Frozen food nuclear contamination monitoring system

Abstract

The present invention provides a frozen food nuclear contamination monitoring system, including one or more temperature control detection devices, a cloud platform and one or more user terminals, wherein the temperature control detection device has a nuclear radiation detection module, a main control module and a communication module, and the cloud platform inputs the data measured by the nuclear radiation detection module into a machine learning model to obtain the predicted value of the nuclear radiation amount of various foods and provides it to the terminal. The present invention fills the gap in the prior art that there is a lack of nuclear radiation detection equipment at the cold chain terminal, and can obtain the predicted value of the nuclear radiation amount of various foods stored in the refrigeration equipment through a machine learning model, thereby solving the problem that the existing nuclear radiation detector can only measure the nuclear radiation amount in a certain space and cannot effectively distinguish the nuclear radiation amount of various foods, thereby providing valuable reference data for managers and loaders of refrigeration equipment, so that they can better manage frozen foods in multiple cold chain terminals and deal with nuclear contaminated foods in a timely manner.

Description

Technical Field

[0001] The invention belongs to the technical field of frozen food management equipment, and in particular relates to a frozen food nuclear contamination monitoring system. Background Art

[0002] With the continuous improvement of people's living standards and the continuous development of related technologies, people are paying more and more attention to food safety, and the aspects of concern have also increased. Seafood is usually provided to consumers as frozen food through cold chain transportation and cold chain terminal storage. In order to enable consumers to purchase frozen food with confidence, it is necessary to carry out inspections during cold chain transportation and at cold chain terminals (such as freezers in large supermarkets), especially at cold chain terminals, because only inspections here can ultimately ensure that the food consumers buy is not contaminated.

[0003] However, there is no equipment and method in the prior art that can detect nuclear contamination of frozen food at a terminal such as a freezer. Although there are some nuclear radiation detectors and nuclear radiation detection chips on the market, if they are directly placed in a freezer, the real-time nuclear radiation amount in a certain space in the freezer will be measured, which cannot well represent the actual nuclear radiation level of the frozen food stored in the freezer. In particular, when a variety of foods are mixed in the freezer, or the freezer has been restocked with food (i.e., the same or different types of food with different production dates are placed), the measured radiation amount will have a large deviation from the actual nuclear radiation level of each food, and it is difficult to provide a valuable reference for frozen food management and consumer food selection. Summary of the invention

[0004] The present invention is made to solve the above problems, and aims to provide a monitoring system that can well monitor the nuclear radiation level of frozen food in each cold chain terminal (such as a freezer). The present invention adopts the following technical solutions:

[0005] The present invention provides a frozen food nuclear contamination monitoring system, which is used to monitor frozen food including nuclear contamination monitoring. The system has the following technical features: one or more temperature control detection devices, which are respectively arranged in one or more refrigeration equipment for storing the frozen food; a cloud platform, which is respectively connected to each of the temperature control detection devices in communication; and one or more user terminals, which are held by an administrator and / or a loader, wherein the temperature control detection device comprises: a nuclear radiation detection module, which comprises a nuclear radiation detection sensor arranged in the cabinet, which is used to detect the nuclear radiation amount of the frozen food in the cabinet; a main control module, which is based on the nuclear The radiation amount generates corresponding nuclear radiation measurement data; and a communication module is used to send the nuclear radiation measurement data to the cloud platform, and the cloud platform at least includes: a data feature extraction and encoding unit, which extracts and encodes the nuclear radiation measurement data to obtain encoding features; a food radiation amount prediction unit, which inputs the encoding features into a trained machine learning model to obtain the radiation amount prediction value of each type of food; a status information generation unit, which generates the status information of each type of food based on at least the radiation amount prediction value; and a cloud platform side communication unit, which is used to obtain the nuclear radiation measurement data from the communication module, and send the status information to the user terminal.

[0006] The frozen food nuclear contamination monitoring system provided by the present invention may also have such a technical feature, wherein the machine learning model is a gradient boosting decision tree model, and the training data set used to train the machine learning model includes the nuclear radiation measurement data collected from the refrigeration equipment in different situations.

[0007] The frozen food nuclear contamination monitoring system provided by the present invention may also have such a technical feature, wherein the training data set includes the nuclear radiation measurement data collected from the following situations and / or their combinations: the same type of food is placed in the refrigeration equipment; multiple types of food are mixed and placed in the refrigeration equipment; food produced on the same date is placed in the refrigeration equipment; multiple foods produced on different dates are placed in the refrigeration equipment; less than 1 / 4 of its maximum storage capacity of food is placed in the refrigeration equipment; and more than 3 / 4 of its maximum storage capacity of food is placed in the refrigeration equipment.

[0008] The frozen food nuclear contamination monitoring system provided by the present invention may also have such technical features, wherein the coding features include food type features, food weight features and time features, and the food type features are vectors obtained through one-hot encoding based on at least the food name and food type name of the food.

[0009] The frozen food nuclear contamination monitoring system provided by the present invention may also have such technical features, wherein the temperature control detection device also includes an equipment information storage module, which stores the equipment data of the refrigeration equipment, which at least includes the equipment location, and the cloud platform side communication unit is also used to obtain the equipment data from the temperature control detection device, and the food nuclear radiation measurement data includes multiple groups of food nuclear radiation measurement values ​​and corresponding timestamps, and the status information generation unit includes: a timing diagram generation part, which generates a time series diagram according to the food nuclear radiation measurement data, the horizontal axis of the diagram is time, and the vertical axis is the corresponding nuclear radiation measurement value; a thermal map generation part, which generates a thermal map according to the food nuclear radiation measurement data and the equipment data, the background of the figure is a regional map of the area where the refrigeration equipment is located, and the foreground is a semi-transparent graphic of different colors, and the color corresponds to the nuclear radiation measurement value of the equipment location where the graphic is located; and / or a bar graph generation part, which generates a bar graph according to the various food types and the corresponding nuclear radiation prediction values, and each bar in the figure represents the mean of the nuclear radiation prediction value of a food type.

[0010] The frozen food nuclear contamination monitoring system provided by the present invention may also have such technical features, wherein the cloud platform also includes: a data storage unit, used to store the nuclear radiation prediction value and the corresponding timestamp; and a food radiation excess judgment unit, used to obtain the nuclear radiation prediction value within a predetermined time range from the data storage unit, calculate the mean thereof, and judge whether the mean is greater than or equal to a predetermined nuclear radiation safety threshold, and the status information generation unit also generates the status information based on the judgment result of the food radiation excess judgment unit.

[0011] The frozen food nuclear contamination monitoring system provided by the present invention may also have such a technical feature, wherein the bar graph generating part generates a bar graph based on the various food types and their corresponding nuclear radiation prediction values, and the judgment result, wherein each bar in the graph represents the mean of the nuclear radiation prediction values ​​of a food type, and the bars of different colors are used to indicate whether the mean of the corresponding food type exceeds / does not exceed the nuclear radiation safety threshold.

[0012] The frozen food nuclear contamination monitoring system provided by the present invention may also have such technical features, wherein the cloud platform also includes: a data preprocessing unit, used to preprocess the nuclear radiation measurement data, including removing outliers, filling missing values ​​and standardizing the nuclear radiation measurement data.

[0013] The frozen food nuclear contamination monitoring system provided by the present invention may also have such a technical feature, wherein the cloud platform periodically sends data acquisition requests to the temperature control detection device of each refrigeration equipment, and the temperature control detection device sends the nuclear radiation measurement data to the cloud platform according to the data acquisition request.

[0014] The frozen food nuclear contamination monitoring system provided by the present invention may also have such technical features, wherein the communication module includes: a 485 communication sub-module, which is respectively connected to the main control module and the nuclear radiation detection module, and is used to obtain the nuclear radiation amount from the nuclear radiation detection module through the RS485 communication protocol; and a 4G communication sub-module, which is connected to the main control module and is communicated with the cloud platform, and is used to send the nuclear radiation measurement data to the cloud platform through the 4G communication protocol.

[0015] The present invention has the following functions and effects.

[0016] According to the frozen food nuclear contamination monitoring system of the present invention, it includes one or more temperature control detection devices, a cloud platform and one or more user terminals. The temperature control detection device is arranged in the refrigeration equipment and has a nuclear radiation detection module, a main control module and a communication module. Therefore, the nuclear radiation detection module can be used to detect the nuclear radiation amount in the refrigeration equipment, and then the corresponding nuclear radiation measurement data can be obtained through the main control module, and the data is sent to the cloud platform through the communication module. The cloud platform has a data feature extraction and encoding unit, a food radiation amount prediction unit, a status information generation unit and a cloud platform side communication unit. Therefore, feature extraction and encoding can be performed based on the nuclear radiation measurement data as the input of the machine learning model, and the predicted values ​​of the nuclear radiation amount of various foods are obtained through the model, and then the corresponding status information is generated based on the predicted values ​​and sent to the user terminal. The present invention fills the gap in the prior art of nuclear radiation detection equipment and methods at cold chain terminals, and can obtain predicted values ​​of nuclear radiation amounts of various foods stored in refrigeration equipment through machine learning models. Therefore, it also solves the problem that existing nuclear radiation detectors can only measure the nuclear radiation amount in a certain space but cannot effectively distinguish the nuclear radiation amount of various foods. Even if a variety of foods are mixed in the refrigeration equipment, radiation level predictions of various foods can be obtained, thereby providing valuable reference data for managers, loaders, etc. of the refrigeration equipment, enabling them to better manage frozen foods. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a logic block diagram of a frozen food nuclear contamination monitoring system according to an embodiment of the present invention;

[0018] Figure 2 is a side view of a refrigeration device in an embodiment of the present invention;

[0019] Figure 3 is a side view of a partial structure of a refrigeration device in an embodiment of the present invention;

[0020] Figure 4 is a top view of a partial structure of a refrigeration device in an embodiment of the present invention;

[0021] Figure 5 is a cross-sectional view of a refrigeration device in an embodiment of the present invention;

[0022] Figure 6 is a logic block diagram of a temperature control detection device in an embodiment of the present invention;

[0023] Figure 7 is a circuit diagram of a main control module in an embodiment of the present invention;

[0024] Figure 8 is a circuit diagram of a 485 communication submodule in an embodiment of the present invention;

[0025] Fig. 9 is a circuit diagram of a 4G communication submodule in an embodiment of the present invention;

[0026] Fig.10 is a logical block diagram of a cloud platform in an embodiment of the present invention;

[0027] Fig.11 is a schematic diagram of nuclear pollution monitoring results in an embodiment of the present invention;

[0028] Fig.12 It is a flow chart of nuclear contamination monitoring of frozen food in an embodiment of the present invention.

[0029] Reference numerals:

[0030] Frozen food nuclear contamination monitoring system 100; refrigeration equipment 10; cabinet 11; storage cavity 111; equipment cavity 112; refrigeration device 13; temperature control detection device 14; main control module 141; power conversion module 142; temperature detection module 143; temperature sensor 1431; refrigeration device control module 144; nuclear radiation detection module 145; nuclear radiation detection sensor 1451; communication module 146; 485 communication submodule 1461; 4G communication submodule 1462; equipment information storage module 147; nuclear contamination monitoring cloud platform 20; cloud platform side communication unit 21; data preprocessing unit 22; abnormal value processing part 221; missing Value processing part 222; standardization processing part 223; data feature extraction encoding part 23; data storage part 24; equipment information storage part 241; food information storage part 242; original nuclear radiation data part 243; pre-processed data temporary storage part 244; prediction model storage part 245; prediction data storage part 246; threshold information storage part 247; food radiation amount prediction part 25; food radiation amount exceeding standard judgment part 26; status information generation part 27; timing diagram generation part 271; thermal map generation part 272; bar graph generation part 273; cloud platform side control part 28; administrator terminal 31; loader terminal 32. DETAILED DESCRIPTION

[0031] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the frozen food nuclear contamination monitoring system of the present invention is specifically described below in conjunction with the embodiments and drawings.

[0032] Figure 1 It is a logic block diagram of the frozen food nuclear contamination monitoring system in this embodiment.

[0033] like Figure 1 As shown, the frozen food nuclear contamination monitoring system 100 includes one or more refrigeration equipment 10, a nuclear contamination monitoring cloud platform 20, and multiple user terminals. The cloud platform 20 is respectively connected to the multiple refrigeration equipment 10 and the multiple user terminals in a wireless communication manner.

[0034] Each refrigeration device 10 is used to store food and keep it at a predetermined low temperature, and uses a variety of sensors to collect relevant data of the food. The refrigeration device 10 can be a large refrigerator installed in a shopping mall, a large supermarket, a food processing plant, etc., or a refrigerator installed in an ordinary user's home.

[0035] The cloud platform 20 is used to obtain sensor data from each refrigeration device 10, and monitor the frozen food in the refrigeration device 10 based on the sensor data, including monitoring of nuclear contamination, and generate monitoring results.

[0036] The user terminal is used to obtain monitoring results from the cloud platform 20 and display them accordingly, so that users can promptly know the status of frozen food, including whether it has excessive nuclear contamination. When the refrigeration equipment 10 is a large refrigerator installed in scenes such as shopping malls, large supermarkets, and food processing plants, the user terminal may include an administrator terminal 31 and a loader terminal 32, which are respectively held by an administrator who manages multiple large refrigerators and a loader who loads goods on large refrigerators. When the refrigeration equipment 10 is a refrigerator installed at home, the user terminal may be a terminal held by a family member. The terminal may include a smart phone, a smart tablet, a computer, etc.

[0037] Figure 2 is a side view of the refrigeration equipment in this embodiment, Figure 3 This is a side view of the refrigeration equipment part of the present embodiment, to show the internal structure. Figure 3 Some side panels of the cabinet are omitted; Figure 4 This is a top view of the refrigeration equipment part of the present embodiment, to show the internal structure. Figure 4 The upper cover and part of the cabinet cavity structure are omitted; Figure 5 2 is a cross-sectional view of the refrigeration equipment in this embodiment.

[0038] like Figures 2 to 5 As shown, the refrigeration device 10 of this embodiment is a large horizontal freezer, which includes a cabinet body 11, a cabinet cover (not shown in the figure), a refrigeration device 13, and a temperature control detection device 14.

[0039] The cabinet 11 is rectangular in shape as a whole, with an open top. The cabinet cover is arranged at the top opening. It can be rotatably connected to the upper end of the cabinet 11, or it can be in the form of two cover plates that can be horizontally pushed and pulled and arranged at the top opening. Two mutually separated rectangular cavities are formed inside the cabinet 11. The upper cavity is a storage cavity 111, and the lower cavity is an equipment cavity 112. The storage cavity 111 is used to store food. The equipment cavity 112 is used to set internal equipment such as a refrigeration device 13.

[0040] The refrigeration device 13 is used to refrigerate the food in the storage cavity 111 .

[0041] The temperature control detection device 14 is used to detect the current temperature of the food in the storage cavity 111, and control the power of the refrigeration device 13 according to the detected temperature and the predetermined standard temperature range to achieve real-time temperature control. In addition, the temperature control detection device 14 is also used to detect the nuclear contamination of the food in the storage cavity 111.

[0042] Figure 6 It is a logic block diagram of the temperature control detection device in this embodiment.

[0043] like Figure 6As shown, the temperature control detection device 14 includes a main control module 141 and a power conversion module 142, a temperature detection module 143, a refrigeration device control module 144, a nuclear radiation detection module 145, a communication module 146, and an equipment information storage module 147 which are electrically connected to the main control module 141 respectively.

[0044] The power conversion module 142 is used to convert the external power supply into a stable DC power supply that can be used by the single-chip microcomputer and other modules.

[0045] The temperature detection module 143 includes a temperature sensor 1431 and a corresponding circuit. The temperature sensor 1431 is arranged on one side of the storage cavity 111. The probe of the temperature sensor 1431 is arranged at the corresponding through hole on the side wall of the storage cavity 111, and the probe faces the inside of the storage cavity 111, so that the current temperature inside the storage cavity 111 can be measured.

[0046] The main control module 141 periodically obtains the measured temperature from the temperature detection module 143, and calculates the amount to be adjusted based on the measured temperature and the pre-set standard temperature range, and controls the refrigeration device control module 144 according to the amount to be adjusted. The refrigeration device control module 144 controls the refrigeration power of the refrigeration device 13 according to the amount to be adjusted, thereby adjusting the real-time temperature inside the storage cavity 111 to keep it within the above-mentioned standard temperature range.

[0047] The nuclear radiation detection module 145 includes a nuclear radiation detection sensor 1451, which is also arranged beside one side of the storage cavity 111 and relatively close to the top opening of the cabinet 11. The probe of the radiation detection sensor 1451 is arranged at the corresponding through hole on the side wall of the storage cavity 111, and the probe is located near the top opening and faces the inside of the storage cavity 111, so that the current nuclear radiation amount of the frozen food placed in the storage cavity 111 can be measured. In this embodiment, the nuclear radiation detection module 145 is a nuclear radiation detection module, and its model is MR-10-J. The types of rays it measures include gamma rays and X-rays, and it has an RS485 output interface, and data can be directly read through the RS485 digital communication protocol. It has a nuclear radiation detector, which is a glass Geiger counter tube, and the above-mentioned probe is a part of the detector.

[0048] The main control module 141 can obtain the food nuclear radiation amount measured by the nuclear radiation detection module 145, and perform analog-to-digital conversion on it to obtain the food nuclear radiation measurement value.

[0049] The communication module 146 is used by the main control module 141 to obtain the food nuclear radiation measurement value and send it to an external device. In this embodiment, it includes a 485 communication sub-module 1461 and a 4G communication sub-module 1462.

[0050] Figure 7is a circuit diagram of the main control module in this embodiment, Figure 8 It is a circuit diagram of the 485 communication submodule in this embodiment.

[0051] like Figure 7 and Figure 8 As shown, the main control module 141 includes a microprocessor (MCU) U303, whose model is STM32WBA52CG and has pins 1-52.

[0052] The 485 communication submodule 1461 includes a connection terminal P407, an RS485 transceiver chip U404, a transistor Q404, and multiple resistors and capacitors.

[0053] The connection terminal P407 has pins 1 to 4 for connecting to the nuclear radiation detector. Pin 1 of the connection terminal P407 is grounded, pin 4 is connected to a 5V power supply, pin 3 is connected to the RS485 A terminal of the nuclear radiation detector, and pin 4 is connected to the RS485 B terminal of the nuclear radiation detector.

[0054] The RS485 transceiver chip U404 has pins 1 to 7, wherein pin 1 is connected to pin 24 (RX2) of the microprocessor U303; pin 2 is short-circuited with pin 3 and connected to the collector of transistor Q404, which is also connected to a 3.3V power supply through a resistor R411; the base of transistor Q404 is connected to pin 25 (TX2) of the microprocessor U303 through a resistor R416, and its emitter is grounded; pin 4 is connected to pin 25 (TX2) of the microprocessor U303; pin 5 is grounded; pin 6 is connected to pin 7 (TX2) of the microprocessor U303; pin 7 is connected to ground; pin 8 is connected to pin 9 (TX2) of the microprocessor U303; pin 9 is connected to pin 10 (TX2) of the microprocessor U303; pin 10 is connected to ground; pin 11 is connected to pin 12 (TX2) of the microprocessor U303; pin 12 is connected to ground; pin 13 is connected to pin 14 (TX2) of the microprocessor U303; pin 14 is connected to pin 15 (TX2) of the microprocessor U303; pin 15 is connected to ground; pin 16 is connected to pin 17 (TX2) of the microprocessor U303; pin 17 is connected to pin 18 (TX2) of the microprocessor U303; pin 18 is connected to pin 19 (TX2) of the microprocessor U303; pin 19 is connected to pin 20 (TX2) of the microprocessor U303; pin 10 is connected to pin 21 (TX2) of the microprocessor U303; pin 11 is connected to pin 22 (TX2) of the microprocessor U303; pin 12 is connected to pin 23 ( It is connected to the cathode of diode D403 through resistor R414, the anode of diode D403 is grounded, the cathode of diode D403 is also connected to the 3.3V power supply through resistor R412, and is also grounded through capacitor C413; pin 7 is connected to the cathode of diode D404 through resistor R417, the anode of diode D404 is grounded, the cathode of diode D404 is also connected to the cathode of diode D403 through resistor R415, and is also grounded through resistor R418, and is also grounded through capacitor C414.

[0055] Pin 3 of the connection terminal P407 is connected to pin 6 of the RS485 transceiver chip U404 through a resistor R414, and pin 2 of the connection terminal P407 is connected to pin 7 of the RS485 transceiver chip U404 through a resistor R417. Therefore, the RS485 transceiver chip U404 can receive the current radiation amount measured by the nuclear radiation detector through the RS485 protocol, and then transmit the received current radiation amount to the microprocessor U303.

[0056] Fig. 9 4G communication submodule in this embodiment.

[0057] like Fig. 9 As shown, the 4G communication submodule 1462 includes a connection terminal P100, 4G communication chips U100A, U100B, U100C, and U100D, all of which are EC800E-CN. The 4G communication chip U100A has pins 1 to 44 and 95 to 98, the 4G communication chip U100B has pins 45 to 72 and 99 to 106, the 4G communication chip U100C has pins 73 to 81 and 107 to 109, and the 4G communication chip U100D has pins 89 to 94. The connection terminal P100 has pins 1 to 4 for connecting a USB device.

[0058] Among them, pins 11 to 13 of the 4G communication chip U100A are respectively connected to the corresponding interfaces of the SIM card, and are used for data input and output, clock output, and reset respectively. Pin 17 of the 4G communication chip U100A is connected to pin 28 of the microprocessor U303, and pin 18 of the 4G communication chip U100A is connected to pin 29 of the microprocessor U303. Therefore, the microprocessor U303 can send the current radiation amount obtained to the cloud platform 20 or other external devices through the 4G communication protocol.

[0059] The device information storage module 147 is used to store the device information of the refrigeration device 10, including the device unique identification number, device model, device location and other information.

[0060] Fig.10 It is a logical block diagram of the nuclear radiation monitoring cloud platform in this embodiment.

[0061] like Fig.10 As shown, the cloud platform 20 includes a cloud platform side communication unit 21, a data preprocessing unit 22, a data feature extraction and encoding unit 23, a data storage unit 24, a food radiation amount prediction unit 25, a food radiation amount exceeding the standard judgment unit 26, a status information generation unit 27, and a cloud platform side control unit 28.

[0062] The cloud platform side communication unit 21 is used to communicate with other devices, including obtaining the food nuclear radiation measurement data measured by the nuclear radiation detection module 145 of each refrigeration device 10, and obtaining its device information from its device information storage module 147, and the food nuclear radiation measurement data at least includes the nuclear radiation measurement value of the food stored in the refrigeration device 10 and the corresponding timestamp. In this embodiment, corresponding to the setting of the nuclear radiation detection module 145, the cloud platform side communication unit 21 also includes a 4G communication module, which can obtain the data through 4G communication.

[0063] In an alternative solution, the cloud platform-side communication unit 21 may further obtain the temperature measurement data measured by the nuclear radiation detection module 145 of the refrigeration equipment 10, including the temperature measurement value in the cabinet and the corresponding timestamp.

[0064] The data preprocessing unit 22 is used to preprocess a batch of food radiation data obtained by the cloud platform side communication unit 21 at predetermined intervals, and temporarily store the preprocessed data in the data storage unit 23. The data preprocessing unit 22 includes an abnormal value processing part 221, a missing value processing part 222, and a standardization processing part 223.

[0065] Among them, the outlier processing part 221 uses the interquartile range (IQR) method to remove the data points (i.e. outliers) in the multiple nuclear radiation amounts of each type of food based on the original food nuclear radiation data. Specifically, for a batch of food nuclear radiation data within a period of time, the first quartile (denoted as Q1) and the third quartile (Q3) are calculated based on the multiple nuclear radiation measurement values ​​in this batch of data, and the upper and lower limits are set based on the two respectively: the lower limit is Q1- 1.5*IQR, and the upper limit is Q3 + 1.5*IQR, and the data points exceeding the upper and lower limits are removed, so as to obtain the food nuclear radiation measurement data after removing the outliers.

[0066] The missing value processing part 222 fills the missing values ​​in the data by using the linear interpolation method or the mean filling method for each type of food data based on the food nuclear radiation data after removing the abnormal values. Specifically, the linear interpolation method uses the mean of the two data points before and after the missing value (sorted by time) to fill the missing value; the mean filling method uses the mean of the column (that is, the mean of the nuclear radiation measured for all other types of food) to fill the missing values ​​in the data, thereby obtaining the food nuclear radiation measurement data after filling the missing values.

[0067] The standardization processing part 223 is used to standardize the food nuclear radiation measurement data after filling the missing values, and obtain the standardized food nuclear radiation measurement data, that is, the food nuclear radiation measurement data after preprocessing. Specifically, the Z-score standardization method is used to convert multiple nuclear radiation measurement values ​​into a standard normal distribution.

[0068] The data feature extraction and encoding unit 23 is used to extract multiple features from the pre-processed nuclear radiation data, and encode the extracted features to form a set of coded features for inputting the prediction model. In this embodiment, a set of coded features includes food type features, food weight features, and time features. Among them, the food type feature is a vector after one-hot encoding based on the food name, food category name, etc. The food weight feature is the food weight value. The storage quantity of the food in the refrigeration device 10 and the weight of each portion of food can be queried according to the unique equipment identification code and the food unique identification code, and the food weight value can be further calculated. The time feature is the timestamp of collecting the corresponding food nuclear radiation measurement value.

[0069] The data storage unit 24 is used to store various data, including an equipment information storage part 241, a food information storage part 242, an original nuclear radiation data part 243, a pre-processed data temporary storage part 244, a prediction model storage part 245, a prediction data storage part 246, and a threshold information storage part 247.

[0070] The device information storage part 241 is used to store the device information of each refrigeration device 10 , including the unique device identification number, device model, device location, etc. of the refrigeration device 10 .

[0071] In an alternative solution, the nuclear radiation detection module 145 may further include a GPS positioning module for acquiring GPS positioning information of the refrigeration equipment 10 as a more accurate equipment location.

[0072] The food information storage part 242 is used to store the frozen food information of the food stored in each refrigeration device 10, which includes the unique equipment identification number of the refrigeration device 10, the unique food identification number of the food stored in the device, the food name, the food quantity, the food weight, etc.

[0073] The original nuclear radiation data part 243 is used to store the original nuclear radiation measurement data obtained from each refrigeration device 10, and the original nuclear radiation measurement data includes the device unique identification number of the refrigeration device 10, the measured nuclear radiation measurement value and the corresponding time stamp.

[0074] The pre-processed data temporary storage part 244 is used to store the nuclear radiation measurement data pre-processed by the data pre-processing unit 22 .

[0075] The prediction model storage part 245 is used to store the food nuclear radiation prediction model, which is a trained machine learning model. In this embodiment, it is a gradient boosting decision tree (GBDT) model, and its input features are the above-mentioned set of encoding features (food type features, food weight features, time features); the output prediction result is the predicted value of the food nuclear radiation of the corresponding type of food.

[0076] When training the above model, multiple groups of data of different situations of the same type of refrigeration equipment 10 can be collected as training data sets, and the collected data can include but are not limited to the following situations and their combinations: only the same type of food is placed in the refrigeration equipment 10; multiple types of food are mixed in the refrigeration equipment 10; only a batch of food produced on the same date is placed in the refrigeration equipment 10; multiple batches of food produced on different dates are placed in the refrigeration equipment 10 (i.e., simulating the situation of replenishment); a small amount of food is placed in the refrigeration equipment 10 (the food is far away from the probe of the nuclear radiation detector, for example, less than 1 / 4 of the food is placed in the storage cavity 111 and roughly spread it on the bottom layer of the storage cavity 111, that is, 1 / 4 of the maximum storage capacity is placed); a large amount of food is placed in the refrigeration equipment 10 (for example, more than 3 / 4 of the maximum storage capacity of food is placed in the storage cavity 111); roughly half of the maximum storage capacity of food is placed in the refrigeration equipment 10, and the food is placed as far away from the probe as possible; roughly half of the maximum storage capacity of food is placed in the refrigeration equipment 10, and the food is placed as close to the probe as possible, and so on.

[0077] For each of the above situations and their combinations, a large amount of data can be collected as a training data set, and for a small amount of data in each situation, other more accurate methods can be used to measure the nuclear radiation amount of food as the actual value, and the measured values ​​measured by the nuclear radiation detection module 145 are manually recorded in correspondence with the actual value, and these data are used as a test set to test and verify the model after a certain training.

[0078] Based on the above training data set, the gradient boosting decision tree optimizes the model by gradually adding decision trees, and each step will reduce the residual of the current model. In this embodiment, after multiple rounds of training, the accuracy and mean square error (MSE) are used to evaluate the effect of the trained model. If the indicators are not up to standard, the model can be further trained.

[0079] The prediction data storage part 246 is used to store food nuclear radiation prediction data, including food type, nuclear radiation prediction value output by the model and corresponding timestamp.

[0080] The threshold information storage part 247 is used to store a variety of threshold information for comparison, including food nuclear radiation threshold information, which includes a predetermined food unique identification number of multiple types of food, food name, unit food nuclear radiation safety threshold (upper limit), etc. The unit food nuclear radiation safety threshold, for example, for a certain type of food, is 500 becquerels / kg.

[0081] The food radiation amount prediction unit 25 is used to input the pre-processed food nuclear radiation data into the nuclear radiation amount prediction model, so as to obtain the prediction result, that is, the nuclear radiation amount prediction value of each type of food stored in the refrigeration device 10.

[0082] The food radiation exceeding standard judging unit 26 is used to judge whether the food radiation exceeds the standard, that is, to judge whether the predicted value is greater than or equal to the safety threshold, based on the food radiation prediction value of the unit food radiation prediction unit 24 and the corresponding food radiation safety threshold stored in the data storage unit 24. If it is judged to be yes, it means that the food radiation exceeds the standard and there is nuclear contamination. In this embodiment, the food radiation exceeding standard judging unit 26 also obtains the food radiation prediction value within a period of time from the data storage unit 24, calculates the average of these predicted values, and judges whether the average is greater than or equal to the safety threshold.

[0083] In an alternative solution, the data storage unit 24 may also store multiple threshold ranges, and the food radiation exceeding standard judgment unit 26 judges which threshold range the predicted value falls into, so as to not only judge whether the nuclear radiation level of the food exceeds a safety threshold, but also further obtain the level of the nuclear radiation level of the food, for example, dividing the threshold range into four levels, corresponding to basically no nuclear radiation, low risk, high risk, and nuclear radiation exceeding standard. In this way, the food with the nuclear radiation level graded can be better managed.

[0084] The status information generating unit 27 generates corresponding status information based on the pre-processed food radiation data, the predicted radiation amount, and the judgment result of whether the radiation amount exceeds the standard, so as to display it to the user.

[0085] In this embodiment, it includes a timing diagram generating part 271, a heat map generating part 272, and a bar chart generating part 273. The generated status information is visualized status information. In an alternative solution, the status information generating part 27 may also include one of them or a combination of any several of them.

[0086] Fig.11 Schematic diagram of the visualization result of nuclear pollution monitoring in this embodiment.

[0087] like Fig.11 As shown, the time series diagram generating section 271 generates a time series diagram ( Fig.11 The horizontal axis of the graph is time in hours, and the vertical axis is the radiation measurement value in the freezer in becquerels, which can intuitively show the radiation level in the freezer at different time points and the change of the radiation level in the freezer over time. This allows managers or loaders to more easily locate a batch of food that was loaded at a specific time.

[0088] In this embodiment, the time series graph is drawn using the chart library Chart.js.

[0089] The heat map generating part 272 generates a heat map ( Fig.11 In B, the background of the figure is a regional map of the area where multiple refrigeration equipment 10 are located, and the foreground is a semi-transparent circle of different colors (other shapes may also be used), and different nuclear radiation measurement value ranges are marked with different colors, so that the distribution of nuclear radiation levels at different equipment locations in an area can be intuitively displayed. This allows administrators or loaders to more easily locate equipment with nuclear contamination risks, and can also handle each equipment in order from high to low according to the nuclear radiation level.

[0090] In this embodiment, the heat map is drawn using Mapbox, a tool of Geographic Information System (GIS).

[0091] The bar graph generating part 273 generates a bar graph according to the predicted value of food nuclear radiation corresponding to each food type and the judgment result of whether the radiation amount exceeds the standard. Fig.11 C in the figure), the horizontal axis of the figure is the food type, and the vertical axis is the average value of the predicted nuclear radiation value of the food. Each column in the figure represents the average value of the predicted nuclear radiation value of a food, and different colored columns are used to mark the food with excessive / not excessive nuclear radiation levels, so as to intuitively display the average nuclear radiation level and distribution of different food types. This makes it easier for administrators or loaders to pay attention to the types of food with high or excessive average nuclear radiation levels over a period of time and manage them in a targeted manner.

[0092] In this embodiment, the bar chart is also drawn using the chart library Chart.js.

[0093] In this embodiment, after the status information generating unit 27 generates the above status information, the cloud platform side communication unit 21 sends it to each administrator terminal 31 and each loading staff terminal 32 respectively. After receiving the information, the terminal displays the corresponding chart, so that the administrator and the loading staff can intuitively know the nuclear contamination of the frozen food in the corresponding refrigeration equipment 10, and timely handle the frozen food with excessive nuclear contamination and the corresponding refrigeration equipment 10. The cloud platform 20 can actively push the above status information to the terminal according to the pre-set settings, or can also send the above status information of the corresponding time period to the terminal according to the request from the terminal, so that the administrator or loading staff can also query the historical data and charts of nuclear radiation detection.

[0094] In an alternative solution, the state information generating unit 27 may further generate a corresponding chart based on the obtained temperature data and send it to the terminal.

[0095] In an alternative solution, a portion of the generated chart may be sent to a user terminal held by the consumer, such as sending the above-mentioned bar chart to the user terminal, so that the consumer can intuitively know the current nuclear radiation level of various types of food, so that they can purchase with greater confidence.

[0096] In an alternative solution, the above-mentioned charts may also be displayed on a display on the cloud platform 20 side, or the cloud platform 20 may be further connected to other computing and analysis equipment, such as equipment that further analyzes the comprehensive status of multiple refrigeration equipment 10. The cloud platform 20 may send the original nuclear radiation measurement data, preprocessed nuclear radiation measurement data, food nuclear radiation prediction values, and any one or more combinations of the above-mentioned multiple charts to the computing and analysis equipment so that it can combine these data and / or charts for further analysis and display.

[0097] The cloud platform side control unit 28 is used to perform overall control over the work of the above-mentioned functional units.

[0098] Fig.12 1 is a flow chart of nuclear contamination monitoring of frozen food in this embodiment.

[0099] like Fig.12 As shown, the process of using the frozen food nuclear contamination monitoring system 100 to monitor the nuclear contamination of frozen foods stored in multiple refrigeration equipment 10 specifically includes the following steps:

[0100] In step S1 , the nuclear radiation detection module 145 (probe of a nuclear radiation detector) of the refrigeration device 10 detects the current nuclear radiation amount in the storage cavity 111 of the cabinet 11 .

[0101] Step S2, the main control module 141 obtains the nuclear radiation amount from the nuclear radiation detection module 145, converts it into a corresponding nuclear radiation measurement value, and sends the nuclear radiation measurement data including the measurement value and timestamp to the cloud platform 20.

[0102] Step S3, the cloud platform side communication unit 21 obtains the nuclear radiation measurement data from the refrigeration equipment 10, and the data preprocessing unit 22 preprocesses the nuclear radiation measurement data, including the above-mentioned outlier removal, missing value filling and standardization.

[0103] Step S4: the data feature extraction and encoding unit 23 extracts and encodes the preprocessed nuclear radiation measurement data to obtain encoding features.

[0104] Step S5, the food radiation prediction unit 25 inputs the coding features into the food radiation prediction model, and the model outputs the corresponding nuclear radiation prediction values ​​of various types of food.

[0105] Step S6, the food radiation excess judgment unit 26 obtains the predicted value of food nuclear radiation within a period of time, calculates its mean, and determines whether the mean exceeds a predetermined safety threshold.

[0106] Step S7, the status information generation unit 27 generates a timing diagram, a heat map, and a bar graph according to the original nuclear radiation measurement data, the nuclear radiation prediction value, and the judgment result of whether the radiation amount exceeds the standard, and the cloud platform side communication unit 21 sends these charts to each administrator terminal 31 and each loader terminal 32.

[0107] Step S8, each administrator terminal 31 and each loader terminal 32 receives the above chart, and the administrator and the loader manage the refrigeration equipment 10 and the food therein according to the nuclear radiation level of the food in the refrigeration equipment 10 shown in the chart.

[0108] It is understandable that the refrigeration device 10 can send its measured nuclear radiation measurement data to the cloud platform 20 regularly according to the settings, that is, repeat the above steps regularly, or the cloud platform 20 can send a corresponding request as needed, and the refrigeration device 10 sends the nuclear radiation measurement data accordingly according to the received request. For example, when there is a relatively high risk of nuclear contamination in the near future according to other information, the cloud platform 20 can send the above request at a relatively higher frequency to achieve more frequent monitoring, so that relevant situations can be discovered more quickly when there is a risk of nuclear contamination.

[0109] The above embodiments have the following effects.

[0110] The frozen food nuclear contamination monitoring system provided according to the present embodiment includes one or more temperature control detection devices, a cloud platform and one or more user terminals. The temperature control detection device is arranged in the refrigeration equipment and has a nuclear radiation detection module, a main control module and a communication module. Therefore, the nuclear radiation detection module can be used to detect the nuclear radiation amount in the refrigeration equipment, and then the corresponding nuclear radiation measurement data can be obtained through the main control module, and the data is sent to the cloud platform through the communication module. The cloud platform has a data feature extraction and encoding unit, a food radiation amount prediction unit, a status information generation unit and a cloud platform side communication unit. Therefore, feature extraction and encoding can be performed based on the nuclear radiation measurement data as the input of the machine learning model, and the predicted values ​​of the nuclear radiation amount of various foods are obtained through the model, and then the corresponding status information is generated based on the predicted values ​​and sent to the user terminal. The present invention fills the gap in the prior art of nuclear radiation detection equipment and methods at cold chain terminals, and can obtain predicted values ​​of nuclear radiation amounts of various foods stored in refrigeration equipment through machine learning models. Therefore, it also solves the problem that existing nuclear radiation detectors can only measure the nuclear radiation amount in a certain space but cannot effectively distinguish the nuclear radiation amount of various foods. Even if a variety of foods are mixed in the refrigeration equipment, radiation level predictions of various foods can be obtained, thereby providing valuable reference data for managers, loaders, etc. of the refrigeration equipment, enabling them to better manage frozen foods.

[0111] In an embodiment, the machine learning model is a gradient boosting decision tree model, which optimizes the model by gradually adding decision trees, and each step reduces the residual of the current model, so the prediction performance of the model can be stably improved based on the training data.

[0112] Furthermore, the training data set contains nuclear radiation measurement data obtained from similar refrigeration equipment in a variety of different situations. Therefore, the trained model has better generalization performance and can output highly accurate prediction results for a variety of actual situations.

[0113] Furthermore, the cloud platform also includes a data preprocessing unit, which preprocesses the original data, including removing outliers, filling missing values, and standardizing the data. Since the original nuclear radiation measurement data is sparse and noisy, and is multi-source heterogeneous data, the fusion processing is relatively complex. Therefore, the direct prediction effect using the original data is not ideal. After the above preprocessing, the data quality and analysis accuracy can be improved.

[0114] Furthermore, the status information generation unit generates time series graphs, heat maps and bar graphs based on the pre-processed data, predicted data and judgment results, which can provide administrators and loaders with comprehensive and intuitive information related to the nuclear radiation levels of food, allowing them to intuitively and quickly discover problems, give priority to and promptly deal with frozen foods with nuclear contamination, thereby better managing the storage of multiple refrigeration equipment.

[0115] Furthermore, in the temperature control detection device, a 485 communication submodule is used to obtain the nuclear radiation amount from the nuclear radiation detection module, and a 4G communication module is used to send the nuclear radiation measurement data to the cloud platform. In this way, there is no need to set up additional wiring outside the refrigeration equipment for the nuclear radiation monitoring function, and there is no specific requirement for the location of the refrigeration equipment. The above solution can be directly deployed in refrigeration equipment in shopping malls, large supermarkets and other scenarios, which has high practical value.

[0116] The above embodiments are only used to illustrate the specific implementation of the present invention, and the present invention is not limited to the description scope of the above embodiments. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only to illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A frozen food nuclear contamination monitoring system, used for monitoring frozen food including nuclear contamination monitoring, characterized in that: include: One or more temperature control detection devices, respectively arranged in one or more refrigeration equipment for storing the frozen food; A cloud platform, respectively connected to each of the temperature control detection devices for communication; as well as One or more user terminals, held by administrators and / or loaders, Wherein, the temperature control detection device comprises: A nuclear radiation detection module, comprising a nuclear radiation detection sensor disposed in the cabinet of the refrigeration equipment, for detecting the amount of nuclear radiation of the frozen food in the cabinet; A main control module generates corresponding nuclear radiation measurement data based on the nuclear radiation amount; and A communication module, used to send the nuclear radiation measurement data to the cloud platform, The cloud platform at least includes: A data feature extraction and encoding unit is used to extract features and encode the nuclear radiation measurement data to obtain encoding features; The food radiation prediction unit inputs the coding features into the trained machine learning model to obtain the predicted values ​​of nuclear radiation for various types of food; a state information generating unit, which generates state information of various types of food based at least on the predicted value of nuclear radiation amount; and The communication unit on the cloud platform side is used to obtain the nuclear radiation measurement data from the communication module and send the status information to the user terminal.

2. The frozen food nuclear contamination monitoring system according to claim 1, characterized in that: in, The machine learning model is a gradient boosting decision tree model, The training data set used to train the machine learning model includes the nuclear radiation measurement data collected from the refrigeration equipment in different situations.

3. The frozen food nuclear contamination monitoring system according to claim 2, Features: in, The training data set includes the nuclear radiation measurement data collected from the following situations and / or combinations thereof: The same type of food is placed in the refrigeration equipment; Multiple types of food are mixed and placed in the refrigeration equipment; The refrigeration equipment is filled with food produced on the same date; A plurality of foods produced on different dates are placed in the refrigeration equipment; The refrigeration equipment contains less than 1 / 4 of its maximum storage capacity of food; and The refrigeration device is filled with more than 3 / 4 of its maximum storage capacity.

4. The frozen food nuclear contamination monitoring system according to claim 2, characterized in that: in, The coding features include food type features, food weight features and time features. The food type feature is a vector obtained by one-hot encoding based on at least the food name and the food type name of the food.

5. The frozen food nuclear contamination monitoring system according to claim 1, Features: The temperature control detection device further includes an equipment information storage module, which stores equipment data of the refrigeration equipment, which at least includes equipment location, The cloud platform side communication unit is also used to obtain the device data from the temperature control detection device. The food nuclear radiation measurement data includes multiple groups of food nuclear radiation measurement values ​​and corresponding timestamps. The state information generating unit comprises: A time series diagram generating part generates a time series diagram according to the food nuclear radiation measurement data, wherein the horizontal axis of the diagram is time and the vertical axis is the corresponding nuclear radiation measurement value; a heat map generating part, which generates a heat map based on the food nuclear radiation measurement data and the equipment data, wherein the background of the map is a regional map of the area where the refrigeration equipment is located, and the foreground is a semi-transparent graphic of different colors, the color of which corresponds to the nuclear radiation measurement value of the equipment location where the graphic is located; and / or The bar graph generating part generates a bar graph according to each of the food types and the corresponding predicted nuclear radiation values, wherein each bar in the graph represents the average value of the predicted nuclear radiation value of a food type.

6. The frozen food nuclear contamination monitoring system according to claim 5, Features: The cloud platform further includes: A data storage unit, used for storing the predicted nuclear radiation value and the corresponding timestamp; and The food radiation excess judgment unit is used to obtain the predicted nuclear radiation value within a predetermined time range from the data storage unit, calculate the mean value, and judge whether the mean value is greater than or equal to a predetermined nuclear radiation safety threshold value. The state information generating unit further generates the state information based on a determination result of the food radiation level exceeding standard determining unit.

7. The frozen food nuclear contamination monitoring system according to claim 6, characterized in that: in, The bar graph generating part generates a bar graph according to each of the food types and the corresponding predicted nuclear radiation values, as well as the judgment result. Each bar in the graph represents the mean of the predicted nuclear radiation values ​​for a type of food, and the bars of different colors are used to indicate whether the mean of the corresponding food type exceeds / does not exceed the nuclear radiation safety threshold.

8. The frozen food nuclear contamination monitoring system according to claim 1 is characterized in that: in, The cloud platform also includes: The data preprocessing unit is used to preprocess the nuclear radiation measurement data, including removing outliers, filling missing values ​​and standardizing the nuclear radiation measurement data.

9. The frozen food nuclear contamination monitoring system according to claim 1, characterized in that: in, The cloud platform periodically sends a data acquisition request to the temperature control detection device of each of the refrigeration equipment, and the temperature control detection device sends the nuclear radiation measurement data to the cloud platform according to the data acquisition request.

10. The frozen food nuclear contamination monitoring system according to claim 1, Features: Wherein, the communication module includes: 485 communication submodule, connected to the main control module and the nuclear radiation detection module respectively, and used to obtain the nuclear radiation data from the nuclear radiation detection module through the RS485 communication protocol; and The 4G communication submodule is connected to the main control module and is in communication connection with the cloud platform, and is used to send the nuclear radiation measurement data to the cloud platform through the 4G communication protocol.

Images