A detection system and method for a frozen fresh-keeping production line based on the Internet of Things

Abstract

The present invention discloses a freezing and fresh-keeping production line detection system and method based on the Internet of Things, which relates to the technical field of the Internet of Things. The present invention connects and networks production line environment monitoring equipment in series through an Internet of Things platform; sets a monitoring window to collect monitoring data; comprehensively processes the collected data of each device through data cleaning, and constructs a curve model for the collected data using a curve simulation model; maps each data curve model to the same coordinate system to construct a control curve analysis model; analyzes the trend difference degree of each time point of the control curve, performs difference fusion analysis processing on each curve, and obtains a comprehensive curve model of the production environment; performs abnormal correlation analysis based on the comprehensive curve model in combination with historical production environment data, and regulates the production line environment data according to the analysis data; displays the monitoring data of each environmental device through a visual port, and regulates the real-time production line environment data based on the abnormal correlation analysis data of the comprehensive curve model.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a freezing and fresh-keeping production line detection system and method based on the Internet of Things. Background Art

[0002] IoT-based frozen fresh-keeping production line inspection utilizes advanced sensors, wireless communication technology, and cloud computing platforms to achieve real-time monitoring and intelligent control of key parameters such as temperature and humidity in the production line. By transmitting data to a cloud platform, managers can remotely monitor and adjust parameters in a timely manner to ensure product quality.

[0003] Under current technical conditions, people have improved the traditional manual monitoring and management mode by introducing remote monitoring equipment, and monitor and adjust the environmental temperature data of the production line in real time through the cloud platform; however, the current remote monitoring mode can only collect actual temperature data through monitoring equipment, and make alarm judgments and adjustments through preset values; however, there are two ways of control, one is local monitoring and control, when there is a local abnormality, local control is performed; the other is overall control, which monitors and adjusts the overall temperature; both of the above modes have defects, local control will cause excessive local temperature differences in the production line, resulting in unbalanced overall space temperature, which is not conducive to product storage; overall control will cause temperature monitoring to lag, and untimely control will lead to product damage; the above modes are not smart enough and the above temperature control is all range temperature control, which cannot perform intelligent and precise temperature adjustment according to actual conditions, and cannot perform correlation analysis on local temperature monitoring and intelligent environmental temperature control. Summary of the Invention

[0004] The purpose of the present invention is to provide a freezing and fresh-keeping production line detection system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for detecting a freezing and fresh-keeping production line based on the Internet of Things, the method comprising the following steps:

[0007] S100. Network and connect the production line environmental monitoring equipment through the Internet of Things platform, and record the data of each device by marking the device number; set up a monitoring window to collect the monitoring data of each device;

[0008] S200, retrieve data from each monitoring device through the data analysis platform, comprehensively process the data collected by each device through data cleaning, and use the curve simulation model to smooth and concatenate the time frame data of the data collected by each device to construct a curve model;

[0009] S300. Construct a control curve analysis model by mapping the data curve models of each device to the same coordinate system; analyze the trend differences of the control curves at each time point, perform differential fusion analysis on each curve, and obtain a comprehensive curve model for the production environment; perform abnormal correlation analysis based on the comprehensive curve model and historical production environment data, and adjust the production line environment data based on the analysis data;

[0010] S400. Display the monitoring data of each environmental device of the production line through the visual port, and adjust the real-time production line environmental data based on the abnormal correlation analysis data of the comprehensive curve model.

[0011] The S100 uses the Internet of Things platform to network and connect the production line environment monitoring equipment, and records the data of each device by marking the device number; the specific steps of setting the monitoring window and collecting the monitoring data of each device are as follows:

[0012] S101. Log into the IoT management platform for the frozen food production line to retrieve equipment data from the production line's environmental monitoring equipment. Establish a device association network to connect each monitoring device in series to the same supervisory network. In the supervisory network, number each device and create a device information column to record each device's information data. The monitoring device is a temperature sensor monitoring device. The device information includes device model data, location data, and operating hours.

[0013] S102. By setting a monitoring cycle window, the environmental data of the production line is monitored in real time through various environmental monitoring devices, and the monitoring data is collected and transmitted to the data analysis platform through the monitoring network; the environmental data is the environmental temperature data of the production line.

[0014] The specific steps of S200 for retrieving data from each monitoring device through the data analysis platform, comprehensively processing the data collected by each device through data cleaning, and using the curve simulation model to smooth and concatenate the time frame data collected by each device to construct a curve model are as follows:

[0015] S201. The data analysis platform retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the device number. The data of the time series temperature set corresponding to each device is cleaned and processed, and the data of each time series temperature set is comprehensively processed by filtering out erroneous data, missing data, and compensating data. The filtering out erroneous data, missing data, and compensating data involves filtering and marking abnormal erroneous data and missing data in each time series temperature set, and filling in data by averaging the compensating data. The comprehensive processing involves normalizing the dimensional length of the time series temperature set corresponding to each device.

[0016] S202. Import the processed time series temperature set data of each device into the simulation through the curve simulation model, import the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and connect the data in series through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

[0017] S300 maps the data curve models of each device to the same coordinate system to construct a control curve analysis model; analyzes the trend differences of the control curves at each time point, performs differential fusion analysis on each curve, and obtains a comprehensive curve model for the production environment; performs abnormal correlation analysis based on the comprehensive curve model and combines historical production environment data, and regulates the production line environment data based on the analysis data. The specific steps are as follows:

[0018] S301. Based on the ambient temperature curve fitted by the time series temperature set of each device, the ambient temperature curve corresponding to each device is mapped to the same coordinate system through the mapping coordinate system to construct a comparison curve analysis model; based on the comparison curve analysis model, trend difference analysis is performed based on the ambient temperature curve value corresponding to each device at each time point, and the value of each curve at the corresponding same time point is marked, and the overlap rate of the values ​​of each curve at the same time point is analyzed. The calculation formula is Cr(t)=m(t) / n(t); where Cr(t) is the overlap rate of each curve value at the corresponding time point t; m(t) is the overlap number of each curve value at the corresponding time point t; n(t) is the total number of each curve value at the corresponding time point t; by setting the comparison overlap rate threshold Cr(v), when the curve overlap rate corresponding to time point t Cr(t) ≥ Cr(v), the curve value of the overlap point of each curve at time t is used as the comprehensive ambient temperature data; if Cr(t) < Cr(v), trend difference analysis is performed on the curve value corresponding to time t, and the calculation formula is

[0019] ;

[0020] Where TDV(z,t) is the trend difference value of the corresponding numbered curve z at time t; k(z,t) is the curve derivative of the corresponding numbered curve z at time t; ave[k(n,t)] is the mean of the corresponding derivatives of each curve at time t; n is the number of curves; p(z,t) is the curve value of the corresponding numbered curve z at time t; ave[p(n,t)] is the mean of the corresponding curve values ​​of each curve at time t; where z is [1,n].

[0021] Based on the curve value of each curve at each time point, the curve value correlation analysis is performed, and the calculation formula is:

[0022] ;

[0023] Wherein, R(n,t) is the intra-group correlation value of the curve value on each curve at the corresponding time point t; combined with the trend difference analysis data of the curve value of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point, the corresponding curve value at each time point is screened out; if TDV(z,t)>R(n,t), the curve value of the numbered z curve at the current time point t is judged to be deviant data and is screened out; if TDV(z,t)≤R(n,t), the curve value of the numbered z curve at the current time point t is judged to be normal data and is retained; the said deviant data refers to the degree of difference between the average level of the data in the group and the degree of correlation between the data in the group, and there is a deviation effect between the curve value and the rest of the data in the group;

[0024] Based on the curve value screening results at each time point, the retained data at each time point is averaged and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by smoothing the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed;

[0025] S302, based on the comprehensive temperature curve of the production line environment in the current cycle, by retrieving the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, the temperature data of the production line in the current cycle corresponding to each time point is compared and analyzed. The calculation formula is:

[0026] ;

[0027] Wherein, OD(t) is the difference between the comprehensive temperature curve of the production line environment in the current cycle and the curve value corresponding to time t on the normal temperature fluctuation curve in the corresponding historical cycle; Y(min) and Y(max) are the maximum and minimum curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle, respectively; Q(min) and Q(max) are the maximum and minimum curve values ​​of the normal temperature fluctuation curve in the corresponding historical cycle, respectively; Y(t) and Q(t) are the curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle and the normal temperature fluctuation curve in the corresponding historical cycle, respectively, at time t.

[0028] By comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the corresponding historical cycle, if Y(t)>Q(max) or Y(t)<Q(min) exists on the comprehensive temperature curve of the production line environment in the current cycle, an abnormal alarm will be issued for the current production line environment temperature; if Y(t)∈[Q(min), Q(max)], the current production line environment will be regulated and analyzed by comparing the historical data. If Y(t)>Q(t), the current production line environment temperature data will be regulated by comparing the difference value of the curve value at the corresponding time point. The calculation formula is Y(t) g=Y(t)-Y(t)*OD(t); if Y(t)<Q(t), the current production line environmental data is regulated, and the calculation formula is Y(t) g =Y(t)+Y(t)*OD(t); if Y(t)=Q(t), then keep the current production line ambient temperature data; where Y(t) g is the production environment temperature data after regulation; when the actual production line temperature data is greater than the fluctuation range of the historical environment temperature data of the corresponding period, it means that the current environment temperature data is abnormal and an alarm needs to be issued; if the current environment temperature data is within the normal range but different from the historical data, it means that the influencing factors in the current environment are different from the historical environment. If it is greater than the historical data, it means that the current environment factors have caused the actual environment temperature to rise; if it is less than the historical data, it means that the current environment factors have caused the actual environment temperature to drop; the temperature is regulated by comparing the difference values; for the time point where the temperature regulation behavior occurs, the time observation interval is set, and no secondary temperature regulation is performed within the interval. It is used to observe the changing trend of the production line environment temperature after regulation; when the observation interval is exceeded, the above comparative regulation analysis is repeated.

[0029] The S400 displays the monitoring data of each environmental device of the production line through the visual port, and based on the abnormal correlation analysis data of the comprehensive curve model, the specific steps of regulating the real-time production line environmental data are as follows:

[0030] S401, using the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the frozen preservation production line in real time;

[0031] S402. Record the curve analysis model data of each device and output the abnormal environmental alarm status and temperature control data of the current production line.

[0032] A freezing and fresh-keeping production line detection system based on the Internet of Things, the system includes an equipment networking module, a data curve processing module, a comprehensive analysis and control module, and a data feedback output module;

[0033] The equipment networking module networks and connects the production line environment monitoring equipment through the Internet of Things platform, and records the data of each device in a network by marking the device number; sets a monitoring window to collect monitoring data of each device; the data curve processing module retrieves data from each monitoring device through the data analysis platform, comprehensively processes the data collected by each device through data cleaning, and uses the curve simulation model to smooth the time frame data of the data collected by each device to construct a curve model; the comprehensive analysis and control module constructs a control curve analysis model by mapping the data curve model of each device to the same coordinate system; by analyzing the trend difference degree of the control curve at each time point, each curve is subjected to difference fusion analysis and processing to obtain a comprehensive curve model of the production environment; based on the comprehensive curve model and combined with historical production environment data, an abnormal correlation analysis is performed, and the production line environment data is regulated according to the analysis data; the feedback output module displays the monitoring data of each environmental device of the production line through the visual port, and regulates the real-time production line environment data based on the abnormal correlation analysis data of the comprehensive curve model.

[0034] The device networking module includes a device networking construction unit and a periodic data acquisition unit;

[0035] The device networking construction unit logs into the Internet of Things management platform for the frozen fresh-keeping production line, retrieves device data from the production line's environmental monitoring equipment, and connects each monitoring device in series to the same supervision network by building a device association network. In the supervision network, each device is numbered and labeled, and a device information column is built to record the information data of each device. The monitoring device is a temperature sensing monitoring device.

[0036] The periodic data acquisition unit sets a monitoring period window and monitors the production line environmental data in real time through various environmental monitoring devices, collects the monitoring data and transmits it to the data analysis platform through the monitoring network; the environmental data is the production line environmental temperature data.

[0037] The data curve processing module includes a data overall processing unit and a data curve fitting unit;

[0038] The data analysis platform of the data coordination processing unit retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the number of each device; performs data cleaning on the time series temperature set corresponding to each device, and coordinates the data of each time series temperature set by filtering out erroneous data, missing data and supplementing data;

[0039] The data curve fitting unit imports the time series temperature set data processed by each device into simulation through the curve simulation model, imports the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and concatenates the data through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

[0040] The comprehensive analysis and control module includes a comprehensive environmental temperature curve analysis unit and a control unit for comparative environmental temperature data;

[0041] The comprehensive ambient temperature curve analysis unit is based on the ambient temperature curve fitted by the time series temperature set of each device, and the corresponding ambient temperature curve of each device is mapped to the same coordinate system through the mapping coordinate system to construct a control curve analysis model; based on the control curve analysis model, the trend difference analysis is performed based on the ambient temperature curve value of each device at each time point, and the value of each curve at the corresponding same time point is marked, and the value overlap rate of each curve at the same time point is analyzed; by setting the comparison overlap rate threshold, the value overlap rate at the same time point is judged; based on the judgment result, the comprehensive ambient temperature data of each time point is analyzed; if the curve at the corresponding time point is greater than or equal to the value overlap rate threshold, the corresponding The curve values ​​of the overlapping points of the curves at the time points are the comprehensive ambient temperature data; if they are less than the value overlap rate threshold, trend difference analysis is performed on each curve value; curve value correlation analysis is performed based on the curve values ​​of each curve at each time point; the curve values ​​corresponding to each time point are screened out based on the trend difference analysis data of the curve values ​​of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point; based on the curve value screening results at each time point, the data retained at each time point are averaged, and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by performing smooth curve fitting on the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed;

[0042] The control environment temperature data control unit is based on the comprehensive temperature curve of the production line environment in the current cycle, and by calling the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, performs a comparative difference value analysis on the temperature data of the production line corresponding to each time point in the current cycle; by comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the historical corresponding cycle, an alarm is issued for abnormal environment temperature data based on the comparison result; for normal environment temperature data, by comparing the environment temperature data of the corresponding historical moment, the current production line environment temperature data is controlled and analyzed based on the comparison result.

[0043] The data feedback output module includes a visual output unit and a control alarm instruction output unit;

[0044] The visual output unit uses the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the freezing and fresh-keeping production line in real time;

[0045] The control alarm instruction output unit records the curve analysis model data of each device and outputs the abnormal environmental alarm situation and temperature control data of the current production line.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention combines the Internet of Things platform to carry out serial networking of the environmental monitoring equipment of the freezing and fresh-keeping production line, and comprehensively processes the series of temperature data collected by the equipment, performs curve fitting, comprehensive curve fusion analysis, and compares and analyzes the historical data for regulation and control, thereby realizing intelligent detection and regulation of the production line environmental data; the present invention performs curve fitting on the local temperature data of the production line and performs overlap rate and trend difference analysis by analyzing the curve values ​​at each time point, thereby realizing overall fusion analysis of the local temperature data of the production line; by retrieving the historical temperature data curve and comparing it with the current production line temperature data curve for comparative difference analysis, and combining with abnormal judgment, it realizes real-time and precise temperature regulation of the current production line environmental data; the present invention combines the local temperatures of the production line for correlation analysis, and obtains the comprehensive environmental temperature data of the production line through fusion analysis, thereby improving the traditional local temperature mean calculation method of the overall temperature and improving the accuracy; by comparing historical data and combining the comparative differences for precise temperature regulation, the rough method of traditional temperature range regulation is improved, and it can more intelligently improve the temperature regulation accuracy of the production line under different environmental factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a structural schematic diagram of a freezing and fresh-keeping production line detection system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0050] Example: Figure 1 As shown, the present invention provides a technical solution:

[0051] A method for detecting a freezing and fresh-keeping production line based on the Internet of Things, the method comprising the following steps:

[0052] S100. Network and connect the production line environmental monitoring equipment through the Internet of Things platform, and record the data of each device by marking the device number; set up a monitoring window to collect the monitoring data of each device;

[0053] S200, retrieve data from each monitoring device through the data analysis platform, comprehensively process the data collected by each device through data cleaning, and use the curve simulation model to smooth and concatenate the time frame data of the data collected by each device to construct a curve model;

[0054] S300. Construct a control curve analysis model by mapping the data curve models of each device to the same coordinate system; analyze the trend differences of the control curves at each time point, perform differential fusion analysis on each curve, and obtain a comprehensive curve model for the production environment; perform abnormal correlation analysis based on the comprehensive curve model and historical production environment data, and adjust the production line environment data based on the analysis data;

[0055] S400. Display the monitoring data of each environmental device of the production line through the visual port, and adjust the real-time production line environmental data based on the abnormal correlation analysis data of the comprehensive curve model.

[0056] The S100 uses the Internet of Things platform to network and connect the production line environment monitoring equipment, and records the data of each device by marking the device number; the specific steps of setting the monitoring window and collecting the monitoring data of each device are as follows:

[0057] S101. Log into the IoT management platform for the frozen fresh-keeping production line to retrieve equipment data from the production line's environmental monitoring equipment. Establish a device association network to connect each monitoring device in series to the same supervisory network. In the supervisory network, number each device and establish an equipment information column to record the information data of each device. The monitoring device is a temperature sensor monitoring device.

[0058] S102. By setting a monitoring cycle window, the environmental data of the production line is monitored in real time through various environmental monitoring devices, and the monitoring data is collected and transmitted to the data analysis platform through the monitoring network; the environmental data is the environmental temperature data of the production line.

[0059] The specific steps of S200 for retrieving data from each monitoring device through the data analysis platform, comprehensively processing the data collected by each device through data cleaning, and using the curve simulation model to smooth and concatenate the time frame data collected by each device to construct a curve model are as follows:

[0060] S201. The data analysis platform retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the equipment number. The platform cleans the time series temperature set corresponding to each equipment and comprehensively processes the data of each time series temperature set by filtering out erroneous data, missing data, and supplementing data.

[0061] S202. Import the processed time series temperature set data of each device into the simulation through the curve simulation model, import the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and connect the data in series through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

[0062] S300 maps the data curve models of each device to the same coordinate system to construct a control curve analysis model; analyzes the trend differences of the control curves at each time point, performs differential fusion analysis on each curve, and obtains a comprehensive curve model for the production environment; performs abnormal correlation analysis based on the comprehensive curve model and combines historical production environment data, and regulates the production line environment data based on the analysis data. The specific steps are as follows:

[0063] S301. Based on the ambient temperature curve fitted by the time series temperature set of each device, the ambient temperature curve corresponding to each device is mapped to the same coordinate system through the mapping coordinate system to construct a comparison curve analysis model; based on the comparison curve analysis model, trend difference analysis is performed based on the ambient temperature curve value corresponding to each device at each time point, and the value of each curve at the corresponding same time point is marked, and the overlap rate of the values ​​of each curve at the same time point is analyzed. The calculation formula is Cr(t)=m(t) / n(t); where Cr(t) is the overlap rate of each curve value at the corresponding time point t; m(t) is the overlap number of each curve value at the corresponding time point t; n(t) is the total number of each curve value at the corresponding time point t; by setting the comparison overlap rate threshold Cr(v), when the curve overlap rate corresponding to time point t Cr(t) ≥ Cr(v), the curve value of the overlap point of each curve at time t is used as the comprehensive ambient temperature data; if Cr(t) < Cr(v), trend difference analysis is performed on the curve value corresponding to time t, and the calculation formula is

[0064] ;

[0065] Where TDV(z,t) is the trend difference value of the corresponding numbered curve z at time t; k(z,t) is the curve derivative of the corresponding numbered curve z at time t; ave[k(n,t)] is the mean of the corresponding derivatives of each curve at time t; n is the number of curves; p(z,t) is the curve value of the corresponding numbered curve z at time t; ave[p(n,t)] is the mean of the corresponding curve values ​​of each curve at time t;

[0066] Based on the curve value of each curve at each time point, the curve value correlation analysis is performed, and the calculation formula is:

[0067] ;

[0068] Where R(n,t) is the intra-group correlation value of the curve values ​​on each curve at the corresponding time point t; combined with the trend difference analysis data of the curve values ​​of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point, the corresponding curve values ​​at each time point are screened out; if TDV(z,t)>R(n,t), the curve value of the numbered z curve at the current time point t is judged to be deviant data and is screened out; if TDV(z,t)≤R(n,t), the curve value of the numbered z curve at the current time point t is judged to be normal data and is retained;

[0069] Based on the curve value screening results at each time point, the retained data at each time point is averaged and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by smoothing the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed;

[0070] S302, based on the comprehensive temperature curve of the production line environment in the current cycle, by retrieving the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, the temperature data of the production line in the current cycle corresponding to each time point is compared and analyzed. The calculation formula is:

[0071] ;

[0072] Wherein, OD(t) is the difference between the comprehensive temperature curve of the production line environment in the current cycle and the curve value corresponding to time t on the normal temperature fluctuation curve in the corresponding historical cycle; Y(min) and Y(max) are the maximum and minimum curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle, respectively; Q(min) and Q(max) are the maximum and minimum curve values ​​of the normal temperature fluctuation curve in the corresponding historical cycle, respectively; Y(t) and Q(t) are the curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle and the normal temperature fluctuation curve in the corresponding historical cycle, respectively, at time t.

[0073] By comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the corresponding historical cycle, if Y(t)>Q(max) or Y(t)<Q(min) exists on the comprehensive temperature curve of the production line environment in the current cycle, an abnormal alarm will be issued for the current production line environment temperature; if Y(t)∈[Q(min), Q(max)], the current production line environment will be regulated and analyzed by comparing the historical data. If Y(t)>Q(t), the current production line environment temperature data will be regulated by comparing the difference value of the curve value at the corresponding time point. The calculation formula is Y(t) g =Y(t)-Y(t)*OD(t); if Y(t)<Q(t), the current production line environmental data is regulated, and the calculation formula is Y(t) g =Y(t)+Y(t)*OD(t); if Y(t)=Q(t), then keep the current production line ambient temperature data; where Y(t) g This is the production environment temperature data after adjustment.

[0074] The S400 displays the monitoring data of each environmental device of the production line through the visual port, and based on the abnormal correlation analysis data of the comprehensive curve model, the specific steps of regulating the real-time production line environmental data are as follows:

[0075] S401, using the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the frozen preservation production line in real time;

[0076] S402. Record the curve analysis model data of each device and output the abnormal environmental alarm status and temperature control data of the current production line.

[0077] A freezing and fresh-keeping production line detection system based on the Internet of Things, the system includes an equipment networking module, a data curve processing module, a comprehensive analysis and control module, and a data feedback output module;

[0078] The equipment networking module networks and connects the production line environment monitoring equipment through the Internet of Things platform, and records the data of each device in a network by marking the device number; sets a monitoring window to collect monitoring data of each device; the data curve processing module retrieves data from each monitoring device through the data analysis platform, comprehensively processes the data collected by each device through data cleaning, and uses the curve simulation model to smooth the time frame data of the data collected by each device to construct a curve model; the comprehensive analysis and control module constructs a control curve analysis model by mapping the data curve model of each device to the same coordinate system; by analyzing the trend difference degree of the control curve at each time point, each curve is subjected to difference fusion analysis and processing to obtain a comprehensive curve model of the production environment; based on the comprehensive curve model and combined with historical production environment data, an abnormal correlation analysis is performed, and the production line environment data is regulated according to the analysis data; the feedback output module displays the monitoring data of each environmental device of the production line through the visual port, and regulates the real-time production line environment data based on the abnormal correlation analysis data of the comprehensive curve model.

[0079] The device networking module includes a device networking construction unit and a periodic data acquisition unit;

[0080] The device networking construction unit logs into the Internet of Things management platform for the frozen fresh-keeping production line, retrieves device data from the production line's environmental monitoring equipment, and connects each monitoring device in series to the same supervision network by building a device association network. In the supervision network, each device is numbered and labeled, and a device information column is built to record the information data of each device. The monitoring device is a temperature sensing monitoring device.

[0081] The periodic data acquisition unit sets a monitoring period window and monitors the production line environmental data in real time through various environmental monitoring devices, collects the monitoring data and transmits it to the data analysis platform through the monitoring network; the environmental data is the production line environmental temperature data.

[0082] The data curve processing module includes a data overall processing unit and a data curve fitting unit;

[0083] The data analysis platform of the data coordination processing unit retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the number of each device; performs data cleaning on the time series temperature set corresponding to each device, and coordinates the data of each time series temperature set by filtering out erroneous data, missing data and supplementing data;

[0084] The data curve fitting unit imports the time series temperature set data processed by each device into simulation through the curve simulation model, imports the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and concatenates the data through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

[0085] The comprehensive analysis and control module includes a comprehensive environmental temperature curve analysis unit and a control unit for comparative environmental temperature data;

[0086] The comprehensive ambient temperature curve analysis unit is based on the ambient temperature curve fitted by the time series temperature set of each device, and the corresponding ambient temperature curve of each device is mapped to the same coordinate system through the mapping coordinate system to construct a control curve analysis model; based on the control curve analysis model, the trend difference analysis is performed based on the ambient temperature curve value of each device at each time point, and the value of each curve at the corresponding same time point is marked, and the value overlap rate of each curve at the same time point is analyzed; by setting the comparison overlap rate threshold, the value overlap rate at the same time point is judged; based on the judgment result, the comprehensive ambient temperature data of each time point is analyzed; if the curve at the corresponding time point is greater than or equal to the value overlap rate threshold, the corresponding The curve values ​​of the overlapping points of the curves at the time points are the comprehensive ambient temperature data; if they are less than the value overlap rate threshold, trend difference analysis is performed on each curve value; curve value correlation analysis is performed based on the curve values ​​of each curve at each time point; the curve values ​​corresponding to each time point are screened out based on the trend difference analysis data of the curve values ​​of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point; based on the curve value screening results at each time point, the data retained at each time point are averaged, and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by performing smooth curve fitting on the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed;

[0087] The control environment temperature data control unit is based on the comprehensive temperature curve of the production line environment in the current cycle, and by calling the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, performs a comparative difference value analysis on the temperature data of the production line corresponding to each time point in the current cycle; by comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the historical corresponding cycle, an alarm is issued for abnormal environment temperature data based on the comparison result; for normal environment temperature data, by comparing the environment temperature data of the corresponding historical moment, the current production line environment temperature data is controlled and analyzed based on the comparison result.

[0088] The data feedback output module includes a visual output unit and a control alarm instruction output unit;

[0089] The visual output unit uses the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the freezing and fresh-keeping production line in real time;

[0090] The control alarm instruction output unit records the curve analysis model data of each device and outputs the abnormal environmental alarm status and temperature control data of the current production line;

[0091] In the examples:

[0092] Currently, a frozen product manufacturing enterprise adopts the Internet of Things-based frozen preservation production line detection system of the present invention to perform environmental monitoring and adjustment on its frozen preservation production line. By logging into the Internet of Things management platform of the frozen preservation production line, the equipment data of the production line environmental monitoring equipment is retrieved, and by establishing a device association network, each monitoring equipment is connected in series to the same supervision network. In the supervision network, each equipment is numbered and labeled, and an equipment information column is established to record the information data of each equipment, wherein the monitoring equipment is a temperature sensing monitoring equipment; by setting a monitoring cycle window, the production line environmental data is monitored in real time by each environmental monitoring equipment, and the monitoring data is collected and transmitted to the data analysis platform through the monitoring network, wherein the environmental data is the production line ambient temperature data;

[0093] The data analysis platform retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the equipment number. It cleans the corresponding time series temperature set for each equipment and comprehensively processes the data of each time series temperature set by filtering out erroneous data, missing data, and compensating for data. The processed time series temperature set data of each equipment is imported into the simulation through the curve simulation model. By importing the time series temperature set data of the corresponding time point on the time axis as time frame temperature data and connecting the data in series through a smooth curve, the monitoring ambient temperature curve within the corresponding equipment cycle is fitted.

[0094] Based on the ambient temperature curve fitted by the time series temperature set of each device, the corresponding ambient temperature curve of each device is mapped to the same coordinate system through the mapping coordinate system to construct a control curve analysis model; based on the control curve analysis model, the trend difference analysis is performed based on the ambient temperature curve value of each device at each time point, and the values ​​of each curve at the corresponding same time point are marked, and the coincidence rate of the values ​​of each curve at the same time point is analyzed, and the calculation formula is Cr(t)=m(t) / n(t); by setting the comparison coincidence rate threshold Cr(v), when the curve coincidence rate corresponding to time point t Cr(t)≥Cr(v), the curve value of the coincidence point of each curve at time t is used as the comprehensive ambient temperature data; if Cr(t)<Cr(v), the trend difference analysis is performed on the curve value corresponding to time t, and the calculation formula is

[0095] ;

[0096] Based on the curve value of each curve at each time point, the curve value correlation analysis is performed, and the calculation formula is:

[0097] ;

[0098] Combined with the trend difference analysis data of the curve values ​​of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point, the corresponding curve values ​​at each time point are screened out; if TDV(z,t)>R(n,t), the curve value of the numbered z curve at the current time point t is judged to be deviated data and is screened out; if TDV(z,t)≤R(n,t), the curve value of the numbered z curve at the current time point t is judged to be normal data and is retained; based on the curve value screening results at each time point, the retained data at each time point is averaged and the calculated result is the comprehensive ambient temperature data at the current corresponding time point; by performing smooth curve fitting on the comprehensive ambient temperature data at each time point, the corresponding production line environment comprehensive temperature curve for the current cycle is constructed;

[0099] Based on the comprehensive temperature curve of the production line environment in the current cycle, the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle is retrieved, and the temperature data of the production line in the current cycle corresponding to each time point is compared and analyzed. The calculation formula is:

[0100] ;

[0101] By comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the corresponding historical cycle, if Y(t)>Q(max) or Y(t)<Q(min) exists on the comprehensive temperature curve of the production line environment in the current cycle, an abnormal alarm will be issued for the current production line environment temperature; if Y(t)∈[Q(min), Q(max)], the current production line environment will be regulated and analyzed by comparing the historical data. If Y(t)>Q(t), the current production line environment temperature data will be regulated by comparing the difference value of the curve value at the corresponding time point. The calculation formula is Y(t) g =Y(t)-Y(t)*OD(t); if Y(t)<Q(t), the current production line environmental data is regulated, and the calculation formula is Y(t) g =Y(t)+Y(t)*OD(t); if Y(t)=Q(t), then maintain the current production line ambient temperature data; use the Internet of Things visualization window to display the ambient temperature monitoring data of each monitoring point on the frozen preservation production line in real time; record the curve analysis model data of each device, and output the environmental abnormality alarm status and temperature control data of the current production line.

[0102] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A method for detecting a freezing and fresh-keeping production line based on the Internet of Things, characterized by: The method comprises the following steps: S100. Network and connect the production line environmental monitoring equipment through the Internet of Things platform, and record the data of each device by marking the device number; set up a monitoring window to collect the monitoring data of each device; S200, retrieve data from each monitoring device through the data analysis platform, comprehensively process the data collected by each device through data cleaning, and use the curve simulation model to smooth and concatenate the time frame data of the data collected by each device to construct a curve model; S300. Construct a control curve analysis model by mapping the data curve models of each device to the same coordinate system; analyze the trend differences of the control curves at each time point, perform differential fusion analysis on each curve, and obtain a comprehensive curve model for the production environment; perform abnormal correlation analysis based on the comprehensive curve model and historical production environment data, and adjust the production line environment data based on the analysis data; S400: Display monitoring data of various environmental equipment on the production line through the visual port, analyze data based on abnormal correlation of the comprehensive curve model, and regulate the real-time production line environmental data; S300 maps the data curve models of each device to the same coordinate system to construct a control curve analysis model; analyzes the trend differences of the control curves at each time point, performs differential fusion analysis on each curve, and obtains a comprehensive curve model for the production environment; performs abnormal correlation analysis based on the comprehensive curve model and combines historical production environment data, and regulates the production line environment data based on the analysis data. The specific steps are as follows: S301. Based on the ambient temperature curve fitted by the time series temperature set of each device, the ambient temperature curve corresponding to each device is mapped to the same coordinate system through the mapping coordinate system to construct a comparison curve analysis model; based on the comparison curve analysis model, trend difference analysis is performed based on the ambient temperature curve value corresponding to each device at each time point, and the value of each curve at the corresponding same time point is marked, and the overlap rate of the values ​​of each curve at the same time point is analyzed. The calculation formula is Cr(t)=m(t) / n(t); where Cr(t) is the overlap rate of each curve value at the corresponding time point t; m(t) is the overlap number of each curve value at the corresponding time point t; n(t) is the total number of each curve value at the corresponding time point t; by setting the comparison overlap rate threshold Cr(v), when the curve overlap rate corresponding to time point t Cr(t) ≥ Cr(v), the curve value of the overlap point of each curve at time t is used as the comprehensive ambient temperature data; if Cr(t) < Cr(v), trend difference analysis is performed on the curve value corresponding to time t, and the calculation formula is ； Where TDV(z,t) is the trend difference value of the corresponding numbered curve z at time t; k(z,t) is the curve derivative of the corresponding numbered curve z at time t; ave[k(n,t)] is the mean of the corresponding derivatives of each curve at time t; n is the number of curves; p(z,t) is the curve value of the corresponding numbered curve z at time t; ave[p(n,t)] is the mean of the corresponding curve values ​​of each curve at time t; Based on the curve value of each curve at each time point, the curve value correlation analysis is performed, and the calculation formula is: ； Where R(n,t) is the intra-group correlation value of the curve values ​​on each curve at the corresponding time point t; combined with the trend difference analysis data of the curve values ​​of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point, the corresponding curve values ​​at each time point are screened out; if TDV(z,t)>R(n,t), the curve value of the numbered z curve at the current time point t is judged to be deviant data and is screened out; if TDV(z,t)≤R(n,t), the curve value of the numbered z curve at the current time point t is judged to be normal data and is retained; Based on the curve value screening results at each time point, the retained data at each time point is averaged and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by smoothing the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed; S302, based on the comprehensive temperature curve of the production line environment in the current cycle, by retrieving the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, the temperature data of the production line in the current cycle corresponding to each time point is compared and analyzed. The calculation formula is: ； Wherein, OD(t) is the difference between the comprehensive temperature curve of the production line environment in the current cycle and the curve value corresponding to time t on the normal temperature fluctuation curve in the corresponding historical cycle; Y(min) and Y(max) are the minimum and maximum curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle, respectively; Q(min) and Q(max) are the minimum and maximum curve values ​​of the normal temperature fluctuation curve in the corresponding historical cycle, respectively; Y(t) and Q(t) are the curve values ​​of the comprehensive temperature curve of the production line environment in the current cycle and the normal temperature fluctuation curve in the corresponding historical cycle, respectively, at time t; By comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the corresponding historical cycle, if Y(t)>Q(max) or Y(t)<Q(min) exists on the comprehensive temperature curve of the production line environment in the current cycle, an abnormal alarm will be issued for the current production line environment temperature; if Y(t)∈[Q(min), Q(max)], the current production line environment will be regulated and analyzed by comparing the historical data. If Y(t)>Q(t), the current production line environment temperature data will be regulated by comparing the difference value of the curve value at the corresponding time point. The calculation formula is Y(t) g =Y(t)-Y(t)*OD(t); if Y(t)<Q(t), the current production line environmental data is regulated, and the calculation formula is Y(t) g =Y(t)+Y(t)*OD(t); if Y(t)=Q(t), then keep the current production line ambient temperature data; where Y(t) g This is the production environment temperature data after adjustment.

2. The method for detecting a freezing and fresh-keeping production line based on the Internet of Things according to claim 1, wherein: The S100 uses the Internet of Things platform to network and connect the production line environment monitoring equipment, and records the data of each device by marking the device number; the specific steps of setting the monitoring window and collecting the monitoring data of each device are as follows: S101. Log into the IoT management platform for the frozen fresh-keeping production line to retrieve equipment data from the production line's environmental monitoring equipment. Establish a device association network to connect each monitoring device in series to the same supervisory network. In the supervisory network, number each device and establish an equipment information column to record the information data of each device. The monitoring device is a temperature sensor monitoring device. S102. By setting a monitoring cycle window, the environmental data of the production line is monitored in real time through various environmental monitoring devices, and the monitoring data is collected and transmitted to the data analysis platform through the monitoring network; the environmental data is the environmental temperature data of the production line.

3. The method for detecting a freezing and fresh-keeping production line based on the Internet of Things according to claim 2, wherein: The specific steps of S200 for retrieving data from each monitoring device through the data analysis platform, comprehensively processing the data collected by each device through data cleaning, and using the curve simulation model to smooth and concatenate the time frame data collected by each device to construct a curve model are as follows: S201. The data analysis platform retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the equipment number. The platform cleans the time series temperature set corresponding to each equipment and comprehensively processes the data of each time series temperature set by filtering out erroneous data, missing data, and supplementing data. S202. Import the processed time series temperature set data of each device into the simulation through the curve simulation model, import the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and connect the data in series through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

4. The method for detecting a freezing and fresh-keeping production line based on the Internet of Things according to claim 3, wherein: The S400 displays the monitoring data of each environmental device of the production line through the visual port, and based on the abnormal correlation analysis data of the comprehensive curve model, the specific steps of regulating the real-time production line environmental data are as follows: S401, using the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the frozen preservation production line in real time; S402. Record the curve analysis model data of each device and output the abnormal environmental alarm status and temperature control data of the current production line.

5. A freezing and fresh-keeping production line detection system based on the Internet of Things, using the freezing and fresh-keeping production line detection method based on the Internet of Things according to claim 1, characterized in that: The system includes an equipment networking module, a data curve processing module, a comprehensive analysis and control module, and a data feedback output module; The equipment networking module networks and connects the production line environment monitoring equipment through the Internet of Things platform, and records the data of each device in a network by marking the device number; sets a monitoring window to collect monitoring data of each device; the data curve processing module retrieves data from each monitoring device through the data analysis platform, comprehensively processes the data collected by each device through data cleaning, and uses the curve simulation model to smooth the time frame data of the data collected by each device to construct a curve model; the comprehensive analysis and control module constructs a control curve analysis model by mapping the data curve model of each device to the same coordinate system; by analyzing the trend difference degree of the control curve at each time point, each curve is subjected to difference fusion analysis and processing to obtain a comprehensive curve model of the production environment; based on the comprehensive curve model and combined with historical production environment data, an abnormal correlation analysis is performed, and the production line environment data is regulated according to the analysis data; the feedback output module displays the monitoring data of each environmental device of the production line through the visual port, and regulates the real-time production line environment data based on the abnormal correlation analysis data of the comprehensive curve model.

6. The Internet of Things-based freezing and fresh-keeping production line detection system according to claim 5, characterized in that: The device networking module includes a device networking construction unit and a periodic data acquisition unit; The device networking construction unit logs into the Internet of Things management platform for the frozen fresh-keeping production line, retrieves device data from the production line's environmental monitoring equipment, and connects each monitoring device in series to the same supervision network by building a device association network. In the supervision network, each device is numbered and labeled, and a device information column is built to record the information data of each device. The monitoring device is a temperature sensing monitoring device. The periodic data acquisition unit sets a monitoring period window and monitors the production line environmental data in real time through various environmental monitoring devices, collects the monitoring data and transmits it to the data analysis platform through the monitoring network; the environmental data is the production line environmental temperature data.

7. The Internet of Things-based freezing and fresh-keeping production line detection system according to claim 6, characterized in that: The data curve processing module includes a data overall processing unit and a data curve fitting unit; The data analysis platform of the data coordination processing unit retrieves the cycle ambient temperature data collected from the production line and constructs a time series temperature set based on the number of each device; performs data cleaning on the time series temperature set corresponding to each device, and coordinates the data of each time series temperature set by filtering out erroneous data, missing data and supplementing data; The data curve fitting unit imports the time series temperature set data processed by each device into simulation through the curve simulation model, imports the time frame temperature data of the time series temperature set data of the corresponding time point on the time axis, and concatenates the data through a smooth curve to fit the monitoring environment temperature curve within the corresponding device cycle.

8. The Internet of Things-based freezing and fresh-keeping production line detection system according to claim 7, characterized in that: The comprehensive analysis and control module includes a comprehensive environmental temperature curve analysis unit and a control unit for comparative environmental temperature data; The comprehensive ambient temperature curve analysis unit is based on the ambient temperature curve fitted by the time series temperature set of each device, and maps the ambient temperature curve corresponding to each device to the same coordinate system through a mapping coordinate system to construct a control curve analysis model; based on the control curve analysis model, a trend difference analysis is performed based on the ambient temperature curve value corresponding to each device at each time point, and the value of each curve at the corresponding same time point is marked, and the overlap rate of the values ​​of each curve at the same time point is analyzed; by setting a comparison overlap rate threshold, the overlap rate of the values ​​at the same time point is judged; based on the judgment result, the comprehensive ambient temperature data of each time point is analyzed; if the curve at the corresponding time point is greater than or equal to the overlap rate threshold, the curve value of the overlap point of the curve at the corresponding time point is used as the comprehensive ambient temperature data; if it is less than the overlap rate threshold, a trend difference analysis is performed on each curve value; a curve value correlation analysis is performed based on the curve value corresponding to each curve at each time point; and the curve value corresponding to each time point is screened out by combining the trend difference analysis data of the curve value of each curve at the corresponding time point and the intra-group correlation data of each curve value at the corresponding time point; Based on the curve value screening results at each time point, the retained data at each time point is averaged and the calculated result is the comprehensive ambient temperature data of the current corresponding time point; by smoothing the comprehensive ambient temperature data at each time point, a comprehensive temperature curve of the production line environment corresponding to the current cycle is constructed; The control environment temperature data control unit is based on the comprehensive temperature curve of the production line environment in the current cycle, and by calling the normal temperature fluctuation curve of the historical frozen preservation production line corresponding to the current cycle, performs a comparative difference value analysis on the temperature data of the production line corresponding to each time point in the current cycle; by comparing the comprehensive temperature curve of the production line environment in the current cycle with the normal temperature fluctuation curve of the historical corresponding cycle, an alarm is issued for abnormal environment temperature data based on the comparison result; for normal environment temperature data, by comparing the environment temperature data of the corresponding historical moment, the current production line environment temperature data is controlled and analyzed based on the comparison result.

9. The Internet of Things-based freezing and fresh-keeping production line detection system according to claim 8, characterized in that: The data feedback output module includes a visual output unit and a control alarm instruction output unit; The visual output unit uses the Internet of Things visualization window to display the environmental temperature monitoring data of each monitoring point on the freezing and fresh-keeping production line in real time; The control alarm instruction output unit records the curve analysis model data of each device and outputs the abnormal environmental alarm situation and temperature control data of the current production line.

Images