JP7182025B1 - Driving support device, driving support method, and driving support program - Google Patents

Abstract

A driving support device, a driving support method, and a driving support program are provided that enable optimal operation of an electrolytic cell in consideration of deterioration in the performance of an ion exchange membrane. An estimating unit for estimating a performance deterioration rate of an ion-exchange membrane based on actual values of impurity data relating to an accumulation rate of impurities in an ion-exchange membrane in an electrolytic cell, wherein the estimation unit is based on the performance deterioration rate. may estimate a production parameter related to a product produced by the electrolytic cell, which is a production parameter when the electrolytic cell is operated under one operating condition, and the impurity data is actual analysis data of the ion exchange membrane can be The electrolytic cell may have an anode compartment and a cathode compartment separated by an ion-exchange membrane, an aqueous solution of an alkali metal chloride being introduced into the anode compartment and an aqueous solution of an alkali metal hydroxide being introduced from the cathode compartment. The derived impurity data may be impurity concentration data in an aqueous solution of an alkali metal chloride. [Selection drawing] Fig. 4

Description

The present invention relates to a driving assistance device, a driving assistance method, and a driving assistance program.

Patent Document 1 describes that "the method for renewing an ion-exchange membrane of the present embodiment includes a step of sandwiching the ion-exchange membrane between an anode-side gasket and a cathode-side gasket, ..." (Paragraph 0052).
[Prior art documents]
[Patent Literature]
[Patent Document 1] JP 2019-19408 A

The performance of an ion exchange membrane in an electrolytic cell can degrade with the operating time of the electrolytic cell. The rate of deterioration of ion exchange membrane performance may vary depending on the operating conditions (temperature, concentration, current, etc.) of the electrolytic cell. Therefore, it is desirable to operate the electrolyzer under optimum operating conditions. The optimum operating conditions at one point in the planned operating period of the electrolyser and the optimum operating conditions considering the entire operating period may differ. Therefore, it is desirable that the electrolyser is operated under optimum operating conditions over the entire planned operating period.

Determining the optimum operating conditions for an electrolyser over the entire planned period of operation can be more difficult than determining the optimum operating conditions at one point in time during the period of operation. Therefore, it is desirable to be able to easily perceive the optimal operating conditions that take into consideration the entire operating period.

A first aspect of the present invention provides a driving assistance device. The driving support device includes an estimating unit that estimates the rate of performance deterioration of the ion-exchange membrane based on the actual value of the impurity data regarding the rate of accumulation of impurities on the ion-exchange membrane in the electrolytic cell.

The estimating unit may estimate a production parameter related to a product produced by the electrolytic cell when the electrolytic cell is operated under one operating condition, based on the performance deterioration rate.

The impurity data may be actual analysis data of the ion exchange membrane.

The electrolytic cell may have an anode compartment and a cathode compartment separated by an ion exchange membrane. An aqueous solution of an alkali metal chloride may be introduced into the anode chamber. An aqueous solution of an alkali metal hydroxide may be discharged from the cathode chamber. The impurity data may be impurity concentration data in an aqueous solution of an alkali metal chloride.

The estimation unit may estimate the performance deterioration rate based on the actual values of the operating conditions of the electrolytic cell.

The driving support device may further include a performance degradation learning unit that generates a performance degradation prediction model. The performance degradation prediction model is based on machine learning of the relationship between the actual impurity data and operating conditions, and the rate of performance degradation. A predicted amount of the rate of degradation of the ion exchange membrane based on the relationship may be output.

The performance degradation prediction model may output a plurality of predicted amounts of performance degradation rate corresponding to each of a plurality of operating conditions.

The driving support device may include a plurality of performance degradation learning units. Each of the plurality of performance degradation learning units may generate a performance degradation prediction model for each of the plurality of ion exchange membrane types.

The performance degradation prediction model may estimate the operating conditions of the electrolyzer that satisfy the production parameters based on the actual values of the impurity data and the production parameters for the product produced by the electrolyzer.

The performance degradation prediction model may estimate at least one of the time to recover the performance of the ion-exchange membrane and the time to replace the ion-exchange membrane when there is no operating condition that satisfies the production parameters.

The operation support device includes an acquisition unit that acquires an impurity accumulation speed when the electrolytic cell is operated under one operating condition, and an actual impurity data value based on the impurity accumulation speed acquired by the acquisition unit. and a correction unit that corrects the .

The estimation unit may acquire the actual value in the first cycle. The obtaining unit may obtain the impurity accumulation rate in a second period shorter than the first period.

Impurities may be at least one of barium, calcium, strontium, iodine, silicon, aluminum, nickel, magnesium, iron, titanium and phosphorus.

A second aspect of the present invention provides a driving assistance method. The driving support method includes a first estimation step in which the estimating unit estimates the performance deterioration rate of the ion-exchange membrane based on the actual value of the impurity data regarding the accumulation rate of impurities in the ion-exchange membrane in the electrolytic cell.

In the operation support method, the estimating unit determines the production parameters produced by the electrolytic cell when the electrolytic cell is operated under one operating condition based on the performance deterioration rate estimated in the first estimating step. A second estimating step of estimating a production parameter for the object may be further included.

The first estimating step may be a step in which the estimating section estimates the performance deterioration rate based on the actual values of the operating conditions of the electrolytic cell.

The first estimation step may include a performance degradation learning step in which the performance degradation learning unit generates a performance degradation prediction model. The performance degradation prediction model is based on machine learning of the relationship between the actual impurity data and operating conditions, and the rate of performance degradation. A predicted amount of the rate of degradation of the ion exchange membrane based on the relationship may be output.

In the first estimation step, the performance deterioration prediction model estimates the operating conditions of the electrolytic cell that satisfy the production parameters based on the actual values of the impurity data and the production parameters related to the products produced by the electrolytic cell. It may further include an estimation step.

The operation support method includes an acquisition step in which the acquisition unit acquires an impurity accumulation rate when the electrolytic cell is operated under one operating condition, and a correction unit acquires the impurity accumulation rate acquired in the acquisition step. and a correction step of correcting the actual value of the impurity data based on the correction step.

A third aspect of the present invention provides a driving assistance program. The driving support program is a driving support program for making the computer function as a driving support device.

It should be noted that the above summary of the invention does not list all the features of the invention. Subcombinations of these feature groups can also be inventions.

It is a figure showing an example of electrolysis device 200 concerning one embodiment of the present invention. It is a figure which shows an example of the detail of one electrolysis cell 91 in FIG. 3 is an enlarged view of the vicinity of an ion exchange membrane 84 in the electrolytic cell 91 shown in FIG. 2. FIG. BRIEF DESCRIPTION OF THE DRAWINGS It is a figure which shows an example of the block diagram of the driving assistance device 100 which concerns on one Embodiment of this invention. FIG. 11 shows an example of an alkali metal concentration profile across the anode compartment 79, the ion exchange membrane 84 and the cathode compartment 98. FIG. 8 is a diagram schematically showing clusters 85 of ion exchange membranes 84. FIG. 8 is a diagram schematically showing clusters 85 of ion exchange membranes 84. FIG. FIG. 3 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention; 6 is a diagram showing an example of a performance degradation prediction model 62; FIG. 4A and 4B are diagrams showing an example of an output mode in an output unit 32; FIG. FIG. 3 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention; 4 is a diagram showing an example of prediction of a predicted amount VLp or estimation of an operating condition Cd by a performance degradation prediction model 62; FIG. 8 is a diagram showing an example of estimating the performance recovery time of the ion exchange membrane 84 or the replacement time of the ion exchange membrane 84 by the performance deterioration prediction model 62. FIG. FIG. 3 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention; 3 is a diagram showing an example of acquisition timing of an accumulation rate of impurities Im by an acquisition unit 35 and acquisition timing of a performance value Vi by an estimation unit 10. FIG. It is a flow chart which shows an example of the driving support method concerning one embodiment of the present invention. 22 is a diagram illustrating an example of a computer 2200 in which the driving assistance device 100 according to embodiments of the invention may be embodied in whole or in part; FIG.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution of the invention.

FIG. 1 is a diagram illustrating an example of an electrolytic device 200 according to one embodiment of the invention. The electrolytic device 200 of this example includes an electrolytic bath 90 , an inlet pipe 92 , an inlet pipe 93 , an outlet pipe 94 and an outlet pipe 95 .

The electrolytic device 200 is a device that electrolyzes an electrolytic solution. The electrolytic bath 90 is a bath that electrolyzes the electrolytic solution. The electrolytic solution is, for example, an aqueous NaCl (sodium chloride) solution. The electrolytic cell 90 generates Cl ₂ (chlorine), NaOH (sodium hydroxide), and H ₂ (hydrogen) by, for example, electrolyzing an aqueous solution of NaCl (sodium chloride). The electrolytic bath 90 may include a plurality of electrolytic cells 91 (electrolytic cells 91-1 to 91-N, where N is an integer of 2 or more). N is 50, for example.

In this example, the introduction pipe 92 and the introduction pipe 93 are connected to the electrolytic cells 91-1 to 91-N, respectively. A liquid 70 is introduced into each of the electrolytic cells 91-1 to 91-N. The liquid 70 may be introduced into each of the electrolytic cells 91-1 to 91-N after passing through the introduction pipe 92. FIG. The liquid 70 is an aqueous solution of an alkali metal chloride. Alkali metals are elements belonging to group 1 of the periodic table of the elements. Liquid 70 is, for example, an aqueous NaCl (sodium chloride) solution.

A liquid 72 is introduced into each of the electrolytic cells 91-1 to 91-N. After passing through the introduction pipe 93, the liquid 72 may be introduced into each of the electrolytic cells 91-1 to 91-N. The liquid 72 is an aqueous solution of alkali metal hydroxide. The liquid 72 is, for example, NaOH (sodium hydroxide) aqueous solution.

In this example, the lead-out tube 94 and the lead-out tube 95 are connected to the electrolytic cells 91-1 to 91-N, respectively. A liquid 76 and a gas 78 (described later) are drawn out from each of the electrolytic cells 91-1 to 91-N. The liquid 76 and the gas 78 (described later) may be led out of the electrolytic device 200 after passing through the outlet tube 95 . Liquid 76 is an aqueous solution of an alkali metal hydroxide. When liquid 72 is NaOH (sodium hydroxide) aqueous solution, liquid 76 is NaOH (sodium hydroxide) aqueous solution. Gas 78 (described below) may be H ₂ (hydrogen).

A liquid 74 and a gas 77 (described later) are drawn out from each of the electrolytic cells 91-1 to 91-N. The liquid 74 and the gas 77 (described later) may be led out of the electrolytic device 200 after passing through the outlet tube 94 . Liquid 74 is an aqueous solution of an alkali metal chloride. If the liquid 70 is an aqueous NaCl (sodium chloride) solution, the liquid 74 is an aqueous NaCl (sodium chloride) solution. Gas 77 (described below) may be Cl ₂ (chlorine).

FIG. 2 is a diagram showing an example of details of one electrolytic cell 91 in FIG. The electrolytic cell 90 has an anode compartment 79 , an anode 80 , a cathode compartment 98 , a cathode 82 and an ion exchange membrane 84 . In this example, one electrolytic cell 91 has an anode compartment 79 , an anode 80 , a cathode compartment 98 , a cathode 82 and an ion exchange membrane 84 . Anode chamber 79 and cathode chamber 98 are provided inside electrolytic cell 91 . The anode chamber 79 and cathode chamber 98 are separated by an ion exchange membrane 84 . An anode 80 is arranged in the anode chamber 79 . A cathode 82 is arranged in the cathode chamber 98 .

In this specification, technical matters may be described using the X-axis, Y-axis, and Z-axis orthogonal coordinate axes. In this specification, the plane parallel to the bottom surfaces 88 of the anode chamber 79 and the cathode chamber 98 is defined as the XY plane. In this specification, the direction connecting the bottom surface 88 and the ceiling surfaces 89 of the anode chamber 79 and the cathode chamber 98 (the direction perpendicular to the bottom surface 88) is defined as the Z-axis direction. In this specification, the direction from the anode 80 to the cathode 82 is defined as the Y-axis direction, and the direction orthogonal to the Y-axis in the XY plane is defined as the X-axis direction. The Z-axis direction may be parallel to the direction of gravity. If the Z-axis direction is parallel to the direction of gravity, the XY plane may be a horizontal plane.

An inlet pipe 92 and an outlet pipe 94 are connected to the anode chamber 79 . An introduction pipe 93 and an extraction pipe 95 are connected to the cathode chamber 98 . A liquid 70 is introduced into the anode chamber 79 . A liquid 72 is introduced into the cathode chamber 98 .

The ion-exchange membrane 84 is a membrane-like substance that blocks the passage of ions having a different sign from the ions arranged on the ion-exchange membrane 84 and allows the passage of ions having the same sign. In this example, the ion exchange membrane 84 is a membrane that allows passage of Na ⁺ (sodium ions) and blocks passage of Cl ⁻ (chloride ions).

Anode 80 and cathode 82 may be maintained at predetermined positive and negative potentials, respectively. Liquid 70 introduced into anode chamber 79 and liquid 72 introduced into cathode chamber 98 are electrolyzed by the potential difference between anode 80 and cathode 82 . At the anode 80 the following chemical reactions take place.
[Chemical Formula 1]
2Cl ⁻ →Cl ₂ +2e ⁻

When the liquid 70 is an NaCl (sodium chloride) aqueous solution, NaCl (sodium chloride) is ionized into Na ⁺ (sodium ions) and Cl ⁻ (chloride ions). At the anode 80, Cl ₂ (chlorine) gas is generated by the chemical reaction shown in Chemical Formula 1. Gas 77 (the Cl ₂ (chlorine) gas) and liquid 74 may be drawn from the anode chamber 79 . Na ⁺ (sodium ions) move from the anode chamber 79 to the cathode chamber 98 after passing through the ion exchange membrane 84 due to the attractive force from the cathode 82 .

A liquid 73 may remain in the anode chamber 79 . Liquid 73 is an aqueous solution of alkali metal chloride. In this example, the liquid 73 is an aqueous NaCl (sodium chloride) solution. The Na ⁺ (sodium ion) and Cl ⁻ (chloride ion) concentrations of liquid 73 may be less than the Na ⁺ (sodium ion) and Cl ⁻ (chloride ion) concentrations of liquid 70 .

At the cathode 82 the following chemical reactions take place.
[Chemical Formula 2]
2H ₂ O+2e ⁻ →H ₂ +2OH ⁻

When the liquid 72 is a NaOH (sodium hydroxide) aqueous solution, NaOH (sodium hydroxide) is ionized into Na ⁺ (sodium ions) and OH ^- (hydroxide ions). At the cathode 82, H ₂ (hydrogen) gas and OH ⁻ (hydroxide ions) are produced by the chemical reaction represented by Chemical Formula 2. A gas 78 (such H ₂ (hydrogen) gas) and a liquid 76 may be drawn from the cathode chamber 98 .

A liquid 75 may be retained in the cathode chamber 98 . The liquid 75 is an aqueous solution of alkali metal hydroxide. In this example, the liquid 75 is an aqueous NaOH (sodium hydroxide) solution. In this example, the cathode chamber 98 contains a liquid 75 in which OH ⁻ (hydroxide ions) produced by the chemical reaction represented by Chemical Formula 2 and Na ⁺ (sodium ions) transferred from the anode chamber 79 are dissolved. staying.

FIG. 3 is an enlarged view of the vicinity of the ion exchange membrane 84 in the electrolytic cell 91 shown in FIG. Anion groups 86 are immobilized on the ion exchange membrane 84 of this example. Since anions are repelled by the anion groups 86 , they are less likely to pass through the ion exchange membrane 84 . In this example, the anion is Cl ⁻ (chloride ion). The cations 71 are not repelled by the anionic groups 86 and thus can pass through the ion exchange membrane 84 . If the liquid 70 (see FIG. 2) is an aqueous NaCl (sodium chloride) solution, the cations 71 are Na ⁺ (sodium ions).

FIG. 4 is a diagram showing an example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention. The operation assistance device 100 assists the operation of the electrolytic cell 90 (see FIG. 1). The driving assistance device 100 includes an estimating unit 10 . The driving assistance device 100 may include a control unit 20 , an input unit 30 , an output unit 32 and a storage unit 40 .

The driving assistance device 100 is, for example, a computer including a CPU, memory, interface, and the like. The control unit 20 may be the CPU. The estimation unit 10 and the control unit 20 may be one CPU. When the driving assistance device 100 is a computer, the computer may be installed with a driving assistance program for executing a driving assistance method described later, and the driving assistance program for making the computer function as the driving assistance device 100 is installed. may be installed.

The input unit 30 is, for example, a keyboard, mouse, or the like. The output unit 32 outputs the result of estimation by the estimation unit 10 . The output unit 32 is, for example, a display, monitor, or the like.

As the electrolytic cell 90 (see FIG. 1) electrolyzes the liquid 70, impurities can accumulate on the ion exchange membrane 84 as the electrolytic cell 90 operates over time. The impurities accumulated in the ion exchange membrane 84 are referred to as impurities Im. When the impurities Im accumulate in the ion exchange membrane 84, the performance of the ion exchange membrane 84 may deteriorate. The performance of the ion exchange membrane 84 refers to the ion exchange performance of the ion exchange membrane 84 .

A liquid 70 (see FIG. 1) obtained by subjecting salt water in which raw salt is dissolved to a predetermined treatment is introduced into the electrolytic cell 90 (see FIG. 1). Predetermined treatments include, for example, precipitation of SS (suspended solids) contained in salt water by a clarifier, removal of the SS by a ceramic filter, Ba (barium), Ca (calcium) contained in salt water by a resin tower, ), removal of at least one of Sr (strontium) and Mg (magnesium), and the like.

Raw salt may contain at least one of I (iodine), Fe (iron), Ti (titanium) and P (phosphorus). SS (suspended solid) may contain at least one of Si (silicon) and Al (aluminum). Impurities Im include Ba (barium), Ca (calcium), Sr (strontium), Mg (magnesium), I (iodine), Fe (iron), Ti (titanium), Si (silicon), Al (aluminum) and At least one of P (phosphorus) may be included.

The surface of the cathode 82 may be provided with Ni (nickel). Ni (nickel) may be formed on the surface of the cathode 82 by plating. Ni (nickel) provided on the surface of the cathode 82 may be included in the liquid 75 (see FIG. 2) as the operating time of the electrolytic cell 90 elapses. The impurity Im may contain Ni (nickel).

The estimating unit 10 estimates the performance deterioration rate of the ion exchange membrane 84 based on the actual value of the impurity data regarding the accumulation rate of the impurity Im in the ion exchange membrane 84 . The impurity data is assumed to be impurity data Di. Let this actual value be the actual value Vi. This performance degradation rate is assumed to be a performance degradation rate VL.

The impurity data Di may be actual analytical data of the ion exchange membrane 84 . The actual analysis data of the ion exchange membrane 84 may be data obtained by analyzing the components of the impurity Im accumulated in the ion exchange membrane 84 and the amount of each component. The actual analysis data of the ion-exchange membrane 84 refers to the relationship between the component of the impurity Im and the amount of each component, and the operating time of the electrolytic cell 90 with the ion-exchange membrane 84 attached to the electrolytic cell 90. It may be analyzed data. The actual analysis data of the ion exchange membrane 84 may be acquired with the ion exchange membrane 84 removed from the electrolytic cell 90 or with the ion exchange membrane 84 installed in the electrolytic cell 90 .

The actual analysis data of the ion exchange membrane 84 may be input through the input section 30 . The actual analysis data input by the input unit 30 may be stored in the storage unit 40 .

When the performance of the ion exchange membrane 84 is lowered, the alkali metal chloride contained in the liquid 73 may pass through the ion exchange membrane 84 . The alkali metal chloride that has passed through the ion exchange membrane 84 may be contained in the liquid 75 . As mentioned above, liquid 75 is an aqueous solution of alkali metal hydroxide.

The impurity data Di may be concentration data of impurities Im in the liquid 73 . When the liquid 73 is an NaCl (sodium chloride) aqueous solution, the actual value Vi may be concentration data of the impurity Im in the NaCl (sodium chloride) aqueous solution.

In the driving assistance device 100, the estimation unit 10 estimates the performance deterioration speed VL based on the actual value Vi. Therefore, the user of the driving assistance device 100 can recognize future performance deterioration of the ion exchange membrane 84 .

Let the operating condition of the electrolytic cell 90 be an operating condition Cd. The operating condition Cd refers to operating conditions of the electrolytic cell 90 that can affect the state of the ion exchange membrane 84 .

Current efficiency CE refers to the ratio of the actual output of the product produced by the electrolytic cell 90 to the theoretical output. Let the product concerned be the product P. The theoretical production amount of the product P is assumed to be the production amount Pa. Let the actual production amount of the product P be the production amount Pr. The current efficiency CE refers to the ratio of the production amount Pr to the production amount Pa. Operating conditions Cd include the pH and flow rate of liquid 70 (see FIG. 2), the pH and flow rate of liquid 72 (see FIG. 2), and the temperature of liquid 73 (see FIG. 2) or liquid 75 (see FIG. 2). may also be included.

The estimation unit 10 may estimate the performance deterioration rate VL of the ion exchange membrane 84 based on the actual value of the operating condition Cd. Let the said actual value be the actual value Vd. The estimation unit 10 may estimate the performance deterioration speed VL based on the actual value Vi and the actual value Vd.

The actual value Vd is the actual value of the current of the electrolytic cell 90, the actual value of the current efficiency CE, the actual value of the voltage CV, the actual values of the pH and flow rate of the liquid 70 (aqueous solution of alkali metal chloride), the liquid 72 (alkali It may be at least one of actual values of pH and flow rate of a metal hydroxide solution) and actual values of temperature of liquid 73 (see FIG. 2) or liquid 75 (see FIG. 2). The actual value Vd may be input by the input unit 30 . The actual value Vd input by the input unit 30 may be stored in the storage unit 40 .

FIG. 5 shows an example of an alkali metal concentration profile across the anode compartment 79, the ion exchange membrane 84 and the cathode compartment 98. In FIG. In FIG. 5, position P0 is the position of anode 80 (see FIG. 2) and position P4 is the position of cathode 82 (see FIG. 2). 5, position P1 is the position of the interface between the anode chamber 79 and the ion exchange membrane 84, and position P3 is the position of the interface between the cathode chamber 98 and the ion exchange membrane 84. In FIG. In FIG. 5, the position P2 is the position where the concentration of the alkali metal in the ion exchange membrane 84 is the lowest (concentration C2 (described later)).

In FIG. 5, the concentration C0 is the concentration of alkali metal in the anode chamber 79 and the concentration C4 is the concentration of alkali metal in the cathode chamber 98. In FIG. In FIG. 5, concentration C1 is the concentration of alkali metal at position P1, and concentration C3 is the concentration of alkali metal at position P3. In FIG. 5, the concentration C2 is the minimum alkali metal concentration in the ion exchange membrane 84 . As shown in FIG. 5, the alkali metal concentration is higher on the cathode 82 side than on the anode 80 side. The alkali metal concentration in the ion exchange membrane 84 decreases from position P1 to position P2 and increases from position P2 to position P3.

If the pH or concentration of liquid 70 (see FIGS. 1 and 2) or the pH or concentration of liquid 76 (see FIGS. 1 and 2) changes, the alkali metal concentration profile shown in FIG. 5 may change. As a result, the supply amount of the impurity Im supplied to the ion exchange membrane 84 or the accumulation position of the impurity Im accumulated in the ion exchange membrane 84 can be changed. Thereby, the performance deterioration rate VL of the ion exchange membrane 84 can be changed. The estimation unit 10 estimates the performance deterioration rate VL based on the actual value Vd. Therefore, the user of the driving assistance device 100 can recognize future performance deterioration of the ion exchange membrane 84 .

6 and 7 are diagrams schematically showing clusters 85 of the ion exchange membrane 84. FIG. 6 and 7 are schematic diagrams of the cluster 85 when the ion exchange membrane 84 is viewed from the anode 80 to the cathode 82 (thickness direction of the ion exchange membrane 84). FIG. 6 is a schematic diagram of the cluster 85 when the liquid 73 (see FIG. 2) and the liquid 75 (see FIG. 2) are at one temperature T1 within a predetermined temperature range. FIG. 7 is a schematic diagram of the cluster 85 when the liquid 73 and the liquid 75 are at another temperature T2 outside the temperature range and on the higher temperature side than the temperature range.

When the temperature of at least one of liquid 73 and liquid 75 changes, the size of clusters 85 of ion exchange membrane 84 can change, as shown in FIGS. By changing the size of the clusters 85, the alkali metal concentration profile shown in FIG. 5 can be changed. As a result, the supply amount of the impurity Im supplied to the ion exchange membrane 84 or the accumulation position of the impurity Im accumulated in the ion exchange membrane 84 can be changed. Thereby, the performance deterioration rate VL of the ion exchange membrane 84 can be changed. The estimating unit 10 estimates the performance deterioration rate VL based on the actual value Vd (actually measured temperature values of the liquids 73 and 75 in this example). Therefore, the user of the driving assistance device 100 can recognize future performance deterioration of the ion exchange membrane 84 .

Let the production parameter for the product P be a production parameter Pr. The production parameter Pr includes the current efficiency CE of the electrolytic cell 90, the rate of decrease of the current efficiency CE, the voltage CV of the electrolytic cell 90, the rate of increase of the voltage CV, the production amount of the product P per unit time, and the quality of the product P. , and at least one parameter related to the operation of the electrolytic cell 90 that can affect the production volume and the quality. The production parameter Pr may include the amount of CO ₂ (carbon dioxide) generated as the electrolyzer 90 operates. CO ₂ (carbon dioxide) generated by the operation of the electrolytic cell 90 refers to CO ₂ (carbon dioxide) generated when the electrolytic cell 90 consumes electricity. The production parameter Pr may include operating costs of the electrolyser 90 . The operating cost may include the cost of electricity associated with the operation of the electrolytic cell 90 and the cost of the ion exchange membrane 84 when the ion exchange membrane 84 is replaced.

The estimation unit 10 may estimate the production parameter Pr when the electrolytic cell 90 is operated under one operating condition Cd based on the performance deterioration rate VL. Thereby, the user of the driving support device 100 can recognize the production parameter Pr that reflects the future performance deterioration of the ion exchange membrane 84 .

FIG. 8 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention. The driving assistance device 100 of this example is different from the driving assistance device 100 shown in FIG. 4 in that it further includes a performance degradation learning unit 60 . The performance degradation learning unit 60 generates a performance degradation prediction model 62 (described later). A performance degradation prediction model 62 (described later) may be stored in the storage unit 40 .

FIG. 9 is a diagram showing an example of the performance degradation prediction model 62. As shown in FIG. The performance degradation prediction model 62 is based on the relationship between the performance degradation rate VL of the ion exchange membrane 84 and the performance degradation rate VL of the impurity data Di related to the rate of accumulation of the impurities Im in the ion exchange membrane 84 and the actual value Vd of the operating condition Cd. is machine-learned to output a predicted amount of the performance degradation rate VL based on the relationship between the performance value Vi and the performance value Vd, and the performance degradation rate VL. The predicted amount of the performance degradation rate is assumed to be the predicted amount VLp.

FIG. 10 is a diagram showing an example of an output mode in the output section 32 (see FIG. 8). The output unit 32 in this example is a display. Let the parameter related to the operating condition Cd be the operating parameter Pd. An operation parameter Pd display section 33 and a production parameter Pr display section 34 are displayed in the output section 32 of this example. A user of the driving support device 100 may input the driving parameter Pd and the production parameter Pr using the input unit 30 (see FIG. 8).

The user of the driving assistance device 100 may specify one or more of the driving parameters Pd to be fixed during the operation of the electrolytic cell 90 . The performance deterioration prediction model 62 (see FIG. 9) may output a plurality of predicted amounts VLp of the performance deterioration rate VL corresponding to each of the plurality of operating conditions Cd. The plurality of operating conditions Cd refer to a first case and a second case of the operating parameter Pd that the user of the driving support device 100 wants to fix when the operating parameter Pd is input in the operating parameter Pd display section 33. . The first case may include one or more of the operating parameters Pd displayed in the operating parameter Pd display section 33, and the second case may include one or more of the operating parameters Pd. Another operating parameter Pd may be included than in the first case. Thereby, the user of the driving assistance device 100 can simulate the predicted amount VLp when the driving condition Cd is varied.

FIG. 11 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention. The driving assistance device 100 of this example differs from the driving assistance device 100 shown in FIG. 8 in that it includes a plurality of performance degradation learning units 60 (performance degradation learning units 60-1 to 60-n).

Each of the plurality of performance degradation learning units 60 may generate a performance degradation prediction model 62 (see FIG. 9) for each of the plurality of types of ion exchange membranes 84 . The type of the ion-exchange membrane 84 may be a physical quantity that may vary depending on the individual ion-exchange membrane 84, such as the density of the anion groups 86 (see FIG. 3) in the ion-exchange membrane 84, the thickness of the ion-exchange membrane 84, and the like. . The type of ion exchange membrane 84 may be a so-called lot number for each individual. The type of ion exchange membrane 84 may be the type of anionic groups 86 (see FIG. 3).

The manner in which the ion-exchange membrane 84 deteriorates in performance may differ depending on the type of the ion-exchange membrane 84 . By generating the performance degradation prediction model 62 for each type of ion exchange membrane 84 , each performance degradation prediction model 62 can output a more appropriate prediction amount VLp reflecting the type of ion exchange membrane 84 .

FIG. 12 is a diagram showing an example of prediction of the predicted amount VLp or estimation of the operating condition Cd by the performance degradation prediction model 62. In FIG. The performance degradation prediction model 62 of this example assumes that machine learning has already been performed on the relationship between the performance degradation rate VL and the actual value Vi of the impurity data Di regarding the accumulation rate of the impurities Im, the actual value Vd of the operating condition Cd, and the performance degradation rate VL. The performance degradation prediction model 62 may estimate an operating condition Cd that satisfies the production parameter Pr based on the actual value Vi and the production parameter Pr (see FIG. 10). When the actual performance value Vi and the production parameter Pr are input to the performance degradation prediction model 62, the performance degradation prediction model 62 may estimate an operating condition Cd that satisfies the production parameter Pr. The operating condition Cd is referred to as an operating condition Cd'. The performance degradation prediction model 62 may estimate the operating condition Cd' and predict the predicted amount VLp.

In this example, the performance degradation prediction model 62 outputs the optimum operating condition Cd' as the target condition when the actual value Vi is used as the explanatory variable and the production parameter Pr is used as the constraint condition. The user of the driving support device 100 designates the production parameter Pr to be satisfied from among the production parameters Pr displayed in the production parameter Pr display unit 34 (see FIG. 10) through the input unit 30 (see FIG. 8), and selects the desired production parameter Pr. A numerical value related to the desired production parameter Pr may be input through the input unit 30 . Thereby, the user of the driving support device 100 can recognize the optimum driving condition Cd' when the production parameter Pr is used as a constraint condition.

The constraint conditions may further include a driving condition Cd that the user of the driving assistance device 100 wishes to satisfy. The user of the driving support device 100 designates the desired driving parameter Pd among the driving parameters Pd displayed in the driving parameter Pd display portion 33 of FIG. A numerical value related to the parameter Pd may be input through the input unit 30 . Thereby, the user of the driving support device 100 can recognize the optimum driving condition Cd' when the production parameter Pr and the driving parameter Pd are used as the constraint conditions. Said operating condition Cd' may be different from said operating parameter Pd.

FIG. 13 is a diagram showing an example of estimating the performance recovery time of the ion-exchange membrane 84 or the replacement time of the ion-exchange membrane 84 by the performance deterioration prediction model 62 . In the prediction of the predicted amount VLp or the estimation of the operating condition Cd shown in FIG. At least one of the replacement timings of the replacement membrane 84 may be estimated. Thereby, the user of the driving support device 100 can recognize at least one of the recovery time of the performance of the ion exchange membrane 84 and the replacement time of the ion exchange membrane 84 in advance.

FIG. 14 is a diagram showing another example of a block diagram of the driving assistance device 100 according to one embodiment of the present invention. The driving assistance device 100 of this example differs from the driving assistance device 100 shown in FIG. 8 in that it further includes an acquisition unit 35 and a correction unit 36 .

The acquiring unit 35 acquires the accumulation rate of the impurities Im when the electrolytic cell 90 is operated under one operating condition Cd. The one driving condition Cd may refer to the driving condition Cd designated by the user of the driving assistance device 100 . The case where the electrolytic cell 90 is operated under the one operating condition Cd may refer to the case where the electrolytic cell 90 is operating under the one operating condition Cd. The acquiring unit 35 may acquire the accumulation speed of the impurities Im in real time while the electrolytic cell 90 is operating under the one operating condition Cd.

The correction unit 36 corrects the actual value Vi of the impurity data Di regarding the accumulation rate based on the accumulation rate of the impurities Im acquired by the acquisition unit 35 . The actual value Vi may differ from the accumulation speed acquired by the acquisition unit 35 . The track record value Vi is the past track record of the accumulation speed. When the acquisition unit 35 acquires the accumulation speed in real time, the accumulation speed is the current measured value. Therefore, the accumulation rate acquired by the acquisition unit 35 may reflect the current state of the ion exchange membrane 84 rather than the actual value Vi. In this example, the correction unit 36 corrects the actual value Vi based on the accumulation speed acquired by the acquisition unit 35 . Therefore, the actual value Vi is likely to be an accumulation rate value that reflects the current state of the ion-exchange membrane 84 .

The estimation unit 10 may estimate the performance deterioration speed VL based on the actual value Vi corrected by the correction unit 36 . The performance degradation prediction model 62 (see FIG. 9) may machine-learn the relationship between the performance value Vd of the operating condition Cd and the performance value Vi corrected by the correction unit 36 and the performance degradation rate VL.

FIG. 15 is a diagram showing an example of acquisition timing of the accumulation speed of the impurity Im by the acquisition unit 35 and acquisition timing of the actual value Vi by the estimation unit 10 . In FIG. 15 , the acquisition timing of the accumulation speed of the impurity Im by the acquisition unit 35 is indicated by a white circle, and the acquisition timing of the actual value Vi is indicated by a black circle.

In this example, the estimation unit 10 acquires the actual value Vi in the first cycle T1, and the acquisition unit 35 acquires the accumulation speed of the impurity Im in the second cycle T2. Obtaining the actual value Vi in the first cycle T1 may refer to reading out the actual value Vi stored in the storage unit 40 (see FIG. 14) by the control unit 20 (see FIG. 14) in the first cycle T1. . Acquiring the impurity Im accumulation rate in the second cycle T2 may refer to acquiring the impurity Im accumulation rate in the second cycle T2 by the acquisition unit 35 while the electrolytic cell 90 is in operation.

The second period T2 may be shorter than the first period T1. The correction unit 36 (see FIG. 14) may correct the actual value Vi obtained in the first period T1 based on the accumulation speed of the impurity Im obtained in the second period T2. As described above, the accumulation rate acquired by the acquisition unit 35 may reflect the current state of the ion exchange membrane 84 rather than the actual value Vi. Therefore, since the second period T2 is shorter than the first period T1, the correction unit 36 can more easily correct the actual value Vi to an accumulation rate that reflects the current state of the ion exchange membrane 84 .

FIG. 16 is a flow chart showing an example of a driving assistance method according to one embodiment of the present invention. A driving assistance method according to one embodiment of the present invention is a driving assistance method for assisting the operation of the electrolytic cell 90 (see FIG. 1).

A driving support method according to one embodiment of the present invention includes a first estimation step S100. The driving assistance method may comprise a first input step S90, a second input step S92 and a third input step S94.

The first input step S90 is a step of inputting the actual value Vi of the impurity Im of the ion exchange membrane 84 to the driving support device 100 (see FIG. 8). The second input step S<b>92 is a step of inputting the actual value Vd of the operating condition Cd to the driving support device 100 . The third input step S<b>94 is a step of inputting the performance value of the performance deterioration speed VL to the driving support device 100 .

The actual value Vi, the actual value Vd, and the actual value of the performance degradation rate VL may be input by the input unit 30 (see FIG. 8). The first input step S90 to the third input step S94 may or may not be performed in this order.

In the first estimating step S100, the estimating unit 10 (see FIG. 4) performs is a step of estimating the performance deterioration rate VL of the ion exchange membrane 84. FIG. The first estimation step S100 may be a step in which the estimation unit 10 (see FIG. 4) estimates the performance deterioration rate VL based on the actual value Vd of the operating condition Cd of the electrolytic cell 90 (see FIG. 1). .

The first estimation step S100 may include a performance degradation learning step S102 in which the performance degradation learning unit 60 (FIG. 8) generates the performance degradation prediction model 62 (see FIG. 9). The performance degradation prediction model 62 performs machine learning on the relationship between the performance degradation rate VL and the actual value Vi of the impurity data Di and the actual value Vd of the operating condition Cd related to the accumulation rate, thereby obtaining the actual value Vi and the actual value Vd, A predicted amount VLp of the performance degradation rate VL of the ion exchange membrane 84 based on the relationship with the performance degradation rate VL is output.

The first estimation step S100 may include a fourth input step S104 and a fifth input step S106. A fourth input step S<b>104 is a step of inputting the actual value Vi of the impurity Im of the ion exchange membrane 84 to the performance deterioration prediction model 62 . A fifth input step S<b>106 is a step of inputting the operating condition Cd and the production parameter Pr into the performance deterioration prediction model 62 .

The actual value Vi in the fourth input step S104, the actual value Vd in the fifth input step S106, and the actual value of the performance degradation rate VL may be input through the input unit 30 (see FIG. 8). In the driving support method, the fifth input step S106 may be performed after the fourth input step S104, and the fourth input step S104 may be performed after the fifth input step S106.

The first estimation step S100 may further include an operating condition estimation step S108. The operating condition estimation step S108 is a step in which the performance deterioration prediction model 62 (see FIG. 12) estimates the operating condition Cd of the electrolytic cell 90 that satisfies the production parameter Pr based on the actual value Vi and the production parameter Pr. . The production parameter Pr may be one of the production parameters Pr displayed in the production parameter Pr display section 34 (see FIG. 10) that the user of the driving support method wants to satisfy.

The driving support method may further include a second estimation step S120. In the second estimating step S120, the estimating unit 10 (see FIG. 4) determines the production capacity when the electrolytic cell 90 is operated under one operating condition Cd based on the performance deterioration rate VL estimated in the first estimating step S100. This is the step of estimating the parameter Pr (see FIG. 10).

The driving support method may further include an output step S130 in which the output unit 32 (see FIG. 8) outputs at least one of the performance deterioration rate VL estimated in the first estimation step S100 and the operating condition Cd'. The output step S130 may be a step in which the output unit 32 further outputs the production parameter Pr estimated in the second estimation step S120. Thereby, the user of the driving assistance method can recognize at least one of the estimated performance deterioration rate VL, the operating condition Cd', and the production parameter Pr. The output step S<b>130 may be a step in which the output unit 32 outputs the state of at least one of the ion exchange membrane 84 , the anode 80 and the cathode 82 to the user of the driving support device 100 .

The driving assistance method may further include an acquisition step S96 and a correction step S98. Acquisition step S96 is a step in which the acquisition unit 35 (see FIG. 14) acquires the accumulation rate of the impurities Im when the electrolytic cell 90 (see FIG. 1) is operated under one operating condition Cd. The correcting step S98 is a step in which the correcting unit 36 (see FIG. 14) corrects the actual value Vi of the impurity data Di regarding the accumulation speed based on the accumulation speed of the impurities Im obtained in the obtaining step S96.

The first estimation step S100 may be a step in which the estimation unit 10 (see FIG. 14) estimates the performance deterioration speed VL based on the actual value Vi corrected in the correction step S98. In the performance degradation learning step S102, the performance degradation prediction model 62 (see FIG. 9) acquires the actual value Vd of the operating condition Cd input in the second input step S92, the actual value Vi corrected in the correction step S98, It may be a step of machine-learning the relationship with the performance degradation rate VL.

Various embodiments of the invention may be described with reference to flowchart illustrations and block diagrams. In various embodiments of the invention, a block may represent (1) a stage of a process in which an operation is performed or (2) a section of equipment responsible for performing the operation.

Certain steps may be performed by dedicated circuitry, programmable circuitry or processors. Certain sections may be implemented by dedicated circuitry, programmable circuitry or processors. The programmable circuit and the processor may be supplied with computer readable instructions. The computer readable instructions may be stored on a computer readable medium.

The dedicated circuitry may include at least one of digital hardware circuitry and analog hardware circuitry. Dedicated circuitry may include integrated circuits (ICs) and/or discrete circuits. Programmable circuits may include hardware circuits for logical AND, logical OR, logical XOR, logical NAND, logical NOR, or other logical operations. Programmable circuits may include reconfigurable hardware circuits, including flip-flops, registers, memory elements such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like.

A computer-readable medium may include any tangible device capable of storing instructions for execution by a suitable device. By including the tangible device, the computer readable medium having instructions stored on the device can be executed to create means for performing the operations specified in the flowcharts or block diagrams. will have a product, including

A computer-readable medium may be, for example, an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, or the like. The computer readable medium is more particularly e.g. Electrically Erasable Programmable Read Only Memory (EEPROM), Static Random Access Memory (SRAM), Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD), Blu-ray (RTM) Disc, Memory Stick, Integration It may be a circuit card or the like.

Computer readable instructions may include any of assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, source code and object code. The source code and the object code may be written in any combination of one or more programming languages, including object-oriented programming languages and traditional procedural programming languages. Object-oriented programming languages may be, for example, Smalltalk®, JAVA®, C++, and the like. The procedural programming language may be, for example, the "C" programming language.

Computer readable instructions may be transferred to a processor or programmable circuitry of a general purpose computer, special purpose computer, or other programmable data processing apparatus, either locally or over a wide area network (WAN), such as a local area network (LAN), the Internet, or the like. ) may be provided via A processor or programmable circuit of a general purpose computer, special purpose computer, or other programmable data processing apparatus may be represented by the flowchart shown in FIG. 16 or the block diagrams shown in FIGS. 4, 8, 11 and 14. Computer readable instructions may be executed to create means for performing specified operations. A processor may be, for example, a computer processor, processing unit, microprocessor, digital signal processor, controller, microcontroller, or the like.

FIG. 17 is a diagram illustrating an example of a computer 2200 in which the driving assistance device 100 according to embodiments of the invention may be embodied in whole or in part. The programs installed on the computer 2200 may cause the computer 2200 to function as operations or one or more sections of the driving assistance device 100 associated with the driving assistance device 100 according to embodiments of the present invention, or The one or more sections can be executed, or the computer 2200 can be caused to execute the steps (see FIG. 16) of the driving assistance method of the present invention. The program instructs the computer 2200 to specify specific steps associated with some or all of the blocks in the flowchart (FIG. 16) and block diagrams (FIGS. 4, 8, 11 and 14) described herein. may be executed by the CPU 2212 to cause the operations of .

Computer 2200 according to this embodiment includes CPU 2212 , RAM 2214 , graphics controller 2216 and display device 2218 . CPU 2212 , RAM 2214 , graphics controller 2216 and display device 2218 are interconnected by host controller 2210 . Computer 2200 further includes input/output units such as communication interface 2222, hard disk drive 2224, DVD-ROM drive 2226 and IC card drive. Communication interface 2222 , hard disk drive 2224 , DVD-ROM drive 2226 , IC card drive, etc. are connected to host controller 2210 via input/output controller 2220 . The computer further includes legacy input/output units such as ROM 2230 and keyboard 2242 . ROM 2230 , keyboard 2242 , etc. are connected to input/output controller 2220 via input/output chip 2240 .

CPU 2212 controls each unit by operating according to programs stored in ROM 2230 and RAM 2214 . Graphics controller 2216 causes the image data to be displayed on display device 2218 by retrieving image data generated by CPU 2212 into RAM 2214 , such as a frame buffer provided in RAM 2214 .

Communication interface 2222 communicates with other electronic devices over a network. Hard disk drive 2224 stores programs and data used by CPU 2212 within computer 2200 . DVD-ROM drive 2226 reads programs or data from DVD-ROM 2201 and provides the read programs or data to hard disk drive 2224 via RAM 2214 . The IC card drive reads programs and data from IC cards or writes programs and data to IC cards.

ROM 2230 stores programs that depend on the hardware of computer 2200, such as a boot program that is executed by computer 2200 upon activation. Input/output chip 2240 may connect various input/output units to input/output controller 2220 via parallel ports, serial ports, keyboard ports, mouse ports, and the like.

A program is provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from a computer-readable medium, installed in hard disk drive 2224 , RAM 2214 , or ROM 2230 , which are also examples of computer-readable medium, and executed by CPU 2212 . The information processing described within these programs is read by computer 2200 to provide coordination between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing information manipulation or processing in accordance with the use of computer 2200 .

For example, when communication is performed between the computer 2200 and an external device, the CPU 2212 executes a communication program loaded into the RAM 2214 and sends communication processing to the communication interface 2222 based on the processing described in the communication program. you can command. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in a recording medium such as the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or an IC card, and outputs the read transmission data. to the network, or writes received data received from the network to a receive buffer processing area or the like provided on the recording medium.

The CPU 2212 may cause the RAM 2214 to read all or necessary portions of files or databases stored in external recording media such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM 2201), and IC cards. CPU 2212 may perform various types of operations on data in RAM 2214 . CPU 2212 may then write back the processed data to an external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored and processed on recording media. CPU 2212 may perform various types of manipulation, information processing, conditional judgment, conditional branching, unconditional branching, information retrieval or Various types of processing may be performed, including permutations and the like. CPU 2212 may write results back to RAM 2214 .

The CPU 2212 may search for information in files in a recording medium, databases, and the like. For example, if a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 2212 determines that the attribute value of the first attribute is specified. search the plurality of entries for an entry that matches the condition, read the attribute value of the second attribute stored in the entry, and read the second attribute value to obtain the predetermined condition An attribute value of a second attribute associated with a first attribute that satisfies may be obtained.

The programs or software modules described above may be stored on computer 2200 or in a computer readable medium of computer 2200 . A storage medium such as a hard disk or RAM provided in a server system connected to a private communication network or the Internet can be used as the computer readable medium. The program may be provided to computer 2200 by the recording medium.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the scope of claims that forms with such modifications or improvements can also be included in the technical scope of the present invention.

The execution order of each process such as actions, procedures, steps, and stages in the devices, systems, programs, and methods shown in the claims, the specification, and the drawings is particularly "before", "before etc., and it should be noted that they can be implemented in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the specification, and the drawings, even if the description is made using "first,""next," etc. for the sake of convenience, it means that it is essential to carry out in this order. not a thing
[Item 1]
A driving support device comprising an estimation unit that estimates a performance deterioration rate of an ion-exchange membrane based on actual impurity data relating to an accumulation rate of impurities on the ion-exchange membrane in an electrolytic cell.
[Item 2]
wherein the estimating unit estimates a production parameter related to a product produced by the electrolytic cell when the electrolytic cell is operated under one operating condition, based on the performance deterioration rate; 1. The driving support device according to 1.
[Item 3]
3. The driving support device according to item 1 or 2, wherein the impurity data is actual analysis data of the ion exchange membrane.
[Item 4]
The electrolytic cell has an anode chamber and a cathode chamber separated by the ion exchange membrane,
An aqueous solution of alkali metal chloride is introduced into the anode chamber, and an aqueous solution of alkali metal hydroxide is discharged from the cathode chamber,
The impurity data is impurity concentration data in the aqueous solution of the alkali metal chloride,
4. The driving support device according to any one of items 1 to 3.
[Item 5]
5. The driving support device according to any one of items 1 to 4, wherein the estimation unit estimates the performance deterioration rate based on actual values of operating conditions of the electrolytic cell.
[Item 6]
further comprising a performance degradation learning unit that generates a performance degradation prediction model,
The performance degradation prediction model performs machine learning on the relationship between the actual impurity data value, the operating condition actual value, and the performance degradation speed, thereby obtaining the impurity data actual value and the operating condition actual value. , outputting a predicted amount of the performance degradation rate of the ion exchange membrane based on the relationship with the performance degradation rate;
A driving support device according to item 5.
[Item 7]
7. The driving support device according to item 6, wherein the performance degradation prediction model outputs a plurality of prediction amounts of performance degradation speeds corresponding to each of the plurality of operating conditions.
[Item 8]
comprising a plurality of the performance degradation learning units,
Each of the plurality of performance degradation learning units generates the performance degradation prediction model for each of the plurality of ion exchange membrane types,
The driving support device according to item 6 or 7.
[Item 9]
Item 6, wherein the performance degradation prediction model estimates operating conditions of the electrolytic cell that satisfy the production parameters based on the actual values of the impurity data and production parameters related to products produced by the electrolytic cell. 9. The driving support device according to any one of 8.
[Item 10]
The operation according to item 9, wherein the performance deterioration prediction model estimates at least one of a recovery time of the performance of the ion exchange membrane and a replacement time of the ion exchange membrane when the operating condition satisfying the production parameter does not exist. support equipment.
[Item 11]
an acquisition unit that acquires the impurity accumulation rate when the electrolytic cell is operated under one operating condition;
a correction unit that corrects the actual value of the impurity data based on the impurity accumulation speed acquired by the acquisition unit;
11. The driving support device according to any one of items 1 to 10, further comprising:
[Item 12]
The estimation unit acquires the actual value in a first period,
The acquisition unit acquires the impurity accumulation rate in a second period shorter than the first period.
12. A driving support device according to item 11.
[Item 13]
13. The driving support device according to any one of items 1 to 12, wherein the impurity is at least one of barium, calcium, strontium, iodine, silicon, aluminum, nickel, magnesium, iron, titanium and phosphorus.
[Item 14]
A driving support method, wherein the estimation unit includes a first estimation step of estimating a performance deterioration rate of the ion exchange membrane based on actual impurity data relating to an accumulation rate of impurities in the ion exchange membrane in an electrolytic cell.
[Item 15]
The estimating unit, based on the performance deterioration rate estimated in the first estimating step, is a production parameter when the electrolytic cell is operated under one operating condition, and is the production produced by the electrolytic cell. 15. The driving assistance method according to item 14, further comprising a second estimating step of estimating a production parameter related to the object.
[Item 16]
16. The driving support method according to item 14 or 15, wherein the first estimation step is a step in which the estimation unit estimates the performance deterioration rate based on actual values of operating conditions of the electrolytic cell.
[Item 17]
The first estimation step includes a performance degradation learning step in which the performance degradation learning unit generates a performance degradation prediction model,
The performance degradation prediction model performs machine learning on the relationship between the actual impurity data value, the operating condition actual value, and the performance degradation speed, thereby obtaining the impurity data actual value and the operating condition actual value. , outputting a predicted amount of the performance degradation rate of the ion exchange membrane based on the relationship with the performance degradation rate;
17. A driving support method according to item 16.
[Item 18]
The first estimating step includes operating the electrolytic cell in which the performance degradation prediction model satisfies the production parameters based on the actual value of the impurity data and the production parameters related to the product produced by the electrolytic cell. 18. The driving support method according to item 17, further including a driving condition estimation step of estimating conditions.
[Item 19]
an obtaining step in which the obtaining unit obtains the impurity accumulation rate when the electrolytic cell is operated under one operating condition;
a correcting step in which the correcting unit corrects the actual value of the impurity data based on the impurity accumulation speed obtained in the obtaining step;
19. The driving assistance method according to any one of items 14 to 18, further comprising:
[Item 20]
A driving assistance program for causing a computer to function as the driving assistance device according to any one of items 1 to 13.

10... Estimation unit 20... Control unit 30... Input unit 32... Output unit 33... Operation parameter Pd display unit 34... Production parameter Pr display unit 35. Acquisition unit 36 Correction unit 40 Storage unit 60 Performance degradation learning unit 62 Performance degradation prediction model 70 Liquid 71 Cation 72 Liquid 73 Liquid 74 Liquid 75 Liquid 76 Liquid 77 Gas 78 Gas 79 Anode chamber 80 ... anode, 82 ... cathode, 84 ... ion exchange membrane, 85 ... cluster, 86 ... anionic group, 88 ... bottom surface, 89 ... ceiling surface, 90 ... Electrolytic bath 91 Electrolytic cell 92 Introduction tube 93 Introduction tube 94 Lead-out tube 95 Lead-out tube 98 Cathode chamber 100 Operation Support device 200 Electrolytic device 2200 Computer 2201 DVD-ROM 2210 Host controller 2212 CPU 2214 RAM 2216 Graphic controller 2218: display device, 2220: input/output controller, 2222: communication interface, 2224: hard disk drive, 2226: DVD-ROM drive, 2230: ROM, 2240: input/output Chip, 2242...Keyboard

Claims (20)

An estimating unit for estimating the rate of performance deterioration of the ion exchange membrane based on the actual value of impurity data regarding the rate of accumulation of impurities on the ion exchange membrane in the electrolytic cell and the actual value of the operating conditions of the electrolytic cell,
The electrolytic cell has an anode chamber and a cathode chamber separated by the ion exchange membrane,
an aqueous solution of an alkali metal chloride is introduced into the anode chamber,
The concentration profile of the alkali metal from the anode chamber to the cathode chamber varies based on actual operating conditions of the electrolytic cell,
The estimation unit estimates the performance deterioration rate based on the concentration profile.
Driving assistance device. Accumulation positions of the impurities on the ion exchange membrane change based on changes in the concentration profile,
The estimation unit estimates the performance degradation rate based on the accumulated position.
The driving assistance device according to claim 1. 3. The driving support device according to claim 1, wherein the actual operating condition value is a pH actual value of the alkali metal aqueous solution. wherein the estimating unit estimates a production parameter related to a product produced by the electrolytic cell when the electrolytic cell is operated under one operating condition, based on the performance deterioration rate. 4. The driving support device according to any one of items 1 to 3. The driving support device according to any one of claims 1 to 4, wherein the impurity data is actual analysis data of the ion exchange membrane. The electrolytic cell has an anode chamber and a cathode chamber separated by the ion exchange membrane,
An aqueous solution of alkali metal chloride is introduced into the anode chamber, and an aqueous solution of alkali metal hydroxide is discharged from the cathode chamber,
The impurity data is impurity concentration data in the aqueous solution of the alkali metal chloride,
The driving assistance device according to any one of claims 1 to 5. an estimating unit for estimating the rate of performance deterioration of the ion-exchange membrane based on actual impurity data relating to the rate of accumulation of impurities on the ion-exchange membrane in an electrolytic cell;
a plurality of performance degradation learning units that generate a performance degradation prediction model;
an acquisition unit that acquires in real time the impurity accumulation rate when the electrolytic cell is operated under one operating condition;
a correction unit that corrects the past performance value of the impurity data based on the current accumulation rate of the impurities acquired by the acquisition unit;
with
The performance degradation prediction model performs machine learning on the relationship between the performance degradation rate and the actual impurity data value and the operating condition of the electrolytic cell, thereby obtaining the actual impurity data value and the operating condition. Outputting a predicted amount of the performance deterioration rate of the ion exchange membrane based on the relationship between the actual value and the performance deterioration rate,
Each of the plurality of performance degradation learning units generates the performance degradation prediction model for each of the plurality of ion exchange membrane types,
The type of the ion-exchange membrane is the density of anion groups in the ion-exchange membrane or the thickness of the ion-exchange membrane.
Driving assistance device. 8. The driving assistance device according to claim 7, wherein said performance deterioration prediction model outputs a plurality of predicted amounts of performance deterioration speed corresponding to each of said plurality of operating conditions. The performance degradation prediction model estimates operating conditions of the electrolytic cell that satisfy the production parameters based on actual values of the impurity data and production parameters related to products produced by the electrolytic cell. 9. The driving support device according to 7 or 8. 10. The performance degradation prediction model according to claim 9, wherein, when the operating conditions that satisfy the production parameters do not exist, at least one of a recovery time of the performance of the ion-exchange membrane and a replacement time of the ion-exchange membrane is estimated. Driving assistance device. The estimation unit acquires the actual value in a first period,
The acquisition unit acquires the impurity accumulation rate in a second period shorter than the first period.
The driving assistance device according to any one of claims 7 to 10 . The driving support device according to any one of claims 1 to 11 , wherein said impurity is at least one of barium, calcium, strontium, iodine, silicon, aluminum, nickel, magnesium, iron, titanium and phosphorus. The estimating unit estimates the rate of deterioration of the performance of the ion exchange membrane based on the actual value of the impurity data regarding the rate of accumulation of impurities in the ion exchange membrane in the electrolytic cell and the actual value of the operating conditions of the electrolytic cell. 1 estimation step,
The electrolytic cell has an anode chamber and a cathode chamber separated by the ion exchange membrane,
an aqueous solution of an alkali metal chloride is introduced into the anode chamber,
The concentration profile of the alkali metal from the anode chamber to the cathode chamber varies based on actual operating conditions of the electrolytic cell,
In the first estimation step, the estimation unit estimates the performance deterioration rate based on the concentration profile.
Driving assistance method. Accumulation positions of the impurities on the ion exchange membrane change based on changes in the concentration profile,
The first estimation step is a step in which the estimation unit estimates the performance degradation rate based on the accumulation position.
The driving support method according to claim 13 . 15. The driving support method according to claim 13 , wherein the actual value of the operating condition is the actual value of pH of the aqueous solution of the alkali metal. The estimating unit, based on the performance deterioration rate estimated in the first estimating step, is a production parameter when the electrolytic cell is operated under one operating condition, and is the production produced by the electrolytic cell. 16. The driving assistance method according to any one of claims 13 to 15 , further comprising a second estimation step of estimating production parameters relating to objects. The first estimation step includes a performance degradation learning step in which a plurality of performance degradation learning units generate a performance degradation prediction model,
The performance degradation prediction model performs machine learning on the relationship between the actual impurity data value, the operating condition actual value, and the performance degradation speed, thereby obtaining the impurity data actual value and the operating condition actual value. , outputting a predicted amount of the performance degradation rate of the ion exchange membrane based on the relationship with the performance degradation rate;
The performance degradation learning step is a step in which each of the plurality of performance degradation learning units generates the performance degradation prediction model for each of the plurality of ion exchange membrane types,
The type of the ion-exchange membrane is the density of anion groups in the ion-exchange membrane or the thickness of the ion-exchange membrane.
The driving assistance method according to any one of claims 13 to 16 . The first estimating step includes operating the electrolytic cell in which the performance degradation prediction model satisfies the production parameters based on the actual value of the impurity data and the production parameters related to the product produced by the electrolytic cell. 18. The driving assistance method according to claim 17 , further comprising a driving condition estimation step of estimating conditions. an obtaining step in which the obtaining unit obtains the impurity accumulation rate when the electrolytic cell is operated under one operating condition;
a correcting step in which the correcting unit corrects the actual value of the impurity data based on the impurity accumulation speed obtained in the obtaining step;
The driving assistance method according to any one of claims 13 to 18 , further comprising: A driving assistance program for causing a computer to function as the driving assistance device according to any one of claims 1 to 12 .

Images