Data collection and management method, system and storage medium for industrial Internet of Things

Abstract

The present invention relates to the technical field of industrial Internet of Things, and specifically discloses a data collection and management method, system and storage medium for industrial Internet of Things. By real-time collection of temperature and humidity data in the working environment of a sensor, temperature anomaly factors and humidity anomaly factors are calculated, and an impact signal is obtained by comprehensive evaluation. When the impact signal score exceeds a preset threshold, the system triggers further pressure sensor status evaluation, and judges the status of the pressure sensor by comparing current pressure data with historical normal data. Once the pressure sensor data is found to be abnormal, the system adjusts the environmental conditions to reduce the impact on the sensor, and continues to monitor the pressure data to evaluate whether the equipment has a fault. If it is detected that the equipment may have a risk of failure, the system will promptly issue a warning signal to remind the operator to take necessary preventive measures.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and in particular to a data collection and management method, system and storage medium for industrial Internet of Things. Background Art

[0002] In modern industrial production processes, various sensors are widely used to monitor equipment status and environmental conditions to ensure the stability and safety of the production process. However, the performance of sensors is often affected by environmental factors, especially changes in temperature and humidity, which may cause inaccurate sensor readings and thus affect the monitoring and control of the entire production process. Therefore, how to effectively monitor and evaluate the impact of environmental factors on sensor performance, and how to take appropriate measures to ensure the accuracy of sensors based on these impacts, has become an urgent problem to be solved.

[0003] Traditional industrial monitoring systems often lack the ability to monitor environmental factors in real time and adjust them intelligently, and are unable to effectively assess the impact of these factors on sensor performance. In addition, for key components such as pressure sensors, once data anomalies occur, if there is no timely early warning mechanism, it may lead to equipment failure or even safety accidents.

[0004] Therefore, the shortcomings of the prior art mainly include:

[0005] Lack of effective means of monitoring environmental factors: Most existing monitoring systems can only simply record temperature and humidity data, but cannot evaluate the impact of this data on sensor performance.

[0006] Unable to accurately judge the sensor status: Traditional methods find it difficult to distinguish whether sensor data anomalies are caused by environmental factors or sensor failures, which leads to misjudgment.

[0007] Lack of automatic adjustment and early warning mechanisms: Most systems lack the ability to automatically adjust environmental conditions when an anomaly is detected, and are unable to issue early warnings to operators, resulting in problems not being resolved in a timely manner. Summary of the invention

[0008] Improve the operational stability and safety of industrial equipment by monitoring environmental factors and equipment status in real time. The core of the technical solution is to monitor and evaluate the impact of environmental conditions on sensor performance in stages, and diagnose and warn the equipment status based on this. First, by collecting temperature and humidity data in the working environment of the sensor in real time and conducting statistical analysis, the temperature anomaly factor and humidity anomaly factor are calculated, and then the signal that has a significant or minor impact on the sensor performance is obtained. Secondly, for sensors that are greatly affected, such as pressure sensors, their status is evaluated by comparing the current pressure data with historical normal data, and whether an abnormality has occurred. Once an abnormality is detected, the system automatically adjusts the environmental conditions to reduce the impact on the sensor and continues to monitor the pressure data to evaluate whether the equipment has failed. Finally, if a possible failure risk of the equipment is detected, the system will promptly issue an early warning signal to remind the operator to take necessary precautions to prevent the occurrence of equipment failure. The entire technical solution builds a closed-loop control system that can continuously monitor environmental changes, evaluate equipment status, and actively intervene to ensure the safe and reliable operation of the equipment, thereby significantly improving the efficiency and safety of industrial production.

[0009] The purpose of the present invention can be achieved through the following technical solutions:

[0010] A data collection and management method for industrial Internet of Things, comprising the following steps:

[0011] S1: by real-time collection of ambient temperature data and ambient humidity data when the pressure sensor is working, and processing the ambient temperature data and ambient humidity data to obtain a temperature anomaly factor and a humidity anomaly factor, the temperature anomaly factor and the humidity anomaly factor are processed to obtain an influence signal score IS, and the influence signal score IS is compared with a preset influence signal score threshold to generate an influence signal when the pressure sensor is working;

[0012] Among them, the influencing signals include normal signals and abnormal signals;

[0013] S2: Collect current pressure data and historical pressure data through the pressure sensor and compare them to obtain a pressure offset coefficient CSV, compare the pressure offset coefficient CSV with a preset pressure offset coefficient threshold; generate a pressure sensor status signal;

[0014] The pressure sensor status signal includes a normal pressure sensor signal and an abnormal pressure sensor signal;

[0015] Among them, the historical pressure data is cleaned to remove noise and outliers;

[0016] S3: Process the impact signal score IS and the pressure offset coefficient CSV to obtain a correlation coefficient r, compare the correlation coefficient r with a preset correlation coefficient threshold, and generate a correlation signal;

[0017] Wherein, the correlation signal includes correlation signal and non-correlation signal;

[0018] S4: Based on the correlation signal, the ambient temperature and humidity are adjusted. By collecting pressure data, it is evaluated whether the industrial equipment is faulty and a timely warning is issued for the fault.

[0019] As a further solution of the present invention: the acquisition process of the influence signal score IS:

[0020] The weight of the temperature anomaly factor WT is assigned to W1, and the weight of the humidity anomaly factor WH is assigned to W2;

[0021] The influence signal score IS is calculated by the formula IS=WT*W1+WH*W2.

[0022] As a further solution of the present invention: the process of obtaining the temperature anomaly factor WT is:

[0023] Get the real-time ambient temperature value of each time subunit;

[0024] The temperature value at the middle moment of each time subunit is recorded as the unit temperature value Ti;

[0025] Wherein, i represents i time subunits, i=1, 2, ..., n;

[0026] Calculate the mean of all temperature values ​​in the temperature value group to obtain the average temperature value Tiy;

[0027] Calculate the variance of all temperature values ​​in the temperature value group to obtain the temperature value variance value S1;

[0028] By formula The temperature anomaly coefficient CT is calculated;

[0029] By formula The temperature abnormal fluctuation ratio MT is calculated;

[0030] Wherein, b1 and b2 are both preset proportional factors, and b1 and b2 are both greater than 0.

[0031] By formula The temperature anomaly factor WT is calculated.

[0032] As a further solution of the present invention: the process of obtaining the humidity anomaly factor WH is:

[0033] Get real-time ambient humidity data for each time subunit;

[0034] The humidity value at the middle moment of each time subunit is recorded as the unit humidity value Hi;

[0035] Wherein, i represents i time subunits, i=1, 2, ..., n;

[0036] Integrate all unit humidity values ​​Hi into the humidity value group;

[0037] Calculate the mean of all humidity values ​​in the humidity value group to obtain the average humidity value Hiy;

[0038] Calculate the variance of all humidity values ​​in the humidity value group to obtain the humidity value variance S2;

[0039] By formula The humidity anomaly coefficient CH is calculated;

[0040] By formula The humidity fluctuation ratio RH is calculated;

[0041] The humidity anomaly factor WH is calculated by the formula WH = b3*CH + b4*RH;

[0042] Among them, b3 and b4 are preset proportional factors, and b3 and b4 are both greater than 0.

[0043] As a further solution of the present invention: the force offset coefficient CSV acquisition process:

[0044] Calculate the mean of the pressure deviation values ​​SVi j in each pressure deviation value group to obtain the unit pressure deviation mean value SVy i;

[0045] The maximum pressure deviation mean SVy imax and the minimum pressure deviation mean SVy imin are used to calculate the extreme difference value to obtain the pressure extreme difference value SC, and the pressure deviation coefficient CSV is calculated by adding it to the preset proportional factor.

[0046] As a further solution of the present invention: the process of obtaining the correlation coefficient r:

[0047] Obtain the impact signal score IS i and the pressure offset coefficient CSVi of the i-th time subunit;

[0048] By formula The correlation coefficient r was calculated;

[0049] Among them, ISy is the average impact signal score, and CSVy is the average pressure shift coefficient.

[0050] As a further solution of the present invention: the pressure anomaly score Ra is compared with a preset pressure anomaly score to generate a fault signal and a non-fault signal.

[0051] As a further solution of the present invention: the process of obtaining the pressure abnormality score Ra is:

[0052] The difference between the maximum pressure value and the minimum pressure value of each unit is calculated to obtain the unit pressure extreme difference value, and the ratio of the unit pressure extreme difference value to the unit average pressure value is calculated to obtain the unit pressure fluctuation ratio qa;

[0053] By formula The pressure value fluctuation ratio Ja is calculated;

[0054] Wherein, b7 and b8 are both preset proportional factors, and b7 and b8 are both greater than 0, and Ja represents the pressure value jump ratio of the a-th time subunit;

[0055] By formula The pressure abnormality score Ra is calculated.

[0056] A data collection and management system for industrial Internet of Things, including a data collection module, an anomaly detection module, a pressure sensor state evaluation module, a correlation analysis module and an adjustment and early warning module;

[0057] A data acquisition module, which collects ambient temperature data, ambient humidity data and pressure data in real time through sensors, and sends the collected data to the anomaly detection module;

[0058] An anomaly detection module, the anomaly detection module is used to receive environmental data, and process the environmental temperature data and the environmental humidity data, and obtain an impact signal score through temperature anomaly factors and humidity anomaly factors, and transmit the impact signal to the pressure sensor state evaluation module;

[0059] A pressure sensor state evaluation module, the pressure sensor state evaluation module is used to receive the impact signal, collect data in real time through the pressure sensor, and compare it with historical data to generate a pressure sensor state signal;

[0060] A correlation analysis module, wherein the correlation analysis module analyzes the correlation between the impact signal score and the pressure transmission deviation coefficient;

[0061] The adjustment and early warning module is used to receive abnormal signals from the pressure sensor, and ensure the accuracy of the data collected by the pressure sensor by adjusting the ambient temperature data and the ambient humidity data, and evaluate the equipment status, generate fault signals, and issue early warnings.

[0062] A computer-readable storage medium stores a computer program, which executes the steps in the above method when executed by a processor.

[0063] Beneficial effects of the present invention:

[0064] (1) By monitoring the changes in environmental conditions in real time, the operating status of industrial equipment can be evaluated, and potential failure risks can be identified in a timely manner; through the steps in the embodiment, the system can effectively detect abnormal changes in ambient temperature and humidity, and generate impact signals accordingly. When the impact signal score exceeds the preset threshold, the system will trigger further pressure sensor status evaluation, which helps to ensure the accuracy of the sensor and the overall stability of the equipment; if the pressure sensor reading is found to be abnormal, the system will adjust the environmental conditions to reduce the impact on sensor performance; this closed-loop control mechanism can significantly improve the operating reliability of industrial equipment and reduce false alarms or missed alarms caused by sensor inaccuracy, thereby avoiding unnecessary downtime and high maintenance costs; in addition, through continuous monitoring and timely adjustments, the system can also extend equipment life, reduce operating costs, and ensure the continuity and efficiency of the production process;

[0065] (2) By real-time monitoring of ambient temperature and humidity, the system can detect environmental factors that may cause equipment failures at an early stage, such as excessively high or low temperatures, humidity changes, etc. Once an abnormality is detected, the system will immediately take measures, such as adjusting the ambient temperature and humidity, to reduce the impact on the sensor. At the same time, by comparing the current pressure data with the historical normal data, the system can evaluate the status of the pressure sensor and determine whether it is accurate and reliable. When the system detects that the pressure sensor data is abnormal, it will generate a pressure sensor abnormality signal and take corresponding adjustment measures to improve the working conditions of the sensor. This proactive intervention method can not only avoid the occurrence of equipment failures, but also arrange preventive maintenance through early warning, thereby minimizing unexpected downtime. In addition, through continuous monitoring and analysis, the system can also accumulate a large amount of data on the health of the equipment, and then use this data to make more accurate predictive maintenance plans, thereby improving the overall safety and production efficiency of the factory. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The present invention will be further described below in conjunction with the accompanying drawings.

[0067] Figure 1 This is a structural schematic diagram of the specific steps of a data collection and management method for industrial Internet of Things of the present invention;

[0068] Figure 2 This is a schematic diagram of the structure of a data collection and management system for industrial Internet of Things in the present invention;

[0069] Figure 3It is a schematic diagram of the structure of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0071] Example 1

[0072] See also Figure 1 As shown, the present invention is a data collection and management method for industrial Internet of Things, comprising the following steps:

[0073] S1: by real-time collection of ambient temperature data and ambient humidity data when the pressure sensor is working, and processing the ambient temperature data and ambient humidity data to obtain a temperature anomaly factor and a humidity anomaly factor, the temperature anomaly factor and the humidity anomaly factor are processed to obtain an influence signal score IS, and the influence signal score IS is compared with a preset influence signal score threshold to generate an influence signal when the pressure sensor is working;

[0074] Among them, the influencing signals include normal signals and abnormal signals;

[0075] S2: Collect current pressure data and historical pressure data through the pressure sensor and compare them to obtain a pressure offset coefficient CSV, compare the pressure offset coefficient CSV with a preset pressure offset coefficient threshold; generate a pressure sensor status signal;

[0076] The pressure sensor status signal includes a normal pressure sensor signal and an abnormal pressure sensor signal;

[0077] Among them, the historical pressure data is cleaned to remove noise and outliers;

[0078] S3: Process the impact signal score IS and the pressure offset coefficient CSV to obtain a correlation coefficient r, compare the correlation coefficient r with a preset correlation coefficient threshold, and generate a correlation signal;

[0079] Wherein, the correlation signal includes correlation signal and non-correlation signal;

[0080] S4: Based on the correlation signal, the ambient temperature and humidity are adjusted. By collecting pressure data, it is evaluated whether the industrial equipment is faulty and a timely warning is issued for the fault.

[0081] Example 2

[0082] On the basis of Example 1, the sensor working cycle is divided into several time sub-units, and the ambient temperature data and ambient humidity data of each time sub-unit are respectively obtained, and the ambient temperature data and ambient humidity data are processed to obtain the temperature anomaly factor and the humidity anomaly factor, and the temperature anomaly factor and the humidity anomaly factor are processed to obtain the sensor device impact signal;

[0083] Among them, the influencing signals include normal signals and abnormal signals;

[0084] Specific:

[0085] During the working cycle of the sensor, the working cycle of the sensor is divided into several time sub-units, and the working environment data of the sensor is collected according to the time series (such as every minute);

[0086] Wherein, the environmental data includes environmental temperature data and environmental humidity data;

[0087] Get the real-time ambient temperature value of each time subunit;

[0088] The temperature value at the middle moment of each time subunit is recorded as the unit temperature value Ti;

[0089] Wherein, i represents i time subunits, i=1, 2, ..., n;

[0090] Integrate all unit temperature values ​​Ti into the temperature value group;

[0091] Calculate the mean of all temperature values ​​in the temperature value group to obtain the average temperature value Tiy;

[0092] Calculate the variance of all temperature values ​​in the temperature value group to obtain the temperature value variance value S1;

[0093] By formula The temperature anomaly coefficient CT is calculated;

[0094] By formula The temperature abnormal fluctuation ratio MT is calculated;

[0095] Wherein, b1 and b2 are both preset proportional factors, and b1 and b2 are both greater than 0.

[0096] By formula The temperature anomaly factor WT is calculated;

[0097] Get real-time ambient humidity data for each time subunit;

[0098] The humidity value at the middle moment of each time subunit is recorded as the unit humidity value Hi;

[0099] Wherein, i represents i time subunits, i=1, 2, ..., n;

[0100] Integrate all unit humidity values ​​Hi into the humidity value group;

[0101] Calculate the mean of all humidity values ​​in the humidity value group to obtain the average humidity value Hiy;

[0102] Calculate the variance of all humidity values ​​in the humidity value group to obtain the humidity value variance S2;

[0103] By formula The humidity anomaly coefficient CH is calculated;

[0104] By formula The humidity fluctuation ratio RH is calculated;

[0105] The humidity anomaly factor WH is calculated by the formula WH = b3*CH + b4*RH;

[0106] Among them, b3 and b4 are preset proportional factors, and b3 and b4 are both greater than 0.

[0107] Process the temperature anomaly factor WT and humidity anomaly factor WH;

[0108] The weight of the temperature anomaly factor WT is assigned to W1, and the weight of the humidity anomaly factor WH is assigned to W2;

[0109] The influence signal score IS is calculated by the formula IS=WT*W1+WH*W2;

[0110] comparing the influence signal score IS with a preset influence signal score threshold;

[0111] If the impact signal score IS is greater than or equal to the preset impact signal score threshold, a normal signal is generated;

[0112] If the impact signal score IS is less than the preset impact signal score threshold, an abnormal signal is generated;

[0113] It should be noted that the impact signal indicates that the sensor is affected by environmental factors.

[0114] Example 3

[0115] On the basis of Example 2, since the pressure sensor is greatly affected by environmental factors, the accuracy of the data collected by the pressure sensor is judged;

[0116] Specific:

[0117] Install pressure sensors on industrial equipment, debug the industrial equipment, and ensure the equipment is in normal condition;

[0118] The pressure data of each time sub-unit is collected in real time according to a time series (such as every minute) by a pressure sensor;

[0119] Get the real-time pressure value Vi j of each time subunit;

[0120] Wherein, i represents the i-th time subunit, j represents the j-th acquisition point of the i-th time subunit;

[0121] All pressure values ​​in each time subunit are integrated separately to obtain several pressure value groups {V11, V12, ..., V1 j}, {V21, V22, ..., V2 j}, ... {V i 1, V i 2, ..., Vi j};

[0122] According to the same collection method, the pressure value group {VL11, VL12, ..., VL1 j}, {VL21, VL22, ..., VL2j}, ... {VL i 1, VLi 2, ..., VL ij} collected in the historical normal period is obtained;

[0123] Wherein, VL ij represents the pressure value of the jth acquisition point in the i-th time subunit of the history;

[0124] According to the sequence order of time acquisition, the difference between the historical pressure value and the current pressure value is calculated and the absolute value is taken, and the pressure deviation value group {SV11, SV12, ..., SV1 j}, {SV21, SV22, ..., SV2j}, ... {SVi 1, SVi 2, ..., SV ij} is obtained by integration;

[0125] Wherein, SVi j represents the pressure deviation value between the historical pressure value and the current pressure value at the i-th time subunit and the j-th acquisition point;

[0126] Calculate the mean of the pressure deviation values ​​SVi j in each pressure deviation value group to obtain the unit pressure deviation mean value SVy i;

[0127] Get the maximum pressure deviation mean SVy imax;

[0128] Get the minimum pressure deviation mean SVy imin;

[0129] The pressure extreme difference value SC is calculated by the formula SC = SVyimax-SVyimin;

[0130] By formula The pressure deviation coefficient CSV is calculated;

[0131] Wherein, b5 and b6 are both preset proportional factors, and b5 and b6 are both greater than 0;

[0132] comparing the pressure offset coefficient with a preset pressure offset coefficient threshold;

[0133] If the pressure deviation coefficient is greater than or equal to the preset pressure deviation coefficient threshold, it means that the data collected by the pressure sensor is inaccurate, and a pressure sensor abnormal signal is generated;

[0134] If the pressure deviation coefficient is less than the preset pressure deviation coefficient threshold, it means that the pressure sensor collects data accurately and generates a normal pressure sensor signal;

[0135] It should be noted that by comparing the pressure offset coefficient with the pressure offset coefficient threshold, the accuracy of the data collected by the sensor can be reflected in a timely manner, so as to facilitate timely calibration of the sensor, ensure the accuracy of the collected data, and ensure the normal operation of the industrial equipment.

[0136] Example 4

[0137] On the basis of Embodiment 2 and Embodiment 3, the influence signal score IS i and the pressure offset coefficient CSVi of the i-th time subunit are obtained;

[0138] Integrate the influence signal scores IS i of all time sub-units to obtain an influence signal score group;

[0139] The average influence signal score I Sy in the influence signal score group is calculated by the mean calculation formula;

[0140] Integrate the pressure offset coefficients CSVi of all time sub-units to obtain a pressure offset coefficient group;

[0141] The average pressure offset coefficient CSVy in the pressure offset coefficient group is calculated by the mean calculation formula;

[0142] By formula The correlation coefficient r was calculated;

[0143] Compare the correlation coefficient r with a preset correlation coefficient threshold;

[0144] If the correlation coefficient r is greater than or equal to the preset correlation coefficient threshold, it means that there is a correlation between the impact signal score IS and the pressure offset coefficient CSV, and the pressure sensor is abnormally affected by environmental factors, generating a correlation signal;

[0145] If the correlation coefficient r is greater than or equal to the preset correlation coefficient threshold, it means that there is no correlation between the impact signal score IS and the pressure offset coefficient CSV, and the pressure sensor abnormality is not affected by environmental factors, and a non-correlation signal is generated;

[0146] Example 5

[0147] On the basis of Example 4, based on the correlation signal, the ambient temperature data and the ambient humidity data are adjusted so that the influence signal score IS is less than a preset influence signal score threshold;

[0148] Install pressure sensors on industrial equipment and calibrate them, and use the pressure sensors to collect pressure data in real time according to a time series (such as every minute);

[0149] Divide the acquisition period into a number of time sub-units;

[0150] Get the real-time pressure value Vab of each time subunit;

[0151] Wherein, a represents the ath time subunit, b represents the bth acquisition point of the ath time subunit;

[0152] Integrate the pressure value of each time sub-unit to obtain several unit pressure value groups;

[0153] The average pressure value Vay of each unit pressure value group is calculated by the mean calculation formula;

[0154] Get the maximum pressure value Vamax of each unit pressure value group;

[0155] Get the minimum pressure value Vamin of each unit pressure value group;

[0156] The difference between the maximum pressure value and the minimum pressure value of each unit is calculated to obtain the unit pressure extreme difference value, and the ratio of the unit pressure extreme difference value to the unit average pressure value is calculated to obtain the unit pressure fluctuation ratio qa;

[0157] By formula The pressure value fluctuation ratio Ja is calculated;

[0158] Wherein, b7 and b8 are both preset proportional factors, and b7 and b8 are both greater than 0, and Ja represents the pressure value jump ratio of the a-th time subunit;

[0159] By formula The pressure abnormality score Ra is calculated;

[0160] Compare the pressure abnormality score Ra with a preset pressure abnormality score threshold;

[0161] If the pressure anomaly score Ra is greater than or equal to the preset pressure anomaly score threshold, it means that the pressure is abnormal for the time period, and the device fails, generating a fault signal;

[0162] If the pressure anomaly score Ra is less than the preset pressure anomaly score threshold, it means that the pressure is normal for the time period, and the device does not fail, and a non-fault signal is generated;

[0163] Based on the fault signal, the fault signal is fed back to the staff in a timely manner, early warning is given in a timely manner, and the industrial equipment is shut down and repaired in a timely manner.

[0164] It should be noted that by collecting and monitoring data through sensors, timely warning of faults can be provided to prevent safety problems caused by abnormalities of industrial equipment.

[0165] Example 5

[0166] See also Figure 2 As shown, a data acquisition and management system for industrial Internet of Things includes a data acquisition module, an anomaly detection module, a pressure sensor state evaluation module, a correlation analysis module and an adjustment and early warning module;

[0167] A data acquisition module, which collects ambient temperature data, ambient humidity data and pressure data in real time through sensors, and sends the collected data to the anomaly detection module;

[0168] An anomaly detection module, the anomaly detection module is used to receive environmental data, and process the environmental temperature data and the environmental humidity data, and obtain an impact signal score through temperature anomaly factors and humidity anomaly factors, and transmit the impact signal to the pressure sensor state evaluation module;

[0169] A pressure sensor state evaluation module, the pressure sensor state evaluation module is used to receive the impact signal, collect data in real time through the pressure sensor, and compare it with historical data to generate a pressure sensor state signal;

[0170] A correlation analysis module, wherein the correlation analysis module analyzes the correlation between the impact signal score and the pressure transmission deviation coefficient;

[0171] The adjustment and early warning module is used to receive abnormal signals from the pressure sensor, and ensure the accuracy of the data collected by the pressure sensor by adjusting the ambient temperature data and the ambient humidity data, and evaluate the equipment status, generate fault signals, and issue early warnings.

[0172] Example 6

[0173] See also Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented:

[0174] S1: by real-time collection of ambient temperature data and ambient humidity data when the pressure sensor is working, and processing the ambient temperature data and ambient humidity data to obtain a temperature anomaly factor and a humidity anomaly factor, the temperature anomaly factor and the humidity anomaly factor are processed to obtain an influence signal score IS, and the influence signal score IS is compared with a preset influence signal score threshold to generate an influence signal when the pressure sensor is working;

[0175] Among them, the influencing signals include normal signals and abnormal signals;

[0176] S2: Collect current pressure data and historical pressure data through the pressure sensor and compare them to obtain a pressure offset coefficient CSV, compare the pressure offset coefficient CSV with a preset pressure offset coefficient threshold; generate a pressure sensor status signal;

[0177] The pressure sensor status signal includes a normal pressure sensor signal and an abnormal pressure sensor signal;

[0178] Among them, the historical pressure data is cleaned to remove noise and outliers;

[0179] S3: Process the impact signal score IS and the pressure offset coefficient CSV to obtain a correlation coefficient r, compare the correlation coefficient r with a preset correlation coefficient threshold, and generate a correlation signal;

[0180] Wherein, the correlation signal includes correlation signal and non-correlation signal;

[0181] S4: Based on the correlation signal, the ambient temperature and humidity are adjusted. By collecting pressure data, it is evaluated whether the industrial equipment is faulty and a timely warning is issued for the fault.

[0182] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0183] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0184] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0185] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0187] The working principle of the present invention is to improve the operational stability and safety of industrial equipment by real-time monitoring of environmental factors and equipment status. The core of the technical solution is to monitor and evaluate the impact of environmental conditions on sensor performance in stages, and diagnose and warn the equipment status based on this. First, by collecting temperature and humidity data in the working environment of the sensor in real time and performing statistical analysis on them, the temperature anomaly factor and humidity anomaly factor are calculated, and then the signal that has a significant or slight impact on the sensor performance is obtained. Secondly, for sensors that are greatly affected, such as pressure sensors, by comparing the current pressure data with historical normal data, its state is evaluated and it is determined whether an abnormality has occurred. Once an abnormality is detected, the system will automatically adjust the environmental conditions to reduce the impact on the sensor, and continue to monitor the pressure data to evaluate whether the equipment has failed. Finally, if a possible failure risk of the equipment is detected, the system will promptly issue an early warning signal to remind the operator to take necessary precautions to prevent the occurrence of equipment failure. The entire technical solution constructs a closed-loop control system that can continuously monitor environmental changes, evaluate equipment status, and actively intervene to ensure the safe and reliable operation of the equipment, thereby significantly improving the efficiency and safety of industrial production.

[0188] 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 data collection and management method for industrial Internet of Things, characterized in that: The following steps are involved: S1: by real-time collection of ambient temperature data and ambient humidity data when the pressure sensor is working, and processing the ambient temperature data and ambient humidity data to obtain a temperature anomaly factor and a humidity anomaly factor, the temperature anomaly factor and the humidity anomaly factor are processed to obtain an influence signal score IS, and the influence signal score IS is compared with a preset influence signal score threshold to generate an influence signal when the pressure sensor is working; Among them, the influencing signals include normal signals and abnormal signals; S2: Collect current pressure data and historical pressure data through the pressure sensor and compare them to obtain a pressure offset coefficient CSV, compare the pressure offset coefficient CSV with a preset pressure offset coefficient threshold; generate a pressure sensor status signal; The pressure sensor status signal includes a normal pressure sensor signal and an abnormal pressure sensor signal; S3: Process the impact signal score IS and the pressure offset coefficient CSV to obtain a correlation coefficient r, compare the correlation coefficient r with a preset correlation coefficient threshold, and generate a correlation signal; Wherein, the correlation signal includes correlation signal and non-correlation signal; S4: Based on the correlation signal, the ambient temperature and humidity are adjusted. By collecting pressure data, it is evaluated whether the industrial equipment is faulty and a timely warning is issued for the fault.

2. The data collection and management method for industrial Internet of Things according to claim 1 is characterized in that: The process of obtaining the influence signal score IS: The weight of the temperature anomaly factor WT is assigned to W1, and the weight of the humidity anomaly factor WH is assigned to W2; The influence signal score IS is calculated by the formula IS=WT*W1+WH*W2.

3. The data collection and management method for industrial Internet of Things according to claim 2 is characterized in that: The process of obtaining the temperature anomaly factor WT is as follows: Get the real-time ambient temperature value of each time subunit; The temperature value at the middle moment of each time subunit is recorded as the unit temperature value Ti; Wherein, i represents i time subunits, i=1, 2, ..., n; Calculate the mean of all temperature values ​​in the temperature value group to obtain the average temperature value Tiy; Calculate the variance of all temperature values ​​in the temperature value group to obtain the temperature value variance value S1; By formula The temperature anomaly coefficient CT is calculated; By formula The temperature abnormal fluctuation ratio MT is calculated; Wherein, b1 and b2 are both preset proportional factors, and b1 and b2 are both greater than 0. By formula The temperature anomaly factor WT is calculated.

4. The data collection and management method for industrial Internet of Things according to claim 2 is characterized in that: The process of obtaining the humidity anomaly factor WH is as follows: Get real-time ambient humidity data for each time subunit; The humidity value at the middle moment of each time subunit is recorded as the unit humidity value Hi; Wherein, i represents the i-th time subunit, i=1, 2, ..., n; Integrate all unit humidity values ​​Hi into the humidity value group; Calculate the mean of all humidity values ​​in the humidity value group to obtain the average humidity value Hiy; Calculate the variance of all humidity values ​​in the humidity value group to obtain the humidity value variance S2; By formula The humidity anomaly coefficient CH is calculated; By formula The humidity fluctuation ratio RH is calculated; The humidity anomaly factor WH is calculated by the formula WH = b3*CH + b4*RH; Among them, b3 and b4 are preset proportional factors, and b3 and b4 are both greater than 0.

5. The data collection and management method for industrial Internet of Things according to claim 1 is characterized in that: Pressure offset coefficient CSV acquisition process: The pressure deviation values ​​SVij in each pressure deviation value group are averaged to obtain the unit pressure deviation average SVyi; The maximum pressure deviation mean SVy imax and the minimum pressure deviation mean SVy imin are used to calculate the extreme difference value to obtain the pressure extreme difference value SC, and the pressure deviation coefficient CSV is calculated by adding it to the preset proportional factor.

6. The data collection and management method for industrial Internet of Things according to claim 1 is characterized in that: The process of obtaining the correlation coefficient r is as follows: Get the impact signal score ISi and pressure offset coefficient CSVi of the i-th time subunit; By formula The correlation coefficient r was calculated; Among them, ISy is the average impact signal score, and CSVy is the average pressure shift coefficient.

7. The data collection and management method for industrial Internet of Things according to claim 1 is characterized in that: The pressure anomaly score Ra is compared with a preset pressure anomaly score to generate a fault signal and a non-fault signal.

8. The data collection and management method for industrial Internet of Things according to claim 7 is characterized in that: The process of obtaining the pressure abnormality score Ra is as follows: The difference between the maximum pressure value and the minimum pressure value of each unit is calculated to obtain the unit pressure extreme difference value, and the ratio of the unit pressure extreme difference value to the unit average pressure value is calculated to obtain the unit pressure fluctuation ratio qa; By formula The pressure value fluctuation ratio Ja is calculated; Wherein, b7 and b8 are both preset proportional factors, and b7 and b8 are both greater than 0, and Ja represents the pressure value jump ratio of the a-th time subunit; By formula The pressure abnormality score Ra is calculated.

9. A data collection and management system for industrial Internet of Things, characterized in that: It includes data acquisition module, anomaly detection module, pressure sensor status evaluation module, correlation analysis module and adjustment and early warning module; A data acquisition module, which collects ambient temperature data, ambient humidity data and pressure data in real time through sensors, and sends the collected data to the anomaly detection module; An anomaly detection module, the anomaly detection module is used to receive environmental data, and process the environmental temperature data and the environmental humidity data, and obtain an impact signal score through temperature anomaly factors and humidity anomaly factors, and transmit the impact signal to the pressure sensor state evaluation module; A pressure sensor state evaluation module, the pressure sensor state evaluation module is used to receive the impact signal, collect data in real time through the pressure sensor, and compare it with historical data to generate a pressure sensor state signal; A correlation analysis module, wherein the correlation analysis module analyzes the correlation between the impact signal score and the pressure transmission deviation coefficient; The adjustment and early warning module is used to receive abnormal signals from the pressure sensor, and ensure the accuracy of the data collected by the pressure sensor by adjusting the ambient temperature data and the ambient humidity data, and evaluate the equipment status, generate fault signals, and issue early warnings.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 8 are executed.

Images