Equipment operation and maintenance management system and method based on IOT technology

Through the IOT technology equipment operation and maintenance management system, real-time data analysis and health scoring are used to solve the problems of inaccurate fault diagnosis and lack of data support in the equipment management system, achieving more efficient equipment maintenance and cost control.

CN119067386APending Publication Date: 2024-12-03ANJIAN AUTOMATION TECH (SHANGHAI) CO LTD

Patent Information

Application Number
CN202411154955.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-22
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing equipment management system lacks in-depth analysis and real-time monitoring capabilities, resulting in insufficient fault diagnosis and lack of data support for maintenance decisions, which increases operational costs and downtime, and affects production efficiency.

Method used

Using the equipment operation and maintenance management system based on IOT technology, the basic data collection module, the equipment status evaluation module and the operation and maintenance decision-making module calculate the real-time average and peak value of the equipment, standard deviation analysis and abnormal identification are carried out, and equipment abnormal identification records are generated and Performance deviation analysis results, health scores are calculated based on maintenance records, and maintenance measures are formulated.

Benefits of technology

Accelerate fault diagnosis, improve maintenance accuracy, early warning of potential faults, significantly improve equipment operation efficiency and life, reduce operation and maintenance costs, and improve equipment reliability and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067386A_ABST
    Figure CN119067386A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of equipment management, in particular to an equipment operation and maintenance management system and method based on the IOT technology, and the system comprises a basic data collection module, an equipment state evaluation module, an equipment performance comparison module and an operation and maintenance decision module. According to the invention, by calculating the time difference and the standard deviation of the equipment data, identifying and recording the abnormal fluctuation, accelerating the fault diagnosis process, improving the maintenance accuracy, comparing the abnormal data with the standard performance data, and analyzing the change trend of the performance index, the early warning of the performance degradation is more timely, and the occurrence of potential faults is prevented. Equipment health scores and maintenance records are comprehensively utilized, specific time points and measures are provided for equipment maintenance, the operation efficiency and service life of equipment are remarkably improved, the reliability and efficiency of the equipment are remarkably improved through a comprehensive analysis and early warning mechanism, the downtime is shortened, the service life of the equipment is prolonged, and meanwhile operation and maintenance cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of equipment management, and in particular to an equipment operation and maintenance management system and method based on IOT technology. Background Art

[0002] The field of equipment management technology mainly involves how to effectively monitor, control, maintain and optimize the use and performance of equipment, combining automation, information technology and network technology to improve the reliability and efficiency of equipment and reduce operating costs. In industrial environments, the application of equipment management technology is particularly critical, helping to predict equipment failures, achieve preventive maintenance and maximize the life cycle of assets, enabling modern equipment management systems to optimize equipment operation and maintenance processes through real-time data collection, analysis and feedback to ensure smooth production processes.

[0003] Among them, the equipment operation and maintenance management system based on IOT technology is a system that uses the Internet of Things technology to achieve equipment maintenance and management. The system collects data by installing sensors on the equipment and sends it to the central processing system through the network. After data analysis, the system can automatically adjust the equipment settings or issue maintenance alerts to prevent failures and improve efficiency. The main uses include improving the reliability and efficiency of equipment operation, reducing downtime, extending the service life of equipment, and ultimately reducing maintenance costs. It has a wide range of applications in many fields such as manufacturing, energy management, and transportation systems.

[0004] Although existing technologies have achieved basic monitoring and maintenance in equipment management, they usually lack the ability to conduct in-depth analysis and real-time monitoring of equipment status, resulting in limited effectiveness in predictive and preventive maintenance, and inaccurate early diagnosis of equipment failures, often reacting only after the failure occurs. In addition, the lack of real-time tracking and analysis of equipment performance degradation trends means that maintenance decisions often lack data support, making it difficult to conduct effective risk management and resource optimization, increasing equipment downtime, increasing operating costs, and affecting overall production efficiency. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an equipment operation and maintenance management system and method based on IOT technology.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solution: an equipment operation and maintenance management system based on IOT technology includes:

[0007] The basic data collection module collects the readings of the equipment temperature sensor, load monitor and power meter, extracts the time series in the data, calculates the real-time average and peak values, reflects the current operating status of the equipment, and outputs a snapshot of the equipment operation;

[0008] The equipment status assessment module calculates the time difference based on the equipment operation snapshot, and performs standard deviation analysis on the sensor data, identifies abnormal fluctuations in the data according to the analysis results, calculates the abnormality identification index, and generates equipment abnormality identification records;

[0009] The equipment performance comparison module uses the equipment abnormality identification record to compare the current abnormal data with the equipment standard performance data, calculates the performance data difference value, performs statistical analysis based on the calculation results, analyzes the change trend of the equipment performance indicators, and generates equipment performance deviation analysis results;

[0010] The operation and maintenance decision module calculates the current health score of the equipment based on the equipment performance deviation analysis results and the equipment maintenance records, analyzes and determines the equipment maintenance time point, formulates maintenance measures, and outputs a comprehensive equipment operation and maintenance management plan.

[0011] As a further solution of the present invention, the steps of obtaining the device operation snapshot are:

[0012] Collect the temperature, load and power readings of the device and use the formula,

[0013] D={(t i ,x i ,y i ,z i )}

[0014] Establish a data set D corresponding to the timestamp and reading, and generate an initial data set, where t i represents the i-th time point, x i ,y i 、z i Corresponding to temperature, load and power readings respectively;

[0015] Based on the initial data set, using the formula,

[0016]

[0017] and

[0018] P=max(wx·xi,wy·yi,wz·zi)

[0019] Calculate the weighted real-time average μ and peak value P of the sensor data to generate weighted real-time average and peak data, where w x 、w y 、w z is the weight parameter used to adjust the impact of differential sensor data, and n represents the number of data points;

[0020] The weighted real-time average and peak data are used in combination with the safety threshold to make a state judgment, using the formula:

[0021]

[0022] Output device operation snapshot S, where 1 indicates abnormality, 0 indicates normality, μ s is the safe average value, P s is the peak threshold.

[0023] As a further solution of the present invention, the step of analyzing the standard deviation of the sensor data is:

[0024] Extract the timestamps of all consecutive measurements from the device run snapshot using the formula,

[0025] Δt i =t i+1 -t i

[0026] Calculate the time difference Δt between two consecutive measurements i , generate a time difference sequence, where i represents the index of the consecutive measurements, t i represents the time point of the i-th measurement, t i+1 represents the time point of the i+1th measurement;

[0027] Using the time difference sequence, the formula is adopted:

[0028]

[0029] Calculates the arithmetic mean of a series of time differences Output average time difference data, where N represents the total number of measurement points;

[0030] Based on the average time difference data, the standard deviation of the measurement data of all sensors is calculated using the formula,

[0031]

[0032] Output standard deviation σ, evaluate the consistency and fluctuation of data, and generate data deviation calculation results, where α is an adjustment parameter used to emphasize the minimum deviation in the data and improve the calculation sensitivity, x i is the sensor reading of the ith measurement, and x is the average of the sensor readings.

[0033] As a further solution of the present invention, the steps of obtaining the device abnormality identification record are:

[0034] Using the data deviation calculation results, abnormal data points are identified using the formula:

[0035]

[0036] Generate anomaly dataset E, where k is the sensitivity coefficient used to adjust the strictness of identifying anomalies;

[0037] The abnormal data set is analyzed using the formula:

[0038]

[0039] Calculate the proportion of abnormal data points p to evaluate the severity of anomalies in the data set, where |E| is the number of abnormal data points;

[0040] According to the abnormal data point ratio, the formula is used:

[0041]

[0042] Calculate the anomaly identification index I and generate the device anomaly identification record, where β is the mitigation factor used to adjust the impact of non-abnormal data on the index, and w is the data importance weight used to adjust the impact of the abnormal proportion.

[0043] As a further solution of the present invention, the steps for calculating the performance data difference value are:

[0044] Based on the device abnormality identification record, extract the timestamp and corresponding performance reading of each abnormal event and record it as D 异常 , output abnormal performance data set;

[0045] Based on the abnormal performance data set, obtain 异常 The timestamp recorded in the D 标准 , generate a standard performance data set;

[0046] Using the abnormal performance data set and the standard performance data set, the formula is adopted:

[0047]

[0048] Calculate the average performance difference value Generate performance difference data, where w i is the weight for each performance indicator, which is used to adjust the importance of the difference indicator, and M is the total number of data point records.

[0049] As a further solution of the present invention, the steps for obtaining the equipment performance deviation analysis result are:

[0050] The performance difference data is statistically analyzed using the formula:

[0051]

[0052] Calculate the standard deviation of the difference value σ ΔD, analyze the dispersion of the difference values ​​and obtain the statistical analysis results of the difference data, where M is the total number of data point records;

[0053] According to the statistical analysis results of the difference data, the formula is used:

[0054]

[0055] Calculate the performance change rate R, evaluate the stability of the performance change, and output the performance change stability analysis results;

[0056] According to the performance change stability analysis results, the performance trend of the equipment is judged, and the formula is used.

[0057]

[0058] Perform logical judgment and generate equipment performance deviation analysis results.

[0059] As a further solution of the present invention, the steps for obtaining the equipment comprehensive operation and maintenance management solution are:

[0060] Based on the performance deviation analysis results and combined with the equipment maintenance records, the formula is used:

[0061]

[0062] Calculate the device health score H, where R i is the deviation score of the difference performance indicator, a i is the importance weight of the performance indicator, b is the maintenance history adjustment factor, which is set according to the equipment type and industry standards, c is the overall score adjustment factor, which is used to adjust the sensitivity of the health score, max(R) is the maximum value of the deviation score, Y is the number of maintenance times, Z is the equipment operation time, and m is the total number of deviation score data;

[0063] According to the equipment health score, the maintenance time point is analyzed to determine the maintenance urgency, using the formula,

[0064]

[0065] Determine the maintenance time point T 维护 , where d represents the health score threshold, which is used to determine the maintenance urgency;

[0066] According to the equipment health score, maintenance measures are formulated using the formula,

[0067]

[0068] Combined with the maintenance time point, the equipment operation and maintenance management plan is output, where e is the secondary threshold of the health score, which determines the type of maintenance.

[0069] An equipment operation and maintenance management method based on IOT technology includes the following steps:

[0070] S1: Collect the temperature, load and power readings of the device, establish a data set corresponding to the timestamp and reading, calculate the weighted real-time average and peak value of the sensor data, combine the safety threshold, make status judgment, and output the device operation snapshot;

[0071] S2: extracting the timestamps of all continuous measurements from the device operation snapshot, calculating the time difference and arithmetic mean between two consecutive measurements, calculating the standard deviation of the measurement data of all sensors, evaluating the consistency and fluctuation of the data, and generating a data deviation calculation result;

[0072] S3: using the data deviation calculation result, identifying abnormal data points, analyzing the proportion of abnormal data points, evaluating the severity of abnormalities in the data set, calculating an abnormality identification index, and generating a device abnormality identification record;

[0073] S4: extracting the timestamp and corresponding performance reading of each abnormal event based on the device abnormality identification record, synchronously acquiring the device standard performance data matching the timestamp, calculating the average performance difference value, and outputting the performance difference data;

[0074] S5: Performing statistical analysis based on the performance difference data, analyzing the dispersion of the difference values, calculating the performance change rate and evaluating the stability of the performance change, determining the equipment performance trend, and generating equipment performance deviation analysis results;

[0075] S6: Based on the performance deviation analysis results and combined with the equipment maintenance records, the equipment health score is calculated, the maintenance time point is analyzed to determine the maintenance urgency, maintenance measures are formulated, and the equipment operation and maintenance management plan is output.

[0076] Compared with the prior art, the advantages and positive effects of the present invention are:

[0077] In the present invention, by calculating the time difference and standard deviation of equipment data, abnormal fluctuations are identified and recorded, the fault diagnosis process is accelerated, the accuracy of maintenance is improved, the abnormal data is compared with the standard performance data, and the changing trend of the performance indicators is analyzed, so that the early warning of performance degradation is more timely and the occurrence of potential faults is prevented. The equipment health score and maintenance records are comprehensively utilized to provide specific time points and measures for equipment maintenance, which significantly improves the operating efficiency and life of the equipment. The comprehensive analysis and early warning mechanism significantly improves the reliability and efficiency of the equipment, reduces downtime, and extends the service life of the equipment, while also helping to reduce operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 is a system flow chart of the present invention;

[0079] Figure 2 A flowchart for obtaining a snapshot of the operation of the device of the present invention;

[0080] Figure 3 This is a flow chart of analyzing standard deviation of sensor data according to the present invention;

[0081] Figure 4 A flowchart for obtaining abnormal identification records of the device of the present invention;

[0082] Figure 5 is a flow chart for calculating the performance data difference value of the present invention;

[0083] Figure 6 A flowchart for obtaining the performance deviation analysis results of the equipment of the present invention;

[0084] Figure 7 The present invention is a flowchart for obtaining the comprehensive operation and maintenance management solution for the equipment. DETAILED DESCRIPTION

[0085] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0086] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0087] See also Figure 1 , an equipment operation and maintenance management system based on IOT technology includes:

[0088] The basic data collection module collects the readings of the equipment temperature sensor, load monitor and power meter, extracts the time series in the data, calculates the real-time average and peak values, reflects the current operating status of the equipment, and outputs a snapshot of the equipment operation;

[0089] The equipment status assessment module calculates the time difference based on the equipment operation snapshot, and performs standard deviation analysis on the sensor data. It identifies abnormal fluctuations in the data based on the analysis results, calculates the abnormal identification index, and generates equipment abnormality identification records.

[0090] The equipment performance comparison module uses the equipment abnormality identification records to compare the current abnormal data with the equipment standard performance data, calculate the performance data difference value, perform statistical analysis based on the calculation results, analyze the change trend of equipment performance indicators, and generate equipment performance deviation analysis results;

[0091] The operation and maintenance decision module is based on the equipment performance deviation analysis results and combined with the equipment maintenance records to calculate the current health score of the equipment, analyze and determine the equipment maintenance time point, formulate maintenance measures, and output the comprehensive operation and maintenance management plan for the equipment.

[0092] The equipment operation snapshot includes real-time average data and peak data. The equipment abnormality identification record includes abnormal fluctuation indicators and abnormal identification index. The equipment performance deviation analysis results include performance difference values ​​and performance change trend analysis results. The equipment comprehensive operation and maintenance management plan includes health scores, maintenance time points and maintenance measures.

[0093] See also Figure 2 , the steps to obtain the device operation snapshot are:

[0094] Collect the temperature, load and power readings of the device and use the formula,

[0095] D={(t i ,x i ,y i ,z i )}

[0096] Establish a data set D corresponding to the timestamp and reading, and generate an initial data set, where t i represents the i-th time point, x i ,y i 、z i Corresponding to temperature, load and power readings respectively;

[0097] Based on the initial data set, using the formula,

[0098]

[0099] and

[0100] P=max(wx·xi,wy·yi,wz·zi)

[0101] Calculate the weighted real-time average μ and peak value P of the sensor data to generate weighted real-time average and peak data, where w x 、w y 、w z is the weight parameter used to adjust the impact of differential sensor data, and n represents the number of data points;

[0102] Use weighted real-time average and peak data, combined with safety thresholds, to make status judgments, using the formula,

[0103]

[0104] Output device operation snapshot S, where 1 indicates abnormality, 0 indicates normality, μ s is the safe average value, P s is the peak threshold. The monitoring collects data at four time points, and the temperature (degrees Celsius), load (kW), and power (kW) are as follows:

[0105] t1: x1=25, y1=15, z1=10

[0106] t2: x2=30, y2=20, z2=15

[0107] t3: x3=28, y3=18, z3=12

[0108] t4: x4=26, y4=16, z4=11

[0109] We obtain D = {(t1, 25, 15, 10), (t2, 30, 20, 15), (t3, 28, 18, 12), (t4, 26, 16, 11)}, which is used to describe the equipment operating parameters at four different time points.

[0110] w x =0.5, w y =1.5,w z =1.0. n is 4.

[0111] Average calculation:

[0112]

[0113] Peak value calculation:

[0114]

[0115] P=max(17.68,24.49,15)=24.49

[0116] The average value μ = 56.875 represents the average effect of the weighted sensor readings. The peak value P = 24.49 represents the maximum device parameter reading in the weighted calculation, focusing on monitoring the highest load point.

[0117] Setting μ s =50 and P s =25, then:

[0118]

[0119] S=1

[0120] Status S=1 indicates that the equipment is abnormal because both the average and peak values ​​exceed the set safety thresholds. This status indication can guide the maintenance team to inspect or maintain the equipment to ensure safe operation.

[0121] See also Figure 3 , the steps for analyzing the standard deviation of sensor data are:

[0122] Extract the timestamps of all consecutive measurements from a snapshot of the device run using the formula,

[0123] Δt i =t i+1 -t i

[0124] Calculate the time difference Δt between two consecutive measurements i , generate a time difference sequence, where i represents the index of the consecutive measurements, t i represents the time point of the i-th measurement, t i+1 represents the time point of the i+1th measurement;

[0125] Using the time difference sequence, the formula is adopted.

[0126]

[0127] Calculates the arithmetic mean of a series of time differences Output average time difference data, where N represents the total number of measurement points;

[0128] Based on the average time difference data, the standard deviation of the measurement data of all sensors is calculated using the formula,

[0129]

[0130] Output standard deviation σ, evaluate the consistency and fluctuation of data, and generate data deviation calculation results, where α is an adjustment parameter used to emphasize the minimum deviation in the data and improve the calculation sensitivity, x i is the sensor reading of the ith measurement, and x is the average of the sensor readings.

[0131] The following data is collected:

[0132] Timestamp sequence: t1=0s, t2=2s, t3=5s.

[0133] but:

[0134] Δt1=t2-t1=2s-0s=2s

[0135] Δt2=t3-t2=5s-2s=3s

[0136] The obtained time difference sequence ΔT={2s, 3s} indicates that the time intervals of the measurements are inconsistent, which may affect the uniformity of data processing and the accuracy of subsequent analysis.

[0137] Combined with the above results, the time difference sequence ΔT = {2s, 3s}, the number of measurements N = 3

[0138] Substituting into the formula, we get:

[0139]

[0140] Average time difference It indicates that the average measurement interval is 2.5 seconds, which is used to evaluate the regularity of sensor data sampling.

[0141] The sequence of acquired measurement values: x1=10, x2=12, x3=14.

[0142] Then the average value is:

[0143]

[0144] α=0.5, substitute into the formula, and we get:

[0145]

[0146]

[0147] The standard deviation σ≈1.63 indicates the fluctuation of the measured data relative to the average value. A smaller standard deviation indicates that the data is more concentrated and has less fluctuation.

[0148] See also Figure 4 , the steps for obtaining device abnormality identification records are:

[0149] Using the data deviation calculation results, abnormal data points are identified using the formula:

[0150]

[0151] Generate anomaly dataset E, where k is the sensitivity coefficient used to adjust the strictness of identifying anomalies;

[0152] To analyze the abnormal data set, we use the formula:

[0153]

[0154] Calculate the proportion of abnormal data points p to evaluate the severity of anomalies in the data set, where |E| is the number of abnormal data points;

[0155] According to the proportion of abnormal data points, the formula is used:

[0156]

[0157] Calculate the anomaly identification index I and generate the device anomaly identification record, where β is the mitigation factor used to adjust the impact of non-abnormal data on the index, and w is the data importance weight used to adjust the impact of the abnormal proportion.

[0158] k=1, combined with the above data, the measurement value sequence is: x1=10, x2=12, x3=14, the average value is x=12, and the standard deviation σ≈1.63.

[0159] The abnormality judgment threshold is:

[0160] k·σ=1×1.63=1.63

[0161] Substituting into the formula, we get:

[0162] E={x i ∣|x i -12|>1.63}

[0163] Check each value:

[0164] |10-12|=2>1.63

[0165] |12-12|=0<1.63

[0166] |14-12|=2>1.63

[0167] Therefore, there are two values ​​exceeding the abnormal threshold, E = {10, 14}, indicating that these two data points are identified as abnormal under the given sensitivity coefficient, indicating that the readings of the equipment at these two time points deviate from the fluctuation range of normal operation.

[0168] If N=3, |E|=2 (obtained from the above calculation), then:

[0169]

[0170] The anomaly proportion p≈0.667 indicates that approximately 67% of the data points are identified as anomalies, indicating that there may be significant equipment operation or environmental problems.

[0171] w=1 (set to 1 to indicate average importance), β=0.5 (moderate adjustment).

[0172] Substituting into the formula, we get:

[0173]

[0174] The anomaly identification index I≈0.572 indicates that the device is experiencing moderate to high abnormal conditions, which helps to further investigate and take appropriate measures.

[0175] See also Figure 5 , the calculation steps of the performance data difference value are:

[0176] Based on the equipment anomaly identification records, extract the timestamp and corresponding performance reading of each abnormal event and record it as D 异常 , output abnormal performance data set;

[0177] Based on the abnormal performance dataset, obtain 异常 The timestamp recorded in the D 标准 , generate a standard performance data set;

[0178] Using the abnormal performance data set and the standard performance data set, the formula is adopted.

[0179]

[0180] Calculate the average performance difference value Generate performance difference data, where w i is the weight for each performance indicator, which is used to adjust the importance of the difference indicator, and M is the total number of data point records.

[0181] Abnormal data: D 异常 ={20, 22, 19, 25}.

[0182] Standard data: D 标准 ={18, 20, 18, 21}.

[0183] The weight w of each performance indicator i The same, both are 1, substitute into the formula and calculate the difference:

[0184] ΔD1=20-18=2

[0185] ΔD2=22-20=2

[0186] ΔD3=19-18=1

[0187] ΔD4=25-21=4

[0188] The average difference is:

[0189]

[0190] The average difference value ΔD = 2.25 obtained indicates that in this set of data, the average performance of the equipment exceeds the standard by 2.25. This number is a quantitative representation of the current performance status of the equipment, which is helpful for further analysis and formulation of maintenance strategies.

[0191] See also Figure 6 , the steps to obtain the equipment performance deviation analysis results are:

[0192] The performance difference data was statistically analyzed using the formula,

[0193]

[0194] Calculate the standard deviation of the difference value σ ΔD , analyze the dispersion of the difference values ​​and obtain the statistical analysis results of the difference data, where M is the total number of data point records;

[0195] According to the statistical analysis results of the difference data, the formula is used:

[0196]

[0197] Calculate the performance change rate R, evaluate the stability of the performance change, and output the performance change stability analysis results;

[0198] According to the performance change stability analysis results, the performance trend of the equipment is judged and the formula is used.

[0199]

[0200] Perform logical judgment and generate equipment performance deviation analysis results.

[0201] Known difference value: ΔD = {2, 2, 1, 4}, that is, M = 4 and Substitute this into the formula to calculate the standard deviation:

[0202]

[0203]

[0204] Standard Deviation ΔD ≈1.09 describes the dispersion of the difference values, indicating that the dispersion of the difference values ​​is high.

[0205] Combined with the above calculation results and σ ΔD =1.09.

[0206] Substituting into the formula, we get:

[0207]

[0208] The performance change rate R≈2.06 means that the average difference value is more than twice its standard deviation, indicating that the trend of equipment performance degradation is not particularly drastic, but its sustainability needs attention.

[0209] A judgment is made based on R≈2.06, because R≈2.06 is greater than 1, indicating that the performance trend is stable or has signs of improvement, and does not show obvious performance degradation.

[0210] See also Figure 7 , the steps to obtain the equipment comprehensive operation and maintenance management plan are:

[0211] Based on the performance deviation analysis results and combined with equipment maintenance records, the formula is used.

[0212]

[0213] Calculate the device health score H, where R i is the deviation score of the difference performance indicator, a i is the importance weight of the performance indicator, b is the maintenance history adjustment factor, which is set according to the equipment type and industry standards, c is the overall score adjustment factor, which is used to adjust the sensitivity of the health score, max(R) is the maximum value of the deviation score, Y is the number of maintenance times, Z is the equipment operation time, and m is the total number of deviation score data;

[0214] According to the equipment health score, the maintenance time point is analyzed to determine the maintenance urgency, and the formula is used.

[0215]

[0216] Determine the maintenance time point T 维护 , where d represents the health score threshold, which is used to determine the maintenance urgency;

[0217] According to the equipment health score, maintenance measures are formulated using formulas.

[0218]

[0219] Combined with the maintenance time point, the equipment operation and maintenance management plan is output, where e is the secondary threshold of the health score, which determines the type of maintenance.

[0220] Get the following parameters:

[0221] The deviation score R={20, 15, 10}, that is, m=3, then max(R)=20.

[0222] Weight a i ={1, 0.8, 0.5}.

[0223] Maintenance times Y=5.

[0224] Equipment operation time Z = 24 months.

[0225] b=0.5, c=1.5.

[0226] Weighted deviation sum:

[0227]

[0228] Normalized Deviation:

[0229]

[0230] Maintenance Impact:

[0231]

[0232] Health score:

[0233] H = 100 - (1.85 + 0.1042) × 1.5

[0234] =100-1.9542×1.5=97.0687

[0235] The calculated health score H = 97.0687 indicates that the equipment is in good health. The closer the score is to 100, the better the equipment is, and a lower score indicates that maintenance is needed.

[0236] Using the above calculation results, H = 97.0687, combined with d = 50, we can get:

[0237] Since 97.0687 is greater than 50, T 维护 = Planned maintenance, planning maintenance for an appropriate time in the future rather than immediate maintenance, allowing for resource optimization and maintenance scheduling.

[0238] Continue to use H = 97.0687 as input, e = 30, then:

[0239] H = 97.0687 is much higher than 30, so: Measures = routine inspection and adjustment.

[0240] Since the equipment health score indicates that the equipment is in good condition, the measures taken are routine inspections and adjustments rather than major repairs. This strategy helps maintain equipment performance and extend its service life while avoiding unnecessary cost expenditures. Finally, combined with the maintenance time point, the equipment operation and maintenance management plan can be output.

[0241] An equipment operation and maintenance management method based on IOT technology includes the following steps:

[0242] S1: Collect the temperature, load and power readings of the device, establish a data set corresponding to the timestamp and reading, calculate the weighted real-time average and peak value of the sensor data, combine the safety threshold, make status judgment, and output the device operation snapshot;

[0243] S2: Extract the timestamps of all continuous measurements from the device operation snapshot, calculate the time difference and arithmetic mean between two consecutive measurements, calculate the standard deviation of the measurement data of all sensors, evaluate the consistency and fluctuation of the data, and generate the data deviation calculation results;

[0244] S3: Use the data deviation calculation results to identify abnormal data points, analyze the proportion of abnormal data points, evaluate the severity of abnormalities in the data set, calculate the abnormality identification index, and generate equipment abnormality identification records;

[0245] S4: Based on the equipment abnormality identification record, extract the timestamp and corresponding performance reading of each abnormal event, synchronously obtain the equipment standard performance data matching the timestamp, calculate the average performance difference value, and output the performance difference data;

[0246] S5: Perform statistical analysis based on performance difference data, analyze the dispersion of difference values, calculate the performance change rate and evaluate the stability of performance change, determine the performance trend of equipment, and generate equipment performance deviation analysis results;

[0247] S6: Based on the performance deviation analysis results and combined with the equipment maintenance records, calculate the equipment health score, analyze the maintenance time points to determine the maintenance urgency, formulate maintenance measures, and output the equipment operation and maintenance management plan.

[0248] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An equipment operation and maintenance management system based on IOT technology, Features: The system comprises: The basic data collection module collects the readings of the equipment temperature sensor, load monitor and power meter, extracts the time series in the data, calculates the real-time average and peak values, reflects the current operating status of the equipment, and outputs a snapshot of the equipment operation; The equipment status assessment module calculates the time difference based on the equipment operation snapshot, and performs standard deviation analysis on the sensor data, identifies abnormal fluctuations in the data according to the analysis results, calculates the abnormality identification index, and generates equipment abnormality identification records; The equipment performance comparison module uses the equipment abnormality identification record to compare the current abnormal data with the equipment standard performance data, calculates the performance data difference value, performs statistical analysis based on the calculation results, analyzes the change trend of the equipment performance indicators, and generates equipment performance deviation analysis results; The operation and maintenance decision module calculates the current health score of the equipment based on the equipment performance deviation analysis results and the equipment maintenance records, analyzes and determines the equipment maintenance time point, formulates maintenance measures, and outputs a comprehensive equipment operation and maintenance management plan.

2. The equipment operation and maintenance management system based on IOT technology according to claim 1, Features: The steps for obtaining the device operation snapshot are as follows: Collect the temperature, load and power readings of the device and use the formula, D={(t i ,x i ,y i ,z i )} Establish a data set D corresponding to the timestamp and reading, and generate an initial data set, where t i represents the i-th time point, x i ,y i 、z i Corresponding to temperature, load and power readings respectively; Based on the initial data set, using the formula, and P=max(w x ·x i ,w y ·y i ,w z ·z i ) Calculate the weighted real-time average μ and peak value P of the sensor data to generate weighted real-time average and peak data, where w x 、w y 、w z is the weight parameter used to adjust the impact of differential sensor data, and n represents the number of data points; The weighted real-time average and peak data are used in combination with the safety threshold to make a state judgment, using the formula: Output device operation snapshot S, where 1 indicates abnormality, 0 indicates normality, μ s is the safe average value, P s is the peak threshold.

3. The equipment operation and maintenance management system based on IOT technology according to claim 2, Features: The steps of analyzing the standard deviation of the sensor data are as follows: Extract the timestamps of all consecutive measurements from the device run snapshot using the formula, Δt i =t i+1 -t i Calculate the time difference Δt between two consecutive measurements i , generate a time difference sequence, where i represents the index of the consecutive measurements, t i represents the time point of the i-th measurement, t i+1 represents the time point of the i+1th measurement; Using the time difference sequence, the formula is adopted: Calculates the arithmetic mean of a series of time differences Output average time difference data, where N represents the total number of measurement points; Based on the average time difference data, the standard deviation of the measurement data of all sensors is calculated using the formula, Output standard deviation σ, evaluate the consistency and fluctuation of data, and generate data deviation calculation results, where α is an adjustment parameter used to emphasize the minimum deviation in the data and improve the calculation sensitivity, x i is the sensor reading of the ith measurement, is the average of the sensor readings.

4. The equipment operation and maintenance management system based on IOT technology according to claim 3, Features: The steps for obtaining the device abnormality identification record are as follows: Using the data deviation calculation results, abnormal data points are identified using the formula: Generate anomaly dataset E, where k is the sensitivity coefficient used to adjust the strictness of identifying anomalies; The abnormal data set is analyzed using the formula: Calculate the proportion of abnormal data points p to evaluate the severity of anomalies in the data set, where |E| is the number of abnormal data points; According to the abnormal data point ratio, the formula is used: Calculate the anomaly identification index I and generate the device anomaly identification record, where β is the mitigation factor used to adjust the impact of non-abnormal data on the index, and w is the data importance weight used to adjust the impact of the abnormal proportion.

5. The equipment operation and maintenance management system based on IOT technology according to claim 4, Features: The calculation steps of the performance data difference value are as follows: Based on the device abnormality identification record, extract the timestamp and corresponding performance reading of each abnormal event and record it as D 异常 , output abnormal performance data set; Based on the abnormal performance data set, obtain 异常 The timestamp recorded in the D 标准 , generate a standard performance data set; Using the abnormal performance data set and the standard performance data set, the formula is adopted: Calculate the average performance difference value Generate performance difference data, where w i is the weight for each performance indicator, which is used to adjust the importance of the difference indicator, and M is the total number of data point records.

6. The equipment operation and maintenance management system based on IOT technology according to claim 5, Features: The steps for obtaining the equipment performance deviation analysis result are: The performance difference data is statistically analyzed using the formula: Calculate the standard deviation of the difference value σ ΔD , analyze the dispersion of the difference values ​​and obtain the statistical analysis results of the difference data, where M is the total number of data point records; According to the statistical analysis results of the difference data, the formula is used: Calculate the performance change rate R, evaluate the stability of the performance change, and output the performance change stability analysis results; According to the performance change stability analysis results, the performance trend of the equipment is judged, and the formula is used. Perform logical judgment and generate equipment performance deviation analysis results.

7. The equipment operation and maintenance management system based on IOT technology according to claim 6, Features: The steps for obtaining the equipment comprehensive operation and maintenance management plan are as follows: Based on the performance deviation analysis results and combined with the equipment maintenance records, the formula is used: Calculate the device health score H, where R i is the deviation score of the difference performance indicator, a i is the importance weight of the performance indicator, b is the maintenance history adjustment factor, which is set according to the equipment type and industry standards, c is the overall score adjustment factor, which is used to adjust the sensitivity of the health score, max(R) is the maximum value of the deviation score, Y is the number of maintenance times, Z is the equipment operation time, and m is the total number of deviation score data; According to the equipment health score, the maintenance time point is analyzed to determine the maintenance urgency, using the formula, Determine the maintenance time point T 维护 , where d represents the health score threshold, which is used to determine the maintenance urgency; According to the equipment health score, maintenance measures are formulated using the formula, Combined with the maintenance time point, the equipment operation and maintenance management plan is output, where e is the secondary threshold of the health score, which determines the type of maintenance.

8. A device operation and maintenance management method based on IOT technology, It is characterized in that According to any one of claims 1 to 7, the device operation and maintenance management system based on IOT technology is implemented, comprising the following steps: Collect the temperature, load and power readings of the device, create a data set corresponding to the timestamp and reading, calculate the weighted real-time average and peak value of the sensor data, combine the safety threshold, make status judgments, and output device operation snapshots; Extracting the timestamps of all continuous measurements from the device operation snapshot, calculating the time difference and arithmetic mean between two consecutive measurements, performing standard deviation calculation on the measurement data of all sensors, evaluating the consistency and fluctuation of the data, and generating a data deviation calculation result; Using the data deviation calculation results, identify abnormal data points, analyze the proportion of abnormal data points, evaluate the severity of abnormalities in the data set, calculate the abnormality identification index, and generate a device abnormality identification record; Based on the device abnormality identification record, extract the timestamp and corresponding performance reading of each abnormal event, synchronously obtain the device standard performance data matching the timestamp, calculate the average performance difference value, and output the performance difference data; Performing statistical analysis based on the performance difference data, analyzing the dispersion of the difference values, calculating the performance change rate and evaluating the stability of the performance change, determining the performance trend of the equipment, and generating equipment performance deviation analysis results; Based on the performance deviation analysis results, combined with equipment maintenance records, the equipment health score is calculated, the maintenance time point is analyzed to determine the maintenance urgency, maintenance measures are formulated, and the equipment operation and maintenance management plan is output.

Citation Information

Patent Citations

  • Equipment monitoring method and device based on Internet of Things, equipment and storage medium

    CN117111568A

  • Equipment health state monitoring system and method based on multi-source data

    CN117909670A

  • Intelligent operation and maintenance cloud platform for industrial equipment

    CN118154174A

  • Big data analysis method and system applied to substation inspection

    CN118467975A

  • Method, system and device for monitoring and analyzing running state of CIR equipment and medium

    CN118474772A

Cited By

  • Safety detection method for boiler flue gas waste heat recovery power system

    CN119223662A

  • Digital intelligent analysis system based on hydropower station physical equipment

    CN119885047A

  • Method, device and equipment for diagnosing running state of attention glasses

    CN120086773A

  • Operating State Diagnosis Method, Device and Equipment for Attention Glasses

    CN120086773B

  • Laboratory intelligent comprehensive management method

    CN121212880A