# US 2025/0148173 A1 · Method and system for predicting hydration reaction degree of cement based on cyclegan

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0148173 A1
- Document ID: US20250148173A1
- Status: Published application
- Kind: A1
- Application number: 18/925,255
- Filed: 2024-10-24
- Published: 2025-05-08
- Earliest claimed: 2023-11-07
- Assignees: Zhengzhou University; China University of Mining and Technology
- Applicants: Zhengzhou University; China University of Mining and Technology
- Inventors: Mingrui DU; Xupei YAO; Hongyuan FANG; Peng ZHAO; Haijian Su; Niannian Wang; Xueming Du; Xiaohua ZHAO; Binghan Xue
- Web page: https://patentgrep.com/patent/US20250148173A1

## CPC

- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- C04B 28/04: Portland cements
- C04B 40/0032: {Controlling the process of mixing, e.g. adding ingredients in a quantity depending on a measured or desired value (B28C7/00 takes precedence)}
- Y02P 90/30: Computing systems specially adapted for manufacturing
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- C04B: LIME, MAGNESIA; SLAG; CEMENTS; COMPOSITIONS THEREOF, e.g. MORTARS, CONCRETE OR LIKE BUILDING MATERIALS; ARTIFICIAL STONE {(roofing granules E04D7/005)}; CERAMICS (devitrified glass-ceramics C03C10/00); REFRACTORIES; TREATMENT OF NATURAL STONE
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

Provided is a method and system for predicting a hydration reaction degree of cement based on a cycle generative adversarial network (CycleGAN). The method includes the following steps: S1, acquiring a micro-structure image of a cement paste test specimen; S2, establishing a micro-pore structure image dataset; S3, establishing a cement micro-hydration prediction model based on a CycleGAN; and S4, completing prediction based on a final cement micro-hydration prediction model. A deep learning algorithm is applied to micro-hydration prediction of cement. A complex theoretical formula is replaced with a data driven mode. Dependence on ideal hypotheses is reduced, and the accuracy of prediction on micro-hydration of cement is thus improved.

## Claims

### Claim 1

A method for predicting a hydration reaction degree of cement based on a cycle generative adversarial network (CycleGAN), comprising the following steps:
S1, acquiring a micro-structure image of a cement paste test specimen;
S2, establishing a micro-pore structure image dataset;
S3, establishing a cement micro-hydration prediction model based on a CycleGAN; and
S4, completing prediction based on a final cement micro-hydration prediction model.

### Claim 2 (depends on 1)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 1, wherein step S1 specifically comprises:
S11, prefabricating a plurality of groups of normal portland cement paste test specimens of different water cement ratios; and
S12, separately sampling the cement paste test specimens at curing ages of 1, 3, 7, 14, 28, and 168 days, and conducting visual micro-pore structure testing using a testing technique of low-melting-point metal pressing-in combined with a back scattering mode of a scanning electron microscope to obtain micro-pore structure images of the test specimens at different curing ages.

### Claim 3 (depends on 1)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 1, wherein step S2 comprises: performing image enhancement on the micro-structure image obtained in step S1, and establishing the micro-pore structure image dataset of cement at different curing ages, wherein the data enhancement comprises random cropping, random rotation, random horizontal flip, and random vertical flip.

### Claim 4 (depends on 1)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 1, wherein step S3 specifically comprises:
S31, establishing 5 CycleGANs, and with the micro-structure image at day 1 as an input, generating micro-structure images at day 3, day 7, day 14, day 28, and day 168, thereby realizing in-situ prediction of micro-structure hydration of cement;
S32, based on image analysis, evaluating the quality of the generated images by comparing micro-structures of the generated images and an actual image obtained from the test specimen, and optimizing the corresponding CycleGANs according to analysis results; and
S33, repeating steps S31 and step S32 until parameter evaluation indicators of the generated images and the image of the test specimen in comparison meet an accuracy requirement, and using the current CycleGAN as the final cement micro-hydration prediction model.

### Claim 5 (depends on 4)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 4, wherein in step S32, the evaluating the quality of the generated images specifically comprises determining, by comparison, errors between the micro-structure images generated by the CycleGANs and the corresponding actual micro-structure image in pore structure parameters of a porosity, a pore size distribution, and a morphological and spatial feature, wherein evaluation indicators are RMSE and R2, which are defined as follows:
RMSE
=
1
n
⁢
∑
i
=
1
n
(
x
i
-
x
i
^
)
2
⁢
R
2
=
1
-
∑
i
=
1
n
⁢
(
x
i
-
x
i
^
)
2
∑
i
=
1
n
⁢
(
x
i
-
x
i
_
)
2
wherein xi represents a porosity, a pore size distribution, or a morphological and spatial feature obtained from the actual image; xl represents an average value of a corresponding parameter in the actual image; represents a porosity, a pore size distribution, or a morphological and spatial feature obtained from the generated image; and n represents a number of test data samples.

### Claim 6 (depends on 4)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 4, wherein in step S32, the CycleGAN comprises two groups of generators (GA, GB) and discriminators (DA, DB); the CycleGAN is trained by optimizing a loss function composed of 1 cycle consistency loss , 1 ontology mapping loss , and 2 adversarial losses , , and by means of random inactivation and cross validation mechanisms; and
calculation formulas of , and are as follows:
ℒ
cyc
(
G
A
,
G
B
)
=
E
x
1
⁢
D
~
p
data
(
x
1
⁢
D
)
[

G
A
(
G
B
(
x
1
⁢
D
)
)
-
x
1
⁢
D

1
]
+
E
x
HD
~
p
data
(
x
HD
)
[

G
B
(
G
A
(
x
HD
)
)
-
x
HD

1
]
⁢
ℒ
identity
(
G
A
,
G
B
)
=
E
x
1
⁢
D
~
p
data
(
x
1
⁢
D
)
[

G
A
(
x
1
⁢
D
)
-
x
1
⁢
D

1
]
+
E
x
HD
~
p
data
(
x
HD
)
[

G
B
(
x
HD
)
-
x
HD

1
]
ℒ
GAN
⁢
1
(
G
A
,
D
A
)
=
E
x
HD
~
p
data
(
x
HD
)
[
log
⁡
(
D
A
(
x
HD
)
)
+
E
x
1
⁢
D
~
p
data
(
x
1
⁢
D
)
[
log
(
1
-
D
A
(
G
A
(
x
1
⁢
D
)
)
]
ℒ
GAN
⁢
2
(
G
B
,
D
B
)
=
E
x
1
⁢
D
~
p
data
(
x
1
⁢
D
)
[
log
⁡
(
D
B
(
x
1
⁢
D
)
)
]
+
E
x
HD
~
p
data
(
x
HD
)
[
log
(
1
-
D
B
(
G
B
(
x
HD
)
)
]
wherein x1D represents a micro-structure image of cement at the curing age of 1 day; xHD represents a micro-structure image of cement at the curing age of 3 days, 7 days, 14 days, 28 days, or 168 days; operator E represents expected calculation; and ∥∥1 represents L1 regularization.

### Claim 7 (depends on 1)

The method for predicting a hydration reaction degree of cement based on a CycleGAN according to claim 1, wherein in step S4, the micro-structure image of cement at day 1 to be measured is input to the final cement micro-hydration prediction model to obtain in-situ micro-structure predicted images at days 3, 7, 14, 28, and 168.

### Claim 8

A system for predicting a hydration reaction degree of cement based on a CycleGAN, comprising:
an image acquisition module (110) configured to acquire a micro-structure image of a cement paste test specimen;
a dataset establishment module (120) configured to establish a micro-pore structure image dataset;
a prediction model establishment module (130) configured to establish a cement micro-hydration prediction model based on a CycleGAN; and
a prediction module (140) configured to complete prediction based on a final cement micro-hydration prediction model.
