Method for intelligently controlling ironing machine based on spectrum sensor
Through the spectral sensor and vector machine (SVM) model, the ironing temperature is automatically identified and adjusted, which solves the shortcomings of manual temperature adjustment of traditional ironing machines and achieves efficient ironing of fabrics of different materials.
Patent Information
- Application Number
- CN202510047325.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-09
- Publication Date
- 2025-06-10
AI Technical Summary
Traditional ironing machine users need to manually adjust the temperature, which is difficult to adapt to the temperature requirements of fabrics of different materials, resulting in too high temperature damage to the delicate fabric or too low to achieve good ironing effect.
Spectral sensors are used to collect raw spectral characteristic data of the fabric, and the classification model is trained through a vector machine (SVM), the fabric type is identified and the ironing temperature and water volume are automatically adjusted.
It realizes automatic identification of fabric type and adjusts ironing temperature, simplifies the operation process, improves ironing efficiency and quality, and adapts to the needs of different materials.
Smart Images
Figure CN120122492A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent household appliances, and in particular to a method for controlling an ironing machine based on a spectrum sensor. Background Art
[0002] In the process of using a traditional ironing machine, the user can usually only manually adjust the ironing temperature based on experience or can only adjust the gear in a fixed position. For fabrics of different materials, the appropriate ironing temperature varies greatly. If the temperature is too high, it is easy to damage delicate fabrics such as silk; if the temperature is too low, a good ironing effect cannot be achieved. With the rapid development of intelligent technology, it is possible to automatically identify the type of fabric and adjust the ironing temperature using spectral sensor technology, thereby improving the efficiency and quality of ironing. The present invention proposes a method for controlling an ironing machine based on a spectral sensor. Summary of the invention
[0003] The purpose of the present invention is to provide a method for controlling an ironing machine based on a spectral sensor. The present invention solves the problem that users manually adjust the ironing temperature based on experience or can only adjust the gear in a fixed position. For fabrics of different materials, the appropriate ironing temperature varies greatly. If the temperature is too high, it is easy to damage delicate fabrics such as silk; if the temperature is too low, a good ironing effect cannot be achieved.
[0004] The present invention discloses a method for controlling an ironing machine based on a spectral sensor, comprising the following steps:
[0005] Step 1: In order to use the spectral sensor to control the ironing machine, it is necessary to first collect the original spectral characteristic data of the fabric. The specific collection method is as follows:
[0006] Standard fabric samples are classified into cotton fabric, linen fabric, wool fabric, silk fabric, synthetic fiber (including polyester, acrylic, polypropylene and other artificial fibers), and blended fabrics. The mixed fabrics are based on the fabric with the larger proportion.
[0007] Lay the fabric flat and use the spectral sensor to capture a flat area without stains or other decorations.
[0008] The spectral method controls the ironing machine by identifying fabrics. The wavelength range of about 780-2500nm is a commonly used band for identifying fabrics. In this region, hydrogen-containing groups (such as -OH, -NH, -CH) in organic molecules (such as cellulose, protein, polyester, etc.) in fabrics will vibrate and absorb. The classification model is trained using labeled fabric spectral data, and the model is used to predict the type of fabric and then control the temperature and water volume of the ironing machine.
[0009] The original spectral characteristic data of the cloth includes 780-1700nm, each piece of original spectral characteristic data of the cloth is (a1, a2, ..., a22), and each piece of original spectral characteristic data of the cloth has 22 dimensions.
[0010] Different fabric components will have different specific spectral characteristics in the near-infrared band.
[0011] Step 2: Train the original spectral feature data of the fabric collected in step 1 to generate a classification model, and use the classification model to predict the type of fabric to control the temperature and water output of the ironing machine. The specific description is as follows:
[0012] The present invention uses a support vector machine (SVM) to train the model using the spectral characteristics of the fabric as input and the fabric category as output. The model parameters are continuously adjusted during the training process, and cross-validation is used to ensure that the model has a high accuracy classification capability for unknown fabric samples, thereby obtaining an accurate fabric classification model.
[0013] Step 3: Perform time difference calibration on the model trained in step 2 so that the type of fabric can be accurately predicted in real time to control the temperature and water output of the ironing machine. The specific processing process is as follows:
[0014] Since equipment aging can cause model drift and the drift is irregular, time difference calibration is required. Through calibration, the model can produce the same result when testing the same sample at different time periods.
[0015] The present invention uses differential processing to calibrate. When collecting the original spectral characteristic data of the fabric, a calibration object (polystyrene) is collected synchronously. When predicting, the calibration object is collected first, and a difference is calculated by comparing it with the calibration object data during modeling. Finally, the data in the model is also updated after subtracting the difference to predict the final sample result. The calculation method is as follows:
[0016] Assume that the original spectral characteristic data of the model calibration object (polystyrene) is a, the original spectral characteristic data of the real-time calibration object (polystyrene) is b, the model calibration data is X, and the original spectral characteristic data of the model fabric is x;
[0017] Δ(PS)diff(Δ1, Δ2, ..., Δ22) = (b1, b2, ..., b22) - (a1, a2, ..., a22);
[0018] X(X1, X2, ..., X22) = x(x1, x2, ..., x22) - Δ(PS)diff(Δ1, Δ2, ..., Δ22)
[0019] Step 4: Adjust the temperature and water volume of the ironing machine based on the predicted output of the retrained model after calibration in step 3. The specific operations are as follows:
[0020] The water spray volume of the ironing machine can be adjusted into 3 levels: low, medium and high.
[0021] When the predicted result is cotton fabric, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0022] When the predicted result is linen fabric, the ironing temperature is set at 180-200℃ and the water spray level is low.
[0023] When the predicted result is wool fabric, the ironing temperature is set at 100-140℃ and the water spray level is high.
[0024] When the predicted result is silk fabric, the ironing temperature is set at 160-180℃ and the water spray level is low.
[0025] When the predicted result is synthetic fiber, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0026] When the predicted result is blended, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0027] The beneficial effects of the present invention are:
[0028] 1. Users do not need to manually adjust the ironing temperature. The system automatically identifies the type of fabric and adjusts it to the appropriate temperature, simplifying the operation process.
[0029] 2. The fabric classification model can be continuously updated and expanded. For new special fabrics that appear in the future, only a small number of samples need to be added and re-trained to achieve intelligent ironing to meet the ever-changing market needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.
[0031] Figure 1 Flowchart of a method for controlling an ironing machine based on a spectral sensor DETAILED DESCRIPTION
[0032] The following will clearly and completely describe and discuss the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings of the present invention. Obviously, what is described here is only a part of the examples of the present invention, not all the examples. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0033] Implementation example:
[0034] The present invention discloses a method for controlling an ironing machine based on a spectral sensor, comprising the following steps:
[0035] Step 1: In order to use the spectral sensor to control the ironing machine, it is necessary to first collect the original spectral characteristic data of the fabric. The specific collection method is as follows:
[0036] Standard fabric samples are classified into cotton fabric, linen fabric, wool fabric, silk fabric, synthetic fiber (including polyester, acrylic, polypropylene and other artificial fibers), and blended fabrics. Mixed fabrics are based on the fabric with the largest proportion. Ten or more representative samples are required for each type.
[0037] Spread the cloth flat, and use the spectral sensor to collect the flat position without stains and other decorations. Table 1 lists the original feature data of parts 1-6 of the 22 dimensional features.
[0038] Table 1 Original characteristic spectral data of cotton fabric, linen fabric, silk fabric and synthetic fiber
[0039]
[0040] The spectral method controls the ironing machine by identifying fabrics. The wavelength range of about 780-2500nm is a commonly used band for identifying fabrics. In this region, hydrogen-containing groups (such as -OH, -NH, -CH) in organic molecules (such as cellulose, protein, polyester, etc.) in fabrics will vibrate and absorb. The classification model is trained using labeled fabric spectral data, and the model is used to predict the type of fabric and then control the temperature and water volume of the ironing machine.
[0041] The original spectral characteristic data of the cloth includes 780-1700nm, each piece of original spectral characteristic data of the cloth is (a1, a2, ..., a22), and each piece of original spectral characteristic data of the cloth has 22 dimensions.
[0042] Different fabric components will have different specific spectral characteristics in the near-infrared band.
[0043] Step 2: Train the original spectral feature data of the fabric collected in step 1 to generate a classification model, and use the classification model to predict the type of fabric to control the temperature and water output of the ironing machine. The specific description is as follows:
[0044] The present invention uses a support vector machine (SVM) to train the model using the spectral characteristics of the fabric as input and the fabric category as output. The model parameters are continuously adjusted during the training process, and cross-validation is used to ensure that the model has a high accuracy classification capability for unknown fabric samples, thereby obtaining an accurate fabric classification model.
[0045] Step 3: Perform time difference calibration on the model trained in step 2 so that the type of fabric can be accurately predicted in real time to control the temperature and water output of the ironing machine. The specific processing process is as follows:
[0046] Since equipment aging can cause model drift and the drift is irregular, time difference calibration is required. Through calibration, the model can produce the same result when testing the same sample at different time periods.
[0047] The present invention uses differential processing to calibrate. When collecting the original spectral characteristic data of the fabric, a calibration object (polystyrene) is collected synchronously. When predicting, the calibration object is collected first, and a difference is calculated by comparing it with the calibration object data during modeling. Finally, the data in the model is also updated after subtracting the difference to predict the final sample result. The calculation method is as follows:
[0048] The original spectral characteristic data of the model calibrant (polystyrene) 1-6 are 2363689, 2884365, 2048834, 2508270, 2204801, 2683830, and the original spectral characteristic data of the real-time calibrant (polystyrene) are 2363300, 2884280, 2041800, 2506312, 2203211, 2688365,
[0049] Δ(PS)diff(Δ1, Δ2, ..., Δ6) =
[0050] (2363300, 2884280, 2041800, 2506312, 2203211, 2688365) - (2363689, 2884365, 2048834, 2508270, 2204801, 2683830) = -389, -85, -7034, -1958, -1590, 4535;
[0051] Table 1 Original characteristic spectrum data; Model calibration data X:
[0052] X(X1, X2, ..., X22) = original characteristic spectrum data in Table 1 - Δ(polystyrene) diff(-389, -85, -7034, -1958, -1590, 4535), the results are shown in Table 2
[0053] Table 2 Calibration data of cotton, linen, silk and synthetic fibers
[0054]
[0055]
[0056] Step 4: Adjust the temperature and water volume of the ironing machine based on the predicted output of the retrained model after calibration in step 3. The specific operations are as follows:
[0057] The water spray volume of the ironing machine can be adjusted into 3 levels: low, medium and high.
[0058] When the predicted result is cotton fabric, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0059] When the predicted result is linen fabric, the ironing temperature is set at 180-200℃ and the water spray level is low.
[0060] When the predicted result is wool fabric, the ironing temperature is set at 100-140℃ and the water spray level is high.
[0061] When the predicted result is silk fabric, the ironing temperature is set at 160-180℃ and the water spray level is low.
[0062] When the predicted result is synthetic fiber, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0063] When the predicted result is blended, the ironing temperature is set at 140-160℃ and the water spray level is low.
[0064] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.
[0065] It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure should be limited by the appended claims.
Claims
1. A method for controlling an ironing machine based on a spectral sensor, characterized in that: The following steps are involved: Step 1: In order for the spectral sensor to control the ironing machine, it is necessary to first collect the original spectral characteristic data of the fabric Step 2: Train the original spectral feature data of the fabric collected in step 1 to generate a classification model, and use the classification model to predict the type of fabric to control the temperature and water output of the ironing machine. The specific description is as follows: The present invention uses a support vector machine (SVM) to train the model using the spectral characteristics of the fabric as input and the fabric category as output. The model parameters are continuously adjusted during the training process, and cross-validation is used to ensure that the model has a high accuracy classification capability for unknown fabric samples, thereby obtaining an accurate fabric classification model. Step 3: Perform time difference calibration on the model trained in step 2 so that the type of fabric can be accurately predicted in real time to control the temperature and water output of the ironing machine. Step 4: Adjust the temperature and water volume of the ironing machine based on the predicted output results of the retrained model after calibration in step 3.
2. The method for controlling an ironing machine based on a spectral sensor according to claim 1, characterized in that: In step 1 above, the specific collection method is as follows: Standard fabric samples are classified into cotton fabric, linen fabric, wool fabric, silk fabric, synthetic fiber (including polyester, acrylic, polypropylene and other artificial fibers), and blended fabrics. The mixed fabrics are based on the fabric with the larger proportion. Lay the fabric flat and use the spectral sensor to capture a flat area without stains or other decorations. The spectral method controls the ironing machine by identifying fabrics. The wavelength range of about 780-2500nm is a commonly used band for identifying fabrics. In this region, hydrogen-containing groups (such as -OH, -NH, -CH) in organic molecules (such as cellulose, protein, polyester, etc.) in fabrics will vibrate and absorb. The classification model is trained using labeled fabric spectral data, and the model is used to predict the type of fabric and then control the temperature and water volume of the ironing machine. The original spectral characteristic data of the cloth includes 780-1700nm, each piece of original spectral characteristic data of the cloth is (a1, a2, ..., a22), and each piece of original spectral characteristic data of the cloth has 22 dimensions. Different fabric components will have different specific spectral characteristics in the near-infrared band.
3. A method for controlling an ironing machine based on a spectral sensor according to claim 1, characterized in that: In step 3 above, the specific processing process is as follows: Since equipment aging can cause model drift and the drift is irregular, time difference calibration is required. Through calibration, the model can produce the same result when testing the same sample at different time periods. The present invention uses differential processing to calibrate. When collecting the original spectral characteristic data of the fabric, a calibration object (polystyrene) is collected synchronously. When predicting, the calibration object is collected first, and a difference is calculated by comparing it with the calibration object data during modeling. Finally, the data in the model is also updated after subtracting the difference to predict the final sample result. The calculation method is as follows: Assume that the original spectral characteristic data of the model calibration object (polystyrene) is a, the original spectral characteristic data of the real-time calibration object (polystyrene) is b, the model calibration data is X, and the original spectral characteristic data of the model fabric is x; Δ(PS)diff(Δ1, Δ2, ..., Δ22) = (b1, b2, ..., b22) - (a1, a2, ..., a22); X(X1, X2, ..., X22) = x(x1, x2, ..., x22) - Δ(PS)diff(Δ1, Δ2, ..., Δ22).
4. A method for controlling an ironing machine based on a spectrum sensor according to claim 1, characterized in that: In step 4 above, the specific operations are as follows: The water spray volume of the ironing machine can be adjusted into 3 levels: low, medium and high. When the predicted result is cotton fabric, the ironing temperature is set at 140-160℃ and the water spray level is low. When the predicted result is linen fabric, the ironing temperature is set at 180-200℃ and the water spray level is low. When the predicted result is wool fabric, the ironing temperature is set at 100-140℃ and the water spray level is high. When the predicted result is silk fabric, the ironing temperature is set at 160-180℃ and the water spray level is low. When the predicted result is synthetic fiber, the ironing temperature is set at 140-160℃ and the water spray level is low. When the predicted result is blended, the ironing temperature is set at 140-160℃ and the water spray level is low.