Edible oil rancidity degree rapid detection system based on electrochemical sensor

Abstract

The invention relates to the technical field of electrochemical detection and food quality safety, and particularly discloses an edible oil rancidity degree rapid detection system based on an electrochemical sensor, comprising: a data acquisition module for receiving an original electrochemical response signal and performing format standardization, abnormal data rejection and integrity verification; the data preprocessing module adopts a statistical optimization algorithm to reduce noise, correct baseline drift, generate a unified dimension data set and complete stability verification; the feature analysis module is used for extracting rancidity related feature parameters through statistical correlation analysis, and carrying out fusion calculation after significance verification to obtain feature values representing rancidity; and the evaluation and judgment module inputs the characteristic value into a pre-training model, outputs a quantitative index through multivariate statistical calculation, dynamically sets a safety threshold in combination with the edible oil type, and outputs a rancidity judgment conclusion after comparison. The method depends on statistical data processing and analysis, the detection reliability and accuracy are improved, and the method is suitable for edible oil quality safety rapid screening and quality monitoring.

Description

Technical Field

[0001] This invention relates to the field of electrochemical detection and food quality and safety technology, and more specifically, to a rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor. Background Technology

[0002] Edible oil, an indispensable food ingredient in daily life, has its quality and safety directly related to human health. During storage, processing, and use, oils are susceptible to oxidation and hydrolysis reactions due to factors such as light, oxygen, temperature, and moisture, leading to rancidity. Rancid edible oil not only produces an unpleasant rancid taste and reduces food quality, but also generates harmful substances such as peroxides, aldehydes, and ketones. Long-term consumption of these substances increases the risk of cardiovascular disease, cancer, and other health problems. Therefore, rapid and accurate detection of the degree of rancidity in edible oils is crucial.

[0003] Currently, the detection of rancidity in edible oils mainly relies on chromatographic and spectroscopic analysis and electrochemical detection methods. Chromatographic and spectroscopic analysis methods include high-performance liquid chromatography, gas chromatography, and near-infrared spectroscopy; chromatography can accurately separate and quantify specific rancid products with high sensitivity, while near-infrared spectroscopy enables non-destructive and rapid detection. Electrochemical detection methods are based on the detection of response signals of electroactive substances in edible oils using electrochemical sensors. A typical implementation of this method involves applying specific electrical excitation to the oil sample using a working electrode and detecting the resulting current or impedance response signal, thereby establishing a correlation model between signal characteristic values ​​and acid value or peroxide value indicators. The advantages of this method are its fast detection speed, small and portable equipment, and the potential for rapid on-site screening.

[0004] However, these methods still have some drawbacks in practical use: 1. Significant limitations in detection conditions: Although chromatographic and spectroscopic analysis methods have high detection accuracy, they are heavily dependent on large precision instruments and professional laboratory environments. The purchase and maintenance costs of such equipment are high, making it difficult to deploy and use them in on-site environments such as production lines and kitchens, and thus failing to achieve truly rapid on-site detection.

[0005] 2. Insufficient model robustness: Existing electrochemical detection methods typically employ simple mapping models between a single electrical parameter and rancidity indicators. Due to the significant differences in matrix composition among different types of edible oils, and the diverse electroactive substances produced during the rancidity process, these models exhibit poor generalization ability and a significant decrease in prediction accuracy when faced with unknown or complex oil samples.

[0006] 3. Insufficient anti-interference capability: Electrochemical signals are easily interfered with by environmental factors such as temperature fluctuations, electrode surface contamination, and moisture content in the sample. Existing technologies lack effective signal preprocessing and feature optimization algorithms, resulting in poor stability and repeatability of detection results, thus affecting the reliability of the method.

[0007] 4. Limited level of intelligence: Existing electrochemical solutions typically only output single indicators such as acid value or peroxide value, failing to achieve multi-indicator collaborative analysis and comprehensive decision-making. When the test results of various indicators contradict each other, the system cannot automatically provide a clear final judgment, still requiring manual interpretation, thus failing to achieve automation and intelligence throughout the entire detection process. Summary of the Invention

[0008] To overcome the aforementioned deficiencies of the prior art, the present invention provides a rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor, which solves the problems mentioned in the background art through the following solutions.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor, comprising: The data acquisition module is used to receive the raw electrochemical response signal of the edible oil sample output by the electrochemical sensor, perform format standardization processing on the signal, remove abnormal data through statistical rules, and verify the integrity. The data preprocessing module is used to reduce noise and correct baseline drift of the received data using statistical optimization algorithms, generate a dataset with uniform dimensions after standardization, and transmit it to the feature analysis module after stability verification. The feature analysis module is used to extract rancidity-related feature parameters from the dataset through statistical correlation analysis. After significance verification, the parameters are fused using numerical calculation methods to obtain feature values ​​that characterize the degree of rancidity. The evaluation and judgment module is used to input feature values ​​into a pre-trained rancidity index prediction model, output quantitative indicators through multivariate statistical calculations, dynamically set safety thresholds based on the type of edible oil, and output rancidity judgment conclusions after comparison.

[0010] Preferably, the raw electrochemical response signal received by the data acquisition module is one of the following: voltammetric curve, impedance spectrum, or current time series, and each signal must meet the statistical sampling requirements.

[0011] Preferably, the current-voltage curve is a differential pulse current-voltage curve or a square wave pulse current-voltage curve, and the signal quality of the two types of curves needs to be verified by statistical methods.

[0012] Preferably, the preprocessing includes the following steps: S1: Noise reduction using a filtering algorithm based on signal statistical characteristics; S2: Eliminate drift by employing a statistical correction algorithm based on baseline drift patterns; S3: Transform the processed data into a dataset with uniform dimensions using a standardization algorithm.

[0013] Preferably, the feature parameters related to rancidity extracted by the feature analysis module need to be confirmed through statistical correlation analysis and then validated through statistical significance test.

[0014] Preferably, the feature analysis module uses one of the following numerical calculation methods: principal component analysis, partial least squares regression, or support vector regression, and each method must be combined with statistical optimization logic.

[0015] Preferably, the rancidity index prediction model of the evaluation and judgment module is learned by machine learning algorithm on a statistically representative training dataset, which contains multiple sets of feature values ​​and corresponding standard acid value and peroxide value labels.

[0016] Preferably, the quantitative indicators output by the evaluation and judgment module are acid value and peroxide value, and the accuracy of the indicators needs to be verified by statistical methods.

[0017] Preferably, the preset safety threshold of the assessment and judgment module needs to be dynamically set by combining the national standard limit for the type of edible oil and referring to the statistical distribution of historical test data of that type of oil sample.

[0018] Preferably, the relationship between quantitative indicators and thresholds is analyzed through a statistical model. If the acid value or peroxide value exceeds the statistical judgment standard of the corresponding threshold, the result is "rancid"; if neither indicator exceeds the threshold, the result is "not rancid".

[0019] The technical effects and advantages of this invention are as follows: 1. Achieve rapid and accurate on-site detection: This invention utilizes a portable electrochemical sensor and intelligent processing system, overcoming the challenges of deploying large instruments on-site. The sensor scan is controlled by a signal acquisition module, completing detection within minutes. No complex pretreatment or toxic reagents are required, enabling rapid and accurate detection in production lines, kitchens, and other on-site environments.

[0020] 2. Improve model robustness and accuracy: A combination of multi-dimensional feature extraction and machine learning algorithms is adopted. The feature extraction module extracts multiple types of feature parameters from the dataset, and the parameter calculation module uses multivariate statistical methods to build a prediction model, effectively overcoming the influence of differences in different edible oil matrices.

[0021] 3. Enhanced anti-interference capability and reliability: The signal preprocessing module addresses the issue of signal susceptibility to interference. Digital filtering for noise reduction, baseline correction to eliminate drift, and data standardization significantly improve signal quality and stability, ensuring the reproducibility of detection results.

[0022] 4. Achieve Intelligent Integrated Decision-Making: The evaluation output module enables multi-indicator collaborative analysis and automated decision-making. The system synchronously outputs acid value and peroxide value, automatically compares them based on dynamic safety thresholds, and directly outputs clear conclusions, avoiding human error and achieving full-process automation and intelligence. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the modular structure of the system of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] refer to Figure 1 The system shown is a rapid detection system for the rancidity of edible oil based on an electrochemical sensor, comprising: The data acquisition module is used to receive the raw electrochemical response signal of the edible oil sample output by the electrochemical sensor, perform format standardization processing on the signal, remove abnormal data through statistical rules, and verify the integrity. The data preprocessing module is used to reduce noise and correct baseline drift of the received data using statistical optimization algorithms, generate a dataset with uniform dimensions after standardization, and transmit it to the feature analysis module after stability verification. The feature analysis module is used to extract rancidity-related feature parameters from the dataset through statistical correlation analysis. After significance verification, the parameters are fused using numerical calculation methods to obtain feature values ​​that characterize the degree of rancidity. The evaluation and judgment module is used to input feature values ​​into a pre-trained rancidity index prediction model, output quantitative indicators through multivariate statistical calculations, dynamically set safety thresholds based on the type of edible oil, and output rancidity judgment conclusions after comparison.

[0026] The data acquisition module is used to receive the original electrochemical response signal of the edible oil sample output by the electrochemical sensor, perform format standardization processing on the signal, remove abnormal data through statistical rules, and verify the integrity.

[0027] The data acquisition module serves as the direct interface between the system and the electrochemical sensor hardware, responsible for acquiring the raw signals and ensuring their quality meets the requirements of subsequent statistical analysis. The physical components of the data acquisition module include: a signal input interface, an embedded processor, a cache memory, and a communication unit. The data acquisition module utilizes algorithms to perform data normalization, anomaly removal, and integrity verification. The specific steps are as follows: 1. Signal reception and format standardization The volt-ampere curve signal output by the electrochemical sensor is converted into a digital signal by a multi-channel analog-to-digital converter via the signal input interface at a sampling rate of not less than 100 kS / s. Preferably, the volt-ampere curve is a differential pulse volt-ampere curve; alternatively, the volt-ampere curve is a square wave volt-ampere curve.

[0028] Embedded processors process digital signals, extract voltage-current data pairs, and convert them into a standardized data format.

[0029] The standardized data is temporarily stored in a cache memory via direct memory access for subsequent statistical processing.

[0030] 2. Outlier removal based on statistical rules 2.1 Anomaly Detection Algorithm: Embedded processor calculates the arithmetic mean of data segments. and standard deviation ,application Criteria Exceeding Anomalies within a range refer to data segments, which are short periods or small subsets of data points extracted from the continuous digital signal of the volt-ampere curve by the embedded processor for independent analysis. For the volt-ampere curve, the number and location of redox peaks are verified using a peak detection algorithm running on the embedded processor, eliminating peakless or multi-peaked abnormal curves. Differential pulse volt-ampere curves should exhibit a single characteristic peak.

[0031] 2.2 Statistical Sampling Requirements: To ensure statistical significance, the voltage scan range of the voltammetry curve must cover the typical redox window, with a voltage scan range of -0.5 V to +1.0 V and a minimum of 500 scan points. All intermediate data during processing are stored in a buffer memory.

[0032] 3. Data integrity verification Data integrity verification is performed by the embedded processor and includes: 3.1 Data length verification: Check whether the number of data points of the voltammetric curve has reached the minimum threshold of 500 points. If it is insufficient, send a command to the electrochemical sensor through the communication unit to trigger re-acquisition. 3.2 Timestamp continuity check: Ensure that the sampling interval is uniform and avoid timestamp breaks that could cause sequence analysis failure.

[0033] Data that passes verification is appended with metadata tags by the embedded processor, including signal quality scores, verification status codes, etc., and then transferred to the output queue area of ​​the cache memory.

[0034] 4. Data is transmitted to the data preprocessing module. The communication unit reads data packets from the output queue of the buffer memory and sends the data packets to the data preprocessing module.

[0035] The data acquisition module significantly improves the quality of the original signal through statistical rule-driven anomaly removal and integrity verification, providing a highly reliable data foundation for subsequent rancidity characteristic analysis.

[0036] The data preprocessing module is used to reduce noise and correct baseline drift of the received data using statistical optimization algorithms, generate a dataset with uniform dimensions after standardization, and transmit it to the feature analysis module after stability verification.

[0037] The data preprocessing module is the core processing unit of the system, responsible for deep processing of the raw data transmitted by the acquisition module, providing a high-quality data foundation for subsequent feature extraction. The physical components of the data preprocessing module include: a data receiving interface, a digital signal processor, an algorithm processing unit, and a data storage unit. The data preprocessing module uses multi-level processing algorithms to achieve data noise reduction, baseline drift correction, and the generation of a dataset with uniform dimensions. The specific steps are as follows: 1. Statistical characteristic-based filtering and noise reduction processing The data receiving interface acquires standardized data packets from the data acquisition module and transmits them to the input buffer of the digital signal processor (DSP) via direct memory access. The DSP employs wavelet thresholding for noise reduction, performing multi-scale decomposition on the volt-ampere curve signal: a 5-level decomposition using Symlets wavelet basis functions; and adaptive thresholding is applied to the detail coefficients of each level. The threshold calculation formula is as follows: ,in, The noise standard deviation refers to the value obtained by statistically estimating the high-frequency detail coefficients of the first layer after wavelet decomposition. The data length is the total number of sampling points for the volt-ampere curve signal; the reconstructed signal yields the denoised data. The processed data is temporarily stored in a dedicated buffer area of ​​the data storage unit and marked with a processing status flag.

[0038] 2. Baseline drift statistical correction The algorithm processing unit uses an adaptive iterative reweighted penalized least squares method to perform baseline correction on the volt-ampere curve signal: the baseline drift pattern is estimated through statistical methods, and an objective function is constructed. ,in, For the first The original current values ​​of each data point For the first Baseline current estimates for each data point No. The weight of each data point For regularization parameters, for The second reciprocal, the formula is: The baseline curvature is used to solve for the optimal baseline current estimate using an iterative algorithm. The baseline component is subtracted from the original signal to obtain the corrected signal. During the correction process, the algorithm processing unit calculates the baseline parameters of each data segment in parallel, and the processing results are stored in real time to the data storage unit.

[0039] 3. Data standardization and unit unification The digital signal processor performs normalization processing: using the Z-score normalization algorithm. ,in, This is the arithmetic mean of all current values ​​along the entire volt-ampere curve. The standard deviation of all current values ​​on the entire volt-ampere curve. This represents a single original current value on the current-voltage curve. The standardized new current value is a dimensionless numerical value; for the volt-ampere curve, maximum-minimum normalization is used to transform each feature to the [0,1] interval; the current signal is uniformly converted to μA units, and the voltage signal is uniformly converted to V units. After generating the dataset with uniform dimensions, a stability check is performed: the coefficient of variation (CV) of the dataset is calculated. ,in, It is the standard deviation of the dataset. It is the arithmetic mean of the dataset. To verify the stability of the data, the CV should be less than 0.05.

[0040] 4. Data is transmitted to the feature analysis module. After preprocessing, the data receiving interface transmits the processed volt-ampere curve dataset to the feature analysis module.

[0041] The preprocessing module achieves efficient data purification and standardization through statistical optimization algorithms, providing a reliable data foundation for subsequent rancidity characteristic analysis.

[0042] The feature analysis module is used to extract feature parameters related to rancidity from the dataset through statistical correlation analysis. After significance verification, the parameters are fused using numerical calculation methods to obtain feature values ​​that characterize the degree of rancidity.

[0043] The feature analysis module is the core of the system's intelligent analysis. Its physical components include a data interface unit, a feature extraction unit, a statistical analysis unit, and a feature database. It is responsible for extracting rancidity-related feature parameters from the preprocessed voltammetric curve data, verifying their effectiveness through statistical methods, and finally using numerical calculation methods to fuse and generate feature values ​​characterizing the degree of rancidity. The specific steps are as follows: 1. Extraction of characteristic parameters from the volt-ampere curve The data interface unit receives the standardized voltammetric curve dataset from the data preprocessing module and transmits it to the memory buffer of the feature extraction unit via direct memory access. Then, feature parameters of the voltammetric curves are extracted, including electrochemical features such as oxidation peak current, reduction peak current, peak potential difference, and full width at half maximum (FWHM); morphological features such as curve slope, curvature change, and peak symmetry index; and integral features such as oxidation peak area, reduction peak area, and peak area ratio. All feature parameters are temporarily stored in a temporary area of ​​the feature database, awaiting further verification.

[0044] 2. Statistical correlation analysis and significance verification The statistical analysis unit performs the following verification process: 2.1 Statistical Correlation Analysis: The Pearson correlation coefficient method was used to analyze the correlation between each characteristic parameter and the standard acid value and peroxide value. The calculation formula is as follows: ,in, Total number of samples, i.e., the number of edible oil samples that are tested and simultaneously possess characteristic parameters and standard chemical values; For the first The value of a certain characteristic parameter of an edible oil sample, such as the oxidation peak current value, peak area, etc. of the sample; For all The arithmetic mean of the values ​​of the same characteristic parameter of each sample; For the first The true acid value or peroxide value of each edible oil sample was determined using standard chemical methods. For all The arithmetic mean of the acid value or peroxide value of each sample; after calculation, retain the characteristic parameter |r|>0.7.

[0045] 2.2 Statistical significance test: The significance of the characteristic parameter is verified using a t-test. , The requirement is p < 0.05 to ensure that the characteristic parameters can effectively reflect changes in the degree of rancidity.

[0046] The validated feature parameters are marked by the statistical analysis unit and transferred to the validated area of ​​the feature database.

[0047] 3. Feature fusion based on partial least squares regression The feature extraction unit uses partial least squares regression for feature fusion. 3.1 Model Establishment: Establishing the Characteristic Parameter Matrix of the Volt-Ampere Curve With rancidity index matrix Regression model between: , in, and For the score matrix, and For the load matrix, and Let be the residual matrix.

[0048] 3.2 Latent Variable Extraction: Latent variables are extracted using a nonlinear iterative partial least squares algorithm to maximize... and The covariance between them.

[0049] 3.3 Statistical optimization: Leave-one-out cross-validation is used to determine the optimal number of latent variables to avoid overfitting.

[0050] 3.4 Prediction Model: Establishing the Regression Equation: , in, The regression coefficient matrix, This is the intercept term.

[0051] Statistical optimization logic ensures the reliability and stability of eigenvalue calculations. All model parameters and intermediate calculation results are stored in the feature database.

[0052] 4. Eigenvalue Output and Transmission The fused feature values ​​are transmitted to the evaluation and judgment module through the data interface unit.

[0053] The feature analysis module employs partial least squares regression for feature fusion, taking into account the characteristics of the voltammetric curve signal. This method considers both the correlation between feature parameters and rancidity indicators, and improves the reliability of feature value calculation through statistical optimization logic. This approach is particularly suitable for handling multicollinearity in voltammetric curve data, effectively extracting the most predictive feature combinations.

[0054] The evaluation and judgment module is used to input feature values ​​into a pre-trained rancidity index prediction model, output quantitative indicators through multivariate statistical calculations, dynamically set safety thresholds in combination with edible oil types, and output rancidity judgment conclusions after comparison.

[0055] The evaluation and judgment module is the decision center of the system. Its physical components include a data receiving unit, a model calculation unit, a threshold management unit, and a result display unit. It is responsible for converting the feature values ​​output by the feature analysis module into specific rancidity indicators and making a final judgment based on dynamic safety thresholds. The specific steps are as follows: 1. Loading and Calculation of Rancidity Index Prediction Model The data receiving unit receives the fused feature value data packet from the feature analysis module, decrypts and verifies it, and then transmits it to the model calculation unit.

[0056] The model computation unit loads a pre-trained rancidity index prediction model: ,in, For the input feature vector, Forecasting indicator: acid value and peroxide value .

[0057] A multivariate statistical method was used to simultaneously calculate two indicators: acid value and peroxide value. , in, For the first time, after significance and correlation are used in the model The characteristic parameter values ​​of each edible oil sample It is the first in the acid value prediction model One feature parameter The regression coefficients, It is the first in the peroxide value prediction model One feature parameter The regression coefficients, and These are the intercept terms of the acid value prediction model and the peroxide value prediction model, respectively.

[0058] 2. Dynamic security threshold setting The threshold management unit dynamically sets safety thresholds based on the type of edible oil: it accesses the built-in national standard database to obtain the standard limits for that type of oil; and it references the statistical distribution of historical test data for that type of oil: the arithmetic mean. and standard deviation ,use The principle is to dynamically adjust the threshold: , Where k is an adjustment coefficient, which is dynamically selected between 2.0 and 3.0 according to the characteristics of the oil.

[0059] 3. Indicator Comparison and Result Judgment The calculated acid value and peroxide value were statistically compared with the corresponding dynamic thresholds: Statistical determination is made using hypothesis testing methods: ,in, for The arithmetic mean of the measurements of secondary acid value or peroxide value. The standard acid value or peroxide value is the safe threshold. This represents the standard deviation of the acid value or peroxide value measurement results. The number of times the measurement was repeated.

[0060] Judgment rules: If either the acid value or the peroxide value exceeds the statistical criteria for its corresponding threshold, then the following conditions are met. If so, it is determined to be rancid; If both acid value and peroxide value do not exceed the threshold criteria, then the following conditions are met. If it is not rancid, it is determined that it has not spoiled.

[0061] 4. Results Output and Display The results show the unit output detection results, including acid value, peroxide value, safety threshold range, and judgment conclusion.

[0062] The evaluation and judgment module combines multivariate statistical calculations with dynamic threshold management to ensure the accuracy and adaptability of the detection results. Employing a pre-trained machine learning model, it can effectively process the feature parameters extracted from the voltammetric curve, achieving rapid and accurate judgment of the degree of rancidity.

[0063] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other. In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor, characterized in that, include: The data acquisition module is used to receive the raw electrochemical response signal of the edible oil sample output by the electrochemical sensor, perform format standardization processing on the signal, remove abnormal data through statistical rules, and verify the integrity. The data preprocessing module is used to reduce noise and correct baseline drift of the received data using statistical optimization algorithms, generate a dataset with uniform dimensions after standardization, and transmit it to the feature analysis module after stability verification. The feature analysis module is used to extract rancidity-related feature parameters from the dataset through statistical correlation analysis. After significance verification, the parameters are fused using numerical calculation methods to obtain feature values ​​that characterize the degree of rancidity. The evaluation and judgment module is used to input feature values ​​into a pre-trained rancidity index prediction model, output quantitative indicators through multivariate statistical calculations, dynamically set safety thresholds based on the type of edible oil, and output rancidity judgment conclusions after comparison.

2. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The raw electrochemical response signal received by the data acquisition module is one of the following: voltammetric curve, impedance spectrum, or current time series, and each signal must meet the statistical sampling requirements.

3. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 2, characterized in that, The current-voltage curve is either a differential pulse current-voltage curve or a square wave pulse current-voltage curve. The signal quality of both types of curves needs to be verified by statistical methods.

4. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The preprocessing Includes the following steps: S1: Noise reduction using a filtering algorithm based on signal statistical characteristics; S2: Eliminate drift by employing a statistical correction algorithm based on baseline drift patterns; S3: Transform the processed data into a dataset with uniform dimensions using a standardization algorithm.

5. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The feature parameters related to rancidity extracted by the feature analysis module need to be confirmed through statistical correlation analysis and then validated through statistical significance testing.

6. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The feature analysis module employs one of the following numerical calculation methods: principal component analysis, partial least squares regression, or support vector regression, and each method must be combined with statistical optimization logic.

7. A rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The rancidity index prediction model of the evaluation and judgment module is learned by machine learning algorithm on a statistically representative training dataset. The training dataset contains multiple sets of feature values ​​and corresponding standard acid value and peroxide value labels.

8. The rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The quantitative indicators output by the evaluation and judgment module are acid value and peroxide value, and the accuracy of the indicators needs to be verified by statistical methods.

9. A rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The preset safety threshold of the assessment and judgment module needs to be dynamically set by combining the national standard limit for the type of edible oil and referring to the statistical distribution of historical test data of that type of oil sample.

10. A rapid detection system for the degree of rancidity of edible oil based on an electrochemical sensor according to claim 1, characterized in that, The relationship between quantitative indicators and thresholds is analyzed by statistical model. If the acid value or peroxide value exceeds the statistical judgment standard of the corresponding threshold, the result is "rancid"; if neither indicator exceeds the threshold, the result is "not rancid".

Images