Injection molding machine material leakage intelligent detection method based on multiple sensors and storage medium

Abstract

The invention relates to the field of injection molding machines, and discloses an intelligent injection molding machine material leakage detection method based on multiple sensors and a storage medium, mold displacement distances of an injection molding machine are respectively collected in multiple preset monitoring areas of the injection molding machine through multiple distance sensors, so that abundant injection molding machine material leakage detection scenes are provided; outputting a dynamic reference value and a fluctuation range value in a detection scene based on the dynamic reference model, and obtaining material leakage evaluation parameters by combining the dynamic reference value, the fluctuation range value, the mold displacement correction data and the weight coefficient with the current operation condition of the injection molding machine, so as to generate a material leakage alarm strategy based on the material leakage evaluation parameters; compared with the prior art, based on rich scenes of multi-sensor detection, overall fusion of a calculation model and an intelligent algorithm, intelligent non-contact real-time detection can be effectively carried out on material leakage of the injection molding machine, the detection precision of the material leakage of the injection molding machine is improved, convenient, intelligent and reliable alarm can be achieved, and the industrial requirements of current injection molding machine application are met.

Description

Technical Field

[0001] The present invention relates to the field of injection molding machines, and in particular to a multi-sensor based intelligent detection method for injection molding machine leakage, electronic equipment and computer-readable storage medium. Background Art

[0002] Currently, when an injection molding machine is operating, the injection nozzle and the mold's main runner gate must be tightly fitted together under high pressure. However, in actual production, since the nozzle and the mold's plastic port are both in contact with steel plates, it is often easy for the nozzle and the mold's main runner gate to not fit completely together, resulting in glue leakage, which in turn leads to problems such as material shortages, shrinkage, or deformation in the product molding quality. Although the market can currently detect the above-mentioned leakage situations, the detection scenarios are relatively simple, and sometimes external personnel are required to confirm the detection scenarios or situations. This not only wastes the production staff's time, but also introduces variable factors to a certain extent, which is likely to lead to a decrease in detection accuracy. Summary of the Invention

[0003] The present invention aims to at least partially address one of the technical problems in the related art. To this end, the present invention proposes a multi-sensor-based intelligent detection method and storage medium for injection molding machine leakage, which can achieve intelligent real-time detection of injection molding machine leakage and improve the detection accuracy of injection molding machine leakage.

[0004] In a first aspect, an embodiment of the present invention provides a multi-sensor based intelligent detection method for injection molding machine leakage, comprising the following steps:

[0005] Step S1, controlling the injection molding machine to maintain operation for a preset injection time, and during the operation of the injection molding machine, respectively collecting mold displacement distances of the injection molding machine in multiple preset monitoring areas of the injection molding machine through multiple pre-configured distance sensors, and pre-processing each mold displacement distance to obtain a corresponding mold displacement correction distance, wherein each distance sensor corresponds to one of the preset monitoring areas;

[0006] Step S2: For each distance sensor, input the corresponding mold displacement correction distance into a pre-trained dynamic reference model to obtain a dynamic reference value and a fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model, wherein the fluctuation range value is associated with the dynamic reference value;

[0007] Step S3, obtaining an abnormality assessment parameter according to the dynamic reference value, the fluctuation range value, and the mold displacement correction data, and determining a material leakage assessment parameter according to all the abnormality assessment parameters and predetermined weight coefficients of the distance sensors in combination with the current operation status of the injection molding machine;

[0008] Step S4: generating a leakage alarm strategy for the injection molding machine according to the leakage evaluation parameters and a preset leakage decision threshold.

[0009] Optionally, in one embodiment of the present invention, when the preset injection time includes multiple injection cycles of the injection molding machine, the step S1 includes:

[0010] Step S11: for each of the distance sensors, respectively collect an original distance measurement value of a corresponding one of the preset monitoring areas in each injection molding cycle, thereby using the original distance measurement value as the mold displacement distance of the injection molding machine;

[0011] Step S12: For each mold displacement distance within the injection molding cycle, correct the mold displacement distance based on a predetermined temperature compensation coefficient to obtain a mold displacement correction distance corresponding to the mold displacement distance, wherein the temperature compensation coefficient represents the sensitivity of the mold displacement distance to temperature changes.

[0012] Optionally, in one embodiment of the present invention, the step of inputting the corresponding mold displacement correction distance into a pre-trained dynamic reference model to obtain a dynamic reference value and a fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model includes:

[0013] Step S21: For each distance sensor, input the mold displacement correction distance within each injection cycle into a pre-trained dynamic benchmark model, and calculate the dynamic benchmark value and fluctuation range value corresponding to each mold displacement correction data using a dynamic benchmark algorithm formula configured in the dynamic benchmark model. The dynamic benchmark algorithm formula is as follows:

[0014]

[0015] t is the serial number of the injection cycle and is a positive integer not less than 1, μ t is the dynamic reference value corresponding to the current injection cycle, X t is the mold displacement correction distance corresponding to the current injection cycle, α is the preset forgetting factor, 0<α<1, σ t is the fluctuation range value corresponding to the current injection cycle; when t is 1, μ t-1 =μ0=0,σ t-1 =σ0=0.

[0016] Optionally, in one embodiment of the present invention, the step in step S3 of obtaining an abnormality assessment parameter according to the dynamic reference value, the fluctuation range value, and the mold displacement correction data includes:

[0017] Step S31: Substitute the current dynamic reference value, the fluctuation range value, and the mold displacement correction data into an abnormality evaluation formula for calculation to obtain an abnormality evaluation parameter; wherein S is the abnormality evaluation parameter, and the abnormality evaluation formula is as follows:

[0018]

[0019] Optionally, in one embodiment of the present invention, the step in step S3, determining the leakage assessment parameter based on all the abnormality assessment parameters and the predetermined weight coefficients of each of the distance sensors, combined with the current operation status of the injection molding machine, includes:

[0020] Step S32: calculating an abnormality assessment component based on all the abnormality assessment parameters and predetermined weight coefficients of the respective distance sensors;

[0021] Step S33: comparing the current operating status of the injection molding machine with pre-stored historical leakage information of the injection molding machine to obtain a historical similarity between the current operating status of the injection molding machine and the historical leakage information;

[0022] Step S34: Obtain the sum of the abnormality assessment component and the historical similarity to obtain a material leakage assessment parameter.

[0023] Optionally, in one embodiment of the present invention, the following formula is used to calculate the abnormality assessment component based on all the abnormality assessment parameters and the predetermined weight coefficients of the distance sensors:

[0024]

[0025] Wherein, Score is the abnormality evaluation component, n is the total number of the distance sensors, i represents the serial number of each distance sensor, ω i is the weight coefficient of the i-th distance sensor, S i is the abnormality assessment parameter of the i-th distance sensor,

[0026] Optionally, in one embodiment of the present invention, step S4 includes:

[0027] Step S41: When the leakage evaluation parameter is greater than or equal to a preset leakage decision threshold, triggering an alarm for the injection molding machine;

[0028] or,

[0029] Step S42: When the leakage evaluation parameter is less than the preset leakage decision threshold, adjust the preset injection time and return to step S1.

[0030] Optionally, in one embodiment of the present invention, step S12 includes:

[0031] Step S121, respectively obtaining the current temperature and calibration temperature of the distance sensor;

[0032] Step S122: Substitute the current temperature, the calibration temperature, and a predetermined temperature compensation coefficient into a distance correction formula to calculate and obtain a mold displacement correction distance corresponding to the mold displacement distance in the current injection cycle; wherein the distance correction formula is as follows:

[0033] X t =X[1+K T (TT ref )];

[0034] Wherein, X is the mold displacement distance in the current injection cycle, X t is the mold displacement correction distance corresponding to X, K T is the temperature compensation coefficient, T is the current temperature, T ref is the calibration temperature.

[0035] In a second aspect, an embodiment of the present invention provides an electronic device, including:

[0036] at least one processor;

[0037] at least one memory for storing at least one program;

[0038] When at least one of the programs is executed by at least one of the processors, the multi-sensor-based intelligent detection method for injection molding machine leakage as described in the first aspect is implemented.

[0039] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to implement the intelligent method for detecting leakage of an injection molding machine based on multiple sensors as described in the first aspect.

[0040] The present invention proposes an intelligent detection method and storage medium for injection molding machine leakage based on multiple sensors. Multiple distance sensors are used to collect the mold displacement distance of the injection molding machine in multiple preset monitoring areas of the injection molding machine to provide a richer injection molding machine leakage detection scenario, and then the dynamic reference value and fluctuation range value under the detection scenario are output based on the intelligently configured dynamic reference model. The leakage evaluation parameters are obtained by combining the dynamic reference value, fluctuation range value, mold displacement correction data and weight coefficient with the current operation status of the injection molding machine, so as to adaptively generate a leakage alarm strategy for the injection molding machine based on the leakage evaluation parameters. It can be seen that compared with the relevant existing technologies, the overall integration of rich scenarios, calculation models and intelligent algorithms based on multi-sensor detection can effectively perform intelligent non-contact real-time detection of injection molding machine leakage, further improve the injection molding machine leakage detection accuracy, and is more conducive to achieving convenient, intelligent and reliable alarms, thereby meeting the current industrial needs of injection molding machine applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of an intelligent method for detecting material leakage in an injection molding machine based on multiple sensors provided by one embodiment of the present invention;

[0042] Figure 2 yes Figure 1 Flowchart of step S1 in FIG.

[0043] Figure 3 yes Figure 2 Flowchart of step S12 in FIG.

[0044] Figure 4 yes Figure 1 A partial flow chart of the step S2 of step "inputting the corresponding mold displacement correction distance into the pre-trained dynamic reference model to obtain the dynamic reference value and the fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model";

[0045] Figure 5 yes Figure 1 A partial flow chart of the step S3 of "determining leakage evaluation parameters based on all abnormality evaluation parameters and predetermined weight coefficients of each distance sensor in combination with the current operation status of the injection molding machine";

[0046] Figure 6 This is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] It should be noted that although the functional modules are divided in the device schematic and the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flowchart.

[0049] Figure 1 The flowchart of the multi-sensor based intelligent detection method for injection molding machine leakage is provided in one embodiment of the present invention. Figure 1 As shown, the multi-sensor based intelligent detection method for injection molding machine leakage may include but is not limited to steps S1 to S4.

[0050] Step S1: Controlling the injection molding machine to maintain operation for a preset injection time. During the operation of the injection molding machine, using multiple pre-configured distance sensors to respectively collect mold displacement distances of the injection molding machine in multiple preset monitoring areas of the injection molding machine, and pre-processing each mold displacement distance to obtain a corresponding mold displacement correction distance, wherein each distance sensor corresponds to one of the preset monitoring areas;

[0051] It should be noted that, as a commonly used operating equipment in this field, the specific types and parameters of the injection molding machine can be various, and can be set accordingly by those skilled in the art according to the actual scenario. The invention of the present invention does not lie in the injection molding machine itself, and will not be described here to avoid redundancy. The preset monitoring area can be determined accordingly according to different scenarios. For example, in the following embodiment, three sensors are mainly used as an example for explanation, wherein the distance sensor corresponding to the monitoring area at the parting surface is used as the main sensor, the distance sensor corresponding to the monitoring area at the nozzle is used as the first auxiliary sensor, and the distance sensor corresponding to the monitoring area at the ejector plate is used as the second auxiliary sensor. Similarly, more sensors can be set. The preset injection time, that is, the pre-set detection time, can be set according to the actual scenario. In order to facilitate the description of its principle, the injection cycle of the injection molding machine is used as an example in the following embodiments, but it is not the only limitation. The distance sensor can be, but is not limited to, a TOF laser sensor, which can be used in conjunction with a magnetic quick-release base (which can provide adsorption force), a universal adjustment pan-tilt head (three-dimensionally adjustable), etc., so that the corresponding preset monitoring area can be quickly located by the laser beam, thereby realizing convenient and reliable data collection.

[0052] Step S2: For each distance sensor, input the corresponding mold displacement correction distance into a pre-trained dynamic reference model to obtain a dynamic reference value and a fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model, wherein the fluctuation range value is associated with the dynamic reference value;

[0053] Step S3: Obtain an abnormality assessment parameter based on the dynamic reference value, the fluctuation range value, and the mold displacement correction data, and determine a leakage assessment parameter based on all abnormality assessment parameters and predetermined weight coefficients of each distance sensor in combination with the current operation status of the injection molding machine. The current operation status of the injection molding machine may be, but is not limited to, presented as: injection parameters and fault conditions of the injection molding machine under current conditions. Since the injection molding machine is controlled to maintain operation at a preset injection time, the operation of the injection molding machine is equivalent to real-time detection of the injection molding machine. Therefore, the above-mentioned "current condition" can be clearly defined as a time node of real-time detection of one of the preset injection times.

[0054] Step S4: Generate a leakage alarm strategy for the injection molding machine based on the leakage evaluation parameters and the preset leakage decision threshold. The leakage decision threshold can be set by those skilled in the art according to the actual scenario and is not limited here.

[0055] In this step, the mold displacement distance of the injection molding machine is collected in multiple preset monitoring areas of the injection molding machine through multiple distance sensors to provide a richer injection molding machine leakage detection scenario, and then the dynamic reference value and fluctuation range value under the detection scenario are output based on the intelligently configured dynamic reference model, and the leakage evaluation parameters are obtained by combining the dynamic reference value, fluctuation range value, mold displacement correction data and weight coefficient with the current operation status of the injection molding machine, so as to adaptively generate a leakage alarm strategy for the injection molding machine based on the leakage evaluation parameters. It can be seen that compared with the relevant existing technologies, the overall integration of rich scenarios, calculation models and intelligent algorithms based on multi-sensor detection can effectively perform intelligent non-contact real-time detection of injection molding machine leakage, further improve the injection molding machine leakage detection accuracy, and is more conducive to achieving convenient, intelligent and reliable alarms, thereby meeting the current industrial needs of injection molding machine applications.

[0056] In one embodiment, if the dynamic benchmark model has not been pre-trained, the dynamic benchmark model can be pre-trained. After it is trained, step S2 is executed. For example, specifically, the empty mold of the injection molding machine is controlled to run 5 to 10 complete injection cycles. During this process, real-time measurement data of each distance sensor is collected, and this part of the real-time measurement data is continuously input into the dynamic benchmark model for training, so that a pre-trained dynamic benchmark model can be obtained; in addition to the dynamic benchmark algorithm configured inside the dynamic benchmark model, its specific architecture, type, etc. can be set accordingly according to the actual scenario, such as integrating a deep network model, etc., which is not limited here.

[0057] In one embodiment, before step S1, each distance sensor may also be self-checked but is not limited to being self-checked to determine whether the initial state of the distance sensor or the impact of the environmental state on the distance sensor is in compliance with regulations. For example, taking temperature-assisted self-check as an example, in order to test whether the impact of the environmental state on the distance sensor is in compliance with regulations, the ambient temperature is tested by the temperature sensor to see whether it is within the expected range. If so, the distance sensor can be used for data collection directly. Otherwise, the ambient temperature needs to be adjusted, and the distance sensor can be used to collect data after it reaches the appropriate conditions.

[0058] like Figure 2 As shown, in one embodiment of the present invention, when the preset injection time includes multiple injection cycles of the injection molding machine, the number of injection cycles can be set according to actual conditions, and can usually be set to about 50, and each injection cycle is numbered in sequence from 1 to 50, that is, injection cycle 1, injection cycle 2...injection cycle 50, and so on; step S1 can include, but is not limited to, the following steps:

[0059] Step S11: For each distance sensor, collect the original distance measurement value of one of the preset monitoring areas in each injection molding cycle, so as to use the original distance measurement value as the mold displacement distance of the injection molding machine;

[0060] Step S12: For the mold displacement distance in each injection cycle, the mold displacement distance is corrected based on a predetermined temperature compensation coefficient to obtain a mold displacement correction distance corresponding to the mold displacement distance, wherein the temperature compensation coefficient represents the sensitivity of the mold displacement distance to temperature changes.

[0061] In this step, the original distance measurement value of one of the corresponding preset monitoring areas in each injection cycle is collected respectively, so as to obtain the original distance measurement value of the corresponding distance sensor. The original distance measurement value can be used as the mold displacement distance of the injection molding machine. The mold displacement distance is further corrected by the temperature compensation coefficient, that is, the influence of temperature on the mold displacement distance test is taken into account, and a mold displacement correction distance that is more in line with the actual test situation is obtained.

[0062] It should be noted that the injection molding cycle can be determined according to the actual working scenario of the injection molding machine. For example, the typical injection molding stage characteristics of the injection molding machine are: clamping → injection → holding pressure → cooling → mold opening. Then the cycle synchronization signal can be taken from the clamping completion signal of the injection molding machine, and one of the injection molding cycles of the injection molding machine can be determined by the clamping completion signal, etc. There is no restriction here.

[0063] like Figure 3 As shown, in one embodiment of the present invention, step S12 may include, but is not limited to, the following steps:

[0064] Step S121, respectively obtaining the current temperature and calibration temperature of the distance sensor;

[0065] Step S122: Substitute the current temperature, the calibration temperature, and the predetermined temperature compensation coefficient into the distance correction formula to calculate and obtain the mold displacement correction distance corresponding to the mold displacement distance in the current injection cycle;

[0066] The distance correction formula is as follows:

[0067] X t =X[1+K T (TT ref )];

[0068] Among them, X is the mold displacement distance in the current injection cycle, X t is the mold displacement correction distance corresponding to X, K T is the temperature compensation coefficient, T is the current temperature, T ref is the calibration temperature.

[0069] In this step, the current temperature and calibration temperature of the distance sensor are detected to reveal the influence of the temperature of the distance sensor on the detection distance result. Among them, the calibration temperature can be regarded as the test temperature under ideal conditions, and the current temperature is the test temperature under actual conditions. Therefore, in the distance correction formula, it is necessary to obtain the temperature difference between the two as a compensation component for calculation. Combined with the mold displacement distance in the current injection molding cycle, the mold displacement correction distance in the current injection molding cycle can be finally calculated.

[0070] In one embodiment, the calibration temperature can be obtained by the self-test method of the distance sensor before detection, for example, the room temperature is 25°C. The current temperature can be obtained by sampling through a temperature sensor provided separately. The temperature compensation coefficient can be set accordingly according to the type and parameters of the specific distance sensor, and is not limited here. For example, K T It can be, but is not limited to, 0.005 / °C.

[0071] like Figure 4 As shown, in one embodiment of the present invention, the step in step S2, inputting the corresponding mold displacement correction distance into the pre-trained dynamic reference model to obtain the dynamic reference value and fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model, may include but is not limited to the following steps:

[0072] Step S21: For each distance sensor, input the mold displacement correction distance within each injection cycle into the pre-trained dynamic benchmark model, and calculate the dynamic benchmark value and fluctuation range value corresponding to each mold displacement correction data using the dynamic benchmark algorithm formula configured in the dynamic benchmark model;

[0073] The dynamic benchmark algorithm formula is as follows:

[0074] μ t =αX t +(1-α)μ t-1 ;

[0075]

[0076] t is the serial number of the injection cycle and is a positive integer not less than 1, μ t is the dynamic reference value corresponding to the current injection cycle, X t is the mold displacement correction distance corresponding to the current injection cycle, α is the preset forgetting factor, 0<α<1, σ t is the fluctuation range value corresponding to the current injection cycle; when t is 1, μ t-1 =μ0=0,σ t-1 =σ0=0.

[0077] In this step, by inputting the mold displacement correction distance within each injection molding cycle into the pre-trained dynamic benchmark model, the dynamic benchmark algorithm formula configured by the dynamic benchmark model can be combined to accurately and reliably calculate the dynamic benchmark value and fluctuation range value corresponding to each mold displacement correction data, wherein the fluctuation range value is associated with the dynamic benchmark value, and the dynamic benchmark value and fluctuation range value within the current injection molding cycle are associated with the dynamic benchmark value and fluctuation range value within the next injection molding cycle. It can be seen that since the accumulation of injection molding cycles during the detection operation of the injection molding machine will obviously gradually increase, this also means that there are differences in the dynamic benchmark value and fluctuation range value corresponding to different injection molding cycles. However, considering the overall operation process, the calculation result obtained in this way fully considers the continuity between different injection molding cycles, reflects the dynamic changes of the dynamic benchmark value and fluctuation range value, has a relatively smaller error, and is more accurate.

[0078] It can be understood that α is used to weigh the influence of the dynamic reference value and the fluctuation range value corresponding to the previous injection molding cycle, and can be set accordingly according to different scenarios. For example, α is preferably 0.2.

[0079] In one embodiment of the present invention, the steps in step S3, obtaining the abnormality assessment parameter based on the dynamic reference value, the fluctuation range value, and the mold displacement correction data, may include, but are not limited to, the following steps:

[0080] Step S31: Substitute the current dynamic reference value, fluctuation range value, and mold displacement correction data into the abnormality evaluation formula to calculate and obtain the abnormality evaluation parameter; wherein S is the abnormality evaluation parameter, and the abnormality evaluation formula is as follows:

[0081]

[0082] It can be seen that in each injection cycle, by comparing the current mold displacement correction data, the difference between the dynamic reference value and the fluctuation range value of a certain preset multiple, the abnormal situation in the current injection cycle can be determined. Specifically, when |X t -μ t |<2σ t , it means that the operation of the injection molding machine in the current injection molding cycle is in a stable state, so the probability of abnormality is low, so S is set to 0; when 2σ t ≤|X t -μ t |<3σ t , the operation of the injection molding machine in the current injection molding cycle is in a transitional state, so there is a certain possibility of abnormality, so S is set accordingly according to the above formula; when |X t -μ t |≥3σ t , it means that the operation of the injection molding machine in the current injection cycle is in an unstable state, so the probability of abnormality is high, and S is set to 1.

[0083] like Figure 5 As shown, in one embodiment of the present invention, the steps in step S3, based on all abnormality evaluation parameters and predetermined weight coefficients of each distance sensor, combined with the current operation status of the injection molding machine, determine the leakage evaluation parameters, which may include but is not limited to the following steps:

[0084] Step S32: Calculate an abnormality assessment component based on all abnormality assessment parameters and predetermined weight coefficients of each distance sensor;

[0085] Step S33: comparing the current operating status of the injection molding machine with pre-stored historical leakage information of the injection molding machine to obtain a historical similarity between the current operating status of the injection molding machine and the historical leakage information;

[0086] Step S34: Obtain the sum of the abnormal assessment component and the historical similarity to obtain the leakage assessment parameter.

[0087] In this step, an abnormal evaluation component can be calculated based on all abnormal evaluation parameters and the predetermined weight coefficients of each distance sensor. The abnormal evaluation component reflects the mixed influence of the operation status of the injection molding machine in the current injection molding cycle and the weight coefficients of the corresponding distance sensors, and the current operation status of the injection molding machine is compared with the pre-stored historical leakage information of the injection molding machine to determine the matching between the current operation status and the historical operation status of the injection molding machine, so as to obtain the historical similarity of the current operation status of the injection molding machine with respect to the historical leakage information. Finally, based on the sum of the abnormal evaluation component and the historical similarity, the leakage evaluation parameter under the comprehensive evaluation influence condition can be obtained.

[0088] In one embodiment, historical leakage information can be generated by recording historical leakage situations. For example, based on the specific causes of leakage situations that occurred in previous detections, corresponding historical leakage information is generated. It can include, but is not limited to, periodic leakage information to record regular anomalies that occur in different molds, or progressive wear information to reflect the slow drift trend of mold displacement correction data, or occasional interference information to reflect the automatic filtering of isolated abnormal points, which can be used to identify specific leakage time points, etc.

[0089] In one embodiment, the historical similarity can be calculated using, but not limited to, a DTW (Dynamic Time Warping) algorithm. The specific formula is as follows:

[0090]

[0091] Among them, H similar is the historical similarity, Z is the preset maximum regularization distance threshold, DTW(X,Y) represents the comparison value between the current operation status of the injection molding machine and the historical leakage information, X represents the current operation status of the injection molding machine, and Y represents the historical leakage information of the injection molding machine; since the DTW algorithm is well known to those skilled in the art, DTW(X,Y) can be easily calculated using the DTW algorithm, and to avoid redundancy, it is not described here.

[0092] In one embodiment, the weight coefficients of each distance sensor can be determined based on, but not limited to, finite element simulation and actual leakage scenarios. For example, the weight coefficient of the distance sensor serving as the main sensor can be set to the highest, and the weight coefficients of the remaining distance sensors can be allocated separately, etc. There is no limitation here.

[0093] In one embodiment, the following formula is used to calculate the abnormality assessment component based on all abnormality assessment parameters and the predetermined weight coefficients of each distance sensor:

[0094]

[0095] Among them, Score is the abnormality evaluation component, n is the total number of distance sensors, i represents the serial number of each distance sensor, ω i is the weight coefficient of the i-th distance sensor, S i is the abnormality evaluation parameter of the i-th distance sensor; further, the leakage evaluation parameter Q can be calculated, that is,

[0096] Q=Score+H similar ;

[0097] In one embodiment of the present invention, step S4 may include, but is not limited to, the following steps:

[0098] Step S41: When the leakage evaluation parameter is greater than or equal to a preset leakage decision threshold, an alarm is triggered for the injection molding machine;

[0099] or,

[0100] Step S42: When the leakage evaluation parameter is less than the preset leakage decision threshold, adjust the preset injection time and return to step S1.

[0101] In this step, by comparing the relative size of the leakage evaluation parameter and the preset leakage decision threshold, the leakage alarm strategy for the injection molding machine can be determined. Specifically, when the leakage evaluation parameter is greater than or equal to the preset leakage decision threshold, it means that the injection molding machine is leaking at this time, and then an alarm is triggered for the injection molding machine. Otherwise, the injection molding machine can still be continuously detected, and the operation scene of the injection molding machine can be changed by adjusting the preset injection time, which is equivalent to changing the detection scene of the injection molding machine, and then returning to execute step S1, that is, executing the overall process of the intelligent detection method for injection molding machine leakage based on multiple sensors of the present invention again, which can further improve the detection accuracy of injection molding machine leakage, and is more conducive to achieving convenient, intelligent and reliable alarms.

[0102] The following is a specific example for illustration.

[0103] The leakage decision threshold is set to 0.8. Taking the three distance sensors as an example, the corresponding weight coefficients ω1, ω2 and ω3 are 0.6, 0.3 and 0.1 respectively. The calculated abnormality evaluation parameters S1, S2 and S3 are 0.9, 0.5 and 0.2 respectively. The historical similarity H similar is 0.35, then the leakage assessment parameter Q can be calculated to be 1.06. Obviously, 1.06>0.8, then an alarm is triggered for the injection molding machine.

[0104] In one embodiment, the leakage decision threshold can also be set in segments, that is, different leakage decision threshold intervals are provided to further divide the leakage evaluation parameters, so as to adopt different alarm processing methods (such as immediate alarm triggering, delayed alarm triggering, continuous observation and immediate shutdown, etc.) corresponding to different leakage decision threshold intervals, so that the staff can understand the actual leakage situation of the injection molding machine more clearly.

[0105] In one embodiment, since the leakage assessment parameters can be calculated in each injection molding cycle, a comprehensive assessment can also be performed based on the continuously obtained leakage assessment parameters. For example, if the leakage assessment parameters corresponding to three consecutive injection molding cycles are all greater than or equal to the leakage decision threshold, an alarm is triggered immediately; if the leakage assessment parameters corresponding to three consecutive injection molding cycles are not all greater than or equal to the leakage decision threshold, the alarm is triggered with a delay; if the leakage assessment parameters corresponding to three consecutive injection molding cycles are all less than the leakage decision threshold, it is determined that no leakage exists.

[0106] Figure 6 FIG. 1 is a schematic diagram of the structure of an electronic device 1000 provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 1000 includes a memory 1100 and a processor 1200. The number of the memory 1100 and the processor 1200 can be one or more. Figure 6 In the embodiment, a memory 1100 and a processor 1200 are taken as an example; the memory 1100 and the processor 1200 in the device can be connected via a bus or other means. Figure 6 The bus connection is taken as an example.

[0107] Memory 1100, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the multi-sensor-based intelligent injection molding machine leakage detection method provided in any embodiment of the present invention. Processor 1200 implements the multi-sensor-based intelligent injection molding machine leakage detection method by executing the software programs, instructions, and modules stored in memory 1100.

[0108] The memory 1100 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function. In addition, the memory 1100 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 1100 may further include a memory remotely located relative to the processor 1200, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] An embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions for executing the multi-sensor-based intelligent detection method for injection molding machine leakage as provided in any embodiment of the present invention.

[0110] An embodiment of the present invention also provides a computer program product, including a computer program or computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the computer device executes the intelligent leakage detection method for injection molding machines based on multiple sensors as provided in any embodiment of the present invention.

[0111] The electronic devices and application scenarios described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Those skilled in the art will appreciate that with the evolution of electronic devices and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0112] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0113] In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0114] As used in this specification, the terms "component," "module," "system," and the like are used to refer to computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components can reside in a process or execution thread, and a component can be located on a single computer or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, through local or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, or a network, such as the Internet interacting with other systems via signals).

Claims

1. An intelligent detection method for injection molding machine leakage based on multiple sensors, characterized in that: The steps include: Step S1, controlling the injection molding machine to maintain operation for a preset injection time, and during the operation of the injection molding machine, respectively collecting mold displacement distances of the injection molding machine in multiple preset monitoring areas of the injection molding machine through multiple pre-configured distance sensors, and pre-processing each mold displacement distance to obtain a corresponding mold displacement correction distance, wherein each distance sensor corresponds to one of the preset monitoring areas; Step S2: For each distance sensor, input the corresponding mold displacement correction distance into a pre-trained dynamic reference model to obtain a dynamic reference value and a fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model, wherein the fluctuation range value is associated with the dynamic reference value; Step S3, obtaining an abnormality assessment parameter according to the dynamic reference value, the fluctuation range value, and the mold displacement correction data, and determining a material leakage assessment parameter according to all the abnormality assessment parameters and predetermined weight coefficients of the distance sensors in combination with the current operation status of the injection molding machine; Step S4: generating a leakage alarm strategy for the injection molding machine according to the leakage evaluation parameters and a preset leakage decision threshold.

2. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 1, characterized in that: When the preset injection time includes multiple injection cycles of the injection molding machine, the step S1 includes: Step S11: for each of the distance sensors, respectively collect an original distance measurement value of a corresponding one of the preset monitoring areas in each injection molding cycle, thereby using the original distance measurement value as the mold displacement distance of the injection molding machine; Step S12: For each mold displacement distance within the injection molding cycle, correct the mold displacement distance based on a predetermined temperature compensation coefficient to obtain a mold displacement correction distance corresponding to the mold displacement distance, wherein the temperature compensation coefficient represents the sensitivity of the mold displacement distance to temperature changes.

3. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 2, characterized in that: The step S2 of inputting the corresponding mold displacement correction distance into a pre-trained dynamic reference model to obtain a dynamic reference value and a fluctuation range value corresponding to the mold displacement correction data output by the dynamic reference model includes: Step S21: For each distance sensor, input the mold displacement correction distance within each injection cycle into a pre-trained dynamic benchmark model, and calculate the dynamic benchmark value and fluctuation range value corresponding to each mold displacement correction data using a dynamic benchmark algorithm formula configured in the dynamic benchmark model. The dynamic benchmark algorithm formula is as follows: m t =αX t +(1-a)m t-1 ; t is the serial number of the injection cycle and is a positive integer not less than 1, μ t is the dynamic reference value corresponding to the current injection cycle, X t is the mold displacement correction distance corresponding to the current injection cycle, α is the preset forgetting factor, 0<α<1, σ t is the fluctuation range value corresponding to the current injection cycle; when t is 1, μ t-1 =μ0=0,σ t-1 =σ0=0.

4. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 3, characterized in that: The step in step S3, obtaining an abnormality assessment parameter based on the dynamic reference value, the fluctuation range value, and the mold displacement correction data, includes: Step S31: Substitute the current dynamic reference value, the fluctuation range value, and the mold displacement correction data into an abnormality evaluation formula for calculation to obtain an abnormality evaluation parameter; wherein S is the abnormality evaluation parameter, and the abnormality evaluation formula is as follows:

5. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 1, characterized in that: The steps in step S3, determining the leakage evaluation parameters based on all the abnormality evaluation parameters and the predetermined weight coefficients of the distance sensors in combination with the current operation status of the injection molding machine, include: Step S32: calculating an abnormality assessment component based on all the abnormality assessment parameters and predetermined weight coefficients of the respective distance sensors; Step S33: comparing the current operating status of the injection molding machine with pre-stored historical leakage information of the injection molding machine to obtain a historical similarity between the current operating status of the injection molding machine and the historical leakage information; Step S34: Obtain the sum of the abnormality assessment component and the historical similarity to obtain a material leakage assessment parameter.

6. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 5, characterized in that: The following formula is used to calculate the abnormality assessment component based on all the abnormality assessment parameters and the predetermined weight coefficients of the distance sensors: Wherein, Score is the abnormality evaluation component, n is the total number of the distance sensors, i represents the serial number of each distance sensor, ω i is the weight coefficient of the i-th distance sensor, S i is the abnormality assessment parameter of the i-th distance sensor, 7. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 1, characterized in that: The step S4 comprises: Step S41: When the leakage evaluation parameter is greater than or equal to a preset leakage decision threshold, triggering an alarm for the injection molding machine; or, Step S42: When the leakage evaluation parameter is less than the preset leakage decision threshold, adjust the preset injection time and return to step S1.

8. The multi-sensor based intelligent detection method for injection molding machine leakage according to claim 2, characterized in that: The step S12 includes: Step S121, respectively obtaining the current temperature and calibration temperature of the distance sensor; Step S122: Substitute the current temperature, the calibration temperature, and a predetermined temperature compensation coefficient into a distance correction formula to calculate and obtain a mold displacement correction distance corresponding to the mold displacement distance in the current injection cycle; wherein the distance correction formula is as follows: X t =X[1+K T (T-T ref )]; Wherein, X is the mold displacement distance in the current injection cycle, X t is the mold displacement correction distance corresponding to X, K T is the temperature compensation coefficient, T is the current temperature, T ref is the calibration temperature.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When at least one of the programs is executed by at least one of the processors, the multi-sensor based intelligent detection method for injection molding machine leakage as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that A program executable by a processor is stored therein, and when the program executable by the processor is executed by the processor, it is used to implement the intelligent detection method for injection molding machine leakage based on multiple sensors as described in any one of claims 1 to 8.

Images