Temperature measuring device and temperature measuring method

Abstract

A temperature measuring device 1: determines the phase state of a metal M over time, on the basis of a visible light image IMGv of the metal M; and uses an emission rate which is in accordance with the determined phase state to convert the infrared intensity of an infrared image IMGi of the metal M into a temperature value.

Description

Temperature measurement device and temperature measurement method

[0001] The present disclosure relates to a temperature measurement device and a temperature measurement method.

[0002] A conventional technique for joining two metal members by laser welding has been known. In laser welding, the temperature of the metal surfaces has been measured in a non-contact manner using an infrared camera to evaluate the welding quality, etc. (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2001-191186

[0004] When measuring temperature without contact, high measurement accuracy is naturally desired.

[0005] The present disclosure has been made in light of these circumstances, and one of its objectives is to provide a technology for improving the accuracy of non-contact temperature measurement.

[0006] One aspect of the present disclosure is a temperature measurement device that determines the phase state of a metal over time based on a visible light image of the metal, and converts infrared intensity in an infrared image of the metal into a temperature value using an emissivity corresponding to the determined phase state.

[0007] Another aspect of the present disclosure is a temperature measurement method that includes capturing an image of a metal with a visible light camera to generate a visible light image, determining a phase state of the metal over time based on the visible light image, capturing an image of the metal with an infrared camera to generate an infrared image, and converting infrared intensity in the infrared image into a temperature value using an emissivity corresponding to the determined phase state.

[0008] Any combination of the above components, and conversion of the expression of the present disclosure into a method, device, system, etc., are also valid aspects of the present disclosure.

[0009] According to the present disclosure, it is possible to improve the accuracy of non-contact temperature measurement.

[0010] Fig. 3 is a block diagram of a temperature measuring device according to an embodiment. Fig. 3 is a diagram showing the brightness values ​​of pixels on line A-A in a visible light image IMGv. Fig. 3(A) is a diagram showing a temperature image generated by a temperature measuring device according to a comparative example. Fig. 3(B) is a diagram showing a temperature image generated by a temperature measuring device according to an embodiment.

[0011] The present disclosure will be described below with reference to the drawings based on preferred embodiments. The embodiments are illustrative and do not limit the present disclosure, and all features and combinations thereof described in the embodiments are not necessarily essential to the present disclosure. The same or equivalent components, parts, and processes shown in each drawing are designated by the same reference numerals, and redundant descriptions will be omitted where appropriate. The scale and shape of each part shown in each drawing are set for convenience to facilitate explanation and should not be interpreted as limiting unless otherwise specified. Furthermore, when terms such as "first" and "second" are used in this specification or claims, unless otherwise specified, these terms do not represent any order or importance, but are intended to distinguish one configuration from another. Furthermore, some components that are not important for explaining the embodiments are omitted from each drawing.

[0012] Fig. 1 is a block diagram of a temperature measuring device 1 according to an embodiment. In Fig. 1, a calculation unit 6 is depicted as a functional block. This functional block is realized as a hardware configuration by elements and circuits such as a computer CPU and memory, and as a software configuration by a computer program or the like. Those skilled in the art will understand that this functional block can be realized in various forms by combining hardware and software.

[0013] As an example, the temperature measuring device 1 includes a visible light camera 2, an infrared camera 4, and a calculation unit 6, and measures the temperature of the surface of the metal M in a non-contact manner. The visible light camera 2, the infrared camera 4, and the calculation unit 6 may be separate entities, or some of the mechanisms may be integrated. For example, all or part of the calculation unit 6 may be mounted on the infrared camera 4. Furthermore, the visible light camera 2 and the infrared camera 4 may be excluded from the configuration of the temperature measuring device 1. In this case, the temperature measuring device 1 can measure the temperature of the surface of the metal M in a non-contact manner by acquiring images from the external visible light camera 2 and infrared camera 4.

[0014] The visible light camera 2 has sensitivity in the visible light region and captures an image of the metal M. The visible light image IMGv generated by the visible light camera 2 is sent to the calculation unit 6. The visible light image IMGv captures the surface of the metal M. As an example, the visible light camera 2 repeatedly captures images of the metal M and repeatedly sends the visible light image IMGv to the calculation unit 6.

[0015] The infrared camera 4 has sensitivity in the infrared region and captures an image of the metal M. The infrared image IMGi generated by the infrared camera 4 is sent to the calculation unit 6. The infrared image IMGi shows the surface of the metal M. As an example, the infrared camera 4 repeatedly captures an image of the metal M and repeatedly sends the infrared image IMGi to the calculation unit 6.

[0016] The calculation unit 6 determines the phase state of the metal M, more specifically, the phase state of the surface of the metal M, over time, based on the visible light image IMGv. For example, the calculation unit 6 determines the phase state of the metal M by analyzing the visible light reflectance of the metal M based on the visible light image IMGv. The phase state includes solid, liquid, gas, and plasma states. As an example of analyzing visible light reflectance, the calculation unit 6 determines the phase state of the metal M based on pixel values ​​related to light intensity in the visible light image IMGv, for example, luminance values.

[0017] 2 is a diagram showing the luminance values ​​of pixels on line A-A in the visible light image IMGv. For example, the calculation unit 6 determines that the metal M is in a solid state when the luminance value of the pixel in the visible light image IMGv is equal to or greater than a predetermined first value. Furthermore, the calculation unit 6 determines that the metal M is in a liquid state when the luminance value of the pixel in the visible light image IMGv is equal to or less than a predetermined second value. When the pixel luminance has 256 gradations, the first value is, for example, 80, and the second value is a value lower than the first value, for example, 60.

[0018] As shown in Figure 2, in pixel regions corresponding to portions Ms in a solid state on the surface of the metal M, the brightness value is generally 80 or higher. In addition, in pixel regions corresponding to portions Ml in a liquid state on the surface of the metal M, the brightness value is generally 60 or lower. Therefore, it is possible to determine the phase state of the metal M based on pixel values ​​related to light intensity in the visible light image IMGv. Note that the calculation unit 6 may determine the phase state of the metal M using a preset program or a trained artificial intelligence (AI) model.

[0019] For the trained artificial intelligence model, time-series image data recording, for example, the melting of a metal is prepared. This image data is labeled as solid and liquid regions. Then, AI learning is performed using the labeled data. Using the artificial intelligence model obtained through this process, the calculation unit 6 determines the phase state of the metal M. By using the artificial intelligence model that has learned images of the change from solid to liquid regions, it is possible to distinguish between solid and liquid regions for metals of the same type and with similar surface conditions.

[0020] The emissivity varies depending on the phase state of the metal M. Therefore, the calculation unit 6 determines the emissivity according to the determined phase state. For example, a conversion table that associates the phase state with the emissivity is stored in advance in the calculation unit 6. The calculation unit 6 can determine the emissivity based on the phase state by using this conversion table. Furthermore, for example, when a laser is irradiated onto the surface of the metal M during laser welding, the phase state of the metal M changes over time. Therefore, the calculation unit 6 updates the emissivity according to the change in the phase state over time. Then, the calculation unit 6 converts the infrared intensity in the infrared image IMGi into a temperature value using the set emissivity.

[0021] As an example, a correspondence between pixels of the visible light image IMGv and pixels of the infrared image IMGi is determined in advance and stored in the calculation unit 6. The calculation unit 6 determines the phase state of the metal M for each pixel of the visible light image IMGv. That is, in the process performed by the calculation unit 6, the surface of the metal M is divided into multiple portions corresponding to each pixel of the visible light image IMGv, and the phase state is determined for each of these portions. Furthermore, based on the correspondence between the pixels of the visible light image IMGv and the pixels of the infrared image IMGi, the calculation unit 6 determines an emissivity for each pixel of the infrared image IMGi corresponding to the phase state determined for each pixel of the visible light image IMGv. Then, using the emissivity set for each pixel, the calculation unit 6 converts the infrared intensity of each pixel of the infrared image IMGi into a temperature value. Note that a set of multiple pixels may be the smallest unit of a portion for which the phase state is determined individually.

[0022] The calculation unit 6 converts the infrared intensity into a temperature value and displays the result as, for example, a temperature image on a monitor (not shown). Fig. 3(A) is a diagram showing a temperature image generated by a temperature measuring device according to a comparative example. Fig. 3(B) is a diagram showing a temperature image generated by the temperature measuring device 1 according to the embodiment. A comparison of Fig. 3(A) and Fig. 3(B) shows that by changing the emissivity in accordance with changes in the phase state of the metal M, it is possible to convert the infrared intensity into a temperature value with high accuracy even if the phase state of the metal M changes over time due to melting or the like.

[0023] As described above, the temperature measuring device 1 of this embodiment grasps the temporal change in the phase state of the metal M based on the continuously generated visible light images IMGv. Then, the emissivity set for each pixel of the infrared image IMGi is changed in accordance with the change in the phase state. Therefore, the infrared intensity can be converted into a temperature value using the emissivity appropriate for the phase state of the metal M. This improves the accuracy of non-contact temperature measurement compared to when the emissivity is kept constant while ignoring the change in the state of the metal M.

[0024] The temperature measuring device 1 of this embodiment can also be used when measuring the temperature of a metal surface in a non-contact manner in techniques other than laser welding. The present disclosure also includes a computer program executed by the calculation unit 6. This computer program causes the calculation unit 6 to perform a function of determining the phase state of the metal M over time based on the visible light image IMGv of the metal M, and converting the infrared intensity in the infrared image IMGi of the metal M into a temperature value using an emissivity corresponding to the determined phase state. The present disclosure also includes a storage medium that stores the computer program.

[0025] The embodiments of the present disclosure have been described in detail above. The above-described embodiments merely illustrate specific examples of implementing the present disclosure. The content of the embodiments does not limit the technical scope of the present disclosure, and many design modifications, such as changing, adding, or deleting components, are possible within the scope of the invention defined in the claims. A new embodiment with design modifications will combine the effects of the combined embodiments and modifications. In the above-described embodiments, content that allows such design modifications is emphasized by using notations such as "in this embodiment" or "in this embodiment," but design modifications are also permitted even in content without such notation. Furthermore, any combination of components included in each embodiment is also valid as an aspect of the present disclosure. Hatching on cross sections in the drawings does not limit the material of the hatched object.

[0026] The embodiments may be specified by the following items: [Item 1] A temperature measurement device (1) that determines the phase state of a metal (M) over time based on a visible light image (IMGv) of the metal (M), and converts the infrared intensity in an infrared image (IMGi) of the metal (M) into a temperature value using an emissivity corresponding to the determined phase state. [Item 2] A temperature measurement method that includes: capturing an image of the metal (M) with a visible light camera (2) to generate a visible light image (IMGv), determining the phase state of the metal (M) over time based on the visible light image (IMGv), capturing an image of the metal (M) with an infrared camera (4) to generate an infrared image (IMGi), and converting the infrared intensity in the infrared image (IMGi) into a temperature value using an emissivity corresponding to the determined phase state.

[0027] The present disclosure can be used in a temperature measurement device and a temperature measurement method.

[0028] 1 Temperature measurement device, 2 Visible light camera, 4 Infrared camera, 6 Calculation unit, IMGi Infrared image, IMGv Visible light image, M Metal.

Claims

1. A temperature measuring device which determines the phase state of a metal over time based on a visible light image of the metal, and converts infrared intensity in an infrared image of the metal into a temperature value using an emissivity corresponding to the determined phase state.

2. A temperature measurement method comprising: capturing an image of a metal with a visible light camera to generate a visible light image; determining a phase state of the metal over time based on the visible light image; capturing an image of the metal with an infrared camera to generate an infrared image; and converting infrared intensity in the infrared image into a temperature value using an emissivity corresponding to the determined phase state.

Images