Chilled fresh egg storage deterioration identification method based on multi-parameter perception and deterioration characteristic modeling

Abstract

The invention relates to the technical field of food quality safety monitoring, in particular to a chilled fresh egg storage deterioration identification method based on multi-parameter perception and deterioration characteristic modeling, which comprises the following steps: S1, collecting a plurality of parameters in a chilled fresh egg storage environment in real time; s2, performing filtering and normalization processing to obtain standardized parameter data; s3, extracting deterioration characteristics related to deterioration of the egg products; s4, calculating a deterioration index based on the deterioration characteristics; s5, comparing the deterioration index with a preset threshold value, and if the deterioration index exceeds the preset threshold value, identifying the state as a deterioration state; and S6, generating and outputting a deterioration identification result. According to the invention, through multi-parameter deterioration characteristic modeling and confidence quantification, accurate identification and risk grade determination of the deterioration state of the chilled fresh eggs are realized, and the quality monitoring accuracy and response efficiency of a storage link are improved.

Description

Technical Field

[0001] This invention relates to the field of food quality and safety monitoring technology, and in particular to a method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling. Background Technology

[0002] In the circulation and storage of chilled eggs, environmental parameters have a direct impact on product quality. In particular, fluctuations in temperature, humidity and carbon dioxide concentration can significantly accelerate the metabolism and deterioration process. Traditional quality monitoring methods rely on timed manual sampling or judgment based on a single indicator, which is not only slow and costly, but also unable to achieve real-time tracking and early identification of spoilage trends.

[0003] However, existing methods generally suffer from the following technical challenges: first, they cannot effectively convert multi-parameter environmental data into quantifiable features highly correlated with the spoilage process; second, they lack unified indicators for comprehensive judgment of the degree of deterioration; and third, the state judgment results lack credible expression, affecting the decision-making basis in practical applications. Therefore, it is necessary to propose a spoilage identification method for chilled egg products based on multi-parameter perception and spoilage feature modeling to solve the above problems. Summary of the Invention

[0004] To achieve the above objectives, this invention provides a method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling.

[0005] A method for identifying spoilage in chilled egg products during storage based on multi-parameter perception and deterioration feature modeling includes the following steps:

[0006] S1: Real-time collection of multiple parameters in the cold storage environment of fresh eggs, including temperature, humidity and carbon dioxide concentration;

[0007] S2: Filter and normalize multiple parameters to obtain standardized parameter data;

[0008] S3: Extract deterioration characteristics related to egg spoilage from standardized parameter data, including temperature fluctuation range, humidity change rate and carbon dioxide accumulation;

[0009] S4: Calculate the degradation index based on degradation characteristics, wherein the degradation index is a weighted sum of temperature fluctuation amplitude, humidity change rate and carbon dioxide accumulation;

[0010] S5: Compare the deterioration index with a preset threshold. If the deterioration index exceeds the preset threshold, it is identified as a deteriorated state.

[0011] S6: Generate and output the deterioration identification result, which includes the deterioration state and confidence level.

[0012] Optionally, S1 specifically includes:

[0013] S11: Temperature sensors, humidity sensors and carbon dioxide concentration sensors are arranged at preset intervals in the cold fresh egg storage area, and each sensor is connected to the data acquisition terminal by wire or wireless means.

[0014] S12: Configure a uniform sampling period for each temperature sensor, humidity sensor and carbon dioxide concentration sensor, poll and collect data from each sensor according to the sampling period, obtain the current temperature measurement value, humidity measurement value and carbon dioxide concentration measurement value, and mark a uniform timestamp for each set of measurement values;

[0015] S13: Combine the temperature measurement, humidity measurement, and carbon dioxide concentration measurement obtained within the same sampling period with the corresponding timestamp and sensor identifier to generate a raw data record of multiple parameters of the storage environment, including temperature, humidity, and carbon dioxide concentration.

[0016] Optionally, S2 specifically includes:

[0017] S21: The original data sequences of temperature, humidity and carbon dioxide concentration collected in S1 are subjected to sliding window filtering. The sliding window filtering performs local mean smoothing on each parameter sequence with a set window length to remove instantaneous jumps or abnormal peak values ​​and obtain a stable data sequence.

[0018] S22: Based on the numerical distribution range of each parameter in the historical storage environment, set the corresponding normalized parameter range, and perform minimum-maximum normalization processing on the temperature, humidity and carbon dioxide concentration data respectively, and map each parameter value to the range [0,1] to eliminate the difference between different physical dimensions.

[0019] S23: Combine the normalized temperature, humidity, and carbon dioxide concentration values ​​from S22 in chronological order to generate a standardized parameter data sequence with corresponding timestamps.

[0020] Optionally, S3 specifically includes:

[0021] S31: Extract the temperature standardized data sequence from the standardized parameter data in chronological order, and statistically analyze the maximum and minimum values ​​of the temperature standardized data within the preset feature analysis period. The difference between the two values ​​is taken as the temperature fluctuation amplitude of the corresponding period.

[0022] S32: Extract the humidity standardized data sequence from the standardized parameter data, calculate the difference between the humidity standardized data at adjacent sampling times, and calculate the average value of the difference within the preset feature analysis period to obtain the humidity change rate for the corresponding period.

[0023] S33: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, and accumulate the carbon dioxide standardized data at each sampling time point by point within the preset feature analysis period to obtain the cumulative amount of carbon dioxide for the corresponding period.

[0024] S34: Align the temperature fluctuation range, humidity change rate, and carbon dioxide accumulation obtained from S31 to S33 according to the timestamps, and combine them to form a deterioration characteristic sequence related to the egg deterioration process.

[0025] Optionally, S32 specifically includes:

[0026] S321: Extract the humidity normalized data sequence from the normalized parameter data obtained in S2 in chronological order, and set the index of adjacent sampling times as... and This ensures that humidity data is arranged continuously over time.

[0027] S322: Calculate the change in humidity for standardized data at adjacent sampling times, and use the difference between the current sample value and the previous sample value as the humidity change at the corresponding time. ;

[0028] S323: Within the preset characteristic analysis period, analyze all humidity changes. Statistical analysis was conducted to calculate the average level of change for the corresponding time period, and the average value was used as the humidity change rate for the corresponding time period.

[0029] Optionally, S33 specifically includes:

[0030] S331: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, setting the analysis start time as the first sampling point, with a total number of sampling points. Construct a standardized carbon dioxide concentration sequence arranged in ascending order over time;

[0031] S332: Within a preset characteristic analysis period, the carbon dioxide standardized data sequence is accumulated point by point, and the concentration values ​​at each moment are summed sequentially to obtain the cumulative amount of carbon dioxide within the analysis period; the calculation formula is as follows: ,in, Indicates the cumulative amount of carbon dioxide; Indicates the first Standardized carbon dioxide concentration values ​​at each sampling time; This indicates the number of sampling points within the analysis period.

[0032] Optionally, S4 specifically includes:

[0033] S41: Call the deterioration feature sequence constructed in S34, and obtain the corresponding temperature fluctuation amplitude, humidity change rate, and carbon dioxide accumulation in each preset feature analysis period, which are denoted as temperature fluctuation amplitude. Humidity change rate and carbon dioxide accumulation ;

[0034] S42: Read the temperature weights from the preset weight parameter library that match the chilled egg product category and storage management strategy. Humidity weight and carbon dioxide weight ;

[0035] S43: Based on temperature fluctuation amplitude Humidity change rate Cumulative carbon dioxide and corresponding weights , , The deterioration index for the current feature analysis period is calculated using the following formula: ,in, This indicates the deterioration index.

[0036] Optionally, S5 specifically includes:

[0037] S51: Deterioration index calculated using S4 The system obtains the risk indicators of egg deterioration during the current feature analysis period and simultaneously obtains the timestamp information for the corresponding period.

[0038] S52: Establish corresponding deterioration judgment thresholds based on historical monitoring data. ;

[0039] S53: Adjust the current deterioration index With the corresponding preset threshold Compare them one by one, if Greater than If the egg quality is within the specified range, it is determined that the egg product is in a spoiled state during the current analysis period; otherwise, it is considered to be in a normal state.

[0040] S54: Bind the comparison result to the current timestamp to form a deterioration status determination record containing time information and status judgment result.

[0041] Optionally, S52 specifically includes:

[0042] S521: Retrieve environmental data of multiple batches of chilled fresh eggs under known storage conditions from the historical monitoring database, generate a corresponding deterioration index sequence for each batch of data, and label each deterioration index as normal or spoiled based on the actual test results.

[0043] S522: Deterioration indices labeled as normal state constitute a normal sample set, and deterioration indices labeled as deteriorated state constitute a deteriorated sample set.

[0044] S523: Based on the statistical distribution relationship between normal samples and deteriorated samples, select the threshold calculation method that maximizes the distinction between the two states, and calculate the deterioration discrimination threshold. The formula is: ,in, Indicates the threshold for detecting deterioration; This represents the mean deterioration index of the normal sample set; This represents the mean deterioration index of the deteriorated sample set;

[0045] S524: Calculate the threshold Record the data into the threshold parameter library and store it according to egg type and storage conditions.

[0046] Optionally, S6 specifically includes:

[0047] S61: Call the deterioration status determination record formed in S5 and extract the deterioration index corresponding to each feature analysis period. The status and timestamp information are used as the basic data for generating the deterioration identification results;

[0048] S62: Based on the deterioration index Deterioration discrimination threshold Calculate the difference and convert it into a confidence score. A confidence level above 0.7 is considered high confidence, a confidence level between 0.4 and 0.7 is considered medium confidence, and a confidence level below 0.4 is considered low confidence.

[0049] S63: Construct deterioration identification result entries that include timestamps, judgment status, and confidence scores, and arrange them in chronological order to form an identification result sequence;

[0050] S64: Output the identification result sequence to the warehouse monitoring terminal in a structured format.

[0051] The beneficial effects of this invention are:

[0052] This invention constructs three types of deterioration characteristics—temperature fluctuation amplitude, humidity change rate, and carbon dioxide accumulation—and calculates a deterioration index based on weighted fusion, thereby achieving a comprehensive quantification of multidimensional abnormal changes in the storage environment of chilled eggs. This effectively improves the sensitivity and accuracy of identifying potential spoilage risks of eggs.

[0053] This invention, by combining a spoilage discrimination threshold and a confidence level scoring mechanism, not only achieves automatic identification of spoilage status, but also provides auxiliary information on the confidence level, which helps cold chain storage systems to provide early warning and intervention based on risk levels. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a schematic diagram of the chilled egg product spoilage identification method according to an embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram of the process for extracting egg deterioration characteristics according to an embodiment of the present invention. Detailed Implementation

[0057] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0058] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0059] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0060] like Figures 1-2 As shown, a method for identifying spoilage in chilled egg products during storage based on multi-parameter perception and deterioration feature modeling includes the following steps:

[0061] S1: Real-time collection of multiple parameters in the cold storage environment of fresh eggs, including temperature, humidity and carbon dioxide concentration;

[0062] S1 specifically includes:

[0063] S11: Temperature sensors, humidity sensors and carbon dioxide concentration sensors are arranged at preset intervals in the cold fresh egg storage area, and each sensor is connected to the data acquisition terminal by wire or wireless connection so that the data acquisition terminal can receive the corresponding measurement signals.

[0064] S12: Configure a unified sampling period for each temperature sensor, humidity sensor, and carbon dioxide concentration sensor. The data acquisition terminal polls each sensor according to the sampling period to obtain the current temperature measurement value, humidity measurement value, and carbon dioxide concentration measurement value, and marks each set of measurement values ​​with a unified timestamp.

[0065] S13: Combine the temperature, humidity, and carbon dioxide concentration measurements obtained within the same sampling period with the corresponding timestamps and sensor identifiers to generate a multi-parameter raw data record of the storage environment containing temperature, humidity, and carbon dioxide concentration. Store the multi-parameter raw data record in a real-time data buffer for subsequent steps. Through the above method, continuous, synchronous, and structured acquisition of temperature, humidity, and carbon dioxide concentration in the storage environment of chilled egg products is achieved, ensuring the timeliness and completeness of multi-parameter sensing data. This provides a stable and reliable environmental data foundation for subsequent extraction of deterioration features and construction of deterioration indices based on multi-parameter data.

[0066] S2: Filter and normalize multiple parameters to obtain standardized parameter data;

[0067] S2 specifically includes:

[0068] S21: Perform sliding window filtering on the raw data sequences of temperature, humidity and carbon dioxide concentration collected in S1. The sliding window filtering performs local mean smoothing on each parameter sequence with a set window length, removes instantaneous jumps or abnormal peak values, and obtains a stable data sequence after noise suppression.

[0069] S22: Based on the numerical distribution range of each parameter in the historical storage environment, set the corresponding normalized parameter range, and perform minimum-maximum normalization processing on the temperature, humidity and carbon dioxide concentration data respectively, and map each parameter value to the range [0,1] to eliminate the difference between different physical dimensions.

[0070] S23: Combine the normalized temperature, humidity, and carbon dioxide concentration values ​​from S22 in chronological order to generate a standardized parameter data sequence with corresponding timestamps, which serves as the basic input for subsequent deterioration feature extraction. Through the above processing method, the abrupt interference and fluctuation noise in the original sensing data can be effectively removed, and the multi-source parameters with different physical dimensions can be unified to a dimensionless standardized scale, which significantly improves the data comparability and model stability in the feature extraction process, thus providing clean and unified input data support for the construction of the deterioration index and the identification of the deterioration state.

[0071] The sliding window filtering process described above is as follows:

[0072] S221: Set the sliding window length for any raw parameter sequence of temperature, humidity, and carbon dioxide concentration in S21. ;

[0073] S222: For the sliding window The mean of each data point is calculated by replacing the data point at the center of the current window with the average of the data within that window; the calculation formula is: ,in, Represents the first of the original parameter sequences A number, The value representing the smoothed result at the center point of the window;

[0074] S223: When the difference between a data point in the original parameter sequence and the mean of the corresponding window is greater than the preset jump threshold. When this occurs, the data point is considered a transient jump or an abnormal spike, and the mean result is used. Replace this data point; the judgment logic is as follows: If the above conditions are met, then Updated to ;

[0075] S224: Move the sliding window globally along the parameter sequence and repeat S221 to S223 to finally generate a smooth parameter sequence after removing instantaneous jumps and spike noise, providing a stable input for the normalization process in S22.

[0076] S3: Extract deterioration characteristics related to egg spoilage from standardized parameter data. Deterioration characteristics include temperature fluctuation range, humidity change rate and carbon dioxide accumulation.

[0077] S3 specifically includes:

[0078] S31: Extract the standardized temperature data sequence from the standardized parameter data in chronological order. Within a preset feature analysis period, statistically analyze the maximum and minimum values ​​of the standardized temperature data. Use the difference between these two values ​​as the temperature fluctuation amplitude for the corresponding period to characterize the intensity of temperature fluctuations in the storage environment. The calculation formula is:

[0079] ,in, Indicates the amplitude of temperature fluctuation; This represents the maximum value of the standardized temperature data within the preset feature analysis period; This represents the minimum value of the standardized temperature data within the preset feature analysis period;

[0080] S32: Extract the humidity standardized data sequence from the standardized parameter data, calculate the difference between the humidity standardized data at adjacent sampling times, and calculate the average value of the difference within the preset feature analysis period to obtain the humidity change rate of the corresponding period, which is used to characterize the dynamic change of humidity in the storage environment.

[0081] S33: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, and accumulate the carbon dioxide standardized data at each sampling time point by point within the preset feature analysis period to obtain the cumulative amount of carbon dioxide for the corresponding period.

[0082] S34: Align the temperature fluctuation amplitude, humidity change rate, and carbon dioxide accumulation obtained from S31 to S33 according to the timestamp, combine them to form a deterioration feature sequence related to the egg deterioration process, and provide this deterioration feature sequence to S4 for the calculation of the deterioration index; through the above steps, on the basis of unified standardized parameter data, temperature, humidity, and carbon dioxide concentration are converted into fluctuation amplitude, change rate, and accumulation characteristics that can reflect the deterioration process of chilled eggs, forming a set of highly targeted deterioration features, providing physically meaningful and temporally continuous feature inputs for the subsequent construction of the deterioration index and identification of deterioration status.

[0083] S32 specifically includes:

[0084] S321: Extract the humidity normalized data sequence from the normalized parameter data obtained in S2 in chronological order, and set the index of adjacent sampling times as... and This ensures that humidity data is arranged continuously over time.

[0085] S322: Calculate the change in humidity for standardized data at adjacent sampling times, and use the difference between the current sample value and the previous sample value as the humidity change at the corresponding time. The calculation formula is as follows: ,in, This indicates the change in humidity between adjacent sampling times; Indicates the time index is Standardized humidity data values; Indicates the time index is Standardized humidity data values;

[0086] S323: Within the preset characteristic analysis period, analyze all humidity changes. Statistical analysis was conducted to calculate the average change level for the corresponding time period, and this average value was used as the humidity change rate for that period. The calculation formula is as follows:

[0087] ,in, Indicates the rate of change of humidity; This indicates the number of data points representing humidity changes within the preset feature analysis period. The sequence value represents the amount of humidity change. Through the above steps, the continuous trend of humidity change within a preset time period can be transformed into a quantifiable rate of change index, which can accurately characterize the stability and rate of change of humidity. This provides a stable and continuous feature input for the quantitative calculation of the humidity dimension in the subsequent deterioration index, which is conducive to improving the sensitivity and discrimination ability of deterioration identification to humidity change factors.

[0088] S33 specifically includes:

[0089] S331: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, setting the analysis start time as the first sampling point, with a total number of sampling points. Construct a standardized carbon dioxide concentration sequence arranged in ascending order over time;

[0090] S332: Within a preset characteristic analysis period, the carbon dioxide standardized data sequence is accumulated point by point, and the concentration values ​​at each moment are summed sequentially to obtain the cumulative amount of carbon dioxide within the analysis period; the calculation formula is as follows: ,in, Indicates the cumulative amount of carbon dioxide; Indicates the first Standardized carbon dioxide concentration values ​​at each sampling time; This indicates the number of sampling points within the analysis period. Through the above steps, the time-series standardized carbon dioxide concentration data is transformed into a total cumulative value index, which can effectively characterize the overall exposure level of carbon dioxide concentration in the storage environment, providing a stable and quantifiable feature input for the identification of spoilage risk, and enhancing the ability to perceive the deterioration process of egg products under low ventilation or high breathing intensity scenarios.

[0091] S4: Calculate the deterioration index based on the deterioration characteristics. The deterioration index is a weighted sum of temperature fluctuation amplitude, humidity change rate and carbon dioxide accumulation.

[0092] S4 specifically includes:

[0093] S41: Call the deterioration feature sequence constructed in S34, and obtain the corresponding temperature fluctuation amplitude, humidity change rate, and carbon dioxide accumulation in each preset feature analysis period, which are denoted as temperature fluctuation amplitude. Humidity change rate and carbon dioxide accumulation , used to characterize the numerical state of multidimensional deterioration features during this period;

[0094] S42: Read the temperature weights from the preset weight parameter library that match the chilled egg product category and storage management strategy. Humidity weight and carbon dioxide weight Each weight is used to reflect the degree of influence of different deterioration characteristics on the risk of egg spoilage, and the three satisfy a weighted constraint relationship.

[0095] Table 1 Weight Parameter Library

[0096] Egg product types Storage temperature range Temperature fluctuation amplitude weight Humidity change rate weighting Carbon dioxide accumulation weight egg 0-4 ℃ 0.4 0.3 0.3 Quail eggs 2-6 ℃ 0.35 0.25 0.4 goose eggs 0-4 ℃ 0.5 0.2 0.3 duck eggs 3-8 ℃ 0.3 0.4 0.3

[0097] The weights in Table 1 above are automatically selected and matched according to the egg type and corresponding storage conditions, so as to realize the differentiated response capability to different deterioration factors and provide highly adaptable and configurable parameter support for the calculation of the deterioration index.

[0098] S43: Based on temperature fluctuation amplitude Humidity change rate Cumulative carbon dioxide and corresponding weights , , Calculate the degradation index for the current feature analysis period, compressing multidimensional degradation features into a single risk indicator. The formula is as follows: ,in, The degradation index is represented by the above steps. The temperature fluctuation range, humidity change rate and carbon dioxide accumulation are summarized into a single degradation index in the form of weights. This not only retains the information of the degradation characteristics of the multi-source environment, but also realizes the quantitative characterization of the risk of spoilage. This is conducive to reflecting the degree of egg spoilage with a unified index in the subsequent threshold discrimination process, thereby improving the sensitivity and interpretability of spoilage identification.

[0099] S5: Compare the deterioration index with a preset threshold. If the deterioration index exceeds the preset threshold, it is identified as a deteriorated state.

[0100] S5 specifically includes:

[0101] S51: Deterioration index calculated using S4 The system obtains the risk indicators of egg deterioration during the current feature analysis period and simultaneously obtains the timestamp information for the corresponding period.

[0102] S52: Establish corresponding deterioration judgment thresholds based on historical monitoring data. This is used to distinguish between normal storage conditions and deteriorated conditions;

[0103] S53: Adjust the current deterioration index With the corresponding preset threshold Compare them one by one, if Greater than If the egg quality is within the specified range, it is determined that the egg product is in a spoiled state during the current analysis period; otherwise, it is considered to be in a normal state.

[0104] S54: Bind the comparison result to the current timestamp to form a deterioration status judgment record containing time information and status judgment results, which serves as the basis for subsequent deterioration identification results output; through the above steps, the continuously calculated deterioration index is compared with the judgment threshold set according to the category and environment on a time-by-time basis to realize the automatic judgment of the deterioration status of egg products, which helps the system to quickly respond to storage abnormal risks.

[0105] S52 specifically includes:

[0106] S521: Retrieve environmental data of multiple batches of chilled fresh eggs under known storage conditions from the historical monitoring database, call the calculation method of S4 to generate a corresponding deterioration index sequence for each batch of data, and mark each deterioration index as normal or deteriorated based on the actual test results.

[0107] S522: Deterioration indices labeled as normal state constitute a normal sample set, and deterioration indices labeled as deteriorated state constitute a deteriorated sample set.

[0108] S523: Based on the statistical distribution relationship between normal samples and deteriorated samples, select the threshold calculation method that maximizes the distinction between the two states, and calculate the deterioration discrimination threshold. The formula is: ,in, Indicates the threshold for detecting deterioration; This represents the mean deterioration index of the normal sample set; This represents the mean deterioration index of the deteriorated sample set;

[0109] S524: Calculate the threshold The data is recorded in the threshold parameter library and categorized and stored according to egg type and storage conditions, serving as the basis for subsequent judgment of deterioration status in S5. Through the above steps, a discrimination threshold can be automatically generated based on the differences between normal and deteriorated samples in historical monitoring data, making the threshold data-driven, objective, and adaptable, which is conducive to improving the accuracy and stability of threshold judgment in the process of deterioration identification.

[0110] S6: Generate and output the deterioration identification results, which include the deterioration status and confidence level;

[0111] S6 specifically includes:

[0112] S61: Call the deterioration status determination record formed in S5 and extract the deterioration index corresponding to each feature analysis period. The status and timestamp information are used as the basic data for generating the deterioration identification results;

[0113] S62: Based on the deterioration index Deterioration discrimination threshold Calculate the difference and convert it into a confidence score. The formula for calculating the confidence score is: ,in, Indicates the confidence score; This represents a stability constant used to adjust the sensitivity of the rating; a confidence level higher than 0.7 is considered a high confidence level, a confidence level between 0.4 and 0.7 is considered a medium confidence level, and a confidence level lower than 0.4 is considered a low confidence level.

[0114] S63: Construct deterioration identification result entries that include timestamps, judgment status, and confidence scores, and arrange them in chronological order to form an identification result sequence, which is used to represent the state change process within the storage cycle;

[0115] S64: Output the identification result sequence to the warehouse monitoring terminal in a structured format to realize visual access and anomaly response processing; through the above steps, the spoilage judgment and confidence score can be generated simultaneously, so that the spoilage identification has both the ability to judge the state and the ability to quantify the confidence level, which makes it easier for the management system to take differentiated control measures under different confidence intervals, thereby improving the accuracy and timeliness of cold fresh egg storage management.

[0116] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0117] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying spoilage in chilled egg products during storage based on multi-parameter perception and deterioration feature modeling, characterized in that, Includes the following steps: S1: Real-time collection of multiple parameters in the cold storage environment of fresh eggs, including temperature, humidity and carbon dioxide concentration; S2: Filter and normalize multiple parameters to obtain standardized parameter data; S3: Extract deterioration characteristics related to egg spoilage from standardized parameter data, including temperature fluctuation range, humidity change rate and carbon dioxide accumulation; S4: Calculate the degradation index based on degradation characteristics, wherein the degradation index is a weighted sum of temperature fluctuation amplitude, humidity change rate and carbon dioxide accumulation; S5: Compare the deterioration index with a preset threshold. If the deterioration index exceeds the preset threshold, it is identified as a deteriorated state. S6: Generate and output the deterioration identification result, which includes the deterioration state and confidence level.

2. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 1, characterized in that, S1 specifically includes: S11: Temperature sensors, humidity sensors and carbon dioxide concentration sensors are arranged at preset intervals in the cold fresh egg storage area, and each sensor is connected to the data acquisition terminal by wire or wireless means. S12: Configure a uniform sampling period for each temperature sensor, humidity sensor and carbon dioxide concentration sensor, poll and collect data from each sensor according to the sampling period, obtain the current temperature measurement value, humidity measurement value and carbon dioxide concentration measurement value, and mark a uniform timestamp for each set of measurement values; S13: Combine the temperature measurement, humidity measurement, and carbon dioxide concentration measurement obtained within the same sampling period with the corresponding timestamp and sensor identifier to generate a raw data record of multiple parameters of the storage environment, including temperature, humidity, and carbon dioxide concentration.

3. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 1, characterized in that, S2 specifically includes: S21: The original data sequences of temperature, humidity and carbon dioxide concentration collected in S1 are subjected to sliding window filtering. The sliding window filtering performs local mean smoothing on each parameter sequence with a set window length to remove instantaneous jumps or abnormal peak values ​​and obtain a stable data sequence. S22: Based on the numerical distribution range of each parameter in the historical storage environment, set the corresponding normalized parameter range, and perform minimum-maximum normalization processing on the temperature, humidity and carbon dioxide concentration data respectively, and map each parameter value to the range [0,1] to eliminate the difference between different physical dimensions. S23: Combine the normalized temperature, humidity, and carbon dioxide concentration values ​​from S22 in chronological order to generate a standardized parameter data sequence with corresponding timestamps.

4. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 1, characterized in that, S3 specifically includes: S31: Extract the temperature standardized data sequence from the standardized parameter data in chronological order, and statistically analyze the maximum and minimum values ​​of the temperature standardized data within the preset feature analysis period. The difference between the two values ​​is taken as the temperature fluctuation amplitude of the corresponding period. S32: Extract the humidity standardized data sequence from the standardized parameter data, calculate the difference between the humidity standardized data at adjacent sampling times, and calculate the average value of the difference within the preset feature analysis period to obtain the humidity change rate for the corresponding period. S33: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, and accumulate the carbon dioxide standardized data at each sampling time point by point within the preset feature analysis period to obtain the cumulative amount of carbon dioxide for the corresponding period. S34: Align the temperature fluctuation range, humidity change rate, and carbon dioxide accumulation obtained from S31 to S33 according to the timestamps, and combine them to form a deterioration characteristic sequence related to the egg deterioration process.

5. The method for identifying spoilage in chilled egg products based on multi-parameter perception and deterioration feature modeling according to claim 4, characterized in that, Specifically, S32 includes: S321: Extract the humidity normalized data sequence from the normalized parameter data obtained in S2 in chronological order, and set the index of adjacent sampling times as... and This ensures that humidity data is arranged continuously over time. S322: Calculate the change in humidity for standardized data at adjacent sampling times, and use the difference between the current sample value and the previous sample value as the humidity change at the corresponding time. ; S323: Within the preset characteristic analysis period, analyze all humidity changes. Statistical analysis was conducted to calculate the average level of change for the corresponding time period, and the average value was used as the humidity change rate for the corresponding time period.

6. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 5, characterized in that, S33 specifically includes: S331: Extract the carbon dioxide standardized data sequence from the standardized parameter data in chronological order, setting the analysis start time as the first sampling point, with a total number of sampling points. Construct a standardized carbon dioxide concentration sequence arranged in ascending order over time; S332: Within a preset characteristic analysis period, the carbon dioxide standardized data sequence is accumulated point by point, and the concentration values ​​at each moment are summed sequentially to obtain the cumulative amount of carbon dioxide within the analysis period; the calculation formula is as follows: ,in, Indicates the cumulative amount of carbon dioxide; Indicates the first Standardized carbon dioxide concentration values ​​at each sampling time; This indicates the number of sampling points within the analysis period.

7. The method for identifying spoilage in chilled egg products based on multi-parameter perception and deterioration feature modeling according to claim 4, characterized in that, S4 specifically includes: S41: Call the deterioration feature sequence constructed in S34, and obtain the corresponding temperature fluctuation amplitude, humidity change rate, and carbon dioxide accumulation in each preset feature analysis period, which are denoted as temperature fluctuation amplitude. Humidity change rate and carbon dioxide accumulation ; S42: Read the temperature weights from the preset weight parameter library that match the chilled egg product category and storage management strategy. Humidity weight and carbon dioxide weight ; S43: Based on temperature fluctuation amplitude Humidity change rate Cumulative carbon dioxide and corresponding weights , , The deterioration index for the current feature analysis period is calculated using the following formula: ,in, This indicates the deterioration index.

8. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 1, characterized in that, S5 specifically includes: S51: Deterioration index calculated using S4 The system obtains the risk indicators of egg deterioration during the current feature analysis period and simultaneously obtains the timestamp information for the corresponding period. S52: Establish corresponding deterioration judgment thresholds based on historical monitoring data. ; S53: Adjust the current deterioration index With the corresponding preset threshold Compare them one by one, if Greater than If the egg quality is within the specified range, it is determined that the egg product is in a spoiled state during the current analysis period; otherwise, it is considered to be in a normal state. S54: Bind the comparison result to the current timestamp to form a deterioration status determination record containing time information and status judgment result.

9. The method for identifying spoilage of chilled egg products in storage based on multi-parameter perception and deterioration feature modeling as described in claim 8, characterized in that, Specifically, S52 includes: S521: Retrieve environmental data of multiple batches of chilled fresh eggs under known storage conditions from the historical monitoring database, generate a corresponding deterioration index sequence for each batch of data, and label each deterioration index as normal or spoiled based on the actual test results. S522: Deterioration indices labeled as normal state constitute a normal sample set, and deterioration indices labeled as deteriorated state constitute a deteriorated sample set. S523: Based on the statistical distribution relationship between normal samples and deteriorated samples, select the threshold calculation method that maximizes the distinction between the two states, and calculate the deterioration discrimination threshold. The formula is: ,in, Indicates the threshold for detecting deterioration; This represents the mean deterioration index of the normal sample set; This represents the mean deterioration index of the deteriorated sample set; S524: Calculate the threshold Record the data into the threshold parameter library and store it according to egg type and storage conditions.

10. A method for identifying spoilage in chilled egg products based on multi-parameter perception and deterioration feature modeling according to claim 9, characterized in that, S6 specifically includes: S61: Call the deterioration status determination record formed in S5 and extract the deterioration index corresponding to each feature analysis period. The status and timestamp information are used as the basic data for generating the deterioration identification results; S62: Based on the deterioration index Deterioration discrimination threshold Calculate the difference and convert it into a confidence score. A confidence level above 0.7 is considered high confidence, a confidence level between 0.4 and 0.7 is considered medium confidence, and a confidence level below 0.4 is considered low confidence. S63: Construct deterioration identification result entries that include timestamps, judgment status, and confidence scores, and arrange them in chronological order to form an identification result sequence; S64: Output the identification result sequence to the warehouse monitoring terminal in a structured format.

Images