Multi-parameter coupling intelligent lubrication method and system for injection molding machine lock shaft sleeve

Abstract

The present application relates to injection molding machine lubrication technical field, provide a kind of injection molding machine lock axle sleeve multi-parameter coupling intelligent lubrication method and system, the method includes: obtaining the operating condition parameter of injection molding machine;Based on operating condition parameter and lubrication coefficient prediction model, determine the lubrication coefficient under current condition;Obtain ambient temperature, compensate lubrication coefficient by room temperature compensation model, obtain compensated lubrication coefficient;Cumulative iterative calculation is carried out to compensated lubrication coefficient, and cumulative lubrication coefficient is obtained;In the case where it is determined that cumulative lubrication coefficient is greater than or equal to lubrication trigger threshold α, control lubrication actuator to lubricate lock axle and axle sleeve, and clear cumulative lubrication coefficient zero.The present application realizes on-demand lubrication, can accurately control lubrication interval and total amount of lubrication, ensure that lock axle sleeve is always in the best lubrication state, solve the defect that cannot adapt to complex working condition change in prior art.

Description

Technical Field

[0001] This invention relates to the field of injection molding machine lubrication technology, and in particular to a multi-parameter coupling intelligent lubrication method and system for injection molding machine locking shaft sleeves. Background Technology

[0002] As a key component of injection molding machines, the mold opening and closing mechanism is responsible for completing the opening and closing actions of the mold. Among them, the locking shaft and bushing are the core kinematic pairs that bear the largest load and move the most frequently. During the injection molding process, the locking shaft and bushing not only have to withstand clamping forces of up to thousands of tons, but also have to perform high-frequency reciprocating rotational motion. Good lubrication is a key factor in ensuring the normal operation of the locking shaft and bushing and extending their service life. Poor lubrication will directly lead to equipment failure and production interruption.

[0003] Currently, the lubrication control technology for locking bushings in the injection molding machine industry generally adopts the traditional timed and quantitative forced lubrication mode. This mode involves pre-setting fixed lubrication intervals and the amount of lubricating oil per application, with the lubrication pump automatically supplying oil to the lubrication points according to a pre-set program. While this lubrication method is simple in structure and low in cost, it completely ignores the changes in actual production conditions and the true wear state of the locking bushing, resulting in the following drawbacks: Firstly, timed and metered lubrication inevitably leads to problems of over- or under-lubrication. When the injection molding machine is operating under light load and low speed, the actual wear rate is low, and a fixed lubrication frequency will result in excessive lubricating oil. This not only causes serious waste of lubricating grease but also allows excess grease to leak onto the mold and product surface, contaminating the mold cavity and plastic product, increasing subsequent cleaning workload and production costs. Conversely, when the injection molding machine is operating under heavy load and high speed, the actual wear rate accelerates significantly, and a fixed lubrication frequency cannot meet the lubrication requirements, resulting in under-lubrication.

[0004] Insufficient lubrication causes direct contact between the metal surfaces of the locking shaft and the bushing, drastically increasing the coefficient of friction. This leads to abnormally high bushing temperatures, exponentially increasing wear rates, and significant operating noise. As wear intensifies, the clearance between the locking shaft and the bushing gradually increases, affecting the motion accuracy of the mold opening and closing mechanism and the stability of the clamping force. In extreme cases, insufficient lubrication can cause the locking shaft and bushing to seize up, resulting in sudden equipment shutdown or even serious accidents such as locking shaft breakage. Summary of the Invention

[0005] This invention aims to at least solve one of the technical problems existing in related technologies. To this end, this invention proposes a multi-parameter coupling intelligent lubrication method for the locking bushing of an injection molding machine.

[0006] This invention also proposes a multi-parameter coupled intelligent lubrication system for the locking shaft sleeve of an injection molding machine.

[0007] A multi-parameter coupling intelligent lubrication method for injection molding machine lock shaft and bushing according to an embodiment of the present invention is used to lubricate the mating pair of the injection molding machine lock shaft and bushing, including: Obtain the operating parameters of the injection molding machine, wherein the operating parameters include at least clamping force, mold opening and closing speed, mold opening and closing stroke, and number of modules; Based on the operating condition parameters and the lubrication coefficient prediction model, the lubrication coefficient under the current operating condition is determined. The lubrication coefficient prediction model is trained based on multi-condition test data and is used to characterize the coupling relationship between different operating condition parameters and lubrication requirements. The ambient temperature is obtained, and the lubrication coefficient is compensated using a room temperature compensation model to obtain the compensated lubrication coefficient. The cumulative lubrication coefficient is obtained by performing cumulative iterative calculation on the compensated lubrication coefficient; If the cumulative lubrication coefficient is determined to be greater than or equal to the lubrication trigger threshold α, the lubrication actuator is controlled to lubricate the lock shaft and bushing, and the cumulative lubrication coefficient is reset to zero.

[0008] According to one embodiment of the present invention, after obtaining the operating condition parameters of the injection molding machine, the method further includes: Real-time acquisition of bushing temperature data, followed by filtering of the acquired bushing temperature data; The filtered temperature data is differentiated to obtain the temperature rise slope curve. The wear initiation point is identified based on the variation characteristics of the temperature rise slope curve with the operating modulus.

[0009] According to one embodiment of the present invention, identifying the wear initiation point based on the variation characteristics of the temperature rise slope curve with the operating modulus specifically includes: A starting point is selected on the temperature rise slope curve. If the slope difference between the starting point and the subsequent preset number of points is positive, and the slope of the preset number of points is greater than the preset slope threshold, and the sleeve temperature rise is greater than the preset temperature rise threshold within a preset length sliding window, then the point is determined to be the wear starting point, and the corresponding operating modulus is the lubrication critical modulus.

[0010] According to one embodiment of the present invention, the method further includes: determining whether the operating conditions of the injection molding machine have changed; If it is determined that the operating conditions have changed or the equipment is started for the first time, the step of obtaining the operating condition parameters of the injection molding machine is performed, and the cached data is updated.

[0011] According to one embodiment of the present invention, the method further includes: when it is determined that the operating conditions have not changed or that this is not the first startup, invoking the cached lubrication coefficient.

[0012] According to one embodiment of the present invention, the method further includes: if it is determined that the cumulative lubrication coefficient is less than the lubrication trigger threshold α, performing the step of determining whether the operating conditions of the injection molding machine have changed.

[0013] According to one embodiment of the present invention, it further includes: When the operating conditions change, the current cumulative lubrication coefficient is retained and directly substituted into the new operating conditions to continue the cumulative calculation, while the lubrication trigger threshold α remains unchanged.

[0014] A multi-parameter coupling intelligent lubrication system for an injection molding machine locking bushing according to an embodiment of the present invention includes: The working condition acquisition unit is used to acquire clamping force, mold opening and closing speed, and mold opening and closing stroke parameters in real time. Temperature acquisition unit, used to acquire bushing temperature data; A room temperature acquisition unit, which is used to acquire ambient temperature parameters in real time; The main control unit is electrically connected to the temperature acquisition unit, the operating condition acquisition unit, and the room temperature acquisition unit, and is used to execute the above-mentioned multi-parameter coupled intelligent lubrication method for the injection molding machine locking shaft sleeve. The main control unit has a built-in lubrication coefficient prediction model, room temperature compensation model, and lubrication control algorithm, which is used to calculate the lubrication coefficient based on the operating condition parameters and perform cumulative iterative calculation. When the cumulative lubrication coefficient reaches the lubrication trigger threshold α, a control signal is output. The lubrication execution unit is electrically connected to the main control unit. The lubrication execution unit is used to receive control signals from the main control unit and complete the fixed-point lubrication action of the locking shaft sleeve.

[0015] According to one embodiment of the present invention, the temperature acquisition unit includes a temperature sensor mounted on a bushing connecting rod, the connecting rod being interference-fitted with the bushing, and the temperature sensor being used to acquire temperature data of the bushing and transmit it to the main control unit to complete the identification of the wear initiation point.

[0016] According to one embodiment of the present invention, the lubrication actuator includes: Lubrication pump, At least one metering valve is provided, and the oil outlet of the lubrication pump is connected to the oil inlet of each metering valve via a pipeline. The lubrication pump and each metering valve are electrically connected to the main control unit. At least one lubrication nozzle is provided, and the lubrication nozzle is connected to the oil outlet of the metering valve through a pipeline to control the amount of lubricating grease used in a single operation.

[0017] The above-described one or more technical solutions in the embodiments of the present invention have at least one of the following technical effects: This invention introduces a lubrication coefficient prediction model, coupling multiple parameters such as clamping force, mold opening and closing speed, mold opening and closing stroke, and operating module to achieve precise quantification of lubrication requirements. By correcting the influence of ambient temperature through a room temperature compensation model and through cumulative iterative calculation and threshold triggering mechanism, it achieves on-demand lubrication, which can accurately control the lubrication interval and total amount of lubrication. This avoids the problems of over-lubrication or under-lubrication caused by traditional timed and quantitative lubrication, ensuring that the locking shaft sleeve is always in the optimal lubrication state. This method fundamentally solves the shortcomings of existing technologies that cannot adapt to complex working conditions.

[0018] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention and are not considered as limitations on this application. Moreover, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0020] Figure 1 This is a schematic structural diagram of a multi-parameter coupled intelligent lubrication system for a locking shaft sleeve of an injection molding machine provided by the present invention.

[0021] Figure 2 This is the bushing temperature-operating modulus variation curve provided by the present invention.

[0022] Figure 3 This is the temperature rise slope curve and sudden rise point identification diagram provided by the present invention.

[0023] Figure 4 This is a schematic diagram of the two-layer neural network model structure provided by the present invention.

[0024] Figure 5 This is the room temperature-lubrication compensation coefficient relationship curve provided by the present invention.

[0025] Figure 6 This is a flowchart of the intelligent lubrication control algorithm provided by the present invention.

[0026] Figure label: 1. Bushing; 2. Locking shaft; 3. Connecting rod; 4. Temperature sensor; 5. Lubrication nozzle; 6. Metering valve; 7. Lubrication pump. Detailed Implementation

[0027] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0028] The specific terms used in this specification are for illustrative purposes only and are not intended to limit the illustrated embodiments. For example, expressions such as "same" and "identical" not only indicate a strictly identical state, but also indicate a state with tolerances or differences in the degree of functionality. For example, expressions indicating relative or absolute arrangement such as "in a certain direction," "along a certain direction," "side by side," "perpendicular," "centered on," "concentric," or "coaxial" not only strictly indicate such an arrangement, but also indicate a state of relative displacement by tolerances or angles or distances with the same degree of functionality.

[0029] The terms “center,” “longitudinal,” “lateral,” “length,” “width,” “thickness,” “upper,” “lower,” “front,” “rear,” “left,” “right,” “vertical,” “horizontal,” “top,” “bottom,” “inner,” “outer,” “clockwise,” “counterclockwise,” “axial,” “radial,” and “circumferential” indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the present invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.

[0030] Furthermore, features specified as "first" or "second" may explicitly or implicitly include one or more of those features. In the description of this invention, unless otherwise stated, "multiple" means two or more. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0031] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0032] The following is combined with Figures 1 to 6 This invention describes a multi-parameter coupling intelligent lubrication system and method for a locking shaft sleeve of an injection molding machine.

[0033] This embodiment provides a multi-parameter coupled intelligent lubrication method for injection molding machine locking shaft and bushing, used to lubricate the mating pair between injection molding machine locking shaft 2 and bushing 1, including the following steps: S100: Obtain the operating parameters of the injection molding machine, including at least the clamping force, mold opening and closing speed, mold opening and closing stroke, and number of modules. S200: Based on the operating condition parameters and the lubrication coefficient prediction model, the lubrication coefficient under the current operating condition is determined. The lubrication coefficient prediction model is trained based on multi-condition test data and is used to characterize the coupling relationship between different operating condition parameters and lubrication requirements. S300: Obtain the ambient temperature, compensate the lubrication coefficient using a room temperature compensation model, and obtain the compensated lubrication coefficient; S400: Perform cumulative iterative calculation on the compensated lubrication coefficient to obtain the cumulative lubrication coefficient; S500: When the cumulative lubrication coefficient is determined to be greater than or equal to the lubrication trigger threshold α, the lubrication actuator is controlled to lubricate the locking shaft 2 and the bushing 1, and the cumulative lubrication coefficient is cleared to zero.

[0034] This invention introduces a lubrication coefficient prediction model, coupling multiple parameters such as clamping force, mold opening and closing speed, mold opening and closing stroke, and operating module to achieve precise quantification of lubrication requirements. By correcting the influence of ambient temperature through a room temperature compensation model and through cumulative iterative calculation and threshold triggering mechanism, it achieves on-demand lubrication, which can accurately control the lubrication interval and total amount of lubrication. This avoids the problems of over-lubrication or under-lubrication caused by traditional timed and quantitative lubrication, ensuring that the locking shaft 2 and the bushing 1 are always in the optimal lubrication state. This method fundamentally solves the defects of existing technologies that cannot adapt to complex working conditions.

[0035] In some embodiments, step S100 involves real-time acquisition of operating parameters using various sensors installed on the injection molding machine. Specifically, clamping force is acquired by a clamping force sensor, mold opening and closing speeds and strokes are acquired by displacement and speed sensors, and the number of operating cycles is counted by a counter inside the injection molding machine controller, representing the number of mold opening and closing cycles completed by the injection molding machine. All parameters are transmitted to the injection molding machine controller in digital signal form.

[0036] The lubrication coefficient prediction model in step S200 is trained based on multi-condition test data and is used to characterize the coupling relationship between different operating condition parameters and lubrication requirements. This model can output a lubrication coefficient value in the range of 0 to 1 based on the input clamping force, mold opening and closing speed, mold opening and closing stroke, and number of cycles. This value reflects the degree of lubrication required per unit cycle under the current operating condition. The larger the lubrication coefficient, the more severe the wear per cycle under the current operating condition.

[0037] In step S300, the ambient temperature can be collected in real time by a room temperature sensor installed in the electrical cabinet of the injection molding machine or near the machine body. The ambient temperature is input into a preset room temperature compensation model to obtain a room temperature lubrication compensation coefficient. This compensation coefficient is used to compensate and correct the lubrication coefficient obtained in step S200 to obtain the compensated lubrication coefficient. Since the ambient temperature directly affects the viscosity of the lubricating grease and the thermal expansion state of the bushing 1, room temperature compensation is an important step to ensure lubrication accuracy.

[0038] In step S400, the compensated lubrication coefficient is iteratively accumulated according to a preset accumulation rule to obtain the cumulative lubrication coefficient. The cumulative lubrication coefficient reflects the total accumulated lubrication demand under the current operating conditions since the last lubrication.

[0039] In step S500, the cumulative lubrication coefficient obtained in step S400 is compared with the preset lubrication trigger threshold α. If the cumulative lubrication coefficient is greater than or equal to the lubrication trigger threshold α, the lubrication actuator is controlled to perform fixed-point lubrication on the locking shaft 2 and the bushing 1. After the lubrication is completed, the cumulative lubrication coefficient is cleared to zero, and the process returns to step S100 to continue monitoring.

[0040] In this embodiment of the invention, after obtaining the operating parameters of the injection molding machine in step S100, the method further includes: Step S110: Real-time acquisition of temperature data of bushing 1, and filtering of the acquired temperature data of bushing 1; by filtering the real-time acquired temperature data of bushing 1, high-frequency noise interference is eliminated and the trend characteristics of temperature change are preserved. The filtering can be carried out by moving average filtering, Kalman filtering or low-pass filtering.

[0041] For example, by using a moving average filtering algorithm to process the raw temperature data, the average of five consecutive sampling points can be taken as the current temperature value, effectively eliminating electromagnetic interference and temperature fluctuation noise in the industrial field while preserving the trend characteristics of temperature changes.

[0042] Step S120: Perform differential operation on the filtered temperature data to obtain the temperature rise slope curve; by performing differential operation on the filtered temperature-operation modulus curve, the temperature rise slope-operation modulus curve is obtained. The temperature rise slope represents the increase in temperature of bushing 1 for each operation, which can more sensitively reflect the change in friction state of bushing 1.

[0043] Step S130: Identify the wear initiation point based on the change characteristics of the temperature rise slope curve with the operating modulus. By monitoring the change characteristics of the temperature rise slope curve in real time, when an abnormal sudden increase in the temperature rise slope is detected, it is determined to be the wear initiation point.

[0044] With this setup, the absolute value of the sleeve 1 temperature is affected by various factors such as ambient temperature and operating time, making it difficult to directly use for wear judgment. However, the temperature rise slope can directly reflect the rate of frictional heat generation and is highly correlated with the wear state. By filtering and differentiating the temperature data, the temperature rise slope feature can be accurately extracted, enabling early identification of the wear initiation point. This invention, by introducing sleeve 1 temperature monitoring and temperature rise slope analysis, can identify the wear initiation signal in the early stage of wear, achieving early warning of wear. It effectively avoids serious failures such as sleeve 1 seizing or breaking due to insufficient lubrication, significantly reducing downtime and maintenance costs.

[0045] In this embodiment, the temperature rise slope of bushing 1 exhibits a typical three-stage variation characteristic with the operating modulus: The first stage is the decreasing stage, during which the new bushing 1 is in its running-in period, the contact surfaces gradually break in, the coefficient of friction decreases, and the temperature rise slope gradually decreases. The second stage is the sudden increase stage, when bushing 1 enters the normal wear period, the friction condition deteriorates, and the temperature rise slope suddenly increases. The third stage is the decreasing stage, when the wear enters the stable period or lubrication is introduced, the temperature rise slope tends to stabilize or decrease again. The starting point of the sudden increase in slope is the wear starting point of bushing 1 of locking shaft 2.

[0046] Step S130 identifies the wear initiation point based on the variation characteristics of the temperature rise slope curve with the operating modulus, specifically including: Select a starting point on the temperature rise slope curve. If the slope difference between the starting point and the subsequent preset number of points is positive, and the slope of the preset number of points is greater than the preset slope threshold, and the temperature rise of bushing 1 is greater than the preset temperature rise threshold within a preset length of sliding window, then the point is determined to be the wear starting point, and the corresponding operating modulus is the lubrication critical modulus.

[0047] In some specific embodiments, during the injection molding machine commissioning phase, the following parameters can be preset according to the machine model, the material of bushing 1, and the type of lubricating grease: number of continuous points N=8, preset slope threshold K0=0.06℃ / mold, sliding window length L=20 points, and preset temperature rise threshold ΔT0=0.7℃. These parameters can be adaptively adjusted according to actual operating conditions.

[0048] Judgment Process: Select a starting point on the temperature rise slope curve. Scan backward from this starting point. If the slope difference between the subsequent preset number of points (e.g., 8) and the starting point is positive, it indicates that the temperature rise slope is continuously increasing. Furthermore, if the slope of the preset number of points is greater than a preset slope threshold K0 (e.g., 0.06), it indicates that the temperature rise slope has reached an abnormal level. Simultaneously, within a preset length L (e.g., 20 points) of a sliding window starting from the judgment starting point, if the temperature rise of bushing 1 is greater than a preset temperature rise threshold ΔT0 (e.g., 0.7℃), it indicates that the temperature rise has actual physical significance rather than noise interference, excluding temporary temperature rises caused by accidental factors. When all three conditions are met simultaneously, this point is determined to be the wear starting point, and the corresponding operating modulus is the lubrication critical modulus.

[0049] When the above three conditions are met simultaneously, the controller determines that the starting point of the determination is the wear starting point, records the corresponding operating modulus as the lubrication critical modulus, and triggers an audible and visual alarm signal to prompt the operator to perform timely inspection and maintenance.

[0050] This design defines specific rules for determining the wear initiation point. The requirement for a continuous number of points ensures the continuity of the temperature rise slope's upward trend; the slope threshold requirement ensures the anomaly of the temperature rise rate; and the sliding window temperature rise requirement ensures the cumulative effect of the temperature rise. This determination method, through a combination of multiple conditions, effectively avoids misjudgments and omissions, ensuring the accuracy and reliability of wear initiation point identification. It can accurately identify wear in its early stages, issuing early warnings and allowing maintenance personnel sufficient time to handle the situation, thus preventing accidents.

[0051] In this embodiment, the training steps for the lubrication coefficient prediction model include: A multi-condition coupled test was designed using the Taguchi method. The clamping force, mold opening and closing speed, and mold opening and closing stroke were each set with at least two different levels. The room temperature was kept constant, and multiple sets of working condition data were collected to construct a lubrication coefficient sample set. The lubrication coefficient ranges from 0 to 1. The lubrication coefficient is 1 when the critical lubrication modulus is reached. Under a single working condition, the lubrication coefficient is linearly related to the operating modulus. The lubrication coefficients under different working conditions are linearly superimposed. The lubrication coefficient prediction model is trained using a sample set, and the trained model is deployed in the injection molding machine controller.

[0052] In some embodiments, the Taguchi Method is used to design a multi-condition coupled test. The three parameters of clamping force, mold opening and closing speed, and mold opening and closing stroke are each set with at least two different levels, preferably 100%, 75%, and 50%, while the room temperature is kept constant. The Taguchi Method orthogonal experimental design is used to form a total of 9 standard test conditions. In a constant temperature laboratory, the injection molding machine is allowed to run automatically and continuously under each set of conditions until the wear initiation point is detected, and the lubrication critical modulus corresponding to each set of conditions is recorded.

[0053] Based on the critical lubrication modulus obtained from the test, a lubrication coefficient in the range of 0 to 1 is constructed to achieve normalization. Under a single operating condition, the lubrication coefficient is set to have a strictly linear proportional relationship with the operating modulus; that is, when the operating modulus reaches 50% of the critical modulus, the lubrication coefficient is 0.5. When the operating condition changes, the wear effects produced by different operating conditions are linearly superimposed, meaning the total lubrication coefficient equals the sum of the lubrication coefficients under each operating condition. This simplifies the handling of varied operating condition combinations and reduces the complexity of model training. A two-layer neural network is trained using a pre-constructed sample set, with the training objective being to minimize the error between the model-predicted lubrication coefficient and the actual lubrication coefficient. When the error no longer decreases, training stops, and the parameters (weights and biases) of the trained neural network model are exported and stored in the injection molding machine's controller (such as a PLC). During operation, the controller directly calls these parameters for real-time calculations without requiring retraining.

[0054] This setup, employing the Taguchi method to design multi-condition tests, enables the acquisition of the most comprehensive operating condition data with the fewest number of tests, reducing testing costs and time. The lubrication coefficient sample is constructed through linear relationships, which is simple, reasonable, and conforms to the fundamental law of linear accumulation of wear over operating time. Furthermore, the dual-layer neural network model possesses powerful nonlinear fitting capabilities, accurately representing the complex coupling relationships between multiple parameters. Deploying the trained model in the controller enables real-time prediction of the lubrication coefficient without relying on cloud or external computing resources, ensuring the system's independence and reliability.

[0055] Furthermore, the lubrication coefficient prediction model is a two-layer neural network model, including an input layer, a hidden layer, and an output layer. The input layer receives input parameters including clamping force ratio, mold opening and closing speed ratio, mold opening and closing stroke ratio, and operating modulus. The output layer outputs the lubrication coefficient.

[0056] like Figure 4 As shown, the two-layer neural network model consists of an input layer, a hidden layer, and an output layer, for a total of three layers. The input layer has four neurons, corresponding to four input parameters: clamping force ratio (0~1), opening / closing speed ratio (0~1), opening / closing stroke ratio (0~1), and operating modulus. The connection weights w from the input layer to the hidden layer are also shown.（1） The bias is b （1） All input parameters are normalized to ensure consistent numerical ranges, thereby improving model training efficiency and accuracy.

[0057] The hidden layer has 10 neurons. The number of neurons is determined by a combination of fitting accuracy and computational complexity. Increasing the number of neurons can improve fitting accuracy, but it will increase the computational load; decreasing the number of neurons will decrease fitting accuracy. Ten neurons achieve the best balance between accuracy and speed in this application scenario.

[0058] The output layer has one neuron, which outputs the lubrication coefficient under the current operating conditions; the connection weight from the hidden layer to the output layer is w. （2） The bias is b （2） By choosing an appropriate activation function, the output value can be strictly constrained to the range of 0 to 1.

[0059] This configuration, employing a single-hidden-layer neural network structure, results in fewer model parameters, faster training speed, and lower computational cost, making it ideal for embedded real-time applications. The four input parameters comprehensively cover the main operating conditions affecting the lubrication requirements of locking shaft 2 and bushing 1, ensuring the model's prediction accuracy. The lubrication coefficient output in the 0-1 range facilitates subsequent cumulative calculations and threshold judgments, resulting in simple and clear control logic.

[0060] Furthermore, the hidden layer of the two-layer neural network model uses the ReLU activation function, while the output layer uses the Sigmoid activation function. Each neuron in the hidden layer uses the ReLU (Modified Linear Unit) activation function, which maintains linear growth in the positive interval and outputs zero in the negative interval. The ReLU activation function has advantages such as simple computation, fast convergence speed, and effective mitigation of the gradient vanishing problem, making it the most commonly used activation function for hidden layers in neural networks. The neurons in the output layer use the Sigmoid activation function, which can map any real number input to the (0,1) interval, adapting to the range requirements of the lubrication coefficient, and producing a smooth output curve, ensuring the continuity and boundedness of the output. Through the reasonable combination of these two activation functions, the model achieves both accuracy and computational efficiency.

[0061] In this embodiment, the room temperature compensation model is obtained by testing the relationship between ambient temperature and critical operating modulus under the condition that the clamping force, mold opening and closing speed and mold opening and closing stroke of the injection molding machine are all set to the rated values, and fitting the model. The room temperature compensation model is used to output the room temperature lubrication compensation coefficient.

[0062] Specifically, in a laboratory environment with precise temperature control, the clamping force, mold opening and closing speed, and mold opening and closing stroke of the injection molding machine are all set to 100% of their rated values. Within the normal operating temperature range of 10℃ to 40℃, a test point is set every 5℃, for a total of 7 test points. At each temperature point, the injection molding machine is run automatically and continuously. The wear initiation point is determined by the temperature rise slope identification method, and the corresponding critical lubrication modulus is recorded.

[0063] The seven sets of data points (temperature, compensation coefficient) obtained from the test were subjected to polynomial fitting to obtain a smooth room temperature-lubrication compensation coefficient curve, as shown below. Figure 5 As shown, the polynomial coefficients of this curve are stored in the injection molding machine's controller as a room temperature compensation model. This model is used to output the room temperature lubrication compensation coefficient; the compensation coefficient is smaller at low temperatures (relatively lower lubrication requirements) and larger at high temperatures (relatively higher lubrication requirements).

[0064] During the operation of the injection molding machine, the ambient temperature is collected once for each mold. The lubrication compensation coefficient P corresponding to the current environment is calculated by combining the room temperature - compensation coefficient fitting model, which is used to correct the current lubrication coefficient.

[0065] This setup addresses the significant impact of ambient temperature on the viscosity and flowability of lubricating grease, thereby affecting lubrication performance and wear rate. At high temperatures, grease viscosity decreases, leading to easier loss, reduced lubrication, and accelerated wear; conversely, at low temperatures, grease viscosity increases, resulting in poor flowability and difficulty reaching the friction surfaces, also accelerating wear. By establishing a room temperature compensation model, the lubrication coefficient can be dynamically adjusted based on ambient temperature, ensuring optimal lubrication performance under various temperature conditions.

[0066] In this embodiment, step S200 also includes determining in real time whether the operating conditions of the injection molding machine have changed; If the operating conditions remain unchanged, the cached lubrication coefficient can be directly used. For example, if the clamping force, mold opening and closing speed, and mold opening and closing stroke remain stable, the cached lubrication coefficient can be directly used without repeatedly collecting sensor data and performing neural network operations. This reduces the computing power consumption of the controller and improves the system response speed.

[0067] If the operating conditions change (any parameter exceeds the preset change threshold) or the equipment is started for the first time, the operating condition parameters are re-collected and input into the lubrication coefficient prediction model to calculate the lubrication coefficient in real time. At the same time, the cached data is updated to ensure the timeliness and accuracy of the lubrication coefficient.

[0068] With this setup and caching mechanism, when the operating conditions are stable, each module only requires simple parameter comparison and cache reading, resulting in minimal computation. Neural network calculations are only performed when the operating conditions change. This optimization reduces the average computing power consumption of the controller, ensuring the real-time performance and stability of the system.

[0069] In some specific embodiments, the working condition change can be determined by the controller comparing the currently collected clamping force, mold opening and closing speed, and mold opening and closing stroke parameters with the parameters of the previous mold in each cycle. If the change in the three parameters is less than 1% of their respective rated values, it is determined that the working condition has not changed; otherwise, it is determined that the working condition has changed.

[0070] Furthermore, it also includes: when switching operating conditions, retaining the current cumulative lubrication coefficient and directly substituting it into the new operating condition for continued accumulation calculation, while keeping the lubrication trigger threshold α unchanged. In other words, the lubrication trigger threshold α is fixed after the injection molding machine is debugged; for example, a preferred lubrication trigger threshold α is 0.8. This threshold can be adjusted once according to different machine models and lubrication requirements, but it does not change with changes in operating conditions during operation.

[0071] When a change in operating conditions is detected, the controller does not clear the current cumulative lubrication coefficient X1, but retains its current value. Under the new operating conditions, a new compensated lubrication coefficient is calculated for each cycle and continues to be added to the original X1 until X1 reaches the lubrication trigger threshold α, at which point the lubrication operation is executed.

[0072] This setup, by employing a fixed threshold and cumulative inheritance rules, ensures a simple and unified control logic. It guarantees that lubrication will be performed when the cumulative lubrication demand reaches the set value, regardless of changes in operating conditions, thus ensuring the timeliness and accuracy of lubrication.

[0073] For example, the cumulative iteration calculation is performed according to the following formula: X1 = X1 + (X × p), where X1 is the cumulative lubrication coefficient, with an initial value of 0, which is reset to zero after each lubrication; X is the lubrication coefficient predicted by the neural network model under the current operating conditions, with a value range of 0 to 1; p is the room temperature lubrication compensation coefficient under the current ambient temperature, with a value range of 0.8 to 1.2.

[0074] Calculation process: After each injection molding cycle (one mold), the above accumulation calculation is performed once. The controller first obtains the current X and p values, calculates their product, and then adds the product to the current X1 to obtain a new cumulative lubrication coefficient. When X1 reaches the lubrication trigger threshold α, the lubrication action is triggered, and then X1 is cleared to zero and accumulation starts again. When X1 is less than α, the lubrication action is not performed, and the system directly returns to the working condition judgment step for continuous monitoring.

[0075] Furthermore, step S500 also includes: if it is determined that the cumulative lubrication coefficient is less than the lubrication trigger threshold α, then the lubrication action is not performed, and the step of determining whether the injection molding machine operating condition has changed is performed.

[0076] This embodiment also provides a multi-parameter coupling intelligent lubrication system for injection molding machine locking bushings, including: The system includes a working condition acquisition unit, a room temperature acquisition unit, a main control unit, and a lubrication execution unit. The working condition acquisition unit is used to collect clamping force, mold opening and closing speed, and mold opening and closing stroke parameters in real time. The room temperature acquisition unit is used to collect ambient temperature parameters in real time. The main control unit has a built-in lubrication coefficient prediction model, room temperature compensation model, and lubrication control algorithm. It is configured to execute the multi-parameter coupled intelligent lubrication method of the injection molding machine's locking shaft and bushing mentioned above to calculate the cumulative lubrication coefficient and generate a lubrication control signal. The lubrication execution unit receives instructions from the main control unit and completes the fixed-point lubrication action between the locking shaft 2 and the bushing 1.

[0077] Specifically, such as Figure 1 As shown, each unit can be connected via a CAN bus or analog signal line. The working condition acquisition unit includes a clamping force sensor, a displacement sensor, and a speed sensor. The clamping force sensor is installed on the tie rod of the injection molding machine to detect the clamping force; the displacement sensor is installed on the moving platen to detect the mold opening and closing stroke; and the speed sensor obtains the mold opening and closing speed by detecting the rate of change of displacement. These sensors are usually standard configurations that come with the injection molding machine and do not require additional installation.

[0078] The room temperature acquisition unit uses a high-precision digital temperature sensor 4, which is installed in a ventilated location inside the electrical cabinet of the injection molding machine or near the machine body, avoiding direct sunlight and heat sources, in order to accurately measure the ambient temperature.

[0079] The main control unit can be the original PLC or industrial controller of the injection molding machine. The pre-trained lubrication coefficient prediction model parameters, room temperature compensation model parameters and lubrication control algorithm program are loaded into the controller.

[0080] The lubrication execution unit includes a lubrication pump 7, multiple metering valves 6, and multiple lubrication nozzles 5. The outlet of the lubrication pump 7 is connected to the inlet of each metering valve 6 via a pipeline. Both the lubrication pump 7 and each metering valve 6 are electrically connected to the main control unit. Each metering valve 6's outlet is connected to a corresponding lubrication nozzle 5 via a pipeline for precise control of the amount of lubricating grease used per cycle. The lubrication pump 7 provides high-pressure lubricating grease. Each metering valve 6 corresponds to a lubrication point between a locking shaft 2 and a bushing 1, and the metering valve 6 can precisely control the amount of grease output for each lubrication cycle. The lubrication nozzles 5 are aligned with the mating gap between the locking shaft 2 and the bushing 1, evenly spraying the grease onto the friction surface.

[0081] Furthermore, it also includes a temperature acquisition unit, which includes a temperature sensor 4 mounted on the connecting rod 3 of the bushing 1. The connecting rod 3 is interference-fitted with the bushing 1 and is used to acquire the temperature data of the bushing 1 and transmit it to the main control unit to complete the identification of the wear start point.

[0082] Optionally, the temperature sensor 4 is a PT100 platinum resistance temperature sensor with a measurement range of -50℃ to 200℃, an accuracy of ±0.1℃, and a response time of less than 1s, which can meet the requirements for temperature measurement of the bushing 1.

[0083] Specifically, on the connecting rod 3, which is interference-fitted with the bushing 1, a blind hole with a diameter matching the diameter of the temperature sensor 4 probe is made at the middle position of the bushing 1, with the hole depth reaching the outer wall of the bushing 1. Thermal grease is applied inside the hole, and then the temperature sensor 4 probe is inserted into the hole and secured with a set screw. This installation method ensures good thermal contact between the sensor and the bushing 1, accurately measuring the actual temperature of the bushing 1, while avoiding the difficulty of installing the sensor on the moving locking shaft 2. The output signal of the temperature sensor 4 can be transmitted to the analog input module of the main control unit via a shielded cable, and converted into a digital signal for processing after A / D conversion.

[0084] Finally, it should be noted that the above embodiments are only for illustrating the present invention and not for limiting the present invention. Although the present invention has been described in detail with reference to the embodiments, those skilled in the art should understand that various combinations, modifications, or equivalent substitutions of the technical solutions of the present invention do not depart from the spirit and scope of the technical solutions of the present invention and should be covered within the scope of the claims of the present invention.

Claims

1. A multi-parameter coupling intelligent lubrication method for the lock shaft sleeve of an injection molding machine, used for lubricating the lock shaft (2) and the sleeve (1) of the injection molding machine, characterized in that, include: Obtain the operating parameters of the injection molding machine, wherein the operating parameters include clamping force, mold opening and closing speed, mold opening and closing stroke, and number of modules; Based on the operating condition parameters and the lubrication coefficient prediction model, the lubrication coefficient under the current operating condition is determined. The lubrication coefficient prediction model is trained based on multi-condition test data and is used to characterize the coupling relationship between different operating condition parameters and lubrication requirements. The ambient temperature is obtained, and the lubrication coefficient is compensated using a room temperature compensation model to obtain the compensated lubrication coefficient. The cumulative lubrication coefficient is obtained by performing cumulative iterative calculation on the compensated lubrication coefficient; If the cumulative lubrication coefficient is determined to be greater than or equal to the lubrication trigger threshold α, the lubrication actuator is controlled to lubricate the locking shaft (2) and the bushing (1), and the cumulative lubrication coefficient is cleared to zero.

2. The multi-parameter coupling intelligent lubrication method for the lock shaft bushing of the injection molding machine according to claim 1, characterized in that, After obtaining the operating parameters of the injection molding machine, the process also includes: Collect temperature data of bushing (1) and filter the collected temperature data of bushing (1); The filtered temperature data is differentiated to obtain the temperature rise slope curve. The wear initiation point is identified based on the variation characteristics of the temperature rise slope curve with the operating modulus.

3. The multi-parameter coupling intelligent lubrication method for the lock shaft bushing of the injection molding machine according to claim 2, characterized in that, The method of identifying the wear initiation point based on the variation characteristics of the temperature rise slope curve with the operating modulus includes: Select a starting point on the temperature rise slope curve. If the slope difference between the starting point and the subsequent preset number of points is positive, and the slope of the preset number of points is greater than the preset slope threshold, and the temperature rise of the bushing (1) is greater than the preset temperature rise threshold within the preset length of the sliding window, then the point is determined to be the wear starting point, and the corresponding operating modulus is the lubrication critical modulus.

4. The multi-parameter coupling intelligent lubrication method for the lock shaft bushing of the injection molding machine according to claim 1, characterized in that, Also includes: Determine if the operating conditions of the injection molding machine have changed; If it is determined that the operating conditions have changed or the equipment is started for the first time, the step of obtaining the operating condition parameters of the injection molding machine is performed, and the cached data is updated.

5. The multi-parameter coupling intelligent lubrication method for the lock shaft bush of the injection molding machine according to claim 4, characterized in that, Also includes: If the operating conditions have not changed or this is not the first startup, the cached lubrication coefficient is invoked.

6. The multi-parameter coupling intelligent lubrication method for the lock shaft bush of the injection molding machine according to claim 5, characterized in that, Also includes: If the cumulative lubrication coefficient is determined to be less than the lubrication trigger threshold α, the step of determining whether the injection molding machine operating condition has changed is performed.

7. The multi-parameter coupling intelligent lubrication method for the lock shaft bush of the injection molding machine according to claim 5, characterized in that, Also includes: When the operating conditions change, the current cumulative lubrication coefficient is retained and directly substituted into the new operating conditions to continue the cumulative calculation, while the lubrication trigger threshold α remains unchanged.

8. A multi-parameter coupling intelligent lubrication system for a lock shaft bushing of an injection molding machine, characterized in that, include: The working condition acquisition unit is used to acquire clamping force, mold opening and closing speed, and mold opening and closing stroke parameters in real time. Temperature acquisition unit, used to acquire temperature data of bushing (1); A room temperature acquisition unit, which is used to acquire ambient temperature parameters in real time; The main control unit is electrically connected to the temperature acquisition unit, the operating condition acquisition unit, and the room temperature acquisition unit, respectively, and is used to execute the multi-parameter coupled intelligent lubrication method for the injection molding machine locking shaft sleeve as described in any one of claims 1 to 7; the main control unit has a built-in lubrication coefficient prediction model, room temperature compensation model, and lubrication control algorithm, which is used to calculate the lubrication coefficient based on the operating condition parameters and perform cumulative iterative calculation, and output a control signal when the cumulative lubrication coefficient reaches the lubrication trigger threshold α. The lubrication execution unit is electrically connected to the main control unit. The lubrication execution unit is used to receive the control signal from the main control unit and complete the fixed-point lubrication action between the locking shaft (2) and the bushing (1).

9. The multi-parameter coupling intelligent lubrication system for injection molding machine locking shaft sleeves according to claim 8, characterized in that, The temperature acquisition unit includes a temperature sensor (4) mounted on a matching connecting rod (3) of the bushing (1). The connecting rod (3) is interference-fitted with the bushing (1). The temperature sensor (4) is used to collect the temperature data of the bushing (1) and transmit it to the main control unit to complete the identification of the wear start point.

10. The multi-parameter coupling intelligent lubrication system for injection molding machine locking shaft sleeves according to claim 9, characterized in that, The lubrication actuator includes: Lubrication pump (7) At least one metering valve (6) is provided. The oil outlet of the lubrication pump (7) is connected to the oil inlet of each metering valve (6) through a pipeline. The lubrication pump (7) and each metering valve (6) are electrically connected to the main control unit. At least one lubrication nozzle (5) is provided, and the lubrication nozzle (5) is connected to the oil outlet of the metering valve (6) through a pipeline to control the amount of lubricating grease used in a single operation.

Images