Abstract: An ion removal apparatus according to this disclosure performs a desalination treatment on a liquid and includes: a first electrode guide having an inlet allowing the liquid to flow in, a first electrode holder holding a first electrode that adsorbs an ion in the liquid, and an inflow passage serving as a flow passage connecting the inlet and the first electrode holder to one another; and a second electrode guide having an outlet allowing the liquid to flow out, a second electrode holder allowing the liquid passing through the first electrode holder to flow in and holding a second electrode that adsorbs the ion in the liquid, and an outflow passage serving as a flow passage connecting the outlet and the second electrode holder to one another.

Abstract: A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

Abstract: A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

Abstract: A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

Abstract: Provided is a manufacturing method of an interior member of a plasma processing apparatus, which improves processing yield. The interior member is disposed inside a processing chamber of the plasma processing apparatus and includes, on a surface thereof, a film of a material having resistance to plasma. The manufacturing method includes: a step of moving a gun by a predetermined distance along the surface of the interior member to spray the material to form the film, and disposing a test piece having a surface having a shape simulating a surface shape of the interior member within a range of the distance within which the gun is moved and forming the film of the material on the surface of the test piece; and a step of adjusting, based on a result of detecting a crystal size of the film on the surface of the test piece and presence or absence of a residual stress or inclusion of a contaminant element, a condition of forming the film on the surface of the interior member by the gun.

Abstract: A computer for determining a control parameter of processing to be performed on a sample includes: a memory unit configured to store a first model indicating a correlation between a first processing output obtained by measuring a first sample used for manufacturing, on which the processing is performed and a second processing output obtained by measuring a second sample that is easier to measure than the first sample and on which the processing is performed, and a second model indicating a correlation between a control parameter of the processing performed on the second sample and the second processing output; and an analysis unit configured to calculate a target control parameter of the processing performed on the first sample based on a target processing output as the target first processing output, the first model, and the second model.

Abstract: The efficiency of operation in a semiconductor processing apparatus is improved. In order to search an input parameter value to be set in a semiconductor processing apparatus for processing into a target processed shape, a predictive model indicating a relationship between an input parameter value and an output parameter value is generated based on the input parameter value and the output parameter value which is a measured value of a processing result processed by setting the input parameter value in the semiconductor processing apparatus. In this case, when the measured value of the processing result processed by the semiconductor processing apparatus is the defective data, the predictive model is generated based on the input parameter value causing defective data and defective substitute data obtained by substituting the measured value which is the defective data.

Abstract: A sample simulates a processing state of a semiconductor sample and is measured by a measurement device. The sample includes: a first surface formed at a first height when viewed from a sample surface; a second surface formed at a second height higher than the first height; and a plurality of inflow parts which allow a particle for performing processing on the first surface to flow between the first surface and the second surface. The processing by the particle flowing from the inflow parts is superimposed in at least a part of a region to be processed on the first surface, and the region where the processing is superimposed on the first surface is measured by the measurement device.

Abstract: A system for determining a processing procedure including a plurality of processes for controlling an object, the system includes a learning unit for performing a learning process for determining a processing condition of each of a plurality of processes, and the learning unit acquires a physical quantity correlating with a state of the object on which a process has been performed under a predetermined processing condition, from a device for controlling the object on the basis of the processing procedure, calculates a pseudo state corresponding to the state of the object on the basis of the physical quantity, performs a learning process using a value function, and determines a processing condition of each of the plurality of processes to achieve a target state of the object.

Abstract: A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

Abstract: A search apparatus receives each input of a target value and a reference value indicated by the target value; generates a prediction model indicating a relation between the condition and the result based on a setting value of the condition inside the search area and a measured value of the result; acquires a prediction value from the prediction model by assigning the target value to the prediction model and specifies a presence area of the prediction value from the search area; determines whether the prediction value is closer to the target value than the reference value; sets the measured value of the result corresponding to the prediction value to the reference value when the prediction value is closer to the target value, and sets the prediction value presence area to the search area; and outputs a prediction value satisfying an achievement condition when the prediction value satisfies the achievement condition.

Abstract: A preprocessor into which time-series sensor data is input includes a correspondence table associating sensor data with a physical unit. A physical extraction unit that obtains sensor data, and specifies a physical unit based on the correspondence table. A latent variable generation unit specifies a nonlinear function from the physical unit, and generates a latent variable for applying the sensor data to the specified nonlinear function. A latent variable addition unit obtains time-series sensor data and sets the data as a variable, applies the obtained time-series sensor data to the latent variable to generate time-series data and sets the data as a variable, and adds the generated time-series data to the obtained time-series sensor data to generate a data set of a plurality of variables. Then a relational expression estimation-processing unit that analyzes a relationship between the variables of the data set, and generates a linear relational expression.

Abstract: A sample simulates a processing state of a semiconductor sample and is measured by a measurement device. The sample includes: a first surface formed at a first height when viewed from a sample surface; a second surface formed at a second height higher than the first height; and a plurality of inflow parts which allow a particle for performing processing on the first surface to flow between the first surface and the second surface. The processing by the particle flowing from the inflow parts is superimposed in at least a part of a region to be processed on the first surface, and the region where the processing is superimposed on the first surface is measured by the measurement device.

Abstract: A search apparatus receives an input target value, which indicates a condition to be set in a semiconductor processing apparatus or a result obtained by processing the semiconductor using the processing apparatus, a reference value of the condition inside a search area, and the result, wherein the reference value is indicated by the target value. A prediction model indicating a relation between the condition and the result based on a setting value of the condition inside the search area is generated and, a measured value of the result is obtained. A prediction value is acquired by assigning the target value to the prediction model. The prediction value is set to the reference value when it is determined that the prediction value is closer to the target value, and a prediction value satisfying an achievement condition is set when the prediction value satisfies the achievement condition of the target value.

Abstract: A retrieval apparatus includes a processor and a memory and retrieves a condition given to a semiconductor treatment apparatus. The processor receives a processing result of a semiconductor, a condition corresponding to the processing result, a target value for treating the semiconductor, and a retrieval region. A prediction model is generated indicating a relationship between the condition and the processing result based on a set value of the condition in the retrieval region, and the processing result; calculates a predicted value, performs a demonstration test, acquires an actually measured value, outputs the predicted value as a set value when the actually measured value reaches the target value. When the actually measured value does not reach the target value, the prediction model is updated by applying the predicted value and the actually measured value to the set value and the processing result, respectively.

Abstract: A system for determining a processing procedure including a plurality of processes for controlling an object, the system includes a learning unit for performing a learning process for determining a processing condition of each of a plurality of processes, and the learning unit acquires a physical quantity correlating with a state of the object on which a process has been performed under a predetermined processing condition, from a device for controlling the object on the basis of the processing procedure, calculates a pseudo state corresponding to the state of the object on the basis of the physical quantity, performs a learning process using a value function, and determines a processing condition of each of the plurality of processes to achieve a target state of the object.

Abstract: A preprocessor includes a sensor data storage part that is connected to an abnormality sign diagnosing device and stores multi-dimensional sensor data, a data analysis processing part that calculates a variable value by using the multi-dimensional sensor data stored in the sensor data storage part, an analysis data storage part that stores the variable value calculated by the data analysis processing part, and an analysis data addition processing part that combines the multi-dimensional sensor data stored at the sensor data storage part and the variable value stored in the analysis data storage part and outputs a combined result to the abnormality sign diagnosing device.

Abstract: The efficiency of operation in a semiconductor processing apparatus is improved. In order to search an input parameter value to be set in a semiconductor processing apparatus for processing into a target processed shape, a predictive model indicating a relationship between an input parameter value and an output parameter value is generated based on the input parameter value and the output parameter value which is a measured value of a processing result processed by setting the input parameter value in the semiconductor processing apparatus. In this case, when the measured value of the processing result processed by the semiconductor processing apparatus is the defective data, the predictive model is generated based on the input parameter value causing defective data and defective substitute data obtained by substituting the measured value which is the defective data.

Abstract: A model learning unit learns a prediction model on the basis of learning data, a target setting unit sets a target output parameter value by interpolating between a goal output parameter value and an output parameter value which is the closest to the goal output parameter value in output parameter values in the learning data, a processing condition search unit estimates input parameter values which corresponds to the goal output parameter value and the target output parameter value, a model learning unit updates the prediction model by using a set of the estimated input parameter value and an output parameter value which is a result of processing that a processing device performs as additional learning data.

Abstract: A computer for determining a control parameter of processing to be performed on a sample includes: a memory unit configured to store a first model indicating a correlation between a first processing output obtained by measuring a first sample used for manufacturing, on which the processing is performed and a second processing output obtained by measuring a second sample that is easier to measure than the first sample and on which the processing is performed, and a second model indicating a correlation between a control parameter of the processing performed on the second sample and the second processing output; and an analysis unit configured to calculate a target control parameter of the processing performed on the first sample based on a target processing output as the target first processing output, the first model, and the second model.