Operation support device, operation support method, and program

Abstract

To provide a technique for calculating a setting value reflecting a control logic.SOLUTION: An operation support device comprises: an acquisition section that acquires operation data including a state variable representing a state of a control target at current time, a logic variable representing a control value of the control target at the current time, and a setting variable representing a setting value for the control target at the current time; a calculation section that calculates the setting variable in a predetermined period in the future by solving a predetermined optimization problem using the operation data, a machine learning model for predicting the state variable, and a control logic for the control target; and an output section that outputs the setting variable in the period to a predetermined output destination determined in advance.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to a driving assistance device, a driving assistance method, and a program. [Background technology]

[0002] In plants such as combustion furnaces, automatic control is performed using a predetermined control logic based on measured values ​​of the furnace's combustion state, etc. (For example, Patent Documents 1 to 7, Non-Patent Document 1, etc.). On the other hand, in order to achieve stable operation of the plant, operators also change the setting values ​​based on the measured values ​​of the combustion state, etc. For this reason, in order to support the operator in operating the plant, it is necessary to propose optimal setting values. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 7-113513 [Patent Document 2] Japanese Patent Application Laid-Open No. 2000-46323 [Patent Document 3] Japanese Patent Application Laid-Open No. 2001-82719 [Patent Document 4] Japanese Patent Application Laid-Open No. 2008-76012 [Patent Document 5] Japanese Patent Publication No. 2021-134966 [Patent Document 6] Japanese Patent Application Publication No. 2023-59470 [Patent Document 7] Japanese Patent Application Publication No. 2023-104104 [Non-patent literature]

[0004] [Non-Patent Document 1] Yashima, S., Large-scale Waste-to-Energy Generation: A Case Study of the Katsushika Incineration Plant in Tokyo, Environmental Technology, Vol. 9, No. 5, (1980) Summary of the Invention [Problem to be solved by the invention]

[0005] However, if the control logic is not reflected in the calculation of the optimal setting value, the setting value may not be applicable in practice, which may result in operators being unable to trust the setting value and preventing sufficient plant operation support.

[0006] The present disclosure has been made in consideration of the above points, and aims to provide a technique for calculating a setting value that reflects control logic. [Means for solving the problem]

[0007] A driving assistance device according to one aspect of the present disclosure includes an acquisition unit that acquires driving data including a state variable that represents a state of a control object at the current time, a logic variable that represents a control value of the control object at the current time, and a setting variable that represents a setting value for the control object at the current time; a calculation unit that calculates setting variables for a predetermined future period by solving a predetermined optimization problem using the driving data, a machine learning model that predicts the state variables, and the control logic for the control object; and an output unit that outputs the setting variables for the period to a predetermined output destination. [Effects of the Invention]

[0008] Techniques are provided for calculating setpoints that reflect control logic. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of a plant control system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the driving assistance device according to the present embodiment. [Figure 3] FIG. 2 is a diagram illustrating an example of a functional configuration of the driving assistance device according to the present embodiment. [Figure 4]4 is a flowchart illustrating an example of a driving assistance process according to the present embodiment. [Figure 5] This is a diagram (part 1) showing an example of how to use it. [Figure 6] This is a diagram (part 2) showing an example of how to use the system. DETAILED DESCRIPTION OF THE INVENTION

[0010] An embodiment of the present invention will be described in detail below with reference to the drawings. In the following embodiment, a plant control system 1 will be described that includes an operation support device 10 that can calculate setting values ​​that reflect control logic and propose the setting values ​​to an operator, for a plant such as a waste incineration plant.

[0011] Hereafter, the physical quantities (e.g., temperature, pressure, flow rate, gas concentration, etc.) that represent the plant state measured by various sensors are called "state variables," and x i (i=1, ,I). Similarly, the control value determined by the control logic is called a "logic variable," and y j (j=1, ,J). Similarly, the setting values ​​set as target values ​​or threshold values ​​of certain physical quantities for the control device that controls the plant are called "setting variables", and r k (k=1, ,K). Also, the state variable x at discrete time s (hereafter simply referred to as "time s") i , logic variable y j and the setting variable r k x i (s), y j (s) and r k Let us denote it as (s), where I is the total number of state variables, J is the total number of logic variables, and K is the total number of setting variables. A control value is a value that represents a control command for controlling the operation of equipment included in a plant. The control value may be a discrete value or a continuous value, but a specific example of a control value that takes a discrete value is a value that represents the start or stop of a feeder or stoker in a waste incineration plant.

[0012] Also, below, the state variable x i (i=1, ,I) and logic variable y j (j=1, ,J) and the setting variable r k The data consisting of (k=1,...,K) is called "operation data" and is represented by z. The operation data z at time s is z(s)=(x1(s),...,x I (s),y1(s),···,y J (s),r1(s),···,r K (s)).

[0013] Control logic refers to the process executed by the control device of a plant to control the plant. Specific examples of control logic include threshold processing (on-off control processing) for a certain state variable, control processing using a control method such as PID control, etc.

[0014] <Example of overall configuration of plant control system 1> An example of the overall configuration of a plant control system 1 according to this embodiment is shown in Fig. 1. As shown in Fig. 1, the plant control system 1 according to this embodiment includes an operation support device 10, a control device 20, and a target plant 30. Here, the operation support device 10 and the control device 20 are connected to each other so as to be able to communicate with each other via an arbitrary communication network. Similarly, the control device 20 and the target plant 30 are connected to each other so as to be able to communicate with each other via an arbitrary communication network.

[0015] The operation support device 10 calculates a setting variable r that reflects the control logic of the target plant 30 based on the operation data z acquired from the control device 20. k In addition, the driving assistance device 10 calculates the setting variable r k This allows the operator to set the configuration variable r k The setting variable r that is actually set for the control device 20 is k It will be possible to make decisions such as:

[0016] The control device 20 is configured with a predetermined control logic and a setting variable r set by an operator. k That is, the control device 20 is a controller that controls the target plant 30 based on the state variable x i and its state variable x i and the setting variable r set to itself k and logic variable y j and the logic variable y at the next time from the control logic. j Determine the logic variable y j to the target plant 30. As a result, the target plant 30 (more precisely, the operation of the equipment included in the target plant 30) is controlled in accordance with the control logic.

[0017] The target plant 30 is any plant that is the target of operation assistance. The target plant 30 is not limited to a specific plant, but a waste incineration plant is a specific example of the target plant 30. However, the target plant 30 is not necessarily limited to a plant, and may be, for example, a supply and demand system such as an energy management system.

[0018] 1 is merely an example, and other configurations may be used. For example, an operator terminal operated by an operator may be provided in addition to the operation support device 10.

[0019] <Example of hardware configuration of driving assistance device 10> An example of the hardware configuration of the driving assistance device 10 according to this embodiment is shown in Fig. 2. As shown in Fig. 2, the driving assistance device 10 according to this embodiment includes an input device 101, a display device 102, an external I / F 103, a communication I / F 104, a RAM (Random Access Memory) 105, a ROM (Read Only Memory) 106, an auxiliary storage device 107, and a processor 108. Each of these pieces of hardware is connected to each other via a bus 109 so as to be able to communicate with each other.

[0020] The input device 101 is, for example, a keyboard, a mouse, a touch panel, a physical button, etc. The display device 102 is, for example, a display, a display panel, etc. Note that the driving assistance device 10 does not necessarily have to have at least one of the input device 101 and the display device 102.

[0021] The external I / F 103 is an interface with an external device such as a recording medium 103a. Examples of the recording medium 103a include a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), and a USB (Universal Serial Bus) memory card.

[0022] The communication I / F 104 is an interface for communicating with other devices and equipment such as the control device 20. The RAM 105 is a volatile semiconductor memory (storage device) that temporarily stores programs and data. The ROM 106 is a non-volatile semiconductor memory (storage device) that can store programs and data even when the power is turned off. The auxiliary storage device 107 is a non-volatile storage device (storage device) such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. The processor 108 is various types of arithmetic device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0023] 2 is an example, and the driving assistance device 10 may have other hardware configurations. For example, the driving assistance device 10 may have multiple auxiliary storage devices 107 or multiple processors 108, or may have various types of hardware other than the hardware shown in the figure.

[0024] <Example of functional configuration of driving assistance device 10> FIG. 3 shows an example of the functional configuration of the driving assistance device 10 according to this embodiment. As shown in FIG. 3, the driving assistance device 10 according to this embodiment includes a driving data acquisition unit 201, a similar setting extraction unit 202, an optimization calculation unit 203, and an input / output unit 204. These units are realized, for example, by a process in which one or more programs installed in the driving assistance device 10 are executed by the processor 108 or the like. The driving assistance device 10 according to this embodiment also includes a database 205. The database 205 is realized, for example, by a storage area of ​​a storage device such as the auxiliary storage device 107. Note that the database 205 may also be realized, for example, by a storage area of ​​a storage device or the like connected to the driving assistance device 10 via a communication network.

[0025] The operating data acquisition unit 201 acquires operating data z(t) at the current time t from the control device 20, where t is the current time.

[0026] The similar setting extraction unit 202 identifies the time s' of the past driving data z(s') that is most similar to the driving data z(t) among the past driving data z(s) stored in the database 205, and calculates the setting variable r k is extracted as a similar setting variable, where H is a predetermined integer equal to or greater than 1.

[0027] The optimization calculation unit 203 calculates the operating data z(t), the similar setting variables, and the future state variables x i Based on the prediction model that predicts the state variable x in the period from time t+1 to time t+H by solving a predetermined optimization problem based on the control logic, i , logic variable y j , and the setting variable r k Calculate.

[0028] The input / output unit 204 receives the state variable x from time t+1 to time t+H. i , logic variable y j , and the setting variable r kto a predetermined output destination (for example, the display device 102 such as a display). k When setting the variable r k and the setting variable r k is output to the control device 20.

[0029] The database 205 stores past driving data z acquired from the control device 20. Hereinafter, the past driving data will also be referred to as "driving performance data", and the set of driving performance data will be represented as E = {z(s)|s = tS, , t-1}, where S is an integer equal to or greater than 1.

[0030] The database 205 also stores the future state variables x i The target plant 30 stores a prediction model that predicts the above and a program or the like that simulates the control logic of the target plant 30. Hereinafter, a function that represents the prediction model is defined as f, and a function that represents an algorithm of a program or the like that simulates the control logic of the target plant 30 is defined as g.

[0031] The prediction model f is a state variable x i (i=1, ,I) and logic variable y j (j=1, ,J) and the setting variable r k (k=1,...,K) as input, the state variable x i Any machine learning model that predicts and outputs (i=1, , I) can be used. Such a machine learning model can be a linear model (e.g., linear regression, partial least squares, Lasso regression, etc.) or a nonlinear model (e.g., neural network, random forest, Transformer, etc.).

[0032] The control logic g is a state variable x i (i=1, ,I) and logic variable y j (j=1, ,J) and the setting variable rk (k=1,...,K) as input, the logic variable y j (j=1,...,J). Specific examples of control logic g include threshold processing (on-off control processing) that sets a logic variable to 1 or 0 when a certain state variable exceeds (or falls below) a threshold, processing that sets a logic variable to 1 or 0 when a certain state variable exceeds (or falls below) a set variable, and control processing that calculates a logic variable of continuous values ​​(which may have upper and lower limits) using a control method such as PID control. Other specific examples of control logic g include processing that sets a logic variable to 1 or 0 when a certain state variable deviates from a certain range set for a set variable.

[0033] <Driving assistance processing> An example of the driving assistance process according to this embodiment will be described with reference to FIG.

[0034] The operating data acquisition unit 201 acquires operating data z(t) at the current time t from the control device 20 (step S101).

[0035] The similar setting extraction unit 202 extracts similar setting variables through the following steps 1 and 2 (step S102).

[0036] Step 1: The similar setting extraction unit 202 identifies, from among the driving performance data z(s)∈E, the time s' of driving performance data z(s')∈E that is similar to the driving data z(t) acquired in step S101 above. Here, any measure of similarity between vectors can be used as a measure of the similarity between the driving data z(t) and each driving performance data z(s), such as cosine similarity or the distance between vectors. However, the similar setting extraction unit 202 identifies the time s' of driving performance data z(s')∈E that satisfies s'+H≦t−1.

[0037] Step 2: The similar setting extraction unit 202 extracts the setting variable r k (k=1,...,K) is extracted from the operation record data set E and used as the similar setting variable. Hereinafter, the similar setting variable will be referred to as r k Let '(s)(k=1,···,K, s=s'+1,···,H).

[0038] The optimization calculation unit 203 calculates the operation data z(t) and the similar setting variables r k '(s)(k=1,···,K, s=s'+1,···,H), a prediction model f, and a control logic g are used to solve a given optimization problem to calculate the state variable x for the period from time t+1 to time t+H. i , logic variable y j , and the setting variable r k (Step S103). Hereinafter, X={x i (t+h)|i=1,...,I, h=1,...,H}, Y={y j (t+h)|j=1,...,J, h=1,...,H}, R={r k (t+h)|k=1,···,K, h=1,···,H}. Also, f=(f1,···,f I ), g=(g1, ,g J ) In this case, the optimization calculation unit 203 calculates the state variable x in the period from time t+1 to time t+H by solving the following optimization problem. i , logic variable y j , and the setting variable r k The optimization calculation unit 203 may solve the following optimization problem by using an optimization technique such as metaheuristics or mathematical programming.

[0039] Objective function: Min R Obj(X,Y,R) Constraints: Cons c (X,Y,R),c∈C x i (t+h)=f i (X <h ,Y <h ,R<h ),i=1,···,I,h=1,···,H y j (t+h)=g j (X <h ,Y <h ,R <h ),i=1,···,I,h=1,···,H where C is the set of constraint numbers. <h When h=1, X <h ={x i (t)|i=1, ,I}, when h>1, X <h ={x i (t+h')|i=1,···,I, h'=1,···,h-1}. Similarly, Y <h When h=1, Y <h ={y j (t)|j=1,···,J}, when h>1, Y <h ={y j (t+h')|j=1,···,J, h'=1,···,h-1}. Similarly, R <h When h=1, R <h ={r k (t)|k=1,···,K}, when h>1, R <h ={r k (t+h')|k=1,···,K, h'=1,···,h-1}.

[0040] <Cons c Specific examples of (X, Y, R)≫ Cons c Specific examples of (X, Y, R) include the following:

[0041] ·r k min ≦r k (t+h)≦r k max This is true for each configuration variable r k is a predetermined upper limit value r k max Less than or equal to lower limit r k min This is a constraint that indicates that the condition is equal to or greater than the above.

[0042] x i (t+h)≦x i max This is true for each state variable x i is a predetermined upper limit x i max This is a constraint that indicates that the state variable x i When considering the exhaust gas concentration, it can be said that this represents a constraint that keeps the exhaust gas concentration below a predetermined regulatory value.

[0043] ·|r k (t+h)-r k (t+h-1)|≦D k max This is true for each configuration variable r k The amount of change per time is a predetermined upper limit D k max This is a constraint that indicates that the set value cannot be changed suddenly.

[0044] ≪x i (t+h)=f i (X <h ,Y <h ,R <h )Specific examples≫ f i (X <h ,Y <h ,R <h ) is a linear regression model that predicts the state variables at the next time from the state variables, logic variables, and setting variables at a certain time. i (t+h)=f i (X h-1 ,Y h-1 ,R h-1 ) where X h-1 ={x i (t+h-1)|i=1,···,I}, Y h-1 ={y j (t+h-1)|j=1,···,J}, R h-1 ={r k(t+h-1)|k=1,···,K}.

[0045] ≪y j (t+h)=g j (X <h ,Y <h ,R <h )Specific examples≫ g j (X <h ,Y <h ,R <h ) is, for example, x for some (i, j, k). i (t+h-1)≦r k If (t+h-1), then y j (t+h)=1, x i (t+h-1)>r k If (t+h-1), then y j For example, (t+h) = 0. This represents logic in which the logic variables at the next time are determined by the state variables and setting variables at the previous time.

[0046] <<Example of Obj(X,Y,R)>> A specific example of Obj(X,Y,R) is the weighted sum of one or more of the following Obj1, Obj2, and Obj3. For example, if Obj(X,Y,R) is the weighted sum of Obj1, Obj2, and Obj3, then Obj(X,Y,R)=λ1×Obj1+λ2×Obj2+λ3×Obj3. Here, λ1, λ2, and λ3 are weights (particularly, weights that satisfy λ1+λ2+λ3=1).

[0047] Obj1 The sum of the change in the set value at each time t+h is defined as Obj1. k (h)=|r k (t+h)-r k (t+h-1)|, Obj1 is Δ for k=1,···,K and h=1,···,H. k (h) is the sum of

[0048] Obj2 Setting variable r at each time t+hk (t+h) and similar setting variable r k The sum of the errors with '(s'+h) is Obj2. Specifically, δ k (h)=|r k (t+h)-r k '(s'+h)|, Obj2 is δ for k=1,···,K and h=1,···,H. k (h) is the sum of

[0049] Obj3 State variable x i Among them, the predetermined state variables such as exhaust gas concentration are expressed as x i Let (i∈Q). Here, Q is a set of numbers of predetermined state variables (especially state variables that represent physical quantities such as exhaust gas concentration, which are better if they are small and become abnormal if they are too large). In this case, x i Let Obj3 be the sum of (i∈Q).

[0050] By solving the above optimization problem, the state variable x i (t+h)(i=1,···,I, h=1,···,H) and the logic variable y j (t+h)(j=1,···,J, h=1,···,H) and the setting variable r k (t+h)(k=1,···,K, h=1,···,H) is obtained.

[0051] The input / output unit 204 receives the state variable x i (t+h)(i=1,···,I, h=1,···,H) and the logic variable y j (t+h)(j=1,···,J, h=1,···,H) and the setting variable r k (t+h)(k=1, . . . , K, h=1, . . . , H) to a predetermined output destination (step S104). i A graph representing (t+h)(i=1,···,I, h=1,···,H) and the logic variable y j The graph representing (t+h)(j=1,···,J, h=1,···,H) and the setting variable r k(t+h)(k=1, , K, h=1, , H) and a graph representing the state variables x i , logic variable y j , and the setting variable r k The setting variable r that is actually set for the control device 20 is k is determined, and the setting variable r is set in the control device 20. k It becomes possible to input the following.

[0052] It should be noted that if Obj2 is not used in Obj(X, Y, R) in step S103, step S102 does not have to be executed.

[0053] <Example> As an example of the above embodiment, a case where the target plant 30 is a stoker-type waste incineration plant will be described below.

[0054] In a stoker-type waste incineration plant, waste is sent into the furnace by moving the feeder or stoker, and air is blown into the waste inside the furnace to combust it.The heat generated by combustion is used to generate steam to generate electricity, and exhaust gases (NOx, CO, HCl, SO2, mercury, etc.) are generated during combustion.

[0055] In this embodiment, the furnace temperature, steam flow rate, and exhaust gas concentration are state variables, the feeder control command and stoker control command are logic variables, and the steam flow rate set value and air flow rate set value are set variables.

[0056] How to use (part 1) An example of how to use the operation support device 10 according to this embodiment is shown in Fig. 5. For example, as shown in the left diagram of Fig. 5, assume that after the current time t, the steam flow rate will fall significantly below the steam flow rate set value due to a feeder being stopped. In this case, by using the operation support device 10 according to this embodiment, it is possible to suggest the setting variables shown in the right diagram of Fig. 5 to the operator. By changing the setting variables to those shown in the right diagram of Fig. 5, the feeder will start up quickly, and a significant drop in the steam flow rate can be avoided.

[0057] Furthermore, the setting variables shown in the right diagram of Figure 5 are consistent with the control logic g, and when Obj2 is included in Obj(X, Y, R), it is similar to the operator's past operations, so stable operation can be expected.

[0058] How to use (part 2) An example of how to use the driving assistance device 10 according to this embodiment is shown in Fig. 6. The upper diagram in Fig. 6 shows the driving results when driving is performed according to the setting variables proposed by the driving assistance device 10 according to this embodiment without changing the setting values ​​as much as possible (i.e., when Obj1 is included in Obj(X,Y,R)). On the other hand, the lower diagram in Fig. 6 shows the driving results when driving is performed according to the setting variables proposed by the driving assistance device 10 according to this embodiment while further considering errors in the past setting variables and reduction of exhaust gas concentration (i.e., when Obj1, Obj2, and Obj3 are included in Obj(X,Y,R)).

[0059] As shown in the upper diagram of Figure 6, if air is injected to reduce the CO concentration when it rises, the set value will not be changed as much as possible, so the CO concentration will fall but the NOx concentration will rise. On the other hand, as shown in the lower diagram of Figure 6, if the error from the past set variable and the reduction in exhaust gas concentration are also taken into consideration, the air flow rate will be reduced when a decrease in CO concentration is expected, making it possible to suppress the increase in NOx concentration and achieve stable plant operation.

[0060] <Modification> Modifications of the above embodiment will be described below. Note that the following modifications can be combined with multiple modifications as appropriate, as long as they do not contradict each other.

[0061] Variation 1 4, when identifying the time s' of the driving performance data z(s') ∈ E similar to the driving data z(t), a moving average or the like may be further used. Specifically, for example, when using a moving average of the period up to time T in the past, first, x i (tT),···,x i (t) average μ x,i (t) and y j (tT),···,y j (t) average μ y,j (t) and r k (tT),···,r k (t) average μ r,k (t), and Z(t) = (x1(t), ,x I (t),y1(t),···,y J (t),r1(t),···,r K (t),μ x,1 (t),···,μ x,I (t),μ y,1 (t),···,μ y,J (t),μ r,1 (t),···,μ r,K Similarly, for each operation record data z(s)∈E, x i (sT),···,x i (s) average μ x,i (s) and y j (sT),···,y j (s) average μ y,j (s) and r k (sT),···,r k (s) average μ r,k (s), and Z(s)=(x1(s), ,x I (s),y1(s),···,y J (s),r1(s),···,r K (s),μ x,1 (s),···,μ x,I(s),μ y,1 (s),···,μ y,J (s),μ r,1 (s),···,μ r,K (s)), and identify the time of Z(s) that is most similar to Z(t) as s'.

[0062] Variation 2 Using the prediction model f and the control logic g, the setting variable r k Without changing the state variable x from time t+1 to time t+H i and logic variable y j The predicted result may also be output to the operator. That is, for k=1, ,K, r k (t)=r k (t+1)==r k (t+H), the state variable x from time t+1 to time t+H i and logic variable y j are predicted by the prediction model f and the control logic g, respectively, and the state variables x from time t+1 to time t+H are calculated. i , logic variable y j , and the setting variable r k This allows the operator to set the configuration variable r k The operation without changing the setting variable r proposed in step S105 above k The setting variable r actually set in the control device 20 is compared with the operation when k It becomes possible to determine

[0063] <Summary> As described above, the driving assistance device 10 according to this embodiment can predict future setting variables that reflect the control logic of the target plant 30, using a prediction model that predicts future state variables and the control logic of the target plant 30. This makes it possible to propose setting variables that are consistent with the control logic of the target plant 30 to the operator, and the operator can refer to these setting variables to determine the setting variables that will actually be set in the control device 20.

[0064] Furthermore, when predicting future setting variables, the driving support device 10 according to this embodiment can calculate setting variables with little change by including Obj1 in the objective function of the optimization problem. Furthermore, when predicting future setting variables, the driving support device 10 according to this embodiment can calculate setting variables similar to the operator's past operations by including Obj2 in the objective function of the optimization problem, and can calculate setting variables with few state variables (e.g., exhaust gas concentration) related to abnormalities by including Obj3 in the objective function of the optimization problem. This makes it possible, for example, to propose optimal setting variables to the operator depending on the items to be emphasized when operating the target plant 30.

[0065] The present invention is not limited to the above-described specifically disclosed embodiments, and various modifications, changes, and combinations with known technologies are possible without departing from the scope of the claims. [Explanation of symbols]

[0066] 1 Plant control system 10 Driving assistance devices 20 Control device 30 Target plants 101 Input Device 102 Display device 103 External I / F 103a Recording media 104 Communication I / F 105 RAM 106 ROM 107 Auxiliary storage 108 processors 109 Bus 201 Operation data acquisition unit 202 Similar settings extraction part 203 Optimization Calculation Unit 204 Input / output section 205 databases

Claims

1. an acquisition unit that acquires operating data including a state variable that represents a state of a control object at a current time, a logic variable that represents a control value of the control object at a current time, and a setting variable that represents a setting value for the control object at a current time; a calculation unit that calculates setting variables for a predetermined period in the future by solving a predetermined optimization problem using the operating data, a machine learning model that predicts the state variables, and a control logic for the control object; an output unit that outputs the setting variables during the period to a predetermined output destination; A driving assistance device having the above configuration.

2. the machine learning model is a prediction model that predicts the state variable at a next time using the state variable, the logic variable, and the setting variable at a same time as input, the control logic is a process of inputting the state variables and the setting variables at a given time and outputting the logic variables at a next time; 2. The driving assistance device according to claim 1, wherein the optimization problem is a problem of finding a setting variable for the time period that minimizes a value of an objective function, the function having as inputs the state variable for the time period, the logic variable for the time period, and the setting variable for the time period.

3. The driving assistance device according to claim 2 , wherein the objective functions include a first objective function that represents a sum of changes in setting variables during the period.

4. 4. The driving assistance device according to claim 3, wherein the objective function includes a second objective function that represents an error between past setting variables during a predetermined period from a time when past driving data similar to the driving data was acquired and setting variables during the predetermined period.

5. The driving assistance device according to claim 4 , wherein the objective functions include a third objective function that represents a sum of the state variables related to an abnormality. The driving assistance device according to claim 4 , wherein the objective function is a weighted sum of the first objective function, the second objective function, and the third objective function.

6. The driving assistance device according to claim 1 , wherein the control logic is a threshold process for a predetermined state variable or a control process according to a predetermined control method including PID control.

7. 5. The driving assistance device according to claim 4, further comprising an extraction unit that acquires past driving data similar to the driving data from a database in which the past driving data is stored, and extracts past setting variables for a predetermined period from a time of the past driving data similar to the driving data from the database.

8. an acquisition step of acquiring operating data including a state variable representing a state of a control object at a current time, a logic variable representing a control value of the control object at a current time, and a setting variable representing a setting value for the control object at a current time; a calculation procedure for calculating setting variables for a predetermined period in the future by solving a predetermined optimization problem using the operating data, a machine learning model for predicting the state variables, and a control logic for the control object; an output procedure for outputting the setting variables for the period to a predetermined output destination; A driving assistance method performed by a computer.

9. an acquisition step of acquiring operating data including a state variable representing a state of a control object at a current time, a logic variable representing a control value of the control object at a current time, and a setting variable representing a setting value for the control object at a current time; a calculation procedure for calculating setting variables for a predetermined period in the future by solving a predetermined optimization problem using the operating data, a machine learning model for predicting the state variables, and a control logic for the control object; an output procedure for outputting the setting variables for the period to a predetermined output destination; A program that causes a computer to execute the following.

Images