Method, device, electronic device, baking oven and storage medium for determining baking stage

By automatically identifying the baking status characteristics and critical status characteristics of the baking target and adjusting the baking parameters, the problem of baking quality being affected by experience and level is solved, and an efficient and stable baking process is achieved.

CN115969073BActive Publication Date: 2024-11-05HENAN IFLYTEK ARTIFICIAL INTELLIGENCE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310079079.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-01-16
Publication Date
2024-11-05
Estimated Expiration
2043-01-16

AI Technical Summary

Technical Problem

In the prior art, the target baking quality is greatly affected by the experience and level of the baking personnel, resulting in uneven baking quality and affecting product quality.

Method used

By automatically determining the baking stage according to the baking status characteristics of each layer of baking target, including moisture content and image characteristics, and adjusting the baking parameters according to the critical baking status characteristics, ensure that the baking target is baked at the appropriate stage.

Benefits of technology

The baking stage can be automatically determined without manual participation, which improves the baking quality, avoids irreversible damage caused by excessive temperature, and ensures the consistency and quality of the product.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115969073B_ABST
    Figure CN115969073B_ABST
Patent Text Reader

Abstract

The present application proposes a baking stage determination method, device, electronic device, baking oven and storage medium. According to the baking state characteristics of each layer of baking targets, the baking stage of each layer of baking targets is determined. If it is detected that there are at least two layers of baking targets that are not in the same baking stage, it is determined whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics. The critical baking state characteristics are used to trigger the baking parameter adjustment according to the baking stage that the baking target is currently in. In this embodiment, according to the baking stage that each layer of baking targets is in, and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, the baking stage that all baking targets are currently in can be automatically determined without manual participation and is not affected by the experience and level of the baking personnel.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of automatic control technology, and in particular to a method, device, electronic device, baking oven and storage medium for determining a baking stage. Background Art

[0002] For some products, baking and dehydrating the raw materials is a necessary step in the production process of these products. For example, tobacco baking is a necessary process in cigarette processing. By baking the tobacco, the water content in the tobacco is reduced to meet the requirements of subsequent production steps such as cigarette packaging.

[0003] At present, in order to ensure the baking quality of the baking target during the baking and dehydration process, the baking personnel need to check the baking target regularly and determine the baking stage of the baking target based on experience, and then adjust the drying temperature, humidity and other parameters according to the baking stage of the baking target. However, this method of determining the baking stage makes the baking quality of the baking target greatly affected by the experience and level of the baking personnel, resulting in uneven baking quality and affecting product quality. Summary of the invention

[0004] In view of this, the present application proposes a baking stage determination method, device, electronic device, baking oven and storage medium to solve the problem that the way of determining the baking stage in the prior art will cause the baking quality of the baking target to be greatly affected by the experience and level of the baking personnel, thereby reducing the product quality.

[0005] The technical solutions proposed in this application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for determining a baking stage, comprising:

[0007] Determining the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target; the baking state characteristics include moisture content and / or image characteristics;

[0008] If it is detected that there are at least two layers of baking targets that are not in the same baking stage, determining whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic; the critical baking state characteristic is used to trigger baking parameter adjustment according to the baking stage currently in which the baking target is located;

[0009] According to the baking stage of each layer of baking targets and the relationship between the baking state feature of each layer of baking targets and its corresponding critical baking state feature, the baking stage currently located by all baking targets is determined.

[0010] In a second aspect, an embodiment of the present application provides a baking stage determination device, comprising:

[0011] A first determination module is used to determine the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target; the baking state characteristics include moisture content and / or image characteristics;

[0012] A second determination module is used to determine whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic if it is detected that there are at least two layers of baking targets that are not in the same baking stage; the critical baking state characteristic is used to trigger the baking parameter adjustment according to the baking stage currently in which the baking target is located;

[0013] The third determination module is used to determine the current baking stage of all baking targets according to the baking stage of each layer of baking targets and the relationship between the baking state feature of each layer of baking targets and its corresponding critical baking state feature.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0015] Memory and processor;

[0016] Wherein, the memory is used to store programs;

[0017] The processor is used to implement any one of the above methods by running the program in the memory.

[0018] In a fourth aspect, an embodiment of the present application provides a baking oven, including: a state acquisition device and a controller;

[0019] The state acquisition device is used to obtain the baking state of each layer of baking target;

[0020] The controller is used to determine the baking state characteristics of each layer of baking targets according to the baking state of each layer of baking targets; the baking state characteristics include moisture content and / or image characteristics; according to the baking state characteristics of each layer of baking targets, determine the baking stage of each layer of baking targets; if it is detected that there are at least two layers of baking targets that are not in the same baking stage, determine whether the baking state characteristics of each layer of baking targets reach critical baking state characteristics; the critical baking state characteristics are used to trigger baking parameter adjustment according to the baking stage currently in which the baking targets are located; according to the baking stage in which each layer of baking targets is located, and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, determine the current baking stage of all baking targets.

[0021] In a fifth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the methods described above is implemented.

[0022] In the baking stage determination method proposed in the present application, the baking stage of each layer of baking targets can be determined according to the baking state characteristics of each layer of baking targets. If it is detected that there are at least two layers of baking targets that are not in the same baking stage, it is determined whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics, and the critical baking state characteristics are used to trigger the baking parameter adjustment according to the baking stage that the baking target is currently in. In this embodiment, according to the baking stage that each layer of baking targets is in, and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, the baking stage that all baking targets are currently in can be automatically determined without manual participation and is not affected by the experience and level of the baking personnel.

[0023] Furthermore, according to the baking stage determined by the technical solution of the present application, the baking state characteristics of the baking target of each baking layer are within the critical baking state characteristics, and baking adjustment is performed according to the adjustment parameters of the baking stage. This can avoid irreversible damage to the baking target in the baking layer due to excessively high temperature, thereby effectively improving the baking quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0025] Figure 1 It is a flow chart of a method for determining a baking stage provided in an embodiment of the present application;

[0026] Figure 2 This is a schematic diagram of the internal structure of a baking room provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of the internal structure of another baking room provided in an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of the internal structure of another baking room provided in an embodiment of the present application;

[0029] Figure 5 is a schematic diagram of the internal structure of another baking room provided in an embodiment of the present application;

[0030] Figure 6 The present invention provides a schematic diagram of a process for determining a baking stage.

[0031] Figure 7 The present invention provides a schematic diagram of a process for determining a characteristic interval of a baking state;

[0032] Figure 8 This is a schematic diagram of the baking stages of tobacco leaves provided by an embodiment of the present application;

[0033] Fig. 9 It is a schematic diagram of a linear regression model provided in an embodiment of the present application;

[0034] Fig.10 is a structural schematic diagram of a baking stage determination device provided in an embodiment of the present application;

[0035] Fig.11 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0036] Fig.12 It is a structural schematic diagram of a baking oven provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] Application Overview

[0038] The technical solution of the embodiment of the present application is applicable to the application scenario of determining the baking stage of the baking target. By adopting the technical solution of the embodiment of the present application, the baking stage of the baking target can be automatically determined to ensure the quality of the baked product.

[0039] For some products, baking and dehydrating the raw materials is a necessary step in the production process of these products. For example, baking tobacco leaves is an important step in the tobacco production process. Its purpose is to bake out the aroma in the tobacco leaves, while promoting the yellowing and dryness of the tobacco leaves, reducing the water content in the tobacco, and meeting the requirements of subsequent production steps such as tobacco packaging. During the baking process, the color of the tobacco leaves changes from green to yellow, the shape changes from fluffy to shrunken, and the moisture content changes from high to low. The tobacco curing personnel will observe the color, shape, and moisture content of the tobacco leaves through the observation window to adjust the temperature, humidity, and wind speed in the tobacco curing room to control the baking rhythm.

[0040] Raw materials are generally baked in a baking room, but most baking rooms in China are dense baking rooms, which have three characteristics: forced ventilation, high density of raw materials, and automatic temperature and humidity control. Among them, automatic temperature and humidity control means that before baking, the staff selects a suitable baking curve according to the variety and picking part of the raw materials. The controller in the baking room will divide the baking process into multiple baking stages according to the selected baking curve. In each baking stage, the raw materials are baked according to the baking parameters such as temperature, humidity and wind speed specified by the baking curve.

[0041] During the baking process, the actual baking stage of the raw materials is not only related to the variety and picking part of the raw materials, but also to different soil, climate, pest conditions, and fertilization conditions. The baking curve cannot meet the needs of intelligent baking. Therefore, during the baking process, the staff needs to frequently observe the state of the raw materials, determine the actual baking stage of the raw materials, and bake the raw materials according to the baking parameters such as temperature, humidity, and wind speed corresponding to the actual baking stage of the raw materials. However, this way of determining the baking stage makes the baking quality of the baking target greatly affected by the experience and level of the baking personnel, resulting in uneven baking quality and affecting product quality.

[0042] Exemplarily, if the above raw materials are tobacco leaves and the curing room is a flue-curing room, the goal is generally to use a ten-stage curing process to cure the tobacco leaves. The ten-stage curing process refers to dividing the entire curing process into 10 stages according to the state of the tobacco leaves, each of which includes a heating process and a constant temperature process. Each stage contains 5 parameters: dry bulb temperature, wet bulb temperature, heating time, constant temperature time and wind speed. Among them, the dry bulb temperature and wet bulb temperature are the target temperatures, which are used to control the temperature and humidity in the flue-curing room; the heating time is the time required for the dry bulb temperature to rise from the previous stage to the dry bulb temperature of this stage, which is used to control the heating rate; the constant temperature time refers to the duration of the dry bulb temperature and the wet bulb temperature, which needs to be adjusted according to the state of the tobacco leaves; the wind speed is used to control the air outlet speed of the flue-curing room, which is achieved by setting "high wind speed" or "low wind speed".

[0043] Before tobacco leaf baking begins, the tobacco-curing personnel first preset 10 stages of baking parameters according to the variety and part of the tobacco leaves to obtain the baking curve. During the baking process, the baking parameters are adjusted in real time according to the experience of the baking personnel. The adjustment content mainly includes two parts: first, by observing the color of the tobacco leaves, the baking stage of the tobacco leaves is judged. If it is judged that the tobacco leaves have reached the next stage, but the constant temperature time has not ended, it is manually adjusted to enter the next stage; if it is judged that the preset constant temperature time is insufficient, the constant temperature time can be manually extended. Second, by observing the shape of the tobacco leaves, the moisture content of the tobacco leaves is judged, and the humidity in the tobacco-curing room is controlled by adjusting the wet-bulb temperature. The baking quality of tobacco leaves is greatly affected by the experience and level of the baking personnel.

[0044] Based on this, the present application proposes a baking stage determination method, device, electronic device, baking oven and storage medium. The technical solution can determine the baking stage of each layer of baking target, and determine the actual baking stage of the baking target according to the baking stage of each layer of baking target, thereby solving the problem that the method of determining the baking stage in the prior art will cause the baking quality of the baking target to be greatly affected by the experience and level of the baking personnel, thereby reducing the product quality.

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] Exemplary Methods

[0047] The present application embodiment provides a method for determining a baking stage, which can be executed by an electronic device, and the electronic device can be any device with data and instruction processing functions, such as a computer, an intelligent terminal, a server, etc. Figure 1 As shown, the method includes:

[0048] S101. Determine the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target.

[0049] The above-mentioned baking target refers to the object to be baked. The baking target can be placed in a baking room, and the baking of the baking target can be achieved by controlling the baking parameters such as temperature, humidity and wind speed in the baking room. When placing the baking target in the baking room, the current method is to place it in layers, leaving a certain gap between the layers for air circulation, so as to achieve the purpose of uniform baking temperature and humidity in the baking room.

[0050] For example, in the production process of tobacco, tobacco leaves can be used as a baking target.

[0051] The above baking state features include moisture content and / or image features. The moisture content refers to the water content in the baking target; the image features refer to image features extracted from the baking target image, including at least one of color features, texture features, and shape features.

[0052] When determining the moisture content of the baking target, the following steps may be adopted: determining the current total weight of the baking target and the dehydrated weight of the baking target; and determining the moisture content of the baking target according to the current total weight of the baking target and the dehydrated weight of the baking target. When determining the current total weight of the baking target and the dehydrated weight of the baking target, the following steps may be specifically adopted: detecting the initial total weight and initial moisture content of the baking target before baking, and determining the dehydrated weight of the baking target according to the initial total weight and the initial moisture content.

[0053] Specifically, before starting to bake, the baking target can be divided into a plurality of test groups, and the initial total weight of each test group can be detected by a weight sensor, and the initial moisture content of each test group can be detected by a dedicated moisture meter. The weight of the water contained in each test group before baking is obtained by calculating the product of the initial total weight of each test group and the initial moisture content. The weight of the water contained in each test group is removed from the initial total weight of each test group to obtain the dehydrated weight of the test group, that is, the weight of the test group in a completely dehydrated state.

[0054] Then, each time the moisture content of the baking target is determined, the weight sensor can be used to detect the actual weight of each current test group, that is, the current total weight of each test group. The dehydrated weight of each test group is subtracted from the current total weight of each test group to obtain the moisture content of the test group. Then, the ratio of the moisture content in each test group to the current total weight of the test group is calculated, and the ratio is the current moisture content of the test group. The average moisture content of each test group is calculated to obtain the moisture content of the baking target.

[0055] Specifically, all baking targets can be divided into multiple detection groups according to the above method, and the moisture content of the baking targets can be determined by calculating the average moisture content of all detection groups. However, considering the large space in the baking room and the large number of baking targets, if the average moisture content of all detection groups is calculated, it will lead to a large workload, and the equipment installation and data processing are relatively complicated. Therefore, a representative position can be selected, and the baking targets in the representative position can be divided into multiple detection groups. According to the above method, the average moisture content of the detection group is calculated as the moisture content of all baking targets. The above representative position can be selected according to actual conditions, and this embodiment does not limit it.

[0056] like Figure 2 As shown, a first baking rack 20, a second baking rack 21 and a weight sensor 22 may be provided in the baking room. There are multiple first baking racks 20 and multiple second baking racks 21.

[0057] Among them, the first baking rack 20 is used to place the baking target. The first baking rack 20 is a baking rod that can hang the baking target or a baking tray that can hold the baking target. Those skilled in the art can choose according to the actual form of the baking target, and this embodiment does not limit it. For example, when baking tobacco leaves, vegetable leaves, etc., a baking rod is generally selected to fix the tobacco leaves, vegetable leaves, etc. on the baking rod. When baking apricots, peaches, etc., a baking tray is generally selected to place apricots, peaches, etc. on the baking tray. The first baking rack 20 is installed on the second baking rack 21, and the second baking rack 21 plays the role of supporting one or more first baking racks 20. Generally, there are multiple first baking racks 20, which are installed on the second baking rack 21 layer by layer.

[0058] The weight sensor 22 is arranged on the second baking rack 21 of the set area, and is located at the position where the first baking rack 20 contacts the second baking rack 21 of the set area. Wherein, both ends of the first baking rack 20 contact the second baking rack 21 of the set area, so two weight sensors 22 can be correspondingly arranged on the second baking rack 21 of the set area, and the sum of the readings of the two weight sensors 22 is used as the weight of the first baking rack 20 and the baking target placed on the first baking rack 20. The weight of the first baking rack 20 can be detected in advance, so the weight of the first baking rack 20 is subtracted from the sum of the readings of the two weight sensors 22 to obtain the total weight of the baking target on the rack.

[0059] The above-mentioned setting position is related to the selected representative position. If the user does not select a representative position and needs to detect the weight of all baking targets, a weight sensor 22 needs to be set on each second baking rack 21; if the user selects a representative position, the setting area is the area where the representative position is located, and a weight sensor 22 needs to be set on all second baking racks 21 in the area where the representative position is located.

[0060] In addition, if Figure 3 and Figure 4 As shown, in order to prevent the first baking rack 20 from sliding on the second baking rack 21, a fixed baffle 23 can be installed on the second baking rack 21, wherein the baffle 23 is generally a U-shaped baffle with high sides and low middle. The two ends of the first baking rack 20 are placed in the baffle 23, and the first baking rack 20 cannot slide. The weight sensor 22 can be set on the side of the baffle 23 close to the second baking rack 21, such as Figure 4As shown, the sum of the readings of the two weight sensors 22 on the same second baking rack 21 is the weight of the first baking rack 20, the baffle 23, and the baking target placed on the first baking rack 20. The weight of the first baking rack 20 and the weight of the baffle 23 need to be detected in advance. The weight of the first baking rack 20 and the weight of the baffle 23 are subtracted from the sum of the readings of the two weight sensors 22 to obtain the total weight of the baking target on the rack.

[0061] For example, the baking target is tobacco leaves, the baking room is a tobacco curing room, the first baking support is a tobacco clip, and the baffle is a tobacco clip baffle. In general, the tobacco curing room hangs three or four layers of tobacco leaves on the top and bottom, and two rods on the left and right. Taking three layers as an example, 5 collection points can be evenly selected on both sides of each baking layer, and one collection point corresponds to one detection group. Then it can be determined that there are 10 collection points per layer, 30 collection points and 60 weight sensors for three layers.

[0062] The collection point can be represented by L, and the value of L is 1, 2, 3...30.

[0063] The weight sensors on the left and right sides of each collection point are represented by 1 and 2 respectively, so (L, 1) and (L, 2) can be used to represent 60 sensors, and G is used to represent the sensor reading value. The value of the 60 weight sensors can be recorded as G (1,1) , G (1,2) , G (2,1) , G (2,2) ……G (30,1) , G (30,2) .

[0064] The sum of the readings of a pair of gravity sensors at a certain collection point is the sum of the weight of the first baking rack, baffle, and tobacco leaves. The weight is represented by M, and the weight of the tobacco leaves hung on the first baking rack at the collection point L is M. L for:

[0065] M L =G (L,1) +G (L,2) -M J -M D

[0066] Where: M L is the weight of the tobacco leaves hung at the Lth collection point; G(L, 1) is the value of the first weight sensor at the Lth collection point; G(L, 2) is the value of the second weight sensor at the Lth collection point; M J represents the weight of the first baking rack, which is a known value; M D Represents the weight of the baffle, which is a known value.

[0067] The moisture content of tobacco leaves varies slightly depending on the variety, location, soil conditions, irrigation, and fertilization. The moisture content of fresh tobacco leaves is generally 80%-90%, and the moisture content of dried tobacco leaves after baking is usually around 16%. The tobacco leaves of the same batch have the same planting environment and basically the same moisture content. Therefore, before baking each batch of tobacco leaves, a special moisture meter is needed to measure their moisture content to ensure the accuracy of subsequent moisture content calculations.

[0068] The weight of water in the fresh tobacco leaves at the Lth sampling point M 水0L for:

[0069] M 水0L =M 0L ×P 0L

[0070] Where: P 0L represents the moisture content of fresh tobacco leaves at the Lth collection point; M 0L It represents the weight of fresh tobacco leaves at the Lth collection point, that is, the initial total weight of tobacco leaves before baking.

[0071] The weight of the dry tobacco leaves at the Lth collection point, that is, the dehydrated weight of the tobacco leaves M 干L for:

[0072] M 干L =M L -M 水0L

[0073] Where: M L is the weight of the tobacco leaves hung at the Lth collection point, that is, the current total weight of the tobacco leaves; M 水0L is the weight of moisture in the fresh tobacco leaves at the Lth collection point.

[0074] During the baking process, the real-time moisture content of tobacco leaves at the Lth collection point P L for:

[0075] P L =(M L -M 干L ) / M L

[0076] Among them: M L is the weight of tobacco leaves hung at the Lth collection point; M 干L The weight of dry tobacco leaves at the Lth collection point.

[0077] At each collection moment, the average moisture content of tobacco leaves is:

[0078]

[0079] Among them, L represents 30 collection points; P L Indicates the moisture content of tobacco leaves during the baking process at the Lth collection point.

[0080] When determining the image features of the baking target, the following steps may be adopted: acquiring an image of each layer of the baking target; and extracting features of different parts of each layer of the baking target from the image of each layer of the baking target as image features corresponding to each layer of the baking target.

[0081] Specifically, when the baking target is being baked, different parts of the baking target change differently at different baking stages. Therefore, different parts of the baking target can be segmented and image features of different parts can be extracted to further improve the accuracy of baking stage judgment. When determining the image features of the baking target, the following steps can be adopted: obtaining an image of each layer of the baking target; extracting features of different parts of each layer of the baking target from the image of each layer of the baking target as image features corresponding to each layer of the baking target.

[0082] Specifically, the image of each layer of baking target can be obtained. A camera outside the baking room can be used to capture the image of each layer of baking target through the observation window of the baking room. A camera can also be set inside the baking room to capture the image of each layer of baking target inside the baking room based on the camera. Such a setting can only capture the image of the outermost layer of each layer of baking target close to the camera. In this embodiment, the image of the outermost layer of each layer of baking target close to the camera is determined as the image of the baking target of this layer.

[0083] When setting up the camera in the baking room, Figure 5 As shown, a windshield 50 is generally arranged in the baking room, and the windshield 50 includes a transparent partition 501 and a bracket 502. The partition 501 is arranged on the bracket 502. The windshield 50 composed of the partition 501 and the bracket 502 is buckled on the inner wall of the baking room to form a photo space. The camera 51 and the fill light box 52 are both installed in the photo space. The camera 51 is used to collect the baking image of each layer of the baking target, and the fill light box 52 is used to fill light when the camera 51 shoots. The number of cameras 51 is equal to the number of baking layers, that is, one camera 51 corresponds to one baking layer, and correspondingly shoots the image of the baking target in the baking layer.

[0084] In addition, the present application spray-paints the bracket 502 in white.

[0085] This setting can produce the following effects:

[0086] First, the shooting field of view is wide. A single camera can capture a layer of baking targets, which improves the accuracy of image analysis. Second, the shooting effect is clear. Compared with the method of using a camera outside the baking room to capture the image of each layer of baking targets through the observation window of the baking room, this method sets the camera inside the baking room, which can capture clearer images. Third, the impact on the baking targets is small. The shooting space is a closed space, which can prevent hot air from entering and causing hot air short circuit, and has little impact on the baking targets around the shooting space, and also improves the reliability of image analysis. Fourth, the shooting color is more accurate. When the camera shoots a single-color object, the image will often be color cast due to the lack of white. In this solution, the bracket is sprayed with white paint to perform white balance correction.

[0087] In the present application, after obtaining the image of each layer of baking target, the image of each layer of baking target can be preprocessed first. Image preprocessing is mainly used to eliminate useless information in the image, simplify image data, enhance the measurability of relevant information, and improve the accuracy of feature values. Image preprocessing includes baking target edge extraction and non-baking target partial elimination. Traditional algorithms can be used for preprocessing, such as HSV threshold segmentation, feature value clustering analysis, etc., which are not limited in this embodiment.

[0088] Then, the image of each layer of the baking target that has been preprocessed is segmented to obtain images of different parts of each layer of the baking target. For example, if the baking target is tobacco leaves, each layer of tobacco leaf image can be segmented to segment the main vein image, the branch vein image, and the leaf flesh image from each layer of tobacco leaf image. Traditional algorithms can be used for segmentation processing, such as using a deep learning semantic segmentation method to segment each layer of the baking target image, which is not limited in this embodiment.

[0089] Then, image feature extraction is performed for the images of different parts of each layer of baking target, respectively, to obtain image features of different parts of each layer of baking target. When performing image feature extraction, at least one of color features, texture features, and shape features can be extracted as image features, which is not limited in this embodiment. Exemplarily, color feature values ​​of different parts can be extracted from images of different parts of each layer of baking target based on RGB color space, and then the color mean of each part of each layer of baking target is calculated as the image feature of the part of the layer of baking target.

[0090] For example, if the baking target is tobacco leaves, each layer of tobacco leaves includes a main vein image, a branch vein image, and a leaf flesh image. Feature value extraction is performed based on the RGB color space, and the color feature average is calculated for the main vein image, branch vein image, and leaf flesh image of each layer to obtain the image features of the main vein part, the image features of the branch vein part, and the image features of the leaf flesh part of the tobacco leaf layer. 肉X 、F 支X 、F 主XTo represent the image features of the X-th layer of mesophyll, branch veins, and main veins, the image feature set of the X-th layer of tobacco leaves is [F 肉X , F 支X , F 主X ].

[0091] In the embodiment of the present application, the baking state characteristics of the baking target can be obtained, and the baking stage of each layer of baking target can be determined according to the baking state characteristics of the baking target currently obtained. The baking state characteristics of the baking target include moisture content and / or image characteristics, that is, the baking stage of each layer of baking target can be determined according to the moisture content of the baking target; the baking stage of each layer of baking target can be determined according to the image characteristics of the baking target; and the baking stage of each layer of baking target can be determined more accurately according to the moisture content and image characteristics of each layer of baking target.

[0092] In the embodiment of the present application, when determining the baking stage of each baking target layer according to the baking state characteristics of each baking target layer, a baking state database can be pre-set to store the baking state characteristic intervals corresponding to the baking targets in different baking layers when they are in different baking stages. In order to determine the target baking state characteristic interval from the baking state characteristic interval corresponding to each baking layer in the baking state database, the target baking state characteristic interval is an interval containing the baking state characteristics of the baking targets of the same baking layer, and the baking stage of the target baking state characteristic interval is determined as the baking stage of the baking target layer.

[0093] For example, the baking target includes a first layer X1, a second layer X2, and a third layer X3, and the corresponding baking state data includes baking state feature intervals corresponding to the baking targets in the first layer X1′, the second layer X2′, and the third layer X3′ when they are in different baking stages. When determining the baking stage of the baking target in the first layer X1, a target baking state feature interval is determined from the baking state feature interval corresponding to the first layer X1′ in the baking state database, and the target baking state feature interval is an interval containing the baking state feature of the baking target in the first layer X1.

[0094] The baking state characteristic interval includes an image characteristic interval and / or a moisture content interval. Generally, if only image feature intervals are stored in the baking status database, the baking stage of the baking target layer can be determined by comparing the image features of each layer of baking targets and the image feature intervals of different baking stages of the same baking layer in the baking status database; similarly, if only moisture content intervals are stored in the baking status database, the baking stage of the baking target layer can be determined by comparing the moisture content of each layer of baking targets and the moisture content intervals of different baking stages of the same baking layer in the baking status database; if moisture content intervals and image feature intervals are stored in the baking status database, the baking stage of the baking target layer can be determined by comparing the moisture content of each layer of baking targets and the moisture content intervals of different baking stages of the same baking layer in the baking status database. The baking stage of the baking target layer can also be determined by comparing the image features of each layer of baking targets and the image feature intervals of different baking stages of the same baking layer in the baking status database. The image features and moisture content of each layer of baking targets and the image feature intervals and moisture content intervals of different baking stages of the same baking layer in the baking status database can also be compared simultaneously to determine the baking stage of the baking target layer, which is not limited in this embodiment.

[0095] In addition. A stage detection model can also be pre-set, and the baking state characteristics of each layer of baking targets are input into the stage detection model to obtain the baking stage of the baking target of this layer output by the stage detection model. When the stage detection model is trained, the training samples are the baking state characteristics of the baking targets of each layer and each stage, and the labels are the actual baking stages of the baking targets of each layer and each stage. During the training process, the training samples are input into the stage detection model to obtain the results output by the stage detection model, and the loss value of the stage detection model is determined by comparing the results and labels output by the stage detection model, and the parameters of the stage detection model are adjusted in the direction of reducing the loss value. After adjustment, the above training process is repeated until the loss value of the stage detection model is less than the set value. The set value can be set according to the actual situation, and this embodiment does not limit it.

[0096] S102: If it is detected that there are at least two layers of baking targets that are not in the same baking stage, determine whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic.

[0097] When it is detected that the baking targets of all baking layers are in the same baking stage, the adjustment can be performed normally according to the baking stage. For example, if the baking target needs to go through three baking stages to complete the baking, when it is detected that the baking targets of all baking layers are in the third baking stage, the baking is performed according to the baking parameters corresponding to the third baking stage.

[0098] However, in the actual baking process, although gaps are set in different baking layers for air circulation, the hot air rises, resulting in high baking temperatures at higher positions in the baking room and low baking temperatures at lower positions in the baking room, and baking targets at different baking layers may not always be in the same baking stage. If the baking targets of not all baking layers are in the same stage, that is, it is detected that at least two layers of baking targets are not in the same baking stage, since the baking room uniformly adjusts the baking parameters, it is necessary to determine the target baking stage according to the baking stage of each layer of baking targets, to ensure that when baking according to the target baking stage, the damage to the baking targets at each layer is minimized, thereby improving the overall baking quality of the baking targets and reducing the defective rate.

[0099] Specifically, it can be determined whether the baking state characteristics of each layer of the baking target have reached a critical baking state characteristic. The critical baking state characteristic triggers the baking parameter adjustment according to the baking stage the baking target is currently in. If the baking state characteristics of the baking target have reached the critical baking state characteristics and the baking parameters are not adjusted, the baking target may be damaged, affecting the quality of the baking target.

[0100] For example, if a baking target needs to go through three baking stages to complete baking, and is currently being baked according to the baking parameters corresponding to the second baking stage, and it is found through detection that the baking target has entered the third baking stage, then it is not necessary to immediately bake according to the baking parameters corresponding to the third baking stage, that is, there is no trigger to adjust the baking parameters according to the baking stage currently in which the baking target is located, but continue to bake with the baking parameters corresponding to the second baking stage. When it is detected that the baking state characteristics of the baking target reach the critical baking state characteristics, the baking parameters must be adjusted to the baking parameters corresponding to the third baking stage, that is, it is triggered to adjust the baking parameters according to the baking stage currently in which the baking target is located, so as to prevent damage to the baking target and affect the quality of the baking target.

[0101] In the embodiment of the present application, a critical baking state feature database may be pre-set, and the critical baking state feature database stores critical baking state features corresponding to baking targets in different baking layers at different baking stages. According to the baking stage of each layer of baking targets, the critical baking state feature of each layer of baking targets may be retrieved from the critical baking state feature database to determine whether the baking state feature of each layer of baking targets reaches the critical baking state feature.

[0102] In addition, a critical baking state feature detection model can be pre-set, and the baking state features and baking stages of each layer of baking targets can be output to the critical baking state feature detection model to obtain the results output by the critical baking state feature detection model, which include whether the baking state features of the baking target layer reach the critical baking state features, or whether the baking state features of the baking target layer do not reach the critical baking state features.

[0103] When the critical baking state feature detection model is trained, the training samples are the baking state features of the baking targets at each layer and each stage, the actual baking stages of the baking targets at each layer and each stage, and the labels are whether the baking state features of the baking targets at each layer and each stage reach the critical baking state features. The specific training process is the same as the training process of the stage detection model in the above embodiment, and those skilled in the art can refer to the records in the above embodiment, which will not be described here.

[0104] S103, determining the current baking stage of all baking targets according to the baking stage of each layer of baking targets and the relationship between the baking state feature of each layer of baking targets and its corresponding critical baking state feature.

[0105] According to the baking stage of each layer of baking target and the relationship between the baking state characteristics of each layer of baking target and its corresponding critical baking state characteristics, the baking stage of all baking targets is further determined. In order to bake according to the baking parameters corresponding to the baking stage of all baking targets, the damage to each layer of baking targets is minimized, the overall baking quality of the baking targets is improved, and the defective rate is reduced.

[0106] The relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics includes whether the baking state characteristics of the baking targets of this layer reach their corresponding critical baking state characteristics, or whether the baking state characteristics of the baking targets of this layer do not reach their corresponding critical baking state characteristics.

[0107] Specifically, the baking layer with the maximum baking stage can be determined according to the baking stage of each baking target. For example, if the baking layer includes three layers, the upper layer, the middle layer and the lower layer, and the baking target of the upper layer is in the fourth baking stage, and the baking targets of the middle layer and the lower layer are in the third baking stage, then the upper layer is the baking layer with the maximum baking stage.

[0108] In an embodiment of the present application, it is possible to determine the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, that is, to determine whether each layer of baking targets is in a stage where baking parameters need to be adjusted according to the current baking stage of the baking targets of that layer, and if no adjustment is made, the baking targets of that layer will be damaged.

[0109] What can be determined is that the baking layer with the maximum baking stage is the baking layer with the highest baking temperature, which is generally the top layer in the baking room. In other words, due to the higher temperature of the upper layer, the upper layer baking target usually reaches the target state of this stage first, but if the temperature is raised to enter the next stage at this time, it will cause the baking quality of the middle or lower layers to be poor. Therefore, you can wait for a while and wait for the middle and lower layers to reach the target state before raising the temperature to enter the next stage. However, if the waiting time is too long, the color of the upper layer tobacco leaves will be too dark, causing the upper layer tobacco leaves to be burned. To avoid this situation, when the color of the upper layer baking target is abnormal, even if the middle and lower layers have not reached the ideal state, the temperature needs to be raised to ensure that the upper layer is not burned.

[0110] Therefore, in this embodiment, if it is detected that the baking state characteristics of each layer of baking targets have not reached the critical baking state characteristics corresponding thereto, it means that even if the baking parameters are not adjusted according to the baking stage of the upper baking target, the uppermost baking target will not be damaged, and the baking stage of the lower baking target can be determined as the baking stage of all baking targets in the baking room, and baking is carried out according to the baking parameters corresponding to the baking stage of the lower baking target; if it is detected that the baking state characteristics of the uppermost baking targets have all reached the critical baking state characteristics corresponding thereto, while the baking state characteristics of the lower baking targets have not reached the critical baking state characteristics corresponding thereto, in order to avoid the uppermost baking target If the target is damaged, the baking stage of the topmost baking target can be determined as the baking stage of all baking targets in the baking room, and baking is carried out according to the baking parameters corresponding to the baking stage of the topmost baking target; if it is detected that N layers (N is an integer greater than 1) located on the upper layer have all reached the critical baking state characteristics corresponding to them, while the baking state characteristics of the lower baking targets have not reached the critical baking state characteristics corresponding to them, since the temperature of the top layer is the highest, in order to avoid damage to the topmost baking target at this time, the baking stage of the topmost baking target can be determined as the baking stage of all baking targets in the baking room, and baking is carried out according to the baking parameters corresponding to the baking stage of the topmost baking target.

[0111] In the actual baking process, since the baking temperature of the top layer is the highest, if the baking state characteristics of the baking target of the top layer do not reach the critical baking state characteristics corresponding thereto, then the baking state characteristics of the baking targets of other layers will not reach the critical baking state characteristics corresponding thereto. Therefore, it can be determined that the situation where the baking state characteristics of the baking target of the top layer do not reach the critical baking state characteristics corresponding thereto, while the baking state characteristics of the baking targets of other layers all reach the critical baking state characteristics corresponding thereto will hardly occur, and therefore it will not be discussed in this embodiment.

[0112] In the above embodiments, the baking stage of each layer of baking targets can be determined according to the baking state characteristics of each layer of baking targets. If it is detected that there are at least two layers of baking targets that are not in the same baking stage, it is determined whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics, and the critical baking state characteristics are used to trigger the baking parameter adjustment according to the baking stage that the baking target is currently in. In this embodiment, according to the baking stage that each layer of baking targets is in, and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, the baking stage that all baking targets are currently in can be automatically determined without manual participation and is not affected by the experience and level of the baking personnel.

[0113] Furthermore, according to the baking stage determined by the technical solution of the present application, the baking state characteristics of the baking target of each baking layer are within the critical baking state characteristics, and baking adjustment is performed according to the adjustment parameters of the baking stage. This can avoid irreversible damage to the baking target in the baking layer due to excessively high temperature, thereby effectively improving the baking quality.

[0114] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment determine the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target, which may specifically include the following steps:

[0115] The baking stage of each baking target layer is determined according to the baking state characteristics of each baking target layer and a preset baking state database; wherein the baking state database includes baking state characteristic intervals corresponding to baking targets in different baking layers at different baking stages.

[0116] In the embodiment of the present application, a baking state database may be pre-set, and the baking state database includes baking state characteristic intervals corresponding to baking targets in different baking layers in different baking stages.

[0117] Specifically, the baking state characteristic intervals corresponding to the baking targets in different baking layers at different baking stages can be determined by repeatedly conducting experiments in the laboratory. In the actual baking process, experts can also determine the baking stage of each baking target according to the actual baking situation, collect the baking state characteristics of the baking targets in different baking layers during the actual baking process according to the records of the above embodiments, and then determine the baking state characteristic intervals corresponding to the baking targets in different baking layers at different baking stages. In order to improve the reliability of the baking state characteristic intervals corresponding to different baking stages, the number of baking times can be increased as much as possible.

[0118] Then, by comparing the baking state characteristics of each layer of baking targets with the baking state characteristic interval of the baking targets of the layer, the baking stage of each layer of baking targets is determined.

[0119] For example, if the baking target is tobacco leaves, the tobacco leaves are divided into three layers of upper, middle and lower layers during baking, the baking state feature interval includes a moisture content interval and an image feature interval, and the baking stage is 10 stages, then the baking state database can be established in the following manner:

[0120] The tobacco leaf baking state database mainly reflects the relevant state parameters of the tobacco leaf during the normal baking process, and provides a basis for the intelligent adjustment of the tobacco flue-curing room. Therefore, tobacco experts need to select tobacco leaves with a relatively standard baking process (better growth, better baking results, and obvious characteristics at each stage) as the basic object for establishing the baking state database. In addition, when collecting data, it is necessary to record the variety, position, and growth characteristics of the tobacco leaves in this furnace. Tobacco leaves with the same variety, position, and growth characteristics are more referenceable and have better intelligent adjustment effects. Therefore, the tobacco leaves used to establish the baking state database should cover as many tobacco leaf varieties, positions, and growth characteristics as possible.

[0121] The basic data that needs to be collected to establish the baking status database include the moisture content of fresh tobacco leaves, the weight of tobacco leaves during baking, the image of tobacco leaves during baking, and baking setting parameters. Among them, the moisture content of fresh tobacco leaves is measured by professional instruments before baking begins; the weight and image of tobacco leaves during baking can be obtained regularly using the method of the above embodiment; and the baking setting parameters are read from the controller of the tobacco curing room.

[0122] The baking cycle of a furnace of tobacco leaves is about 7 days. If the collection interval is set too long, the sample size will be relatively small, which will reduce the reliability of the baking status database; if the collection interval is set too short (for example, 1 minute), the image annotation and calculation amount will be too large, resulting in slow system operation. Taking all factors into consideration, the collection interval can be set to 10 minutes, that is, a set of pictures is collected every 10 minutes (a set of pictures includes three pictures: upper, middle and lower), and about 3024 pictures can be collected for a furnace of tobacco leaves. The more images are collected and the better the quality, the higher the accuracy of the baking status database; a set of weight information is collected every 10 minutes, including 60 sensor values, and about 60480 values ​​can be collected for a furnace of tobacco leaves; the baking setting data includes 10 stages of dry bulb temperature, wet bulb temperature, wind speed, heating time, and constant temperature time. This type of data is read from the controller after the baking is completed, with a total of 50 values.

[0123] By processing the obtained basic images and data according to the method described in the above embodiment, the baking state database data can be obtained. Each complete set of data in the baking state database contains the following information:

[0124] First, basic information. Including varieties, parts (upper, middle, lower), growth characteristics (unripe, mature, overripe). Second, baking parameters, including dry bulb temperature W in stages 1-10 干(标准) , wet bulb temperature W湿(标准) , constant temperature time T 恒(标准) , Heating time T 升(标准) , wind speed F (标准) Third, tobacco leaf state parameters. This includes the color feature value set F of each layer obtained at regular intervals. 上 、F 中 、F 下 , moisture content P (标 allow ) .

[0125] In the above embodiment, the baking stage of each layer of the baking target can be accurately determined without relying on the personal experience and level of the baking personnel.

[0126] As an optional implementation, Figure 6 As shown, in another embodiment of the present application, the steps of the above embodiment are disclosed, according to the baking state characteristics of each layer of baking target and a preset baking state database, to determine the baking stage of each layer of baking target, which may specifically include the following steps:

[0127] S601 , searching a baking state database for a baking state characteristic interval corresponding to a baking target in a different baking layer being in a next baking stage adjacent to a target baking stage.

[0128] Among them, all baking targets are currently baked according to the baking parameters of the target baking stage.

[0129] Specifically, if there is a baking target of a baking layer at stage X, but the baking parameters currently used in baking are baking parameters corresponding to stage X-1, then it can be determined that the target baking stage is stage X-1, and the next baking stage adjacent to the target baking stage is stage X. From the baking state database, the baking state feature interval corresponding to stage X is detected.

[0130] S602, detect whether the baking state characteristics of each layer of baking targets are located in the baking state characteristic interval corresponding to the baking targets in the baking layer; if the baking state characteristics of the baking targets in the first target baking layer are located in the baking state characteristic interval corresponding to the baking layer, execute step S603; if the baking state characteristics of the baking targets in the second target baking layer are not located in the baking state characteristic interval corresponding to the baking layer, execute step S604.

[0131] After retrieving the corresponding baking state feature interval when the baking targets in different baking layers are in the next baking stage adjacent to the target baking stage, it can be further detected whether the baking state feature of each layer of baking targets is located within the corresponding baking state feature interval when the baking targets in the retrieved baking layer are in the next baking stage adjacent to the target baking stage.

[0132] Exemplarily, if a baking target in a baking layer is in the next baking stage adjacent to the target baking stage, the corresponding baking state characteristic interval is the moisture content interval, and the specific range is [50%-60%]. If the moisture content of the baking target of this layer is 55%, the baking state characteristics of the baking target of this layer can be determined to be within the corresponding baking state characteristic interval when the baking target in the baking layer obtained by retrieval is in the next baking stage adjacent to the target baking stage.

[0133] S603: Determine that the baking target in the first target baking layer is in a next baking stage adjacent to the target baking stage.

[0134] If the baking state characteristics of the baking target in the first target baking layer are located in the baking state characteristic interval corresponding to the baking layer, it can be determined that the baking state characteristics of the baking target in the first target baking layer are consistent with the baking state characteristics of the next baking stage adjacent to the target baking stage, and the baking target in the first target baking layer is already in the next baking stage adjacent to the target baking stage.

[0135] S604: Determine whether the baking target in the second target baking layer is in the target baking stage.

[0136] If the baking state characteristics of the baking target in the second target baking layer are not located in the baking state characteristic interval corresponding to the baking layer, it can be determined that the baking state characteristics of the baking target in the second target baking layer do not meet the baking state characteristics of the next baking stage adjacent to the target baking stage, and the baking target in the first target baking layer is still in the target baking stage.

[0137] During the baking process, as the temperature increases, the baking target will gradually transition from one baking stage to the next baking stage. For example, when it is detected that a certain layer of baking target is in the X baking stage, baking is performed according to the baking parameters of the X baking stage. As the baking progresses, the baking target of this layer may enter the X+1 baking stage. Therefore, it is necessary to extract the baking state characteristics of the baking target of this layer once by setting a time length at each interval, for example, every ten minutes, to determine whether the baking state characteristics of the baking target of this layer have met the baking state characteristics of the X+1 baking stage. If it is determined that the baking state characteristics of the baking target of this layer have met the baking state characteristics of the X+1 baking stage, it means that the baking target of this layer is actually in the X+1 baking stage. If it is determined that the baking state characteristics of the baking target of this layer do not meet the baking state characteristics of the X+1 baking stage, it means that the baking target of this layer is actually still in the X baking stage and has not yet reached the X+1 baking stage.

[0138] In addition, after determining that the baking state characteristics of the baking target layer do not meet the baking state characteristics of the X+1 baking stage, the baking state characteristics of the baking target layer can be further compared to see whether they meet the baking state characteristics of the X baking stage. If the baking state characteristics of the baking target layer do not meet the baking state characteristics of the X baking stage, it means that during the baking process, the temperature may rise rapidly in a short period of time, and the baking target layer has gone through multiple baking stages within the interval. At this time, the baking state characteristic interval of the layer in the X+2 baking stage, the baking state characteristic interval of the X+3 baking stage, etc. can be determined from the baking state database, and compared with the baking state characteristics of the baking target layer to determine the baking stage of the baking target layer.

[0139] In the above embodiments, the baking interval of each layer of baking target can be quickly determined without relying on the experience and level of the baking personnel, and the reliability is high.

[0140] As an optional implementation, Figure 7 As shown, in another embodiment of the present application, it is disclosed that, in the case where the baking state feature of each layer of baking targets includes an image feature, the baking state feature interval of the above embodiment includes an image feature interval, and the image feature includes image features of different parts of the baking target; the steps of the above embodiment to detect whether the baking state feature of each layer of baking targets is located in the baking state feature interval corresponding to the baking target in the baking layer may specifically include the following steps:

[0141] S701, retrieving weights of different parts of a baking target in a next baking stage adjacent to the target baking stage from a preset weight database.

[0142] In the embodiment of the present application, a weight database is pre-set, and the weights of different parts of the baking target in different baking stages are stored in the weight database. Specifically, when the baking target is baked, different parts of the baking target change differently. Therefore, in each baking stage, a higher weight can be set for the part with the most obvious change to improve the accuracy of the final baking stage.

[0143] For example, during the flue-curing process, as the dry-bulb temperature and wet-bulb temperature in the flue-curing room continue to rise, the color of the tobacco leaves will gradually change from green to yellow. The temperature required for yellowing in different regions is different. Referring to the description of the curing process, before 42°C (1-3 curing stages), the main leaf flesh changes from green to yellow, and the yellowing of the side veins and main veins is not obvious; during 42-54°C (4-7 curing stages), the main leaf veins change from green to yellow, the main veins do not change significantly, and the leaf flesh does not change significantly; during 54-65°C (8-10 curing stages), the main veins change from green to yellow, and the leaf flesh and side veins do not change significantly.

[0144] Therefore, the focus of observation is different in different roasting stages: in stages 1-3, the changes in leaf flesh are the main focus, and the weight of the leaf flesh is set to the highest; in stages 4-7, the changes in branch veins are the main focus, and the weight of the branch veins is set to the highest; in stages 8-10, the changes in the main veins are the main focus, and the weight of the main veins is set to the highest.

[0145] Exemplarily, the weight x corresponding to the leaf flesh at different roasting stages, the weight y corresponding to the branch veins, and the weight z corresponding to the main veins can be set as shown in Table 1.

[0146] Baking stage x-value y value z-value Phase 1 0.9 0.5 0.1 Phase 2 1 0.6 0.2 Phase 3 0.9 0.7 0.3 Stage 4 0.4 0.9 0.4 Stage 5 0.3 1 0.5 Stage 6 0.2 1 0.6 Stage 7 0.1 0.9 0.7 Stage 8 0.3 0.4 0.9 Stage 9 0.2 0.3 1 Stage 10 0.1 0.2 0.9

[0147] Table 1

[0148] If the target roasting stage is the 7th roasting stage, it can be obtained from Table 1 that at the 8th roasting stage, the weight corresponding to the leaf flesh is 0.3, the weight corresponding to the branch vein is 0.4, and the weight corresponding to the main vein is 0.9.

[0149] S702: According to the weights of different parts of each layer of baking target, a weighted sum of image features of different parts of each layer of baking target is calculated as a comprehensive image feature value of each layer of baking target.

[0150] In this embodiment, according to the weights of different parts of each baking target layer determined in the above steps, the weighted sum of image features of different parts in each baking target layer is calculated, and the weighted sum is determined as the comprehensive image feature value of each baking target layer.

[0151] For example, if the baking target is tobacco leaves, the image feature set of the Xth layer of tobacco leaves is [F 肉X , F 支X , F 主X ]. The baking parameters currently used in baking are the baking parameters corresponding to the X-1 baking stage. The weight corresponding to the leaf flesh in the X baking stage is retrieved from the pre-set weight database as x1, the weight corresponding to the branch vein is y1, and the weight corresponding to the main vein is z1. Then the comprehensive image feature value F of the Xth layer of tobacco leaves is:

[0152] F=x1F 肉X +y1F 支X +z1F 主X

[0153] S703, detecting whether the comprehensive image feature value of each baking target layer is within the image feature interval corresponding to the baking layer, and determining whether the baking state feature of each baking target layer is within the baking state feature interval corresponding to the baking layer according to the detection result.

[0154] It should be noted that when generating the baking state database, the image features of each baking stage obtained during the baking process of the sample baking target are processed in the above manner to obtain the comprehensive feature values ​​of each baking stage, and the image feature interval is generated by the comprehensive feature values. For example, if the image features of each baking stage obtained during the baking process of the sample are processed in the above manner to obtain the comprehensive feature values ​​of each baking stage between Y1 and Y2, then the image feature interval is determined to be [Y1, Y2].

[0155] Detect whether the comprehensive image feature value of each layer of baking target is within the image feature interval corresponding to the baking layer. If the baking stage of each layer of baking target is judged only according to the image feature of each layer of baking target without considering other factors, then if the comprehensive image feature value of a certain layer of baking target is within the image feature interval corresponding to the baking layer, then determine that the baking state characteristics of the baking target layer are within the baking state characteristic interval corresponding to the baking layer; if the comprehensive image feature value of a certain layer of baking target is not within the image feature interval corresponding to the baking layer, then determine that the baking state characteristics of the baking target layer are within the baking state characteristic interval corresponding to the baking layer.

[0156] Detect whether the comprehensive image feature value of each layer of baking target is within the image feature interval corresponding to the baking layer. If other features are considered in addition to image features, such as moisture content, and the baking status database includes moisture content intervals, then if the comprehensive image feature value of a layer of baking target is within the image feature interval corresponding to the baking layer, and the moisture content is within the moisture content interval corresponding to the baking layer, then determine that the baking status feature of this layer of baking target is within the baking status feature interval corresponding to the baking layer.

[0157] In the above embodiments, it is possible to automatically determine whether the baking state feature of each baking target layer is within the baking state feature interval corresponding to the baking target in the baking layer, so as to determine the baking state of the baking target layer according to the detection result.

[0158] As an optional implementation, a baking target image comparison library may be established, in which standard images of baking targets at different baking stages are stored, and the baking stages of the baking targets are marked accordingly. Since each baking stage includes a constant temperature stage and a temperature increase stage, images of the constant temperature stage and the temperature increase stage in the same baking stage may also be stored and marked.

[0159] In the above embodiment, when determining the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target and the pre-set baking state database, in addition to the above embodiment, the image of each layer of baking target can also be compared with the image in the target image comparison library to determine the baking stage that the image of each layer of baking target may be in. For example, if the image of a certain layer of baking target is very similar to the image of the Xth baking stage in the target image comparison library, it can be preliminarily determined that the layer of baking target is in the Xth baking stage.

[0160] Then the comprehensive image feature value of the baking target layer can be calculated according to the weight data corresponding to the Xth baking stage of the baking target; by comparing the comprehensive image feature value of the baking target layer and the image feature interval of the Xth baking stage corresponding to the baking target layer, it is verified whether the baking target layer is in the Xth baking stage. If it is determined that the baking target layer is not in the Xth baking stage, the comprehensive image feature value of the baking target layer is calculated according to the weight data corresponding to the X-1th or X+1th baking stage of the baking target, and then it is determined whether the baking target layer is in the X-1th or X+1th baking stage, and so on, until the baking stage of the baking target is determined.

[0161] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment determine whether the baking state characteristics of each layer of the baking target reach the critical baking state characteristics, which may specifically include the following steps:

[0162] Retrieving critical baking state features of baking targets in different baking layers from a preset critical baking state feature database; the critical baking state feature database includes critical baking state features corresponding to baking targets in different baking layers at different baking stages;

[0163] Whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics is determined according to the baking state characteristics of each layer of baking targets and the critical baking state characteristics of the baking targets in the baking layer.

[0164] The critical baking state feature may include a critical moisture content and / or a critical image feature, which is not limited in this embodiment. The critical image feature is a critical comprehensive image feature value.

[0165] Specifically, in the embodiment of the present application, a critical baking state feature database is pre-set, and the critical baking state feature database includes critical baking state features corresponding to baking targets in different baking layers at different baking stages. It should be noted that the critical baking state features corresponding to baking targets in different baking layers at different baking stages can be obtained by conducting experiments, and this embodiment does not limit this.

[0166] The critical baking state characteristics of the baking targets in different baking layers are retrieved from a preset critical baking state characteristic database, and then the baking state characteristics of each baking target layer are compared with the critical baking state characteristics of the baking targets in the baking layer, and whether the baking state characteristics of each baking target layer reaches the critical baking state characteristics is determined based on the comparison result. For example, if the baking state characteristics of a baking target layer are greater than or equal to the critical baking state characteristics corresponding to the layer, it means that the baking state characteristics of the baking target layer reach the critical baking state characteristics.

[0167] For example, if the baking target is tobacco leaves, a critical baking state feature database can be established in the following manner:

[0168] The critical baking state characteristics of tobacco leaves are the image characteristics and moisture content of a certain type of tobacco leaves at the moment when the temperature must be raised in each baking stage. The critical baking state characteristics database mainly reflects the fault tolerance range of tobacco leaves at different baking stages in an environment that is not suitable for their own state. Since the critical baking state characteristics database needs to be obtained under specific conditions, it will cause damage to the tobacco leaves and is difficult to implement in the tobacco flue-curing room. Therefore, the data in the critical baking state characteristics database needs to be obtained through a large number of tests in the flue-cured tobacco test box, and the boundary state is determined by flue-cured tobacco experts. A complete set of data in the critical baking state characteristics database includes the following information:

[0169] First, basic information, including varieties, parts (upper, middle, lower), growth characteristics (unripe, mature, overripe). Second, boundary state parameters. Mainly including image features F at the boundary state of stage 1-10 图像边 and moisture content F 水边 .

[0170] In the above embodiments, it is possible to quickly determine whether the baking state characteristics of each layer of baking targets have reached the critical baking state characteristics, so as to automatically determine the current baking stage of all baking targets according to the baking stage of each layer of baking targets and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, thereby improving the accuracy of baking stage judgment.

[0171] As an optional implementation, another embodiment of the present application discloses that the steps of the above embodiment determine the current baking stage of all baking targets according to the baking stage of each layer of baking targets and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, and specifically may include the following steps:

[0172] Determine the third target baking layer with the maximum baking stage from each layer of baking targets; detect whether the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the baking layer, and determine the current baking stage of all baking targets according to the detection results.

[0173] The baking layer with the maximum baking stage is the baking layer with the highest baking temperature, which is generally the top layer in the baking room. The temperature of this layer is the highest and the baking progress is the fastest. Generally speaking, if the baking layer with the maximum baking stage does not reach the critical baking state characteristics of this baking layer, then other baking layers will not reach the critical baking state characteristics corresponding to other baking layers.

[0174] Based on this, in the embodiment of the present application, the third target baking layer with the maximum baking stage can be first determined from the baking targets of each layer, which is generally the top layer in the baking room. Then, it is detected whether the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the baking layer, and the current baking stage of all baking targets is determined according to the detection result.

[0175] Specifically, if the baking state characteristics of the baking target in the third target baking layer reach the critical baking state characteristics of the layer, the baking stage of the baking target in the third target baking layer is determined as the baking stage of all baking targets; if the baking state characteristics of the baking target in the third target baking layer do not reach the critical baking state characteristics of the layer, the baking stage of the baking target in the baking layer with the minimum baking stage is determined as the baking stage of all baking targets.

[0176] That is to say, if the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the layer, it means that if the baking parameters are not adjusted, the baking targets in the third target baking layer may be damaged. In order to avoid damage to the baking targets in the third target baking layer, the baking stage of the baking targets in the third target baking layer is determined as the baking stage of all baking targets, and the baking is carried out according to the baking parameters corresponding to the baking stage of the baking targets in the third target baking layer. The baking stage of the baking targets in the third target baking layer is the maximum stage, and the baking parameter temperature corresponding to the baking stage of the baking targets in the third target baking layer is the highest. The baking targets in other layers are baked according to this temperature, and the baking targets in other layers can be heated up and gradually enter the subsequent baking stages, and the probability of damage is relatively low.

[0177] Since the temperature of the third target baking layer is the highest, if the baking state characteristics of the baking targets in the third target baking layer do not reach the critical baking state characteristics of the layer, it means that the baking targets of all other baking layers do not reach the critical baking state characteristics of each layer, which means that if the baking parameters are not adjusted, the baking targets in each baking layer will not be damaged. In order to improve the overall quality of the baking targets, at this time, the baking stage of the baking targets in the baking layer with the smallest baking stage is preferentially determined as the baking stage of all baking targets, and baking is performed according to the baking parameters corresponding to the smallest stage. Without affecting the baking quality of other layers, the baking layer with the smallest baking stage can enter the next stage normally.

[0178] In a specific embodiment, the baking target is tobacco leaves, which include three layers: upper, middle and lower. The baking stage of the baking target is determined only by image features, and when baking tobacco in a tobacco-curing room, the temperature of the upper layer > the temperature of the middle layer > the temperature of the lower layer. The temperature difference between two adjacent layers is about 2-4 degrees. Usually, the baking progress of the upper layer of tobacco leaves is faster than that of the middle layer, and the baking progress of the middle layer is faster than that of the lower layer.

[0179] The judgment principle is to focus on the upper layer of tobacco leaves, while taking into account the middle and lower layers of tobacco leaves. That is, if the upper layer of tobacco leaves has entered the next stage, but the middle and lower layers have not yet reached the next stage, the time of this stage can be extended, but the extension time is limited, that is, to ensure that the image feature value and moisture content of the tobacco leaves do not exceed the corresponding parameters under the boundary state.

[0180] Use F 上 、F 中 、F 下 Indicates the comprehensive image feature value of each layer of tobacco leaves in the actual baking process. X is used to represent the key node. The X value is 0, 1, 3...10. For example, in the fresh tobacco state, X=0, in the state at the end of the first baking stage, X=1, and in the state at the end of the second baking stage, X=2. Figure 8 shown.

[0181] Compared with tobacco leaves with the same basic information in the baking status database, the following situations are found:

[0182] If F 上X <F 上 <F 上X+1 ,F 中X <F 中 <F 中X+1 ,F X <F 下 <F 下X+1, This means that the three layers of tobacco leaves are currently in the X+1 baking stage, and the actual baking stage should be X+1.

[0183] F 上X It represents the comprehensive characteristic value of the upper tobacco leaves at the Xth key node in the baking state database;

[0184] F 中X It represents the comprehensive characteristic value of the middle tobacco leaf at the Xth key node in the baking state database;

[0185] F 下X It represents the comprehensive characteristic value of the lower tobacco leaves at the Xth key node in the baking status database.

[0186] If F 上X+1 <F 上 <F 边上x+1 , F 中X <F 中 <F 中X+1 ,F 下X <F 下 <F 下X+1 , it means that the upper layer has reached the X+2 stage and has not exceeded the corresponding critical comprehensive image feature value, but the middle and lower layers are still in the X+1 stage. At this time, the actual baking stage should be X+1.

[0187] F 边上x+1 Represents the critical comprehensive image feature value of the upper tobacco leaves at stage X+2 in the critical baking state feature database.

[0188] If F 上X+1 <F 上 <F 边上x+1 , F 中X+1 <F 中 <F 边中x+1 ,F 下X <F 下 <F 下X+1 , it means that the upper and middle layers have reached the X+2 stage and have not exceeded the corresponding critical comprehensive image feature value, but the lower layer is still in the X+1 stage. At this time, the actual baking stage should be X+1.

[0189] F 边中x+1 Represents the critical comprehensive image feature value of the middle layer tobacco leaves at the X+2 stage in the critical baking state feature database.

[0190] If F 边上x+1 ≤F 上 , it means that the upper layer has reached or exceeded the critical comprehensive image feature value of the X+1 stage. At this time, no matter whether the middle layer and the next layer complete the baking of this stage, they must enter the X+2 baking stage.

[0191] The above can cover most situations in the tobacco flue-curing process, but the actual tobacco flue-curing situation is affected by many factors, such as the mixing of tobacco leaves of different varieties or parts, power outage and restart, etc., which may cause abnormal situations and require human intervention.

[0192] In the above embodiment, the baking stage currently in which all baking targets are located can be determined, and baking can be performed according to the baking parameters corresponding to the baking stage currently in which all baking targets are located, so as to minimize the damage caused to the baking targets at each layer, improve the overall baking quality of the baking targets, and reduce the defective rate.

[0193] As an optional implementation, another embodiment of the present application discloses that the method in the above embodiment may specifically include the following steps:

[0194] The baking is adjusted according to the baking parameters corresponding to the baking stages of all baking targets.

[0195] Different baking targets correspond to different baking parameters in different baking stages. In this embodiment, baking parameters corresponding to the baking stages of all baking targets are determined, including dry bulb temperature, constant temperature time, heating time, wind speed, etc., and baking is performed according to the baking parameters.

[0196] In the embodiment of the present application, a sample baking target can be baked, and different baking stages can be determined by professionals, and baking parameters can be adjusted. The baking parameters corresponding to different baking stages can be determined by interacting with a controller that controls baking parameters, and the baking parameters corresponding to different baking stages can be stored in the above-mentioned baking state database. When the baking stages of all baking targets are obtained, the baking parameters corresponding to the baking stages of all baking targets are detected from the baking state database.

[0197] In the above embodiments, the baking parameters can be automatically determined according to the determined baking stage, and baking is performed according to the baking parameters, thereby achieving the purpose of fully automatic baking and effectively saving manpower.

[0198] As an optional implementation, another embodiment of the present application discloses that the baking parameters of the above embodiment include dry-bulb temperature. The above implementation method may specifically include the following steps:

[0199] According to the preset linear regression model of moisture content and dry-bulb and wet-bulb temperature difference, the dry-bulb and wet-bulb temperature difference corresponding to the current moisture content is determined; the linear regression model includes a linear mapping relationship between different moisture contents and dry-bulb and wet-bulb temperature differences; the wet-bulb temperature is determined according to the dry-bulb temperature and the dry-bulb and wet-bulb temperature difference.

[0200] Specifically, since the baking target moisture content is affected by many factors such as the growing environment, irrigation, and fertilization, even if the actual baking stage is the same as the baking stage in the baking status database, the moisture content will be different. Therefore, it is not reasonable to directly set the wet-bulb temperature of this stage in the baking status database as the actual baking parameter.

[0201] In this embodiment, by comparing and analyzing the baking target moisture content at a certain stage of actual baking and the moisture content of the corresponding data group in the baking state database at the baking stage, a wet-bulb temperature value more consistent with actual baking is calculated.

[0202] Through the baking state database, the dry bulb temperature of the baking target at a certain baking stage is obtained as W 干(标准) , wet bulb temperature is W 湿(标准) , moisture content is P (标准) The actual dry bulb temperature of the tobacco leaves obtained during baking is W 干 , wet bulb temperature is W 湿 , the moisture content is P.

[0203] ΔW=W 干(标准) -W 湿(标准)

[0204] Based on a large amount of data in the baking state database, ΔW and P are established. (标准) The linear regression model of . Substituting the moisture content P obtained in real time into the formula, the difference between the dry-bulb temperature and the wet-bulb temperature ΔW can be obtained.

[0205] The wet bulb temperature W 湿 =W 干 -Δ W .

[0206] Exemplarily, if the baking target is tobacco leaves, a set of data is selected from the baking state database, as shown in Tables 2 to 7.

[0207]

[0208] Table 2

[0209]

[0210] Table 3

[0211]

[0212] Table 4

[0213]

[0214] Table 5

[0215]

[0216] Table 6

[0217] P 20.00% 19.00% 18.00% 17.00% 16.00% 15.00% ΔW 21.70 22.40 22.70 22.10 21.80 22.20

[0218] Table 7

[0219] Based on the data in Tables 2 to 7, the moisture content P, the difference between the dry-bulb temperature and the wet-bulb temperature ΔW are fitted to obtain the linear regression model as follows: Fig. 9 shown.

[0220] Fig. 9 In the above example, the formula of linear regression model is:

[0221] ΔW=-33.75P+28.414

[0222] R 2 =0.9639 (This value indicates that there is a strong correlation between moisture content and ΔW)

[0223] Through the above operation and calculation, the control parameter group [dry bulb temperature W干 , wet bulb temperature W湿 , Constant temperature time T恒 , Heating time T升 , wind speed F], and send the parameter group to the controller of the baking room to realize intelligent control of the baking room.

[0224] Exemplary Devices

[0225] Corresponding to the above-mentioned method for determining the baking stage, the embodiment of the present application also discloses a device for determining the baking stage, see Fig.10 As shown, the device comprises:

[0226] The first determination module 100 is used to determine the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target; the baking state characteristics include moisture content and / or image characteristics;

[0227] The second determination module 110 is used to determine whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic if it is detected that there are at least two layers of baking targets that are not in the same baking stage; the critical baking state characteristic is used to trigger the baking parameter adjustment according to the baking stage currently in which the baking target is located;

[0228] The third determining module 120 is used to determine the current baking stage of all baking targets according to the baking stage of each layer of baking targets and the relationship between the baking state feature of each layer of baking targets and its corresponding critical baking state feature.

[0229] As an optional implementation, another embodiment of the present application discloses that the first determination module 100 of the above embodiment, when determining the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target, is specifically used to:

[0230] The baking stage of each baking target layer is determined according to the baking state characteristics of each baking target layer and a preset baking state database; wherein the baking state database includes baking state characteristic intervals corresponding to baking targets in different baking layers at different baking stages.

[0231] As an optional implementation, another embodiment of the present application discloses that the first determination module 100 in the above embodiment specifically includes:

[0232] A first retrieval unit is used to retrieve, from a baking state database, a baking state characteristic interval corresponding to a baking target in a different baking layer when the baking target is in a next baking stage adjacent to a target baking stage; wherein all baking targets are currently baked according to baking parameters of the target baking stage;

[0233] A detection unit, used to detect whether the baking state feature of each baking target layer is located within the baking state feature interval corresponding to the baking target in the baking layer;

[0234] The first determination unit is used to determine that the baking target in the first target baking layer is in a next baking stage adjacent to the target baking stage if the baking state characteristics of the baking target in the first target baking layer are located in the baking state characteristic interval corresponding to the baking layer; and to determine that the baking target in the second target baking layer is in the target baking stage if the baking state characteristics of the baking target in the second target baking layer are not located in the baking state characteristic interval corresponding to the baking layer.

[0235] As an optional implementation, another embodiment of the present application discloses that, in the case where the baking state feature of each layer of baking targets includes an image feature, the baking state feature interval includes an image feature interval; the image feature includes image features of different parts of the baking target; when the detection unit detects whether the baking state feature of each layer of baking targets is located within the baking state feature interval corresponding to the baking target in the baking layer, it is specifically used to:

[0236] The weights of different parts of the baking target in the next baking stage adjacent to the target baking stage are retrieved from a pre-set weight database; the weights of different parts of the baking target in different baking stages are stored in the weight database; according to the weights of different parts of each layer of baking target, the weighted sum of image features of different parts in each layer of baking target is calculated as the comprehensive image feature value of each layer of baking target; it is detected whether the comprehensive image feature value of each layer of baking target is within the image feature interval corresponding to the baking layer, and it is determined whether the baking state feature of each layer of baking target is within the baking state feature interval corresponding to the baking layer according to the detection result.

[0237] As an optional implementation, another embodiment of the present application discloses that the second determination module 110 in the above embodiment specifically includes:

[0238] The second retrieval unit is used to retrieve the critical baking state characteristics of the baking targets in different baking layers from a preset critical baking state characteristic database; the critical baking state characteristic database includes the critical baking state characteristics corresponding to the baking targets in different baking layers in different baking stages;

[0239] The second determining unit is used to determine whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics according to the baking state characteristics of each layer of baking targets and the critical baking state characteristics of the baking targets in the baking layer.

[0240] As an optional implementation, another embodiment of the present application discloses that the third determination module 120 in the above embodiment specifically includes:

[0241] A third determining unit, configured to determine a third target baking layer whose baking stage is the maximum stage from among the baking targets of each layer;

[0242] The fourth determining unit is used to detect whether the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the baking layer, and determine the current baking stage of all the baking targets according to the detection result.

[0243] As an optional implementation, another embodiment of the present application discloses that the fourth determination unit of the above embodiment, when detecting whether the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the baking layer, and determining the current baking stage of all baking targets according to the detection result, is specifically used to:

[0244] If the baking state characteristics of the baking target in the third target baking layer reach the critical baking state characteristics of the layer, the baking stage of the baking target in the third target baking layer is determined as the baking stage of all baking targets; if the baking state characteristics of the baking target in the third target baking layer do not reach the critical baking state characteristics of the layer, the baking stage of the baking target in the baking layer with the minimum baking stage is determined as the baking stage of all baking targets.

[0245] As an optional implementation, another embodiment of the present application discloses that the device in the above embodiment further includes:

[0246] The adjustment module is used to adjust the baking according to the baking parameters corresponding to the baking stages of all baking targets.

[0247] As an optional implementation, another embodiment of the present application discloses that the device in the above embodiment further includes:

[0248] The fourth determination module is used to determine the dry-bulb temperature difference corresponding to the current moisture content according to a preset linear regression model of moisture content and dry-bulb temperature difference; the linear regression model includes a linear mapping relationship between different moisture contents and dry-bulb temperature differences;

[0249] The fifth determination module is used to determine the wet bulb temperature according to the dry bulb temperature and the dry-bulb and wet-bulb temperature difference.

[0250] Specifically, for the specific working contents of each unit of the above-mentioned baking stage determination device, please refer to the contents of the above-mentioned method embodiment, which will not be repeated here.

[0251] Exemplary Electronic Devices

[0252] Corresponding to the above-mentioned method for determining the baking stage, the embodiment of the present application further discloses an electronic device, see Fig.11 As shown, the electronic device includes:

[0253] Memory 200 and processor 210;

[0254] The memory 200 is connected to the processor 210 and is used to store programs;

[0255] The processor 210 is used to implement the method for determining the baking stage disclosed in any of the above embodiments by running the program stored in the memory 200.

[0256] Specifically, the electronic device may further include: a bus, a communication interface 220 , an input device 230 and an output device 240 .

[0257] The processor 210, the memory 200, the communication interface 220, the input device 230 and the output device 240 are connected to each other via a bus.

[0258] A bus may include a pathway that transfers information between components of a computer system.

[0259] The processor 210 may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0260] The processor 210 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0261] The memory 200 stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory 200 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0262] The input device 230 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0263] Output device 240 may include devices that allow information to be output to a user, such as a display screen, printer, speaker, etc.

[0264] The communication interface 220 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0265] The processor 210 executes the program stored in the memory 200 and calls other devices, which can be used to implement each step of the baking stage determination method provided in the above embodiment of the present application.

[0266] Exemplary Ovens

[0267] Another embodiment of the present application also provides a baking oven, see Fig.12 As shown, the oven comprises:

[0268] A state acquisition device 300 and a controller 310;

[0269] The state acquisition device 300 is used to obtain the baking state of each layer of the baking target;

[0270] The controller 310 is used to determine the baking state characteristics of each layer of baking targets according to the baking state of each layer of baking targets; the baking state characteristics include moisture content and / or image characteristics; according to the baking state characteristics of each layer of baking targets, the baking stage of each layer of baking targets is determined; if it is detected that there are at least two layers of baking targets that are not in the same baking stage, it is determined whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics; the critical baking state characteristics are used to trigger the adjustment of baking parameters according to the current baking stage of the baking targets; according to the baking stage of each layer of baking targets and the relationship between the baking state characteristics of each layer of baking targets and their corresponding critical baking state characteristics, the current baking stage of all baking targets is determined.

[0271] As an optional implementation method, another embodiment of the present application discloses that the baking state of the above embodiment includes the current total weight of the baking target, and the state acquisition device includes a weight sensor; the baking oven also includes a first baking bracket and a second baking bracket; the first baking bracket is used to place the baking target, and the first baking bracket is installed on the second baking bracket; the weight sensor is arranged on the second baking bracket in the set area, and is located at a position where the first baking bracket contacts the second baking bracket in the set area, and is used to collect the current total weight of the baking target in the set area.

[0272] The specific structures and configurations of the weight sensor, the first baking bracket, and the second baking bracket can refer to the above embodiments and Figure 2 The records in the article are not repeated here.

[0273] As an optional implementation method, another embodiment of the present application discloses that the baking state of the above embodiment includes a baking image, and the state acquisition device includes a camera, a fill light box and a wind shield arranged on the inner wall of the baking oven; the wind shield is buckled on the inner wall of the baking oven to form a photo taking space; the camera and the fill light box are both installed in the photo taking space; the camera is used to collect the baking image of each layer of the baking target through the wind shield.

[0274] The specific structure and configuration of the state acquisition device can refer to the description of the camera, fill light box and windshield in the above embodiment, and Figure 3 , which will not be elaborated here.

[0275] The baking oven provided in this embodiment belongs to the same application concept as the baking stage determination method provided in the above embodiments of the present application, and can execute the baking stage determination method provided in any of the above embodiments of the present application, and has the corresponding functional modules and beneficial effects for executing the above baking stage determination method. For technical details not fully described in this embodiment, please refer to the specific processing content of the baking stage determination method provided in the above embodiments of the present application, which will not be repeated here.

[0276] Computer program product and storage medium

[0277] In addition to the above methods and devices, the embodiments of the present application may also be a computer program product, which includes computer program instructions. When the computer program instructions are executed by the processor 210, the processor 210 executes each step of the baking stage determination method provided in the above embodiments.

[0278] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0279] In addition, the embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by the processor, the processor 210 executes each step of the baking stage determination method provided in the above embodiment.

[0280] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0281] Specifically, the specific working contents of each part of the above-mentioned computer program product and storage medium, as well as the specific processing contents of the computer program product or the computer program on the above-mentioned storage medium when being executed by the processor, can be found in the contents of each embodiment of the above-mentioned baking stage determination method, which will not be repeated here.

[0282] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0283] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0284] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0285] The modules and sub-modules in the devices and terminals in the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0286] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, such as multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0287] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0288] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0289] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0290] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0291] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0292] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for determining a baking stage, characterized in that: include: Determining the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target; the baking state characteristics include moisture content and / or image characteristics; If it is detected that there are at least two layers of baking targets that are not in the same baking stage, determining whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic; The critical baking state feature is used to trigger baking parameter adjustment according to the baking stage currently in which the baking target is located; Determine a third target baking layer whose baking stage is the maximum stage from the baking targets of each layer; If the baking state characteristic of the baking target in the third target baking layer reaches the critical baking state characteristic of the layer, the baking stage of the baking target in the third target baking layer is determined as the baking stage of all baking targets; If the baking state characteristics of the baking targets in the third target baking layer do not reach the critical baking state characteristics of the layer, the baking stage of the baking targets in the baking layer with the minimum baking stage is determined as the baking stage of all baking targets.

2. The method according to claim 1, characterized in that According to the baking state characteristics of each layer of baking target, the baking stage of each layer of baking target is determined, including: The baking stage of each baking target layer is determined according to the baking state characteristics of each baking target layer and a pre-set baking state database; wherein the baking state database includes baking state characteristic intervals corresponding to baking targets in different baking layers at different baking stages.

3. The method according to claim 2, characterized in that According to the baking state characteristics of each layer of baking target and the pre-set baking state database, the baking stage of each layer of baking target is determined, including: Retrieving, from the baking state database, the baking state characteristic intervals corresponding to the baking targets in different baking layers when they are in the next baking stage adjacent to the target baking stage; wherein all baking targets are currently baked according to the baking parameters of the target baking stage; Detecting whether the baking state feature of each baking target layer is within the baking state feature interval corresponding to the baking target in the baking layer; If there is a baking state feature of a baking target in the first target baking layer that is located in the baking state feature interval corresponding to the baking layer, it is determined that the baking target in the first target baking layer is in the next baking stage adjacent to the target baking stage; If the baking state feature of the baking target in the second target baking layer is not located in the baking state feature interval corresponding to the baking layer, it is determined that the baking target in the second target baking layer is in the target baking stage.

4. The method according to claim 3, characterized in that In the case where the baking state feature of each layer of the baking target includes an image feature, the baking state feature interval includes an image feature interval; the image feature includes image features of different parts of the baking target; Detecting whether the baking state feature of each baking target layer is within the baking state feature interval corresponding to the baking target in the baking layer includes: Retrieving the weights of different parts of the baking target in the next baking stage adjacent to the target baking stage from a preset weight database; the weight database stores the weights of different parts of the baking target in different baking stages; According to the weights of different parts of each layer of baking target, the weighted sum of the image features of different parts of each layer of baking target is calculated as the comprehensive image feature value of each layer of baking target; It is detected whether the comprehensive image feature value of each baking target layer is within the image feature interval corresponding to the baking layer, and it is determined whether the baking state feature of each baking target layer is within the baking state feature interval corresponding to the baking layer according to the detection result.

5. The method according to claim 1, characterized in that Determine whether the baking state characteristics of each layer of baking target have reached the critical baking state characteristics, including: Retrieving critical baking state features of baking targets in different baking layers from a preset critical baking state feature database; the critical baking state feature database includes critical baking state features corresponding to baking targets in different baking layers at different baking stages; Whether the baking state characteristics of each layer of baking targets reach the critical baking state characteristics is determined according to the baking state characteristics of each layer of baking targets and the critical baking state characteristics of the baking targets in the baking layer.

6. The method according to claim 1, characterized in that Also includes: The baking is adjusted according to the baking parameters corresponding to the baking stages of all baking targets.

7. The method according to claim 6, characterized in that The baking parameters include dry bulb temperature; the method further includes: Determine the dry-bulb temperature difference corresponding to the current moisture content according to a pre-set linear regression model of moisture content and dry-bulb temperature difference; the linear regression model includes a linear mapping relationship between different moisture contents and dry-bulb temperature differences; The wet bulb temperature is determined based on the dry bulb temperature and the dry-bulb and wet-bulb temperature difference.

8. A baking stage determination device, characterized in that: include: A first determination module is used to determine the baking stage of each layer of baking target according to the baking state characteristics of each layer of baking target; The baking state characteristics include moisture content and / or image characteristics; A second determination module is used to determine whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic if it is detected that there are at least two layers of baking targets that are not in the same baking stage; The critical baking state feature is used to trigger baking parameter adjustment according to the baking stage currently in which the baking target is located; The third determination module is used to determine a third target baking layer whose baking stage is the maximum stage from each layer of baking targets; if the baking state characteristics of the baking targets in the third target baking layer reach the critical baking state characteristics of the layer, the baking stage of the baking targets in the third target baking layer is determined as the baking stage of all baking targets; if the baking state characteristics of the baking targets in the third target baking layer do not reach the critical baking state characteristics of the layer, the baking stage of the baking targets in the baking layer whose baking stage is the minimum stage is determined as the baking stage of all baking targets.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to implement the method according to any one of claims 1 to 7 by running the program in the memory.

10. A baking oven, characterized in that: include: Status acquisition equipment and controllers; The state acquisition device is used to obtain the baking state of each layer of baking target; The controller is used to determine the baking state characteristics of each layer of baking targets according to the baking state of each layer of baking targets; The baking state characteristics include moisture content and / or image characteristics; according to the baking state characteristics of each layer of baking targets, the baking stage of each layer of baking targets is determined; if it is detected that there are at least two layers of baking targets that are not in the same baking stage, it is determined whether the baking state characteristics of each layer of baking targets reach a critical baking state characteristic; The critical baking state characteristic is used to trigger the adjustment of baking parameters according to the baking stage currently in which the baking target is located; a third target baking layer with the maximum baking stage is determined from each layer of baking targets; if the baking state characteristic of the baking target in the third target baking layer reaches the critical baking state characteristic of the layer, the baking stage of the baking target in the third target baking layer is determined as the baking stage of all baking targets; if the baking state characteristic of the baking target in the third target baking layer does not reach the critical baking state characteristic of the layer, the baking stage of the baking target in the baking layer with the minimum baking stage is determined as the baking stage of all baking targets.

11. The baking oven according to claim 10, characterized in that: The baking state includes a baking image; the state acquisition device includes a camera, a fill light box and a wind shield arranged on the inner wall of the baking box; wherein the wind shield is buckled on the inner wall of the baking box to form a photo taking space; the camera and the fill light box are both installed in the photo taking space; the camera is used to acquire the baking image of each layer of the baking target through the wind shield.

12. The baking oven according to claim 10, characterized in that: The baking state includes the current total weight of the baking target, and the state acquisition device includes a weight sensor; the baking oven also includes a first baking rack and a second baking rack; The first baking bracket is used to place the baking target, and the first baking bracket is installed on the second baking bracket; the weight sensor is arranged on the second baking bracket within the set area, and is located at the position where the first baking bracket contacts the second baking bracket within the set area, and is used to collect the current total weight of the baking target within the set area.

13. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.