Intelligent management system and method based on big data

Through the intelligent big data management system, the temperature changes of mechanical equipment parts are accurately predicted, and a variety of control strategies are adopted to solve the problem of temperature exceeding the limit, which improves the service life of the parts and fault detection efficiency.

CN118917829APending Publication Date: 2024-11-08HARBIN SHENGSHUN NETWORK TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410962726.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The prior art is difficult to accurately predict the failure of mechanical equipment parts, which leads to the inability to avoid temperature exceeding limits in advance, affecting production progress and reducing the service life of parts.

Method used

Adopt an intelligent management system based on big data, by collecting part temperature and parameter records, calculating the limited temperature and time limit, predicting the temperature changes of parts, filtering out parts whose predicted temperature is greater than the limited temperature, and using avoidance, splitting tasks or Replace with control policies of similar devices.

Benefits of technology

It realizes accurate prediction and control of mechanical equipment parts failures, extends the service life of parts, reduces wear and aging speed caused by temperature exceeding the limit, and improves fault detection efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917829A_ABST
    Figure CN118917829A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent management system and method based on big data, and belongs to the technical field of equipment control. The system comprises a data acquisition module, a data processing module, a production analysis module and an equipment control module. The data acquisition module is used for acquiring temperatures of different parts of each device in a production area and parameter records of each part; the data processing module is used for analyzing parameter records and calculating the limited temperature and the limited duration of each part; the production analysis module fits the temperature and the time in the calling time period of each part into a temperature relation formula, meanwhile, the equipment and the parts needing to be called in each step in the production task are disassembled, the calling time length of each part is estimated, and the calling time length is substituted into the temperature relation formula to calculate and predict the temperature; the equipment control module marks the part with the predicted temperature larger than the limited temperature, and on the premise that the production schedule is not affected, a proper strategy is selected according to the actual situation, and the temperature of the marked part is prevented from exceeding the limit.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of equipment control technology, and in particular to an intelligent management system and method based on big data. Background Art

[0002] With the development of modern industry, mechanical equipment plays an important role in the production process. However, due to the long-term operation and high-load work of mechanical equipment, the increase in the temperature of internal parts may cause overheating, damage or even shutdown of mechanical equipment, which has a serious impact on production. Therefore, it is of great significance to predict the temperature of parts in mechanical equipment and handle abnormalities.

[0003] At present, the equipment failure problems caused by abnormal temperature of parts are mainly solved by regular maintenance and fault repair. Regular maintenance refers to the inspection and maintenance of mechanical equipment by humans at regular intervals. Humans use their maintenance experience to judge whether there are obvious faults in the parts of the mechanical equipment and whether they need to be replaced. This method relies too much on human experience and intuition. When facing some problems that only occur during operation, it is often difficult for humans to quickly locate the problem parts, causing the problem to be ignored. Fault repair refers to fault monitoring during the operation of mechanical equipment, and when a fault is detected, humans are notified to repair the faulty parts. Although this method can quickly discover and solve problems, the production progress has been affected when the fault occurs and the subsequent maintenance behavior, and even if the maintenance is not timely, it will further cause damage to other parts in the mechanical equipment. Although the above two methods can solve the equipment failure problems caused by abnormal temperature of parts to a certain extent, due to the limitations of the scheme itself, it is not possible to locate the faulty parts more accurately, nor can it predict the probability of failure of each part in advance, and it is impossible to take targeted avoidance measures. Therefore, at this stage, a more efficient mechanical equipment fault prediction scheme is needed to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent management system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent management method based on big data, the method comprising the following steps:

[0006] S1. Collect the temperature of different parts of each equipment in the production area, and record the parameters of each part;

[0007] S2. Calculate the limit temperature and limit time of each part according to the parameter record;

[0008] S3. Analyze the calling time of each part in the production task and predict the final temperature of each part;

[0009] S4. Filter out the parts whose predicted temperature is greater than the limited temperature and reselect other control strategies.

[0010] In S1, temperature refers to the temperature value of the part during the call period. When the part is called, the temperature sensor in contact with the part automatically collects temperature information. Parameter records include call records, temperature records, and maintenance records. Call records refer to the start and end time of the part call, temperature records refer to the temperature change value of the part from the start time to the end time of the call, and maintenance records refer to the maintenance time of the part.

[0011] Parts are called when the equipment is running, and some of its parts are activated to work together. The activated parts are used as calling parts, and the call start time is recorded. When the equipment adjusts its working state and no longer needs the previously activated parts to work together, the previously activated parts stop working, and the call end time is recorded.

[0012] In S2, the specific steps are as follows:

[0013] S201, analyzing the maintenance record of each part, calculating the time between each maintenance time and the last maintenance time, selecting the time period corresponding to the maximum time period as the maximum usage time period, and each part corresponds to a maximum usage time period.

[0014] S202, obtaining all call records of each part in the corresponding maximum usage time period, as well as the temperature records of the call start time and the call end time under each call record, and calculating the working temperature and working time of each call record. The calculation steps are as follows:

[0015] S202-1. The call start time to the call end time in the call record is used as the call time period, and the call time period is evenly divided into N time periods. The temperature at the start time and end time of each time period is retrieved from the temperature record respectively, and the temperature difference between the start time and the end time is divided by the length of the corresponding time period to obtain the temperature change rate.

[0016] S202-2, marking the time period corresponding to the temperature change rate being less than the temperature change rate threshold, summing up the temperature at the start time and the temperature at the end time of all marked time periods, and calculating the average value to obtain the operating temperature.

[0017] S202-3. Take the average of the temperature at the start time and the temperature at the end time of each time period to obtain the average temperature, filter out the time periods with an average temperature greater than the working temperature, and determine whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, sort the time periods greater than the temperature change rate threshold in chronological order of the time period start times, and subtract the start time of the corresponding calling time period from the start time of the first-ranked time period to obtain the working time; if the result is no, sort the time periods with an average temperature greater than the working temperature in chronological order of the time period start times, and subtract the start time of the corresponding calling time period from the start time of the first-ranked time period to obtain the working time.

[0018] S203, summing up the working temperatures of all the call records and calculating the average value to obtain the limited temperature; summing up the working time of all the call records and calculating the average value to obtain the limited time; each part corresponds to a limited temperature and a limited time.

[0019] In S3, the specific steps are as follows:

[0020] S301. Obtain all call records for each part, analyze each call record one by one, and use the call start time in the call record as the start time. When the difference between the call start time and the call end time is less than or equal to the corresponding limited time, the call end time is used as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, the call start time plus the corresponding limited time is used as the end time.

[0021] S302, associating the temperature and time from the start time to the end time of each call record to obtain associated data, fitting the associated data of all call records under the same part to obtain a temperature relationship formula, and each part corresponds to a temperature relationship formula.

[0022] S303. Analyze the equipment required for each step in the production task, obtain the equipment that needs to be called and the calling time of each part under the equipment, bring the calling time into the temperature relationship formula corresponding to the part, and calculate the increased temperature of each part; the formula is as follows:

[0023] W zf =a×log f T+1

[0024] Where W zf is the increase temperature in °C, a is the temperature influence coefficient, f is a constant greater than 1, T is the call duration in min, and the increase temperature plus the room temperature is the predicted temperature.

[0025] In S4, the specific steps are as follows:

[0026] S401. Filter out parts whose predicted temperature is greater than the specified temperature and mark them, and determine whether the equipment corresponding to each marked part can avoid the marked parts and complete the task without affecting the production progress. If the result is yes, adjust the working state of the corresponding equipment to avoid the marked parts, and the parts involved in the new working state do not have a situation where the predicted temperature is greater than the specified temperature; if the result is no, proceed to the next step.

[0027] S402. Determine whether the equipment corresponding to the marked part can be split and carried out in time without affecting the production progress. If yes, split the work tasks of the corresponding equipment so that they can be completed in time. The predicted temperatures of the split work tasks are not greater than the limited temperatures of the parts, and there is enough time between the work tasks to cool to room temperature. If no, proceed to the next step.

[0028] S403, determine whether the equipment corresponding to the marked part can be replaced by other similar equipment without affecting the production progress. If the result is yes, the work task of the corresponding equipment will be handed over to other similar equipment to complete, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limit temperature; if the result is no, proceed to the next step.

[0029] S404. Raise the predicted temperature corresponding to the marked part until any one of the conditions in steps S401-S403 is met, so that the production task can be smoothly executed.

[0030] S405. After the production task is completed, the call records, maintenance records and temperature records of all called parts are stored in the parameter records to provide data support for the follow-up.

[0031] An intelligent management system based on big data, the system includes a data acquisition module, a data processing module, a production analysis module and an equipment control module.

[0032] The data acquisition module is used to collect the temperature of different parts of each device in the production area, as well as the parameter records of each part. The data processing module analyzes the parameter records and calculates the limit temperature and limit time of each part. The production analysis module disassembles the equipment and parts that need to be called in each step of the production task, estimates the call time of each part and calculates the predicted temperature. The equipment control module marks the parts whose predicted temperature is greater than the limit temperature, and selects the appropriate control strategy for the marked parts according to the actual situation.

[0033] The data collection module includes a call record collection unit, a temperature record collection unit and a historical record collection unit.

[0034] The call record collection unit is used to collect time information of the called parts, and the time information includes the call start time and the call end time.

[0035] The temperature recording and collecting unit is used to collect the temperature change value of the called part from the start time to the end time of the call, and automatically collects the temperature information through the temperature sensor in contact with the part.

[0036] The history record collection unit is used to collect the historical parameter records of each part. The parameter records include call records, temperature records and maintenance records. The maintenance record refers to the maintenance time of the part.

[0037] The data processing module includes a limited temperature calculation unit and a limited time calculation unit.

[0038] The limit temperature calculation unit is used to calculate the limit temperature of each part. First, calculate the duration of adjacent maintenance times for each part, and obtain all call records within the two maintenance times with the longest duration. Secondly, take the call start time to the call end time in each call record as the call time period and divide it into N time periods, calculate the temperature change rate of each time period, obtain all time periods corresponding to the temperature change rate less than the temperature change rate threshold, and take the average of the temperature at the start time and the temperature at the end time of these time periods to obtain the working temperature. Finally, take the average working temperature of all call records under the same part to obtain the limit temperature.

[0039] The value of N refers to the thermal conductivity of each part. When the duration of the call time period is the same, the temperature of the part with good thermal conductivity rises quickly during operation, and the value of N is large; the temperature of the part with poor thermal conductivity rises slowly during operation, and the value of N is small.

[0040] The temperature of parts is closely related to the wear and aging speed. The wear and aging speeds are different at different temperatures, and the three are in direct proportion. Under high temperature conditions, the wear and aging speeds of parts will accelerate, but the working efficiency of parts will decrease.

[0041] The limited temperature refers to the optimal temperature at which the parts work. The optimal temperature means that the parts can just work normally without causing a large wear and aging rate due to excessively high temperature, nor will it reduce working efficiency.

[0042] The time limit calculation unit is used to calculate the time limit of each part.

[0043] First, calculate the interval between adjacent maintenance times for each part, and obtain all call records between the two maintenance times with the largest interval.

[0044] Selecting the call records between the two maintenance times with the longest interval can better obtain the optimal temperature of the parts.

[0045] Secondly, the call start time to the call end time in each call record is taken as the call time period and divided into N time periods. The temperature change rate of each time period is calculated, and the time periods corresponding to all temperature change rates less than the temperature change rate threshold are obtained. The working temperature is obtained by taking the average of the temperature at the start time and the temperature at the end time of these time periods.

[0046] Then, the average temperature is obtained by taking the average of the temperature at the start time and the temperature at the end time of each time period, and the time periods with an average temperature greater than the working temperature are screened out to determine whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, the time periods greater than the temperature change rate threshold are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time; if the result is no, the time periods with an average temperature greater than the working temperature are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time.

[0047] During the working process, the temperature of the parts first rises rapidly from room temperature to a stable value, and then fluctuates within a stable temperature range for a period of time due to the influence of various factors such as the heat dissipation device. However, as the working time increases, the performance of the heat dissipation device decreases and the heat conduction phenomenon of other parts causes the heat to accumulate rapidly, and the temperature will gradually rise again.

[0048] Working time refers to the interval from the time when the temperature starts to rise to the time when it rises again after being stable for a period of time. During this interval, the temperature is usually less than or equal to the limit temperature.

[0049] Finally, the working time of all call records under the same part is averaged to obtain the limited time.

[0050] The production analysis module includes a production task splitting unit and an operation status prediction unit.

[0051] The production task splitting unit is used to analyze the calling time of each part. When the system receives a production task, it analyzes the equipment required for each step in the production task, and obtains the equipment that needs to be called and the calling time of each part under the equipment.

[0052] The operation status prediction unit is used to predict the status of the called parts. First, all the call records in the historical parameter records of each called part are obtained, and the call start time in each call record is used as the start time. When the difference between the call start time and the call end time is less than or equal to the corresponding limited time, the call end time is used as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, the call start time plus the corresponding limited time is used as the end time. Secondly, the temperature and time from the start time to the end time of each call record are associated to obtain the associated data, and the associated data of all call records under the same part are fitted to obtain the temperature relationship formula. Finally, the call duration is substituted into the temperature relationship formula corresponding to the part, and the predicted temperature of each part is calculated. When the predicted temperature of the part is greater than the limited temperature, it is an abnormal state.

[0053] The equipment control module is used to select appropriate control strategies for parts in abnormal conditions.

[0054] When the equipment corresponding to the abnormal state parts can complete the task while avoiding the abnormal state parts without affecting the production progress, the working state of the corresponding equipment is adjusted to avoid the abnormal state parts. The parts involved in the new working state do not have a predicted temperature greater than the limit temperature.

[0055] Mechanical equipment usually has redundant designs. Using this redundant design in appropriate scenarios to avoid abnormal parts can reduce the occurrence of temperature exceeding the limit.

[0056] When the equipment corresponding to the abnormal state part can split the task and carry out it in time without affecting the production progress, the work task of the corresponding equipment is split and completed in time. The predicted temperature of the split work task is not greater than the limit temperature of the part, and there is enough time to cool to room temperature between the work tasks.

[0057] In the production process where the step sequence requirements are not strict, appropriately adjusting the task execution steps and pausing for a while to wait for the parts to cool before continuing to perform the same task can reduce the occurrence of temperature exceeding the limit of the parts.

[0058] When the equipment corresponding to the abnormal state part can be replaced by other similar equipment without affecting the production progress, the work task of the corresponding equipment will be handed over to other similar equipment to complete, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limit temperature.

[0059] When there are other substitute equipment, using similar substitute equipment to perform production tasks can reduce the occurrence of temperature exceeding the limit of parts.

[0060] When none of the above conditions can be met, the predicted temperature corresponding to the abnormal state parts is increased until any of the above conditions is met so that the production task can be smoothly executed.

[0061] By continuously lowering or raising the predicted temperature value, we can find the appropriate predicted temperature, increase the maintenance interval and improve the service life of parts.

[0062] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0063] 1. Adaptive setting of limit temperature: This application analyzes the maintenance records of different parts of each device separately, selects the call records within the longest maintenance time interval as the reference basis for the limit temperature, improves the accuracy of the limit temperature, and sets different limit temperatures for parts in different environments to better adapt to the actual situation. In the subsequent control strategy, the limit temperature will be continuously adjusted to increase the maintenance time interval of the parts.

[0064] 2. Accurate prediction of faults: This application adopts a predictive approach to equipment failures caused by abnormal temperatures of parts. By analyzing the equipment required for each step in the production task, the equipment that needs to be called and the calling time of each part under the equipment are obtained, and the predicted temperature of each part is calculated by substituting them into the temperature relationship formula. Parts with temperature exceeding the limit are discovered in advance, and control strategies are reselected for these parts, reducing the risk of failures caused by accelerated wear and aging of parts due to temperature exceeding the limit.

[0065] 3. Diversified control strategies: This application provides a variety of control strategies for parts predicted to exceed the temperature limit. It adopts various methods such as avoiding parts predicted to exceed the temperature limit, splitting tasks and completing them in time, and replacing similar equipment to solve the problem of parts exceeding the temperature limit and increase the service life of each part.

[0066] In summary, compared with traditional technologies, the present invention has the advantages of limited temperature adaptive setting, accurate fault prediction and diversified control strategies, and can improve the efficiency of mechanical equipment fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0068] Figure 1 It is a flow chart of an intelligent management method based on big data of the present invention;

[0069] Figure 2 It is a structural schematic diagram of an intelligent management system based on big data of the present invention. DETAILED DESCRIPTION

[0070] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] See also Figure 1 The present invention provides an intelligent management method based on big data, which comprises the following steps:

[0072] S1. Collect the temperature of different parts of each equipment in the production area, and record the parameters of each part;

[0073] S2. Calculate the limit temperature and limit time of each part according to the parameter record;

[0074] S3. Analyze the calling time of each part in the production task and predict the final temperature of each part;

[0075] S4. Filter out the parts whose predicted temperature is greater than the limited temperature and reselect other control strategies.

[0076] In S1, temperature refers to the temperature value of the part during the call period. When the part is called, the temperature sensor in contact with the part automatically collects temperature information. Parameter records include call records, temperature records, and maintenance records. Call records refer to the start and end time of the part call, temperature records refer to the temperature change value of the part from the start time to the end time of the call, and maintenance records refer to the maintenance time of the part.

[0077] Parts are called when the equipment is running, and some of its parts are activated to work together. The activated parts are used as calling parts, and the call start time is recorded. When the equipment adjusts its working state and no longer needs the previously activated parts to work together, the previously activated parts stop working, and the call end time is recorded.

[0078] In S2, the specific steps are as follows:

[0079] S201, analyzing the maintenance record of each part, calculating the time between each maintenance time and the last maintenance time, selecting the time period corresponding to the maximum time period as the maximum usage time period, and each part corresponds to a maximum usage time period.

[0080] S202, obtaining all call records of each part in the corresponding maximum usage time period, as well as the temperature records of the call start time and the call end time under each call record, and calculating the working temperature and working time of each call record. The calculation steps are as follows:

[0081] S202-1. The call start time to the call end time in the call record is used as the call time period, and the call time period is evenly divided into N time periods. The temperature at the start time and end time of each time period is retrieved from the temperature record respectively, and the temperature difference between the start time and the end time is divided by the length of the corresponding time period to obtain the temperature change rate.

[0082] S202-2, marking the time period corresponding to the temperature change rate being less than the temperature change rate threshold, summing up the temperature at the start time and the temperature at the end time of all marked time periods, and calculating the average value to obtain the operating temperature.

[0083] Assume that there are two marked time periods Q1 and Q2 in the calling time period, the temperature at the start time of Q1 is t1, and the temperature at the end time of Q1 is t2; the temperature at the start time of Q2 is t3, and the temperature at the end time of Q2 is t4; then the working temperature of the calling time period is: (t1+t2+t3+t4)÷4.

[0084] S202-3. Take the average of the temperature at the start time and the temperature at the end time of each time period to obtain the average temperature, filter out the time periods with an average temperature greater than the working temperature, and determine whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, sort the time periods greater than the temperature change rate threshold in chronological order of the time period start times, and subtract the start time of the corresponding calling time period from the start time of the first-ranked time period to obtain the working time; if the result is no, sort the time periods with an average temperature greater than the working temperature in chronological order of the time period start times, and subtract the start time of the corresponding calling time period from the start time of the first-ranked time period to obtain the working time.

[0085] S203, summing up the working temperatures of all the call records and calculating the average value to obtain the limited temperature; summing up the working time of all the call records and calculating the average value to obtain the limited time; each part corresponds to a limited temperature and a limited time.

[0086] In S3, the specific steps are as follows:

[0087] S301. Obtain all call records for each part, analyze each call record one by one, and use the call start time in the call record as the start time. When the difference between the call start time and the call end time is less than or equal to the corresponding limited time, the call end time is used as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, the call start time plus the corresponding limited time is used as the end time.

[0088] S302, associating the temperature and time from the start time to the end time of each call record to obtain associated data, fitting the associated data of all call records under the same part to obtain a temperature relationship formula, and each part corresponds to a temperature relationship formula.

[0089] S303. Analyze the equipment required for each step in the production task, obtain the equipment that needs to be called and the calling time of each part under the equipment, bring the calling time into the temperature relationship formula corresponding to the part, and calculate the increased temperature of each part; the formula is as follows:

[0090] W zf =a×log f T+1

[0091] Where W zf is the increase temperature in °C, a is the temperature influence coefficient, f is a constant greater than 1, T is the call duration in min, and the increase temperature plus the room temperature is the predicted temperature.

[0092] In S4, the specific steps are as follows:

[0093] S401. Filter out parts whose predicted temperature is greater than the specified temperature and mark them, and determine whether the equipment corresponding to each marked part can avoid the marked parts and complete the task without affecting the production progress. If the result is yes, adjust the working state of the corresponding equipment to avoid the marked parts, and the parts involved in the new working state do not have a situation where the predicted temperature is greater than the specified temperature; if the result is no, proceed to the next step.

[0094] S402. Determine whether the equipment corresponding to the marked part can be split and carried out in time without affecting the production progress. If yes, split the work tasks of the corresponding equipment so that they can be completed in time. The predicted temperatures of the split work tasks are not greater than the limited temperatures of the parts, and there is enough time between the work tasks to cool to room temperature. If no, proceed to the next step.

[0095] S403, determine whether the equipment corresponding to the marked part can be replaced by other similar equipment without affecting the production progress. If the result is yes, the work task of the corresponding equipment will be handed over to other similar equipment to complete, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limit temperature; if the result is no, proceed to the next step.

[0096] S404. Raise the predicted temperature corresponding to the marked part until any one of the conditions in steps S401-S403 is met, so that the production task can be smoothly executed.

[0097] S405. After the production task is completed, the call records, maintenance records and temperature records of all called parts are stored in the parameter records to provide data support for the follow-up.

[0098] See also Figure 2 The present invention provides an intelligent management system based on big data, which includes a data acquisition module, a data processing module, a production analysis module and an equipment control module.

[0099] The data acquisition module is used to collect the temperature of different parts of each device in the production area, as well as the parameter records of each part. The data processing module analyzes the parameter records and calculates the limit temperature and limit time of each part. The production analysis module disassembles the equipment and parts that need to be called in each step of the production task, estimates the call time of each part and calculates the predicted temperature. The equipment control module marks the parts whose predicted temperature is greater than the limit temperature, and selects the appropriate control strategy for the marked parts according to the actual situation.

[0100] The data collection module includes a call record collection unit, a temperature record collection unit and a historical record collection unit.

[0101] The call record collection unit is used to collect time information of the called parts, and the time information includes the call start time and the call end time.

[0102] The temperature recording and collecting unit is used to collect the temperature change value of the called part from the start time to the end time of the call, and automatically collects the temperature information through the temperature sensor in contact with the part.

[0103] The history record collection unit is used to collect the historical parameter records of each part. The parameter records include call records, temperature records and maintenance records. The maintenance record refers to the maintenance time of the part.

[0104] The data processing module includes a limited temperature calculation unit and a limited time calculation unit.

[0105] The limit temperature calculation unit is used to calculate the limit temperature of each part. First, calculate the duration of adjacent maintenance times for each part, and obtain all call records within the two maintenance times with the longest duration. Secondly, take the call start time to the call end time in each call record as the call time period and divide it into N time periods, calculate the temperature change rate of each time period, obtain all time periods corresponding to the temperature change rate less than the temperature change rate threshold, and take the average of the temperature at the start time and the temperature at the end time of these time periods to obtain the working temperature. Finally, take the average working temperature of all call records under the same part to obtain the limit temperature.

[0106] The value of N refers to the thermal conductivity of each part. When the duration of the call time period is the same, the temperature of the part with good thermal conductivity rises quickly during operation, and the value of N is large; the temperature of the part with poor thermal conductivity rises slowly during operation, and the value of N is small.

[0107] The temperature of parts is closely related to the wear and aging speed. The wear and aging speeds are different at different temperatures, and the three are in direct proportion. Under high temperature conditions, the wear and aging speeds of parts will accelerate, but the working efficiency of parts will decrease.

[0108] The limited temperature refers to the optimal temperature at which the parts work. The optimal temperature means that the parts can just work normally without causing a large wear and aging rate due to excessively high temperature, nor will it reduce working efficiency.

[0109] The time limit calculation unit is used to calculate the time limit of each part.

[0110] First, calculate the interval between adjacent maintenance times for each part, and obtain all call records between the two maintenance times with the largest interval.

[0111] Selecting the call records between the two maintenance times with the longest interval can better obtain the optimal temperature of the parts.

[0112] Secondly, the call start time to the call end time in each call record is taken as the call time period and divided into N time periods. The temperature change rate of each time period is calculated, and the time periods corresponding to all temperature change rates less than the temperature change rate threshold are obtained. The working temperature is obtained by taking the average of the temperature at the start time and the temperature at the end time of these time periods.

[0113] Then, the average temperature is obtained by taking the average of the temperature at the start time and the temperature at the end time of each time period, and the time periods with an average temperature greater than the working temperature are screened out to determine whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, the time periods greater than the temperature change rate threshold are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time; if the result is no, the time periods with an average temperature greater than the working temperature are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time.

[0114] During the working process, the temperature of the parts first rises rapidly from room temperature to a stable value, and then fluctuates within a stable temperature range for a period of time due to the influence of various factors such as the heat dissipation device. However, as the working time increases, the performance of the heat dissipation device decreases and the heat conduction phenomenon of other parts causes the heat to accumulate rapidly, and the temperature will gradually rise again.

[0115] Working time refers to the interval from the time when the temperature starts to rise to the time when it rises again after being stable for a period of time. During this interval, the temperature is usually less than or equal to the limit temperature.

[0116] Finally, the working time of all call records under the same part is averaged to obtain the limited time.

[0117] The production analysis module includes a production task splitting unit and an operation status prediction unit.

[0118] The production task splitting unit is used to analyze the calling time of each part. When the system receives a production task, it analyzes the equipment required for each step in the production task, and obtains the equipment that needs to be called and the calling time of each part under the equipment.

[0119] The operation status prediction unit is used to predict the status of the called parts. First, all the call records in the historical parameter records of each called part are obtained, and the call start time in each call record is used as the start time. When the difference between the call start time and the call end time is less than or equal to the corresponding limited time, the call end time is used as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, the call start time plus the corresponding limited time is used as the end time. Secondly, the temperature and time from the start time to the end time of each call record are associated to obtain the associated data, and the associated data of all call records under the same part are fitted to obtain the temperature relationship formula. Finally, the call duration is substituted into the temperature relationship formula corresponding to the part, and the predicted temperature of each part is calculated. When the predicted temperature of the part is greater than the limited temperature, it is an abnormal state.

[0120] The equipment control module is used to select appropriate control strategies for parts in abnormal conditions.

[0121] When the equipment corresponding to the abnormal state parts can complete the task while avoiding the abnormal state parts without affecting the production progress, the working state of the corresponding equipment is adjusted to avoid the abnormal state parts. The parts involved in the new working state do not have a predicted temperature greater than the limit temperature.

[0122] Mechanical equipment usually has redundant designs. Using this redundant design in appropriate scenarios to avoid abnormal parts can reduce the occurrence of temperature exceeding the limit.

[0123] When the equipment corresponding to the abnormal state part can split the task and carry out it in time without affecting the production progress, the work task of the corresponding equipment is split and completed in time. The predicted temperature of the split work task is not greater than the limit temperature of the part, and there is enough time to cool to room temperature between the work tasks.

[0124] In the production process where the step sequence requirements are not strict, appropriately adjusting the task execution steps and pausing for a while to wait for the parts to cool before continuing to perform the same task can reduce the occurrence of temperature exceeding the limit of the parts.

[0125] When the equipment corresponding to the abnormal state part can be replaced by other similar equipment without affecting the production progress, the work task of the corresponding equipment will be handed over to other similar equipment to complete, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limit temperature.

[0126] When there are other substitute equipment, using similar substitute equipment to perform production tasks can reduce the occurrence of temperature exceeding the limit of parts.

[0127] When none of the above conditions can be met, the predicted temperature corresponding to the abnormal state parts is increased until any of the above conditions is met so that the production task can be smoothly executed.

[0128] By continuously lowering or raising the predicted temperature value, we can find the appropriate predicted temperature, increase the maintenance interval and improve the service life of parts.

[0129] Example 1: Assume that the call time of part A and part B is 30 minutes and 45 minutes respectively, the room temperature is 20°C, the call time influence coefficient of part A is 1.2, and the constant is 1.1; the call time influence coefficient of part B is 1.5, and the constant is 1.3; substitute into the temperature relationship formula to calculate the predicted temperature of each part:

[0130] Predicted temperature of part A: 20+1.2×log 1.1 30+1≈63℃;

[0131] Predicted temperature of part B: 20+1.5×log 1.3 45+1≈42℃;

[0132] Assume that the temperature limit of part A is 65℃ and the temperature limit of part B is 40℃:

[0133] Then part B is in abnormal state.

[0134] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0135] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent management method based on big data, characterized by: The method comprises the following steps: S1. Collect the temperature of different parts of each equipment in the production area, and record the parameters of each part; S2. Calculate the limit temperature and limit time of each part according to the parameter record; S3. Analyze the calling time of each part in the production task and predict the final temperature of each part; S4. Filter out the parts whose predicted temperature is greater than the limited temperature and reselect other control strategies.

2. The intelligent management method based on big data according to claim 1, characterized in that: In S1, temperature refers to the temperature value of the part during the call period. When the part is called, the temperature sensor in contact with the part automatically collects temperature information; parameter records include call records, temperature records and maintenance records; call records refer to the start time and end time of the part being called, temperature records refer to the temperature change value of the part from the start time to the end time of the call, and maintenance records refer to the maintenance time of the part.

3. The intelligent management method based on big data according to claim 2, characterized in that: In S2, the specific steps are as follows: S201, analyzing the maintenance records of each part, calculating the time between each maintenance time and the last maintenance time, selecting the time period corresponding to the maximum time period as the maximum usage time period, and each part corresponds to a maximum usage time period; S202, obtaining all call records of each part in the corresponding maximum usage time period, as well as the temperature records of the call start time and the call end time under each call record, and calculating the working temperature and working time of each call record. The calculation steps are as follows: S202-1, taking the call start time to the call end time in the call record as the call time period, evenly dividing the call time period into N time periods, respectively searching the temperature at the start time and the end time of each time period in the temperature record, and dividing the temperature difference between the start time and the end time by the length of the corresponding time period to obtain the temperature change rate; S202-2, marking the time period corresponding to the temperature change rate being less than the temperature change rate threshold, summing up the temperature at the start time and the temperature at the end time of all marked time periods, and calculating the average value to obtain the operating temperature; S202-3, averaging the temperature at the start time and the temperature at the end time of each time period to obtain an average temperature, screening out time periods with an average temperature greater than the working temperature, and determining whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, then sorting the time periods greater than the temperature change rate threshold in chronological order, and subtracting the call start time of the corresponding call time period from the start time of the first-ranked time period to obtain the working time; if the result is no, then sorting the time periods with an average temperature greater than the working temperature in chronological order, and subtracting the call start time of the corresponding call time period from the start time of the first-ranked time period to obtain the working time; S203, summing up the working temperatures of all the call records and calculating the average value to obtain the limited temperature; summing up the working time of all the call records and calculating the average value to obtain the limited time; each part corresponds to a limited temperature and a limited time.

4. The intelligent management method based on big data according to claim 3 is characterized in that: In S3, the specific steps are as follows: S301, obtain all call records of each part, analyze each call record one by one, take the call start time in the call record as the start time, and when the difference between the call start time and the call end time is less than or equal to the corresponding limited time, take the call end time as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, take the call start time plus the corresponding limited time as the end time; S302, subtract the room temperature from the temperature within the start time to the end time of each call record and associate it with the time to obtain associated data, fit the associated data of all call records under the same part to obtain a temperature relationship formula, and each part corresponds to a temperature relationship formula; S303. Analyze the equipment required for each step in the production task, obtain the equipment that needs to be called and the calling time of each part under the equipment, bring the calling time into the temperature relationship formula corresponding to the part, and calculate the increased temperature of each part; the formula is as follows: W zf =a×log f T+1 Where W zf is the increase temperature, a is the temperature influence coefficient, f is a constant greater than 1, T is the calling time, and the increase temperature plus the room temperature is the predicted temperature.

5. The intelligent management method based on big data according to claim 4 is characterized in that: In S4, the specific steps are as follows: S401, filter out parts with predicted temperatures greater than the limit temperature and mark them, and determine whether the equipment corresponding to each marked part can avoid the marked parts and complete the task without affecting the production progress. If the result is yes, adjust the working state of the corresponding equipment to avoid the marked parts, and the parts involved in the new working state do not have a situation where the predicted temperature is greater than the limit temperature; if the result is no, proceed to the next step; S402, judging whether the equipment corresponding to the marked part can be split and performed in time without affecting the production progress, if the result is yes, then split the work tasks of the corresponding equipment so that they can be completed in time, and the predicted temperatures corresponding to the split work tasks are not greater than the limited temperatures corresponding to the parts, and there is enough time to cool down to room temperature between the work tasks; if the result is no, proceed to the next step; S403, judging whether the equipment corresponding to the marked part can be replaced by other similar equipment without affecting the production progress, if the result is yes, then the work task of the corresponding equipment is handed over to other similar equipment to complete, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limited temperature; if the result is no, then proceed to the next step; S404, increasing the predicted temperature corresponding to the marked part until any one of the conditions in steps S401-S403 is met, so that the production task can be smoothly executed; S405. After the production task is completed, the call records, maintenance records and temperature records of all called parts are stored in the parameter records to provide data support for the follow-up.

6. An intelligent management system based on big data, characterized by: The system includes a data acquisition module, a data processing module, a production analysis module and an equipment control module; The data acquisition module is used to collect the temperature of different parts of each equipment in the production area, as well as the parameter records of each part; the data processing module analyzes the parameter records and calculates the limit temperature and limit time of each part; The production analysis module breaks down the equipment and parts that need to be called in each step of the production task, estimates the calling time of each part and calculates the predicted temperature; the equipment control module marks the parts whose predicted temperature is greater than the limited temperature, and selects appropriate control strategies for the marked parts based on actual conditions.

7. The intelligent management system based on big data according to claim 6, characterized in that: The data acquisition module includes a call record acquisition unit, a temperature record acquisition unit and a historical record acquisition unit; The call record collection unit is used to collect the time information of the called parts, and the time information includes the call start time and the call end time; The temperature recording and collecting unit is used to collect the temperature change value of the called part from the start time to the end time of the call, and automatically collects the temperature information through the temperature sensor in contact with the part; The history record collection unit is used to collect the historical parameter records of each part. The parameter records include call records, temperature records and maintenance records. The maintenance record refers to the maintenance time of the part.

8. The intelligent management system based on big data according to claim 7, characterized in that: The data processing module includes a limited temperature calculation unit and a limited time calculation unit; The limit temperature calculation unit is used to calculate the limit temperature of each part; first, the duration of adjacent maintenance time under each part is calculated, and all call records within the two maintenance times with the longest duration are obtained; second, the call start time to the call end time in each call record is used as the call time period and divided into N time periods, the temperature change rate of each time period is calculated, and all time periods corresponding to the temperature change rate less than the temperature change rate threshold are obtained, and the working temperature is obtained by averaging the temperature at the start time and the temperature at the end time of these time periods; finally, the limit temperature is obtained by averaging the working temperatures of all call records under the same part; The time limit calculation unit is used to calculate the time limit of each part; First, calculate the interval between adjacent maintenance times for each part, and obtain all call records between the two maintenance times with the largest interval; Secondly, the call start time to the call end time in each call record is taken as the call time period and divided into N time periods. The temperature change rate of each time period is calculated, and the time periods corresponding to all temperature change rates less than the temperature change rate threshold are obtained. The working temperature is obtained by taking the average of the temperature at the start time and the temperature at the end time of these time periods; Then, the average temperature is obtained by averaging the temperature at the start time and the temperature at the end time of each time period, and the time periods with an average temperature greater than the working temperature are screened out to determine whether the temperature change rate of these time periods is greater than the temperature change rate threshold. If the result is yes, the time periods greater than the temperature change rate threshold are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time. If the result is no, the time periods with an average temperature greater than the working temperature are sorted in chronological order, and the start time of the first-ranked time period is subtracted from the call start time of the corresponding call time period to obtain the working time. Finally, the working time of all call records under the same part is averaged to obtain the limited time.

9. The intelligent management system based on big data according to claim 8, characterized in that: The production analysis module includes a production task splitting unit and an operation status prediction unit; The production task splitting unit is used to analyze the calling time of each part. When the system receives a production task, it analyzes the equipment required for each step in the production task, and obtains the equipment that needs to be called and the calling time of each part under the equipment. The operation status prediction unit is used to predict the status of the called parts; first, all the call records in the historical parameter records of each called part are obtained, and the call start time in each call record is used as the start time. When the difference between the call start time and the call end time is less than or equal to the corresponding limited time, the call end time is used as the end time; when the difference between the call start time and the call end time is greater than the corresponding limited time, the call start time plus the corresponding limited time is used as the end time; secondly, the temperature from the start time to the end time of each call record is subtracted from the room temperature and then associated with the time to obtain the associated data, and the associated data of all call records under the same part are fitted to obtain the temperature relationship formula; finally, the call duration is substituted into the temperature relationship formula corresponding to the part, and the predicted temperature of each part is calculated. When the predicted temperature of the part is greater than the limited temperature, it is an abnormal state.

10. The intelligent management system based on big data according to claim 9, characterized in that: The equipment control module is used to select appropriate control strategies for parts in abnormal conditions; When the equipment corresponding to the abnormal state part can avoid the abnormal state part and complete the task without affecting the production progress, the working state of the corresponding equipment is adjusted to avoid the abnormal state part, and the parts involved in the new working state do not have a predicted temperature greater than the limit temperature; When the equipment corresponding to the abnormal state part can be split and completed in time without affecting the production progress, the work tasks of the corresponding equipment are split and completed in time. The predicted temperature of the split work tasks is not greater than the limit temperature of the part, and there is enough time to cool down to room temperature between the work tasks. When the equipment corresponding to the abnormal state part can be replaced by other similar equipment without affecting the production progress, the work task of the corresponding equipment will be completed by other similar equipment, and the predicted temperature of the parts involved in other similar equipment is not greater than the corresponding limit temperature; When none of the above conditions can be met, the predicted temperature corresponding to the abnormal state parts is increased until any of the above conditions is met so that the production task can be smoothly executed.

Citation Information

Patent Citations

  • Air cleaner and method for predicting breakthrough time for same

    CN103402585A

  • Medical equipment maintenance recording system

    CN112435738A

  • Information processing system and method based on computer big data

    CN116541175A

  • Cable trench operation and maintenance state monitoring method and monitoring analysis cloud platform

    CN118040904A

  • Film deposition apparatus, film deposition method, monitoring program for film deposition apparatus, and recording medium thereof

    US20070095799A1