Abstract:
A process analysis apparatus according to an aspect may include a first acquisition unit that acquires a plurality of pieces of state data related to states of a plurality of mechanisms that constitute a manufacturing line, a second acquisition unit that acquires a control program for controlling an operation of the manufacturing line, a first analyzer that analyzes the acquired plurality of pieces of state data so as to identify a connection state between the plurality of mechanisms, a second analyzer that analyzes the acquired control program so as to identify an order relationship between the plurality of mechanisms, and a relationship identifying unit that identifies a causal relationship between the plurality of mechanisms in a process that is carried out on the manufacturing line, based on the identified connection state and order relationship.
Abstract:
A technology for associating and ascertaining the location of device variables which are in a control program and correspond to devices, and the dependency relations between the device variables, when division programming is carried out, is provided. A graph display device according to one aspect of the present invention generates a first directed graph, which comprises a plurality of first nodes respectively representing the device variables, and edges representing the existence of a dependency relation, and a second directed graph, which comprises a plurality of regions corresponding respectively to each subprogram, a plurality of first nodes, and edges, wherein the first nodes are arranged in a region of a subprogram that uses the device variable to be expressed from among the plurality of regions. In response to an instruction from a user the display device switches between displaying the generated first directed graph and displaying the generated second directed graph.
Abstract:
A monitoring system according to an aspect may construct a predictive model that predicts a value of a removal amount depending on values of an accumulated operating time and an accumulated number of processed wafers, based on learning data; acquires actual values of the accumulated operating time, the accumulated number of processed wafers, and the removal amount with respect to a wet etching apparatus when it is in operation; calculates a predicted value of the removal amount by inputting the acquired actual values of the accumulated operating time and the accumulated number of processed wafers to the predictive model; calculates the difference between the predicted value and the actual value of the removal amount, as an indicator value serving as a measure of how necessary it is to replace a chemical solution; and outputs information regarding replacement of the chemical solution based on the calculated indicator value.
Abstract:
A graph display device according to one aspect of the present invention generates a first directed graph, which contains a plurality of first nodes respectively representing device variables, edges representing the existence of a dependency relation, and a block representing a function, and a second directed graph, which contains a plurality of first nodes, edges, a block, and a plurality of second nodes arranged in the block and respectively representing function parameters. In response to an instruction from a user the display device switches between displaying the generated first directed graph and displaying the generated second directed graph.
Abstract:
A prediction model creation apparatus includes a feature amount acquisition unit that acquires values of types of feature amounts that are calculated from operating state data indicating an operating state of a production facility that produces a product, for both a normal time at which the production facility produces the product normally and a defective time at which a defect occurs in the product that is produced, a feature amount selection unit that selects a feature amount effective in predicting the defect from among the acquired types of feature amounts, based on a predetermined algorithm that specifies a degree of association between the defect and the types of feature amounts, from the values of the types of feature amounts acquired at the normal time and the defective time, and a prediction model construction unit that constructs a prediction model for predicting occurrence of the defect, using the selected feature amount.
Abstract:
An analysis device according to one aspect of the present invention supplies a definition for a dependency relation between an input parameter and an output parameter of a standard function, which cannot be derived in a dependency analysis of a control program, the definition being supplied by use of function structure information which is external information. In other words, an analysis device according to this configuration identifies a dependency relation between an input parameter and an output parameter of the standard function on the basis of function structure information that defines a dependency relation between the input parameter and the output parameter of the standard function. Therefore, the dependency relation between the input and the output of a standard function becomes clear, so the dependency relations between a plurality of device variables that mediate the standard function can be identified.
Abstract:
A technology for associating and ascertaining dependency relations between device variables corresponding to respective devices with dependency relations of device variables for respective parameters of a function in a control program is provided. A graph display device according to one aspect of the present invention generates a first directed graph including a plurality of first nodes that respectively express device variables and edges that express having dependency relations, and a second directed graph including the plurality of first nodes, the edges, and a block that expresses the function, and switches and displays the generated first directed graph and second directed graph on a display device.
Abstract:
A generated power estimation model to be used for estimating an expected generated power amount that is expected to be generated by a solar power generation module is constructed based on a daily correlative relationship between a generated power amount generated by a solar power generation module that generates power by receiving sunlight, and an energy amount of sunlight emitted to the solar power generation module. Furthermore, the expected generated power amount is estimated based on the generated power estimation model, and it is determined whether or not an abnormality has occurred by comparing the expected generated power amount and the generated power amount actually generated by the solar power generation module. This technique can be applied to a solar power generation system, for example.