Method and system for predicting health degree of tobacco primary processing equipment, and storage medium

Abstract

The invention discloses a tobacco primary processing equipment health degree prediction method, a storage medium and a system, and the prediction method comprises the steps: obtaining the real-time operation data of equipment, distinguishing the hidden danger types of devices contained in the equipment, endowing the different hidden danger types with proportion quantity weights, and carrying out the prediction of the health degree of the equipment. And the equipment health degree is calculated by calculating the maintenance completion rate, the importance degree proportion of a single device in the whole machine, the service life T of the equipment, the attenuation rate J of the equipment and the like, and the obtained equipment health degree prediction score result can predict the health condition of the equipment in advance. By adopting the equipment health assessment method, the accuracy of the result for equipment health prediction is ensured. In practical application, the health condition of the equipment can be predicted and managed more effectively, and powerful data support is provided for maintenance and operation decisions.

Description

Technical Field

[0001] The present invention relates to the field of equipment health prediction, and in particular to a method, storage medium and system for predicting the health of tobacco silk making equipment. Background Art

[0002] The performance of equipment will gradually decline as the usage time increases. Therefore, equipment health prediction is very necessary to prevent equipment failures and improve equipment reliability.

[0003] Currently, workers are usually arranged to repair equipment only after it fails. However, since the type of failure cannot be known in advance, the repair time is long and the efficiency is low. Moreover, the equipment cannot be used after the failure, which will cause great losses during the equipment maintenance period.

[0004] Common equipment maintenance methods mainly include post-maintenance and preventive maintenance. Post-maintenance is the most common maintenance method in enterprises. It is to complete the maintenance of equipment in the shortest time after the failure occurs, and minimize downtime. However, due to the damage of key components such as the spindle and vibration groove of large equipment, the maintenance time of the failure is long. In addition to the direct loss of equipment, equipment failure will also have a more serious impact on the production progress. Preventive maintenance refers to the inspection and replacement of equipment regularly or based on a certain workload (such as the number of products produced) according to traditional means such as experience, relevant data or equipment user manuals to avoid sudden failures. It can avoid the risks of safety and downtime caused by potential failures to a certain extent, but this regular or empirical maintenance has the disadvantages of being inaccurate and not economical. Some equipment may not be worn or decayed to the degree that requires maintenance. Premature maintenance will cause a waste of manpower and resources and affect normal production. For equipment with severe decay, it is necessary to carry out cone maintenance at a fixed time, which may cause accelerated aging of equipment due to delays in timing, affect product quality, and even bring serious safety hazards.

[0005] In the prior art, to predict the health of industrial computer equipment in the industrial field, the environmental sensitive parameter information of the equipment (such as temperature, pressure and vibration) is usually collected to evaluate the health status of the equipment. However, these environmental sensitive parameter information are easily affected by the external environment, resulting in the inability to accurately reflect the internal operation status and potential failures of the equipment, making it difficult to accurately predict and evaluate the health status of the equipment. For example, a slight fluctuation in temperature may only be caused by a change in ambient temperature or a short fluctuation in load, rather than a failure inside the equipment. This single method of estimating the health of the equipment cannot accurately evaluate the health status of the equipment and is likely to affect the normal operation of the equipment.

[0006] For tobacco silk-making equipment, most machines are large-scale equipment. If a machine breaks down, the repairman needs to first identify the specific faulty device of the machine and then analyze the cause of the failure of the device to solve the problem. Such an operation takes a long time, which will delay the production progress and affect production efficiency. If the intensity of daily maintenance and maintenance inspections is increased, it is easy to cause "over-maintenance" phenomenon, wasting manpower and material resources. The production equipment has been in high-speed operation for a long time, and "insufficient maintenance" and too many temporary repairs have seriously affected the production efficiency of silk making. Therefore, if you want to improve production efficiency, you need to accurately estimate the health of each device of the equipment, and realize the accurate maintenance, repair and replacement of specific devices of large equipment. Therefore, how to calculate, evaluate and predict the health status of the equipment as a reference for equipment failure maintenance and repair is an urgent problem to be solved. Summary of the invention

[0007] In view of the above, it is necessary to provide a health prediction method for tobacco silk making equipment to solve the problem that it is difficult to accurately evaluate the health status of the equipment, which affects the normal operation of the tobacco silk making equipment.

[0008] The present invention constructs an evaluation index for equipment health, wherein the evaluation index is constructed based on the equipment performance, fault conditions, equipment work order maintenance conditions, operating status, equipment replacement status and safety status of the equipment; based on the evaluation index, equipment data of multiple devices are collected, the equipment data is processed to obtain the health score of each device, and based on the health score, the health status of the equipment is predicted.

[0009] Specifically, a method for predicting the health of tobacco silk making equipment comprises the following steps:

[0010] S1, counting and registering equipment hidden dangers, the equipment hidden dangers include:

[0011] (1) Physical damage that destroys the integrity of the equipment due to limitations in materials, processes, technical levels, costs, etc.;

[0012] (2) Hidden dangers caused by uneven operator quality and improper operation;

[0013] S2, according to the effectiveness of equipment interlocking, reliability of hazard sources, and the degree of danger of equipment operation, equipment hazards are divided into three categories: A, B, and C; among them:

[0014] Category A is a major hidden danger, which refers to those hidden dangers that are extremely harmful and difficult to rectify. They may require full or partial suspension of production and business, and take a long time to rectify. A device marked as a Category A hidden danger will be deducted 50 points;

[0015] Category B is a major hidden danger, which requires some time to deal with. A device marked as a Category B hidden danger will be scored 30 points;

[0016] Category C is a general hidden danger that can be handled and eliminated immediately. If a device is marked as a Category C hidden danger, 20 points will be deducted;

[0017] S3, calculate the health score X of a single device i

[0018] X i =[100-(K A ×A+K B ×B+K C ×C)]×M%

[0019] Among them: K represents the weight of the indicator, K A Indicates the weight of the proportion of Class A hidden dangers; K B Indicates the weight of the proportion of Class B hidden dangers; K C Indicates the weight of the proportion of Class C hidden dangers; M indicates the maintenance completion status, and M% indicates the maintenance completion rate. The maintenance status depends on the equipment operation status, including the equipment's operating efficiency, effective operation rate, fault downtime rate, number of fault downtimes, and the equipment's own static work order status, including the equipment's own online maintenance status;

[0020] S4, calculate the importance ratio P of a single device in the total devices i

[0021] P i = (the number or value of a single device ÷ the number or value of all devices in the equipment) × 100%

[0022] S5, calculate the device attenuation rate J

[0023] The equipment performance decay rate J refers to the rate at which the equipment's performance decreases after long-term use. It is usually expressed as a percentage and calculated using the following formula: Equipment performance decay rate J = (initial performance value - current performance value) ÷ initial performance value × 100%

[0024] Among them: "Initial performance value" is the performance index when the device is started, and "Current performance value" is the performance index measured after long-term use;

[0025] S6, calculate the health of the device Y

[0026] Y=∑ i＝1 n P i ×X i -T×J

[0027] Where: i is the index of the summed variable and n is the total number of devices in the device.

[0028] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for predicting the health of tobacco shred equipment described in the present invention.

[0029] A tobacco shred equipment health prediction system comprises a computer and a computer-readable storage medium of the present invention.

[0030] Compared with the prior art, the beneficial effects of the present invention include:

[0031] The present invention avoids the subjectivity of human experience, can depict the comprehensive impact of multiple evaluation indicators without testing, and has no strict restrictions on data distribution, sample size, and the number of evaluation indicators. It is suitable for both small sample data and large systems with multiple evaluation units and multiple indicators, and is more flexible and convenient. This application uses the model to evaluate the health status of the tobacco factory's silk-making equipment, quantify the health status of the equipment, facilitate maintenance personnel to understand the health status of the equipment in a timely manner, achieve more accurate equipment control, and promote production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 The figure is a flow chart of the prediction method of the present invention.

[0033] Figure 2 This is the equipment attenuation rate curve. DETAILED DESCRIPTION

[0034] A method for predicting the health of tobacco silk making equipment comprises the following steps:

[0035] S1, counting and registering equipment hidden dangers, the equipment hidden dangers include:

[0036] (1) Physical damage that destroys the integrity of the equipment due to limitations in materials, processes, technical levels, costs, etc.;

[0037] (2) Hidden dangers caused by uneven operator quality and improper operation;

[0038] S2, according to the effectiveness of equipment interlocking, reliability of hazard sources, and the degree of danger of equipment operation, equipment hazards are divided into three categories: A, B, and C; among them:

[0039] Category A is a major hidden danger, which refers to those hidden dangers that are extremely harmful and difficult to rectify. They may require full or partial suspension of production and business, and take a long time to rectify. A device marked as a Category A hidden danger will be deducted 50 points;

[0040] Category B is a major hidden danger, which requires some time to deal with. A device marked as a Category B hidden danger will be scored 30 points;

[0041] Category C is a general hidden danger that can be handled and eliminated immediately. If a device is marked as a Category C hidden danger, 20 points will be deducted;

[0042] S3, calculate the health score X of a single device i

[0043] X i =[100-(K A ×A+K B ×B+K C ×C)]×M%

[0044] Among them: K represents the weight of the indicator, K A Indicates the weight of the proportion of Class A hidden dangers; K B Indicates the weight of the proportion of Class B hidden dangers; K C Indicates the weight of the proportion of Class C hidden dangers; M indicates the maintenance completion status, and M% indicates the maintenance completion rate. The maintenance completion status depends on the equipment operation status, including the equipment's operating efficiency, effective operation rate, fault downtime rate, number of fault downtimes, and the equipment's own static work order status, including the equipment's own online maintenance status;

[0045] S4, calculate the importance ratio P of a single device in the total devices i

[0046] P i = (the number or value of a single device ÷ the number or value of all devices in the equipment) × 100%

[0047] S5, calculate the device attenuation rate J

[0048] The equipment performance decay rate J refers to the rate at which the equipment's performance decreases after long-term use. It is usually expressed as a percentage and calculated using the following formula: Equipment performance decay rate J = (initial performance value - current performance value) ÷ initial performance value × 100%

[0049] Among them: "Initial performance value" is the performance index when the device is started, and "Current performance value" is the performance index measured after long-term use;

[0050] S6, calculate the health of the device Y

[0051] Y=∑ i＝1 n P i ×X i -T×J

[0052] Where: i is the index of the summed variable and n is the total number of devices in the device.

[0053] Example 1

[0054] Statistics and registration of equipment hidden dangers: physical damage that destroys the integrity of the equipment itself due to limitations of materials, processes, technical levels, costs, etc. Hidden dangers caused by uneven operator quality and improper operation. Equipment hidden dangers are divided into three categories: A, B, and C based on the effectiveness of equipment interlocking, reliability of hazard sources, and the degree of danger of equipment operation.

[0055] Class A is a major hidden danger, which refers to those hidden dangers that are extremely harmful and difficult to rectify. They may require full or partial suspension of production and business, and take a long time to rectify. If a device is marked as a Class A hidden danger, it will be scored 50 points. Class B is a major hidden danger, which will take some time to deal with. If a device is marked as a Class B hidden danger, it will be scored 30 points. Class C is a general hidden danger, which can be handled and eliminated immediately. If a device is marked as a Class C hidden danger, it will be scored 20 points. The specific hidden danger classification is shown in the table below.

[0056]

[0057] Class A hidden dangers account for 1 / 5 of the total hidden dangers, Class B hidden dangers account for 3 / 10 of the total hidden dangers, and Class C hidden dangers account for 1 / 2 of the total hidden dangers. K represents the weight of the indicator, K A Indicates the weight of the proportion of Class A hidden dangers; K B Indicates the weight of the proportion of Class B hidden dangers; K C The weights of the proportion of Class C hidden dangers are shown in Table 2.

[0058] Hazard Classification K Value Class A hazards 20％ Class B hidden dangers 30％ Class C hazards 50％

[0059] M represents the maintenance completion status, and M% represents the maintenance completion rate. The maintenance status depends on the equipment operation status, including the equipment's operating efficiency, effective operation rate, failure downtime rate, number of failure downtimes, and the equipment's own static work order status, including the equipment's own online maintenance status. There are five maintenance methods: lubrication, inspection, spot inspection, repairman maintenance, and regular maintenance. The maintenance completion rates corresponding to different maintenance methods are shown in the following table:

[0060] Maintenance method Maintenance completion rate (M%) Lubrication (M1) 87.9％ Inspection (M2) 90.6％ Inspection (M3) 83.5％ Mechanic maintenance (M4) 85.7％ Periodic maintenance (M5) 95.4％

[0061] This gives a score X for each device. i =[100-(K A *A+K B *B+K C *C)]*M%

[0062] The proportion of a single device in the total devices can be calculated by the following formula: proportion = (value of a single device / value of total devices) × 100%. i Indicates the importance of a single component in the entire machine. Taking the wire cutter as an example, the value of a single component accounts for P of the total components.i As shown in the following table:

[0063]

[0064]

[0065] The service life of the equipment can be calculated from the purchase date or production date of the equipment, depending on the actual situation. The service life of the equipment is usually related to its depreciation period, which is generally calculated from the time when the equipment begins to be used. The calculation of the service life of the equipment is usually based on: physical loss of the equipment, technology update speed, economic depreciation, industry standards and actual use conditions. Physical loss is the basis for calculating the service life of the equipment. It includes factors such as wear and aging of the equipment during use. The physical life of the equipment can be evaluated by factors such as cumulative operating time, load rate and working environment. Secondly, the impact of the technology update speed on the service life of the equipment cannot be ignored. With the rapid development of technology, many equipment may still be physically available, but they are technologically backward and cannot meet production needs. Therefore, the technical life of the equipment is usually determined by the industry technology update cycle. In addition, industry standards and actual use conditions will also affect the calculation of the service life of the equipment. The equipment use standards in different industries are different, and the same equipment will have different service lives under different use environments and maintenance conditions. Therefore, T is used to represent the time when the equipment is put into production. For example, the service life of all silk-making equipment is 30 years from the date of commissioning. If there is any replacement or update of equipment, it will be renewed.

[0066] The device performance decay rate refers to the rate at which the performance of the device decreases after long-term use. It is usually expressed as a percentage and calculated using the following formula: Device performance decay rate = (initial performance value - current performance value) / initial performance value × 100%, where "initial performance value" is the performance index when the device is started, and "current performance value" is the performance index measured after long-term use. J is used to represent the device decay rate.

[0067] The attenuation rate of most equipment is a function of time. The typical attenuation curve is called the bathtub curve, which means that the attenuation rate of the equipment shows a certain regularity in the entire life cycle of 30 years from the time of investment to the time of scrapping. If the attenuation rate of the equipment is taken as the vertical coordinate and the use time is taken as the horizontal coordinate, the curve will be high at both ends and low in the middle.

[0068] The equipment attenuation rate varies with usage time and is divided into three stages: early debugging period, mid-term stabilization period and late wear and tear period.

[0069] Early debugging period. Equipment failures are caused by design and manufacturing defects; poor matching of parts; handling, transportation, installation, improper operation of operators, etc. There are many problems in this stage and they are exposed quickly. When these problems are gradually dealt with, the equipment attenuation rate changes from high to low and tends to be stable over time. For the early debugging period, it is necessary to do a good job in equipment delivery and put it into production, and the formal mass production stage should enter the mid-term stabilization period as soon as possible.

[0070] Mid-term stable period. The equipment is in normal operation, the equipment attenuation rate is low and stable, or even basically unchanged. This period is called the best period for equipment operation and the effective life of the equipment. Equipment attenuation is mainly caused by accidental factors such as poor maintenance and operating errors. The occurrence of failures is random and unpredictable. In order to reduce occasional failures and extend the effective life of the equipment, the focus of this stage is to strengthen operation management and the effectiveness management of daily maintenance.

[0071] Late wear and tear period. During this period, the equipment attenuation rate rises sharply, mainly because the equipment has been in operation for a long time, and some parts have entered the stage of severe wear and tear, and the effective service life is approaching the end. The equipment is already in an abnormal state. In view of the reasons for wear and tear, we should pay attention to daily work inspections, monitoring, data analysis, prediction of wear and tear trends, and early maintenance. Of course, if the cost of replacing parts and assemblies exceeds the cost of purchasing new equipment, scrapping measures should be taken to scrap the equipment. Through preventive maintenance and improved corrective maintenance, the equipment can return to a stable stage.

[0072] The bathtub curve of the equipment attenuation rate J is as follows Figure 2 shown.

[0073] From this, we can get the health score of a device Y=∑ i＝1 n P i *X i -T*J

[0074] Where i is the index of the sum variable and n is the upper limit of the sum. This expression means that for all P from i = 1 to i = n i The importance of a single component in the entire machine multiplied by the score of the single component X i Take the sum and subtract the age of the equipment multiplied by the attenuation factor.

[0075] Example 2

[0076] In daily production, a repairman was inspecting the production site in the workshop and found that the feed trolley of the wire cutting machine at the wire cutting position was leaking material. Now the health score of the feed trolley of this wire cutting machine is calculated.

[0077] If there is leakage during the production process, the material consumption hidden danger is scored 20 points, and the material consumption hidden danger belongs to Class C hidden danger, accounting for 50% of the total hidden dangers. The leakage phenomenon was discovered by the repairman during the inspection process, and the maintenance type belongs to the inspection (M2), and the maintenance completion rate of the inspection (M2) is 90.6%. According to the scoring formula of a single device X i =[100-(K A *A+K B *B+K C *C)]*M% We calculate the feeding trolley X of this shredder i =[100-(50%*20)]*90.6% to get X i =81.54 points. The importance of the feeder trolley in the entire wire cutter (P1) is 3.67%, and the wire cutter has been in operation for 3 years, so T = 3. At present, the wire cutter equipment is in normal operation, the equipment attenuation rate is low and stable, and even basically remains unchanged, and is in the mid-term stable period. According to the bathtub curve of the equipment attenuation rate J, J = 50%. From the equipment health score Y = ∑ i＝1 n P i *X i -T*J, calculate the feeding trolley Y of this wire cutting machine = ∑ i＝1 n 3.67%*81.54-3*50% equals Y=1.49 points, so we know that the equipment health score is extremely low, which means that there must be something wrong with the equipment and it needs to be tracked and repaired. Therefore, the equipment health score can be counted every week, and when the equipment health score is found to be low, daily tracking and maintenance can be carried out.

[0078] It can be seen from the above embodiments that the present invention provides a device health prediction formula, which obtains the real-time operation data of the device, wherein the real-time operation data includes Class A major hidden dangers, Class B major hidden dangers, and Class C general hidden dangers; K A : The proportion of Class A hidden dangers, quantity weight, K B : The proportion of Class B hidden dangers, quantity weight, K C : The proportion and quantity weight of Class C hidden dangers; maintenance completion rate, P i The importance of a single device in the entire machine, the equipment service life T, and the equipment attenuation rate J. Input the real-time operation data into the health prediction formula analysis to obtain the weight of the first indicator of the equipment health score. The equipment health prediction score result can predict the health status of the equipment in advance; the above equipment health assessment method is used to ensure the accuracy of the results used for equipment health prediction. In practical applications, this means that the health status of the equipment can be predicted and managed more effectively, providing strong data support for maintenance and operation decisions.

Claims

1. A method for predicting the health of tobacco shred equipment, characterized in that: The following steps are involved: S1, count and register equipment hidden dangers; S2, according to the effectiveness of equipment interlocking, reliability of hazard sources, and dangerousness of equipment operation, equipment hidden dangers are divided into three categories: A, B, and C; Category A is a major hidden danger; Category B is a relatively large hidden danger; Category C is a general hidden danger; S3, calculate the health score X of a single device i X i =[100-(K A ×A+K B ×B+K C ×C)]×M% Among them: K represents the weight of the indicator, K A Indicates the weight of the proportion of Class A hidden dangers; K B Indicates the weight of the proportion of Class B hidden dangers; K C Indicates the weight of the proportion of Class C hidden dangers; M indicates the maintenance completion status, and M% indicates the maintenance completion rate; S4, calculate the importance ratio P of a single device in the total devices i P i = (the number or value of a single device ÷ the number or value of all devices in the equipment) × 100% S5, calculate the device attenuation rate J J = (initial performance value - current performance value) ÷ initial performance value × 100%; S6, calculate the health of the device Y And=∑ i＝1 n P i ×X i -T×J Where: i is the index of the summed variable and n is the total number of devices in the device.

2. The method for predicting the health of tobacco silk-making equipment according to claim 1, characterized in that: The equipment hazards include: (1) Physical damage that destroys the integrity of the equipment due to limitations in materials, processes, technical levels, costs, etc.; (2) Hidden dangers caused by uneven operator quality and improper operation.

3. The method for predicting the health of tobacco silk processing equipment according to claim 1, characterized in that: The Class A hidden dangers include hidden dangers that are extremely harmful and difficult to rectify, which may require full or partial suspension of production and business, and require a long time to rectify. If a device is marked as a Class A hidden danger, 50 points will be recorded.

4. The method for predicting the health of tobacco silk-making equipment according to claim 1, characterized in that: The Class B hidden dangers include hidden dangers that require a period of time to deal with, and a device marked as a Class B hidden danger will be scored 30 points.

5. The method for predicting the health of tobacco silk-making equipment according to claim 1, characterized in that: The Class C hidden dangers include hidden dangers that can be immediately handled and eliminated. If a device is marked as a Class C hidden danger, 20 points will be recorded.

6. The method for predicting the health of tobacco shredded equipment according to claim 1, characterized in that: The maintenance completion status includes the equipment's operating efficiency, effective operation rate, failure downtime rate, number of failure downtimes, equipment-based or static work order status, and the equipment's own online maintenance status.

7. The method for predicting the health of tobacco shredded equipment according to any one of claims 1 to 6, characterized in that: The initial performance value is a performance indicator when the device is started, and the current performance value is a performance indicator measured after long-term use.

8. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for predicting the health of tobacco silk making equipment as described in any one of claims 1 to 7.

9. A tobacco silk processing equipment health prediction system, comprising a computer and a computer-readable storage medium as claimed in claim 8.

Images