Potato liquor quality control method, system and equipment

Abstract

The invention discloses a potato liquor quality control method, system and equipment, and the method comprises the steps: extracting a to-be-detected raw material from target raw materials according to a sampling inspection rule, and obtaining the first physicochemical data of the to-be-detected raw material; and judging whether matched second physicochemical data exist in the brewing record according to the data. If the matched data exist, processing the to-be-detected raw material according to the corresponding first process parameter to obtain a first wine liquid; and if no matched data exist, processing is carried out according to preset second process parameters. And detecting the first wine liquid to obtain a detection result, and judging whether the detection result meets the quality standard or not. If so, continuously processing the target raw material according to the first or second process parameters; and if the detection result does not accord with the standard, adjusting the process parameters according to the detection result and a preset quality response model to form new third process parameters, and processing according to the parameters. The problem that industrial production of the potato white spirit lacks a systematic quality control scheme is at least solved.

Description

Technical Field

[0001] The present application relates to the field of production automation technology, and in particular to a method, system and equipment for controlling the quality of potato liquor. Background Art

[0004] At present, since potato liquor is made from potatoes through fermentation, the flavor of the fermentation product is greatly affected by the raw materials and brewing process. Although there are some evaluation systems for the flavor of potato liquor, these evaluation systems can only be used to evaluate the quality of the final product, but cannot guide the entire brewing process, resulting in the lack of a systematic quality control plan for the industrial production of potato liquor. Summary of the invention

[0005] The present invention provides a method, system and equipment for controlling the quality of potato liquor, which at least solves the problem that although there are some evaluation systems for the flavor of potato liquor, these evaluation systems can only be used to evaluate the quality of the final product, but cannot guide the entire brewing process, resulting in a lack of a systematic quality control solution for the industrial production of potato liquor.

[0006] The present invention provides a method for controlling the quality of potato liquor, comprising the following steps:

[0007] Selecting a raw material to be inspected from the target raw materials according to a preset sampling rule, and obtaining first physical and chemical data of the raw material to be inspected;

[0008] According to the first physical and chemical data of the raw material to be inspected, determining whether the brewing record includes second physical and chemical data matching the first physical and chemical data;

[0009] If the brewing record includes second physical and chemical data matching the first physical and chemical data, the raw material to be inspected is processed according to a first process parameter corresponding to the second physical and chemical data to obtain a first liquor;

[0010] If the brewing record does not include second physical and chemical data matching the first physical and chemical data, processing the raw material to be inspected according to a preset second process parameter to obtain a first liquor;

[0011] According to the first wine liquid, testing the first wine liquid to obtain a first testing result;

[0012] According to the first test result, determining whether the first wine meets a preset quality standard;

[0013] If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter;

[0014] If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and the target raw material is processed according to the third process parameter.

[0015] Optionally, judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data of the raw material to be inspected includes:

[0016] Obtaining a first component ratio of the raw material to be tested according to the first physical and chemical data of the raw material to be tested;

[0017] Obtaining first weight data according to the proportion of the first component of the raw material to be inspected;

[0018] According to the brewing record, obtaining the proportion of the second component of the brewing record;

[0019] Obtaining second weight data according to the difference between the first component proportion and the second component proportion;

[0020] According to the first weight data and the second weight data, it is determined whether the brewing record includes second physicochemical data matching the first physicochemical data.

[0021] Optionally, the testing the first wine liquid to obtain a first test result according to the first wine liquid includes:

[0022] According to the first wine liquid, extracting a first wine liquid to be tested from the first wine liquid;

[0023] According to the first wine to be tested, a spectral analysis is performed on the first wine to be tested to obtain a first detection result.

[0024] Optionally, judging whether the first wine meets a preset quality standard according to the first detection result includes:

[0025] Preprocessing the first detection result according to the first detection result;

[0026] Extracting a first feature of the first detection result based on a deep learning network according to the preprocessed first detection result;

[0027] Using a target encoder to perform a hybrid parallel attention calculation on the first feature, wherein a result of the calculation is used to fuse with a residual of the first feature to obtain a second feature;

[0028] Inputting the second feature into a convolutional feedforward network, wherein the convolutional feedforward network is used to perform data dimension reduction to obtain a sensory feature of the first detection result;

[0029] Based on the sensory characteristics of the first test result and a preset indicator system, it is determined whether the first wine meets the preset quality standards.

[0030] Optionally, if the first liquor does not meet a preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and before processing the target raw material according to the third process parameter, the method further includes:

[0031] Establishing an initial quality response model, wherein the initial quality response model is configured to take the original spectrum data and the target spectrum data as input and take the process parameter adjustment value as output;

[0032] Acquiring historical brewing data, wherein the historical brewing data includes process parameters and corresponding spectral data of wine;

[0033] According to the historical brewing data, obtaining a data set for training the initial quality response model;

[0034] The initial quality response model is trained according to the data set to obtain the quality response model.

[0035] Optionally, if the first liquor does not meet a preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter includes:

[0036] If the first liquor does not meet the preset quality standard, based on the first detection result, the first detection result is used as the original spectrum data, and the preset target detection result is used as the target spectrum data to input into the quality response model to obtain the first process parameter adjustment value;

[0037] According to the first process parameter adjustment value, adjusting the first process parameter or the second process parameter to obtain a third process parameter;

[0038] The target raw material is processed according to the third process parameter.

[0039] Optionally, if the first liquor does not meet a preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter includes:

[0040] If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter;

[0041] Processing the raw material to be inspected according to the third process parameter to obtain a second liquor;

[0042] According to the second wine liquid, testing the second wine liquid to obtain a second test result;

[0043] According to the second test result, determining whether the second wine meets a preset quality standard;

[0044] If the second wine liquid does not meet the preset quality standard, the third process parameter is adjusted according to the second test result and the preset quality response model to obtain the adjusted third process parameter, and the raw material to be tested is processed according to the third process parameter to obtain a new second wine liquid;

[0045] If the second wine liquid meets the preset quality standard, the target raw material is processed according to the third process parameter.

[0046] Optionally, if the first liquor does not meet a preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and after processing the target raw material according to the third process parameter, the method further includes:

[0047] The first physical and chemical data and the third process parameter are matched and stored in the brewing record.

[0048] On the other hand, a potato liquor quality control system includes a raw material management platform and a brewing management platform;

[0049] The raw material management platform is configured as follows:

[0050] Selecting a raw material to be inspected from the target raw materials according to a preset sampling rule, and obtaining first physical and chemical data of the raw material to be inspected;

[0051] The brewing management platform is configured to:

[0052] According to the first physical and chemical data of the raw material to be inspected, determining whether the brewing record includes second physical and chemical data matching the first physical and chemical data;

[0053] If the brewing record includes second physical and chemical data matching the first physical and chemical data, the raw material to be inspected is processed according to a first process parameter corresponding to the second physical and chemical data to obtain a first liquor;

[0054] If the brewing record does not include second physical and chemical data matching the first physical and chemical data, processing the raw material to be inspected according to a preset second process parameter to obtain a first liquor;

[0055] According to the first wine liquid, testing the first wine liquid to obtain a first testing result;

[0056] According to the first test result, determining whether the first wine meets a preset quality standard;

[0057] If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter;

[0058] If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and the target raw material is processed according to the third process parameter.

[0059] On the other hand, a device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0060] On the other hand, a computer-readable storage medium is provided. The device includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement any of the above methods.

[0061] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0062] The present invention discloses a method, system and equipment for controlling the quality of potato liquor, comprising: selecting a raw material to be inspected from target raw materials according to a preset sampling rule, and obtaining first physicochemical data of the raw material to be inspected; judging whether a brewing record includes second physicochemical data matching the first physicochemical data according to the first physicochemical data of the raw material to be inspected; if the brewing record includes the second physicochemical data matching the first physicochemical data, processing the raw material to be inspected according to first process parameters corresponding to the second physicochemical data to obtain first liquor; if the brewing record does not include the second physicochemical data matching the first physicochemical data, processing the raw material to be inspected according to first process parameters corresponding to the second physicochemical data to obtain first liquor; Process the raw materials to be tested to obtain a first liquor; based on the first liquor, test the first liquor to obtain a first test result; based on the first test result, determine whether the first liquor meets the preset quality standard; if the first liquor meets the preset quality standard, process the target raw material according to the first process parameter or the second process parameter; if the first liquor does not meet the preset quality standard, adjust the first process parameter or the second process parameter according to the first test result and a preset quality response model to obtain a third process parameter, and process the target raw material according to the third process parameter. At least it solves the problem that although there are some evaluation systems for the flavor of potato liquor, these evaluation systems can only be used to evaluate the quality of the final product, but cannot guide the entire brewing process, resulting in the lack of a systematic quality control solution for the industrial production of potato liquor. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0064] Figure 1 The figure is a flow chart of the method for controlling the quality of potato liquor in this application;

[0065] Figure 2 This is a schematic diagram of the structure of a computer device in this application.

[0066] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0067] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0068] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0069] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0070] Example 1

[0071] like Figure 1 As shown, a method for controlling the quality of potato liquor comprises the following steps:

[0072] S1. Select a raw material to be inspected from target raw materials according to a preset sampling rule, and obtain first physical and chemical data of the raw material to be inspected.

[0073] Optionally, the preset sampling rules may be one or more sampling methods of simple random sampling, systematic sampling, cluster sampling and stratified sampling.

[0074] Optionally, the first physical and chemical data may include average mass, starch content, moisture content, content of other components, etc.

[0075] S2. According to the first physicochemical data of the raw material to be inspected, determine whether the brewing record includes second physicochemical data that matches the first physicochemical data.

[0076] Specifically, by judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data, it is determined whether similar raw materials have been brewed.

[0077] S3. If the brewing record includes second physical and chemical data that matches the first physical and chemical data, the raw material to be inspected is processed according to the first process parameters corresponding to the second physical and chemical data to obtain the first liquor.

[0078] Specifically, if similar raw materials have been brewed before, brewing can be directly carried out according to the previous brewing process parameters.

[0079] S4. If the brewing record does not include the second physical and chemical data that matches the first physical and chemical data, the raw material to be inspected is processed according to the preset second process parameters to obtain the first liquor.

[0080] Specifically, the second process parameter may be a predetermined standard parameter, or an average parameter or other parameters obtained according to brewing records.

[0081] S5. According to the first wine liquid, the first wine liquid is tested to obtain a first test result.

[0082] Specifically, a first wine liquid brewed using the raw material to be tested is tested to obtain a first test result of the first wine liquid.

[0083] S6. According to the first test result, determine whether the first wine meets the preset quality standard.

[0084] Specifically, based on the first test result of the first wine, it is determined whether the first wine meets the preset quality standard.

[0085] S7. If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter.

[0086] Specifically, if the first liquor meets the preset quality standard, the target raw material can be produced directly according to the first process parameter or the second process parameter for obtaining the first liquor.

[0087] S8. If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain the third process parameter, and the target raw material is processed according to the third process parameter.

[0088] Specifically, the target raw material is potato, and the process parameters may include one or more of the production processes such as cooking time, the ratio of potato to other raw materials, fermentation time, and distillation temperature. The production process belongs to the production links such as steaming, adding koji, making nests, fermentation, and distillation.

[0089] Specifically, if the first wine does not meet the preset quality standards, the first process parameter or the second process parameter is adjusted to obtain the third process parameter, and the third process parameter is configured so that the wine obtained by brewing the raw materials to be inspected according to the third process parameter meets the preset quality standards.

[0090] By adopting the above scheme, costs can be saved when the raw materials meet expectations or are stable, and production can be carried out directly according to the existing process parameters. When the raw materials are unstable, the process parameters matching the raw materials can be quickly obtained through trial production. This at least solves the problem that although there are some evaluation systems for the flavor of potato liquor, these evaluation systems can only be used to evaluate the quality of the final product, but cannot guide the entire brewing process, resulting in the lack of a systematic quality control program for the industrial production of potato liquor.

[0091] Example 2

[0092] This embodiment provides a method for controlling the quality of potato liquor based on embodiment 1, comprising the following steps:

[0093] S1. Select a raw material to be inspected from target raw materials according to a preset sampling rule, and obtain first physical and chemical data of the raw material to be inspected.

[0094] Optionally, the preset sampling rules can be one or more sampling methods among simple random sampling, systematic sampling, cluster sampling and stratified sampling; simple random sampling: number all observation units of the survey population, and then randomly select some observation units to form a sample by drawing lots or using a random number table; systematic sampling: also known as mechanical sampling, equal-interval sampling, that is, first divide the observation units of the population into n parts according to a certain sequence number, and then randomly select the kth observation unit from the first part, and then use equal intervals to select one observation unit from each part to form a sample; cluster sampling: divide the population into groups, and then randomly select several groups to form a sample, and all the groups are surveyed; stratified sampling: first divide the population into several categories according to a certain feature that has a greater impact on the observed indicators, and then randomly select a certain number of observation units from each layer to form a sample. There are two schemes: proportional allocation and optimal allocation.

[0095] Optionally, the first physical and chemical data may include average mass, starch content, moisture content, content of other components, etc.

[0096] S2. According to the first physicochemical data of the raw material to be inspected, determine whether the brewing record includes second physicochemical data that matches the first physicochemical data.

[0097] Specifically, by judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data, it is determined whether similar raw materials have been brewed.

[0098] Optionally, judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data according to the first physical and chemical data of the raw material to be inspected includes:

[0099] Obtaining a first component ratio of the raw material to be tested according to the first physical and chemical data of the raw material to be tested;

[0100] According to the proportion of the first component of the raw material to be tested, first weight data is obtained;

[0101] According to the brewing record, the proportion of the second component of the brewing record is obtained;

[0102] According to the difference between the proportion of the first component and the proportion of the second component, the second weight data is obtained;

[0103] According to the first weight data and the second weight data, it is determined whether the brewing record includes the second physicochemical data matching the first physicochemical data.

[0104] Specifically, according to the first weight data and the second weight data, a method for determining whether the brewing record includes the second physical and chemical data matching the first physical and chemical data is:

[0105]

[0106] E≤E1;

[0107] Where n is the total number of components of the raw material to be tested, P i is the proportion of component i in the raw material to be tested, Q i is the proportion of ingredient i in a brewing record, E1 is the preset first threshold, when there is a set of records Q in the brewing record i When E is not greater than E1, the brewing record includes second physicochemical data matching the first physicochemical data. If E is minimum at this time, the group of records corresponds to the second physicochemical data.

[0108] S3. If the brewing record includes second physical and chemical data that matches the first physical and chemical data, the raw material to be inspected is processed according to the first process parameters corresponding to the second physical and chemical data to obtain the first liquor.

[0109] Specifically, if similar raw materials have been brewed before, brewing can be directly carried out according to the previous brewing process parameters.

[0110] S4. If the brewing record does not include the second physical and chemical data that matches the first physical and chemical data, the raw material to be inspected is processed according to the preset second process parameters to obtain the first liquor.

[0111] Specifically, the second process parameter may be a predetermined standard parameter, or an average parameter or other parameters obtained according to brewing records.

[0112] S5. According to the first wine liquid, the first wine liquid is tested to obtain a first test result.

[0113] Specifically, a first wine liquid brewed using the raw material to be tested is tested to obtain a first test result of the first wine liquid.

[0114] Optionally, according to the first wine liquid, testing the first wine liquid to obtain a first test result includes:

[0115] According to the first wine liquid, extracting a first wine liquid to be tested from the first wine liquid;

[0116] According to the first wine liquid to be tested, a spectral analysis is performed on the first wine liquid to be tested to obtain a first detection result.

[0117] S6. According to the first test result, determine whether the first wine meets the preset quality standard.

[0118] Specifically, based on the first test result of the first wine, it is determined whether the first wine meets the preset quality standard.

[0119] Optionally, judging whether the first liquor meets a preset quality standard according to the first test result includes:

[0120] Preprocessing the first detection result according to the first detection result;

[0121] Extracting a first feature of the first detection result based on a deep learning network according to the preprocessed first detection result;

[0122] The target encoder is used to perform hybrid parallel attention calculation on the first feature, and the calculation result is used to fuse with the residual of the first feature to obtain the second feature;

[0123] Inputting the second feature into a convolutional feedforward network, where the convolutional feedforward network is used to perform data dimension reduction to obtain a sensory feature of the first detection result;

[0124] Based on the sensory characteristics of the first test result and a preset indicator system, it is determined whether the first wine meets the preset quality standards.

[0125] Optionally, in order to implement the above solution, this embodiment provides a deep learning framework to generate sensory characteristic results of wine, and the framework includes:

[0126] S601: Preprocessing is performed according to the first detection result, which generally includes steps such as denoising, normalization and standardization.

[0127] Python

[0128] import numpy as npfrom sklearn.preprocessing import StandardScaler

[0129] def preprocess_data(raw_data):

[0130] #Assume that raw_data is the original detection data, perform denoising and standardization

[0131] data = raw_data - np.mean(raw_data) # remove mean

[0132] scaler = StandardScaler()

[0133] normalized_data = scaler.fit_transform(data.reshape(-1,1)) # Standardization

[0134] return normalized_data;

[0135] S602, using a deep learning model, such as a multi-layer perceptron (MLP) or a convolutional neural network (CNN), to extract the first feature first_feature of the detection result:

[0136] Python

[0137] import torchimport torch.nn as nnimport torch.optim as optim

[0138] class FeatureExtractor(nn.Module):

[0139] def __init__(self):

[0140] super(FeatureExtractor,self).__init__()

[0141] self.fc1 = nn.Linear(128,64) #Assume that the input data dimension is 128

[0142] self.fc2 = nn.Linear(64,32)

[0143] self.fc3 = nn.Linear(32,16) #The extracted dimension is 16

[0144] def forward(self,x):

[0145] x = torch.relu(self.fc1(x))

[0146] x = torch.relu(self.fc2(x))

[0147] x = self.fc3(x)

[0148] return x

[0149] #Assume that raw_data has been preprocessed

[0150] model = FeatureExtractor()

[0151] input_data=torch.tensor(normalized_data,dtype=torch.float32)

[0152] first_feature=model(input_data);

[0153] S603, use the target encoder to perform hybrid parallel attention calculation to obtain the second feature second_feature:

[0154] Python

[0155] class AttentionLayer(nn.Module):

[0156] def__init__(self,input_dim,output_dim):

[0157] super(AttentionLayer,self).__init__()

[0158] self.query=nn.Linear(input_dim,output_dim)

[0159] self.key=nn.Linear(input_dim,output_dim)

[0160] self.value=nn.Linear(input_dim,output_dim)

[0161] def forward(self,x):

[0162] q = self.query(x)

[0163] k = self.key(x)

[0164] v = self.value(x)

[0165] attention_scores=torch.matmul(q,k.transpose(-2,-1)) / np.sqrt(q.size(-1))#Scaled dot-product attention

[0166] attention_weights=torch.nn.functional.softmax(attention_scores,dim=-1)

[0167] output=torch.matmul(attention_weights,v)

[0168] return output

[0169] attention_layer=AttentionLayer(input_dim=16, output_dim=8)

[0170] second_feature=attention_layer(first_feature)

[0171] S604, perform residual fusion on the calculated second feature and the first feature to obtain a fused feature fused_feature:

[0172] Python

[0173] class ResidualFusionLayer(nn.Module):

[0174] def __init__(self):

[0175] super(ResidualFusionLayer,self).__init__()

[0176] self.fc = nn.Linear(16,16) #Assume that the dimension is the same as the second feature

[0177] def forward(self,first_feature,second_feature):

[0178] fused_feature=first_feature+second_feature#residual fusion

[0179] fused_feature=self.fc(fused_feature)

[0180] return fused_feature

[0181] fusion_layer=ResidualFusionLayer()

[0182] fused_feature=fusion_layer(first_feature,second_feature);

[0183] S605. Use the convolutional feedforward network to reduce the dimension of the fused features to obtain sensory features sensor_features:

[0184] Python

[0185] class CNNForDimReduction(nn.Module):

[0186] def __init__(self):

[0187] super(CNNForDimReduction,self).__init__()

[0188] self.conv1=nn.Conv1d(16,8,kernel_size=3)

[0189] self.pool = nn.MaxPool1d(2)

[0190] self.fc = nn.Linear(8,4) # Output sensory feature dimension is 4

[0191] def forward(self,x):

[0192] x=self.pool(torch.relu(self.conv1(x)))

[0193] x=x.view(x.size(0),-1)#Flatten

[0194] x = self.fc(x)

[0195] return x

[0196] cnn_layer=CNNForDimReduction()

[0197] sensory_features = cnn_layer(fused_feature.unsqueeze(0).unsqueeze(2)) # adapt input dimension;

[0198] S606, judging whether the first liquor meets the quality standard based on the sensory characteristics and the preset indicator system;

[0199] The optional, preset indicator system is shown in Table 1 below:

[0200] Table 1: Evaluation index system of sensory characteristics of potato liquor

[0201]

[0202]

[0203] Among them, features 01 to 19 are texts or feature codes that match the sensory features sensory_features. For example, feature 01 can be clear, transparent, or a feature symbol indicating clear or transparent; feature 05 can be mellow and rich, or a feature symbol indicating mellow and rich, and so on.

[0204] S7. If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter.

[0205] Specifically, if the first liquor meets the preset quality standard, the target raw material can be produced directly according to the first process parameter or the second process parameter for obtaining the first liquor.

[0206] S8. If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain the third process parameter, and the target raw material is processed according to the third process parameter.

[0207] Specifically, if the first wine does not meet the preset quality standards, the first process parameter or the second process parameter is adjusted to obtain the third process parameter, and the third process parameter is configured so that the wine obtained by brewing the raw materials to be inspected according to the third process parameter meets the preset quality standards.

[0208] Optionally, if the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and before the step of processing the target raw material according to the third process parameter, the method further includes:

[0209] An initial quality response model is established, where the initial quality response model is configured to take the original spectrum data and the target spectrum data as input and take the process parameter adjustment value as output;

[0210] Obtain historical brewing data, which includes process parameters and corresponding spectral data of wine;

[0211] Based on historical brewing data, a data set for initial quality response model training is obtained;

[0212] The initial quality response model is trained according to the data set to obtain a quality response model.

[0213] Optionally, the historical brewing data is structured data, and the fields include parameters of various process parameters and various spectral data; the method for obtaining a data set for initial quality response model training based on the historical brewing data includes:

[0214] Obtain all records (rows in the data table) in the historical brewing data, combine every two records into a new record and store it in the data set used for initial quality response model training. The data set is structured data, and the fields include the adjustment values ​​of various process parameters and the parameters of two sets of spectral data, one of which is the parameters of the original spectral data and the other is the parameters of the target spectral data. ;

[0215] Specifically, as an example, some data of historical brewing data is shown in Table 2:

[0216] Table 2 Partial data table of historical brewing data

[0217] serial number Process parameters A Spectral data A 1 a c 2 b d

[0218] The data set for initial quality response model training obtained according to Table 2 is shown in Table 3:

[0219] Table 3 Dataset data table

[0220] serial number Adjustment value of process parameter A Original spectral data A Target spectral data A 1 ab c d 2 ba d c

[0221] Specifically, in this embodiment, a multi-layer perceptron (MLP) regression model is used to establish an initial quality response model; the input is spectral data, and the output is the process parameter adjustment value. The following is part of the code for establishing the initial quality response model:

[0222]

[0223] self.fc2 = nn.Linear(128,64)

[0224] self.fc3 = nn.Linear(64,32)

[0225] self.fc4=nn.Linear(32,1)#Output process parameter adjustment value

[0226] def forward(self,x):

[0227] x = torch.relu(self.fc1(x))

[0228] x = torch.relu(self.fc2(x))

[0229] x = torch.relu(self.fc3(x))

[0230] x = self.fc4(x)

[0231] return x.

[0232] Optionally, if the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and the preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including:

[0233] If the first liquor does not meet the preset quality standard, based on the first test result, the first test result is used as the original spectrum data, and the preset target test result is used as the target spectrum data to input into the quality response model to obtain the first process parameter adjustment value;

[0234] According to the first process parameter adjustment value, adjusting the first process parameter or the second process parameter to obtain a third process parameter;

[0235] The target raw material is processed according to the third process parameter.

[0236] Optionally, if the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and the preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including:

[0237] If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first test result and the preset quality response model to obtain a third process parameter;

[0238] Processing the raw material to be inspected according to the third process parameter to obtain a second liquor;

[0239] According to the second wine liquid, testing the second wine liquid to obtain a second test result;

[0240] According to the second test result, determining whether the second wine meets the preset quality standard;

[0241] If the second liquor does not meet the preset quality standard, the third process parameter is adjusted according to the second test result and the preset quality response model to obtain the adjusted third process parameter, and the raw material to be tested is processed according to the third process parameter to obtain a new second liquor;

[0242] If the second liquor meets the preset quality standard, the target raw material is processed according to the third process parameter.

[0243] Through the above scheme, it can be ensured that the process parameters for final large-scale production meet the requirements of quality control.

[0244] Optionally, if the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and after the target raw material is processed according to the third process parameter, the method further includes:

[0245] The first physical and chemical data and the third process parameter are matched and stored in the brewing record.

[0246] By the above method, the brewing records can be continuously updated.

[0247] Example 3

[0248] A potato liquor quality control system, including a raw material management platform and a brewing management platform;

[0249] The raw material management platform is configured as:

[0250] Selecting raw materials to be inspected from target raw materials according to preset sampling rules, and obtaining first physical and chemical data of the raw materials to be inspected;

[0251] The brew management platform is configured to:

[0252] According to the first physical and chemical data of the raw material to be inspected, determining whether the brewing record includes second physical and chemical data matching the first physical and chemical data;

[0253] If the brewing record includes second physical and chemical data that matches the first physical and chemical data, the raw material to be inspected is processed according to the first process parameter corresponding to the second physical and chemical data to obtain the first liquor;

[0254] If the brewing record does not include the second physical and chemical data matching the first physical and chemical data, the raw material to be inspected is processed according to the preset second process parameters to obtain the first liquor;

[0255] According to the first wine liquid, the first wine liquid is tested to obtain a first test result;

[0256] According to the first test result, determining whether the first liquor meets the preset quality standard;

[0257] If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter;

[0258] If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first test result and the preset quality response model to obtain the third process parameter, and the target raw material is processed according to the third process parameter.

[0259] Optionally, judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data according to the first physical and chemical data of the raw material to be inspected includes:

[0260] Obtaining a first component ratio of the raw material to be tested according to the first physical and chemical data of the raw material to be tested;

[0261] According to the proportion of the first component of the raw material to be tested, first weight data is obtained;

[0262] According to the brewing record, the proportion of the second component of the brewing record is obtained;

[0263] According to the difference between the proportion of the first component and the proportion of the second component, the second weight data is obtained;

[0264] According to the first weight data and the second weight data, it is determined whether the brewing record includes the second physicochemical data matching the first physicochemical data.

[0265] Optionally, according to the first wine liquid, testing the first wine liquid to obtain a first test result includes:

[0266] According to the first wine liquid, extracting a first wine liquid to be tested from the first wine liquid;

[0267] According to the first wine liquid to be tested, a spectral analysis is performed on the first wine liquid to be tested to obtain a first detection result.

[0268] Optionally, judging whether the first liquor meets a preset quality standard according to the first test result includes:

[0269] Preprocessing the first detection result according to the first detection result;

[0270] Extracting a first feature of the first detection result based on a deep learning network according to the preprocessed first detection result;

[0271] The target encoder is used to perform hybrid parallel attention calculation on the first feature, and the calculation result is used to fuse with the residual of the first feature to obtain the second feature;

[0272] Inputting the second feature into a convolutional feedforward network, where the convolutional feedforward network is used to perform data dimension reduction to obtain a sensory feature of the first detection result;

[0273] Based on the sensory characteristics of the first test result and a preset indicator system, it is determined whether the first wine meets the preset quality standards.

[0274] Optionally, if the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and before the step of processing the target raw material according to the third process parameter, the method further includes:

[0275] An initial quality response model is established, where the initial quality response model is configured to take the original spectrum data and the target spectrum data as input and take the process parameter adjustment value as output;

[0276] Obtain historical brewing data, which includes process parameters and corresponding spectral data of the wine;

[0277] Based on historical brewing data, a data set for initial quality response model training is obtained;

[0278] The initial quality response model is trained according to the data set to obtain a quality response model.

[0279] Optionally, if the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and the preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including:

[0280] If the first liquor does not meet the preset quality standard, based on the first test result, the first test result is used as the original spectrum data, and the preset target test result is used as the target spectrum data to input into the quality response model to obtain the first process parameter adjustment value;

[0281] According to the first process parameter adjustment value, adjusting the first process parameter or the second process parameter to obtain a third process parameter;

[0282] The target raw material is processed according to the third process parameter.

[0283] Optionally, if the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and the preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including:

[0284] If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first test result and the preset quality response model to obtain a third process parameter;

[0285] Processing the raw material to be inspected according to the third process parameter to obtain a second liquor;

[0286] According to the second wine liquid, testing the second wine liquid to obtain a second test result;

[0287] According to the second test result, determining whether the second wine meets the preset quality standard;

[0288] If the second liquor does not meet the preset quality standard, the third process parameter is adjusted according to the second test result and the preset quality response model to obtain the adjusted third process parameter, and the raw material to be tested is processed according to the third process parameter to obtain a new second liquor;

[0289] If the second liquor meets the preset quality standard, the target raw material is processed according to the third process parameter.

[0290] Optionally, if the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and after the target raw material is processed according to the third process parameter, the method further includes:

[0291] The first physical and chemical data and the third process parameter are matched and stored in the brewing record.

[0292] Example 4

[0293] This embodiment provides a device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0294] Specifically, Figure 2 As shown, Figure 2This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0295] Those skilled in the art will appreciate that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0296] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing a method for controlling the quality of potato liquor.

[0297] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program stored in the memory 105 for implementing a method for controlling the quality of potato liquor through the processor 101 to implement the above method.

[0298] Example 5

[0299] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0300] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0301] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0302] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, 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 through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0303] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0304] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0305] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0306] The above are only preferred embodiments of the present disclosure. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. A method for controlling the quality of potato liquor, characterized in that: The following steps are involved: Selecting a raw material to be inspected from the target raw materials according to a preset sampling rule, and obtaining first physical and chemical data of the raw material to be inspected; According to the first physical and chemical data of the raw material to be inspected, determining whether the brewing record includes second physical and chemical data matching the first physical and chemical data; If the brewing record includes second physical and chemical data matching the first physical and chemical data, the raw material to be inspected is processed according to a first process parameter corresponding to the second physical and chemical data to obtain a first liquor; If the brewing record does not include second physical and chemical data matching the first physical and chemical data, processing the raw material to be inspected according to a preset second process parameter to obtain a first liquor; According to the first wine liquid, testing the first wine liquid to obtain a first testing result; According to the first test result, determining whether the first wine meets a preset quality standard; If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter; If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and the target raw material is processed according to the third process parameter.

2. A method for controlling the quality of potato liquor as claimed in claim 1, characterized in that: The step of judging whether the brewing record includes second physical and chemical data matching the first physical and chemical data according to the first physical and chemical data of the raw material to be inspected comprises: Obtaining a first component ratio of the raw material to be tested according to the first physical and chemical data of the raw material to be tested; Obtaining first weight data according to the proportion of the first component of the raw material to be inspected; According to the brewing record, obtaining the proportion of the second component of the brewing record; Obtaining second weight data according to a difference between the first component proportion and the second component proportion; According to the first weight data and the second weight data, it is determined whether the brewing record includes second physicochemical data matching the first physicochemical data.

3. A method for controlling the quality of potato liquor as claimed in claim 1, characterized in that: The step of testing the first wine liquid to obtain a first test result according to the first wine liquid includes: According to the first wine liquid, extracting a first wine liquid to be tested from the first wine liquid; According to the first wine liquid to be tested, a spectral analysis is performed on the first wine liquid to be tested to obtain a first detection result.

4. A method for controlling the quality of potato liquor as claimed in claim 3, characterized in that: The step of judging whether the first liquor meets a preset quality standard according to the first detection result includes: Preprocessing the first detection result according to the first detection result; Extracting a first feature of the first detection result based on a deep learning network according to the preprocessed first detection result; Using a target encoder to perform hybrid parallel attention calculation on the first feature, and using a result of the calculation to fuse with a residual of the first feature to obtain a second feature; Inputting the second feature into a convolutional feedforward network, wherein the convolutional feedforward network is used to perform data dimension reduction to obtain a sensory feature of the first detection result; Based on the sensory characteristics of the first test result and a preset indicator system, it is determined whether the first wine meets the preset quality standards.

5. A method for controlling the quality of potato liquor as claimed in claim 3, characterized in that: If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and a preset quality response model to obtain a third process parameter, and before the step of processing the target raw material according to the third process parameter, the step further includes: Establishing an initial quality response model, wherein the initial quality response model is configured to take the original spectrum data and the target spectrum data as input and take the process parameter adjustment value as output; Acquiring historical brewing data, wherein the historical brewing data includes process parameters and corresponding spectral data of wine; According to the historical brewing data, obtaining a data set for training the initial quality response model; The initial quality response model is trained according to the data set to obtain the quality response model.

6. A method for controlling the quality of potato liquor as claimed in claim 5, characterized in that: If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including: If the first liquor does not meet the preset quality standard, based on the first detection result, the first detection result is used as the original spectrum data, and the preset target detection result is used as the target spectrum data to input into the quality response model to obtain the first process parameter adjustment value; According to the first process parameter adjustment value, adjusting the first process parameter or the second process parameter to obtain a third process parameter; The target raw material is processed according to the third process parameter.

7. A method for controlling the quality of potato liquor as claimed in claim 1, characterized in that: If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter, and processing the target raw material according to the third process parameter, including: If the first liquor does not meet the preset quality standard, adjusting the first process parameter or the second process parameter according to the first detection result and a preset quality response model to obtain a third process parameter; Processing the raw material to be inspected according to the third process parameter to obtain a second liquor; According to the second wine liquid, testing the second wine liquid to obtain a second test result; According to the second test result, determining whether the second wine meets a preset quality standard; If the second wine liquid does not meet the preset quality standard, the third process parameter is adjusted according to the second test result and the preset quality response model to obtain the adjusted third process parameter, and the raw material to be tested is processed according to the third process parameter to obtain a new second wine liquid; If the second wine liquid meets the preset quality standard, the target raw material is processed according to the third process parameter.

8. The method for controlling the quality of potato liquor according to claim 1, characterized in that: If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and a preset quality response model to obtain a third process parameter, and after the target raw material is processed according to the third process parameter, the method further includes: The first physical and chemical data and the third process parameter are matched and stored in the brewing record.

9. A potato liquor quality control system, characterized in that: Including raw material management platform and brewing management platform; The raw material management platform is configured as follows: Selecting a raw material to be inspected from the target raw materials according to a preset sampling rule, and obtaining first physical and chemical data of the raw material to be inspected; The brewing management platform is configured to: According to the first physical and chemical data of the raw material to be inspected, determining whether the brewing record includes second physical and chemical data matching the first physical and chemical data; If the brewing record includes second physical and chemical data matching the first physical and chemical data, the raw material to be inspected is processed according to a first process parameter corresponding to the second physical and chemical data to obtain a first liquor; If the brewing record does not include second physical and chemical data matching the first physical and chemical data, processing the raw material to be inspected according to a preset second process parameter to obtain a first liquor; According to the first wine liquid, testing the first wine liquid to obtain a first testing result; According to the first test result, determining whether the first wine meets a preset quality standard; If the first liquor meets the preset quality standard, the target raw material is processed according to the first process parameter or the second process parameter; If the first liquor does not meet the preset quality standard, the first process parameter or the second process parameter is adjusted according to the first detection result and the preset quality response model to obtain a third process parameter, and the target raw material is processed according to the third process parameter.

10. A device, characterized in that: The device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 8.

Images