JP7235051B2 - Information processing device, control method, and program - Google Patents

Description

The present invention relates to analysis of gas characteristics.

Techniques for obtaining information about gas by measuring gas with a sensor have been developed. Also, in gas measurement, techniques for reducing the influence of unnecessary moisture are being studied.

Patent Literature 1 describes a technique in which a gas sample containing moisture and odor components is passed through an odor component collection material to be carried thereon, and then sent to a sensor by an inert gas. In addition, this document describes that the influence of moisture can be corrected by setting the amount of moisture carried on the odor component trapping material to a constant value.

Patent Document 2 discloses a detection output when a carrier gas containing no sample component is supplied to an odor detecting means via a dehumidifying means, and a carrier gas containing a sample component is supplied to the odor detecting means via the dehumidifying means. It is described that an odor detection process is executed based on the difference from the detection output when the odor is detected.

Patent Literature 3 describes obtaining the sterilization gas concentration by subtracting the amount corresponding to the humidity from the value detected by the gas concentration sensor according to the value detected by the humidity sensor.

Patent Literature 4 discloses an odor measuring device characterized by having means for adjusting the amount of water vapor in the gas to be measured.

JP-A-2002-350299 JP-A-11-125613 JP-A-2000-97906 JP-A-10-111224

The techniques of Patent Documents 1 to 4 are based on the premise that the unnecessary component is moisture. However, the unwanted component is not necessarily water.

The present invention has been made in view of the above problems. SUMMARY OF THE INVENTION An object of the present invention is to provide a technique for extracting the characteristics of a desired component among a plurality of components contained in a measured gas in gas measurement by a sensor.

The information processing apparatus of the present invention includes: 1) a first acquisition unit that acquires a feature amount of the measurement target gas, which is obtained based on the result of measuring the measurement target gas containing the first component and the second component by the first sensor; 2) a second acquisition unit that acquires a characteristic amount of the reference gas obtained based on the result of measuring the reference gas containing the second component with a second sensor; 3) a characteristic amount of the gas to be measured and the reference gas; and a calculating unit that calculates the feature amount of the estimation target gas that includes the first component but does not include the second component, based on the feature amount of . Both the first sensor and the second sensor are sensors whose detection values change according to the adhesion and detachment of molecules contained in the measured gas.

The control method of the present invention is executed by a computer. The control method includes: 1) a first obtaining step of obtaining a characteristic quantity of the gas to be measured, which is obtained based on the result of measuring the gas to be measured containing the first component and the second component with the first sensor; a second acquisition step of acquiring a feature amount of the reference gas obtained based on the result of measuring the reference gas containing the second component with the second sensor; 3) a feature amount of the gas to be measured and a feature amount of the reference gas; and a calculating step of calculating the feature quantity of the estimation target gas containing the first component but excluding the second component based on the above. Both the first sensor and the second sensor are sensors whose detection values change according to the adhesion and detachment of molecules contained in the measured gas.

The program of the present invention causes a computer to execute each step of the control method of the present invention.

ADVANTAGE OF THE INVENTION According to this invention, the technique which extracts the characteristic of a desired component among the several components contained in the measured gas in the measurement of gas by a sensor is provided.

The above objectives, as well as other objectives, features and advantages, will become further apparent from the preferred embodiments described below and the accompanying drawings below.
1 is a diagram illustrating an overview of an information processing apparatus according to a first embodiment; FIG. It is a figure which illustrates the sensor for obtaining the data which an information processing apparatus acquires. 2 is a diagram illustrating the functional configuration of the information processing apparatus according to Embodiment 1; FIG. It is a figure which illustrates the computer for implement|achieving an information processing apparatus. 4 is a flowchart illustrating the flow of processing executed by the information processing apparatus of Embodiment 1; It is a figure which illustrates the usage environment of an information processing apparatus. It is a figure which illustrates several time series data obtained from a sensor. FIG. 4 is a diagram illustrating a transform matrix for downsampling; FIG. 4 illustrates a linear transformation that removes offsets;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings. In addition, in all the drawings, the same constituent elements are denoted by the same reference numerals, and the description thereof will be omitted as appropriate. Moreover, in each block diagram, each block does not represent a configuration in units of hardware, but a configuration in units of functions, unless otherwise specified.

[Embodiment 1]
<Overview and theoretical background of the invention>
FIG. 1 is a diagram illustrating an overview of an information processing apparatus 2000 according to the first embodiment. FIG. 2 is a diagram exemplifying the sensor 10 for obtaining data acquired by the information processing apparatus 2000. As shown in FIG. The sensor 10 is a sensor that has a receptor to which a molecule adheres and whose detection value changes according to the adhesion and detachment of the molecule to the receptor. Here, the time-series data of the detection values output from the sensor 10 in response to gas sensing is referred to as time-series data 14 . Note that the time-series data 14 will also be referred to as a measurement result vector Y, and the detected value at time t will also be referred to as y(t), as required. Y will be a vector of y(t) enumerations.

For example, sensor 10 is a membrane-type surface stress (MSS) sensor. The MSS sensor has a functional membrane as a receptor to which molecules are attached, and the attachment and detachment of molecules to and from the functional membrane changes the stress generated in the support member of the functional membrane. The MSS sensor outputs a detection value based on this change in stress. Note that the sensor 10 is not limited to the MSS sensor. Various types of sensors such as cantilever type, membrane type, optical type, piezo sensor, and vibration response type can be used as long as they output a detection value based on a change.

As will be described later, the sensor 10 can also be referred to as an "odor sensor" because it is possible to obtain characteristic amounts of the components contained in the gas to be measured based on the results of measurement using the sensor 10. That is, when it is desired to grasp the characteristics of the odor emitted by a certain substance, the vapor generated from the substance (if the substance is a gas, the gas itself) is measured by the sensor 10, and the feature amount is obtained based on the measurement result. , the characteristics of the odor emitted by the substance can be grasped.

The information processing apparatus 2000 estimates the feature amount of the gas obtained by removing unnecessary components from the measurement target gas using the feature amount of the measurement target gas containing a plurality of types of components. Here, the feature amount of the measurement target gas is data based on the result of measuring the measurement target gas with the sensor 10 (that is, the measurement result vector Y). For example, the characteristic quantity of the gas to be measured is the measurement result vector Y (that is, the time-series data of the detection values of the sensor 10) itself. Alternatively, for example, the characteristic quantity of the gas to be measured may be a vector ξ (=AY) obtained by applying arbitrary linear transformation to the measurement result vector Y. where A is the transformation matrix. A specific example of linear transformation applied to Y will be described later.

For example, suppose we want to obtain features for a gas that contains ethanol molecules but not water molecules. In this case, for example, a gas obtained by vaporizing an ethanol aqueous solution (that is, a gas containing ethanol molecules and water molecules) is used as the measurement target gas, and the sensor 10 measures this measurement target gas. As a result, the feature quantity of the measurement target gas containing ethanol molecules and water molecules is obtained. The information processing apparatus 2000 uses the characteristic amount of the measurement target gas to estimate the characteristic amount of the gas obtained by removing the influence of water molecules from the measurement target gas (that is, the gas containing ethanol molecules but not water molecules). . Hereinafter, a gas for which the feature amount is estimated in this way (that is, a gas obtained by removing unnecessary molecules from the measurement target gas) is referred to as an estimation target gas.

For example, the information processing apparatus 2000 operates as follows in order to implement the above-described processing. First, the information processing device 2000 acquires the characteristic amount of the gas to be measured. Here, the gas to be measured contains at least different types of components, ie, a first component and a second component. Components contained in the measurement target gas other than the first component and the second component are not particularly limited. For example, the gas to be measured is composed of a carrier gas, a first component, and a second component. A carrier gas is, for example, an inert gas such as nitrogen or air.

One component may be composed of only a single type of molecule, or may be composed of a combination of multiple types of molecules. In the latter case, for example, one component is a combination of molecules that produce a particular odor.

Further, the information processing device 2000 acquires the feature quantity of the reference gas containing the second component. For example, the reference gas contains the same carrier gas as the carrier gas contained in the gas to be measured, and the second component. Here, the reference gas preferably does not contain the first component, but the content of the first component in the reference gas does not necessarily have to be zero. Also, the second component may be a component that can be contained in the carrier gas, such as moisture in the air.

The characteristic amount of the reference gas is obtained based on the result of measuring the reference gas with the sensor 20. FIG. The sensor 20, like the sensor 10, is a sensor that has the property that the detected value changes according to the attachment and detachment of molecules contained in the sensed gas. Note that the sensor 20 may be the same as or different from the sensor 10 . The feature amount of the reference gas may be the vector (time-series data) itself obtained by measuring the reference gas with the sensor 20, similarly to the feature amount of the gas to be measured. may be applied.

The information processing device 2000 calculates the feature quantity of the estimation target gas based on the feature quantity of the measurement target gas and the feature quantity of the reference gas. The estimation target gas is a gas that contains the first component but does not contain the second component.

It should be noted that the feature amount of the gas to be measured and the feature amount of the reference gas are of the same type. For example, if a vector representing the detection result of the sensor is used as the feature quantity of the gas to be measured, the vector representing the detection result of the sensor is also used as the feature quantity of the reference gas. On the other hand, if the feature value of the gas to be measured is obtained by linearly transforming the vector representing the detection result of the sensor, the feature value of the reference gas is also linearly transformed to the vector representing the detection result of the sensor. Use the one that has been subjected to

<Effect>
According to the information processing apparatus 2000 of the present embodiment, by using the characteristic amount of the reference gas containing the second component, the characteristic amount of the gas to be measured containing the first component and the second component is determined to include the first component. is calculated as the feature quantity of the estimation target gas that does not include the second component. That is, it is possible to obtain a feature quantity (that is, a feature quantity from which the effects of unnecessary components are removed) for a specific component among the gas containing a plurality of types of components. According to this method, the influence of any component can be removed without being limited to moisture.

Moreover, the information processing apparatus 2000 of the present embodiment is particularly useful in cases where it is difficult to actually measure the estimation target gas with a sensor. For example, depending on the type of molecule, it may be easier to handle the molecule dissolved in a solvent than to handle the molecule alone. For example, the aforementioned ethanol is easier to handle as an ethanol aqueous solution than as ethanol alone. Therefore, rather than directly measuring ethanol alone with the sensor 10, the gas obtained by vaporizing the aqueous ethanol solution is measured with the sensor 10, and the effect of water molecules is removed from the information (feature quantity) obtained based on the measurement. Obtaining information on ethanol alone makes the measurement easier. In this way, the information processing apparatus 2000 has the effect of facilitating the measurement required to obtain the feature amount of the desired component.

Note that the above description with reference to FIG. 1 is an example for facilitating understanding of the information processing apparatus 2000 and does not limit the functions of the information processing apparatus 2000 . The information processing apparatus 2000 of this embodiment will be described in further detail below.

<Example of Functional Configuration of Information Processing Device 2000>
FIG. 3 is a diagram illustrating the functional configuration of the information processing apparatus 2000 according to the first embodiment. The information processing apparatus 2000 has a first acquisition section 2020 , a second acquisition section 2040 and a calculation section 2060 . The first acquisition unit 2020 acquires the feature quantity of the gas to be measured. The second acquisition unit 2040 acquires the feature quantity of the reference gas. The calculation unit 2060 calculates the feature quantity of the estimation target gas based on the feature quantity of the measurement target gas and the feature quantity of the reference gas.

<Hardware Configuration of Information Processing Device 2000>
Each functional configuration unit of the information processing apparatus 2000 may be implemented by hardware (eg, hardwired electronic circuit) that implements each functional configuration unit, or may be implemented by a combination of hardware and software (eg, combination of an electronic circuit and a program for controlling it, etc.). A case where each functional component of the information processing apparatus 2000 is implemented by a combination of hardware and software will be further described below.

FIG. 4 is a diagram illustrating a computer 1000 for realizing the information processing apparatus 2000. As shown in FIG. Computer 1000 is any computer. For example, the computer 1000 is a stationary computer such as a personal computer (PC) or a server machine. In addition, for example, the computer 1000 is a portable computer such as a smart phone or a tablet terminal. The computer 1000 may be a dedicated computer designed to implement the information processing apparatus 2000, or may be a general-purpose computer.

Computer 1000 has bus 1020 , processor 1040 , memory 1060 , storage device 1080 , input/output interface 1100 and network interface 1120 . The bus 1020 is a data transmission path through which the processor 1040, memory 1060, storage device 1080, input/output interface 1100, and network interface 1120 mutually transmit and receive data. However, the method of connecting processors 1040 and the like to each other is not limited to bus connection.

The processor 1040 is various processors such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and an FPGA (Field-Programmable Gate Array). The memory 1060 is a main memory implemented using a RAM (Random Access Memory) or the like. The storage device 1080 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, ROM (Read Only Memory), or the like.

The input/output interface 1100 is an interface for connecting the computer 1000 and input/output devices. For example, the input/output interface 1100 is connected to an input device such as a keyboard and an output device such as a display device. In addition, for example, the sensor 10 is connected to the input/output interface 1100 . However, the sensor 10 does not necessarily have to be directly connected to the computer 1000 . For example, the sensor 10 may store the time-series data 14 in a storage device shared with the computer 1000 .

A network interface 1120 is an interface for connecting the computer 1000 to a communication network. This communication network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). A method for connecting the network interface 1120 to the communication network may be a wireless connection or a wired connection.

The storage device 1080 stores program modules that implement each functional component of the information processing apparatus 2000 . The processor 1040 reads each program module into the memory 1060 and executes it, thereby realizing the function corresponding to each program module.

<Process flow>
FIG. 5 is a flowchart illustrating the flow of processing executed by the information processing apparatus 2000 of the first embodiment. The first acquisition unit 2020 acquires the characteristic amount of the gas to be measured (S102). The second acquisition unit 2040 acquires the feature quantity of the reference gas (S104). The calculation unit 2060 calculates the feature quantity of the estimation target gas based on the feature quantity of the measurement target gas and the feature quantity of the reference gas (S106).

<Example of Usage Environment of Information Processing Device 2000>
Here, in order to facilitate understanding of the following description, a specific example of the usage environment of the information processing apparatus 2000 will be given. FIG. 6 is a diagram illustrating a usage environment of the information processing device 2000. As shown in FIG. The sensor 10 of FIG. 6 has a housing 102 , a sensor body (receptor) 104 , a sampling pump 106 , a purge pump 108 and an output interface 110 . The sampling pump 106 is a pump for introducing the gas to be measured into the housing 102 . By introducing the gas to be measured into the housing 102 using the sampling pump 106, the sensor body 104 is exposed to the gas to be measured. Thereby, the gas to be measured is measured by the sensor 10 .

The sensor body 104 outputs the time-series data 14 described above. The time-series data 14 are output to the outside via the output interface 110 . In the example of FIG. 6, the time-series data 14 are output to the information processing device 2000 .

The information processing device 2000 is connected to the storage device 120 . The storage device 120 stores the feature quantity of the reference gas. The feature amount of the reference gas is generated based on the result of measuring the reference gas with the sensor 20 and stored in the storage device 120 in advance. For the sensor 20, for example, the same sensor as the sensor 10 is used.

The information processing device 2000 uses the time-series data 14 obtained from the sensor 10 to calculate the feature quantity of the gas to be measured. Further, the information processing device 2000 acquires the feature quantity of the reference gas from the storage device 120 . Then, the information processing apparatus 2000 calculates the feature quantity of the inference target gas using the feature quantity of the measurement target gas and the feature quantity of the reference gas. A specific calculation method for this will be described later.

A purge pump 108 is utilized to direct purge gas to the sensor body 104 . The purge gas is a gas used to remove the measurement target gas from the sensor body 104 and return the sensor body 104 to the same state as before exposure to the measurement target gas. By repeating the operation of exposing the sensor main body 104 to the measurement target gas and the operation of removing the measurement target gas from the sensor main body 104 , a plurality of pieces of time-series data 14 may be obtained from the sensor 10 .

FIG. 7 is a diagram illustrating a plurality of time-series data 14 obtained from the sensor 10. As shown in FIG. In FIG. 7, the rising time-series data is represented by a solid line and the falling time-series data is represented by a dotted line so that the rising time-series data and the falling time-series data can be easily distinguished. . In FIG. 7, the time-series data 14-1 for the period P1 and the time-series data 14-3 for the period P3 are obtained by exposing the sensor body 104 to the gas to be measured. The time-series data obtained by exposing the sensor to the gas to be measured in this way is called "rising" time-series data.

On the other hand, the time-series data 14-2 for the period P2 and the time-series data 14-4 for the period P4 are obtained by the operation of removing the gas to be measured from the sensor (the operation of exposing the sensor main body 104 to the purge gas). The time-series data obtained by removing the gas to be measured from the sensor is called "falling" time-series data.

The feature value of the gas to be measured may be the rise time series data or the result obtained by adding an arbitrary linear transformation to this (hereinafter referred to as the feature value obtained from the rise time series data), or the fall time series data. It may be data or a result obtained by adding an arbitrary linear transformation to this (hereinafter referred to as a feature amount obtained from falling time-series data). Further, the feature amount of the target gas may be data obtained by concatenating the feature amount obtained from the rise time-series data and the feature amount obtained from the fall time-series data. The same applies to the feature quantity of the reference gas.

Here, the usage environment shown in FIG. 6 is an example for facilitating understanding of the following description, and does not limit the usage environment of the information processing apparatus 2000 . For example, in the example of FIG. 6, the feature amount of the gas to be measured is generated at the timing used by the information processing apparatus 2000 (generated online), and the feature amount of the reference gas is generated in advance (generated off-line). ), but the timing of generating these feature quantities is arbitrary. For example, the characteristic quantity of the gas to be measured may also be generated in advance and stored in the storage device. In addition, for example, the feature quantity of the reference gas may also be generated online.

<Acquisition of Characteristic Amount of Measurement Target Gas: S102>
The first acquisition unit 2020 acquires the characteristic amount of the gas to be measured (S102). Any method may be used by the first acquisition unit 2020 to acquire the feature amount of the gas to be measured. For example, as illustrated in FIG. 6, the first acquisition unit 2020 acquires the time-series data 14 output from the sensor 10 that measured the measurement target gas, and acquires the characteristic amount of the measurement target gas based on the time-series data 14. do. Here, when the feature amount is generated by transforming the time-series data 14, the first acquiring unit 2020 performs this transforming process. In addition, for example, a conversion device having a function of converting the time-series data 14 into the feature quantity of the gas to be measured may be interposed between the sensor 10 and the information processing device 2000 . In this case, the information processing device 2000 calculates the feature quantity of the gas to be measured from this conversion device.

Alternatively, for example, the information processing apparatus 2000 may acquire the feature amount of the measurement target gas by accessing a storage device in which the feature amount of the measurement target gas is stored. The storage device in which the characteristic amount of the gas to be measured is stored may be provided inside the information processing device 2000 or may be provided outside the information processing device 2000 .

<Acquisition of Feature Amount of Reference Gas: S104>
The second acquisition unit 2040 acquires the feature quantity of the reference gas (S104). Any one of the various methods described above as methods for obtaining the feature quantity of the measurement target gas can be adopted as the method of obtaining the feature quantity of the reference gas.

However, the characteristic quantity of the gas can change under the measurement conditions. Measurement conditions include, for example, gas temperature and gas flow rate. Therefore, for example, the second acquisition unit 2040 may acquire the feature amount of the reference gas in consideration of the measurement conditions of the measurement target gas. In other words, the second acquisition unit 2040 acquires the feature quantity of the reference gas corresponding to the measurement conditions similar to or matching the measurement conditions of the measurement target gas. In this case, the reference gas is measured under various measurement conditions, and a plurality of correspondences between the measurement conditions and the reference gas feature quantities are stored in the storage device 120 .

For example, the second acquisition unit 2040 acquires the characteristic quantity of the reference gas associated with the measurement conditions most similar to the measurement conditions of the measurement target gas. In addition, for example, the second acquisition unit 2040 acquires the feature amounts of the reference gas associated with each of a plurality of measurement conditions similar to the measurement conditions of the measurement target gas, and acquires the feature amounts of the acquired plurality of reference gases. may be used to calculate the feature quantity of the reference gas used for calculating the feature quantity of the estimation target gas. For example, the second acquisition unit 2040 performs arbitrary interpolation on a plurality of acquired sets of “measurement conditions and reference gas feature values” to obtain reference gas values under the same measurement conditions as those of the measurement target gas. Estimate features.

In addition, for example, an estimation model for estimating the feature amount of the reference gas from the measurement conditions is generated in advance using a plurality of associations between the measurement conditions and the feature amounts of the reference gas, and this estimation model is stored in the storage device. It may be stored. The second acquisition unit 2040 acquires this estimation model from the storage device, acquires the measurement conditions of the measurement target gas, and inputs them into the estimation model, thereby obtaining the reference gas corresponding to the same measurement conditions as the measurement conditions of the measurement target gas. Get the features of

In addition, the second acquisition unit 2040 acquires information indicating the measurement conditions of the measurement target gas in order to grasp the measurement conditions of the measurement target gas. This information may be manually input to the information processing apparatus 2000, or may be stored in any storage device.

ここで、F1 は、成分 X と成分 Y を含み、それぞれの濃度が x1 と y1 であるガスの特徴量である。F2 は、成分 X を含み、その濃度が x2 であるガスの特徴量である。F3 は、成分 Y を含み、その濃度が y2 であるガスの特徴量である。<Calculation of Characteristic Value of Estimation Target Gas: S106>
The calculation unit 2060 calculates the feature quantity of the estimation target gas based on the feature quantity of the measurement target gas and the feature quantity of the reference gas (S106). Here, the feature amount of the gas handled by the information processing apparatus 2000 is generally a linear sum of feature amounts caused by the respective components contained in the gas. Specifically, the following formula (1) holds. The reason why the formula (1) holds will be described later.

where F1 is a feature of a gas containing components X and Y with concentrations x1 and y1, respectively. F2 is a feature of a gas containing component X with concentration x2. F3 is a feature of a gas containing component Y with concentration y2.

ここで、測定対象ガスと推定対象ガスにおいて、第１成分の濃度は等しいとする。また、測定対象ガスにおいて、第２成分の濃度は a であるとする。さらに、参照ガスにおいて、第２成分の濃度は b であるとする。なお、0<a<1, 0<b<=1 を満たす。From this, the following equation (2) holds for the feature quantity Ft of the measurement target gas, the feature quantity Fe of the estimation target gas, and the feature quantity Fr of the reference gas.

Here, it is assumed that the measurement target gas and the estimation target gas have the same concentration of the first component. It is also assumed that the concentration of the second component is a in the gas to be measured. Further, let the concentration of the second component be b in the reference gas. Note that 0<a<1 and 0<b<=1 are satisfied.

Furthermore, from the above equation (2), the feature quantity of the estimation target gas is determined by the following equation (3).

The calculation unit 2060 calculates the feature quantity Fe of the estimation target gas from the feature quantity Ft of the measurement target gas and the feature quantity Fr of the reference gas based on the above equation (3). The methods are broadly divided into 1) calculation methods that do not require specification of the ratio s, and 2) calculation methods that require specification of the ratio s. Specific examples of each are given below.

<<Method that does not require specification of ratio s>>
In equation (3), if s=1, then Fe=Ft-Fr. That is, if the concentration of the second component in the gas to be measured is equal to the concentration of the second component in the reference gas, the feature amount of the estimation target gas is obtained by subtracting the feature amount of the reference gas from the feature amount of the gas to be measured. can be calculated by Equalizing the concentration of the second component in the gas to be measured and the concentration of the second component in the reference gas means that the partial pressure of the second component in the gas to be measured is equal to the partial pressure of the second component in the reference gas. is equivalent to equating

Therefore, the measurement for obtaining the characteristic quantity of the measurement target gas and the measurement for obtaining the characteristic quantity of the reference gas are performed under the measurement condition that the concentrations of the second component in the measurement target gas and the reference gas are equal. . The first acquisition unit 2020 acquires the feature quantity of the measurement target gas obtained under this measurement condition. Also, the second acquisition unit 2040 acquires the feature quantity of the reference gas obtained under this measurement condition. Then, the calculation unit 2060 calculates the feature amount of the estimation target gas by subtracting the feature amount of the reference gas from the feature amount of the measurement target gas.

Methods for equalizing the concentration of the second component in the gas to be measured and the reference gas include, for example, the following method. Here, it is assumed that the sensor 10 measures an odor emitted by a certain object. Here, the object may be solid, liquid, or gas. In this case, a gas obtained by passing a carrier gas through a container containing the object is used as the gas to be measured, and the carrier gas is used as the reference gas. By doing so, the concentrations of the components other than the odor component emitted by the object (that is, the second component) become equal.

As another method for equalizing the concentration of the second component in the gas to be measured and the reference gas, there is, for example, the following method. Here, it is assumed that it is desired to remove the influence of the solvent from the gas to be measured, which is the vapor of the solution (for example, to remove the influence of water vapor from the vapor of the aqueous solution). In this case, for example, a solution is put in the container for the gas to be measured, and a solvent is put in the container for the reference gas. Then, by equalizing the temperatures of these gases and performing an operation to make the vapor in the measurement vessel saturated vapor, the concentrations of the second component (gas molecules of the solvent) in the measurement target gas and the reference gas are equalized. can be done. Here, as a method of equalizing the temperature of the gas to be measured and the reference gas, for example, there is a method of leaving them in a place close to each other or in a place with the same temperature for a sufficient period of time. Further, as an operation for making the steam in the measurement container saturated, for example, there is an operation of sufficiently stirring the measurement container.

<<Method that requires identification of ratio s>>
Calculation unit 2060 identifies the ratio s in equation (3) (that is, the ratio of the concentration b of the second component in the target gas to the concentration a of the second component in the reference gas), and using equation (3), A feature value of the estimation target gas is calculated. That is, the calculation unit 2060 calculates the feature quantity of the estimation target gas by subtracting the feature quantity of the reference gas multiplied by the ratio s from the feature quantity of the measurement target gas.

To use this method, we need to specify the ratio s. Three methods for specifying the ratio s are exemplified below.

<<<Method 1 for identifying ratio s>>>
For each of the gas to be measured and the reference gas, the concentration of the second component is measured using a sensor that measures the concentration of the second component contained in the gas. As a result, the concentration of the second component in each gas can be specified, so that s, which is their ratio, can be specified. That is, the calculation unit 2060 calculates the ratio s (=a/b) by dividing the concentration a of the measurement target gas specified by the measurement by the concentration b of the reference gas specified by the measurement.

For example, assume that the second component is water molecules. In this case, a humidity sensor is used as the concentration sensor. Thereby, the concentration of water molecules can be measured. The measurement by the concentration sensor may be performed together with the measurement by the sensor 10, or may be performed separately. In the former case, for example, in the sensor 10 of FIG. 6, the sampling pump 106 is provided with a concentration sensor.

Here, it is assumed that the feature quantity of the reference gas is stored in the storage device 120 in advance. In this case, in addition to the feature quantity of the reference gas, the measurement result of the concentration of the second component in the reference gas is also stored in the storage device 120 . The calculation unit 2060 calculates the ratio s by dividing the concentration a of the second component in the measurement target gas obtained by the concentration sensor by the concentration b of the second component in the reference gas obtained from the storage device 120 .

<<<Method 2 for identifying ratio s>>>
The calculation unit 2060 may calculate the ratio s by solving an optimization problem that minimizes the size of the feature quantity of the estimation target gas as follows.

This optimization problem can be solved by identifying s with various search methods. Here, known methods such as binary search and gradient method can be used as search methods.

<<<Method 3 for identifying ratio s>>>
The calculation unit 2060 calculates the ratio s by solving the optimization problem of minimizing the residual when the feature quantity (Fe=Ft-sFr) of the estimation target gas is expressed as the sum of linear combinations of the basis feature quantities. You can Here, the base feature amount is a feature amount based on the measured value of a gas containing only a certain base component (hereinafter referred to as base gas). For example, if the gas to be measured is the vapor of sake, it is thought that it contains ethyl acetate, isoamyl acetate, ethyl caproate, etc., which are produced by yeast during fermentation, so these substances are used as base components. be able to. Also, the base component may be a mixture of multiple substances instead of a specific substance as described above.

ただし、Fm は各基底成分 m のみが含まれているガス（基底ガス）の測定値から算出した基底特徴量である。また、係数 um は、推定対象ガスにおける基底成分 m の濃度 am と基底ガスにおける基底成分の濃度 bm の比 am/bm である。 Here, when the types of components contained in the target gas for estimation include M kinds of base components, the target gas for estimation is expressed by the following linear sum as explained in the above equation (1). .

However, Fm is the base feature quantity calculated from the measured value of the gas containing only each base component m (basic gas). Also, the coefficient um is the concentration am of the base component m in the target gas and the concentration bm of the base component in the base gas ratio am/bm is.

ここで、目的関数の第２項は L1 正則化項である。For example, the calculation unit 2060 calculates the ratio s by solving the following optimization problem based on Equation (5). Note that the above-described "method 2 for specifying the ratio α" corresponds to the case where M=0 in the following formula (5).

where the second term of the objective function is the L1 regularization term.

This optimization problem can be solved by identifying s (and u _m ) with various search methods. Here, known methods such as the quadratic programming method and the gradient method can be used as the search method. Any distance other than the L2 distance can be used for the residual (the first term of the objective function) in Equation (6). Also, the regularization method is not limited to L1 regularization, and any regularization such as L2 regularization can be used.

It should be noted that the gas to be estimated need not consist only of M kinds of basis components. However, it is preferable to use components that may be included in the estimation target gas as base components as much as possible.

A base component that is not included in the estimation target gas may be selected as the base component. In this case, it is preferable to use the aforementioned L1 regularization term (λ ₁ >0) so that the coefficient um of the basis component that is not included in the gas to be estimated tends to become zero.

Note that the calculation unit 2060 may calculate the coefficients u1, u2, . . . , and uM as feature quantities of the estimation target gas.

<<<Method 3 for identifying ratio s>>>
Suppose the second component is a water molecule. For water molecules, the relationship between temperature and saturated water vapor content is known. Therefore, when measuring the gas to be measured with the sensor 10, if the amount of water molecules contained in the gas to be measured reaches the saturated water vapor content before the measurement is performed (for example, by stirring), the gas to be measured will contain The concentration of water molecules contained in the gas to be measured can be specified without measuring the concentration of water molecules. As for the reference gas, the concentration of water molecules contained in the reference gas can also be specified by a similar method.

The calculator 2060 acquires the temperatures of the measurement target gas and the reference gas. The calculation unit 2060 uses information that associates the temperature of the gas with the saturated water vapor content (for example, a function that converts the temperature to the saturated water vapor content) to calculate the number of water molecules in the gas to be measured from the temperature of the gas to be measured. Determine the saturated water vapor content. By a similar method, the calculator 2060 identifies the saturated water vapor content of water molecules in the reference gas from the temperature of the reference gas. Calculation unit 2060 then divides the saturated water vapor content specified for the measurement target gas by the saturated water vapor content specified for the reference gas as ratio s. Information that associates the temperature of the gas with the amount of saturated water vapor is stored in a storage device (for example, the storage device 120) accessible from the calculation unit 2060. FIG.

As described above, the saturated water vapor amount is related to the temperature. For example, the temperature of the measurement target gas can be specified by measuring the temperature of the measurement target gas with a temperature sensor. In addition, for example, if the temperature of the gas to be measured is made equal to the air temperature at the measurement location, the temperature of the gas to be measured can be specified by measuring the temperature at the measurement location. For example, the temperature of the gas to be measured can be made equal to the air temperature by leaving the target gas at the measurement location for a sufficient time before performing the measurement.

The temperature of the reference gas can be specified, for example, in the same way as the temperature of the gas to be measured. In addition, for example, a plurality of correspondences between temperatures (corresponding to the measurement conditions described above) and reference gas feature quantities are stored in the storage device 120, and the second acquisition unit 2040 acquires the temperature similar to or similar to the measurement target gas temperature. A feature quantity of the reference gas corresponding to the matching temperature may be obtained. In addition, for example, an estimation model for estimating the feature amount of the reference gas from the temperature of the reference gas is stored in the storage device 120, and the second acquisition unit 2040 acquires this estimation model and calculates the temperature of the gas to be measured. may be input into this estimation model to obtain the feature quantity of the reference gas.

In addition, even if the temperature of the target gas and the reference gas are not specified, these temperatures are equalized and the water molecule content is adjusted to reach the saturated water vapor content in both cases. For example, the concentrations of water molecules in the measurement target gas and the reference gas are equal. Therefore, in this way, the feature quantity of the estimation target gas can be calculated without specifying the ratio s. This corresponds to a method that does not require the specification of s. The method for equalizing the temperature of the reference gas of the gas to be measured is as described above.

<Output by Information Processing Device 2000>
The information processing device 2000 outputs information about the calculated feature amount of the estimation target gas. For example, the information processing device 2000 generates and outputs text data, image data (for example, graphs), and the like representing the feature amount of the estimation target gas. The output destination is arbitrary. For example, the output destination is a storage device or a display device.

<Reason why formula (1) holds>
As described above, the gas feature quantity handled by the information processing apparatus 2000 is generally a linear sum of the feature quantities resulting from the respective components contained in the gas. Therefore, the following formula (1) holds.

Here, the gas feature amount is a measurement result vector obtained as a result of measuring the gas with the sensor 10 or the sensor 20, or an arbitrary linear transformation of the measurement result vector. Here, data obtained by linearly transforming data having linearity always has linearity. Therefore, if the feature quantity represented by the measurement result vector has linearity, the feature quantity obtained by performing arbitrary linear transformation on the measurement result vector also has linearity.

Therefore, the fact that the feature quantity represented by the measurement result vector has linearity will be described below.

First, sensing in a sensor, such as the sensor 10 and the sensor 20, which has a receptor to which a molecule attaches and whose detection value changes according to the attachment and detachment of the molecule to the receptor, can be modeled as follows. . The sensor 10 is described below as an example.
(1) The sensor 10 is exposed to a target gas containing K types of molecules.
(2) The concentration of each molecule k in the gas is a constant ρk.
(3) A total of N molecules can be adsorbed on the sensor 10 .
(4) The number of molecules k attached to the sensor 10 at time t is nk(t).

The time variation of the number nk(t) of molecules k attached to the sensor 10 can be formulated as follows.

The first and second terms on the right side of equation (7) are the amount of increase (the number of molecules k newly attached to the sensor 10) and the amount of decrease (the number of molecules k detached from the sensor 10) per unit time, respectively. number). Also, .alpha.k and .beta.k are a rate constant representing the rate at which molecule k attaches to sensor 10 and a rate constant representing the rate at which molecule k separates from sensor 10, respectively.

Here, since the concentration ρk is constant, the number nk(t) of molecules k at time t can be formulated as follows from the above equation (7).

Also, assuming that no molecules adhere to the sensor 10 at time t0 (initial state), nk(t) is expressed as follows.

The detection value of the sensor 10 is determined by physical quantities related to viscoelasticity and dynamic characteristics such as stress acting on the sensor 10 by molecules contained in the gas. Then, it is considered that the physical quantity of the sensor 10 can be represented by a linear sum of the contributions of individual molecules to the physical quantity. However, the contributions of molecules to physical quantities are considered to vary depending on the types of molecules. That is, it can be said that the contribution of a molecule to the detection value of the sensor 10 varies depending on the type of molecule.

ここで、γk とξk はいずれも、センサ１０の検出値に対する分子 k の寄与を表す。Therefore, the detected value y(t) of the sensor 10 can be formulated as follows.

where γk and ξk both represent the contribution of the numerator k to the sensor 10 detection value.

The above equation (10) indicates that the time-series data 14 obtained by measuring the gas with the sensor 10 is the linear sum of the time-series data exp{-βkt} of the detected values due to each molecule k contained in the gas. It means that it will become Furthermore, equation (10) expresses that the coefficient .xi.k is proportional to each gas .rho.k concentration. Therefore, it can be seen that the time-series data 14 (that is, the measurement result vector) obtained by measuring the gas with the sensor 10 has linearity.

<Specific example of linear transformation>
As described above, the gas feature amount may be obtained by performing arbitrary linear transformation on the vector representing the detection result of the sensor. A specific example of this linear transformation is described here.

<<Statistics>>
For example, the average value of each element (detection value) indicated by the measurement result vector, or the amplitude of the time-series data represented by the measurement result vector can be used as the characteristic quantity of the gas. A conversion matrix A for calculating the average value can be represented by (1/N, 1/N, ..., 1/N). where N is the number of elements in the measurement result vector.

A transformation matrix A for calculating the amplitude can be expressed as (0, 0, -1, 0, 0, ..., 1, 0, ..., 0). Here, the column with a conversion matrix element of -1 corresponds to the element with the smallest detected value in the measurement result vector, and the column with a conversion matrix element of 1 corresponds to the element with the largest detected value in the measurement result vector. corresponds to

<<Downsampling>>
For example, a vector obtained by downsampling the measurement result vector can be used as the feature quantity. Specific downsampling methods include a method of thinning out the elements of the measurement result vector and a method of averaging the elements of the measurement result vector at predetermined intervals.

FIG. 8 is a diagram illustrating a transform matrix for downsampling. By using the transformation matrix in the upper part of FIG. 8, a vector obtained by extracting only one out of three elements from the measurement result vector can be obtained. On the other hand, if the conversion matrix in the lower part of FIG. 8 is used, a vector obtained by averaging three elements of the measurement result vector can be obtained.

<<Smoothing Filter>>
For example, a vector obtained by linearly transforming a measurement result vector using a smoothing filter such as a Gaussian filter can be used as a feature amount. In this case, the smoothing filter becomes the transformation matrix.

<<Remove Offset>>
The detection value of the sensor 10 can output a detection value greater than 0 even when the sensor 10 is not exposed to the gas to be measured. Transformation that removes the effects of such offsets from the detection result vector can also be implemented by linear transformation. FIG. 9 is a diagram illustrating a linear transform that removes the offset. The transformation matrix shown in the upper part of FIG. 9 implements a linear transformation that subtracts the average value from each detection value so that the average of the detection values indicated by the measurement result vector is zero. On the other hand, the transformation matrix shown in the lower part of FIG. 9 realizes linear transformation of subtracting the detection value at the reference time from each detection value so that the detection value at the reference time (for example, time t0) becomes 0.

ここで、目的関数の第２項は L2 正則化項である。

<<Method of least squares>>
The process of "representing the measurement result vector as a linear sum of other vectors by the method of least squares to obtain a vector listing the coefficients of each vector" can be represented by linear transformation. Specifically, when the least-squares method is formulated as the following equation (11), the transformation matrix for obtaining the above coefficients can be formulated as the transformation matrix shown in equation (12).

where the second term of the objective function is the L2 regularization term.

As a specific example of applying the least squares method, for example, the contribution of each type of component contained in the gas is taken out as the above-mentioned coefficients, and a vector listing the contributions is used as the characteristic quantity of the gas. A specific description will be given below.

First, as described above, the detected value y(t) of the sensor 10 can be expressed by the following equation (10).

ここで、ξi は、センサ１０の検出値に対する特徴定数θi の寄与を表す寄与値である。なお、ガスに含まれていない成分に対応する特徴定数については、寄与ξがゼロとなる。Therefore, for example, by defining a set of characteristic constants Θ={θ1, θ2, .

where .xi.i is a contribution value representing the contribution of the characteristic constant .theta.i to the detected value of the sensor 10; Note that the contribution ξ is zero for the characteristic constants corresponding to the components not contained in the gas.

Then, the vector Ξ listing the contribution values ξi is used as the feature quantity of the gas. As the characteristic constant θ, the rate constant β described above or the time constant τ, which is the reciprocal of the rate constant, can be used. For each case of using β and τ as θ, Equation (13) can be expressed as follows.

The decomposition shown in Equation (14) can be realized, for example, by the least-squares method formulated by Equation (16) below. Therefore, for the reason described above, the feature quantity Ξ that lists the coefficients ξk can be obtained by linearly transforming the measurement result vector. Note that the same applies to the decomposition shown in Equation (15).

<Method for removing the influence of two or more components>
The information processing device 2000 may calculate the feature quantity from which the effects of two or more components contained in the gas to be measured are removed. For example, in a situation where the gas to be measured contains n types of components from the 1st component to the n-th component, the characteristics of the gas to be measured include the first component but not the 2nd to n-th components. A feature amount of the gas may be calculated.

For example, the information processing apparatus 2000 repeats the above-described method of calculating the feature quantity from which the influence of the unnecessary component is removed, so that the estimation target that includes the first component but does not include the second to n-th components. A feature amount of the gas may be calculated. Specifically, first, the information processing apparatus 2000 uses the feature quantity of the measurement target gas containing the first to n-th components and the feature quantity of the reference gas containing the n-th component to obtain the first to (n -1) Calculate the feature value of the gas containing the component. Next, the information processing apparatus 2000 uses the feature quantity of the gas containing the first to (n-1)th components and the feature quantity of the reference gas containing the (n-1)th component to obtain the first to the Calculate the feature value of the gas containing the (n-2) component. By repeating such processing, it is possible to calculate the feature amount of the estimation target gas that includes the first component but does not include the second to n-th components.

In this method, in addition to the reference gas containing the second component, the reference gas containing the third component to the reference gas containing the n-th component, a total of (n-1) types of reference gas feature quantities are required. The method of obtaining the characteristic amount of each reference gas is the same as the method of obtaining the characteristic amount of the reference gas containing the second component described above.

ここで、Ft は測定対象ガスの特徴量であり、Fri は第 i 成分を含む参照ガスの特徴量である。In addition, for example, the information processing device 2000 uses the characteristic amounts of (n−1) kinds of reference gases to perform calculations to collectively remove the effects of the second to n-th components from the characteristic amounts of the gas to be measured. may This can be realized by solving an optimization problem for minimizing the magnitude of the feature quantity of the estimation target gas, as in the method represented by Equation (4). Specifically, the value of the objective function obtained as a result of solving the following least-squares method is the feature quantity of the estimation target gas. An existing technique can be used for the method of solving the least squares method.

where Ft is the characteristic quantity of the gas to be measured, and Fri is the characteristic quantity of the reference gas containing the i-th component.

In addition, when the concentration ratio of a plurality of types of components contained in the gas to be measured is known, this concentration ratio may be used. For example, suppose that the gas to be measured is liquor vapor, and the effects of ethanol molecules and water molecules are removed from the gas to be measured. In this case, if the alcohol content of sake is known, the concentration ratio of ethanol molecules and water molecules in the gas to be measured can be known.

For example, suppose the concentration of the kth component is w times the concentration of the jth species. In this case, for example, in equation (14), αk can be replaced with w*αj. By reducing the unknown coefficients in this way, it is possible to reduce the time required to calculate the feature amount and to more accurately calculate the feature amount of the estimation target gas.

Although the embodiments of the present invention have been described above with reference to the drawings, these are merely examples of the present invention, and configurations combining the above embodiments and various configurations other than those described above can also be adopted.

Some or all of the above-described embodiments can also be described in the following supplementary remarks, but are not limited to the following.
1. a first acquisition unit that acquires a feature amount of the measurement target gas, which is obtained based on the result of measuring the measurement target gas containing the first component and the second component with the first sensor;
a second acquisition unit that acquires a feature amount of the reference gas, which is obtained based on a result of measuring the reference gas containing the second component with a second sensor;
a calculating unit that calculates the feature quantity of the estimation target gas that includes the first component but does not include the second component based on the feature quantity of the measurement target gas and the feature quantity of the reference gas; ,
The information processing apparatus, wherein both the first sensor and the second sensor are sensors whose detection values change according to adhesion and detachment of molecules contained in the measured gas.
2. the concentration of the second component in the gas to be measured is equal to the concentration of the second component in the reference gas,
1. The calculation unit calculates the feature amount of the estimation target gas by subtracting the feature amount of the reference gas from the feature amount of the measurement target gas; The information processing device according to .
3. The calculation unit
identifying a ratio of the concentration of the second component in the measurement target gas to the concentration of the second component in the reference gas;
1. calculating the feature quantity of the gas to be measured by subtracting the feature quantity of the reference gas multiplied by the ratio from the feature quantity of the gas to be measured; The information processing device according to .
4. 3, wherein the calculation unit specifies the coefficient that minimizes the magnitude of the difference between the feature quantity of the measurement target gas and the feature quantity of the reference gas multiplied by the coefficient, and uses the specified coefficient as the ratio; . The information processing device according to .
5. The calculation unit calculates the coefficient that minimizes the residual between the difference between the characteristic quantity of the measurement target gas and the characteristic quantity of the reference gas multiplied by the coefficient, and the linear sum of the characteristic quantities of one or more components. 3. identify and use said identified factor as said ratio; The information processing device according to .
6. The first acquisition unit further acquires the concentration of the second component in the measurement target gas measured using a sensor that measures the concentration of the second component,
The second acquisition unit further acquires the concentration of the second component in the reference gas in addition to the feature amount of the reference gas,
The calculation unit calculates the ratio, the concentration of the second component in the measurement target gas obtained by the first acquisition unit, and the concentration of the second component in the reference gas obtained by the second acquisition unit. 3. calculated by dividing by . The information processing device according to .
7. the second component is a water molecule,
Both the amounts of the water molecules contained in the measurement target gas and the reference gas are saturated water vapor amounts,
3. The calculation unit calculates the ratio by dividing the saturated water vapor amount in the measurement target gas by the saturated water vapor amount in the reference gas; The information processing device according to .
8. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
The second acquisition unit acquires the measurement environment of the measurement target gas, and acquires the feature quantity of the reference gas associated with the measurement environment similar to the acquired measurement environment from the first storage device. 2. to 7. The information processing device according to any one of the above.
9. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
The second acquisition unit
Acquiring the measurement environment of the measurement target gas, acquiring a plurality of pairs of feature amounts of the measurement environment and the reference gas from the first storage device,
calculating a feature quantity of the reference gas in a measurement environment that matches the measurement environment of the measurement target gas using the acquired plurality of sets;
2. The calculation unit uses the calculated feature amount of the reference gas; to 7. The information processing device according to any one of the above.
10. an estimation model for estimating the feature quantity of the reference gas corresponding to the measurement conditions is stored in the second storage device;
The second acquisition unit acquires the measurement environment of the measurement target gas and the estimation model, and uses the estimation model to obtain the feature quantity of the reference gas corresponding to the measurement environment that matches the measurement environment of the measurement target gas. 2. to 7. The information processing device according to any one of the above.
11. The feature amount of the measurement target gas is time-series data of detected values obtained as a result of measuring the measurement target gas with the first sensor, or data obtained by applying a predetermined linear transformation to the time-series data,
1. The feature amount of the reference gas is time-series data of detected values obtained as a result of measuring the reference gas with the second sensor, or data obtained by applying a predetermined linear transformation to the time-series data. to 10. The information processing device according to any one of the above.

12. A control method implemented by a computer, comprising:
a first obtaining step of obtaining a feature amount of the gas to be measured, which is obtained based on the result of measuring the gas to be measured containing the first component and the second component with the first sensor;
a second acquisition step of acquiring a characteristic quantity of the reference gas, which is obtained based on a result of measuring the reference gas containing the second component with a second sensor;
a calculating step of calculating a feature quantity of the estimation target gas containing the first component but excluding the second component based on the feature quantity of the measurement target gas and the feature quantity of the reference gas. ,
The control method, wherein both the first sensor and the second sensor are sensors whose detection values change according to adhesion and detachment of molecules contained in the measured gas.
13. the concentration of the second component in the gas to be measured is equal to the concentration of the second component in the reference gas,
12. In the calculating step, the feature amount of the estimation target gas is calculated by subtracting the feature amount of the reference gas from the feature amount of the measurement target gas; The control method described in .
14. In the calculation step,
identifying a ratio of the concentration of the second component in the measurement target gas to the concentration of the second component in the reference gas;
12. calculating the feature quantity of the gas to be measured by subtracting the feature quantity of the reference gas multiplied by the ratio from the feature quantity of the gas to be measured; The control method described in .
15. 14, in the calculating step, specifying the coefficient that minimizes the magnitude of the difference between the characteristic quantity of the measurement target gas and the characteristic quantity of the reference gas multiplied by the coefficient, and using the identified coefficient as the ratio; . The control method described in .
16. In the calculating step, the coefficient that minimizes the residual between the difference between the characteristic quantity of the measurement target gas and the characteristic quantity of the reference gas multiplied by the coefficient and the linear sum of the characteristic quantities of one or more components is calculated. 13. Identifying and using said identified factor as said ratio; The control method described in .
17. In the first acquisition step, further acquiring the concentration of the second component in the gas to be measured, which is measured using a sensor that measures the concentration of the second component;
In the second obtaining step, in addition to the feature quantity of the reference gas, further obtaining the concentration of the second component in the reference gas;
In the calculating step, the ratio is the concentration of the second component in the measurement target gas obtained in the first obtaining step, and the concentration of the second component in the reference gas is obtained in the second obtaining step. 14. calculated by dividing by . The control method described in .
18. the second component is a water molecule,
Both the amounts of the water molecules contained in the measurement target gas and the reference gas are saturated water vapor amounts,
14. In the calculating step, the ratio is calculated by dividing the saturated water vapor amount in the measurement target gas by the saturated water vapor amount in the reference gas; The control method described in .
19. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
In the second obtaining step, the measurement environment of the measurement target gas is obtained, and the characteristic amount of the reference gas associated with the measurement environment similar to the obtained measurement environment is obtained from the first storage device. , 13. to 18. A control method according to any one of the preceding claims.
20. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
In the second acquisition step,
Acquiring the measurement environment of the measurement target gas, acquiring a plurality of pairs of feature amounts of the measurement environment and the reference gas from the first storage device,
calculating a feature quantity of the reference gas in a measurement environment that matches the measurement environment of the measurement target gas using the acquired plurality of sets;
13. Utilizing the calculated feature amount of the reference gas in the calculating step; to 18. A control method according to any one of the preceding claims.
21. an estimation model for estimating the feature quantity of the reference gas corresponding to the measurement conditions is stored in the second storage device;
In the second acquiring step, the measurement environment of the measurement target gas and the estimation model are acquired, and the estimation model is used to obtain the feature quantity of the reference gas corresponding to the measurement environment that matches the measurement environment of the measurement target gas. 13. to 18. A control method according to any one of the preceding claims.
22. The feature amount of the measurement target gas is time-series data of detected values obtained as a result of measuring the measurement target gas with the first sensor, or data obtained by applying a predetermined linear transformation to the time-series data,
12. The feature amount of the reference gas is time-series data of detected values obtained as a result of measuring the reference gas with the second sensor, or data obtained by applying a predetermined linear transformation to the time-series data. 21. A control method according to any one of the preceding claims.

23. 12. 22. A program that causes a computer to execute each step of the control method described in any one.

Claims (10)

a first acquisition unit that acquires a feature amount of the measurement target gas, which is obtained based on the result of measuring the measurement target gas containing the first component and the second component with the first sensor;
a second acquisition unit that acquires a feature amount of the reference gas, which is obtained based on a result of measuring the reference gas containing the second component with a second sensor;
a calculating unit that calculates the feature quantity of the estimation target gas that includes the first component but does not include the second component based on the feature quantity of the measurement target gas and the feature quantity of the reference gas; ,
Both the first sensor and the second sensor are sensors whose detection values change according to the adhesion and detachment of molecules contained in the measured gas,
The calculation unit
identifying a ratio of the concentration of the second component in the measurement target gas to the concentration of the second component in the reference gas;
calculating the feature amount of the estimation target gas by subtracting the feature amount of the reference gas multiplied by the ratio from the feature amount of the measurement target gas;
The feature amount of the measurement target gas is time-series data of detected values obtained as a result of measuring the measurement target gas with the first sensor, or data obtained by applying a predetermined linear transformation to the time-series data,
The feature amount of the reference gas is time-series data of detected values obtained as a result of measuring the reference gas with the second sensor, or data obtained by applying a predetermined linear transformation to the time-series data.
Information processing equipment. wherein the calculation unit specifies the coefficient that minimizes a difference between the feature quantity of the measurement target gas and the feature quantity of the reference gas multiplied by the coefficient, and uses the specified coefficient as the ratio. Item 1. The information processing apparatus according to item 1. The calculation unit calculates the coefficient that minimizes the residual between the difference between the characteristic quantity of the measurement target gas and the characteristic quantity of the reference gas multiplied by the coefficient, and the linear sum of the characteristic quantities of one or more components. 2. The information processing apparatus according to claim 1, wherein the specified coefficient is used as the ratio. The first acquisition unit further acquires the concentration of the second component in the measurement target gas measured using a sensor that measures the concentration of the second component,
The second acquisition unit further acquires the concentration of the second component in the reference gas in addition to the feature quantity of the reference gas,
The calculation unit calculates the ratio, the concentration of the second component in the measurement target gas obtained by the first acquisition unit, and the concentration of the second component in the reference gas obtained by the second acquisition unit. 2. The information processing apparatus according to claim 1, calculated by dividing by . the second component is a water molecule,
Both the amounts of the water molecules contained in the measurement target gas and the reference gas are saturated water vapor amounts,
2. The information processing apparatus according to claim 1, wherein said calculator calculates said ratio by dividing the saturated water vapor content in said measurement target gas by the saturated water vapor content in said reference gas. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
The second acquisition unit acquires the measurement environment of the measurement target gas, and acquires the feature quantity of the reference gas associated with the measurement environment similar to the acquired measurement environment from the first storage device. The information processing apparatus according to any one of claims 1 to 5. A feature amount of the reference gas obtained as a result of measurement under the measurement conditions is stored in a first storage device in association with a plurality of different measurement conditions,
The second acquisition unit
Acquiring the measurement environment of the measurement target gas, acquiring a plurality of pairs of feature amounts of the measurement environment and the reference gas from the first storage device,
calculating a feature quantity of the reference gas in a measurement environment that matches the measurement environment of the measurement target gas using the acquired plurality of sets;
The information processing apparatus according to any one of claims 1 to 5, wherein the calculation unit uses the calculated feature amount of the reference gas. an estimation model for estimating the feature quantity of the reference gas corresponding to the measurement conditions is stored in the second storage device;
The second acquisition unit acquires the measurement environment of the measurement target gas and the estimation model, and uses the estimation model to obtain the feature quantity of the reference gas corresponding to the measurement environment that matches the measurement environment of the measurement target gas. The information processing apparatus according to any one of claims 1 to 5, which acquires A control method implemented by a computer, comprising:
a first obtaining step of obtaining a feature amount of the gas to be measured, which is obtained based on the result of measuring the gas to be measured containing the first component and the second component with the first sensor;
a second acquisition step of acquiring a characteristic quantity of the reference gas, which is obtained based on a result of measuring the reference gas containing the second component with a second sensor;
a calculating step of calculating a feature quantity of the estimation target gas containing the first component but excluding the second component based on the feature quantity of the measurement target gas and the feature quantity of the reference gas. ,
Both the first sensor and the second sensor are sensors whose detection values change according to the adhesion and detachment of molecules contained in the measured gas,
In the calculation step,
identifying a ratio of the concentration of the second component in the measurement target gas to the concentration of the second component in the reference gas;
calculating the feature amount of the estimation target gas by subtracting the feature amount of the reference gas multiplied by the ratio from the feature amount of the measurement target gas;
The feature amount of the measurement target gas is time-series data of detected values obtained as a result of measuring the measurement target gas with the first sensor, or data obtained by applying a predetermined linear transformation to the time-series data,
The feature amount of the reference gas is time-series data of detected values obtained as a result of measuring the reference gas with the second sensor, or data obtained by applying a predetermined linear transformation to the time-series data.
control method. A program that causes a computer to execute each step of the control method according to claim 9 .

Images