Intelligent parameter control method and system for wear-resistant coating cladding process optimization

Abstract

The invention discloses an intelligent parameter control method and system for wear-resistant coating cladding process optimization, and relates to the technical field of material processing. Comprising the following steps: establishing a database, marking a variable parameter value of each device, calibrating associated parameter items of each device to a device connected with the device, and carrying out laser cladding operation according to the database; obtaining production demand data, and adjusting corresponding parameter values of corresponding equipment; when the corresponding parameter value of the corresponding equipment changes, the other parameter values of the corresponding equipment and the multiple parameter values of the related equipment are dynamically adjusted on the basis of the dynamic regulation and control method, and the parameters of the equipment can be continuously adjusted according to the production demand data in the production process until the production demand data are met; in addition, parameter change data in the continuous adjustment process can be recorded, direct calling can be conveniently carried out when the same production requirement is generated subsequently, the dynamic adjustment method can be continuously optimized, and therefore the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of material processing, and in particular to an intelligent parameter control method and system for optimizing the wear-resistant coating cladding process. Background Technique

[0002] Wear-resistant coating cladding is a technology that clads a layer of wear-resistant material on the surface of a material through a specific process to improve the wear resistance of the material surface. Among them, laser cladding is one of the commonly used types: it uses a high-energy density laser as a heat source to clad a layer of alloy material on the surface of the substrate, so as to achieve metallurgical bonding with the substrate. Laser cladding has concentrated energy and a small heat-affected zone, can accurately control the cladding area and thickness, and can prepare wear-resistant coatings with dense structures and excellent properties. It is commonly used for surface strengthening and repair of parts in the fields of aerospace, automobiles, and molds.

[0003] In the production of laser cladding, it is necessary to adjust equipment parameters. For example, the Chinese invention with the patent publication number CN108873700A provides a laser cladding closed-loop control method based on stereo vision, which includes installing a CCD connected to the control system and moving synchronously on each of the opposite sides of the laser, calibrating the two CCDs, monitoring the molten pool by the two CCDs at the same time, comparing the data obtained by the control system with the standard shape of the preset clad forming layer, obtaining the width error and height error, using the width error and / or height error as the input of the fuzzy controller, and the change amount of the controlled quantity as the output, that is, obtaining the adjustment change amount of the laser power or defocus amount, so as to achieve precise adjustment of the cladding accuracy and quality. It can obtain the molten pool change image during laser cladding by two CCDs in real time, then compare it with the preset standard molten pool forming layer shape by using the control system, and adjust the laser according to the error, so that the current molten pool is always consistent with the preset forming layer, realizing real-time control of the cladding process and achieving the purpose of improving the cladding accuracy and quality.

[0004] The laser cladding process involves the adjustment and optimization of multiple parameters. The above method needs to input production parameters into the system in advance. During the production process, the system will automatically fine-tune the laser power according to the real-time feedback data to achieve the best cladding effect. However, in actual production, due to the influence of various factors, the production requirements may change. In this case, the parameters of the corresponding equipment need to be adjusted, and the parameters of related equipment also need to be adjusted adaptively. The above method cannot adaptively adjust the parameters of each equipment. The existing parameter adjustment relies on a large amount of experimental data records, adjusts to specific parameter values, cannot be gradually adjusted during the production process, and cannot select the optimal parameter value, resulting in low production efficiency. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent parameter control method and system for optimizing the wear-resistant coating cladding process to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: An intelligent parameter control method for optimizing the wear-resistant coating cladding process, the method comprising:

[0007] Establish a database, mark the variable parameter values of each device, and calibrate the associated parameter items of each device for its connected devices, and perform laser cladding operations according to the database;

[0008] Obtain production requirement data, and adjust the corresponding parameter values of the corresponding devices according to the preliminary adjustment method;

[0009] When the corresponding parameter values of the corresponding devices change, dynamically adjust the remaining parameter values of the corresponding devices and multiple parameter values of related devices based on the dynamic regulation method. During the production process, continuously adjust the parameters of the devices according to the production requirement data until the production requirement data is met, and the parameter change data during the continuous adjustment process can be recorded, which is convenient for direct calling when the same production requirement data is generated subsequently, and can continuously optimize the dynamic regulation method, thereby improving production efficiency;

[0010] The dynamic regulation method includes:

[0011] S1: Adjust the remaining variable parameter values of the corresponding device, and obtain feedback data information, and adjust the variable parameter values according to the marked adjustment method;

[0012] S2: Obtain the changed parameter items of the corresponding device, and compare the associated parameter items to determine the related devices that need to adjust the parameters;

[0013] S3: Change the variable parameter items of the related devices determined in step S2, and obtain feedback data information, and adjust the variable parameter values according to the marked adjustment method;

[0014] S4: Take the device with the changed parameters in step S3 as the new corresponding device object, and repeat steps S2 and S3 until there is no new corresponding device object;

[0015] After the parameter adjustment is completed, perform a stability evaluation of the current data through the stability evaluation method;

[0016] After passing the stability evaluation, record the stable operation parameters of the device under this requirement and enter them into the database; when the production requirement data appears again, directly call the stable operation parameters of the device under this requirement.

[0017] Preferably, the stability evaluation method includes:

[0018] L1: Obtain the usage data of the device and divide the usage data into several groups according to time periods;

[0019] L2: For each device, perform stability calculation on different groups separately through a stability calculation method to obtain a preliminary stability evaluation;

[0020] L3: Compare the preliminary stability evaluation results of the same groups of different devices. When the consecutive several groups of the same group of different devices all pass the preliminary stability evaluation, it is determined that the current data passes the stability evaluation, and the situation where the device is affected by external factors during the time periods of several groups and cannot pass the stability evaluation can be excluded, improving the accuracy of the stability evaluation. When there is no situation where the consecutive several groups of the same group of different devices all pass the preliminary stability evaluation, it is determined that the current data fails the stability evaluation;

[0021] L4: When the stability evaluation fails, select the corresponding devices from the group with the largest number of devices that fail the preliminary stability evaluation, and re-adjust the variable parameter values through a dynamic regulation method. And after the parameter adjustment of the devices that fail the preliminary stability evaluation in the target group is completed, repeat the stability evaluation method again until the current data passes the stability evaluation and record the data, which can continuously optimize the adjusted parameters. Prioritizing to select the corresponding devices from the group with the largest number of devices that fail the preliminary stability evaluation for adjustment can cover unstable parameters as much as possible, reduce the number of adjustments, and further improve the adjustment speed.

[0022] Preferably, the stability calculation method includes:

[0023] B1: Collect and organize the usage data of the device. The usage data includes energy consumption data, start-stop data, maintenance data, and consumable data. Obtain the percentage scores a, b, c, d of the energy consumption data, start-stop data, maintenance data, and consumable data through big data;

[0024] B2: Then calculate the preliminary stability value according to the formula:

[0025]

[0026]

[0027] where Z is the preliminary stability value, are the weight coefficients of a, b, c, d respectively, Δ is the target device constant, the magnitude of its value can represent the gap between the stability of the target device of the company and the stability of this type of device in the big data, n is the number of times of passing the preliminary stability evaluation before, Z i+1 is the preliminary stability value of the previous i + 1 times of passing the preliminary stability evaluation, Z iis the initial stable value of the stability evaluation in the previous i times, λ i Z i+1 With Z i The weight coefficient of the difference is set by the technicians, K is the big data evaluation value, which represents the recognition of the equipment stability by big data;

[0028] B3: When Z ≥ 0.5, the device is judged to have passed the preliminary stability assessment, otherwise it has not passed the preliminary stability assessment. The preliminary stability value that has passed the stability assessment before can be brought into the calculation of this preliminary stability assessment, so that the historical stability of the device can be used as a comparative reference to improve the accuracy of the preliminary stability assessment. In addition, the standard of the preliminary stability assessment of the target device can be increased or decreased according to the actual situation, reducing the dependence on big data. Combined with the device's own situation, the preliminary stability assessment has more practical value.

[0029] Preferably, the usage data also includes an environmental protection coefficient H. When the equipment meets the environmental protection requirements, the value of H is 1, and when the equipment does not meet the environmental protection requirements, the value of H is 0. The calculation formula for the preliminary stability value is:

[0030]

[0031]

[0032] Where Z is the initial stability value, are the weight coefficients of a, b, c, and d, Δ is the local device constant, n is the number of times the preliminary stability assessment has been passed, and Z i+1 is the initial stability value of the first i+1 passes of the initial stability assessment, Z i is the initial stable value of the stability evaluation in the previous i times, λ i Z i+1 With Z i The weight coefficient of the difference is set by technical personnel, K is the big data evaluation value, which represents the recognition of big data on the stability of the equipment. The environmental factor H is included in the calculation of the preliminary stability value and used as a prerequisite for the preliminary stability assessment of the current data, which is conducive to avoiding environmental risks and meeting the requirements of laws and regulations.

[0033] Preferably, during the adjustment process of the dynamic control method, feedback data of a device with a specific parameter as a non-associated parameter item is obtained. If the feedback data is abnormal, the specific parameter is recalibrated as an associated parameter item between the corresponding device and the device, and the parameter changes of the device with an associated parameter item with the corresponding device during multiple adjustments are recorded. When the parameter has not changed, the associated parameter item is released, the database information is updated, and the calibration accuracy of the associated parameter item is continuously improved, thereby optimizing the adjustment speed of the dynamic control method for the variable parameter value.

[0034] Preferably, the marker adjustment method is as follows:

[0035] N1: Positively or negatively adjust the variable parameter value with the corresponding parameter value, and obtain real-time feedback data. Based on the change of the feedback data, judge the direction of parameter change;

[0036] N2: Record the direction of parameter change, and mark the relationship between the target parameter value and the corresponding parameter value as positive correlation, negative correlation, and non-correlation;

[0037] N3: When the same variable parameter value and corresponding parameter value are used as the adjustment target again, the adjustment speed can be increased according to the mark in N2.

[0038] Preferably, the preliminary adjustment method is as follows:

[0039] E1: Establish a demand classification menu containing various demand types for technicians to select. Match the equipment with each category in the concentrated demand classification, and match the adjustable parameter values of each equipment with each category in the concentrated demand classification;

[0040] E2: According to the demand classification selected by the technician, select the corresponding variable parameter values of the corresponding equipment and the target equipment;

[0041] E3: Establish a secondary quantization menu, and technicians can quantify the demand types at the upper level;

[0042] E4: Continuously adjust the selected adjustable parameter value according to the change amount set in E3, and obtain result feedback data. When the feedback data matches the quantified value of the demand type, stop adjusting the adjustable parameter value, classify and quantify the production demand data, clarify the adjustment target, and improve the adjustment efficiency.

[0043] Preferably, the demand classification menu can be edited. During the adjustment process, when the result feedback data is abnormal, mark the current demand classification menu item and notify the technician for correction, which can perform self-detection in a timely manner, prevent errors when technicians select demand types, and continuously optimize the matching degree between demand types and equipment, as well as between demand types and variable parameter values.

[0044] Compared with the prior art, the beneficial effects of the present invention are:

[0045] Based on production demand data, adjust the corresponding parameter values, and dynamically adjust the remaining parameter values of the corresponding equipment and multiple parameter values of related equipment based on the dynamic regulation method. During the production process, continuously adjust the parameters of the equipment according to the production demand data until the production demand data is met, and the parameter change data during the continuous adjustment process can be recorded, facilitating direct invocation when the same production demand data is generated subsequently, and continuously optimizing the dynamic regulation method to improve production efficiency;

[0046] Meanwhile, after the parameter adjustment is completed, conduct a stability assessment on the current data through the stability assessment method. After passing the stability assessment, record the stable operation parameters of the equipment under this demand and enter them into the database; when the production demand data appears again, directly invoke the stable operation parameters of the equipment under this demand to further improve the parameter adjustment efficiency and then improve the production efficiency;

[0047] Moreover, when conducting the preliminary stability assessment, the preliminary stability values that have passed the stability assessment previously can be brought into the calculation of this preliminary stability assessment, thereby using the historical stability situation of the equipment as a comparison reference to improve the accuracy of the preliminary stability assessment, and being able to increase or decrease the standard of the preliminary stability assessment of the target equipment according to the actual situation, reducing the dependence on big data, and combining the actual situation of the equipment to make the preliminary stability assessment more valuable in practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic flow chart of the intelligent parameter control method of the present invention;

[0049] Figure 2 It is a schematic flow chart of the preliminary adjustment method of the present invention;

[0050] Figure 3 It is a schematic flow chart of the dynamic regulation method of the present invention;

[0051] Figure 4 It is a schematic flow chart of the stability calculation method of the present invention (the equipment has an environmental protection coefficient);

[0052] Figure 5 It is a schematic structural diagram of the stability calculation method of the present invention (the equipment does not have an environmental protection coefficient). DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] In the operation of laser cladding, when production requirements change, such as an increase in production speed, an improvement in detection standards, etc., it is necessary to adjust the parameters of the corresponding equipment to ensure that production requirements are met. The present invention provides an intelligent adjustment method for equipment parameters when production requirements change. According to the change in production requirements, the parameters of each device on the production line are adjusted in a matching manner to ensure continuous production, thereby improving production efficiency.

[0055] As Figures 1 - 5 shown, the present invention provides a technical solution: an intelligent parameter control method for optimizing the wear-resistant coating cladding process, including:

[0056] Establish a database, mark the variable parameter values of each device, and calibrate the associated parameter items of each device for its connected devices, and perform laser cladding operations according to the database;

[0057] It should be noted that the variable parameter value of each device refers to the parameter item that can be changed during the use of the device, which can be summarized from the device's instruction manual and multiple trial runs of the device. In addition, the associated parameter item refers to a certain parameter of the target device. When this parameter changes, the devices connected upstream and downstream of the target device also need to adjust their parameters. At this time, this parameter can be determined as the associated parameter item of the target device and the connected devices. The associated parameter item can be summarized from the instruction manuals of the two devices and the multiple trial run data of the devices.

[0058] Obtain production requirement data, and adjust the corresponding parameter values of the corresponding devices according to the preliminary adjustment method;

[0059] When the corresponding parameter values of the corresponding devices change, based on the dynamic regulation method, dynamically adjust the remaining parameter values of the corresponding devices and multiple parameter values of related devices. During the production process, continuously adjust the parameters of the devices according to the production requirement data until the production requirement data is met, and the parameter change data during the continuous adjustment process can be recorded, which is convenient for direct calling when the same production requirement data appears later, and can continuously optimize the dynamic regulation method, thereby improving production efficiency;

[0060] After the parameter adjustment is completed, through the stability evaluation method, perform the stability evaluation of the current data;

[0061] After passing the stability evaluation, record the stable operation parameters of the device under this requirement and enter them into the database; when the production requirement data appears again, directly call the stable operation parameters of the device under this requirement.

[0062] Based on production demand data, adjust the corresponding parameter values according to the production demand data, and dynamically adjust the remaining parameter values of the corresponding equipment and multiple parameter values of related equipment based on the dynamic regulation method. During the production process, continuously adjust the parameters of the equipment according to the production demand data until the production demand data is met, and the parameter change data during the continuous adjustment process can be recorded, which is convenient for direct calling when the same production demand data is generated subsequently, and can continuously optimize the dynamic regulation method, thereby improving production efficiency.

[0063] Reference Figure 2 As shown, the preliminary adjustment method is as follows:

[0064] E1: Establish a demand classification menu containing various demand types for technicians to select, match the equipment with each category in the concentrated demand classification, and match the adjustable parameter values of each equipment with each category in the concentrated demand classification;

[0065] It should be noted that the demand types can be formulated according to the demands often encountered in actual production, such as production speed, detection intensity, cleaning intensity, cladding thickness, etc. The matching of demand types, equipment, and parameters can be summarized from multiple channels such as the equipment manual, the manufacturer's data of the equipment, and the multiple trial machine data of the equipment, and sorted out by technicians. For example, the cleaning intensity matches the cleaning equipment and also matches parameter items such as the dosage of cleaning agent and water pressure intensity of the cleaning equipment.

[0066] E2: According to the demand classification selected by the technician, select the corresponding variable parameter values of the corresponding equipment and the target equipment;

[0067] E3: Establish a secondary quantization menu for technicians to quantify the demand types at the upper level;

[0068] E4: Continuously adjust the selected adjustable parameter values according to the change amount set in E3, and obtain the result feedback data. When the feedback data matches the quantization value of the demand type, stop adjusting the adjustable parameter values, classify and quantify the production demand data, clarify the adjustment target, and improve the adjustment efficiency.

[0069] It should be noted that during the process of continuously adjusting the selected adjustable parameter values, the dynamic regulation method is also carried out simultaneously, and it does not need to wait for the preliminary adjustment method to end before proceeding. The result feedback data is collected by various sensors installed on the equipment, and in actual use, it is not limited to the sensors on the corresponding equipment. For example, during the adjustment process of the cladding thickness parameter, image collection can be carried out according to the CCD camera in the laser scanning equipment and the thickness can be calculated to obtain the result feedback data, and the result feedback data can also be obtained according to the detection results of the ray detection equipment.

[0070] Furthermore, the requirement classification menu can be edited. During the adjustment process, when the result feedback data is abnormal, the current requirement classification menu items are marked, and the technicians are notified to make corrections. It can perform self-detection in a timely manner to prevent errors when technicians select requirement types, and can continuously optimize the matching degree between requirement types and equipment, as well as between requirement types and variable parameter values.

[0071] It should be noted that the abnormal result feedback can be set by the technician. For example, in actual use, the laser power of the laser scanning device is set between 800W and 1200W, and the abnormal ranges set by the technician are 800W - 850W and 1000W - 1200W. When other equipment is being adjusted and causes the laser power of the laser scanning device to enter the abnormal range, it is determined that the result feedback data is abnormal, and the technician is notified to make corrections in a timely manner through an alarm light, buzzer, or sending remote information, etc., so that the preliminary adjustment method can be continuously optimized, and the matching degree between requirement types and equipment, as well as between requirement types and variable parameter values, can be improved.

[0072] Reference Figure 1 As shown, the dynamic regulation method is as follows:

[0073] S1: Adjust the remaining variable parameter values of the corresponding equipment, and obtain the feedback data information. Adjust the variable parameter values according to the marking adjustment method, where the corresponding equipment is the equipment selected in the preliminary adjustment method, and the feedback data information is obtained by various sensors installed on the equipment;

[0074] S2: Obtain the changed parameter items of the corresponding equipment, and compare the associated parameter items to determine the relevant equipment that needs to adjust the parameters;

[0075] S3: Change the variable parameter items of the relevant equipment determined in step S2, and obtain the feedback data information. Adjust the variable parameter values according to the marking adjustment method;

[0076] S4: Take the equipment whose parameters are changed in step S3 as the new corresponding equipment object, and repeat steps S2 and S3 until there is no new corresponding equipment object;

[0077] It can continuously adjust the parameters of the equipment until the production requirement data is met, and the parameter change data during the continuous adjustment process can be recorded, which is convenient for direct calling when the same production requirement data is generated later, and can continuously optimize the dynamic adjustment method, thereby improving production efficiency.

[0078] Furthermore, during the adjustment process of the dynamic regulation method, feedback data of devices with specific parameters as non-associated parameter items is obtained. If the feedback data is abnormal, the specific parameters are recalibrated as the associated parameter items of the corresponding devices and these devices. The parameter changes of the devices with associated parameter items corresponding to the corresponding devices are recorded during multiple adjustment processes. When the parameters do not change, the associated parameter items are removed, and the database information is updated, continuously improving the calibration accuracy of the associated parameter items, thereby optimizing the adjustment speed of the dynamic regulation method for variable parameter values.

[0079] It should be noted that the above feedback data is obtained through multiple sensors installed on devices with specific parameters as non-associated parameter items, and the abnormal range is set by technicians. When the data obtained by the sensors reaches the abnormal range, it is determined that the feedback data is abnormal, indicating that the specific parameters can affect the normal operation of the device. Then, the specific parameters can be recorded as the associated parameter items of the corresponding devices and these devices. Similarly, when adjusting the specific parameters, after the specific parameters are adjusted multiple times (the number of adjustment times can be set by technicians), if the devices with associated parameter items corresponding to the corresponding devices (i.e., related devices) do not have parameter changes, it means that the adjustment of the associated parameter items will not affect the normal operation of the related devices. Then, this associated parameter item can be deleted. This way can continuously optimize the associated parameters, improve the accuracy of the associated parameter items, clarify the adjustment target for subsequent adjustments, and improve the adjustment speed.

[0080] Furthermore, the marking adjustment method is as follows:

[0081] N1: Adjust the variable parameter value in a positive or negative correlation with the corresponding parameter value, and obtain real-time feedback data. According to the change of the feedback data, judge the direction of parameter change;

[0082] N2: Record the direction of parameter change, and mark the relationship between the target parameter value and the corresponding parameter value as positive correlation, negative correlation, and non-correlation;

[0083] N3: When the same variable parameter value and the corresponding parameter value are used as the adjustment target again, the adjustment speed can be increased according to the marking in N2.

[0084] When adjusting the corresponding parameter value, the variable parameter value is adjusted in a random direction. At this time, feedback data can be obtained through the sensors on the device. According to the change of the feedback data, the change relationship (positive correlation, negative correlation, or non-correlation) between the variable parameter value and the corresponding parameter value can be determined and marked. When adjusting next time, the adjustment can be directly carried out according to the recorded change relationship, improving the adjustment speed.

[0085] Reference Figure 3 As shown, the stability evaluation method is as follows:

[0086] L1: Obtain the usage data of the device and divide the usage data into several groups according to time periods; the length of the time period and the number of groups can be set by technicians;

[0087] L2: For each device, perform stability calculation on different groups separately through a stability calculation method to obtain a preliminary stability assessment;

[0088] L3: Compare the preliminary stability assessment results of the same groups of different devices. When the same groups of several consecutive groups (the number is set by technicians) of different devices all pass the preliminary stability assessment, it is determined that the current data passes the stability assessment, which can exclude the situation that the device is affected by external factors during the time periods of several groups and cannot pass the stability assessment, improving the accuracy of the stability assessment. When there is no situation where the same groups of several consecutive groups of different devices all pass the preliminary stability assessment, it is determined that the current data fails the stability assessment;

[0089] L4: When the stability assessment fails, select the corresponding devices from the group with the largest number of devices that fail the preliminary stability assessment, and adjust the variable parameter values again through a dynamic regulation method. And after the parameter adjustment of the devices that fail the preliminary stability assessment in the target group is completed, repeat the stability assessment method again until the current data passes the stability assessment and record the data, which can continuously optimize the adjusted parameters. Prioritizing to select the corresponding devices from the group with the largest number of devices that fail the preliminary stability assessment for adjustment can cover unstable parameters as much as possible, reduce the number of adjustments, and further improve the adjustment speed.

[0090] It should be noted that for the convenience of understanding, the following simulated data is set:

[0091] Mark the devices as X1, X2, X3, and X4 respectively;

[0092] Mark the time periods as Y1, Y2, Y3, Y4, Y5, Y6, Y7, and Y8;

[0093] Set the number of consecutive groups passing the stability assessment to 3 groups;

[0094] The obtained preliminary stability assessment is as shown in Table 1 below (where "Yes" represents passing the preliminary stability assessment and "No" represents failing the preliminary stability assessment):

[0095] Table 1

[0096]

[0097]

[0098] It can be found from Table 1 that in four consecutive time periods from time period Y4 to time period Y7, devices X1, X2, X3, and X4 all passed the preliminary stability assessment, and the number of consecutive groups exceeded 3 groups. It can be determined that the current data passed the stability assessment. During the time period Y2, the grouped usage data of devices X2, X3, and X4 did not pass the preliminary stability assessment. However, it may be affected by external factors or human factors. Therefore, this stability assessment method can avoid the instability caused by external factors or human factors affecting the device within a single time period, ensuring the accuracy of the stability assessment.

[0099] Example 1:

[0100] As Figure 4 shown, when conducting the preliminary stability assessment, when the device does not affect environmental factors, the stability calculation method is:

[0101] B1: Collect and organize the usage data of the device. The usage data includes energy consumption data, start-stop data, maintenance data, and consumable data. Obtain the percentage scores a, b, c, and d of the energy consumption data, start-stop data, maintenance data, and consumable data through big data.

[0102] It should be noted that to obtain the percentage scores a, b, c, and d of the energy consumption data, start-stop data, maintenance data, and consumable data, the data from multiple sources such as the device parameters provided by the device manufacturer, the data collected from the network platform, the data of the same type of company, and the data purchased from professional third-party data providers can be integrated first, and the percentage scores a, b, c, and d of the energy consumption data, start-stop data, maintenance data, and consumable data of the target device of the company can be calculated through the percentile method. The percentile method is an existing calculation method and will not be elaborated here.

[0103] B2: Then calculate the preliminary stability value according to the formula:

[0104]

[0105]

[0106] where Z is the preliminary stability value, are the weight coefficients of a, b, c, and d respectively, Δ is the target device constant, and its numerical value can represent the gap between the stability of the target device and the stability of this type of device in the big data. n is the number of times passing the preliminary stability assessment before, Z i+1 is the preliminary stability value of the (i + 1)-th time passing the preliminary stability assessment, Z i is the preliminary stability value of the i-th time passing the stability assessment, λ i is Z i+1 and Z iThe weight coefficient of the difference is set by the technical staff, and K is the big data evaluation value;

[0107] It should be noted that It is set by the technical staff in combination with the actual situation of the company, and The sum is 1. For example, set to 0.2, set to 0.5, set to 0.2, set to 0.1, which means the company attaches the most importance to start-stop data, relatively attaches importance to energy consumption data, and attaches the least importance to maintenance data and consumable data.

[0108] In addition, according to the data records of multiple trial runs of the equipment installation, when the equipment runs at a stable level acceptable to the company (which may be affected by factors other than the company's equipment), the K value calculated by obtaining the operating data at this time is used, and then the value obtained by subtracting the K value from 0.5 is the Δ value. The larger the Δ, the greater the gap in the operating stability between the company's equipment and the equipment recorded in the big data (which may be affected by negative factors other than the company's equipment, such as poor power supply stability of the local power supply bureau, etc.). When Δ is negative, it means that the operating stability of the company's equipment is better than that of the equipment recorded in the big data (which may be affected by positive factors other than the company's equipment, such as more perfect technology of the company's technical staff, etc.).

[0109] B3: When Z ≥ 0.5, it is determined that the equipment passes the preliminary stability assessment; otherwise, it fails the preliminary stability assessment. The preliminary stability value that passed the stability assessment before can be brought into the calculation of this preliminary stability assessment, so as to use the historical stability situation of the equipment as a comparison reference, improve the accuracy of the preliminary stability assessment, and can increase or decrease the standard of the preliminary stability assessment of the target equipment according to the actual situation, reduce the dependence on big data, and combine the situation of the equipment itself to make the preliminary stability assessment more practical.

[0110] It should be noted that for the convenience of understanding, the following simulated data is set:

[0111] Set to 0.2, set to 0.5, set to 0.2, set to 0.1;

[0112] Set a to 50%, set b to 40%, set c to 60%, set d to 40%;

[0113] Set Δ to 0.06;

[0114] Set n to 5;

[0115] The preliminary stability values for the first five times passing the preliminary stability assessment are 0.52, 0.54, 0.53, 0.58, and 0.58 respectively. For the convenience of calculating λ i They are all set to 1, indicating that the importance attached to each difference is the same.

[0116] Substitute into the calculation formula:

[0117]

[0118]

[0119] The value of K is obtained as 0.46, and the value of Z is 0.50. At this time, Z is equal to 0.5. Therefore, it is determined that the current data has passed the preliminary stability assessment.

[0120] It should be noted that Δ is a positive number, representing the stability of this device during installation and trial operation. Compared with the stability that this device should have in the big data, it is relatively poor, indicating that the device is affected by external factors. Since the preliminary stability values for the first five times passing the preliminary stability assessment are 0.52, 0.54, 0.53, 0.58, and 0.58 respectively, the value of in the formula is calculated as 0.06. It can be seen that the preliminary stability values of the device for the first five times passing the preliminary stability assessment show an upward trend, which means that the amplitude of the influence of external factors on the device is decreasing. Therefore, subtracting 0.06 when calculating the Z value can improve the standard of the preliminary stability assessment of the device. Thus, when conducting the preliminary stability assessment of the device, the assessment standard can be continuously optimized according to the previous historical data, fully considering the gap between this device and the devices in the big data, reducing the dependence on the big data, and combining the actual situation of the device, making the preliminary stability assessment more valuable in practice.

[0121] Example 2:

[0122] As Figure 5 shown, when conducting the preliminary stability assessment, when the device can affect environmental factors:

[0123] The data used also includes the environmental protection coefficient H. When the device meets the environmental protection requirements, the value of H is 1, and when the device does not meet the environmental protection requirements, the value of H is 0. The calculation formula for the preliminary stability value is:

[0124]

[0125]

[0126] where Z is the preliminary stability value, The weight coefficients are a, b, c, and d respectively, Δ is the local device constant, n is the number of times of passing the preliminary stability assessment before, and Z i+1 is the preliminary stability value of the first i + 1 times of passing the preliminary stability assessment, and Z i is the preliminary stability value of the first i times of passing the stability assessment, and λ i is the weight coefficient of the difference between Z i+1 and Z i , which is set by the technical staff. K is the big data evaluation value, representing the recognition of the equipment stability by big data. The environmental coefficient H is included in the calculation of the preliminary stability value and is used as a prerequisite for the preliminary stability assessment of the current data, which is conducive to avoiding environmental risks and meeting the requirements of laws and regulations.

[0127] It should be noted that the environmental protection coefficient H is obtained by sensor detection. First, query the emission standards of the equipment according to local laws and regulations and the company's rules and regulations, and then set the parameters of various sensors at the emission detection point of the equipment according to the parameters of the purification system. When it is detected that the pollutants exceed the standard, it is determined that the value of the environmental protection coefficient H is 0, otherwise it is 1.

[0128] It should be noted that for the convenience of understanding, the following simulated data are set:

[0129] The environmental protection coefficient H is 0;

[0130] Set to 0.2, set to 0.5, set to 0.2, set to 0.1;

[0131] Set a to 60%, set b to 70%, set c to 50%, and set d to 60%;

[0132] Set Δ to 0.02;

[0133] Set n to 5;

[0134] The preliminary stability values of the first five times of passing the preliminary stability assessment are 0.64, 0.68, 0.67, 0.66, and 0.64 respectively. For the convenience of calculating λ i are all set to 1, representing the same degree of attention to each difference;

[0135] Substitute into the calculation formula:

[0136]

[0137]

[0138] The value of K is 0.63 and the value of Z is 0. At this time, the Z value is less than 0.5, so it is determined that the current data has passed the preliminary stability assessment.

[0139] Although the K value is large, meeting the recognition of the equipment stability by big data, since the pollutant emissions of the equipment exceed the allowable standards of the company or local regulations, it is directly determined that it fails the preliminary stability assessment. The environmental coefficient H is included in the calculation of the preliminary stability value and is used as a prerequisite for the preliminary stability assessment of the current data, which is beneficial to avoiding environmental risks and meeting the requirements of laws and regulations.

[0140] It should be noted that for Embodiment 1 and Embodiment 2, they can be applied simultaneously during the dynamic adjustment process. For example, when equipment X1 is in operation, it will discharge sewage, while equipment X2, equipment X3, and equipment X4 will not have an impact on the environment. Then, the calculation method of Embodiment 2 can be used for equipment X1, and the calculation method of Embodiment 1 can be used for equipment X2, equipment X3, and equipment X4, and the preliminary stability assessment is carried out separately.

[0141] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended embodiments and their equivalents.

Claims

1. An intelligent parameter control method for optimizing the wear-resistant coating cladding process, characterized in that: The method comprises: Establish a database, mark the variable parameter values ​​of each device, calibrate the associated parameter items of each device to its connected devices, and perform laser cladding operations according to the database; Obtain production demand data and adjust corresponding parameter values ​​of corresponding equipment according to preliminary adjustment methods; When the corresponding parameter value of the corresponding equipment changes, the remaining parameter values ​​of the corresponding equipment and multiple parameter values ​​of related equipment are dynamically adjusted based on the dynamic control method. During the production process, the parameters of the equipment are continuously adjusted according to the production demand data until the production demand data is met. The parameter change data in the continuous adjustment process can be recorded, which is convenient for direct call when the same production demand data is generated later. The dynamic control method can be continuously optimized, thereby improving production efficiency; The dynamic control method comprises: S1: Adjust the remaining variable parameter values ​​of the corresponding device, obtain feedback data information, and adjust the variable parameter values ​​according to the marking adjustment method; S2: Obtain the changed parameter items of the corresponding equipment, and compare the associated parameter items to determine the related equipment that needs to adjust the parameters; S3: changing the variable parameter items of the relevant equipment determined in step S2, obtaining feedback data information, and adjusting the variable parameter values ​​according to the marking adjustment method; S4: taking the device whose parameters are changed in step S3 as the new corresponding device object, repeating steps S2 and S3 until there is no new corresponding device object; After the parameters are adjusted, the stability of the current data is evaluated using the stability evaluation method; After the stability assessment, the stable operating parameters of the equipment under this demand are recorded and entered into the database; when the production demand data recurs again, the stable operating parameters of the equipment under this demand are directly called.

2. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 1 is characterized in that: The stability assessment method comprises: L1: Obtain device usage data and divide the usage data into several groups according to time periods; L2: For each device, stability calculations are performed on different groups separately using the stability calculation method to obtain a preliminary stability assessment; L3: Compare the preliminary stability evaluation results of the same group of different devices. When several consecutive groups of the same group of different devices pass the preliminary stability evaluation, the current data is judged to have passed the stability evaluation. This can exclude the situation where the device fails to pass the stability evaluation due to the influence of external factors during the time period of several groups, thereby improving the accuracy of the stability evaluation. When several consecutive groups of the same group of different devices do not pass the preliminary stability evaluation, the current data is judged to have failed the stability evaluation. L4: When the stability assessment fails, the corresponding equipment is selected from the group with the largest number of equipment that failed the preliminary stability assessment, and the variable parameter values ​​are re-adjusted through the dynamic control method. After the parameters of the equipment in the target group that failed the preliminary stability assessment are adjusted, the stability assessment method is repeated again until the current data passes the stability assessment and the data is recorded. The adjusted parameters can be continuously optimized, and the corresponding equipment is selected from the group with the largest number of equipment that failed the preliminary stability assessment for adjustment. This can cover as many unstable parameters as possible, reduce the number of adjustments, and further improve the adjustment speed.

3. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 2 is characterized in that: The stability calculation method comprises: B1: Collect and organize equipment usage data, including energy consumption data, start-stop data, maintenance data and consumables data. Obtain the percentage scores of a, b, c, d for energy consumption data, start-stop data, maintenance data and consumables data through big data; B2: Calculate the preliminary stability value again according to the formula: Where Z is the initial stability value, are the weight coefficients of a, b, c, and d respectively. Δ is the target device constant, and its value can represent the difference between the stability of the target device and the stability of the device in the big data. n is the number of times the preliminary stability assessment has been passed before. Z i+1 is the initial stability value of the first i+1 passes of the initial stability assessment, Z i is the initial stable value of the stability evaluation in the previous i times, λ i Z i+1 With Z i The weight coefficient of the difference is set by the technicians, K is the big data evaluation value, which represents the recognition of the equipment stability by big data; B3: When Z ≥ 0.5, the device is judged to have passed the preliminary stability assessment, otherwise it has not passed the preliminary stability assessment. The preliminary stability value that has passed the stability assessment before can be brought into the calculation of this preliminary stability assessment, so that the historical stability of the device can be used as a comparative reference to improve the accuracy of the preliminary stability assessment. In addition, the standard of the preliminary stability assessment of the target device can be increased or decreased according to the actual situation, reducing the dependence on big data. Combined with the device's own situation, the preliminary stability assessment has more practical value.

4. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 3 is characterized in that: The usage data also includes an environmental protection coefficient H. When the equipment meets the environmental protection requirements, the value of H is 1, and when the equipment does not meet the environmental protection requirements, the value of H is 0. The calculation formula for the preliminary stability value is: Where Z is the initial stability value, are the weight coefficients of a, b, c, and d, Δ is the local device constant, n is the number of times the preliminary stability assessment has been passed, and Z i+1 is the initial stability value of the first i+1 passes of the initial stability assessment, Z i is the initial stable value of the stability evaluation in the previous i times, λ i Z i+1 With Z i The weight coefficient of the difference is set by technical personnel, K is the big data evaluation value, which represents the recognition of big data on the stability of the equipment. The environmental factor H is included in the calculation of the preliminary stability value and used as a prerequisite for the preliminary stability assessment of the current data, which is conducive to avoiding environmental risks and meeting the requirements of laws and regulations.

5. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 1 is characterized in that: During the adjustment process of the dynamic control method, feedback data of the device with specific parameters as non-associated parameter items is obtained. If the feedback data is abnormal, the specific parameters are recalibrated as associated parameter items between the corresponding device and the device, and the parameter changes of the device with associated parameter items with the corresponding device during multiple adjustment processes are recorded. When the parameters have not changed, the associated parameter items are released, the database information is updated, and the calibration accuracy of the associated parameter items is continuously improved, thereby optimizing the adjustment speed of the dynamic control method for the variable parameter values.

6. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 1 is characterized in that: The marking adjustment method is: N1: Adjust the variable parameter value and the corresponding parameter value in a positive or negative correlation, obtain real-time feedback data, and determine the direction of parameter change based on the change of feedback data; N2: Record the direction of parameter change and mark the target parameter value and the corresponding parameter value as positively correlated, negatively correlated, and uncorrelated; N3: When the same variable parameter value and corresponding parameter value are used as adjustment targets again, the adjustment speed can be increased according to the mark in N2.

7. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 1 is characterized in that: The initial adjustment method is: E1: Establish a demand classification menu containing various demand types for technicians to choose from, match the equipment with each category in the demand classification set, and match the adjustable parameter value of each equipment with each category in the demand classification set; E2: According to the requirement classification selected by the technician, select the corresponding variable parameter values ​​of the corresponding equipment and the target equipment; E3: Establish a secondary quantitative menu, and the technicians can quantify the demand types of the previous level; E4: Continuously adjust the selected adjustable parameter value according to the change set in E3, and obtain the result feedback data. When the feedback data matches the quantitative value item of the demand type, stop adjusting the adjustable parameter value, classify and quantify the production demand data, clarify the adjustment target, and improve the adjustment efficiency.

8. The intelligent parameter control method for optimizing the wear-resistant coating cladding process according to claim 7 is characterized in that: The demand classification menu can be edited. During the adjustment process, when the result feedback data is abnormal, the current demand classification menu item is marked and the technician is notified to make corrections. It can perform self-detection in time to prevent errors when the technician selects the demand type, and can continuously optimize the matching between the demand type and the equipment, as well as the demand type and the variable parameter value.

9. An intelligent parameter control system for optimizing the wear-resistant coating cladding process, characterized in that: An intelligent parameter control method for optimizing the wear-resistant coating cladding process as described in any one of claims 1 to 8 is used.

Images