Non-destructive detection system for livestock and poultry meat quality based on near infrared spectrum technology

Abstract

The invention belongs to the technical field of livestock and poultry meat quality detection, and provides a livestock and poultry meat quality non-destructive detection system based on a near infrared spectrum technology, which comprises a near infrared spectrum acquisition module, a data preprocessing module, a model establishment module, a quality detection module and a result display module, spectral data of livestock and poultry meat samples are rapidly collected through the near infrared spectrum collection module, the spectral data are optimized through the data preprocessing module, noise interference is effectively reduced, and the data quality is improved; then, a model establishing module establishes a multivariate correction model based on the preprocessed spectral data and known livestock and poultry meat quality index data, and the model can accurately predict various quality indexes of livestock and poultry meat; and the quality detection module inputs spectral data of a sample to be detected into the model for prediction and outputs a result in real time, so that rapid and nondestructive detection of the quality of the livestock and poultry meat is realized.

Description

Technical Field

[0001] The invention belongs to the technical field of livestock and poultry meat quality detection, in particular to a livestock and poultry meat quality non-destructive detection system based on near infrared spectroscopy technology. Background Art

[0002] In traditional livestock and poultry meat quality testing, chemical analysis methods are usually used, such as the Kjeldahl method for determining protein content and the Soxhlet extraction method for determining fat content. Although these methods are accurate, they are destructive, require a lot of time and reagents, and cannot be used to test the same meat sample multiple times. In addition, these methods usually need to be carried out in a laboratory environment, which is not conducive to rapid testing at livestock and poultry meat processing or storage sites.

[0003] With the advancement of science and technology, some non-destructive testing technologies have begun to be applied to livestock and poultry meat quality testing, such as machine vision, electronic nose, etc. However, these technologies can often only detect surface features such as the appearance or smell of livestock and poultry meat, and cannot accurately reflect its internal quality indicators.

[0004] In recent years, near-infrared spectroscopy has been widely used in agriculture, food and other fields due to its advantages such as rapidity, non-destructiveness and simultaneous detection of multiple components. However, there are still some problems when it is applied to livestock and poultry meat quality detection, such as spectral data is easily affected by noise and the accuracy of model prediction needs to be improved.

[0005] To this end, those skilled in the art have proposed a non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology to solve the problems raised by the background technology. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology, so as to solve some problems that still exist in the prior art when near-infrared spectroscopy technology is applied to livestock and poultry meat quality detection, such as spectral data is easily affected by noise and the accuracy of model prediction needs to be improved.

[0007] The non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology includes:

[0008] A near-infrared spectrum acquisition module is used to collect the reflection or transmission spectrum data of livestock and poultry meat samples within the near-infrared spectrum range;

[0009] The data preprocessing module is used to perform preprocessing operations such as smoothing, differentiation, and multiplicative scatter correction on the collected spectral data to improve the quality of the spectral data;

[0010] A model building module, used to build a multivariate calibration model based on preprocessed spectral data and known livestock and poultry meat quality index data;

[0011] The quality detection module is used to input the spectral data of the livestock and poultry meat samples to be tested into the established model, predict and output the quality indicators of the livestock and poultry meat, including but not limited to moisture content, protein content, fat content, volatile basic nitrogen content, pH value, etc.;

[0012] The result display module is used to visually display the detected livestock and poultry meat quality indicators.

[0013] Preferably, the near-infrared spectrum acquisition module includes a stable light source, a high-precision spectroscopic system, a high-sensitivity detector, and a fiber optic probe or an integrating sphere accessory to accommodate livestock and poultry meat samples of different shapes and sizes.

[0014] Preferably, the smoothing operation in the data preprocessing module adopts a Gaussian filtering algorithm to reduce noise and retain important features.

[0015] Preferably, the data preprocessing module also includes an outlier detection and removal function to ensure the accuracy and reliability of the spectral data used for model building, and the outlier detection and removal function detects and removes outliers in the spectral data by introducing the Z-score algorithm in statistics.

[0016] Preferably, the multivariate correction model adopts a support vector machine regression model.

[0017] Preferably, the model building module also includes a model optimization function, which adjusts the model parameters through a regularization algorithm to improve the prediction accuracy and stability of the model. The regularization algorithm introduces L1 and L2 regularization terms during the model training process to prevent overfitting and improve the generalization ability of the model.

[0018] Preferably, the quality detection module also includes a real-time online detection function, which can collect spectral data in real time and perform quality prediction during the processing or storage of livestock and poultry meat. The real-time online detection function uses a recursive least squares (RLS) algorithm to update model parameters online to adapt to changes in real-time collected data.

[0019] A processor is configured to execute the above-mentioned non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology.

[0020] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. The present invention can realize the rapid collection of reflection or transmission spectrum data of livestock and poultry meat samples within the near-infrared spectrum range through a near-infrared spectrum acquisition module, providing a reliable data basis for subsequent quality inspection; at the same time, the module also includes a stable light source, a high-precision spectroscopic system, a high-sensitivity detector, and an optical fiber probe or an integrating sphere accessory to adapt to livestock and poultry meat samples of different shapes and sizes, thereby improving the applicability and flexibility of the system.

[0023] 2. The present invention uses a data preprocessing module to perform preprocessing operations such as smoothing, differentiation, and multiplicative scatter correction on the collected spectral data, which effectively reduces noise interference and improves the quality of spectral data; in addition, the module also includes outlier detection and removal functions to ensure the accuracy and reliability of the spectral data used for model establishment.

[0024] 3. The present invention establishes a multivariate calibration model based on the preprocessed spectral data and known livestock and poultry meat quality index data through a model building module; the model can accurately predict the quality indicators of livestock and poultry meat, including but not limited to moisture content, protein content, fat content, volatile basic nitrogen content, pH value, etc., providing strong support for the rapid detection of livestock and poultry meat quality.

[0025] 4. The present invention uses a quality detection module to input the spectral data of the livestock and poultry meat samples to be tested into the established model, which can predict and output the quality indicators of livestock and poultry meat in real time, thereby realizing rapid and non-destructive detection of the quality of livestock and poultry meat. At the same time, the module also includes a real-time online detection function, which can collect spectral data in real time and make quality predictions during the processing or storage of livestock and poultry meat, thus providing important guarantees for the production and quality control of livestock and poultry meat. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a framework diagram of the non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology of the present invention. DETAILED DESCRIPTION

[0027] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0028] Embodiment: The present invention provides a non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology, such as Figure 1 As shown, it includes a near-infrared spectrum acquisition module, a data preprocessing module, a model building module, a quality detection module and a result display module, and the near-infrared spectrum acquisition module, the data preprocessing module, the model building module, the quality detection module and the result display module are electrically connected in sequence:

[0029] A near-infrared spectrum acquisition module is used to collect the reflection or transmission spectrum data of livestock and poultry meat samples within the near-infrared spectrum range;

[0030] The data preprocessing module is used to perform preprocessing operations such as smoothing, differentiation, and multiplicative scatter correction on the collected spectral data to improve the quality of the spectral data;

[0031] A model building module, used to build a multivariate calibration model based on preprocessed spectral data and known livestock and poultry meat quality index data;

[0032] The quality detection module is used to input the spectral data of the livestock and poultry meat samples to be tested into the established model, predict and output the quality indicators of the livestock and poultry meat, including but not limited to moisture content, protein content, fat content, volatile basic nitrogen content, pH value, etc.;

[0033] The result display module is used to visually display the detected livestock and poultry meat quality indicators.

[0034] As can be seen from the above, the system quickly collects the spectral data of livestock and poultry meat samples through the near-infrared spectral acquisition module, and uses the data preprocessing module to optimize the spectral data, effectively reducing noise interference and improving data quality. Then, the model building module establishes a multivariate correction model based on the preprocessed spectral data and the known livestock and poultry meat quality index data. The model can accurately predict the various quality indicators of livestock and poultry meat. The quality detection module inputs the spectral data of the sample to be tested into the model for prediction, and outputs the results in real time, realizing rapid and non-destructive detection of livestock and poultry meat quality. Finally, the result display module intuitively displays the detected quality indicators, which is convenient for the staff to understand and grasp the quality status of livestock and poultry meat in a timely manner. The entire system is easy to operate, accurate in detection, and widely applicable, providing important guarantees for the production and quality control of livestock and poultry meat.

[0035] Furthermore, the near-infrared spectrum acquisition module includes a stable light source, a high-precision spectroscopic system, a high-sensitivity detector, and an optical fiber probe or an integrating sphere accessory to accommodate livestock and poultry meat samples of different shapes and sizes.

[0036] Furthermore, the smoothing operation in the data preprocessing module adopts a Gaussian filtering algorithm to reduce noise and retain important features. The formula of the Gaussian filtering algorithm includes:

[0037]

[0038] Where f(x,y) is the original spectral data, g(x,y) is the smoothed data, and σ is the standard deviation of the Gaussian kernel.

[0039] From the above, we can see that the beneficial effect of using Gaussian filtering algorithm for smoothing operation in the data preprocessing module is that it can effectively reduce the noise interference in the spectral data while retaining the important feature information in the data. σ The degree of smoothing can be flexibly controlled, thereby improving data quality while ensuring the accuracy and reliability of subsequent model establishment. This operation is of great significance for improving the accuracy and stability of the entire livestock and poultry meat quality detection system.

[0040] Furthermore, the data preprocessing module also includes an outlier detection and removal function to ensure the accuracy and reliability of the spectral data used for model building. The outlier detection and removal function detects and removes outliers in the spectral data by introducing the Z-score algorithm in statistics. The formula of the Z-score algorithm includes:

[0041]

[0042] Among them, X is the observation value, μ is the mean, and σ is the standard deviation; when |Z| exceeds a certain threshold, the observation value is considered to be an outlier.

[0043] As can be seen from the above, the beneficial effect of introducing the Z-score algorithm for outlier detection and elimination in the data preprocessing module is that it can accurately identify and exclude outliers in spectral data, thereby ensuring that the data set used for model building is purer and more reliable. This function is crucial to improving the accuracy and robustness of livestock and poultry meat quality detection systems, helping to reduce misjudgments and missed judgments, and improving the detection performance and practical value of the entire system.

[0044] Furthermore, the multivariate correction model adopts a support vector machine regression model, and the algorithm formula of the support vector machine regression model includes:

[0045]

[0046] in, is the predicted value, α i is the Lagrange multiplier, K(x i ,x) is the kernel function and b is the bias term.

[0047] From the above, it can be seen that the multivariate correction model adopts the support vector machine regression model, which can make full use of the complex nonlinear relationship between spectral data and livestock and poultry meat quality indicators to achieve high-precision prediction and classification. The support vector machine regression model maps the input data to a high-dimensional space by introducing a kernel function, thereby finding the optimal decision boundary and improving the generalization ability and prediction accuracy of the model. It is crucial for the livestock and poultry meat quality detection system. It can better adapt to livestock and poultry meat samples of different types and qualities, and provide strong support for quality control and food safety assurance in the production process.

[0048] Furthermore, the model building module also includes a model optimization function, which adjusts the model parameters through a regularization algorithm to improve the prediction accuracy and stability of the model. The regularization algorithm introduces L1 and L2 regularization terms in the model training process to prevent overfitting and improve the generalization ability of the model. The L1 regularization formula is: Add λ∑ j |w j |, where w j is the model parameter, λ is the regularization coefficient; L2 regularization formula: add in the loss function

[0049] From the above, it can be seen that the introduction of regularization algorithm in the model building module for model optimization can significantly improve the prediction accuracy and stability of the livestock and poultry meat quality detection model. By introducing L1 and L2 regularization terms, the model parameters can be effectively constrained to prevent the model from overfitting during the training process, thereby improving the generalization ability of the model. It is of great significance to ensure the long-term stable operation and accurate prediction of the livestock and poultry meat quality detection system, and help provide more reliable technical support for meat production and quality control.

[0050] Furthermore, the quality detection module also includes a real-time online detection function, which can collect spectral data in real time and perform quality prediction during the processing or storage of livestock and poultry meat. The real-time online detection function uses a recursive least squares (RLS) algorithm to update model parameters online to adapt to changes in real-time collected data. The formula of the recursive least squares (RLS) algorithm includes:

[0051]

[0052] θ(k)=θ(k-1)+P(k)x(k)[d(k)-x T (k)θ(k-1)];

[0053] Where P(k) is the covariance matrix, θ(k) is the weight vector, x(k) is the input data, d(k) is the expected output, and λ is the forgetting factor.

[0054] As can be seen from the above, the quality inspection module introduces real-time online detection function and uses the recursive least squares (RLS) algorithm to update the model parameters online. It can realize real-time monitoring and prediction of the quality of livestock and poultry meat during processing or storage, so as to timely discover and deal with quality problems. By updating the model parameters online, it can ensure that the quality inspection model is always synchronized with the real-time collected data, improving the adaptability and accuracy of the model. It is of great significance to ensure the quality and safety of meat products, help reduce the occurrence of quality problems, and improve the production efficiency and market competitiveness of enterprises.

[0055] Furthermore, the effects of the livestock and poultry meat quality non-destructive detection system based on near infrared spectroscopy technology of the embodiment and the traditional livestock and poultry meat quality detection method (comparative example) were compared to obtain the following table:

[0056]

[0057]

[0058] As can be seen from the table above, the non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology has significant advantages over traditional livestock and poultry meat quality detection methods, including non-destructive, rapid, multi-component simultaneous detection, high data quality, real-time online detection, convenient operation and wide application range. These advantages make the system have higher application value in the production and quality control of livestock and poultry meat.

[0059] Working principle: By integrating near-infrared spectroscopy acquisition, data preprocessing, model building, quality detection and result display modules, the system realizes rapid, non-destructive and high-precision detection of livestock and poultry meat quality. In particular, by using Gaussian filtering algorithm for smoothing, Z-score algorithm for outlier detection, support vector machine regression model to establish multivariate correction model, regularization algorithm to optimize model parameters and recursive least squares algorithm to realize online detection and other functions, the system significantly improves the accuracy and stability of detection, provides strong technical support for the production and quality control of livestock and poultry meat, helps to ensure the quality and safety of meat products, and improves the production efficiency and market competitiveness of enterprises.

[0060] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology, including:

[0061] Memory, used to protect computer programs and data;

[0062] Processor, used to run system programs.

[0063] The embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0064] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0065] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0066] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0067] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0068] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0069] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0070] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0071] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0072] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology, characterized in that: include: A near-infrared spectrum acquisition module is used to collect the reflection or transmission spectrum data of livestock and poultry meat samples within the near-infrared spectrum range; The data preprocessing module is used to perform smoothing, differentiation, and multiplicative scatter correction operations on the collected spectral data; A model building module, used to build a multivariate calibration model based on preprocessed spectral data and known livestock and poultry meat quality index data; The quality detection module is used to input the spectral data of the livestock and poultry meat samples to be tested into the established model, and predict and output the quality indicators of the livestock and poultry meat; The result display module is used to visually display the detected livestock and poultry meat quality indicators.

2. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The near-infrared spectrum acquisition module includes a stable light source, a high-precision spectroscopic system, a high-sensitivity detector, and an optical fiber probe or an integrating sphere accessory.

3. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The smoothing operation in the data preprocessing module adopts Gaussian filtering algorithm.

4. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The data preprocessing module also includes an outlier detection and removal function, which detects and removes outliers in spectral data by introducing a Z-score algorithm in statistics.

5. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The multivariate correction model adopts a support vector machine regression model.

6. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The model building module also includes a model optimization function, which adjusts the model parameters through a regularization algorithm. The regularization algorithm introduces L1 and L2 regularization terms during the model training process.

7. The non-destructive detection system for livestock and poultry meat quality based on near infrared spectroscopy technology as claimed in claim 1, characterized in that: The quality detection module also includes a real-time online detection function, which can collect spectral data in real time and perform quality prediction during the processing or storage of livestock and poultry meat. The real-time online detection function uses a recursive least squares algorithm to update model parameters online.

8. A processor, characterized in that: The system is configured to implement a non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the non-destructive detection system for livestock and poultry meat quality based on near-infrared spectroscopy technology as described in any one of claims 1 to 7 is implemented.

Images