. If the first occupancy threshold is exceeded by the first ingress rolling mean, the controller outputs a start command to the environmental conditioning hardware.

Abstract: A system and method for advanced storage device telemetry. The system includes multiple SSDs. I/O is executed on the SSDs in conjunction with a host software. As the I/O is executed, error log information is stored in a persistent memory as well as in a volatile memory. In various embodiments, granular performance information for the execution of the I/O is also stored in a persistent memory.

Abstract: The disclosure relates to a device that saves water, energy, and money and may record the savings with a software analytics dashboard. The device allows cold water to flow out when the shower is first turned on and slows or shuts water flow once the water is heated and the shower is unoccupied. After the presence of the user is detected, the shower flow may resume.

Abstract: A pseudo-emotion generating system configured to generate pseudo-emotions of a vehicle includes an emotion generating section that generates a pseudo-emotion of the vehicle based on external force information representing an external force applied to the vehicle from outside during travel of the vehicle.

Abstract: A electrical distribution system has been developed to provide a remote central control point for individual circuits, and methods have been developed for retrofitting it to existing service panels or installing it into new service panels. This system provides a power circuit monitoring and control system that fits inside standard residential service panels, both new and retrofitted panels. The entire system can be retrofitted into existing breaker panel systems without the need of removing any permanent structure such as a wall. During this retrofit process, the panel cover on the existing distribution panel is first removed after the power to it is disconnected. The old breaker assembly is removed from the panel, and a circuit controller is then installed in the now available space within the panel. A new service panel enclosure with a circuit breaker assembly is installed directly over top of the enclosure.

Abstract: A method includes acquiring process data collected in an industrial process control and automation system. The method also includes reducing a dimension space of the process data by combining two or more parameters of the process data or examining a frequency response of the process data. The method further includes determining a change in a process based on a change in the process data in the reduced dimension space. The method also includes outputting a result based on the determined change in the process.

Abstract: An apparatus is provided for generating a generalized linear model structure definition by generating a gradient boosted tree model and separating each decision tree into a plurality of indicator variables upon which a dependent variable of the generalized linear model depends. A first number of plurality of decision tree structures each having a maximum tree depth of one (1) is formed, where the first number represents a number of decision tree structures necessary to exhaust all main effects of a plurality of predictor variables on a dependent variable. Successive pluralities of decision tree structures each having a maximum tree depth increased by one (1) as compared to its immediately preceding plurality of decision tree structures are iteratively formed. Each successive plurality of decision tree structures comprises a second number of decision tree structures necessary to exhaust all interactions between the plurality of predictor variables.

Abstract: A control system includes a drive-side control device and a host-side control device. The drive-side control device has a drive-side control structure including a drive-side feedback system and a drive-side control model part and configured so as to be capable of model tracking control in accordance with a control model which the drive-side control model part has. The host-side control device has a host-side control structure including a host-side control model part a host-side correcting signal based on a deviation between an output of the host-side control model part and the operation command signal is fed back to an input side of the host-side control model part, and a corrected command signal generated based on the host-side correcting signal that is fed back and the operation command signal is input to the host-side control model part. The corrected command signal is further input to the drive-side control structure.

Abstract: Heating, ventilation, and air conditioning (HVAC) controllers are described herein. One method includes receiving an approximate relationship between each of a number of controlled and manipulated variables of an HVAC system, designating one of the number of controlled variables as a primary controlled variable, determining operating parameters for each of the number of manipulated variables that maintain the primary controlled variable based, at least in part, on the approximate relationship between the primary controlled variable and each respective manipulated variable, and determining operating parameters for each of the number of manipulated variables that maintain each of the other controlled variables based, at least in part, on the approximate relationship between each respective other controlled variable and each respective manipulated variable and the determined operating parameters for each of the number of manipulated variables that maintain the primary controlled variable.

Abstract: Techniques are described for implementing automated control systems that repeatedly perform automated modifications to control system actuator components' ongoing operations to improve functionality for electrical devices in target systems, such as to reduce power dissipation while using the electrical devices. The described techniques further include synchronizing a particular control system's state improvements with corresponding control system state improvements being performed for one or more other control systems that are each controlling one or more distinct electrical devices in the target system(s), so as to improve the collective control system functionality according to one or more criteria (e.g., to reduce power dissipation)—such synchronizing may include, for example, generating a mean field representation of the overall control system state for the target system(s) and using the mean field representation to improve the overall control system state.

Abstract: An industrial automation system may include an automation device and a control system communicatively coupled to the automation device. The control system may include a first module of a number of modules, such that the first module may receive an indication of a target variable associated with the industrial automation device. The first module may then receive parameters associated with the target variable, identify a portion of data points associated with controlling the target variable with respect to the parameters, generate a model of each data point of the portion over time with respect to the parameters based on the data points, determine functions associated with the model. The functions represent one or more relationships between the each data point of the portion with respect to controlling the target variable. The first module may then adjust one or more operations of the automation device based on the functions.

Abstract: An apparatus for controlling consumption of a resource by a facility includes devices, an occupancy determination system, and control nodes. The devices each consume a portion of the resource and perform a function. The occupancy determination system is disposed in a network operations center that is external to the facility and generates schedules which coordinate run times for the devices to control the consumption of the resource and adjusts the schedules based upon occupancy components and occupancy levels that are generated based on the consumption of the resource and outside temperature only. The control nodes are coupled to a corresponding one of the devices, and are coupled together via an energy management network that is operatively coupled to the NOC, The control nodes transmit sensor data and device status to the NOC for generation of the plurality of run time schedules, and where the control nodes execute selected ones of the run time schedules to cycle the devices on and off.

Abstract: An apparatus for controlling consumption of a resource by a facility includes devices, an occupancy determination system, control nodes, and monitor nodes. The devices each consume a portion of the resource and perform a function. The occupancy determination system is disposed in a network operations center that is external to the facility and generates schedules which coordinate run times for the devices to control the consumption of the resource and adjusts the schedules based upon occupancy components and occupancy levels that are generated based on the consumption of the resource and outside temperature only. The control nodes are coupled to a corresponding one of the devices, and are coupled together via an energy management network that is operatively coupled to the NOC, The control nodes transmit sensor data and device status to the NOC for generation of the plurality of run time schedules, and where the control nodes execute selected ones of the run time schedules to cycle the devices on and off.

Abstract: [Object] To provide a control system, a control method, and a storage medium through which a moving object can change a surrounding environment of a user depending on an emotion of the user. [Solution] Provided is a control system including: an estimation unit that estimates an emotion of a user; and a moving object controller that controls a moving object to change a surrounding environment of the user depending on the estimated emotion.

Abstract: An apparatus for controlling facility resource consumption includes devices, a network operations center (NOC), and control nodes. The devices each consume a portion of the resource and perform a function. The NOC generates schedules which coordinate run times for the devices to control the consumption of the resource and adjusts the schedules based upon occupancy components and occupancy levels that are generated based on the consumption of the resource and outside temperature only. The control nodes are coupled to a corresponding one of the devices, and are coupled together via an energy management network that is operatively coupled to the NOC, The control nodes transmit sensor data and device status to the NOC for generation of the plurality of run time schedules, and where the control nodes execute selected ones of the run time schedules to cycle the devices on and off.

Abstract: Techniques for multimodal data fusion having a multimodal hierarchical dictionary learning framework that learns latent subspaces with hierarchical overlaps are provided. In one aspect, a method for multi-view data fusion with hierarchical multi-view dictionary learning is provided which includes the steps of: extracting multi-view features from input data; defining feature groups that group together the multi-view features that are related; defining a hierarchical structure of the feature groups; and learning a dictionary using the feature groups and the hierarchy of the feature groups. A system for multi-view data fusion with hierarchical multi-view dictionary learning is also provided.

Abstract: According to some embodiments, a system calculates a first trajectory based on a map and a route information. The system generates a path profile based on the first trajectory, traffic rules, and an obstacle information describing one or more obstacles perceived by the ADV. The system generates a speed profile based on the path profile, where the speed profile includes, for each of the obstacles, a decision to yield or overtake the obstacle. The system performs a quadratic programming optimization on the path profile and the speed profile to identify an optimal path with optimal speeds. The system generates a second trajectory based on the optimal path and optimal speeds to control the ADV autonomously according to the second trajectory.

Abstract: An IGV opening command value is corrected to calculate an actual opening equivalent value that indicates an approximate value of an actual opening. A temperature estimation value, for a case where a mixture of fuel and in-flowing air is combusted, is calculated using the actual opening equivalent value, atmospheric conditions, and an output from a gas turbine. A fuel distribution command value that indicates distribution of fuel output from a plurality of fuel supply systems is calculated on the basis of the temperature estimation value. The fuel distribution command value and a fuel control signal command value that indicates the total flow rate of fuel to be output to the plurality of fuel supply systems are acquired, and respective valve openings of fuel flow rate regulating valves of the fuel supply systems are calculated on the basis of the fuel distribution command value and the fuel control signal command value.

Abstract: A method for producing a tunnel magnetoresistive element includes a stacking step, then in-magnetic field heating, and then dry etching. The stacking includes stacking a B absorption layer which is in contact with an upper surface of a CoFeB layer. The dry etching includes removal of layers to the B absorption layer. An end of etching is set as an end point time detected by an analysis device when a final layer before the B absorption layer directly above the CoFeB layer is exposed has reduced to a prescribed level, or when the B absorption layer directly above the CoFeB layer has increased to the prescribed level. An amount of over-etching after the end point time is specified in advance, and the B absorption layer is stacked such that the thickness from the prescribed level to the upper surface of the CoFeB layer corresponds to the over-etching amount.

Abstract: The disclosed embodiments illustrate a method and a system for predicting future activities of a user on a social media platform. The method includes extracting a first time series of one or more historical activities performed by the user from a social media platform server. The method further includes receiving a second time series of one or more future events from a requestor-computing device. The method further includes determining a first set of forecast values and a second set of forecast values based on the first time series and/or the second time series, wherein the first set of forecast values is determined using an ARIMA technique, and the second set of forecast values is determined using a regression modelling technique. The method further includes predicting the future activities of the user based on the first set of forecast values and the second set of forecast values.

Abstract: A computing system implements a telematics service that obtains a set of vehicle telematics data for each vehicle of a population. Within each set of vehicle telematics data, a set of time-based measurements for a measurement type is identified. The set of time-based measurements identified for each vehicle are combined to obtain a combined set of time-based observations for the measurement type across the population of vehicles or a sub-set of the population defined by vehicle make, model, and/or year of production. An outlier observation is identified from among the combined set of time-based observations. A determination is made whether the outlier observation is part of a temporary deviation or a persistent deviation. For a temporary deviation, an impact of the outlier observation on the set of time-based measurements is reduced. For a persistent deviation, the outlier observation is programmatically characterized.

Abstract: Lighting elements are disposed within the enclosure doors surrounding an automated material handling machine such as a packaging machine. The clear panels in the door are edge-lit so that the entire door window corresponding to the location of the maintenance notice is illuminated a contrasting color to call the operator's quick attention to that portion of the machine. A method of notifying the operator of a maintenance issue in a particular portion of the machine is provided by illuminating a window panel in a door of the machine enclosure.