Research and development production data monitoring system and method based on Internet of Things

Abstract

The invention relates to the technical field of research and development and production, in particular to a research and development and production data monitoring system and method based on the Internet of Things, and the method comprises the steps: analyzing research and development and production data of an acquisition node to obtain a missing characterization value, analyzing the missing data type of an abnormal acquisition node based on an analysis signal to obtain a missing continuous value, analyzing the correlation between the missing data type and the adjacent data type on the basis of the missing data continuity low signal to obtain a correlation coefficient deviation value, determining a missing adjacent ratio mean value on the basis of the filling signal, and performing filling operation on the missing data type in the type data set to obtain the missing data type. According to the method, whether the missing data can be reasonably filled based on the adjacent data or not can be judged by distinguishing the continuous type missing from the interval type missing and analyzing the correlation between the missing data type and the adjacent data type, so that unnecessary recollection is avoided, and the data processing efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of research and development production, and in particular to a research and development production data monitoring system and method based on the Internet of Things. Background Art

[0002] In the modern R&D and production process, whether in industrial manufacturing, biomedical R&D or electronic information product development, real-time and accurate monitoring of production and R&D data is crucial. Traditional data monitoring methods often rely on regular manual inspections and records, which is not only inefficient and prone to human errors, but also difficult to capture sudden abnormal situations in the production and R&D process in a timely manner. With the vigorous development of Internet of Things technology, its real-time perception, interconnection and intelligent processing capabilities have brought new solutions and opportunities for R&D and production data monitoring.

[0003] However, the existing technology lacks specificity when dealing with missing data. It is unable to determine whether data needs to be re-collected based on continuous missingness and interval missingness. When dealing with interval type missingness, it cannot reasonably use adjacent data to fill in the missing data and blindly re-collects data. At the same time, there is a lack of comprehensive monitoring and early warning mechanism for R&D and production area data, making it difficult to timely discover potential risks in the production process. Managers are unable to make decisions in a timely manner, which is not conducive to reducing production risks and improving production efficiency.

[0004] To this end, we proposed a R&D and production data monitoring system and method based on the Internet of Things. Summary of the invention

[0005] The object of the present invention is to provide a research and development production data monitoring system and method based on the Internet of Things to solve at least one of the above-mentioned prior art problems.

[0006] In a first aspect, the present invention provides a method for monitoring R&D and production data based on the Internet of Things, specifically comprising: Step 1: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Step 2: Based on the analysis signal, analyze the missing data type of the abnormal collection node to obtain the missing continuous value. If the missing continuous value is greater than the missing continuous threshold, a missing data continuity high signal is generated; Step 3: Based on the missing data continuity low signal, analyze the correlation between the missing data type and the adjacent data type to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, generate a filling signal; Step 4: Based on the filling signal, determine the mean of the missing adjacent ratio and perform filling operations on the missing data types in the type data group.

[0007] In a second aspect, the present invention provides a research and development production data monitoring system based on the Internet of Things, specifically comprising: Missing data judgment module: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Missing data continuity judgment module: Based on the analysis signal, the missing data type of the abnormal collection node is analyzed to obtain the missing data continuity value. If the missing data continuity value is greater than the missing data continuity threshold, a missing data continuity high signal is generated. Filling analysis module: Based on the missing data continuity low signal, the correlation between the missing data type and the adjacent data type is analyzed to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, a filling signal is generated; Data filling module: Based on the filling signal, determine the mean of the missing adjacent ratio and perform filling operations on the missing data types in the type data group.

[0008] Beneficial effects of the present invention: 1. The present invention analyzes the R&D and production data of the collection node within the collection cycle to obtain a missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated. The present invention analyzes the number of R&D and production data at the collection node, and can promptly discover the situation of missing data types, judge the degree of data missing according to the missing characterization value, re-collect data with a high degree of missingness, generate an analysis signal for data with a low degree of missingness, and continue to perform subsequent analysis, thereby improving the efficiency and pertinence of data processing, helping to improve the reliability of R&D and production data collection, and providing strong support for R&D and production decisions based on these data.

[0009] 2. Based on the analysis signal, the present invention analyzes the missing data type of the abnormal acquisition node to obtain the missing continuous value. If the missing continuous value is greater than the missing continuous threshold, a missing data continuity high signal is generated. Based on the missing data continuity low signal, the correlation between the missing data type and the adjacent data type is analyzed to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, a filling signal is generated. Based on the filling signal, the missing adjacent ratio mean is determined, and the missing data type in the type data group is filled. The present invention can clearly identify the specific pattern of data missing by distinguishing between continuous type missing and interval type missing, help quickly locate the characteristics of data missing, and provide a basis for subsequent targeted processing. By calculating the missing continuous value, it is helpful to determine whether it is necessary to re-collect the research and development production data, thereby ensuring the reliability and integrity of the data. For interval type missing, by analyzing the correlation between the missing data type and the adjacent data type, it can be determined whether the missing data can be reasonably filled based on the adjacent data, thereby avoiding unnecessary re-collection and improving the efficiency of data processing. The missing adjacent ratio mean is used as the filling coefficient, and the missing data is filled based on this, providing a scientific and reasonable method for data filling, so that the filled data has a certain rationality and credibility, and the availability of the data is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 This is a flow chart of a method for monitoring R&D and production data based on the Internet of Things according to an embodiment of the present invention; Figure 2 This is a block diagram of a research and development production data monitoring system based on the Internet of Things according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a research and development production data monitoring device based on the Internet of Things according to an embodiment of the present invention; Figure numbers: 3, computer device; 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. 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 creative work should fall within the scope of protection of the present invention.

[0013] Embodiment 1

[0014] Figure 1 A flowchart of a research and development production data monitoring method based on the Internet of Things is provided for the first embodiment of the present invention. A research and development production data monitoring method based on the Internet of Things can be performed by a research and development production data monitoring system based on the Internet of Things. A research and development production data monitoring system based on the Internet of Things can be implemented by software and / or hardware. A research and development production data monitoring system based on the Internet of Things can be configured in a research and development production data monitoring device based on the Internet of Things. Optionally, a research and development production data monitoring device based on the Internet of Things can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0015] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring R&D and production data based on the Internet of Things, which specifically includes: Step 1: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Preset the collection cycle and divide the collection cycle into several collection nodes with equal time intervals; It should be noted that the collection period includes but is not limited to 10 days, 20 days, and 30 days; Based on any collection node; Use IoT sensors to obtain R&D and production data from collection nodes, where IoT sensors include but are not limited to vibration sensors and pressure sensors; Count the number of R&D and production data at the collection node, and compare and analyze the number of R&D and production data at the collection node with the number of standard R&D and production data, specifically: If the number of R&D and production data at a collection node is less than the standard number of R&D and production data, the collection node is marked as an abnormal number collection node; If the number of R&D and production data at a collection node is greater than or equal to the number of standard R&D and production data, the collection node is marked as a normal number collection node; It should be noted that the types of standard R&D and production data are set by those skilled in the art based on past historical experience; Based on any abnormal number collection node; Obtain the number of R&D and production data of the abnormal number collection node and perform subtraction processing on the number of standard R&D and production data, and take the absolute value of the difference to obtain the abnormal number deviation, perform ratio processing on the abnormal number deviation and the standard R&D and production data to obtain the abnormal number deviation ratio; Extract the missing R&D and production data types in the abnormal number collection node and mark them as missing data types. Sum the numbers corresponding to all missing data types to get the missing type number sum. Ratio the missing type number sum with the number corresponding to the standard R&D and production data types to get the missing type degree ratio. The missing representation value is calculated by summing the abnormal number deviation ratio and the missing type degree ratio; Compare the missing token value to the missing token threshold: If the missing characterization value is greater than or equal to the missing characterization threshold, it indicates that the R&D and production data collected during the collection period have a high degree of missingness, and the R&D and production data are recollected to generate a collection signal; If the missing characterization value is less than the missing characterization threshold, it means that the missing degree of the R&D and production data collected during the collection period is low, and an analysis signal is generated; The technical solution of this embodiment is: within the collection cycle, the R&D and production data of the collection node are analyzed to obtain a missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated. The present invention analyzes the number of R&D and production data at the collection node, so as to promptly discover the situation of missing data types, judge the degree of data missing according to the missing characterization value, re-collect data with a high degree of missingness, generate an analysis signal for data with a low degree of missingness, and continue subsequent analysis, thereby improving the efficiency and pertinence of data processing, helping to improve the reliability of R&D and production data collection, and providing strong support for R&D and production decisions based on these data.

[0016] Embodiment 2

[0017] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring R&D and production data based on the Internet of Things, which specifically includes: Step 2: Based on the analysis signal, analyze the missing data type of the abnormal collection node to obtain the missing continuous value. If the missing continuous value is greater than the missing continuous threshold, a missing data continuity high signal is generated; Based on the abnormal number collection node, if the number of missing data types that appear continuously is ≥2, it means a continuous type missing, and a continuous type missing signal is generated; if the number of missing data types that appear continuously is <2, it means an interval type missing, and an interval type missing signal is generated; For example, suppose that the R&D and production data of an electronic product assembly process is collected. The collection cycle is 10 days, which is divided into 10 collection nodes, one collection node per day. The collected data types include temperature, humidity, part vibration frequency, part pressure, and production line speed. The number of standard R&D and production data types is these five types; After comparison, it was found that the two data types of humidity and part vibration frequency were missing; because the number of consecutive missing data types is 2, it meets the condition of "the number of consecutive missing data types ≥ 2", so this is a continuous type missing, and the system will generate a continuous type missing signal; At the 7th acquisition node, only the part pressure data type is found to be missing. Since the number of consecutive missing data types is 1, the condition of "the number of consecutive missing data types < 2" is satisfied. Therefore, this is an interval type missing, and the system will generate an interval type missing signal. For another example, at the 8th and 9th acquisition nodes, it is found that the two data types of production line speed and temperature are missing. Each node has a single data type missing, and the number of consecutive missing data types is less than 2. Therefore, these two nodes are both interval type missing. The system will generate interval type missing signals for the 8th and 9th acquisition nodes respectively. Count the number of occurrences of continuous type missing signals and mark them as the number of continuous type missing signals LQ; By formula: The missing continuous value QL is calculated, where m represents the number of acquisition nodes; Compare missing continuous values ​​to the missing continuous threshold: If the missing continuous value is greater than the missing continuous threshold, it means that the R&D and production data need to be recollected to generate a high missing data continuity signal; If the missing continuity value is less than or equal to the missing continuity threshold, a missing data continuity low signal is generated; Step 3: Based on the missing data continuity low signal, analyze the correlation between the missing data type and the adjacent data type to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, generate a filling signal; Extract the adjacent data types when the interval type missing signal is generated, combine the previous data type or the next data type in the adjacent data type with the missing data type to obtain a type data group, and analyze the correlation between the missing data type and the adjacent data type in the type data group, specifically: Based on any type data group, obtain data values ​​of missing data types and adjacent data types in the type data group within the same historical period, mark the data values ​​corresponding to the missing data types as missing data values, and mark the data values ​​corresponding to the adjacent data types as adjacent data values; Divide the historical cycle into a number of historical time points with equal time intervals; By formula: Calculate the correlation coefficient r between the missing data type and the adjacent data type; Where n is the number of samples, and are the observed values ​​of the variable missing data value and adjacent data value at the i-th historical time point, and are the sample means of the missing data values ​​and adjacent data values ​​of the variable, respectively; Take the absolute value of the correlation coefficient r to obtain the absolute value of the correlation coefficient, and perform a difference process between 1 and the absolute value of the correlation coefficient to obtain the deviation value of the correlation coefficient; Compare the correlation coefficient deviation value to the correlation coefficient deviation threshold: If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, it means that the correlation between the missing data value and the adjacent data value in the historical period is high, that is, the correlation between the missing data type and the adjacent data type in the type data group in the historical period is high, and a filling signal is generated; If the correlation coefficient deviation value is greater than the correlation coefficient deviation threshold, it means that the correlation between the missing data value and the adjacent data value in the historical period is low, that is, the correlation between the missing data type and the adjacent data type in the type data group in the historical period is low, and a non-filling signal is generated, and the missing data type is re-collected; Step 4: Based on the filling signal, determine the mean of the missing adjacent ratio, and perform a filling operation on the missing data type in the type data group; Specifically, the missing data value of the historical time point is processed with the adjacent data value to obtain the missing adjacent ratio, and the missing adjacent ratios of all historical time points are summed and averaged to obtain the missing adjacent ratio mean; The mean value of the missing adjacent ratio is used as the filling coefficient, and the filling coefficient is multiplied by the adjacent data value to obtain the missing data value to be filled, and the data of the current missing data type is filled based on the missing data value to be filled; The technical solution of this embodiment is: based on the analysis signal, the missing data type of the abnormal acquisition node is analyzed to obtain the missing continuous value. If the missing continuous value is greater than the missing continuous threshold, a missing data continuity high signal is generated. Based on the missing data continuity low signal, the correlation between the missing data type and the adjacent data type is analyzed to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, a filling signal is generated. Based on the filling signal, the missing adjacent ratio mean is determined, and the missing data type in the type data group is filled. The present invention can clearly identify the specific pattern of data missing by distinguishing between continuous type missing and interval type missing, which helps It helps to quickly locate the characteristics of missing data and provides a basis for subsequent targeted processing. By calculating the missing continuous values, it helps to decide whether it is necessary to re-collect the R&D and production data, ensuring the reliability and integrity of the data. For interval type missing, by analyzing the correlation between the missing data type and the adjacent data type, it can determine whether the missing data can be reasonably filled based on the adjacent data, avoiding unnecessary re-collection and improving the efficiency of data processing. The mean of the missing adjacent ratio is used as the filling coefficient, and the missing data is filled on this basis, providing a scientific and reasonable method for data filling, so that the filled data has a certain degree of rationality and credibility, and improves the availability of data.

[0018] Embodiment 3

[0019] like Figure 2 As shown, an embodiment of the present invention provides a research and development production data monitoring system based on the Internet of Things, which specifically includes: Missing data judgment module: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Missing data continuity judgment module: Based on the analysis signal, the missing data type of the abnormal collection node is analyzed to obtain the missing data continuity value. If the missing data continuity value is greater than the missing data continuity threshold, a missing data continuity high signal is generated. Filling analysis module: Based on the missing data continuity low signal, the correlation between the missing data type and the adjacent data type is analyzed to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, a filling signal is generated; Data filling module: Based on the filling signal, determine the mean of the missing adjacent ratio and perform filling operations on the missing data types in the type data group.

[0020] Embodiment 4

[0021] Reference Figure 3The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, a research and development production data monitoring method based on the Internet of Things as described in any one of the above methods is implemented.

[0022] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0023] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0024] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0025] Embodiment 5

[0026] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements a method for monitoring R&D and production data based on the Internet of Things as described in any of the above methods.

[0027] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0028] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0029] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0030] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal equipment and method can be implemented in other ways. For example, the apparatus / terminal equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. One point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0031] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0032] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0033] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for monitoring R&D and production data based on the Internet of Things, characterized in that: include: Step 1: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Step 2: Based on the analysis signal, analyze the missing data type of the abnormal collection node to obtain the missing continuous value. If the missing continuous value is greater than the missing continuous threshold, a missing data continuity high signal is generated; Step 3: Based on the missing data continuity low signal, analyze the correlation between the missing data type and the adjacent data type to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, generate a filling signal; Step 4: Based on the filling signal, determine the mean of the missing adjacent ratio and perform filling operations on the missing data types in the type data group.

2. According to the method for monitoring R&D and production data based on the Internet of Things according to claim 1, it is characterized in that: The missing characterization value is obtained in the following manner: Obtain the R&D and production data of the collection node, and analyze to obtain the abnormal number deviation ratio and missing type degree ratio; The missing representation value is calculated by summing the anomaly number deviation ratio and the missing type degree ratio.

3. According to the method for monitoring R&D and production data based on the Internet of Things according to claim 2, it is characterized in that: The abnormal number deviation ratio is obtained as follows: Preset the collection cycle and divide the collection cycle into several collection nodes with equal time intervals; Based on any collection node; Obtain the R&D and production data of the collection node, count the number of R&D and production data at the collection node, and compare the number of R&D and production data at the collection node with the number of standard R&D and production data: If the number of R&D and production data at a collection node is less than the standard number of R&D and production data, the collection node is marked as an abnormal number collection node; Based on any abnormal number collection node; The number of R&D and production data obtained from the abnormal number collection node is subtracted from the number of standard R&D and production data, and the absolute value of the difference is taken to obtain the abnormal number deviation. The abnormal number deviation is then ratioed with the standard number of R&D and production data to obtain the abnormal number deviation ratio.

4. According to the method for monitoring R&D and production data based on the Internet of Things according to claim 3, it is characterized in that: The abnormal number deviation ratio is obtained as follows: Extract the missing R&D and production data types in the abnormal number collection node and mark them as missing data types. Sum the corresponding quantities of all missing data types to get the sum of the missing type quantities. Ratio the sum of the missing type quantities with the quantities corresponding to the standard R&D and production data types to get the missing type degree ratio.

5. According to the method for monitoring R&D and production data based on the Internet of Things according to claim 4, it is characterized in that: The missing continuous value is obtained as follows: Based on the abnormal number collection node, if the number of missing data types that appear continuously is ≥2, it means a continuous type missing, and a continuous type missing signal is generated; if the number of missing data types that appear continuously is <2, it means an interval type missing, and an interval type missing signal is generated; Count the number of occurrences of continuous type missing signals and mark them as the number of continuous type missing signals LQ; By formula: The missing continuous value QL is calculated, where m represents the number of collection nodes.

6. According to the method for monitoring R&D and production data based on the Internet of Things according to claim 5, it is characterized in that: The correlation coefficient deviation value is obtained in the following way: Extract the adjacent data types when the interval type missing signal is generated, combine the previous data type or the next data type in the adjacent data type with the missing data type to obtain a type data group, and based on the type data group, analyze the missing data values ​​corresponding to the missing data type and the adjacent data values ​​corresponding to the adjacent data type to obtain the correlation coefficient r, take the absolute value of the correlation coefficient r to obtain the absolute value of the correlation coefficient, and perform difference processing between 1 and the absolute value of the correlation coefficient to obtain the correlation coefficient deviation value.

7. The method for monitoring R&D and production data based on the Internet of Things according to claim 6 is characterized in that: The correlation coefficient r is obtained as follows: Based on any type data group, obtain data values ​​of missing data types and adjacent data types in the type data group within the same historical period, mark the data values ​​corresponding to the missing data types as missing data values, and mark the data values ​​corresponding to the adjacent data types as adjacent data values; Divide the historical cycle into a number of historical time points with equal time intervals; The correlation coefficient r between the missing data type and the adjacent data type is calculated using the Pearson correlation coefficient formula.

8. The method for monitoring R&D and production data based on the Internet of Things according to claim 7, characterized in that: The specific operation of filling the missing data types in the type data group is as follows: Get the mean of the missing adjacent ratio, use the mean of the missing adjacent ratio as the filling coefficient, multiply the filling coefficient by the adjacent data value to obtain the missing data value to be filled, and perform a filling operation on the data of the current missing data type based on the missing data value to be filled.

9. The method for monitoring R&D and production data based on the Internet of Things according to claim 8, characterized in that: The method for obtaining the missing adjacent ratio mean is: The missing data value of the historical time point is ratioed with the adjacent data value to obtain the missing adjacent ratio, and the missing adjacent ratios of all historical time points are summed and averaged to obtain the mean of the missing adjacent ratios.

10. A R&D and production data monitoring system based on the Internet of Things, the system implements the R&D and production data monitoring method based on the Internet of Things as described in any one of claims 1 to 9, characterized in that: include: Missing data judgment module: During the collection period, the R&D and production data of the collection node are analyzed to obtain the missing characterization value. If the missing characterization value is less than the missing characterization threshold, an analysis signal is generated; Missing data continuity judgment module: Based on the analysis signal, the missing data type of the abnormal collection node is analyzed to obtain the missing data continuity value. If the missing data continuity value is greater than the missing data continuity threshold, a missing data continuity high signal is generated. Filling analysis module: Based on the missing data continuity low signal, the correlation between the missing data type and the adjacent data type is analyzed to obtain the correlation coefficient deviation value. If the correlation coefficient deviation value is less than or equal to the correlation coefficient deviation threshold, a filling signal is generated; Data filling module: Based on the filling signal, determine the mean of the missing adjacent ratio and perform filling operations on the missing data types in the type data group.

Images