A wire electrical discharge machine includes: a determination unit that determines whether or not a first route and a second route, each including an approach path, a machining path and an escape path in this order, are set in this order as a movement route of a wire electrode; and a wire movement control unit that, when the first route and the second route are determined to be set in a machining program in this order as the movement route of the wire electrode, causes the wire electrode to transition from the machining path of the first route to the machining path of the second route without moving the wire electrode along the escape path of the first route and the approach path of the second route.

The invention relates to a system for generating sets of control data for networked robots, comprising a plurality of robots (R.sub.i), wherein i=1, 2, 3, . . . , n, and n≧2, an optimizer (OE) and a database (DB), which are networked via a data network, wherein each robot (R.sub.i) comprises at least: a control unit (SE.sub.i) for controlling and/or regulating the robot (R.sub.i); a storage unit (SPE.sub.i) for controlling sets of control data SD.sub.i(A.sub.k), which in each case enable the control of the robot (R.sub.i) in accordance with a predetermined task (A.sub.k), wherein k=1, 2, 3, . . . , m; a unit (EE.sub.i) for specifying a new task A.sub.m+1 for the robot (R.sub.i), wherein A.sub.m+1≠A.sub.k; a unit (EH.sub.i) for determining a set of control data SD,(A.sub.m+1) for execution of the task (A.sub.m+1) by the robot (R.sub.i), an evaluation unit (BE.sub.i), which evaluates the set of control data SD.sub.i(A.sub.m+1) determined by the unit (EH.sub.i), with regard to at least one parameter (P1) with the characteristic number K.sub.P1(SD.sub.i(A.sub.m+1)), and a communication unit (KE.sub.i) for communication with the optimizer (OE) and/or the database (DB) and/or other robots (R.sub.j≠i), the optimizer (OE), which is designed and configured in order to determine, upon request by a robot (R.sub.i), at least one optimized set of control data SD.sub.i,P2(A.sub.m+1) with regard to at least one predetermined parameter (P2), wherein the request by the robot (R.sub.i) occurs when the characteristic number K.sub.P1(SD.sub.i(A.sub.m+1) does not meet a predetermined condition, and the data base (DB) stores the set of control data SD.sub.i,P2(A.sub.m+1) optimized by the optimizer (OE) and provides it to the robot (R.sub.i) for execution of the task (A.sub.m+1).

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes repeatedly selecting control settings for the environment based on (i) a causal model that identifies causal relationships between possible settings for controllable elements in the environment and environment responses that reflect a performance of the control system in controlling the environment and (ii) current values of a set of internal parameters; and during the repeatedly selecting: monitoring environment responses to the selected control settings; determining, based on the environment responses, an indication that one or more properties of the environment have changed; and in response, modifying the current values of one or more of the internal parameters.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.

A system and methods for multivariant learning and optimization repeatedly generate self-organized experimental units (SOEUs) based on the one or more assumptions for a randomized multivariate comparison of process decisions to be provided to users of a system. The SOEUs are injected into the system to generate quantified inferences about the process decisions. Responsive to injecting the SOEUs, at least one confidence interval is identified within the quantified inferences, and the SOEUs are iteratively modified based on the at least one confidence interval to identify at least one causal interaction of the process decisions within the system. The causal interaction can be used for testing, diagnosis, and optimization of the system performance.

A production process optimization method includes: acquiring a starting point execution procedure to be a starting point for a search, where one or more operations performed by the production process are defined and contents relevant to the operation are defined; specifying one or more variable parameter items capable of setting a variable parameter value in the starting point execution procedure; generating an execution procedure by setting the variable parameter value in the variable parameter item specified on the basis of a previous execution performance result and an evaluation performance result thereof; acquiring an execution result when an execution subject executes actual execution according to the execution procedure in an execution environment; acquiring an evaluation result with respect to the execution result; and recording the execution procedure, the variable parameter value, the execution result, and the evaluation result in association with each other.

A program analysis device divides a machining program into processes, obtains a command speed from the divided machining program for each process, and measures an actual speed of an axis for each process obtained when machining based on the machining program is performed. Then, the program analysis device calculates an integral value of the difference between the command speed and the actual speed, rearranges the order of the processes based on the calculated integral value, and creates screen data for displaying the sorted processes in order. Provided is an assistive technology for effectively improving the difference between the command speed of the machining program and the actual speed of an axis movement of a machine tool, based on the screen data.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing operations of a supply chain. In one aspect, the method comprises repeatedly performing the following: i) selecting a configuration of input settings for operating a supply chain, based on a causal model that measures causal relationships between input settings and a measure of success of the supply chain; ii) determining the measure of success of the supply chain operated using the configuration of input settings; and iii) adjusting, based on the measure of success of the supply chain operated using the configuration of input settings, the causal model.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes obtaining data specifying baseline probability distributions for each of a plurality of controllable elements; maintaining a causal model; repeatedly performing the following: selecting control settings for the environment based on the causal model and values for a particular internal parameter of the control system that are sampled from a range of possible values; selecting control settings for the environment based on the baseline probability distributions; monitoring environment responses to the control settings selected based on the causal model and the control settings selected based on the baseline probability distributions; determining, for each of the possible values, a measure of a difference between a current system performance and a baseline system performance; and updating how frequently each of the possible values is sampled.