Bridge erection machine maintenance system based on cloud data

Abstract

The present invention relates to the technical field of maintenance systems, specifically to a bridge crane maintenance system based on cloud data, the system comprising: a data acquisition control module collects sensor data based on power components, performs timestamp marking, performs integrity and consistency checks on the collected data, verifies data quality, excludes abnormal or damaged data items, and generates a standardized data set. In the present invention, by dynamically adjusting the data sampling frequency and transmission rate, it effectively adapts to environmental changes and fluctuations in equipment load, ensures the real-time and accuracy of data transmission, reconfigures the spatial position of sensor nodes, and ensures that all key mechanical structural parts are monitored in real time by generating an optimal coverage map, which enhances the comprehensiveness and accuracy of monitoring, uses statistical models to conduct in-depth analysis of equipment operating conditions, predicts potential failures and expected life of key components, improves the preventive maintenance capabilities of equipment, effectively extends the service life of equipment, and reduces the occurrence rate of failures.

Description

Technical Field

[0001] The present invention relates to the technical field of maintenance systems, and in particular to a bridge erection machine maintenance system based on cloud data. Background Art

[0002] Maintenance systems cover a range of technologies and methods designed to ensure the long-term operation and performance optimization of equipment, machinery or infrastructure. These systems typically include functions such as preventive maintenance, fault diagnosis, repair and performance monitoring. Its core goal is to reduce equipment downtime and extend equipment life through effective resource management and predictive analysis, thereby reducing maintenance costs and improving production efficiency. Maintenance systems have a wide range of applications, covering multiple industries such as manufacturing, transportation, energy, and medical care to ensure the reliable operation and safety of critical equipment and infrastructure.

[0003] Among them, the cloud-based bridge crane maintenance system uses the cloud computing platform to store and process large-scale data to achieve real-time monitoring and data analysis of bridge crane equipment. Bridge cranes play a key role in building and infrastructure construction, so the stability of their operating status and maintenance efficiency directly affect project progress and cost control. Through cloud data technology, the maintenance system can collect, store and analyze large-scale equipment data, thereby remotely monitoring the operating status of the equipment and predicting possible failures or parts that need maintenance. Maintenance personnel can respond quickly based on real-time data, perform precise maintenance and management, and improve equipment operating efficiency and the safety and reliability of the overall project.

[0004] Existing technologies often fail to flexibly respond to changes in the environment and equipment loads and adopt fixed data processing strategies, resulting in data processing that is not real-time or accurate enough, affecting maintenance efficiency and equipment performance. Traditional monitoring systems lack adjustability in sensor layout and cannot ensure that key components are always within the monitoring range, which easily leads to monitoring blind spots. In this case, mechanical failures may be missed and equipment status may be misjudged, thus affecting equipment reliability and operational safety. For example, if key power components are not effectively monitored, once a failure occurs, it may quickly affect overall equipment performance, increase the need for emergency repairs, increase maintenance costs, and cause unnecessary equipment downtime. These defects show that existing technologies have obvious deficiencies in operational efficiency and system safety, which need to be addressed by introducing innovative measures. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a bridge erection machine maintenance system based on cloud data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: The bridge erection machine maintenance system based on cloud data includes:

[0007] The data acquisition control module collects sensor data from the power components, performs time stamping, performs integrity and consistency checks on the collected data, verifies data quality, excludes abnormal or damaged data items, and generates a standardized data set;

[0008] The environment matching adjustment module analyzes the feedback data of the control interface based on the standardized data set, adjusts the data sampling frequency according to the real-time feedback, optimizes the data transmission rate to match the environmental changes and equipment load conditions, integrates the environmental data and operation feedback, and formulates an adjusted transmission strategy;

[0009] The layout optimization decision module re-evaluates and configures the spatial position of the sensor nodes based on the adjusted transmission strategy, verifies whether the key mechanical structure parts are within the monitoring range, optimizes the spatial distribution of the sensors, and generates an optimal coverage map;

[0010] The life prediction and failure analysis module analyzes the operating status of the equipment based on the optimal coverage map and real-time data of the monitoring interface, applies statistical models to predict potential failures and expected life of key components, refines data features, updates equipment status assessment according to real-time monitoring data, and generates equipment health results.

[0011] As a further solution of the present invention, the step of acquiring the standardized data set is specifically:

[0012] Collect data from the sensors of the power components, record the timestamp of each data point, and use the formula:

[0013] T i =t0+i·Δt+α·sin(i·ω)

[0014] Calculate and generate raw data sets with timestamps;

[0015] Among them, T i is the timestamp of the i-th data point, t0 is the initial acquisition time, Δt is the time interval between two consecutive data points, i is the index of the data point, α is the adjustment coefficient, and ω is the angular frequency;

[0016] The integrity and consistency check of the original data set with timestamp is performed using the formula:

[0017]

[0018] To ensure the consistency of data time intervals and obtain a consistency verification data set;

[0019] Where ΔC represents the standard deviation of the timestamp interval, and n is the total number of data points;

[0020] Abnormal or damaged data items are screened out from the consistency verification data set using the formula:

[0021]

[0022] After screening, the cleaned data set is obtained;

[0023] Among them, D i is the filtered data set, ΔC i is the timestamp deviation of the ith data point, ∈ is the maximum allowed deviation, and x i is the original data point, sign(x) represents the sign function of x;

[0024] The cleaned data set is standardized using the formula:

[0025]

[0026] Generate standardized datasets;

[0027] Among them, S i is the normalized data point, x i is the original data point, μ x is the mean value, σ x is the standard deviation and γ is the adjustment coefficient.

[0028] As a further solution of the present invention, the step of acquiring the data sampling frequency is specifically as follows:

[0029] The feedback data of the control interface is extracted from the standardized data set using the formula:

[0030]

[0031] Calculate and obtain a weighted feedback value;

[0032] Where R is the weighted feedback value, f i is the weight factor of the corresponding data point, and n is the total number of data points;

[0033] According to the weighted feedback value, the sampling frequency of the data is adjusted using the formula:

[0034]

[0035] Match data changes to get a new sampling frequency;

[0036] Among them, F is the adjusted sampling frequency, α, β, γ, κ are the coefficients of the adjustment frequency;

[0037] Based on the new sampling frequency, comprehensive reference equipment load and environmental factors, the formula is adopted:

[0038] F ′=F·(1+δ·log(1+L))

[0039] Calculate the data sampling frequency;

[0040] Among them, F ′ is the data sampling frequency, δ is the environmental sensitivity coefficient, and L is the equipment load value.

[0041] As a further solution of the present invention, the step of acquiring the adjusted transmission strategy is specifically:

[0042] According to the data sampling frequency, the data transmission rate is optimized to match the environmental changes and equipment load conditions, using the formula:

[0043]

[0044] Calculate the current data transmission rate;

[0045] Among them,T is the optimized data transmission rate, θ,∈,σ,are the parameters for adjusting the data transmission rate, and L is the current load of the device;

[0046] Integrate environmental data and operational feedback, using the formula:

[0047]

[0048] calculating an adjusted transmission strategy;

[0049] Among them, P is the adjusted transmission strategy, λ and μ are parameters that integrate environmental data and operation feedback, and E represents the measure of environmental changes.

[0050] As a further solution of the present invention, the step of obtaining the optimal coverage map is specifically as follows:

[0051] Based on the adjusted transmission strategy, the spatial position of the sensor nodes is re-evaluated and configured using the formula:

[0052]

[0053] Calculate and generate spatial influence distribution;

[0054] Where D is the sum of the node spatial influence, P i is the node’s policy weight, A i is the spatial region controlled by the node, r i is the monitoring radius of the node, κ is the adjustment parameter of spatial attenuation, and the denominator r in the formula i 2 represents the adjustment of the influence by the square of the distance;

[0055] Use the spatial influence distribution to verify whether the key mechanical structure parts are within the monitoring range, using the formula:

[0056]

[0057] Generate maximum coverage area;

[0058] Where C is the estimated value of the maximum coverage area, D j is the influence of the key structure selected from D, J is the index set of the key structure, σ, V j is the adjustment coefficient of monitoring effect and structural complexity;

[0059] The maximum coverage area is used to optimize the spatial distribution of sensors using the formula:

[0060]

[0061] Calculate and generate optimal coverage map;

[0062] Among them, G is the evaluation result of the optimal coverage map, D i is the influence of each sensor calculated from D, T k is the target coverage value of each solution, K is the set of configuration solutions, and λ is the adjustment coefficient of target matching.

[0063] As a further solution of the present invention, the steps of obtaining the device health result are specifically as follows:

[0064] Based on the optimal coverage map and the real-time data of the monitoring interface, the operating status of the equipment is analyzed using the formula:

[0065]

[0066] The coverage quality and real-time data quality of each monitoring point are evaluated by weighted average of the attenuation coefficient to generate equipment health indicators;

[0067] Among them, H is the average value of the equipment health index, G i represents the coverage quality of the ith monitoring point, R i is the quality score of real-time data, α, β i is the attenuation coefficient.

[0068] Using the equipment health indicators, a statistical model is applied to predict the potential failure and life expectancy of key components using the formula:

[0069]

[0070] Using the overall health of the equipment as the denominator, potential failures are predicted through the exponential decay of the risk factor and loading history of each component to generate failure predictions for key components;

[0071] Among them, Z is the fault prediction result, λ j is the risk factor of the jth component, γ is the attenuation constant, L j is the loading history of the component;

[0072] Using the failure prediction results of the key components, the data features are refined, and the equipment status assessment is updated according to the real-time monitoring data, using the formula:

[0073]

[0074] According to the difference between the fault prediction result and the target health state, the weight factor is used to reflect the current health state of each component and generate the equipment health result;

[0075] Among them, U is the equipment health result, Z j is the failure prediction value of each component, T j is the target health state of the component, ω j is the weight factor.

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

[0077] In the present invention, by dynamically adjusting the data sampling frequency and transmission rate, the environmental changes and fluctuations of the equipment load are effectively adapted to ensure the real-time and accuracy of data transmission. The spatial position of the sensor nodes is reconfigured, and the optimal coverage map is generated to ensure that all key mechanical structure parts are monitored in real time, which enhances the comprehensiveness and accuracy of monitoring. The statistical model is used to conduct in-depth analysis of the equipment operation status, predict the potential failures and expected life of key components, improve the preventive maintenance capability of the equipment, effectively extend the service life of the equipment, and reduce the failure rate. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0079] Figure 2 A flow chart of the steps for obtaining a standardized data set of the present invention;

[0080] Figure 3 A flow chart of the steps for obtaining the data sampling frequency of the present invention;

[0081] Figure 4 A flow chart of the steps for obtaining the transmission strategy adjusted by the present invention;

[0082] Figure 5A flow chart of the steps for obtaining the optimal coverage map of the present invention;

[0083] Figure 6 The figure is a flow chart of the steps for obtaining the health results of the device of the present invention. DETAILED DESCRIPTION

[0084] 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.

[0085] 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.

[0086] Embodiment 1

[0087] See also Figure 1 The cloud-based bridge crane maintenance system includes:

[0088] The data acquisition control module collects sensor data from the power components, performs time stamping, performs integrity and consistency checks on the collected data, verifies data quality, excludes abnormal or damaged data items, and generates a standardized data set;

[0089] The environment matching adjustment module analyzes the feedback data of the control interface based on the standardized data set, adjusts the data sampling frequency according to the real-time feedback, optimizes the data transmission rate to match the environmental changes and equipment load conditions, integrates the environmental data and operation feedback, and formulates the adjusted transmission strategy;

[0090] The layout optimization decision module re-evaluates and configures the spatial position of sensor nodes based on the adjusted transmission strategy, verifies whether key mechanical structure parts are within the monitoring range, optimizes the spatial distribution of sensors, and generates the optimal coverage map;

[0091] The life prediction and failure analysis module analyzes the operating status of the equipment based on the optimal coverage map and real-time data of the monitoring interface, applies statistical models to predict the potential failures and expected life of key components, refines data features, updates the equipment status assessment according to real-time monitoring data, and generates equipment health results.

[0092] The adjusted transmission strategy specifically includes sampling frequency setting, transmission rate adjustment, environmental adaptability, and load responsiveness. The optimal coverage map specifically includes spatial configuration efficiency, monitoring coverage, and key monitoring point positioning. The equipment health results include fault warning indicators, life estimation values, and status assessment reports.

[0093] See also Figure 2 , the specific steps for obtaining the standardized data set are:

[0094] Collect data from the sensors of the power components, record the timestamp of each data point, and use the formula:

[0095] T i =t0+i·Δt+α·sin(i·ω)

[0096] Calculate and generate raw data sets with timestamps;

[0097] Among them, T i is the timestamp of the i-th data point, t0 is the initial acquisition time, Δt is the time interval between two consecutive data points, i is the index of the data point, α is the adjustment coefficient, and ω is the angular frequency;

[0098] The integrity and consistency check of the original data set with timestamp is performed using the formula:

[0099]

[0100] To ensure the consistency of data time intervals and obtain a consistency verification data set;

[0101] Where ΔC represents the standard deviation of the timestamp interval, and n is the total number of data points;

[0102] To filter out abnormal or corrupted data items from the consistency verification data set, use the formula:

[0103]

[0104] After screening, the cleaned data set is obtained;

[0105] Among them, D i is the filtered data set, ΔC i is the timestamp deviation of the ith data point, ∈ is the maximum allowed deviation, and x i is the original data point, sign(x) represents the sign function of x;

[0106] The cleaned data set is standardized using the formula:

[0107]

[0108] Generate standardized datasets;

[0109] Among them, S i is the normalized data point, x i is the original data point, μ x is the mean value, σ x is the standard deviation and γ is the adjustment coefficient.

[0110] Step 1: Timestamp calculation

[0111] formula:

[0112] T i =t0+i·Δt+α·sin(i·ω)

[0113] Parameter details:

[0114] T i : The timestamp of the ith data point.

[0115] t0: Initial acquisition time, assumed to be 0 seconds.

[0116] Δt: The time interval between two consecutive data points, assumed to be 1 second.

[0117] i: The index of the data point, starting from 1.

[0118] α: adjustment coefficient, indicating the amplitude of the sine wave, assumed to be 0.1 second.

[0119] ω: angular frequency, assumed to be π (period is 2 data points).

[0120] Example derivation:

[0121] Assume i = 1,

[0122] T1=0+1·1+0.1·sin(1·π)=0+1+0=1 second

[0123] Note: The timestamp of the first data point is 1 second.

[0124] Step 2: Consistency Verification

[0125] formula:

[0126]

[0127] Parameter details:

[0128] △C: Standard deviation of timestamp intervals.

[0129] T i : The timestamp of the ith data point obtained from step 1.

[0130] n: The total number of data points, assumed to be 3.

[0131] Δt: The time interval from step 1 is 1 second.

[0132] Example derivation:

[0133] T2=0+2·1+0.1·sin(2·π)=0+2+0=2 seconds

[0134]

[0135] Note: The timestamp consistency of the data points is perfect and there is no deviation.

[0136] Step 3: Data screening

[0137] formula:

[0138]

[0139] Parameter details:

[0140] D i : The filtered dataset.

[0141] ΔC i : Deviation from step 2.

[0142] ∈: Maximum allowable deviation, assumed to be 0.05 seconds.

[0143] x i : The value of the original data point, assuming x1=10.

[0144] Δt: time interval 1 second.

[0145] Example derivation:

[0146]

[0147] Explanation: The first data point is considered an anomaly because its deviation is less than the threshold.

[0148] Step 4: Data Standardization

[0149] formula:

[0150]

[0151] Parameter details:

[0152] S i : The data points after normalization.

[0153] x i : The value of the original data point.

[0154] μ x : The mean of the data set, assumed to be 10.

[0155] σ x : The standard deviation of the data set, assumed to be 2.

[0156] γ: adjustment factor, assumed to be 1 (no adjustment).

[0157] Example derivation:

[0158]

[0159] Note: The deviation of the first data point during normalization is 0, which means that the data point is at the average level.

[0160] See also Figure 3 , the steps for obtaining the data sampling frequency are as follows:

[0161] Extract the feedback data of the control interface from the standardized data set using the formula:

[0162]

[0163] Calculate and obtain a weighted feedback value;

[0164] Where R is the weighted feedback value, f i is the weight factor of the corresponding data point, and n is the total number of data points;

[0165] According to the weighted feedback value, the sampling frequency of the data is adjusted using the formula:

[0166]

[0167] Match data changes to get a new sampling frequency;

[0168] Among them, F is the adjusted sampling frequency, α, β, γ, κ are the coefficients of the adjustment frequency;

[0169] Based on the new sampling frequency, comprehensive reference equipment load and environmental factors, the formula is used:

[0170] F ′ =F·(1+δ·log(1+L))

[0171] Calculate the data sampling frequency;

[0172] Among them, F ′ is the data sampling frequency, δ is the environmental sensitivity coefficient, and L is the equipment load value.

[0173] Derivation of the formula for step 1

[0174] formula:

[0175]

[0176] Parameter Description:

[0177] R: Weighted feedback value, which indicates the average weighted value of the control interface feedback data.

[0178] S i : The value of the i-th data point, obtained from the standardized data set.

[0179] f i : The weight factor of the i-th data point, which is used to reflect the importance of the data point.

[0180] n: The total number of data points.

[0181] Calculation process:

[0182] Assume that there are 5 data points S = [2, 3, 5, 7, 11], and the weight of each point is f = [0.2, 0.3, 0.1, 0.3, 0.1], then the weighted feedback value is calculated as:

[0183] Calculate the weighted value for each data point:

[0184] 2×0.2=0.4

[0185] 3×0.3=0.9

[0186] 5×0.1=0.5

[0187] 7×0.3=2.1

[0188] 11×0.1=1.1

[0189] Add up all weighted values:

[0190] 0.4+0.9+0.5+2.1+1.1=5.0

[0191] Calculate the average:

[0192]

[0193] Derivation of the formula for step 2

[0194] formula:

[0195]

[0196] Parameter Description:

[0197] F: adjusted sampling frequency.

[0198] α, β, γ, κ: adjustment coefficients used to control frequency flexibility and responsiveness.

[0199] R: Weighted feedback value obtained from step 1.

[0200] Calculation process:

[0201] Using the previously obtained R = 1.0 and the assumed parameters α = 2.0, β = 1.0, γ = 1.5, κ = 0.5: Calculate the first part of the sampling frequency:

[0202]

[0203] The second part of calculating the sampling frequency:

[0204]

[0205] Final sampling frequency:

[0206] F=1.463+1.837=3.3

[0207] Derivation of the formula for step 3

[0208] formula:

[0209] F ′ =F·(1+δ·log(1+L))

[0210] Parameter Description:

[0211] F ′ : Data sampling frequency.

[0212] δ: Sensitivity coefficient to environmental changes.

[0213] L: Current load of the device.

[0214] Calculation process:

[0215] Assume δ = 0.05 and equipment load L = 10:

[0216] Calculate the adjustment factor:

[0217] log(1+10)≈2.3979

[0218] 1+0.05·2.3979≈1.12

[0219] Final sampling frequency:

[0220] F ′ =3.3·1.12≈3.696

[0221] These parameter settings and calculation processes are reasonably set according to actual conditions to ensure the practical rationality of the examples.

[0222] See also Figure 4 , the specific steps for obtaining the adjusted transmission strategy are:

[0223] According to the data sampling frequency, the data transmission rate is optimized to match the environmental changes and equipment load conditions, using the formula:

[0224]

[0225] Calculate the current data transmission rate;

[0226] Among them,T is the optimized data transmission rate, θ,∈,σ,are the parameters for adjusting the data transmission rate, and L is the current load of the device;

[0227] Integrate environmental data and operational feedback, using the formula:

[0228]

[0229] calculating an adjusted transmission strategy;

[0230] Among them, P is the adjusted transmission strategy, λ and μ are parameters that integrate environmental data and operation feedback, and E represents the measure of environmental changes.

[0231] Detailed explanation and example of step 1 formula

[0232] formula:

[0233]

[0234] Parameter explanation:

[0235] F ′ : Data sampling frequency, assumed to be 100Hz

[0236] θ: rate adjustment factor, assumed to be 0.8

[0237] ∈: environmental adjustment constant, assumed to be 1

[0238] L: Equipment load, assumed to be 50%

[0239] σ: Load influence coefficient, assumed to be 0.02

[0240] Calculation process:

[0241] Calculate L+∈: 50+1=51

[0242] Calculate the square root part:

[0243] Calculate the numerator:

[0244] Calculate the square root part:

[0245] Calculate the numerator:

[0246] Calculate the denominator: 1+σ·L=1+0.02·50=2

[0247] Compute the entire fraction:

[0248] Calculate the final transmission rate T: 100·2.855=285.5Hz

[0249] Explanation of the example results:

[0250] The final transmission rate T is 285.5 Hz, indicating that under the current device load and environmental factors, the data transmission rate should be adjusted to this value to optimize performance.

[0251] Detailed explanation and example of step 2 formula

[0252] formula:

[0253]

[0254] Parameter explanation:

[0255] T: Result from step 1, 285.5Hz

[0256] λ: Environmental integration coefficient, assumed to be 0.5

[0257] μ: Environmental response sensitivity, assumed to be 0.05

[0258] E: Environmental change index, assumed to be 10

[0259] Calculation process:

[0260] Calculate e -μ·E :e -0.05·10 =e -0.5 ≈0.606

[0261] Calculate the denominator: λ·0.606+1=0.5·0.606+1≈1.303

[0262] Calculate the transmission strategy P:

[0263] Explanation of the example results:

[0264] The adjusted transmission strategy P is 219.11, which means that after considering environmental factors, the transmission strategy should be adjusted to this value to maintain system efficiency.

[0265] See also Figure 5 , the steps to obtain the optimal coverage map are as follows:

[0266] Based on the adjusted transmission strategy, the spatial position of the sensor nodes is re-evaluated and configured using the formula:

[0267]

[0268] Calculate and generate spatial influence distribution;

[0269] Where D is the sum of the node spatial influence, P i is the node’s policy weight, A i is the spatial region controlled by the node, r i is the monitoring radius of the node, κ is the adjustment parameter of spatial attenuation, and the denominator r in the formula i 2 represents the adjustment of the influence by the square of the distance;

[0270] Use the spatial influence distribution to verify whether the key mechanical structure parts are within the monitoring range, using the formula:

[0271]

[0272] Generate maximum coverage area;

[0273] Where C is the estimated value of the maximum coverage area, D j is the influence of the key structure selected from D, J is the index set of the key structure, σ, V j is the adjustment coefficient of monitoring effect and structural complexity;

[0274] The spatial distribution of sensors is optimized using the maximum coverage area, using the formula:

[0275]

[0276] Calculate and generate optimal coverage map;

[0277] Among them, G is the evaluation result of the optimal coverage map, D i is the influence of each sensor calculated from D, T k is the target coverage value of each solution, K is the set of configuration solutions, and λ is the adjustment coefficient of target matching.

[0278] Step 1: Calculation of spatial influence

[0279] formula:

[0280]

[0281] P i : The strategic importance weight of the i-th node, assumed value: P i =5 (assuming high importance)

[0282] A i : The spatial area controlled by the i-th node, assumed value: A i =100m 2

[0283] r i : The monitoring radius of the ith node, assumed value: r i =50m

[0284] κ: spatial attenuation coefficient, assumed value: κ = 0.01

[0285] Calculation process:

[0286] Calculation of influence on a single node:

[0287] 100 1.5 =1000,50 2 =2500, 0.01 2500 = 25

[0288]

[0289] For simplified calculation, if there are 3 such nodes, the total influence D = 3 × 192.31 = 576.92 Example result explanation:

[0290] D = 576.92 represents the total influence of the three important nodes under given space and attenuation conditions.

[0291] Step 2: Maximum coverage area calculation

[0292] formula:

[0293]

[0294] D j : The influence selected from step 1, assumed to be 192.31

[0295] σ: Monitoring effect adjustment coefficient, assumed value: σ=0.05

[0296] V j : Visualization complexity of the structure, assumed value: V j =10

[0297] Calculation process:

[0298] Coverage evaluation for a single key structure: Explanation of the example results:

[0299] C=128.21 represents the maximum coverage evaluation value of the key structure under the current configuration.

[0300] Step 3: Optimal coverage map generation

[0301] formula:

[0302]

[0303] D i : The influence of the previous step, assumed to be 192.31

[0304] T k : Target coverage value, assuming: T k =150

[0305] λ: target matching coefficient, assuming: λ = 0.1

[0306] Calculation process:

[0307] For optimization calculations of a single configuration:

[0308] 1+0.1·150=16

[0309]

[0310] Example results and explanation:

[0311] G = 2.64 represents the minimum average deviation from the target coverage value under the optimal configuration.

[0312] See also Figure 6 , the specific steps for obtaining device health results are:

[0313] Based on the optimal coverage map and real-time data from the monitoring interface, analyze the operating status of the equipment using the formula:

[0314]

[0315] The coverage quality and real-time data quality of each monitoring point are evaluated by weighted average of the attenuation coefficient to generate equipment health indicators;

[0316] Among them, H is the average value of the equipment health index, G i represents the coverage quality of the ith monitoring point, R i is the quality score of real-time data, α, β i is the attenuation coefficient.

[0317] Using equipment health indicators, statistical models are applied to predict potential failures and life expectancy of key components using the formula:

[0318]

[0319] Using the overall health of the equipment as the denominator, potential failures are predicted through the exponential decay of the risk factor and loading history of each component to generate failure predictions for key components;

[0320] Among them, Z is the fault prediction result, λ jis the risk factor of the jth component, γ is the attenuation constant, L j is the loading history of the component;

[0321] Use the failure prediction results of key components to extract data features and update the equipment status assessment based on real-time monitoring data using the formula:

[0322]

[0323] According to the difference between the fault prediction result and the target health state, the weight factor is used to reflect the current health state of each component and generate the equipment health result;

[0324] Among them, U is the equipment health result, Z j is the failure prediction value of each component, T j is the target health state of the component, ω j is the weight factor.

[0325] Formula analysis and derivation process of step 1:

[0326] formula:

[0327]

[0328] Parameter explanation:

[0329] G i : The coverage quality of the ith monitoring point, assumed to be a random value in the range of 0.5 to 1. R i : Quality score of real-time data, assumed to be a random value in the range of 0 to 1.

[0330] α: global attenuation coefficient, assumed to be 0.05.

[0331] β i : The local attenuation coefficient for each monitoring point, assumed to be a random value in the range of 1 to 2. n: The total number of monitoring points, assumed to be 10.

[0332] Assume a numerical example:

[0333] G=[0.8,0.9,0.85,0.95,0.75,0.8,0.9,0.85,0.95,0.75]

[0334] R=[0.9,0.85,0.8,0.75,0.9,0.85,0.8,0.75,0.9,0.85]

[0335] β=[1.5,1.2,1.8,1.4,1.6,1.5,1.2,1.8,1.4,1.6]

[0336] Calculation process:

[0337]

[0338] After calculating each item, sum it up and then divide it by 10 to get the average health index H.

[0339] Formula analysis and derivation process of step 2:

[0340] formula:

[0341]

[0342] Parameter explanation:

[0343] λ j : The risk coefficient of the jth component is assumed to be a random value in the range of 0.1 to 0.5.

[0344] γ: decay constant, assumed to be 0.03.

[0345] L j : The loading history of the component, assumed to be random values ​​in the range of 100 to 500 hours.

[0346] m: The total number of parts, assumed to be 5.

[0347] Assume a numerical example:

[0348] λ=[0.3,0.2,0.4,0.1,0.5]

[0349] L = [120,350,200,500,450]

[0350] Calculation process:

[0351] Assume that H = 0.75 is obtained from step 1,

[0352]

[0353] After calculating each item and summing them up, we get the fault prediction Z.

[0354] Formula analysis and derivation process of step 3:

[0355] formula:

[0356]

[0357] Parameter explanation:

[0358] Z j : Component failure prediction value obtained from step 2.

[0359] T j : The target health state of the component, assumed to be a random value in the range of 0 to 1.

[0360] ω j : Weight factor, assuming 1 means all components are equally important.

[0361] m: The total number of parts, assumed to be 5.

[0362] Assume a numerical example:

[0363] T = [0.8, 0.7, 0.6, 0.9, 0.85]

[0364] Assume that Z = [0.75, 0.65, 0.55, 0.80, 0.70] obtained from step 2

[0365] Calculation process:

[0366]

[0367] After calculating each item, sum it up and then divide it by 5 to get the final health result U of the device.

[0368] 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. The bridge erection machine maintenance system based on cloud data is characterized by: The system comprises: The data acquisition control module collects sensor data from the power components, performs time stamping, performs integrity and consistency checks on the collected data, verifies data quality, excludes abnormal or damaged data items, and generates a standardized data set; The environment matching adjustment module analyzes the feedback data of the control interface based on the standardized data set, adjusts the data sampling frequency according to the real-time feedback, optimizes the data transmission rate to match the environmental changes and equipment load conditions, integrates the environmental data and operation feedback, and formulates an adjusted transmission strategy; The layout optimization decision module re-evaluates and configures the spatial position of the sensor nodes based on the adjusted transmission strategy, verifies whether the key mechanical structure parts are within the monitoring range, optimizes the spatial distribution of the sensors, and generates an optimal coverage map; The life prediction and failure analysis module analyzes the operating status of the equipment based on the optimal coverage map and the real-time data of the monitoring interface, applies statistical models to predict the potential failures and expected life of key components, extracts data features, updates the equipment status assessment according to the real-time monitoring data, and generates equipment health results; The steps for obtaining the adjusted transmission strategy are specifically as follows: According to the data sampling frequency, the data transmission rate is optimized to match the environmental changes and equipment load conditions, using the formula: Calculate the current data transmission rate; in, is the optimized data transfer rate, is the parameter for adjusting the data transmission rate, is the current load of the device; Integrate environmental data and operational feedback, using the formula: calculating an adjusted transmission strategy; in, is the adjusted transmission strategy, is a parameter that integrates environmental data and operational feedback. A measure of environmental change; The steps for obtaining the optimal coverage map are specifically as follows: Based on the adjusted transmission strategy, the spatial position of the sensor nodes is re-evaluated and configured using the formula: Calculate and generate spatial influence distribution; in, is the sum of the spatial influence of the nodes, is the node’s policy weight, is the spatial region controlled by the node, is the monitoring radius of the node, is the adjustment parameter of spatial attenuation. The denominator in the formula represents the adjustment of the influence by the square of the distance; Use the spatial influence distribution to verify whether the key mechanical structure parts are within the monitoring range, using the formula: Generate maximum coverage area; in, is the estimated value of the maximum coverage area, is from The influence of the key structures selected in is a collection of indexes of key structures, , is the adjustment coefficient of monitoring effect and structural complexity; The maximum coverage area is used to optimize the spatial distribution of sensors using the formula: Calculate and generate optimal coverage map; in, is the evaluation result of the optimal coverage map, is from The influence of each sensor calculated in is the target coverage value of each solution, is a collection of configuration schemes. is the adjustment factor for target matching; The steps for obtaining the device health results are specifically as follows: Based on the optimal coverage map and the real-time data of the monitoring interface, the operating status of the equipment is analyzed using the formula: The coverage quality and real-time data quality of each monitoring point are evaluated by weighted average of the attenuation coefficient to generate equipment health indicators; in, is the average value of the device health indicator, Indicates The coverage quality of each monitoring point, is the quality score of the real-time data, , is the attenuation coefficient; Using the equipment health indicators, a statistical model is applied to predict the potential failure and life expectancy of key components using the formula: Using the overall health of the equipment as the denominator, potential failures are predicted through the exponential decay of the risk factor and loading history of each component to generate failure predictions for key components; in, is the fault prediction result, It is The risk factor of each component, is the decay constant, is the loading history of the component; Using the failure prediction results of the key components, the data features are refined, and the equipment status assessment is updated according to the real-time monitoring data, using the formula: According to the difference between the fault prediction result and the target health state, the weight factor is used to reflect the current health state of each component and generate the equipment health result; in, is the device health result, is the failure prediction value of each component, is the target health state of the component, is the weight factor.

2. The cloud data-based bridge erection machine maintenance system according to claim 1 is characterized in that: The steps for obtaining the standardized data set are specifically as follows: Collect data from the sensors of the power components, record the timestamp of each data point, and use the formula: Calculate and generate raw data sets with timestamps; in, It is The timestamp of each data point, is the initial acquisition time, is the time interval between two consecutive data points, is the index of the data point, is the adjustment coefficient, is the angular frequency; The integrity and consistency check of the original data set with timestamp is performed using the formula: To ensure the consistency of data time intervals and obtain a consistency verification data set; in, represents the standard deviation of the timestamp interval, is the total number of data points; Abnormal or damaged data items are screened out from the consistency verification data set using the formula: After screening, the cleaned data set is obtained; in, is the filtered data set, It is The timestamp deviation of data points, is the maximum permissible deviation, is the original data point, express The symbolic function of The cleaned data set is standardized using the formula: Generate standardized datasets; in, is the normalized data point, is the original data point, is the average value, is the standard deviation, is the adjustment factor.

3. The cloud data-based bridge erection machine maintenance system according to claim 2 is characterized in that: The steps for obtaining the data sampling frequency are specifically as follows: The feedback data of the control interface is extracted from the standardized data set using the formula: Calculate and obtain a weighted feedback value; in, is the weighted feedback value, is the weight factor for the corresponding data point, is the total number of data points; According to the weighted feedback value, the sampling frequency of the data is adjusted using the formula: Match data changes to get a new sampling frequency; in, is the adjusted sampling frequency, is the coefficient for adjusting the frequency; Based on the new sampling frequency, comprehensive reference equipment load and environmental factors, the formula is adopted: Calculate the data sampling frequency; in, is the data sampling frequency, is the environmental sensitivity coefficient, is the device load value.

Images