Intelligent remote control system and method applied to laminating machine

Abstract

The invention relates to the technical field of laminating machine control, in particular to an intelligent remote control system and method applied to a laminating machine, and the intelligent remote control system comprises a data module, a model building module and an output module. According to the method, the cycle index of idle running in the self-checking link after each shutdown is extracted and analyzed, the final shutdown time length range output corresponding to the cycle index of each idle running is output, the end point of the previous shutdown time length range is used as the starting point of the next shutdown time length range, and the shutdown time length of the next shutdown time length range is calculated. According to the method, the shutdown duration ranges corresponding to different cycle times are obtained, the shutdown duration ranges are used as input, the cycle times of empty engine operation are used as output, the model is trained, the cycle times training model is obtained to accurately control the cycle times of empty engine operation, and resource waste is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of laminating machine control, and in particular to an intelligent remote control system and method applied to a laminating machine. Background Art

[0002] As the core of the green energy field in today's world, the photovoltaic industry has been receiving global attention for its development speed and technological progress. In particular, in the manufacturing process of photovoltaic modules, lamination technology plays a vital role. In this key link, how to achieve more efficient, accurate and stable automated production has become a key factor restricting the production efficiency and quality of photovoltaic modules.

[0003] After the laminator has been shut down for a period of time, do not put in the product before the formal lamination. Run the machine empty for a few cycles first to ensure that all parameters are correct after the laminator self-checks and the water vapor adsorbed in the machine is removed before it can be used normally. However, in the current existing technology, the number of cycles of empty machine operation is manually set by workers based on experience, without accurate data analysis, and because the product cannot be processed when the machine is empty, each additional empty machine operation wastes a lot of resources. Therefore, how to accurately control the number of cycles of empty machine operation is a technical problem that must be solved. Summary of the invention

[0004] The object of the present invention is to provide an intelligent remote control system and method for a laminator to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions: an intelligent remote control system applied to a laminator, the intelligent remote control system comprising a data module, a model building module and an output module;

[0006] The data module is used to collect historical processing data of the laminator to form a historical database, and to extract historical downtime data of the laminator to obtain the downtime duration corresponding to each downtime event;

[0007] The model building module is used to obtain the number of cycles of the laminator running idle during the self-checking process, and the downtime duration corresponding to the downtime event to form chain link information, and build a cycle number training model according to the chain link information;

[0008] The output module is used to input the current downtime of the laminator into the cycle number training model, output the number of cycles of idle machine operation required before formal lamination, and recommend it to the user terminal;

[0009] The output end of the data module is electrically connected to the input end of the model building module, and the output end of the model building module is electrically connected to the input end of the output module.

[0010] Furthermore, the data module includes a downtime data unit and a downtime duration unit; the downtime data unit is used to obtain all downtime events in the historical records to form downtime data; the downtime duration unit is used to obtain the downtime duration corresponding to each downtime event, and extract all downtime duration data into a collection.

[0011] Furthermore, the model building module includes a self-check unit, a processing unit, a chain unit, a data analysis unit and a model building unit; the self-check unit is used to mark the period from the normal start of the laminator to the formal lamination as a self-check link, and obtain the number of cycles of the laminator's idling operation in the self-check link; the processing unit is used to mark the period from the formal lamination to the equipment shutdown of the laminator as a processing link, and obtain a target processing time period for the processing link, the target processing time period being the period from the formal lamination of the laminator to the appearance of the first lamination result qualified product, if there is a target event of unqualified lamination result in the target processing time period, the processing link is marked as an abnormal processing link, if there is no target event of unqualified lamination result in the target processing time period, the processing link is marked as an abnormal processing link, If a qualified target event is found, the processing link is marked as a normal processing link; the chain division unit is used to match the shutdown event corresponding to the self-check link before the self-check link and the processing link corresponding to the self-check link one by one to form a chain link event, and extract the chain link information of the chain link event, wherein the chain link information includes the shutdown duration and the number of cycles of the idle machine operation; the data analysis unit is used to extract the chain link events with the same number of cycles of the idle machine operation in the chain link information into the same set to form a first subset, extract the chain link events whose processing links in the first subset are normal processing links into the second subset, mark the chain link events in the second subset in the first coordinate system, and mark each chain link event as a chain node to obtain Take the two chain nodes with the farthest distance as two endpoints, mark them as target time periods, and use the target time period as the initial downtime duration range corresponding to the number of cycles of the idle machine operation; mark the chain link events in the first subset in the second coordinate system, divide the initial downtime duration range into several time intervals T, obtain the total number I of normal chain nodes and the total number J of abnormal chain nodes in each time interval T, calculate the abnormal proportion W in each time interval T, W=J / I+J, if W is greater than the W threshold, then eliminate the time range corresponding to the time interval, regenerate a new downtime duration range for the remaining time intervals, and output the new downtime duration range as the final downtime duration range; the model building unit The number of cycles for extracting idle operation is N, N+1, N+2, N+3..., and the final downtime duration range corresponding to the N number of cycles of idle operation is obtained as [t1, t2]. The t2 time point is used as the starting point of the downtime duration corresponding to the N+1 number of cycles of idle operation, and the downtime duration range corresponding to the N+1 number of cycles of idle operation is obtained as [t2, t3]. Similarly, the end point of the previous downtime duration range is used as the starting point of the next downtime duration range, so as to obtain the downtime duration ranges corresponding to different numbers of cycles, and the downtime duration range is used as input and the number of cycles of idle operation as output to train the model and obtain a cycle number training model.

[0012] An intelligent remote control method for a laminator is applied to an intelligent remote control system for a laminator, and the intelligent remote control method comprises the following steps:

[0013] Step S1, according to the historical processing data of the laminator, the historical shutdown data of the laminator is obtained, the shutdown of the laminator until the next normal start is marked as a shutdown event, and the shutdown duration corresponding to each shutdown event is extracted;

[0014] Step S2, mark the period from the normal start of the laminator to the formal lamination as the self-checking stage, mark the period from the formal lamination to the equipment shutdown as the processing stage, form chain link events with the corresponding shutdown events, self-checking stages and processing stages, obtain the number of cycles of the laminator running idle during the self-checking stage, and the shutdown duration corresponding to the shutdown event to form chain link information, and construct a cycle number training model based on the chain link information;

[0015] Step S3: According to the current downtime of the laminator, the model is trained by the number of cycles, and the number of cycles of idle operation required before formal lamination is output and recommended to the user terminal.

[0016] Furthermore, the step S1 includes:

[0017] Mark the period from the shutdown of the laminator to the next normal startup as a shutdown event, obtain all the shutdown events in the historical records, and form a set A, A = {a 1 , a 2 , a 3 ,......a n}, where a 1 , a 2 , a 3 ,......,a n It represents the first shutdown event, the second shutdown event, the third shutdown event, ..., the nth shutdown event in sequence;

[0018] The downtime duration of each downtime event is marked as s, and all downtime duration data are extracted to form a set S, where S = {s 1 ,s 2 ,s 3 ,......s n}, where s 1 ,s 2 ,s 3 ,......s n It represents the downtime duration of the first downtime event, the downtime duration of the second downtime event, the downtime duration of the third downtime event, ..., the downtime duration of the nth downtime event in sequence.

[0019] Furthermore, the step S2 includes:

[0020] Step S201, marking the period from the normal start of the laminator to the formal lamination as a self-checking phase, and obtaining the number of cycles of the laminator running idle in the self-checking phase;

[0021] Step S202, marking the laminator from formal lamination to equipment shutdown as a processing link, obtaining a target processing time period for the processing link, the target processing time period being the time period from the formal lamination of the laminator until the first lamination result qualified product appears, if there is a target event of unqualified lamination result in the target processing time period, then the processing link is marked as an abnormal processing link, if there is no target event of unqualified lamination result in the target processing time period, then the processing link is marked as a normal processing link;

[0022] Step S203, the shutdown event corresponding to the self-checking link before the self-checking link and the processing link corresponding to the self-checking link after the self-checking link are matched one by one to form a chain link event, and the chain link information of the chain link event is extracted, and the chain link information includes the shutdown duration and the number of cycles of the idle machine operation;

[0023] Step S204, extract the chain link events with the same number of cycles of idle machine operation in the chain link information into the same set to form a first subset, extract the chain link events whose processing links are normal processing links in the first subset into a second subset, establish a first coordinate system, take the downtime as the x-axis, take the number of cycles of idle machine operation as the y-axis, mark the chain link events in the second subset in the first coordinate system, mark each chain link event as a chain node, obtain the two chain nodes with the farthest distance as two endpoints, mark them as a target time period, and use the target time period as the initial downtime range corresponding to the number of cycles of the idle machine operation;

[0024] Step S205, establish a second coordinate system, take the downtime as the x-axis, take the number of cycles of idle operation as the y-axis, mark the link events in the first subset in the second coordinate system, extract all link events within the initial downtime range, mark the link events of normal processing links as normal chain nodes, mark the link events of abnormal processing links as abnormal chain nodes, divide the initial downtime range into several time intervals T, obtain the total number of normal chain nodes I and the total number of abnormal chain nodes J in each time interval T, calculate the abnormal proportion W in each time interval T, W = J / I + J, if W is greater than W 阈值 , then the time range corresponding to the time interval is removed, and the remaining time intervals are used to regenerate a new downtime duration range, which is output as the final downtime duration range;

[0025] Step S206, extract the number of cycles of idle operation as N, N+1, N+2, N+3..., obtain the final downtime range corresponding to the number of cycles of N idle operation as [t1, t2] through steps S201-S205, take the time point t2 as the starting point of the downtime corresponding to the number of cycles of N+1 idle operation, repeat the above steps S201-S205, and obtain the downtime range corresponding to the number of cycles of N+1 idle operation as [t2, t3]; and so on, take the end point of the previous downtime range as the starting point of the next downtime range, so as to obtain the downtime ranges corresponding to different numbers of cycles;

[0026] Step S207, taking the downtime duration range as input and the number of cycles of idling operation as output, training the model to obtain a cycle number training model.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention extracts the number of cycles of idle machine operation performed in the self-check link after each shutdown, analyzes it, outputs the final shutdown time range corresponding to the number of cycles of each idle machine operation, and uses the end point of the previous shutdown time range as the starting point of the next shutdown time range, so as to obtain the shutdown time range corresponding to different cycle numbers, uses the shutdown time range as input, and the number of cycles of idle machine operation as output, and trains the model. After obtaining the cycle number training model, the corresponding number of cycles of idle machine operation can be output according to the shutdown time of the current laminator, so as to achieve the purpose of accurately controlling the number of cycles of idle machine operation, and reduce the waste of resources caused by idle machine operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The figure is a schematic structural diagram of an intelligent remote control system applied to a laminating machine according to the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] Embodiment 1: Figure 1 As shown, the present invention provides an intelligent remote control system applied to a laminator, the intelligent remote control system includes a data module, a model building module and an output module;

[0032] The data module is used to collect historical processing data of the laminator to form a historical database, and to extract historical downtime data of the laminator to obtain the downtime duration corresponding to each downtime event;

[0033] The output end of the data module is electrically connected to the input end of the model building module, and the output end of the model building module is electrically connected to the input end of the output module.

[0034] Among them, the data module includes a shutdown data unit and a shutdown duration unit; the shutdown data unit is used to obtain all shutdown events in the historical records to form shutdown data; the shutdown duration unit is used to obtain the shutdown duration corresponding to each shutdown event, and extract all shutdown duration data into a collection; the output module is used to input the current shutdown duration of the laminator into the cycle number training model, output the number of cycles of idle machine operation required before formal lamination, and recommend it to the user terminal; the model building module is used to obtain the number of cycles of idle machine operation of the laminator during the self-inspection link, and the shutdown duration corresponding to the shutdown event to form chain link information, and build a cycle number training model based on the chain link information.

[0035] Specifically, the model building module includes a self-check unit, a processing unit, a chain unit, a data analysis unit and a model building unit; the self-check unit is used to mark the period from the normal start of the laminator to the formal lamination as a self-check link, and obtain the number of cycles of the laminator running idle in the self-check link; the processing unit is used to mark the period from the formal lamination to the equipment shutdown of the laminator as a processing link, and obtain the target processing time period of the processing link. The target processing time period is the time period from the formal lamination of the laminator to the appearance of the first qualified lamination result product. If there is a target event of unqualified lamination result in the target processing time period, the processing link is marked as an abnormal processing link. If there is no target event of unqualified lamination result in the target processing time period, the processing link is marked as an abnormal processing link. If a target event of the grid is found, the processing link is marked as a normal processing link; the chain division unit is used to correspond the shutdown event corresponding to the self-check link before the self-check link and the processing link corresponding to the self-check link one by one to form a chain link event, and extract the chain link information of the chain link event, and the chain link information includes the shutdown duration and the number of cycles of the idle machine operation; the data analysis unit is used to extract the chain link events with the same number of cycles of the idle machine operation in the chain link information into the same set to form a first subset, extract the chain link events whose processing links in the first subset are normal processing links into the second subset, mark the chain link events in the second subset in the first coordinate system, and mark each chain link event as a chain node to obtain The two chain nodes with the farthest distance are taken as two endpoints, marked as the target time period, and the target time period is taken as the initial downtime duration range corresponding to the number of cycles of the idle machine operation; the chain link events in the first subset are marked in the second coordinate system, and the initial downtime duration range is divided into a number of time intervals T, and the total number I of normal chain nodes and the total number J of abnormal chain nodes in each time interval T are obtained, and the abnormal proportion W in each time interval T is calculated, W=J / I+J, if W is greater than the W threshold, then the time range corresponding to the time interval is eliminated, and the remaining time intervals are regenerated into a new downtime duration range, and the new downtime duration range is output as the final downtime duration range; the model construction unit The number of cycles for extracting idle operation is N, N+1, N+2, N+3..., and the final downtime duration range corresponding to the N number of cycles of idle operation is obtained as [t1, t2]. The t2 time point is used as the starting point of the downtime duration corresponding to the N+1 number of cycles of idle operation, and the downtime duration range corresponding to the N+1 number of cycles of idle operation is obtained as [t2, t3]. Similarly, the end point of the previous downtime duration range is used as the starting point of the next downtime duration range, so as to obtain the downtime duration ranges corresponding to different numbers of cycles, and the downtime duration range is used as input and the number of cycles of idle operation as output to train the model and obtain a cycle number training model.

[0036] Embodiment 2, an intelligent remote control method applied to a laminator, which is applied to an intelligent remote control system applied to a laminator, the intelligent remote control method comprises the following steps:

[0037] Step S1, according to the historical processing data of the laminator, the historical shutdown data of the laminator is obtained, the shutdown of the laminator until the next normal start is marked as a shutdown event, and the shutdown duration corresponding to each shutdown event is extracted;

[0038] The step S1 comprises:

[0039] Mark the period from the shutdown of the laminator to the next normal startup as a shutdown event, obtain all the shutdown events in the historical records, and form a set A, A = {a 1 , a 2 , a 3 ,......a n}, where a 1 , a 2 , a 3 ,......,a n It represents the first shutdown event, the second shutdown event, the third shutdown event, ..., the nth shutdown event in sequence;

[0040] The downtime duration of each downtime event is marked as s, and all downtime duration data are extracted to form a set S, where S = {s 1 ,s 2 ,s 3 ,......s n}, where s 1 ,s 2 ,s 3 ,......s n It represents the downtime duration of the first downtime event, the downtime duration of the second downtime event, the downtime duration of the third downtime event, ..., the downtime duration of the nth downtime event in sequence.

[0041] For example, the downtime duration of the first downtime event is recorded as s1, and the downtime duration of the second downtime event is recorded as s2, and all downtime events of the laminator are obtained to form downtime data. In order to ensure the data volume of the downtime events, the downtime events of all laminators of the same model can be retrieved and used.

[0042] Step S2, mark the period from the normal start of the laminator to the formal lamination as the self-checking stage, mark the period from the formal lamination to the equipment shutdown as the processing stage, form chain link events with the corresponding shutdown events, self-checking stages and processing stages, obtain the number of cycles of the laminator running idle during the self-checking stage, and the shutdown duration corresponding to the shutdown event to form chain link information, and construct a cycle number training model based on the chain link information;

[0043] The step S2 comprises:

[0044] Step S201, marking the period from the normal start of the laminator to the formal lamination as a self-checking phase, and obtaining the number of cycles of the laminator running idle in the self-checking phase;

[0045] Step S202, marking the laminator from formal lamination to equipment shutdown as a processing link, obtaining a target processing time period for the processing link, the target processing time period being the time period from the formal lamination of the laminator until the first lamination result qualified product appears, if there is a target event of unqualified lamination result in the target processing time period, then the processing link is marked as an abnormal processing link, if there is no target event of unqualified lamination result in the target processing time period, then the processing link is marked as a normal processing link;

[0046] Step S203, the shutdown event corresponding to the self-checking link before the self-checking link and the processing link corresponding to the self-checking link after the self-checking link are matched one by one to form a chain link event, and the chain link information of the chain link event is extracted, and the chain link information includes the shutdown duration and the number of cycles of the idle machine operation;

[0047] Step S204, extract the chain link events with the same number of cycles of idle machine operation in the chain link information into the same set to form a first subset, extract the chain link events whose processing links are normal processing links in the first subset into a second subset, establish a first coordinate system, take the downtime as the x-axis, take the number of cycles of idle machine operation as the y-axis, mark the chain link events in the second subset in the first coordinate system, mark each chain link event as a chain node, obtain the two chain nodes with the farthest distance as two endpoints, mark them as a target time period, and use the target time period as the initial downtime range corresponding to the number of cycles of the idle machine operation;

[0048] Step S205, establish a second coordinate system, take the downtime as the x-axis, take the number of cycles of idle operation as the y-axis, mark the link events in the first subset in the second coordinate system, extract all link events within the initial downtime range, mark the link events of normal processing links as normal chain nodes, mark the link events of abnormal processing links as abnormal chain nodes, divide the initial downtime range into several time intervals T, obtain the total number of normal chain nodes I and the total number of abnormal chain nodes J in each time interval T, calculate the abnormal proportion W in each time interval T, W = J / I + J, if W is greater than W 阈值 , W 阈值 If it can be set fixedly, the time range corresponding to the time interval will be removed, and the remaining time intervals will be used to regenerate a new downtime duration range, which will be output as the final downtime duration range;

[0049] Step S206, extract the number of cycles of idle operation as N, N+1, N+2, N+3..., obtain the final downtime range corresponding to the number of cycles of N idle operation as [t1, t2] through steps S201-S205, take the time point t2 as the starting point of the downtime corresponding to the number of cycles of N+1 idle operation, repeat the above steps S201-S205, and obtain the downtime range corresponding to the number of cycles of N+1 idle operation as [t2, t3]; and so on, take the end point of the previous downtime range as the starting point of the next downtime range, so as to obtain the downtime ranges corresponding to different numbers of cycles;

[0050] Step S207, taking the downtime duration range as input and the number of cycles of idling operation as output, training the model to obtain a cycle number training model.

[0051] For example, in the historical data, all self-check links with a cycle number of 1 for idle machine operation are obtained, and the preceding shutdown events corresponding to the self-check link are extracted, such as the first shutdown event, the second shutdown event, the third shutdown event..., and the shutdown duration corresponding to the shutdown event is obtained to form a first subset, and then the processing link that each shutdown event in the first subset undergoes after the self-check link is obtained. If there is no unqualified lamination product before the first product with a qualified lamination result in the processing link, then the processing link is marked as a normal processing link. If the first product in the processing link has a qualified lamination result, then the processing link is marked as a normal processing link. If the product is an unqualified lamination product, the processing link is marked as an abnormal processing link, and the downtime duration in the downtime event corresponding to the normal processing link is extracted into the second subset. After the first marking is established, the downtime duration is used as the x-axis, and the x-axis can be used as the time axis. The downtime duration in the second subset is marked on the time axis, and the two farthest time points on the time axis are obtained as two endpoints to form a target time period [t1, t2]. A time interval T is set, and the target time period is divided into several time intervals T. The abnormal proportion in each time interval T is calculated. If the abnormal proportion W is greater than W 阈值, it means that when the downtime includes the time interval T, the probability of the first product lamination result being unqualified when the number of cycles of the idle machine operation is 1 is relatively high. For example, if the interval is 1 hour and the downtime is from the 8th hour to the 9th hour, if only one idle machine operation is performed, the lamination result of the first product during formal lamination is very likely to be unqualified. Therefore, when the downtime is between the 8th hour and the 9th hour, it is not recommended to run the empty machine for only one cycle. Then, the time interval of 8-9 hours is eliminated, and the remaining time intervals are combined to form a new downtime range of 0-7. The number of cycles of the empty machine operation When it is 1, the corresponding final downtime duration range is 0-7 hours. The 7th hour is taken as the starting point of the downtime duration range when the number of cycles of idle operation is 2. Through the above steps, it can be obtained that when the number of cycles of idle operation is 2, the corresponding final downtime duration range is 7-15 hours. By analogy, the number of cycles of idle operation is 3, 4, 5, 6..., and the corresponding downtime duration range is obtained. The obtained number of cycles of idle operation and its corresponding downtime duration range are formed into a one-to-one corresponding data group, which is input into the training model for training to obtain a cycle number training model.

[0052] Step S3: According to the current downtime of the laminator, the model is trained by the number of cycles, and the number of cycles of idle operation required before formal lamination is output and recommended to the user terminal.

[0053] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An intelligent remote control system for a laminator, characterized in that: The intelligent remote control system includes a data module, a model building module and an output module; The data module is used to collect historical processing data of the laminator to form a historical database, and to extract historical downtime data of the laminator to obtain the downtime duration corresponding to each downtime event; The model building module is used to obtain the number of cycles of the laminator running idle during the self-checking process, and the downtime duration corresponding to the downtime event to form chain link information, and build a cycle number training model according to the chain link information; The output module is used to input the current downtime of the laminator into the cycle number training model, output the number of cycles of idle machine operation required before formal lamination, and recommend it to the user terminal; The output end of the data module is electrically connected to the input end of the model building module, and the output end of the model building module is electrically connected to the input end of the output module.

2. According to claim 1, an intelligent remote control system for a laminator is characterized in that: The data module includes a downtime data unit and a downtime duration unit; the downtime data unit is used to obtain all downtime events in the historical records to form downtime data; the downtime duration unit is used to obtain the downtime duration corresponding to each downtime event, and extract all downtime duration data into a collection.

3. The intelligent remote control system for a laminator according to claim 1, characterized in that: The model building module includes a self-checking unit, a processing unit, a chain unit, a data analysis unit and a model building unit; the self-checking unit is used to mark the period from the normal start of the laminator to the formal lamination as a self-checking link, and obtain the number of cycles of the laminator running idle in the self-checking link; the processing unit is used to mark the period from the formal lamination to the equipment shutdown of the laminator as a processing link, and obtain the target processing time period of the processing link. The target processing time period is the time period from the formal lamination of the laminator to the appearance of the first qualified lamination result product. If there is a target event of unqualified lamination results in the target processing time period, the processing link is marked as abnormal. If there is no target event of unqualified lamination results in the target processing period, the processing link is marked as a normal processing link; the chain division unit is used to correspond the shutdown event corresponding to the self-check link before the self-check link and the processing link corresponding to the self-check link one by one to form a chain link event, and extract the chain link information of the chain link event, and the chain link information includes the shutdown time and the number of cycles of the idle machine operation; the data analysis unit is used to extract the chain link events with the same number of cycles of the idle machine operation in the chain link information into the same set to form a first subset, and extract the chain link events whose processing links in the first subset are normal processing links into the second subset. In the second subset, the link events in the second subset are marked in the first coordinate system, each link event is marked as a chain node, the two chain nodes with the farthest distance are obtained as two endpoints, marked as the target time period, and the target time period is used as the initial downtime range corresponding to the number of cycles of the idle machine operation; the link events in the first subset are marked in the second coordinate system, the initial downtime range is divided into several time intervals T, the total number of normal chain nodes I and the total number of abnormal chain nodes J in each time interval T are obtained, and the abnormal proportion W in each time interval T is calculated, W = J / I + J, if W is greater than W Threshold, then the time range corresponding to the time interval is eliminated, and the remaining time intervals are regenerated into a new downtime range, and the new downtime range is output as the final downtime range; the model building unit is used to extract the number of cycles of idle operation as N, N+1, N+2, N+3..., and the final downtime range corresponding to the number of cycles of N idle operation is obtained as [t1, t2], and the t2 time point is used as the starting point of the downtime corresponding to the number of cycles of N+1 idle operation, and the downtime range corresponding to the number of cycles of N+1 idle operation is obtained as [t2, t3]; Similarly, the end point of the previous downtime range is used as the starting point of the next downtime range, so as to obtain the downtime range corresponding to different numbers of cycles. The downtime range is used as input and the number of cycles of idle operation is used as output to train the model and obtain a cycle number training model.

4. An intelligent remote control method for a laminator, applied to an intelligent remote control system for a laminator as claimed in any one of claims 1 to 3, characterized in that: The intelligent remote control method comprises the following steps: Step S1, according to the historical processing data of the laminator, the historical shutdown data of the laminator is obtained, the shutdown of the laminator until the next normal start is marked as a shutdown event, and the shutdown duration corresponding to each shutdown event is extracted; Step S2, mark the period from the normal start of the laminator to the formal lamination as the self-checking link, mark the period from the formal lamination to the equipment shutdown as the processing link, form chain link events with the corresponding shutdown events, self-checking links and processing links, obtain the number of cycles of the laminator running idle during the self-checking link, and the shutdown duration corresponding to the shutdown event to form chain link information, and construct a cycle number training model based on the chain link information; Step S3: According to the current downtime of the laminator, the model is trained by the number of cycles, and the number of cycles of idle operation required before formal lamination is output and recommended to the user terminal.

5. The intelligent remote control method for a laminator according to claim 4, characterized in that: The step S1 comprises: Mark the period from the shutdown of the laminator to the next normal startup as a shutdown event, obtain all the shutdown events in the historical records, and form a set A, where A = {a1, a2, a3, ... a n }, where a1, a2, a3, ..., a n It represents the first shutdown event, the second shutdown event, the third shutdown event, ..., the nth shutdown event in sequence; The downtime duration of each downtime event is marked as s, and all downtime duration data are extracted to form a set S, where S = {s1, s2, s3, ... s n }, where s1, s2, s3, ... s n It represents the downtime duration of the first downtime event, the downtime duration of the second downtime event, the downtime duration of the third downtime event, ..., the downtime duration of the nth downtime event in sequence.

6. The intelligent remote control method for a laminator according to claim 5, characterized in that: The step S2 comprises: Step S201, marking the period from the normal start of the laminator to the formal lamination as a self-checking phase, and obtaining the number of cycles of the laminator running idle in the self-checking phase; Step S202, marking the laminator from formal lamination to equipment shutdown as a processing link, obtaining a target processing time period for the processing link, the target processing time period being the time period from the formal lamination of the laminator until the first lamination result qualified product appears, if there is a target event of unqualified lamination result in the target processing time period, then the processing link is marked as an abnormal processing link, if there is no target event of unqualified lamination result in the target processing time period, then the processing link is marked as a normal processing link; Step S203, the shutdown event corresponding to the self-checking link before the self-checking link and the processing link corresponding to the self-checking link after the self-checking link are matched one by one to form a chain link event, and the chain link information of the chain link event is extracted, and the chain link information includes the shutdown duration and the number of cycles of the idle machine operation; Step S204, extract the chain link events with the same number of cycles of idle machine operation in the chain link information into the same set to form a first subset, extract the chain link events whose processing links are normal processing links in the first subset into a second subset, establish a first coordinate system, take the downtime as the x-axis, take the number of cycles of idle machine operation as the y-axis, mark the chain link events in the second subset in the first coordinate system, mark each chain link event as a chain node, obtain the two chain nodes with the farthest distance as two endpoints, mark them as a target time period, and use the target time period as the initial downtime range corresponding to the number of cycles of the idle machine operation; Step S205, establish a second coordinate system, take the downtime as the x-axis, take the number of cycles of idle operation as the y-axis, mark the link events in the first subset in the second coordinate system, extract all link events within the initial downtime range, mark the link events of normal processing links as normal chain nodes, mark the link events of abnormal processing links as abnormal chain nodes, divide the initial downtime range into several time intervals T, obtain the total number of normal chain nodes I and the total number of abnormal chain nodes J in each time interval T, calculate the abnormal proportion W in each time interval T, W = J / I + J, if W is greater than W 阈值 , then the time range corresponding to the time interval is removed, and the remaining time intervals are used to regenerate a new downtime duration range, which is output as the final downtime duration range; Step S206, extract the number of cycles of idle operation as N, N+1, N+2, N+3..., obtain the final downtime range corresponding to the number of cycles of N idle operation as [t1, t2] through steps S201-S205, take the time point t2 as the starting point of the downtime corresponding to the number of cycles of N+1 idle operation, repeat the above steps S201-S205, and obtain the downtime range corresponding to the number of cycles of N+1 idle operation as [t2, t3]; and so on, take the end point of the previous downtime range as the starting point of the next downtime range, so as to obtain the downtime ranges corresponding to different numbers of cycles; Step S207, taking the downtime duration range as input and the number of cycles of idling operation as output, training the model to obtain a cycle number training model.

Images