Predictive maintenance system for injection mold of automotive trim panel

Abstract

The invention relates to the technical field of injection molds, and discloses an automotive trim panel injection mold predictive maintenance system, which comprises an acoustic pulse injection and receiving device arranged at an inlet and an outlet of a mold cooling water channel, and a signal processing and decision module, according to the method, a degradation index is determined by analyzing the difference between an acoustic echo signal and a reference signal, and when the index is abnormal, fault qualification is carried out in combination with macroscopic process parameters, and early recognition and state perception of microcosmic damage in the mold are realized in a non-intrusive manner by utilizing a cooling water channel of the mold, so that the detection accuracy is improved. The maintenance decision can be based on the real health state of the mold, and hysteresis and resource waste of a traditional maintenance mode are avoided.

Description

Technical Field

[0001] The invention relates to a predictive maintenance system for an automobile interior trim panel injection mold, belonging to the technical field of injection molds. Background Art

[0002] Currently, in the field of injection molding of products such as automotive interior panels, the health of the mold is a fundamental factor affecting production efficiency and product quality. Therefore, the industry generally adopts periodic preventive maintenance based on a fixed number of injections or responsive repairs after a failure occurs to maintain mold operation.

[0003] The effectiveness of the aforementioned maintenance methods is limited when addressing progressive micro-damage such as microcracks or early wear within the mold. Since these damages typically do not directly cause changes in macro-process parameters such as injection pressure or mold temperature in the early stages of their evolution, the mold's internal health is effectively in an information-unknown state. This creates conditions for unplanned production stoppages, but also makes fixed-cycle maintenance strategies unable to match the actual wear and tear of different molds, leading to unnecessary disassembly and maintenance and resource consumption.

[0004] While existing technologies exist to monitor internal mold status by implanting fiber optic sensors, this approach, coupled with additional hardware, is difficult to implement in the cost-effective injection molding industry due to factors such as deployment costs, invasive mold modifications, and operational stability in industrial environments. In summary, existing technologies exhibit the following main limitations in their application: 1. A lack of technical means to detect the evolution of microscopic damage within the mold without increasing hardware costs or intruding into the mold itself; and 2. An information gap exists between existing maintenance logic and the mold's true health status, resulting in a mismatch between maintenance actions and actual needs. Therefore, the technical problem addressed by this invention is how to utilize existing components of the injection molding system to establish a monitoring method that can reflect the mold's internal health status in real time. Summary of the Invention

[0005] The present invention provides a predictive maintenance system for automobile interior panel injection molds, the main purpose of which is to solve the problem of early real-time monitoring of microscopic damage inside the mold without changing the hardware configuration of the injection molding system and without invading the mold body.

[0006] To achieve the above objectives, the present invention provides a predictive maintenance system for automobile interior panel injection molds, characterized in that the system includes:

[0007] an acoustic pulse injection device, disposed at the cooling water channel inlet of the mold, for injecting an acoustic pulse signal having a reference waveform into the cooling medium circulating in the cooling water channel;

[0008] An acoustic echo receiving device is arranged at the outlet of the cooling water channel and is used to receive the acoustic echo signal after the water flows through the mold;

[0009] A signal processing and decision module is connected to the acoustic pulse injection device and the acoustic echo receiving device, and the signal processing and decision module is configured to: store the reference acoustic echo signal measured by the acoustic echo receiving device when the mold is in a healthy state ; Real-time acoustic echo signal received by acoustic echo receiving device and the reference acoustic echo signal Perform time domain cross-correlation operation and determine a characterizing acoustic echo signal based on the operation result Relative to the reference acoustic echo signal Deterioration index of the degree of distortion on the waveform ; Deterioration index Compared with the degradation threshold, the degradation index When the degradation threshold is exceeded, an early warning signal is generated; and after the early warning signal is generated, the two macro parameters of mold temperature and injection pressure related to the injection molding process are further retrieved, based on the stored degradation index The association rules between abnormalities and changes in macro parameters are used to make qualitative judgments on potential fault types.

[0010] Preferably, the signal processing and decision module is configured to determine the degradation index by the following mathematical relationship: , ,in, is the acoustic echo signal received in real time. is the reference acoustic echo signal, is the maximum value of the cross-correlation function of the two signals, is the energy of the reference acoustic echo signal.

[0011] Preferably, the signal processing and decision module is further configured to perform benchmark adaptive compensation. After receiving a signal indicating that the injection molding material has been changed from the injection molding machine control system, the signal processing and decision module controls the clamping system of the injection molding machine to apply a perturbation pressure pulse with a certain amplitude and duration to the mold in a subsequent injection molding cycle; and the signal processing and decision module uses the pressure sensor of the injection molding machine to collect the attenuation response of the melt pressure in the mold cavity caused by the perturbation pressure pulse, and based on the characteristics of the pressure attenuation response, performs a benchmark acoustic echo signal. Dynamic compensation is performed to generate a compensated reference acoustic echo signal adapted to the physical properties of the new replacement material.

[0012] Preferably, the signal processing and decision module is configured to calculate the time taken for the pressure decay response to decay from the peak value to half of the peak value as the pressure half-life, and determine a relative viscosity coefficient related to the viscosity of the new material melt based on the pressure half-life; and the signal processing and decision module uses a stored nonlinear mapping function to map the reference acoustic echo signal based on the relative viscosity coefficient. The time domain axis is adjusted to complete dynamic compensation.

[0013] Preferably, the signal processing and decision module is also configured to perform closed-loop self-purification of the cooling water channel. When the signal processing and decision module determines that there are fluctuation characteristics that conform to the noise interference model in the acoustic echo signal, the signal processing and decision module controls the acoustic pulse injection device to send a swept frequency acoustic signal; and the signal processing and decision module analyzes the signal spectrum received by the acoustic echo receiving device to identify the resonance absorption peak caused by bubbles in the cooling medium.

[0014] Preferably, when the signal processing and decision module identifies the resonance absorption peak, it controls the acoustic pulse injection device to send a sound wave corresponding to the resonance absorption peak frequency to remove the bubbles attached to the inner wall of the cooling water channel, and switches back to the original working mode after removal to re-determine the degradation index. .

[0015] Preferably, the signal processing and decision module is also configured to perform accompanying perception of the material mixing uniformity. The signal processing and decision module processes the injection pressure signal to separate the high-frequency pressure fluctuation residual signal; and the signal processing and decision module determines the mixing uniformity index of the plastic material in the current injection molding cycle based on the energy characteristics of the pressure fluctuation residual signal, and generates a control instruction for adjusting the plasticizing parameters of the injection molding machine when the mixing uniformity index is worse than the process threshold.

[0016] Preferably, the acoustic pulse injection device and the acoustic echo receiving device are both piezoelectric ceramic vibrators.

[0017] Preferably, the association rule includes: when the degradation index When the degradation threshold is exceeded and the injection pressure shows an upward trend, the potential failure type is determined to be flow abnormality related to flash or micro cracks.

[0018] Preferably, the association rule includes: when the degradation index When the degradation threshold is exceeded and the local temperature drop rate of the mold slows down after the product is ejected, the potential fault type is determined to be a heat dissipation abnormality related to carbon deposition or decreased cooling efficiency.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. This invention transforms the mold's existing cooling water circuit from a single-function temperature control loop into an active acoustic diagnostic network throughout the mold. By injecting acoustic pulses into the cooling medium and analyzing their echo signals, microscopic damage hidden deep within the mold, which is difficult to detect using traditional macroscopic process parameters, can be monitored externally in the form of acoustic fingerprint distortion. This approach avoids invasive modifications to the mold itself or the addition of costly dedicated sensors. By reconstructing the functions of existing components, it achieves transparent perception of the mold's internal health status, allowing maintenance decisions to be based on the mold's actual condition rather than fixed production cycles.

[0021] 2. The present invention establishes a hierarchical diagnostic logic that stratifies microscopic state changes to macroscopic fault characterization. The system first calculates a degradation index that characterizes the degree of deviation from the mold's overall health state through highly sensitive acoustic echo comparison. This can capture the subtle acoustic characteristics of physical damage in its infancy, thereby issuing an early warning before traditional parameters such as pressure or temperature change. Only when this degradation index is abnormal does the system further retrieve and correlate these macroscopic process parameters for analysis. This conditionally triggered diagnostic process avoids continuous and complex data analysis, ensuring early warning capabilities while balancing the economy of computing resources and efficiency of decision-making.

[0022] 3. The present invention solves the key bottleneck faced by acoustic diagnostic methods when applied in real industrial environments through a set of adaptive and self-purification mechanisms. When replacing plastic raw materials with different physical properties, the system can actively apply clamping force perturbations and analyze pressure attenuation, online sense changes in material viscosity and dynamically compensate for the reference acoustic signal; when there is bubble interference in the cooling water channel, the system can switch to sweep mode to identify the resonant frequency and actively remove bubbles. This self-regulating capability enables the core acoustic diagnostic function to maintain monitoring continuity and reliability of results under changing production conditions and non-ideal medium environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a diagram of the overall functional architecture of a predictive maintenance system for an automobile interior panel injection mold according to the present invention;

[0024] Figure 2 This is a comparison chart of the sensitivity of the degradation index of the present invention and the monitoring of micro damage by traditional injection molding pressure;

[0025] Figure 3 This is the core diagnostic flow chart of a predictive maintenance system for an automobile interior panel injection mold according to the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described implementation methods are only part of the implementation methods of the present invention, not all of the implementation methods. Based on the implementation methods in the present invention, all other implementation methods obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] The present invention discloses a predictive maintenance system for injection molds of automobile interior panels. Its technical solution is based on a set of non-invasive acoustic diagnostic logic. The system uses the existing cooling water channel of the mold as a waveguide for acoustic diagnosis. Through an acoustic pulse injection and receiving device configured at the inlet and outlet of the water channel and a signal processing and decision-making module, a monitoring system that can sense the internal health status of the mold in real time is formed. After completing the capture of the acoustic characteristics of the internal state of the mold, the system further performs condition-triggered correlation analysis with the process parameters of the injection molding process, thereby realizing hierarchical diagnosis from early damage warning to fault qualitative analysis; in a specific application scenario, for example, for an injection mold for a large automobile door panel interior part, the production cycle requirements are high and modified polypropylene material with recycled materials added will be used. At this time, early damage caused by slight wear or stress concentration of the mold is detected. Predicting the risk of premature failure has become a link in ensuring continuous production. It relies on the monitoring method of process parameters such as mold temperature or injection pressure. Its perception ability is limited for hidden damage such as microcrack initiation or local carbon deposition that already exists before these parameters drift significantly. To meet this challenge, this system is configured to execute a set of mold condition monitoring procedures based on acoustic time domain reflection. The procedure starts with an acoustic pulse injection device, which can be a piezoelectric ceramic vibrator installed at the inlet pipe of the mold cooling water channel. It injects an acoustic pulse signal with a reference waveform into the circulating cooling water medium. The acoustic pulse signal propagates along the cooling water network inside the mold and is received by an acoustic echo receiving device, which is also a piezoelectric ceramic vibrator and is configured at the outlet of the cooling water channel, thereby obtaining an acoustic echo signal that carries the current complete acoustic response information of the mold. When the mold is confirmed to be in a healthy initial state, such as the first production shift of a new mold, the signal processing and decision module will collect and store the acoustic echo signal at that moment and define it as the baseline acoustic echo signal. In each subsequent injection cycle, the module will receive the latest acoustic echo signal in real time. With the stored reference acoustic echo signal Perform time domain cross-correlation calculations and use a degradation index that characterizes the degree of waveform distortion The mathematical relationship of To quantify the deviation of the mold health status, where the denominator is represents the energy of the reference signal, and the numerator The maximum value of the cross-correlation function of the two signals after the optimal time domain alignment. This ratio reflects the waveform similarity of the two signals. When any micro damage that changes the acoustic impedance occurs inside the mold, such as microcracks, it will cause an acoustic echo signal. The waveform is distorted, which reduces the similarity. The value increases accordingly. In this way, the system monitors the internal microscopic damage of the mold that cannot be directly perceived by the process parameters externally in the form of a quantifiable degradation index.

[0028] When the system only outputs a scalar degradation index When the on-site maintenance personnel still lack the direct basis for targeted maintenance, in view of this, the system is configured to monitor the degradation index When a preset degradation threshold is exceeded, the process of retrieving and analyzing relevant process parameters is triggered. The determination of the degradation threshold can follow a deterministic procedure, that is, within the initial 1000 production cycles after the new mold or the health status is confirmed, all The statistical distribution of the values ​​is calculated, and the mean of the distribution plus three times the standard deviation is set as the initial degradation threshold. The process parameters mainly include the mold temperature and injection pressure obtained from the injection molding machine control system. The system makes a qualitative judgment on the potential fault type based on the preset association rules stored internally. For example, an association rule can be defined as when the degradation index When the degradation threshold is exceeded and the signal processing and decision module analyzes the injection pressure curve peak value for multiple consecutive cycles and finds that it presents a unidirectional upward trend, the system determines the potential fault type as a fault related to overflow or abnormal melt flow caused by microcracks; another association rule can be defined as: when the degradation index If the degradation threshold is exceeded and the system analyzes the local temperature sensor readings of the mold after the product is ejected and finds that the temperature drop rate has slowed compared to the historical average, the system will determine the potential fault type as a fault related to reduced heat dissipation efficiency caused by local carbon deposition or blockage in the cooling water channel. In this way, through a diagnostic process that begins with acoustic state perception and ends with process parameter verification, the system not only provides early warning capabilities but also provides qualitative judgments with engineering guidance value for subsequent maintenance decisions.

[0029] In flexible production operations, it is common to replace plastics of different brands or different colors of masterbatches. Different materials have different physical properties such as melt viscosity, which will directly change the reflection and transmission characteristics of the sound wave at the mold and melt interface, thereby causing the original reference acoustic echo signal to Failure and false alarms occur. To address the challenges brought by this state transition, the system is configured to execute a set of benchmark adaptive compensation procedures. The triggering of this procedure depends on the system receiving a signal from the PLC of the injection molding machine control system indicating that the injection molding material has been changed. This is the preferred information acquisition path; as a backup path, when the material change signal cannot be directly obtained, the system is configured to trigger the compensation procedure when it detects that the integral value or peak value of the injection pressure curve has a systematic jump of more than 10% in more than 5 consecutive injection cycles. After the procedure is started, at the end of the holding phase of a subsequent injection cycle, the signal processing and decision module will control the clamping system of the injection molding machine to apply a perturbation pressure pulse with a certain amplitude and duration to the mold. For example, a pressure pulse with an amplitude of 0.5% of the total clamping force and a duration of 0.1 seconds. The system uses the pressure sensor of the injection molding machine to collect the decay response curve of the melt pressure in the mold cavity caused by the perturbation pressure pulse, and calculates the time taken for the pressure decay response to decay from the peak value to half of the peak value, that is, the pressure half-life. The system obtains a relative viscosity coefficient related to the viscosity of the new material melt, and based on this coefficient, the original reference acoustic echo signal is mapped through a nonlinear mapping function stored in the system. The time domain axis is dynamically adjusted to generate a reference acoustic echo signal that has compensated for the physical properties of the newly replaced material. This mechanism enables the acoustic diagnostic function to maintain the continuity and reliability of its monitoring results under changing production conditions.

[0030] In an industrial environment, tiny bubbles may precipitate from the circulating cooling medium and adhere to the inner wall of the cooling water channel. These bubbles will become acoustic scatterers, and the noise they generate will interfere with the weak signal generated by real mold damage. In order to eliminate the impact of such unclean measurement media, the system is further configured to execute a set of closed-loop self-purification procedures for the cooling water channel. This procedure is automatically triggered when the system determines that there are fluctuation characteristics in the acoustic echo signal that conform to the preset noise interference model, for example, when the short-term variance of the signal continues to be higher than a statistical threshold. At this time, the system controls the working mode of the acoustic pulse injection device, switching from sending a single pulse to sending an acoustic signal that is linearly swept within a specific frequency band, such as 20-100kHz, and the signal processing and decision modules are synchronized and separated. The signal spectrum received by the acoustic echo receiving device is analyzed to identify whether there is a resonance absorption peak generated by bubbles of a specific size in the cooling medium at its resonant frequency. If the resonance absorption peak is identified in the spectrum, the system confirms that there is bubble interference and immediately switches the working mode of the acoustic pulse injection device to send continuous sound waves with a corresponding frequency and appropriately enhanced power corresponding to the resonance absorption peak. This specific frequency of sound wave energy can cause the bubbles attached to the inner wall of the water channel to vibrate, thereby falling off and being carried away by the flowing cooling water. After performing a short acoustic wave clearing operation, the system automatically switches back to the original pulse working mode and re-confirms the benchmark, thereby completing a self-purification closed-loop operation of the acoustic channel. This purification mechanism ensures the high signal-to-noise ratio input required by the diagnostic algorithm.

[0031] In addition to monitoring the health of the mold body, the quality of the injection molded parts is also related to the mixing uniformity of the plastics, especially when using a mixture of recycled and new materials for injection molding. For this reason, the system is also configured to sense the material mixing uniformity without adding hardware. This function is achieved by processing the injection pressure signal obtained by the signal processing and decision module. Specifically, the module applies a high-pass digital filter to the injection pressure signal of each cycle to separate the high-frequency pressure fluctuation residual signal. The pressure curve of a uniformly mixed melt tends to be smooth when it flows, while an unevenly mixed melt will produce small high-frequency resistance fluctuations during the flow. These fluctuations are reflected in the pressure fluctuation residual signal. The system determines the mixing uniformity index of the plastic material in the current cycle by calculating the energy characteristics of the residual signal in an injection molding cycle, such as its root mean square value or variance. When the mixing uniformity index is continuously worse than a preset process threshold, the system can generate control instructions for adjusting the plasticizing parameters of the injection molding machine, such as recommending adjusting the screw back pressure or melt temperature, in order to improve the mixing effect of the material in subsequent production. This will expand the monitoring dimension of the system from the health of the mold equipment to the online perception of the status of the processed material, thereby providing data support for achieving more comprehensive quality control of the injection molding process.

[0032] Example 1: In a production unit for automotive interior panels that provides just-in-time supply to an automaker, an injection mold used to produce center console side trim panels has been running continuously for 300,000 production cycles. According to its regular maintenance plan, it will be disassembled for maintenance at the 400,000th cycle. However, during a data review at the 320,000th cycle, the predictive maintenance system deployed on the mold, and its signal processing and decision module calculated the degradation index The value showed a low-slope but continuous linear growth trend for about 500 consecutive cycles. Its absolute value had not yet reached the preset degradation threshold, so no warning signal was generated. During this period, the closed-loop self-purification procedure of the cooling water channel configured by the system was automatically triggered several times. After switching to the sweep mode, the acoustic pulse injection device identified the resonance absorption peak caused by bubbles in the cooling medium in the spectrum of the received signal and immediately sent sound waves of the corresponding frequency to purify the channel. This process confirmed the aforementioned degradation index. The physical source of the continuous change is not the noise interference of the acoustic channel, but the state evolution of the mold body. When the mold runs to the 335,000th cycle, the degradation index The value exceeded the preset degradation threshold for the first time, and the system immediately generated an early warning signal. However, at this moment, the two process parameters, mold temperature and injection pressure, retrieved from the injection molding machine control system, did not show any identifiable abnormalities compared with the historical fluctuation range.

[0033] The generation of the early warning signal triggered the system's built-in hierarchical diagnostic logic. The signal processing and decision-making module was now configured to perform a high-resolution trend analysis of the injection pressure curve of the last 100 cycles. The analysis results showed that the injection pressure peak had a slight increase of an average amplitude of 0.2%. The system then matched its internally stored association rules, that is, when the deterioration index When both the threshold value and the injection pressure showing an upward trend are met at the same time, the potential fault type is judged as early damage related to abnormal melt flow. The qualitative judgment result and the early warning signal are output to the maintenance terminal together and serve as the basis for targeted inspection of the mold cavity during the next planned material change interval. During the inspection, the maintenance personnel used the dye penetrant flaw detection method and found a surface microcrack less than one millimeter in length at the root of a deep rib in the cavity. This crack is difficult to find under conventional visual inspection. It is the generation of this microcrack that causes the early overflow of a small amount of melt and causes a slight increase in injection pressure. The acoustic monitoring method of this system detects the pressure change through the acoustic echo signal when the pressure change is still within the instrument noise range. The distortion of the micro crack captured the change of this physical state. The micro crack was repaired after local micro area welding and polishing. The entire inspection and repair process was completed within the planned downtime. After the mold resumed production, the degradation index monitored by the system The value also dropped back to the normal baseline level, and a mold failure event that could have led to an unplanned production stoppage was avoided. At the same time, the original 400,000-cycle disassembly maintenance plan also had the objective conditions to be further optimized and extended due to the information obtained on the internal health status of the mold.

[0034] Example 2: To objectively verify the degradation index in the technical solution of the present invention The monitoring sensitivity of the evolution of microscopic damage inside the mold and its early warning compared with traditional process parameters were designed and executed. The purpose of the test is to quantitatively present the degradation index. The correlation between the physical damage inside the mold and a controllable and progressive development is studied. The test uses a standard injection molding machine and a test mold. A replaceable metal plug-in is embedded in the mold cavity. Micron-level scratches of different sizes are pre-processed on the plug-in to simulate the early wear or microcracks generated by the mold in long-term service. A total of five groups of plug-ins are prepared for the test, corresponding to the healthy state, i.e. no scratches, and four damage states with scratch depths of 50 microns, 100 microns, 150 microns and 200 microns. The acoustic pulse injection and receiving device used in the test is consistent with the piezoelectric ceramic vibrator in the aforementioned specific embodiment, and its signal acquisition is carried out by The sampling frequency was set to 1 MHz. The consideration for setting this sampling frequency was to strike a balance between signal fidelity and data processing load. Since the spectral energy of the injected acoustic pulse signal is mainly concentrated below 100 kHz, a sampling frequency ten times the upper limit of the signal bandwidth was chosen to avoid signal aliasing according to the Nyquist sampling theorem and to retain a margin for capturing high-frequency distortion components caused by damage. During the experiment, except for replacing the plug-in to change the damage state, all other injection molding process parameters, including material batch, melt temperature, injection speed, and pressure, were kept constant as a control condition to eliminate the interference of process fluctuations on the monitoring results.

[0035] The test process is as follows: First, a healthy plug-in is installed in the mold and continuously runs for 1,000 injection cycles. During this stage, the system collects data to establish a stable baseline acoustic echo signal. , and record the deterioration index under this health state The baseline fluctuation range is 100%. Then, four groups of damaged plug-ins with scratch depths ranging from 50 microns to 200 microns were replaced in turn. Each group of plug-ins was continuously run for 2,000 injection cycles. In each cycle, the system calculated the degradation index in real time. The value is recorded simultaneously with the peak value of the injection pressure sensor. During the test, it was observed that when the mold switches from a healthy state to a 50 micron damage state, the degradation index The average value of the injection pressure has a step out of the healthy baseline fluctuation range, while the average value of the injection pressure in the same period is still fluctuating within the statistical noise range of the healthy state. As the scratch depth gradually increases, the deterioration index The average value of shows a monotonically increasing trend that is positively correlated with the scratch depth, while the injection pressure value does not begin to rise out of its normal fluctuation range until the scratch depth increases to 150 microns. For relevant core data, see Table 1.

[0036] Table 1: Comparison of degradation index and injection pressure under different damage states.

[0037]

[0038] The phenomenon presented by the above test data is due to the degradation index The calculation is based on the entire acoustic echo signal Waveform and reference signal Even a tiny scratch with a depth of 50 microns, as a new acoustic impedance discontinuity point, is sufficient to produce identifiable scattering or reflection of the propagating sound wave, thereby causing an echo signal. The distortion on the time domain waveform is reflected in the In contrast, the injection pressure mainly depends on the overall resistance of the melt to flow in the cavity. When the scratch depth is not sufficient to have a substantial impact on the macroscopic flow of the melt, the change in injection pressure will be submerged in the process fluctuation noise. Its response does not deviate from the statistical fluctuation range in the initial stage of damage evolution, showing hysteresis.

[0039] Example 3: This example combines Figures 1 to 3 , describes a predictive maintenance system for an automobile interior panel injection mold, such as Figure 1 As shown, an acoustic pulse injection device injects an acoustic pulse into the injection mold containing the cooling water channel. After propagating through the mold, an acoustic echo receiving device receives the echo carrying damage information. The system calculates a degradation index that characterizes the degree of waveform distortion by comparing the acoustic echoes. , and perform degradation index threshold judgment, if the If the value does not exceed the preset threshold, the process returns; if it exceeds the threshold, the system generates an early warning signal on the one hand, and starts a fault qualitative process on the other hand. This process associates macro process parameters such as mold temperature and injection pressure, and makes qualitative judgments on potential fault types, such as flow anomalies or heat dissipation anomalies, based on preset association rules; the system also includes two closed-loop adaptive modules, one of which is the benchmark adaptive compensation, which can sense the material change signal sent by the injection molding machine control system and actively compensate the benchmark acoustic signal to adapt to the physical properties of the new material; the other is the closed-loop self-purification of the cooling water channel, which can identify and actively remove bubble interference in the cooling medium, thereby ensuring the signal-to-noise ratio of the core diagnostic signal.

[0040] like Figure 2 As shown, the figure is in units of scratch depth As the horizontal axis, the dimensionless degradation index The left vertical axis is the injection pressure peak unit The vertical axis on the right side, the solid line connected by the circular data points in the figure represents the degradation index The dotted line connected by the triangle data points represents the change of injection pressure. It can be clearly observed from the figure that when the scratch depth increases from 0 healthy state to 50 When the degradation index The value of the injection pressure increases significantly, while the injection pressure remains basically unchanged until the scratch depth increases to 150 When the injection pressure begins to show a recognizable upward trend, this comparison clearly confirms the deterioration index The sensitivity of the indicator for monitoring early micro damage of the mold is much higher than the traditional injection pressure parameter.

[0041] like Figure 3 As shown, the process begins with the acquisition of acoustic signals from the cooling water channel of the injection mold through module 1.0, thereby obtaining real-time acoustic echo signals. The reference acoustic echo signal stored in the D1 reference acoustic echo signal library when the mold is in a healthy state , then, Module 2.0 is based on and Calculate the degradation index ,Should The value is passed to module 3.0 for diagnosing potential faults. Module 3.0 combines the association rules retrieved from the D2 fault-parameter association rule library and the macro process parameters obtained from the injection molding machine control system to characterize the fault and generate a judgment report for maintenance personnel. In addition, when the injection molding machine control system issues a material change signal, module 4.0 is triggered to perform compensation for the reference signal and update the compensated reference signal to the D1 library, thereby ensuring the continued accuracy of the diagnosis.

[0042] Example 4: In a newly built automobile dashboard air outlet assembly injection molding production line, the matching new mold and the predictive maintenance system of the present invention are subjected to a debugging and calibration procedure before being put into mass production to match the system's internal diagnostic model and control threshold with the physical properties of the specific mold and the production materials. The procedure first calibrates the baseline adaptive compensation function for material changes. On-site engineers prepared three types of plastic particles planned for the production of this product: high-gloss ABS, PC / ABS alloy, and TPE soft plastic. Their respective melt flow indexes are known. The engineers put these three materials into the injection molding machine in turn for trial production. During the stable injection molding stage of each material, the clamping force perturbation pressure pulse in the aforementioned specific embodiment is triggered once. The system uses the injection molding machine pressure sensor to record the melt pressure decay response caused by the pulse and calculates the pressure half-life corresponding to each material. , by combining the three known melt flow indices with the three measured pressure half-lives The numerical value is fitted, and a second-order polynomial curve is generated and stored. This curve is used as a nonlinear mapping function from pressure half-life to relative viscosity coefficient, and is used for the benchmark acoustic echo signal due to material replacement in subsequent production. Motion compensation.

[0043] The procedure then entered the stage of building a fault qualitative association rule library. While ensuring the mold was in a healthy state and using ABS material for stable production, engineers artificially introduced fault simulations. By placing a 0.05 mm thick metal gasket on the mold parting surface, they simulated flow anomalies caused by early flash or microcracks. The system ran the mold continuously for 100 cycles in this state, and the system recorded any degradation index that continued to exceed the degradation threshold during this period. The values ​​of the injection pressure data, which showed a slight upward trend, were collected simultaneously. This set of data pairs was stored in the association rule library, which defined the association between the degradation index exceeding the threshold and the injection pressure increase. After that, the gasket was removed to restore the mold to health. Then, the outlet of one of the cooling water channels was partially blocked to simulate heat dissipation abnormality. The system also ran for 100 consecutive cycles and recorded the degradation index in this state. The system detects the over-threshold phenomenon and the slowdown in the rate of decrease in the local temperature of the mold after the product is ejected. This data is stored in the rule library. In this way, through physical simulation and data collection of several typical failure modes, a set of data-supported qualitative fault judgment logic is established, from acoustic fingerprint anomalies to changes in specific process parameters.

[0044] Finally, the procedure calibrated the threshold of the accompanying perception function of material mixing uniformity. The engineer first used 100% pure ABS new material for 200 cycles of injection molding and recorded the statistical distribution of the mixing uniformity index calculated from the pressure fluctuation residual signal, with a mean of 0.08. Then, the material was replaced with a mixture of new material and recycled material in a ratio of 7 to 3, and the same 200 cycles were run. At this time, the mean of the mixing uniformity index rose to 0.25, and some of the products produced had flow marks on the appearance. Combined with the offline quality inspection of the product, the engineer used the The process threshold of the mixing uniformity index is set at 0.18, which is between the statistical upper limit of the index distribution in the pure new material production state and the statistical lower limit of the index distribution when the mixed material production has appearance defects. By executing the above complete debugging and calibration procedures, all algorithm models, association rules and process thresholds related to specific molds and materials within the predictive maintenance system are given definite values ​​from on-site measurements. All functional modules of the system have been transformed from the initial general configuration state to a dedicated state for this specific production task, providing status monitoring and process control guarantees for the upcoming mass production.

[0045] Example 5: In the actual operating environment of an injection molding workshop, the circulating water supply temperature of its cooling water system deviates by more than 15 degrees Celsius between winter and summer due to seasonal temperature differences. This change in the physical properties of the cooling water, which serves as the acoustic diagnostic medium, will cause the baseline acoustic echo signal of a healthy mold to Drift occurs and causes degradation index The system is configured to continuously monitor the temperature readings at the cooling water inlet in the background and calculate its 24-hour sliding average. When the sliding average is compared with the current reference acoustic echo signal stored in the system, the system will generate an indication that is not related to mold damage. When the temperature value corresponding to the acquisition exceeds 5 degrees Celsius, the system generates an instruction to prompt the operator to update the acoustic baseline at the next planned shutdown. After obtaining the operator's confirmation input that the mold status is normal, the system automatically executes a new baseline acoustic echo signal The water temperature at the time of collection is used as the new reference temperature.

[0046] The triggering of the closed-loop self-purification procedure of the cooling water channel is based on a dual-condition judgment logic. The execution of this logic is that the signal processing and decision modules simultaneously test the signal characteristics of two dimensions. The first dimension is the stability of the short-term degradation index, which is determined by judging the degradation index of the last ten injection cycles. The second dimension is the frequency domain characteristics of the signal, which is achieved by analyzing the received acoustic echo signal. Perform spectrum analysis to determine whether the signal energy integral within the high-frequency noise observation band is greater than a second energy threshold. When the above two conditions are met at the same time, the system determines that there is channel noise interference caused by bubbles and starts the subsequent frequency sweep identification and resonance removal process.

[0047] Example 6: When the predictive maintenance system of the present invention is first deployed on an injection mold with multiple parallel cooling circuits for producing automotive B-pillar interior covers, a pre-engineering configuration procedure is required to determine the system's physical installation and signal parameters. This procedure provides a basis for subsequent system debugging and calibration. The first step of this procedure is to determine the installation locations of the acoustic pulse injection device and the acoustic echo receiving device. The engineering personnel use the mold's cooling system design drawings to determine the installation locations according to a selection procedure. The procedure specifies that two piezoelectric ceramic vibrators be installed on the main water supply manifold and the main water return manifold, respectively. This layout allows the injected acoustic pulse to traverse all parallel cooling circuits within the mold, thereby obtaining a global acoustic echo signal reflecting the overall status of the mold. The procedure also stipulates that if enhanced monitoring of a known high-risk area is required in the future, a pair of vibrators can be added to the branches of that specific circuit for local diagnosis.

[0048] After the location was determined, the procedure entered the calibration phase of the core parameters of the acoustic pulse. Engineers performed a channel attenuation test, sending a sweeping signal with a linear frequency sweep from 10kHz to 150kHz into the selected main waterway through the acoustic pulse injection device. The acoustic echo receiving device simultaneously recorded the signal amplitude at different frequencies. Based on the test results, the engineers selected the 20kHz to 80kHz frequency band as the operating frequency band, where the signal attenuation was lower than a preset decibel value and the signal-to-noise ratio was higher than a preset ratio. Within this frequency band, the center frequency of the diagnostic acoustic pulse signal was set to 50kHz, and its pulse width was set to 50 microseconds. This setting was intended to balance signal energy and time resolution. The pulse injection amplitude was determined by a feedback adjustment program, starting from a low initial voltage, gradually increasing the driving voltage of the injection device while monitoring the spectrum of the received signal. When the second harmonic component caused by the nonlinear effect of the acoustic wave began to appear in the spectrum, 90% of the driving voltage at that time was set as the operating voltage.

[0049] Finally, the procedure specifies an algorithm for generating qualitative association rules for faults. After obtaining a field data set with fault labels according to the above method, the signal processing and decision module uses the C4.5 decision tree algorithm to process the data set to automatically generate association rules. The input feature of the algorithm is the quantified degradation index. The output of the algorithm is a specific fault type judgment. By adopting this well-known algorithm, the construction path from raw data to diagnostic logic is reproducible. After completing the above-mentioned pre-engineering configuration procedures, the hardware installation, signal parameters and core algorithms of the predictive maintenance system on the current B-pillar interior cover mold have been adapted, providing a definite initial condition for subsequent system debugging and calibration work.

[0050] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A predictive maintenance system for automobile interior panel injection molds, characterized in that: The system includes: an acoustic pulse injection device, disposed at the cooling water channel inlet of the mold, for injecting an acoustic pulse signal having a reference waveform into the cooling medium circulating in the cooling water channel; An acoustic echo receiving device is arranged at the outlet of the cooling water channel and is used to receive the acoustic echo signal after the water flows through the mold; A signal processing and decision module is connected to the acoustic pulse injection device and the acoustic echo receiving device, and the signal processing and decision module is configured to: store the reference acoustic echo signal measured by the acoustic echo receiving device when the mold is in a healthy state ; Real-time acoustic echo signal received by acoustic echo receiving device and the reference acoustic echo signal Perform time domain cross-correlation operation and determine a characterizing acoustic echo signal based on the operation result Relative to the reference acoustic echo signal Deterioration index of the degree of distortion on the waveform ; Deterioration index Compared with the degradation threshold, the degradation index When the degradation threshold is exceeded, an early warning signal is generated; and after the early warning signal is generated, the two macro parameters of mold temperature and injection pressure related to the injection molding process are further retrieved, based on the stored degradation index The association rules between abnormalities and changes in macro parameters are used to make qualitative judgments on potential fault types.

2. The predictive maintenance system for automobile interior panel injection mold according to claim 1 is characterized in that: The signal processing and decision module is configured to determine the degradation index by the following mathematical relationship: , ,in, is the acoustic echo signal received in real time. is the reference acoustic echo signal, is the maximum value of the cross-correlation function of the two signals, is the energy of the reference acoustic echo signal.

3. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: The signal processing and decision module is further configured to perform a benchmark adaptive compensation. After receiving a signal indicating that the injection molding material has been changed from the injection molding machine control system, the signal processing and decision module controls the clamping system of the injection molding machine to apply a perturbation pressure pulse with a certain amplitude and duration to the mold in a subsequent injection molding cycle. The signal processing and decision module uses the pressure sensor of the injection molding machine to collect the attenuation response of the melt pressure in the mold cavity caused by the perturbation pressure pulse, and based on the characteristics of the pressure attenuation response, performs a benchmark acoustic echo signal. Dynamic compensation is performed to generate a compensated reference acoustic echo signal adapted to the physical properties of the new replacement material.

4. The predictive maintenance system for automobile interior panel injection mold according to claim 3 is characterized in that: The signal processing and decision module is configured to calculate the time taken for the pressure decay response to decay from a peak value to half of the peak value as the pressure half-life, and determine a relative viscosity coefficient related to the viscosity of the new material melt based on the pressure half-life; and the signal processing and decision module uses a stored nonlinear mapping function to map the reference acoustic echo signal based on the relative viscosity coefficient. The time domain axis is adjusted.

5. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: The signal processing and decision module is also configured to perform closed-loop self-purification of the cooling water channel. When the signal processing and decision module determines that there are fluctuation characteristics in the acoustic echo signal that conform to the noise interference model, the signal processing and decision module controls the acoustic pulse injection device to send a swept-frequency acoustic signal; and the signal processing and decision module analyzes the signal spectrum received by the acoustic echo receiving device to identify the resonance absorption peak caused by bubbles in the cooling medium.

6. The predictive maintenance system for automobile interior panel injection mold according to claim 5, characterized in that: When the signal processing and decision module identifies the resonance absorption peak, it controls the acoustic pulse injection device to send sound waves corresponding to the resonance absorption peak frequency to remove bubbles attached to the inner wall of the cooling water channel. After the bubbles are removed, it switches back to the original working mode and re-determines the degradation index. .

7. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: The signal processing and decision-making module is also configured to perform accompanying perception of the material mixing uniformity. The signal processing and decision-making module processes the injection pressure signal to separate the high-frequency pressure fluctuation residual signal; and the signal processing and decision-making module determines the mixing uniformity index of the plastic material in the current injection molding cycle based on the energy characteristics of the pressure fluctuation residual signal. When the mixing uniformity index is worse than the process threshold, it generates a control instruction for adjusting the plasticizing parameters of the injection molding machine.

8. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: The acoustic pulse injection device and the acoustic echo receiving device are both piezoelectric ceramic vibrators.

9. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: Association rules include: when the deterioration index When the degradation threshold is exceeded and the injection pressure shows an upward trend, the potential failure type is determined to be flow abnormality related to flash or micro cracks.

10. The predictive maintenance system for automobile interior panel injection mold according to claim 1, characterized in that: Association rules include: when the deterioration index When the degradation threshold is exceeded and the local temperature drop rate of the mold slows down after the product is ejected, the potential fault type is determined to be a heat dissipation abnormality related to carbon deposition or decreased cooling efficiency.

Images