An automatic diagnosis system for operating failures of packaging buckle machines
By collecting and analyzing temperature, pressure, speed and vibration data on the packaging and buckle machine, combining historical maintenance records and usage frequency, identifying fault points and optimizing maintenance plans, the problem of difficult to identify complex faults in traditional systems is solved and the fault response speed is improved and maintenance efficiency reduce maintenance costs.
Patent Information
- Application Number
- CN202410982023.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-22
AI Technical Summary
The fault diagnosis system for running traditional packaging machine is difficult to identify complex or initial faults, and lacks in-depth analysis of historical maintenance data, resulting in fault analysis relying on empirical judgment, reducing maintenance efficiency and increasing maintenance costs.
The data acquisition module is used to collect temperature, pressure, speed and vibration data through sensors, perform time stamp marking and data screening, and the feature analysis and prediction module calculates the temperature change rate and pressure difference values, performs pattern matching and fault simulation tests, and combines historical maintenance records and Use frequency analysis to identify failure points and optimize maintenance plans.
It realizes early abnormality detection, accurately identify fault types, reduce unnecessary maintenance work, optimizes the targetedness and effectiveness of maintenance activities, reduces equipment downtime, and improves production efficiency and equipment stability.
Smart Images

Figure CN118503769B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of fault diagnosis, and in particular to an automatic diagnosis system for operating faults of a packaging buckle-fastening machine. Background Art
[0002] The field of fault diagnosis technology focuses on discovering and identifying faults in mechanical, electronic or software systems. This technology is widely used, including industrial robots, production line equipment, automotive electronics and other automated manufacturing equipment. The purpose is to automatically detect abnormalities or signs of failure by monitoring the operating status and performance of the equipment. It usually involves data acquisition, signal analysis, pattern recognition, and prediction and identification of fault types. It can not only reduce equipment downtime, but also prevent failures in advance and optimize maintenance plans, thereby significantly improving production efficiency and equipment reliability.
[0003] Among them, the automatic diagnosis system for operation faults of packaging and buckling machines is a system specially designed to monitor and diagnose various faults that occur during the operation of packaging and buckling machines. This system uses sensors to collect data during machine operation, such as speed, pressure, and temperature, and then processes the data through analysis software to identify abnormal patterns that cause machine failures. Its main purpose is to monitor the equipment status in real time, automatically detect and report faults, thereby helping the maintenance team to respond quickly, reduce machine downtime, and ensure efficient operation of the production line.
[0004] Traditional systems mostly rely on threshold judgments or simple rules, which make it difficult to identify complex or early fault conditions. This causes serious damage before the problem is clearly identified. The lack of systematic analysis of historical maintenance data and in-depth exploration of failure modes makes fault analysis mostly rely on experience judgment and lack of data-supported accurate diagnosis, which not only reduces maintenance efficiency, but also leads to repeated and ineffective maintenance work due to incorrect fault diagnosis, increasing maintenance costs and affecting the stable operation of the packaging buckle machine. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose an automatic diagnosis system for operating faults of a packaging buckle-fastening machine.
[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical scheme: an automatic diagnosis system for operating faults of a packaging buckle-fastening machine, the system comprising:
[0007] The data acquisition module is based on sensors to collect temperature, pressure, speed and vibration data of the packaging buckle machine, timestamp the data, and record the data changes of the equipment under the target operating conditions to obtain the operation data set;
[0008] The feature analysis and prediction module analyzes the operation abnormality of the equipment based on the operation data set by calculating the temperature change rate and the pressure difference value, performs pattern matching on the operation abnormality, extracts features matching the known fault patterns, and obtains a fault feature set;
[0009] The key fault diagnosis module compares the historical maintenance records of the packaging and buckling machine based on the fault feature set, analyzes the frequency and influencing factors of the fault, and combines the correlation of multiple types of parameters to perform fault simulation tests, determine the fault point of the packaging and buckling machine, and obtain the fault diagnosis confirmation result;
[0010] Based on the fault diagnosis confirmation result, the maintenance optimization module analyzes the usage frequency and maintenance history of the packaging buckle machine, determines the optimal maintenance activity, evaluates the expected maintenance cost and time, optimizes the maintenance cycle, and obtains a maintenance plan optimization log.
[0011] The present invention is improved in that the step of obtaining the operation data set is specifically as follows:
[0012] Based on sensors, the operating data of the packaging buckle machine is collected, including temperature, pressure, speed and vibration data. Each data point is timestamped and the formula is used:
[0013]
[0014] Generate timestamped sensor datasets ,in, and Respectively represent the time Temperature, pressure, velocity and vibration data, Represents the timestamp of data collection, is the weight factor, which is used to adjust the impact weight of sensor data;
[0015] Filter the data under the target operating conditions and use the decision function Identify data points Whether the conditions are met, the formula is:
[0016]
[0017] Get the operation data set that meets the conditions ,in, is a Boolean function, is the decision threshold, Sensor datasets labeled with timestamps;
[0018] Summarize the filtered data points using the formula:
[0019]
[0020] Get the operation data set ,in, is the number of data points after filtering, is the data point, The operation data set that meets the conditions.
[0021] The present invention is improved in that the steps for calculating the temperature change rate and the pressure difference value are specifically as follows:
[0022] Based on the operational data set, extract the temperature data sequence And the pressure data series , using the formula:
[0023]
[0024] and
[0025]
[0026] Calculate the adjusted temperature and pressure change sequence ,in, and Respectively represent The temperature and pressure at a given time point, and is the smoothing coefficient for temperature and pressure data, and is the influence coefficient of environmental noise on temperature and pressure measurement;
[0027] The obtained and Divide by the time interval , using the formula:
[0028]
[0029] and
[0030]
[0031] Get the temperature change rate and the rate of pressure change ,in, and It is The temperature and pressure change sequence at each time point, is the time interval between adjacent time points, is the total number of data points;
[0032] Analyze the temperature change rate and the rate of pressure change , using the formula:
[0033]
[0034] Aggregate into change indicators , used for exception pattern matching, where and are the rate of change of temperature and pressure, and is the weighting factor for the rate of change of temperature and pressure.
[0035] The present invention is improved in that the step of pattern matching for operation anomalies is specifically as follows:
[0036] Based on the operational anomaly, the fault mode threshold is compared using the formula:
[0037]
[0038] Determine whether to trigger a fault alarm and generate a fault identification signal ,in, is a change indicator, is the failure mode threshold, is the fault sensitivity adjustment factor, is the fault triggering threshold;
[0039] If the fault identification signal indicates an abnormality, then extract The matching fault mode description is obtained by querying the fault database using the formula:
[0040]
[0041] Get the matching failure mode ,in, is the matching sensitivity adjustment factor, is a change indicator, It is a failure mode database.
[0042] The present invention is improved in that the analysis steps of the fault occurrence frequency and influencing factors are specifically as follows:
[0043] Based on the fault feature set, the number of occurrences of each fault type is counted using the formula:
[0044]
[0045] Generates the number of occurrences of the fault type ,in, It is Class fault event count, is the impact weight of the fault type, is the total number of fault types;
[0046] According to the number of occurrences of the fault type, the frequency of each fault type is calculated using the formula:
[0047]
[0048] Get the adjusted fault frequency ,in, is the number of failures during the monitoring period, is the frequency adjustment constant, is the number of occurrences of the fault type;
[0049] According to the adjusted fault frequency, the correlation between the fault frequency and the equipment parameters is analyzed, and the formula is:
[0050]
[0051] Get the failure influencing factors ,in, is the adjusted fault frequency, is the operating parameter weight, is the data uncertainty factor.
[0052] The present invention is improved in that the steps of determining the fault point of the packaging buckle machine are specifically as follows:
[0053] Based on the influencing factors, a fault simulation test is performed using the formula:
[0054]
[0055] Get simulation test results ,in, and is the adjustment coefficient, is the equipment operating parameter, is the environmental impact parameter, It is the failure influencing factor;
[0056] According to the simulation test results, determine whether the fault matches the expectation, using the formula:
[0057]
[0058] Get fault matching results ,in, is the matching adjustment factor, is the expected failure mode, It is the result of simulation test.
[0059] The present invention is improved in that the steps for analyzing the usage frequency and maintenance history of the packaging buckle machine are specifically as follows:
[0060] Based on the fault diagnosis confirmation results, analyze the frequency of equipment use using the formula:
[0061]
[0062] Generate device usage frequency ,in, For the Number of hours of use recorded, is the equipment usage intensity coefficient;
[0063] Based on the frequency of use of the equipment, calculate the average maintenance cost using the formula:
[0064]
[0065] Generate average maintenance cost ,in, It is The cost of maintenance, It is with The weight factor of the secondary maintenance association.
[0066] The present invention is improved in that the steps of evaluating the expected maintenance cost and time are specifically as follows:
[0067] Based on the optimal maintenance activities, calculate the expected maintenance cost using the formula:
[0068]
[0069] Generate expected maintenance costs ,in, It is The cost of maintenance, It is The amount of resources required for maintenance. is the efficiency factor of the resource, is the risk adjustment factor;
[0070] Based on the expected maintenance costs, estimate the time required for maintenance using the formula:
[0071]
[0072] Calculate the total expected maintenance time ,in, It is The time unit required for maintenance. It is The amount of resources required for maintenance. It is the speed factor, which indicates the speed of resource investment.
[0073] Compared with the prior art, the advantages and positive effects of the present invention are:
[0074] In the present invention, by real-time analysis of temperature changes and pressure differences, tiny equipment changes can be effectively captured, and rapid detection of early abnormalities can be achieved, thereby preventing the fault from further expanding. Through pattern matching, the system can conduct an in-depth analysis of the abnormal state, directly compare it with the known fault mode, and accurately identify the fault type. This not only improves the fault response speed, but also reduces unnecessary maintenance work, optimizes the pertinence and effectiveness of maintenance activities, and combines historical maintenance data. The system ensures the accuracy of fault judgment through fault simulation testing, enabling the maintenance team to accurately deal with the problem instead of adopting conventional maintenance strategies, reducing equipment downtime and improving production efficiency and equipment stability. BRIEF DESCRIPTION OF THE DRAWINGS
[0075] Figure 1 The present invention proposes a module diagram of an automatic diagnosis system for operating faults of a packaging buckle machine;
[0076] Figure 2 The present invention proposes a flow chart for obtaining an operation data set in an automatic diagnosis system for operating faults of a packaging buckle fastening machine;
[0077] Figure 3 The present invention proposes a flow chart for calculating the temperature change rate and pressure difference value in the automatic diagnosis system of the running fault of the packaging buckle machine;
[0078] Figure 4 The present invention proposes a flow chart for pattern matching of operation anomalies in an automatic diagnosis system for operation failure of a packaging buckle machine;
[0079] Figure 5 The present invention proposes a flow chart for analyzing the frequency of faults and influencing factors in the automatic diagnosis system for the operation faults of a packaging buckle machine;
[0080] Figure 6 The present invention proposes a flow chart for determining the fault point of a packaging buckle machine in an automatic diagnosis system for operation faults of a packaging buckle machine;
[0081] Figure 7 The present invention proposes a flow chart for analyzing the usage frequency and maintenance history of a packaging buckle-fastening machine in an automatic diagnosis system for operating faults of the packaging buckle-fastening machine;
[0082] Figure 8 The present invention proposes a flow chart for evaluating the expected maintenance cost and time in an automatic diagnosis system for operating faults of a packaging buckle fastening machine. DETAILED DESCRIPTION
[0083] 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.
[0084] 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", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying 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, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example
[0085] See also Figure 1 The present invention provides a technical solution: an automatic diagnosis system for operating faults of a packaging buckle machine comprises:
[0086] The data acquisition module is based on sensors, which collects the temperature, pressure, speed and vibration data of the packaging buckle machine, timestamps the data, and records the data changes of the equipment under the target operating conditions to obtain the operation data set; the sensors include temperature sensors, pressure sensors, speed sensors and vibration sensors.
[0087] The feature analysis and prediction module is based on the operation data set. It calculates the temperature change rate and pressure difference value, analyzes the operation anomaly of the equipment, performs pattern matching on the operation anomaly, extracts features that match the known fault pattern, and obtains the fault feature set.
[0088] The key fault diagnosis module compares the historical maintenance records of the packaging and buckling machine based on the fault feature set, analyzes the frequency and influencing factors of the fault, and combines the correlation of multiple types of parameters to perform fault simulation tests, determine the fault point of the packaging and buckling machine, and obtain the fault diagnosis confirmation result;
[0089] Based on the fault diagnosis confirmation results, the maintenance optimization module analyzes the usage frequency and maintenance history of the packaging buckle machine, determines the optimal maintenance activities, evaluates the expected maintenance cost and time, optimizes the maintenance cycle, and obtains the maintenance plan optimization log.
[0090] The operation data set includes temperature log, pressure log, speed log, and vibration log. The fault feature set includes temperature anomaly identification, pressure anomaly identification, and pattern anomaly identification. The fault diagnosis confirmation result includes historical fault comparison information, a list of influencing factors, and confirmed fault locations. The maintenance plan optimization log includes the maintenance schedule, cost-benefit analysis results, and cycle adjustment information.
[0091] See also Figure 2 , the specific steps for obtaining the operation data set are:
[0092] Based on sensors, the operating data of the packaging buckle machine is collected, including temperature, pressure, speed and vibration data. Each data point is timestamped and the formula is used:
[0093]
[0094] Generate timestamped sensor datasets ,in, and Respectively represent the time Temperature, pressure, velocity and vibration data, Represents the timestamp of data collection, is the weight factor, which is used to adjust the impact weight of sensor data;
[0095] Filter the data under the target operating conditions and use the decision function Identify data points Whether the conditions are met, the formula is:
[0096]
[0097] Get the operation data set that meets the conditions ,in, is a Boolean function used to determine whether a data point satisfies the operating condition. is the decision threshold, Sensor datasets labeled with timestamps;
[0098] Summarize the filtered data points using the formula:
[0099]
[0100] Get the operation data set ,in, is the number of data points after filtering, is the data point, The operation data set that meets the conditions.
[0101] Assume the following data:
[0102] Assume that at a certain point in time , the measured temperature ,pressure Pa, speed m / s, vibration , timestamp (Unix timestamp, representing 00:00:00 on January 1, 2024), and set the weight factor .
[0103] Calculate the weighted result of the data points:
[0104]
[0105] The calculation results represent weighted temperature, pressure, velocity, vibration, and adjusted timestamps, and the data will be used in subsequent steps.
[0106] Assume the following data:
[0107] Hypothesis decision threshold , based on the data obtained in the previous step, assume that the judgment function Is the average value of the temperature and speed of the data point greater than the threshold? .
[0108]
[0109] Because 52>25, the data point meets the condition, indicating that the data point is valid under the operating conditions and will be included in the operating data set.
[0110] Assume the following data:
[0111] Assumptions There is only one data point mentioned above ,and (There is only one data point).
[0112]
[0113] The calculated results represent the entire operational data set, i.e., a representative data set of the packaging buckle machine under operating conditions.
[0114] See also Figure 3 , the calculation steps of temperature change rate and pressure difference value are as follows:
[0115] Extract temperature data series based on the operational data set And the pressure data series , using the formula:
[0116]
[0117] and
[0118]
[0119] Calculate the adjusted temperature and pressure change sequence ,in, and Respectively represent The temperature and pressure at a given time point, and is the smoothing coefficient for temperature and pressure data, and is the influence coefficient of environmental noise on temperature and pressure measurement;
[0120] Will get and Divide by the time interval , using the formula:
[0121]
[0122] and
[0123]
[0124] Get the temperature change rate and the rate of pressure change ,in, and It is The temperature and pressure change sequence at each time point, is the time interval between adjacent time points, is the total number of data points;
[0125] Analyze the rate of temperature change and the rate of pressure change , using the formula:
[0126]
[0127] Aggregate into change indicators , used for exception pattern matching, where and are the rate of change of temperature and pressure, and is the weighting factor for the rate of change of temperature and pressure.
[0128] Assume the following parameters:
[0129] and Set to 0.05, and Set to 0.01;
[0130] temperature ;
[0131] pressure bar bar.
[0132] Calculate the temperature and pressure changes at adjacent time points:
[0133]
[0134]
[0135] It shows that after considering environmental noise and data smoothing, the actual temperature change is 1.999℃ and the pressure change is 0.9995bar.
[0136] Assume the following parameters:
[0137] and The above is obtained;
[0138] Assume 1 hour;
[0139] is the total number of data points, assuming there are 10 time points.
[0140] Assume that all temperature changes and pressure changes are similar to the results of the above steps:
[0141]
[0142]
[0143] It means that the average hourly temperature change rate is 1.999°C and the pressure change rate is 0.9995bar.
[0144] Assume the following parameters:
[0145] and Obtained from the above;
[0146] and Assume 0.6 and 0.4.
[0147] calculate:
[0148]
[0149]
[0150]
[0151]
[0152] The value of the comprehensive change index is 1.673, which takes into account the change rates of temperature and pressure and adjusts their respective influences through weight factors, and is used to evaluate whether the operating status of the equipment is abnormal.
[0153] See also Figure 4 , the specific steps for pattern matching of operation exceptions are:
[0154] According to the operation anomaly, it is compared with the failure mode threshold and the formula is used:
[0155]
[0156] Determine whether to trigger a fault alarm and generate a fault identification signal ,in, is a change indicator, is the failure mode threshold, is the fault sensitivity adjustment factor, is the fault triggering threshold;
[0157] If the fault identification signal indicates an abnormality, extract The matching fault mode description is obtained by querying the fault database using the formula:
[0158]
[0159] Get the matching failure mode ,in, is the matching sensitivity adjustment factor, is a change indicator, is the failure mode database, Refers to the action of retrieving or obtaining data from a database or other data source.
[0160] Assume the following data:
[0161] The assumed value is 1.673;
[0162] is 1.5;
[0163] is 2;
[0164] is 1.
[0165] Calculation of fault identification signal :
[0166]
[0167]
[0168]
[0169] It means that the comprehensive change index exceeds the value adjusted by the preset fault mode threshold, so it is identified as a fault and a fault alarm is triggered.
[0170] Assume the following data:
[0171] Still at 1.673;
[0172] is 0.95.
[0173] Assume that there is a fault mode threshold in the database set to 1.65. Under the regulation of , the matching calculation process is:
[0174] pattern=fetch(1.673, DB, 0.95)
[0175] Assume that the function is based on and The adjusted value is queried and the closest matching pattern is determined because 1.673 is close to 1.65 in the database, and with the adjustment factor, the pattern is successfully matched.
[0176] See also Figure 5 , the analysis steps of fault frequency and influencing factors are as follows:
[0177] Based on the fault feature set, the number of occurrences of each fault type is counted using the formula:
[0178]
[0179] Generates the number of occurrences of the fault type ,in, It is Class fault event count, is the impact weight of the fault type, is the total number of fault types;
[0180] According to the number of occurrences of the fault type, the frequency of each fault type is calculated using the formula:
[0181]
[0182] Get the adjusted fault frequency ,in, is the number of failures during the monitoring period, is the frequency adjustment constant, is the number of occurrences of the fault type;
[0183] According to the adjusted fault frequency, the correlation between the fault frequency and the equipment parameters is analyzed, and the formula is:
[0184]
[0185] Get the failure influencing factors ,in, is the adjusted fault frequency, is the operating parameter weight, is the data uncertainty factor.
[0186] Assume the following data:
[0187] Fault type A occurred 10 times, with a weight of 0.8;
[0188] Fault type B occurred 5 times, with a weight of 0.5.
[0189] Calculation process:
[0190]
[0191] It means that after weighting the severity of the fault, the total number of faults occurring is 10.5 times.
[0192] Assume the following data:
[0193] is the number of failures mentioned above;
[0194] is 50;
[0195] is 0.1.
[0196] Calculation process:
[0197]
[0198]
[0199]
[0200] This indicates that the adjusted fault frequency is 0.31414, which is the weighted frequency of faults A and B.
[0201] Assume the following data:
[0202] is 0.31414;
[0203] is 0.6;
[0204] is 0.05.
[0205] Calculation process:
[0206]
[0207] The weighted impact factor of faults A and B is 0.17951, which is the degree of impact of these fault types on equipment performance.
[0208] See also Figure 6 The specific steps to determine the fault point of the packaging buckle machine are as follows:
[0209] Based on the influencing factors, a fault simulation test is performed using the formula:
[0210]
[0211] Get simulation test results , indicating whether the fault is successfully reproduced, where and is the adjustment coefficient, is the equipment operating parameter, is the environmental impact parameter, It is the failure influencing factor;
[0212] According to the simulation test results, determine whether the fault matches the expectation, using the formula:
[0213]
[0214] Get fault matching results ,in, is the matching adjustment factor, is the expected failure mode, It is the result of simulation test.
[0215] Assume the following data:
[0216] Assuming 0.7, it represents the comprehensive score of the fault impact;
[0217] Set to 1.5;
[0218] Assume it is 100 units;
[0219] is 0.3;
[0220] Assume it is 50 units;
[0221] Indicates whether the fault has been reproduced. 1 indicates that the fault has been reproduced, and 0 indicates that the fault has not been reproduced.
[0222] Calculation process:
[0223]
[0224]
[0225]
[0226] The calculation process is used to evaluate the possibility of fault reproduction. Assume that the simulation test function simulate returns 1 (fault reproduction) when the sum of input parameters exceeds 160, otherwise it returns 0. The simulation test returns 1, indicating that the fault is successfully reproduced.
[0227] Assume the following data:
[0228] Obtained from the above;
[0229] is 1.2;
[0230] The expected normal range is 140, and any value exceeding this is considered a fault;
[0231] When 1, it indicates a match (confirmation is a fault), and 0 indicates a mismatch (confirmation is not a fault).
[0232] Calculation process:
[0233]
[0234]
[0235] According to the matching logic, it is assumed that the match function returns 1 when the simulation result is equal to or higher than the adjusted expected fault mode. Therefore, the fault matching function returns 1, confirming that it is an expected fault.
[0236] See also Figure 7 The specific steps for analyzing the usage frequency and maintenance history of the packaging buckle machine are as follows:
[0237] Based on the fault diagnosis confirmation results, analyze the frequency of equipment use using the formula:
[0238]
[0239] Generate device usage frequency ,in, For the Number of hours of use recorded, is the equipment usage intensity coefficient;
[0240] Calculate the average maintenance cost based on the frequency of equipment use using the formula:
[0241]
[0242] Generate average maintenance cost ,in, It is The cost of maintenance, It is with The weight factor of the secondary maintenance association.
[0243] Assume data:
[0244] There are three records in a certain period:
[0245] First record: hours of use Hours, usage intensity ;
[0246] Second record: hours of use Hours, usage intensity ;
[0247] The third record: hours of use Hours, usage intensity .
[0248] Calculation process:
[0249]
[0250]
[0251]
[0252] It means that after weighting different usage intensities, the average usage frequency of the equipment is 6.17 hours per cycle.
[0253] Assume data:
[0254] There are three maintenances in a certain period:
[0255] Maintenance 1: Cost , weight ;
[0256] Second maintenance: cost , weight ;
[0257] Maintenance 3: Cost , weight .
[0258] Calculation process:
[0259]
[0260]
[0261]
[0262] This shows that after taking into account the complexity or importance of maintenance, the average cost of each maintenance is about 233.33 yuan.
[0263] See also Figure 8 , the specific steps for evaluating expected maintenance costs and time are:
[0264] Based on the optimal maintenance activities, calculate the expected maintenance cost using the formula:
[0265]
[0266] Generate expected maintenance costs ,in, It is The cost of maintenance, It is The amount of resources required for maintenance. is the efficiency factor of the resource, is the risk adjustment factor;
[0267] Based on the expected maintenance cost, the time required for maintenance is evaluated using the formula:
[0268]
[0269] Calculate the total expected maintenance time ,in, It is The time unit required for maintenance. It is The amount of resources required for maintenance. It is the speed factor, which indicates the speed of resource investment.
[0270] Assume the following data:
[0271] Maintenance 1: units, (efficiency), (risk);
[0272] Maintenance 2: units, .
[0273] Calculation process:
[0274]
[0275]
[0276]
[0277] The expected total maintenance cost is 701.14 yuan.
[0278] Assume the following data:
[0279] Maintenance 1: Hour, units, (speed);
[0280] Maintenance 2: Hour, units, .
[0281] Calculation process:
[0282]
[0283]
[0284] Indicates that the expected total maintenance time is 11 hours.
[0285] 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 automatic diagnosis system for operating failures of a packaging buckle machine, characterized in that: The system comprises: The data acquisition module is based on sensors to collect temperature, pressure, speed and vibration data of the packaging buckle machine, timestamp the data, and record the data changes of the equipment under the target operating conditions to obtain the operation data set; The feature analysis and prediction module analyzes the operation abnormality of the equipment based on the operation data set by calculating the temperature change rate and the pressure difference value, performs pattern matching on the operation abnormality, extracts features matching the known fault patterns, and obtains a fault feature set; The key fault diagnosis module compares the historical maintenance records of the packaging and buckling machine based on the fault feature set, analyzes the frequency and influencing factors of the fault, and combines the correlation of multiple types of parameters to perform fault simulation tests, determine the fault point of the packaging and buckling machine, and obtain the fault diagnosis confirmation result; The maintenance optimization module analyzes the usage frequency and maintenance history of the packaging buckle machine based on the fault diagnosis confirmation result, determines the optimal maintenance activity, and evaluates the expected maintenance cost and time, optimizes the maintenance cycle, and obtains a maintenance plan optimization log; The calculation steps of the temperature change rate and the pressure difference value are specifically as follows: Based on the operational data set, extract the temperature data sequence And the pressure data series , using the formula: ; and ; Calculate the adjusted temperature and pressure change sequence ,in, and Respectively represent The temperature and pressure at a given time point, and is the smoothing coefficient for temperature and pressure data, and is the influence coefficient of environmental noise on temperature and pressure measurement; The obtained and Divide by the time interval , using the formula: ; and ; Get the temperature change rate and the rate of pressure change ,in, and It is The temperature and pressure change sequence at each time point, is the time interval between adjacent time points, is the total number of data points; Analyze the temperature change rate and the rate of pressure change , using the formula: ; Aggregate into indicators of change , used for exception pattern matching, where and are the rate of change of temperature and pressure, and is the weighting factor for the rate of change of temperature and pressure.
2. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The steps for obtaining the operation data set are specifically as follows: Based on sensors, the operating data of the packaging buckle machine is collected, including temperature, pressure, speed and vibration data. Each data point is timestamped and the formula is used: ; Generate timestamped sensor datasets ,in, and Respectively represent the time Temperature, pressure, velocity and vibration data, Represents the timestamp of data collection, is the weight factor, which is used to adjust the impact weight of sensor data; Filter the data under the target operating conditions and use the decision function Identify data points Whether the conditions are met, the formula is: ; Get the operation data set that meets the conditions ,in, is a Boolean function, is the decision threshold, Sensor datasets labeled with timestamps; Summarize the filtered data points using the formula: ; Get the operation data set ,in, is the number of data points after filtering, is the data point, The operation data set that meets the conditions.
3. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The steps of pattern matching for operation anomalies are specifically as follows: Based on the operational anomaly, the fault mode threshold is compared using the formula: ; Determine whether to trigger a fault alarm and generate a fault identification signal ,in, is a change indicator, is the failure mode threshold, is the fault sensitivity adjustment factor, is the fault triggering threshold; If the fault identification signal indicates an abnormality, then extract The matching fault mode description is obtained by querying the fault database using the formula: ; Get the matching failure mode ,in, is the matching sensitivity adjustment factor, is a change indicator, It is a failure mode database.
4. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The analysis steps of the fault occurrence frequency and influencing factors are specifically as follows: Based on the fault feature set, the number of occurrences of each fault type is counted using the formula: ; Generates the number of occurrences of the fault type ,in, It is Class fault event count, is the impact weight of the fault type, is the total number of fault types; According to the number of occurrences of the fault type, the frequency of each fault type is calculated using the formula: ; Get the adjusted fault frequency ,in, is the number of failures during the monitoring period, is the frequency adjustment constant, is the number of occurrences of the fault type; According to the adjusted fault frequency, the correlation between the fault frequency and the equipment parameters is analyzed, and the formula is: ; Get the failure influencing factors ,in, is the adjusted fault frequency, is the operating parameter weight, is the data uncertainty factor.
5. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The steps for determining the fault point of the packaging buckle machine are specifically as follows: Based on the influencing factors, a fault simulation test is performed using the formula: ; Get simulation test results ,in, and is the adjustment coefficient, is the equipment operating parameter, is the environmental impact parameter, It is the failure influencing factor; According to the simulation test results, determine whether the fault matches the expectation, using the formula: ; Get fault matching results ,in, is the matching adjustment factor, is the expected failure mode, It is the result of simulation test.
6. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The specific steps for analyzing the usage frequency and maintenance history of the packaging buckle machine are as follows: Based on the fault diagnosis confirmation results, analyze the frequency of equipment use using the formula: ; Generate device usage frequency ,in, For the Number of recorded hours of use, is the equipment usage intensity coefficient; Based on the frequency of use of the equipment, calculate the average maintenance cost using the formula: ; Generate average maintenance cost ,in, It is The cost of maintenance, It is with The weight factor of the secondary maintenance association.
7. The automatic diagnosis system for operating failure of a packaging and buckling machine according to claim 1 is characterized in that: The steps for evaluating the expected maintenance cost and time are as follows: Based on the optimal maintenance activities, calculate the expected maintenance cost using the formula: ; Generate expected maintenance costs ,in, It is The cost of maintenance, It is The amount of resources required for maintenance. is the efficiency factor of the resource, is the risk adjustment factor; Based on the expected maintenance costs, estimate the time required for maintenance using the formula: ; Calculate the total expected maintenance time ,in, It is The time unit required for maintenance. It is The amount of resources required for maintenance. It is the speed factor, which indicates the speed of resource investment.
