Information processing device, control device, and recording medium

Abstract

An information processing device 1 obtains a range of values for a manipulated variable corresponding to a minimum constraint as a minimum solution set range, and sets a solution set range in which the range of solutions is limited inward of the minimum solution set range by a distance D determined by a ratio for the distance between an ideal value for the constraint and a value corresponding to the minimum constraint. The information processing device 1 then presents the solution set range, which is a restricted range of values for the manipulated variable.

Description

Information processing device, control device, and recording medium

[0001] The present invention relates to an information processing device, a control device, and a recording medium.

[0002] In the manufacture of pharmaceuticals, a method is known in which constraints are set in advance for various indicators that vary depending on raw materials and manufacturing process parameters (input variables), and the range of input variables that satisfies the constraints (called design space) is calculated and used (e.g., Non-Patent Document 1).

[0003] US Department of Health and Human Services Food and Drug Administration, Guidance for Industry Q8(R2) Pharmaceutical Development, Nov.2009

[0004] The above-mentioned conventional method is widely used as a method for determining the range of input variables that can guarantee the quality of the manufactured pharmaceuticals. However, since it is sufficient to maintain the determined range, the reality is that no consideration has been given to input variables that can produce products of higher quality.

[0005] Determining the optimal parameters within the range of input variables that satisfy the constraints can be achieved by solving a constrained optimization problem. Determining parameters in this way is not limited to pharmaceutical manufacturing, but can be applied to a variety of fields.

[0006] The present invention has been made in consideration of the above-mentioned situation, and one of its objects is to provide an information processing device, a control device, and a recording medium that can provide information for optimizing parameters during product manufacturing under constraints such as specified product quality.

[0007] An information processing device according to one aspect of the present invention includes: a space determination means for determining, as a minimum solution set range, a range of values ​​of the manipulated variable corresponding to at least one constraint that is numerically determined in relation to an artificially controllable manipulated variable; a restricted range setting means for setting a solution set range that is a range of values ​​of the manipulated variable that is more restricted than the minimum solution set range, the restricted range setting means calculating the distance between an ideal value G for the constraint and a value G corresponding to the minimum constraint for the corresponding constraint, and setting a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value G and the ideal value G, the distance D being determined by a predetermined ratio r (0 < r ≦ 1) to the distance between the value G and the ideal value G; and a presentation means for presenting at least the solution set range that is the restricted range of values ​​of the manipulated variable set by the restricted range setting means.

[0008] This makes it possible to provide information for optimizing parameters during product manufacturing under constraints such as predetermined product quality.

[0009] FIG. 1 is a block diagram showing an example of the configuration of an information processing device according to an embodiment of the present invention; FIG. 2 is a functional block diagram showing an example of an information processing device according to an embodiment of the present invention; FIG. 3 is an explanatory diagram showing an overview of a solution restriction range calculated by an information processing device according to an embodiment of the present invention; FIG. 4 is another explanatory diagram showing an overview of a solution restriction range calculated by an information processing device according to an embodiment of the present invention; FIG. 5 is a still another explanatory diagram showing an overview of a solution restriction range calculated by an information processing device according to an embodiment of the present invention; FIG. 6 is an explanatory diagram showing an example of an output from an information processing device according to an embodiment of the present invention; and FIG. 7 is a flowchart showing an example of the operation of an information processing device according to an embodiment of the present invention.

[0010] An information processing device 1 according to an embodiment of the present invention includes a control unit 11, a storage unit 12, an operation unit 13, a display unit 14, and an input / output unit 15, as shown in FIG.

[0011] The control unit 11 is a circuit including one or more program-controlled processors, such as a CPU, and operates according to a program stored in the memory unit 12. In this embodiment, the control unit 11 first determines a minimum solution set range, which is a range of values ​​of at least one constraint numerically defined in relation to an artificially controllable manipulated variable, corresponding to the minimum constraint. The control unit 11 then sets a solution set range, which is a range of values ​​of the manipulated variable that is more restricted than the minimum solution set range. That is, the control unit 11 determines the distance between an ideal value GI related to the constraint and a value GB corresponding to the minimum constraint, and sets a solution set range that is limited inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, which is determined by a predetermined ratio r (0 < r ≦ 1) of the distance between the value GB and the ideal value GI. The control unit 11 then presents at least the solution set range, which is the limited range of values ​​of the manipulated variables that has been set. The detailed operation of the control unit 11 will be described later.

[0012] The storage unit 12 is a memory device or a disk device, and stores a program executed by the control unit 11. This program may be provided by being stored in a computer-readable, non-transitory recording medium and copied to the storage unit 12. The storage unit 12 also operates as a work memory for the control unit 11.

[0013] The operation unit 13 is a keyboard, a mouse, etc., which accepts operations from the user and outputs information representing the operations (input information, etc.) to the control unit 11. The display unit 14 is a display, etc., which displays and outputs information to present to the user in accordance with instructions input from the control unit 11.

[0014] The input / output unit 15 includes a network interface, a serial interface, etc. This input / output unit 15 transmits and receives various information to and from external devices (such as manufacturing equipment) in accordance with instructions input from the control unit 11.

[0015] Next, a description will be given of the operation of the control unit 11 of the information processing device 1 according to this embodiment. In this embodiment, the control unit 11 executes a program stored in the storage unit 12, and is configured to include an information receiving unit 21, a space determining unit 22, a restricted range setting unit 23, and an information presenting unit 24, as shown in FIG.

[0016] In the operation of the control unit 11 of this embodiment, the number of manually controllable operating variables (input variables) may be two or more. However, for simplicity of explanation, the following description will be given using an example in which there is only one operating variable.

[0017] The information receiving unit 21 receives input of information for determining the solution set range by the space determining unit 22. In one example of this embodiment, the information receiving unit 21 receives input of information such as experimental results related to manipulated variables and constraints responsive to the manipulated variables. For example, the information receiving unit 21 receives input of the results of an experiment conducted with a certain manipulated variable x (specifically, the flow rate of a raw material in the case of flow precision synthesis) while varying the manipulated variable x. Here, the experimental results are information that includes a set of the value of the manipulated variable x, an evaluation value of the experimental results related to safety, a purity value of the resulting product, and a yield value. The information receiving unit 21 receives multiple sets of these sets. Here, the evaluation value of the experimental results related to safety, the purity value of the resulting product, and the yield value are values ​​related to the constraints.

[0018] The space determination unit 22 determines, as a minimum solution set range, a range of values ​​of the manipulated variables corresponding to the minimum constraints based on the information received by the information reception unit 21. For example, when the information reception unit 21 receives the results of the above experiment, the space determination unit 22 estimates an equation (hereinafter referred to as an estimated correlation equation) that represents the response of the value of each constraint to the manipulated variable x by a method such as regression calculation or response surface methodology. Then, the space determination unit 22 determines a range of values ​​of the manipulated variable x that satisfies the minimum constraints (assuming that inputs are received from the user) that the values ​​of each constraint should satisfy.

[0019] For example, in the above example, the space determination unit 22 determines that the range of values ​​of the manipulated variable x is x > x1 from the constraint condition related to safety, determines that the range of values ​​of the manipulated variable x is x < x2 from the constraint condition related to purity, and determines that the range of values ​​of the manipulated variable x is x3 < x < x4 from the constraint condition related to yield. Here, it is assumed that x1 < x3 < x2 < x4.

[0020] In this case, the space determination unit 22 determines the range of the value of the operating variable x (the minimum solution set range) as x3<x<x2.

[0021] The restricted range setting unit 23 sets a solution set range, which is a range of values ​​of the manipulated variables that is more restricted than the minimum solution set range. Specifically, the restricted range setting unit 23 calculates the distance |GI - GB| between the ideal value GI for each constraint, which is determined for that constraint, and the value GB corresponding to the minimum constraint for that constraint. Here, |α| means the absolute value of α (the same applies below). The restricted range setting unit 23 then sets a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, which is determined by a predetermined ratio r (0 < r ≦ 1) to the distance between the value GB and the ideal value GI.

[0022] Specifically, the ideal value GI for the yield is set to "1," and the minimum constraint value GB is set to 0.8. In this case, the limit range setting unit 23 determines the range between these values ​​GB and the ideal value GI, that is, the yield I(x) is 0.8≦I(x)≦1, and the ratio r of the distance |I(x)−GB| from the value GB to |GI−GB| is: to find the value of I(x) corresponding to a given r.

[0023] The limited range setting unit 23 then sets the distance |xB - x'| between the value x' of the manipulated variable corresponding to the calculated I(x) and the value xB of the manipulated variable corresponding to the value GB as distance D, and sets a solution set range that limits the range of solutions inward (in the direction narrowing the set of solutions) from the minimum solution set range by the value x' corresponding to this distance D. Note that if the minimum solution set range has a lower limit and an upper limit, the solution set range is set to a range limited by x' from both limits.

[0024] In the above example, for example, when r = 0.05, |GI - GB| = |1 - 0.8| = 0.2, so |I(x) - GB| = 0.2 × 0.05 = 0.01, and therefore the limit range setting unit 23 determines the value of I(x) corresponding to r = 0.05 as I(x) = 0.01 + 0.8 = 0.81 (adopting I(x) that is closer to the ideal value).

[0025] When there are two values ​​GB corresponding to the constraint conditions (upper and lower boundaries), such as the yield constraint conditions described above, the value of I(x) is found for each of them.

[0026] In the above example, the limit range setting unit 23 determines the value of I(x) corresponding to the ratio r for the three constraints of safety, purity, and yield. Hereinafter, it is assumed that I(x) is determined for the constraint of safety, I(x) for purity, and I(x) corresponding to the lower boundary and I(x) corresponding to the upper boundary for the yield.

[0027] The limit range setting unit 23 determines the values ​​of the manipulated variables x (denoted as x'1, x'2, x'3, and x'4) corresponding to the determined values ​​of I(x), I1(x), I2(x), I3(x), and I4(x), respectively, using an estimated correlation equation between the corresponding constraints and the manipulated variables. The limit range setting unit 23 further determines the distances D between the determined values ​​of the manipulated variables x and the corresponding boundaries (x1, x2, x3, and x4) of the minimum solution set range: D1 = |x1 - x'1| D2 = |x2 - x'2| D3 = |x3 - x'3| D4 = |x4 - x'4|, and selects the smallest value min(Di) (i = 1, 2, ...) among these.

[0028] The limit range setting unit 23 limits the minimum solution set range using the selected minimum distance Di. For example, in the above example, if D4 is the minimum, the limit range setting unit 23 sets the range of the value of the manipulated variable x (solution set range) as x3 + D4 < x < x2 - D4 using the minimum solution set range x3 < x < x2 and this distance D4. Note that if x3 + D4 > x2 - D4 at this time, the limit range setting unit 23 determines that there is no solution corresponding to the ratio r, and ends the processing.

[0029] The information presenting unit 24 presents to the user information representing the solution set range set by the limit range setting unit 23 by displaying it on the display unit 14. The information presenting unit 24 may also output the information representing the solution set range set by the limit range setting unit 23 to another device via the input / output unit 15.

[0030] In this example, the limit range setting unit 23 may sequentially obtain solution set ranges corresponding to a plurality of different predetermined ratios r=r1, r2... (for example, 0<r1<r2<...<1).

[0031] In this example, the limit range setting unit 23 calculates the value of I(x) corresponding to the ratio r for each specified constraint (in the above example, the three constraints of safety, purity, and yield), and for each calculated value I(x) (i = 1, 2, ...), calculates the value x'i of the corresponding manipulated variable x using an estimated correlation equation between the corresponding constraint and the manipulated variable. The limit range setting unit 23 further calculates the distance Di from the calculated value x'i of the manipulated variable and the corresponding boundary (xi) of the minimum solution set range as Di = |xi - x'i|, and selects the smallest value min(Di) (i = 1, 2, ...) among these.

[0032] The limit range setting unit 23 then uses the selected value of the smallest distance Di to limit the minimum solution set range and set the solution set range corresponding to r. Note that if x_low + Di > x_high - Di at this time, the limit range setting unit 23 determines that there is no solution corresponding to the ratio r and terminates the processing. Here, x_low means the lower boundary of the minimum solution set range, and x_high means the upper boundary of the minimum solution set range (in the above example, x_low = x3, x_high = x2).

[0033] On the other hand, if x_low + Di < x_high - Di, the limit range setting unit 23 further increases the ratio r by a predetermined value (or a value specified by the user) Δr (rk+1 = rk + Δr), and repeats the above process to set the solution set range corresponding to the new rk+1.

[0034] In this case, the limit range setting unit 23 repeats the above process until there are no more solution set ranges, sequentially setting solution set ranges corresponding to r1, r2, .... The information presenting unit 24 presents each of the solution set ranges thus set to the user. This presentation is performed, for example, by graphically displaying each solution set range for the manipulated variable x, as shown in FIG.

[0035] The user determines the manipulated variable x (i.e., the manufacturing condition) assuming that the optimum value of the manipulated variable x is in the smallest solution set range (R) among the displayed solution set ranges.

[0036] [Display of Optimal Value] Furthermore, the information processing device 1 may obtain an optimal value as follows and present it to the user. That is, for example, as one of the processes of the restriction range setting unit 23, the information processing device 1 obtains, as the optimal value, the value of the manipulated variable that maximizes the distance D (the minimum value when distances D corresponding to multiple constraint conditions are obtained for a certain ratio r) within the set minimum solution set range or the solution set range.

[0037] In this example, the information processing device 1 finds the optimal value of the operating variable x_opt by searching for the maximum value of the distance D while changing the operating variable x within the minimum solution set range or solution set range that is the smallest (narrowest range of possible solutions) set before performing the process to find the optimal value.

[0038] When the information processing device 1 finds the optimum value of the operating variable x_opt, the information presenting unit 24 presents the value of the operating variable x_opt to the user.

[0039] [When there are multiple operating variables] Furthermore, as already mentioned, even when there are multiple operating variables, the information processing device 1 of this embodiment presents the solution set range for each operating variable and also presents a set of operating variables that result in an optimal value by performing similar processing.

[0040] In this example, the control unit 11 of the information processing device 1, in its operation as the information receiving unit 21, receives inputs such as information specifying a plurality of manipulated variables and information on experimental results related to constraints (there may be a plurality of constraints) corresponding to each of the plurality of manipulated variables. For example, the information receiving unit 21 receives inputs of the results of an experiment conducted for certain manipulated variables x1 and x2 while varying these manipulated variables x1 and x2. Here, the experimental results are information in the form of pairs of values ​​of the manipulated variables x1 and x2 and values ​​representing constraints such as yield, safety, purity (amount of impurities), etc., and the information receiving unit 21 receives a plurality of such pairs.

[0041] Also in this example, the space determination unit 22 determines the range of values ​​of the manipulated variables corresponding to the minimum constraints as the minimum solution set range based on the information received by the information receiving unit 21. In this example, when the information receiving unit 21 receives the results of the above experiment, the space determination unit 22 estimates an equation (hereinafter referred to as an estimated correlation equation) that represents the response of the values ​​of each constraint to the multiple manipulated variables x1, x2... by a method such as regression calculation or response surface methodology. Then, the space determination unit 22 determines the range of values ​​of each manipulated variable x1, x2... (minimum solution set range) that satisfies the minimum constraints (assuming input is received from the user) that the values ​​of each constraint must satisfy.

[0042] For example, when there are two manipulated variables and the system is two-dimensional, the minimum solution set range is shown as an area limited by constraints such as yield, safety, and purity, as illustrated in Figure 4 (Figure 4(R)). (Note that here, the response surface is defined as a surface that monotonically increases or decreases with respect to each manipulated variable.)

[0043] The restricted range setting unit 23 sets a solution set range, which is a range of values ​​of the manipulated variables that is more restricted than the minimum solution set range set by the space determination unit 22. As in the example already described, the restricted range setting unit 23 calculates the distance |GI - GB| between the ideal value GI for each constraint, which is determined for each constraint, and the value GB corresponding to the minimum constraint for the corresponding constraint. The restricted range setting unit 23 then sets a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, which is determined by a predetermined ratio r (0 < r ≦ 1) to the distance between the value GB and the ideal value GI.

[0044] The limit range setting unit 23 repeats the following process for each constraint condition. That is, for the i-th constraint condition, the limit range setting unit 23 calculates, for each manipulated variable x, the ratio r of the distance |I(x)-GB| from the value GB to |GI-GB|: Using the above equation, the value of Ii(xj) (i=1, 2..., j=1, 2...) corresponding to a predetermined r is found between these values ​​GB and the ideal value GI, where Ii(xj) means the value obtained by solving equation (1) for the manipulated variable xj related to the i-th constraint, corresponding to a predetermined value of r.

[0045] The limit range setting unit 23 determines the value of the manipulated variable xj (referred to as x'ij) corresponding to each of the Ii(xj) determined for the predetermined ratio value r, using an estimated correlation equation between the corresponding constraint and the manipulated variable. The limit range setting unit 23 further determines the distance Dij from the determined value x'ij of the manipulated variable to the surface (curve in the case of two dimensions) xiB that defines the boundary of the corresponding minimum solution set range.

[0046] When the limit range setting unit 23 determines the distance Dij (j = 1, 2, ...) from the surface (a curve in the two-dimensional case) x iB that defines the boundary of the minimum solution set range for the i-th constraint for each manipulated variable, it calculates the minimum value min(D iB) of these distances and sets a surface x' iB that defines the solution set range by limiting the range of solutions inward (in the direction narrowing the set of solutions) from the surface x iB that defines the boundary of the minimum solution set range by the value x' corresponding to this minimum value.

[0047] The limit range setting unit 23 repeats the above process for each constraint condition, sets surfaces x′iB that define the solution set range for each constraint condition, and sets a solution set range R′ that limits the solution set range to the minimum using these surfaces x′iB (i = 1, 2, ...) (Figure 5).

[0048] If the range of solutions is exhausted due to the surface x'iB (i=1, 2, . . . ), the limited range setting unit 23 determines that there is no solution corresponding to the ratio r and terminates the process.

[0049] The information presenting unit 24 presents to the user information representing the solution set range set by the limit range setting unit 23 by displaying it on the display unit 14. The information presenting unit 24 may also output the information representing the solution set range set by the limit range setting unit 23 to another device via the input / output unit 15.

[0050] In this example, the limit range setting unit 23 may also sequentially determine solution set ranges corresponding to a plurality of different predetermined ratios r = r1, r2, ... (for example, 0 < r1 < r2 < ... < 1).

[0051] In this case, the limit range setting unit 23 determines the value of I(x) corresponding to the ratio r for each specified constraint (e.g., constraints such as safety, purity, and yield). The limit range setting unit 23 further determines the value x'ij of the corresponding jth manipulated variable x for each determined value I(x) (i = 1, 2 ...) using an estimated correlation equation between the corresponding constraint (i-th constraint) and the manipulated variable (j-th manipulated variable). The limit range setting unit 23 determines the distance Dij from the determined manipulated variable value x'ij and the corresponding boundary (x) of the minimum solution set range, and selects the smallest value Dij = min(Dij) (j = 1, 2 ...) among the distances Dij related to each manipulated variable for each i-th constraint.

[0052] The limit range setting unit 23 then uses the value of the smallest distance Di selected for each constraint to limit the solution set range to the minimum and set the solution set range corresponding to r. If the solution set range is exhausted at this time, it is determined that there is no solution corresponding to the ratio r, and the limit range setting unit 23 ends the process.

[0053] On the other hand, if a solution set range exists, the limit range setting unit 23 further increases the ratio r by a predetermined value (or a value specified by the user) Δr (r = r + Δr), and repeats the above process to set a solution set range corresponding to the new r.

[0054] In this case, the limit range setting unit 23 repeats the above process until the solution set range is exhausted, sequentially setting solution set ranges corresponding to r1, r2, .... The information presenting unit 24 presents each of the solution set ranges thus set to the user. This presentation is performed, for example, by graphically displaying each solution set range for the manipulated variable xj (j = 1, 2, ...). Specifically, when there are two manipulated variables, each of the solution set ranges becomes a two-dimensional region, which can be illustrated like a contour map (Figure 6).

[0055] The user determines each of the manipulated variables xj (i.e., each manufacturing condition) assuming that the optimum set of manipulated variables xj is in the smallest solution set range among the displayed solution set ranges.

[0056] Also, in the information processing device 1 of this example, an optimal set of values ​​of the manipulated variables xj may be found and presented to the user. In this case, the information processing device 1 also finds, as one of the processes of the restriction range setting unit 23, a set of values ​​of the manipulated variables that maximizes the distance D (the minimum value when distances D corresponding to multiple constraint conditions and manipulated variables are found for a certain ratio r) within the set minimum solution set range or solution set range as an optimal set of values.

[0057] In this example, the information processing device 1 finds the optimal value of the operating variable xj_opt (j = 1, 2, ...) by searching for the maximum value of the distance D while changing the set of operating variables xj within the minimum solution set range or solution set range that is the smallest (narrowest range of possible solutions) set before performing the process to find the optimal value.

[0058] When the information processing device 1 finds a set of the operational variables x_opt that results in an optimal value, the information presenting unit 24 presents the value of the operational variable x_opt to the user. This presentation may be performed by superimposing it on the display of the area of ​​each solution set illustrated in FIG. 6 (FIG. 6(Q)).

[0059] [Operation] The information processing device 1 of this embodiment has the above configuration and operates as follows: The information processing device 1 executes the process illustrated in Fig. 7 and accepts input from the user information specifying a plurality of operation variables xj (j = 1, 2...), for example, two operation variables x1 and x2, and information on experimental results related to constraint conditions (there may be a plurality of constraint conditions) corresponding to each of the plurality of operation variables (S11: Acceptance of Experimental Results).

[0060] Here, it is assumed that the input of the results of an experiment conducted by varying the manipulated variables x1 and x2 is accepted. The experimental results are information consisting of pairs of values ​​of the manipulated variables x1 and x2 and values ​​representing constraints such as yield, safety, purity (amount of impurities), etc. The information processing device 1 accepts multiple pairs of these pairs.

[0061] Based on the information received in step S11, the information processing device 1 determines a range of values ​​of the manipulated variables corresponding to the minimum constraints as a minimum solution set range (S12). Here, the information processing device 1 estimates an equation (hereinafter referred to as an estimated correlation equation) representing the response of the values ​​of each constraint to multiple manipulated variables x1, x2... using response surface methodology based on the experimental results received in step S11. The information processing device 1 then determines a range of values ​​(minimum solution set range) for each manipulated variable x1, x2... that satisfies the minimum constraints (assuming input is received from the user) that each constraint value must satisfy. As already explained, the minimum solution set range in this example is shown as a region (region R not restricted by any constraints) that satisfies all of the constraints, such as yield, safety, and purity, by superimposing the regions restricted by these constraints, as illustrated in FIG. 4.

[0062] Next, the information processing device 1 sets the value of the ratio r0 to a predetermined initial value (e.g., r0 = 0.05) (S13) in order to set a solution set range that is a range of values ​​of the operating variables that is more restricted than the minimum solution set range obtained in step S12, and repeats the following processing for each constraint condition.

[0063] The information processing device 1 also determines, for the i-th constraint, for each manipulated variable xj (j = 1, 2 ...), the value Ii(xj) (i = 1, 2 ..., j = 1, 2 ...) corresponding to the above rk between the value GB and the ideal value GI, assuming that the ratio between |I(x) - GB| and the distance from the value GB shown in equation (1) is equal to the above rk (k = 0, 1, 2 ...) (S14). Here, Ii(xj) means the value obtained by solving equation (1) corresponding to the value of the ratio rk at the time of processing for the manipulated variable xj related to the i-th constraint.

[0064] The information processing device 1 determines the value (x'ij) of the manipulated variable xj corresponding to each of the Ii(xj) determined for the set rk using an estimated correlation equation between the corresponding ith constraint and the manipulated variable xj (S15). The information processing device 1 further determines the distance Dij from the determined manipulated variable value x'ij and the surface (curve in the case of two dimensions) xiB that defines the boundary of the corresponding minimum solution set range (S16).

[0065] The information processing device 1 repeatedly executes steps S14 to S16 for each operation variable xj, calculates the minimum value min(Dij) of the obtained distances Dij (S17), and sets a surface x'iB that defines the solution set range by limiting the range of solutions by the value x'i = min(Dij) corresponding to the minimum value inward from the surface x that defines the boundary of the solution set range (in the direction of narrowing the solution set) (S18).

[0066] The information processing device 1 repeatedly executes the processes from steps S14 to S18 (including the process repeated for each operating variable) for each constraint condition, and sets the surface x'iB (i = 1, 2, ...) that defines the solution set range for each constraint condition.The information processing device 1 then overlaps the areas restricted by these surfaces to set the area that satisfies all of the constraints (the area that is not restricted by any constraints) as the solution set range corresponding to the ratio rk at this point (S19).

[0067] The information processing device 1 then checks whether or not a solution set range was set in step S19, i.e., whether or not a range of solutions exists that can be created by overlapping the surfaces x'iB (i = 1, 2, ...) (S20). If a range of solutions exists (S20: Yes), the information processing device 1 updates the ratio r at that time by a further predetermined value (or a value designated by the user) Δr (rk+1 = rk + Δr) (S21), returns to the process of repeating for each constraint condition, and repeats the process from step S14 onwards (A).

[0068] On the other hand, if there is no range with a solution in step S20 (S20: No), the information processing device 1 terminates the process assuming that there is no solution corresponding to the ratio r, and displays information indicating the solution set range (or the minimum solution set range) determined for each ratio r, r, r, ... (S22). This display may be performed as in the example of FIG. 6 already shown.

[0069] According to this example of the present embodiment, it is possible to provide information that represents the range of values ​​of manipulated variables that satisfy stricter constraints, such as information for optimizing parameters during product manufacturing under constraints such as predetermined product quality.

[0070] [Display of Boundary Lines] As described in the examples so far, the surface (or curve, straight line) enclosing the solution set range is formed by combining the surfaces (or lines) corresponding to each of the multiple constraints.

[0071] Therefore, when displaying information indicating the solution set range, the information processing device 1 of this embodiment may display the surfaces (or lines) of each constraint condition that defines the solution set range in a manner that makes them distinguishable from each other, such as in different colors.

[0072] In this way, it is possible to confirm which range of the manipulated variables is mainly restricted by which constraints.

[0073] [Collaboration with Manufacturing Apparatus] As described in the examples above, the manipulated variables may relate to manufacturing conditions for an object. In this case, the information processing device 1 of this embodiment may output its output to a manufacturing apparatus for the object. The manufacturing apparatus that receives the output of the information processing device 1 uses information on the solution set range presented by the information processing device 1 (if multiple solution set ranges are set, the narrowest solution set range may be used, for example) to determine manufacturing conditions for the object. For example, if the flow rate of raw materials in flow precision synthesis is used as the manipulated variable, the manufacturing apparatus that receives the information on the solution set range controls the manufacturing conditions so that raw materials are supplied at a flow rate that falls within the solution set range represented by the information.

[0074] REFERENCE SIGNS LIST 1 information processing device, 11 control unit, 12 storage unit, 13 operation unit, 14 display unit, 15 input / output unit, 21 information receiving unit, 22 space determining unit, 23 restricted range setting unit, 24 information presenting unit.

Claims

1. An information processing device comprising: a space determination means for determining, as a minimum solution set range, a range of values ​​of at least one constraint condition that is numerically determined in relation to an artificially controllable manipulated variable, the range of values ​​of the manipulated variable that corresponds to a minimum constraint condition; a restriction range setting means for setting a solution set range that is a range of values ​​of the manipulated variable that is more restricted than the minimum solution set range, the restriction range setting means determining a distance between an ideal value GI related to the constraint condition and a value GB related to the corresponding constraint condition that corresponds to the minimum constraint condition, and setting a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, the distance D being determined by a predetermined ratio r (0<r≦1) to the distance between the value GB and the ideal value GI; and a presentation means for presenting at least the solution set range that is the restricted range of values ​​of the manipulated variable set by the restriction range setting means.

2. An information processing device as described in claim 1, further comprising an optimal solution calculation means for determining values ​​of operational variables that maximize the distance D within the minimum solution set range or the solution set range, and the presentation means further presents the values ​​of operational variables that maximize the distance D determined by the optimal solution calculation means.

3. An information processing device as described in claim 1, wherein the restriction range setting means calculates, in the minimum solution set range, a distance between an ideal value GI for the constraint condition and a value GB corresponding to the minimum constraint condition related to the corresponding constraint condition, and sets a plurality of solution set ranges between the value GB and the ideal value GI, which limit the range of solutions inward from the minimum solution set range by distances D1, D2... determined by a plurality of predetermined ratios r = r1, r2... that are different from each other with respect to the distance between the value GB and the ideal value GI; and the presentation means presents a solution set range which is a range of values ​​of a plurality of different, restricted operating variables set by the restriction range setting means.

4. An information processing device according to claim 3, further comprising: an optimal solution calculation means for determining values ​​of operation variables that maximize the distance D within a solution set range among the plurality of solution set ranges in which the corresponding distance Di (i = 1, 2 ...) is the largest; and the presentation means for presenting the values ​​of operation variables that maximize the distance D determined by the optimal solution calculation means.

5. An information processing device according to any one of claims 1 to 4, wherein the operational variables are operational variables relating to manufacturing conditions of an object, and information on the solution set range presented by the presentation means is used in the process of determining the manufacturing conditions of the object.

6. A control device that receives input of information related to manufacturing conditions and is connected to a manufacturing device that manufactures an object and controls the manufacturing device, comprising: a space determination means for determining, as a minimum solution set range, a range of values ​​of the manipulated variables corresponding to at least one constraint condition that is numerically determined in relation to an manipulated variable related to the manufacturing condition, the minimum constraint condition; a restriction range setting means for setting a solution set range that is a range of values ​​of the manipulated variables that is more restricted than the minimum solution set range, the restriction range setting means determining a distance between an ideal value GI related to the constraint condition and a value GB corresponding to the minimum constraint condition related to the corresponding constraint condition, and setting a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, the distance D being determined by a predetermined ratio r (0<r≦1) to the distance between the value GB and the ideal value GI; a presentation means for presenting at least the solution set range that is the limited range of values ​​of the manipulated variables set by the restriction range setting means; and an output means for outputting information related to the manufacturing conditions that are set by the manipulated variables within the solution set range presented by the presentation means to the manufacturing device.

7. A computer-readable, non-transitory recording medium storing a program causing a computer to function as: a space determination means for determining, as a minimum solution set range, a range of values ​​of at least one constraint condition that is numerically determined in relation to an artificially controllable manipulated variable, the minimum constraint condition; a restriction range setting means for setting a solution set range that is a range of values ​​of the manipulated variable that is more restricted than the minimum solution set range, the restriction range setting means determining the distance between an ideal value GI related to the constraint condition and a value GB related to the corresponding constraint condition that corresponds to the minimum constraint condition, and setting a solution set range that limits the range of solutions inward from the minimum solution set range by a distance D between the value GB and the ideal value GI, the distance D being determined by a predetermined ratio r (0<r≦1) to the distance between the value GB and the ideal value GI; and a presentation means for at least presenting the solution set range that is the limited range of values ​​of the manipulated variable set by the restriction range setting means.

Images