JP2007041784A - Optimal value retrieval supporting apparatus, optimal value retrieval support method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an optimal value retrieving apparatus, an optimal value retrieving method and a computer program for calculating a global optimal value under the consideration of the influence of an error factor becoming the factor of variation of a characteristic value. <P>SOLUTION: This optimal value retrieval support method to be used for executing design, analysis or test relating to equipment having a plurality of factors affecting characteristics includes: preparing an orthogonal chart where a standard value to be calculated from the initial value of each factor is set at each coordinate of a two-dimensional table constituted of the matrix of each characteristic and each factor (S1 to S3); obtaining a characteristic value to be obtained on the basis of the combination of the standard values of each factor with the same characteristic from each characteristic in the orthogonal chart (S4); selecting the combination having the most excellent characteristic value (S5); allocating the error factors to the orthogonal charts (S6); calculating the mean value and standard deviation of the characteristic values on the basis of the combination of the orthogonal charts to which the error factors are allocated (S7); evaluating the influence of the error factors (S8); confirming the number of times of retrieval (S9); and determining the standard width of the next step from the calculated optimal value, and repeatedly calculating the characteristic value by performing reallocation to the orthogonal chart. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an apparatus, a method, and a program for searching for an optimum value of a combination of factors that realizes a required characteristic to the maximum when designing, analyzing, or testing a device having a plurality of factors, for example. It is.

  In designing or analyzing or testing a device having a plurality of factors, various methods for searching for an optimum value of a combination of factors have been proposed in order to realize the required characteristics to the maximum.

Methods that have been proposed so far include a method of searching for an optimum value by applying mathematical programming such as Newton's method or sequential quadratic programming (eg, Non-Patent Document 1), genetic algorithm, annealing method, etc. A method for searching for an optimum value by applying a method based on random search (for example, Non-Patent Document 1), or a method for creating a response surface expression for estimating characteristics by an experimental design method and searching for an optimum value by a mathematical programming method (For example, refer to Patent Document 1), and a method of investigating the distribution state of characteristic values obtained from an orthogonal table and searching for an optimum value by estimating a search direction based on the distribution state (for example, refer to Patent Document 2). .
Japanese Patent Laid-Open No. 10-207926 JP 2000-132535 A "Basics and applications of optimization theory" published by Corona Co., Ltd. (2000)

  However, such a conventional optimum value searching method has the following problems.

  That is, in general, when designing, analyzing, or testing a device, in order to realize the required characteristics to the maximum, multiple factors that affect the characteristics are grasped and an optimum value search support device is used. The optimum level of each factor is required.

  Hereinafter, an optimum value search support apparatus according to the prior art will be described with reference to FIGS.

  FIG. 12 is a flowchart when searching for an optimum value by applying mathematical programming such as Newton's method or sequential quadratic programming, and corresponds to the contents of Non-Patent Document 1. In this case, after setting the initial value of the design factor (S80), the optimum solution search condition is set (S81), the optimum value is searched by mathematical programming (S82), and the obtained optimum value is evaluated (S83). ) Is provided.

  FIG. 13 is a flowchart when searching for an optimum value by applying a method based on a random search such as a genetic algorithm or an annealing method, and corresponds to the contents of Non-Patent Document 1. In this case, after setting the initial value of the design factor (S90), the optimum value search condition is set (S91), the optimum value is searched by the random search method (S92), and the obtained optimum value is evaluated (S93). ) Is provided.

  FIG. 14 is a flowchart in the case of searching for the optimum value by applying the response surface method, and corresponds to the content of Patent Document 1. In this case, after setting the initial value of the design factor (S101), the design factor and the number of levels are set (S102) and assigned to the orthogonal table (S103). Furthermore, device function calculation is performed for each combination of orthogonal tables (S104), and a response surface equation that approximates the relationship between the characteristic value and the design factor is created (S105). Furthermore, after setting optimum solution search conditions (S106), an optimum value is searched on the response surface equation (S107), and the effect of the optimum combination of the obtained design factors is confirmed on actual characteristics (S108). The

  FIGS. 15 and 16 show an optimum value searching method related to the present invention, and an optimum value is searched by repeatedly using an orthogonal table.

  In these conventional optimum value search methods, it is possible to obtain a global optimum value in consideration of the influence of error factors (design tolerances, manufacturing process accuracy, changes in use environment conditions, etc.) that cause fluctuations in characteristic values. There is a problem of difficulty.

  In the case of searching for an optimum value by applying mathematical programming such as the quasi-Newton method or sequential quadratic programming shown in FIG. 12, the optimum value is searched while obtaining the characteristic gradient etc. using the initial value as a starting point. In the case of a characteristic having a large number of peaks (local optimum solution indicated by ● in the figure and global optimum solution indicated by ☆ in the figure) having an optimum value as shown in FIG. There is a case where it is captured by the optimal value.

  In the case of searching for an optimum value by applying a method based on a random search such as the genetic algorithm of FIG. 13, a calculation with a very large number of combinations is necessary, so that there is a high possibility of reaching a global optimum value. A huge amount of calculation is required, and it is difficult to consider the influence of error factors.

  In the case of searching for the optimum value by applying the response surface method of FIG. 14, the calculation time is short because the optimum value is searched on the response surface equation, but the accuracy of the response surface equation may be a problem. . In particular, when there are many design factors and there are many interactions between design factors, the prediction accuracy of the response surface equation tends to decrease. Patent Document 2 proposes a method of investigating a distribution state of characteristic values obtained from an orthogonal table, and searching for an optimum value by estimating a search direction based on the distribution state. In this method, it is necessary to determine which level value is selected for improvement for each factor. For the two-level problem shown as an example of the patent, it is considered that the improvement direction can be judged because the characteristic of the factor is linear, but in many design problems, there is an interaction between the factors. Because it has non-linear characteristics, it is necessary to use an orthogonal table of three levels or more. In such a case, the improvement direction of each factor is determined only by the distribution of characteristic values described in the patent. Is extremely difficult.

  FIG. 15 is a technique related to the present invention, and searches for an optimum value by changing factors based on an orthogonal table for each search step.

  FIG. 16 is a schematic diagram showing a state in which all 27 combinations in the case of 3 factors and 3 levels are assigned to the vertexes and midpoints of a cube and an optimum value is searched for. In the case of this method, there is a high possibility that the global optimum value can be obtained with a small number of searches, but it is difficult to consider the influence of error factors.

  The present invention has been made in view of such circumstances, and an optimum value search apparatus, an optimum value search method capable of obtaining a global optimum value in consideration of an influence of an error factor that causes a variation in characteristic values, And to provide a computer program.

  In order to achieve the above object, the present invention takes the following measures.

  That is, the present invention is an optimum value search support apparatus used when designing, analyzing, or testing a device having a plurality of factors that affect characteristics, and includes a matrix of the characteristics and the factors. The first orthogonal table in which the level value obtained from the initial value of each factor is set at each coordinate of the two-dimensional table, and the level value of each factor of the same characteristic is obtained from each characteristic in the first orthogonal table. A selection means for selecting the combination that provides the most excellent characteristic value from the characteristic values obtained based on the combination, and a level value of each factor in the characteristic corresponding to the combination selected by the selection means is the orthogonal value. The resetting means resetting in the table, and after the resetting by the resetting means, the selection by the selection means is repeatedly performed to repeatedly select the characteristic value from among the characteristic values. A first search means for searching for an optimum value which is a characteristic value obtained, and an optimum value searched by the first search means is set as a median value, and an error factor affecting the fluctuation of the characteristic value is set. An optimum value provided with a second orthogonal table and a second search means for obtaining an average value and a standard deviation of characteristics due to error factors from characteristic values obtained based on a combination of the first and second orthogonal tables. A search support apparatus is provided.

  According to the present invention, it is possible to provide an optimum value search apparatus, an optimum value search method, and a computer program that can obtain a global optimum value in consideration of the influence of an error factor that causes a fluctuation of a characteristic value.

  The best mode for carrying out the present invention will be described below with reference to the drawings.

  FIG. 1 is a block diagram showing a configuration example of an optimum value search support apparatus to which an optimum value search support method according to an embodiment of the present invention is applied.

  That is, the optimum value search support device includes an input device unit 1, a computer main body 2, an output device unit 3, and a recording medium unit 4. Further, the recording medium unit 4 includes a device function calculation unit 5 that records a program that performs device function calculation, and an optimum value search calculation unit 6 that records a program that performs an optimum value search.

  The above programs can be executed by the computer main body 2 which is a computer, for example, as a magnetic disk (floppy (registered trademark) disk, hard disk, etc.), optical disk (CD-ROM, DVD, etc.). It can also be stored in a recording medium such as a semiconductor memory, or transmitted to the recording medium unit 4 via a communication medium and distributed. In this case, the program stored in the recording medium includes a setting program for configuring the above-described programs (including not only the execution program but also an orthogonal table and data structure described later) in the computer main body 2.

  The computer main body 2 reads the above-mentioned programs recorded in the recording medium unit 4, and in some cases, constructs software means using these programs by a setting program, and executes processing by controlling the operation by the software means. To do.

  The optimum value search support device having such a configuration stores each program recorded in the device function calculation unit 5 and the optimum value search calculation unit 6 based on the initial value of the device design input from the input device unit 1. The optimum value search calculation applied to the design or analysis or test of the device is performed, and the calculation result is output from the output device unit 3.

  Hereinafter, specific calculations corresponding to each claim performed using the optimum value search support apparatus having such a configuration will be described in the following embodiments. Therefore, in each of the following embodiments, description regarding the configuration of the optimum value search support apparatus is omitted.

(First embodiment)
FIG. 2 is a flowchart showing a flow of processing performed by the optimum value search support apparatus to which the optimum value search support method according to the first embodiment is applied.

  This flowchart shows a combination of step S1 for setting initial values of factors that affect the characteristics of the device, step S2 for setting the level width, step S3 for assigning to the orthogonal table (first orthogonal table), and the orthogonal table. Step S4 for obtaining a characteristic value based on the above, Step S5 for selecting an optimum value having the best characteristic from the obtained characteristic values, Step S6 for assigning error factors to an orthogonal table, and Orthogonalization for assigning error factors Step S7 for obtaining the average value and standard deviation of the characteristic values based on the combination of the table, Step S8 for evaluating the influence of the error factor, Step S9 for checking the number of searches, and the level of the next step from the obtained optimum value The step includes a step of determining the width and a step of reassigning the orthogonal table to obtain a repeated characteristic value. Details of these steps will be described below.

  First, in step S1, an initial value of each factor when a design, analysis, or test regarding a device having a plurality of factors is performed is set. Next, in step S2, an orthogonal table suitable for the number of factors and the number of levels is selected, and in step S3, each factor is assigned to the orthogonal table. In this case, an orthogonal table suitable for allocation is selected in consideration of the number of design factors and the number of levels.

  FIG. 3A shows an example in which seven types of design factors a to g are assigned, taking as an example an L18 orthogonal table indicating (characteristic-1) to (characteristic-18) as characteristic values. In this case, the number of levels is 3 levels for each design factor, and the level values are displayed as 1, 2, 3 in the orthogonal table. Since the orthogonal table combines the factors in a balanced manner, it can be said that the orthogonal table is a suitable method for grasping the characteristics of the device having a plurality of factors with a small number of combinations.

  Next, in step S4, a characteristic value is obtained for each combination of orthogonal tables, and in step S5, an optimum value having the best characteristic is selected from the characteristic values obtained in step S4.

  (Characteristic-1) to (Characteristic-18) are obtained for each combination of orthogonal tables, and the most excellent characteristics are obtained from the obtained characteristic values (Characteristic-1) to (Characteristic-18) (FIG. 3A). The optimum value is selected, and this combination is set as the first optimum value.

  FIG. 3B shows a step of obtaining an average value and a standard deviation in consideration of an error factor of the optimum value. Possible error factors include design tolerance, accuracy during the manufacturing process, and changes in operating environment conditions. Here, error factors Na to Ng (for example, tolerances for each design factor) related to seven types of design factors are assigned. An example is shown (step S6).

  In a certain search step, when the characteristics of the orthogonal table No. 12 of design factors are the best, each design factor is combined with the orthogonal table of error factors with the combination of the No. 12 design factors set to the median. 18 characteristic values (characteristic-1) to (characteristic-18) (FIG. 3B) are obtained. From this characteristic value, the average value (μ) and standard deviation (Stdev.) Of the characteristic due to the error factor defined by the following equation are obtained (step S7). In this case, the number of data (N) is 18.

μ = (ΣZi) / N (1)
Stdev. = (Σ (Zi-μ) 2 / (N-1)) 0.5 (2)
Next, it is checked whether the number of searches is within the limit, and if it is within the limit, the search is continued. If the limit is exceeded, the calculation result is output and the process ends (step S9).

  When the search is continued (YES in step S9), the level width of the orthogonal table is changed for each search step.

  In the flowchart of FIG. 2, Opt (n−1) represents the (n−1) th optimum value, and Opt (n−2) represents the (n−2) th optimum value. In step S10, first, the difference between the optimum values obtained at the (n-1) th and (n-2) th is determined. When ΔOpt = Opt (n−1) −Opt (n−2)> 0, the search for the optimum value is in progress, and the optimum values of (n−1) and (n−2) are used as functions. The level width W (n) for the next search is obtained by the following equation (step S13).

W (n) = f (Opt (n−1), Opt (n−2)) × W (n−1) (3)
The f function of the above equation is such that the level width becomes larger than the previous step when the change amount of the optimum value is large, and the level width becomes smaller than the previous step when the change amount of the optimum value is small. The f function is set as follows. This is because, in a search process that shows a characteristic with a large amount of change in the optimum value, a larger level width can approach the optimum value with a smaller number of searches, while a characteristic with a small amount of change in the optimum value. This is because, in the search process, it is considered that a higher level optimal value can be reached if the level width is set smaller.

  If ΔOpt = 0, that is, if the previous and current optimum values do not change, the search range may be changed larger or smaller than the previous search because there is a possibility of being captured by the local optimum value in step S11. .

  If it is determined in step S11 that the equality of the optimum value is established for the first time, the level width W (n) of the next step is determined by the following equation in step S14.

W (n) = A x W (n-1) ... (4)
A in the above formula is a constant arbitrarily set within a range of A> 1.0. This search process corresponds to No. 5 in FIG. Although it is captured by the local optimum value in No. 4, the peak of the global optimum value at a position distant from the current optimum value is searched by changing the level range greatly. If the slope of the mountain containing the global optimum value can be searched by changing the level width greatly according to equation (4), then the global optimum value can be reached based on the change in the level width according to equation (3). .

  In step S11, if the optimum value equality is established for the second time, that is, if the optimum value does not change even if the level width is greatly changed, a global optimum value exists in the vicinity of the current optimum value in step S12. Therefore, the level width is changed small as shown in the following equation.

W (n) = B x W (n-2) ... (5)
B in the above formula is a constant arbitrarily set within the range of B <1.0. It should be noted that the order of equations (4) and (5) is switched, that is, when the optimal value equality is established for the first time, the level width is changed small, and the optimal value equality is established for the second time. There is no problem even if the level range is changed greatly.

  If it is determined in step S11 that the equality of the optimum value is established for the third time or more, that is, if the optimum value does not change even if the level width is increased or decreased, the current optimum value is determined to be a global optimum in step S16. It is determined that the value is a value and the calculation is terminated. It should be noted that the method of changing the level width and the number of times the convergence determination equality is established can be changed according to the characteristics of the target problem.

  Next, the optimum value of the obtained factor is set to the median value of the level, and a new orthogonal table (second orthogonal table) is created by changing the level width. Calculate the value and standard deviation.

  Thus, according to the present method, the global optimum value can be reached with a small number of searches while evaluating the influence of the error factor for each search step.

(Second Embodiment)
FIG. 4 is a flowchart for explaining the second embodiment of the present invention.

  The difference from the first embodiment is that an error factor is assigned to an orthogonal table, an average value / standard deviation is calculated, and an influence evaluation of the error factor is performed on the finally obtained optimum value. .

  Specifically, the processing of steps S33 to S36 in FIG. 4 is performed after step S26.

  According to the second embodiment as described above, the influence of the error factor on the optimum value in the midway search process cannot be grasped, but the number of searches can be reduced as compared with the case of the first embodiment.

(Third embodiment)
FIG. 5 is a flowchart for explaining the third embodiment of the present invention.

  The difference from the first embodiment is that a “contribution rate” is newly calculated after the calculation of the average value and the standard deviation (step S48).

  The contribution rate ρ is one of the statistics used for analysis of variance. The following equation is used to calculate the variation (S), error variance (Ve), degree of freedom (f), and total variation (ST). Defined and represents the magnitude of the influence on variation.

ρ = (S−Ve × f) / ST (6)
According to the third embodiment, by calculating the contribution rate defined by the above equation for each error factor, it is possible to quantitatively grasp the degree of influence of the error factor on the characteristic variation.

(Fourth embodiment)
FIG. 6 is a flowchart for explaining the fourth embodiment of the present invention.

  The difference from the second embodiment is that a “contribution rate” is newly calculated after the calculation of the average value and the standard deviation (step S76).

  According to such 4th Embodiment, in addition to the effect of 2nd Embodiment, there can exist an effect similar to 3rd Embodiment.

  Next, a method in which the above-described embodiment is applied to a device design calculation method will be described.

  The number of design factors is 7, the number of error factors is 7, and the error factors are the tolerances of the design factors. Moreover, in order to improve the equipment efficiency which is the objective function of this method, each design factor was optimized using this method, and the influence degree of the error factor was evaluated. The orthogonal table used is the L18 orthogonal table shown in FIG.

  FIG. 7 shows a calculation result using the size of the tolerance as a parameter. The horizontal axis represents the number of search steps, and the vertical axis represents the difference Δη between the average efficiency value (μ) and the initial efficiency. The tolerance was set to the same value for the seven design factors and varied from 0% to 1% in 6 ways.

  First, even if the tolerance is changed up to 11 steps (STEP), the level of the optimum value is the same, but after 12 steps, the optimum value changes greatly due to the difference in tolerance, and Δη decreases as the tolerance increases. Therefore, the response surface that represents the relationship between equipment efficiency and design factors is a smooth curved surface shape when Δη at the initial stage of search is relatively small, while a plurality of irregularities are observed when Δη near the global optimum is large. It is expected to have a shape with some multimodal characteristics.

  It can also be seen that there is an optimum value with excellent robustness that does not change the level of Δη even if the tolerance is changed, as in 18 steps.

  FIG. 8 is a schematic diagram showing a trend of changes in standard deviation (Stdev.).

  As shown in FIG. 8, it can be seen that the standard deviation varies greatly depending on the level of tolerance. Up to eleven steps, the standard deviation changes continuously, and the standard deviation becomes smaller as the tolerance is set smaller. This is presumably because the characteristic in this range is composed of a relatively smooth curved surface as described above.

  In addition, after 12 steps, the standard deviation varies greatly depending on the number of steps and tolerance. Even if the tolerance is changed in FIG. 7, the standard deviation is small in any tolerance in 18 steps in which the variation in Δη is small. On the other hand, in 22 steps where Δη is the largest when the influence of tolerance is not taken into account, the standard deviation varies greatly due to the difference in tolerance.

  As described above, in the optimization problem of the design factor of the device, it can be said that the region where the efficiency improvement amount in the vicinity of the global optimum value is larger is more sensitive to the variation of the design factor. Therefore, it is important to understand the effects of tolerances and set appropriate tolerances. In addition, reducing the design tolerance causes the processing cost to be raised, so how to increase the tolerance and improve the robustness is the point of optimum design.

  FIG. 9 is a schematic diagram illustrating a calculation example of the contribution ratio of each error factor.

  In FIG. 9, the contribution ratio of N2 is the largest, followed by N3.

  10 and 11 are schematic diagrams showing Δη and standard deviation values when the values of the seven error factors are variously changed.

  It can be seen that as the tolerance of each factor increases, Δη decreases and the standard deviation increases. Further, by setting the tolerance of N2 and N3, which has a large contribution ratio to the variation of Δη, to be small, the characteristics can be greatly improved.

  For example, tole. (0.5-0.25%) with N2 and N3 tolerances set to 0.25% and other tolerances set to 0.5%, The standard deviation is 1/10 or less than the case of 0.5%), and the same level of Δη and standard deviation compared to tole. (0.25%) with all tolerances set to 0.25% I know that there is. Furthermore, tole. (1.0-0.25%) with N2 and N3 tolerances of 0.25% and other tolerances of 1.0% is equivalent to Δη compared to tole. (0.5%). It can be said that the standard deviation is greatly improved.

  In this way, by finding a factor that greatly affects the fluctuation of the objective function and suppressing the variation of the factor to be small, it is possible to effectively improve the robustness of the objective function. For this reason, it can be said that it is very effective to incorporate the step of evaluating the average value and standard deviation of the characteristics in consideration of the error factor into the optimum solution search method using the orthogonal table, which is a feature of the present invention.

  As mentioned above, although the best form for implementing this invention was demonstrated referring an accompanying drawing, this invention is not limited to this structure, It is provided. Within the scope of the invented technical idea of the scope of claims, a person skilled in the art can conceive of various changes and modifications. The technical scope of the present invention is also applicable to these changes and modifications. It is understood that it belongs to.

The block diagram which shows the structural example of the optimum value search assistance apparatus to which the optimum value search assistance method which concerns on embodiment of this invention is applied. The flowchart which shows the flow of the process performed by the optimum value search assistance apparatus to which the optimum value search assistance method which concerns on 1st Embodiment is applied. The schematic diagram which showed an example of the 1st direct table | surface. The flowchart explaining the 2nd Embodiment of this invention. The flowchart explaining the 3rd Embodiment of this invention. The flowchart explaining the 4th Embodiment of this invention. FIG. 4 is a calculation result using a tolerance value as a parameter, a horizontal axis indicating the number of search steps, and a vertical axis indicating a difference Δη between an average efficiency value (μ) and an initial efficiency. Schematic showing the trend of changes in standard deviation (Stdev.). The schematic diagram which showed the example of calculation of the contribution rate of each error factor. The schematic diagram which showed (DELTA) (eta) and the standard deviation value at the time of changing the value of seven error factors variously. The schematic diagram which showed (DELTA) (eta) and the standard deviation value at the time of changing the value of seven error factors variously. The flowchart in the case of searching for an optimum value by applying mathematical programming such as Newton's method or sequential quadratic programming. The flowchart in the case of searching for an optimal value by applying a method based on a random search such as a genetic algorithm or an annealing method. The flowchart in the case of searching an optimal value by applying the response surface method. The flowchart which showed the optimal value search method to which the prior art was applied. The schematic diagram which showed a mode that 27 total combinations in the case of 3 factor 3 level were allocated to the vertex and midpoint of a cube, and the optimal value was searched. The schematic diagram which shows a mode that the optimal value searched for by the difference in an initial value changes.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Input device part, 2 ... Computer main body, 3 ... Output device part, 4 ... Recording medium part, 5 ... Device function calculation part, 6 ... Optimum value search calculation part

Claims (12)

An optimum value search support device used when designing, analyzing, or testing a device having a plurality of factors affecting characteristics,
A first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table composed of a matrix of each characteristic and each factor;
Selecting means for selecting the combination that provides the most excellent characteristic value from among the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table;
Resetting means for resetting the level value of each factor in the characteristic corresponding to the combination selected by the selection means in the orthogonal table;
A first search means for searching for an optimum value that is the best characteristic value from among the characteristic values by repeatedly performing selection by the selection means after resetting by the resetting means;
A second orthogonal table in which the optimum value searched by the first search means is set as a median value, and error factors affecting the fluctuation of the characteristic value are set;
There is provided an optimum value search support device comprising a second search means for obtaining an average value and a standard deviation of a characteristic due to an error factor from a characteristic value obtained based on a combination with the first and second orthogonal tables. . An optimum value search support device used when designing, analyzing, or testing a device having a plurality of factors affecting characteristics,
A first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table composed of a matrix of each characteristic and each factor;
Selecting means for selecting the combination that provides the most excellent characteristic value from among the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table;
Resetting means for resetting the level value of each factor in the characteristic corresponding to the combination selected by the selection means in the first orthogonal table;
A first search means for searching for an optimum value that is the best characteristic value from among the characteristic values by repeatedly performing selection by the selection means after resetting by the resetting means;
A second orthogonal table in which an optimum value searched and finally obtained by the first search means is set as a median value, and an error factor affecting the fluctuation of the characteristic value is set;
There is provided an optimum value search support device comprising a second search means for obtaining an average value and a standard deviation of a characteristic due to an error factor from a characteristic value obtained based on a combination with the first and second orthogonal tables. . In the optimum value search support device according to claim 1 or 2,
An optimum value search characterized in that a contribution rate indicating the magnitude of influence of an error factor is obtained with respect to the optimum value obtained in the search, and the error factor is changed based on the magnitude of the contribution rate. A support device is provided. In the optimum value search support device according to claim 1 or 2,
There is provided an optimum value search support device characterized in that tolerances of design factors are used as the error factors. An optimum value search support method used when designing, analyzing, or testing a device having a plurality of factors that affect characteristics,
A first creation step of creating a first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table including a matrix of each characteristic and each factor;
A selection step of selecting the combination that provides the most excellent characteristic value from among the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table;
A resetting step of resetting the level value of each factor in the characteristic corresponding to the combination selected by the selecting step in the orthogonal table;
A first search step for searching for an optimum value that is the most excellent characteristic value from among the characteristic values by repeatedly performing the selection by the selection step after the resetting by the resetting step;
A second creation step of creating a second orthogonal table in which the optimum value searched in the first search step is set as a median value and an error factor affecting the fluctuation of the characteristic value is set;
There is provided an optimum value search support method including a second search step for obtaining an average value and a standard deviation of characteristics due to error factors from characteristic values obtained based on a combination with the first and second orthogonal tables. An optimum value search support method used when designing, analyzing, or testing a device having a plurality of factors that affect characteristics,
A first creation step of creating a first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table including a matrix of each characteristic and each factor;
A selection step of selecting the combination that provides the most excellent characteristic value from among the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table;
A resetting step for resetting the level value of each factor in the characteristic corresponding to the combination selected by the selection step in the first orthogonal table;
A first search step for searching for an optimum value that is the most excellent characteristic value from among the characteristic values by repeatedly performing the selection by the selection step after the resetting by the resetting step;
A second creation step for creating a second orthogonal table in which an optimum value searched and finally obtained by the first search step is set as a median value and an error factor affecting the fluctuation of the characteristic value is set. When,
There is provided an optimum value search support method including a second search step for obtaining an average value and a standard deviation of characteristics due to error factors from characteristic values obtained based on a combination with the first and second orthogonal tables. In the optimum value search support method according to claim 5 or 6,
An optimum value search characterized in that a contribution rate indicating the magnitude of influence of an error factor is obtained with respect to the optimum value obtained in the search, and the error factor is changed based on the magnitude of the contribution rate. A support method is provided. In the optimum value search support method according to claim 5 or 6,
An optimum value search support method is provided in which tolerances of design factors are used as the error factors. A program used when designing, analyzing, or testing a device having multiple factors that affect characteristics,
A first creation function for creating a first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table including a matrix of each characteristic and each factor;
A selection function for selecting the combination that provides the most excellent characteristic value from the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table,
A reset function for resetting the level value of each factor in the characteristic corresponding to the combination selected by the selection function in the orthogonal table;
A first search function for searching for an optimum value that is the most excellent characteristic value from among the characteristic values by repeatedly performing selection by the selection function after resetting by the resetting function;
A second creation function for creating a second orthogonal table in which an optimum value searched by the first search function is set as a median value and an error factor affecting the fluctuation of the characteristic value is set;
A program for causing a computer to realize a second search function for obtaining an average value and a standard deviation of characteristics due to error factors from characteristic values obtained based on a combination with the first and second orthogonal tables is provided. A program used when designing, analyzing, or testing a device having multiple factors that affect characteristics,
A first creation function for creating a first orthogonal table in which a level value obtained from an initial value of each factor is set at each coordinate of a two-dimensional table including a matrix of each characteristic and each factor;
A selection function for selecting the combination that provides the most excellent characteristic value from the characteristic values obtained based on the combination of the level values of the factors of the same characteristic from the respective characteristics in the first orthogonal table,
A reset function for resetting the level value of each factor in the characteristic corresponding to the combination selected by the selection function in the first orthogonal table;
A first search function for searching for an optimum value that is the most excellent characteristic value from among the characteristic values by repeatedly performing selection by the selection function after resetting by the resetting function;
A second creation function for creating a second orthogonal table in which an optimum value searched and finally obtained by the first search function is set as a median value and an error factor affecting the fluctuation of the characteristic value is set. ,
A program for causing a computer to realize a second search function for obtaining an average value and a standard deviation of characteristics due to error factors from characteristic values obtained based on a combination with the first and second orthogonal tables is provided. In the program according to claim 9 or claim 10,
A program is provided in which a contribution rate indicating the magnitude of the influence of the error factor is obtained with respect to the optimum value obtained by the search, and the error factor is changed based on the magnitude of the contribution rate. In the program according to claim 9 or claim 10,
A program is provided in which the tolerance of each design factor is used as the error factor.

Images