Method, device and equipment for detecting needle of flat knitting machine and storage medium

Abstract

The application discloses a detection method, device and equipment for a needle of a flat knitting machine and a storage medium. The detection method is applied to a flat knitting machine. The flat knitting machine is provided with an accelerometer, a servo motor encoder and a vibration sensor. The detection method comprises the following steps: obtaining an impact signal through the accelerometer; calculating an energy value based on the impact signal and a signal energy integral formula; determining that a primary alarm is triggered in response to the energy value being greater than a preset dynamic baseline threshold; obtaining a servo motor speed fluctuation through the servo motor encoder and obtaining a wavelet packet entropy value through the vibration sensor; determining that a needle collision event occurs in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy threshold; and triggering an alarm and stopping the machine based on the needle collision event. In the foregoing manner, the pulse energy characteristics of the needle collision instant can be captured sensitively, and a multidimensional cross-validation mechanism is constructed, so that the possibility of false alarms of a single sensor is fundamentally solved.

Description

Technical Field

[0001] This application relates to the field of knitting technology, and in particular to methods, apparatus, equipment and storage media for detecting needle collisions on flat knitting machines. Background Technology

[0002] During the knitting process of a flat knitting machine, the needles reciprocate at high speed within the needle bed grooves to complete the loop-forming action. Due to abnormal yarn tension, needle blockage, or mechanical wear, the needles are prone to abnormal displacement or jamming, leading to violent collisions between the needle feet and other machine parts, known as needle strikes. Needle strikes can not only cause needle breakage but also damage precision components such as sinkers and needle guides, severely affecting fabric quality and production continuity. To address this problem, a vibration detection solution based on piezoelectric ceramic sensors is currently the primary approach. This solution involves installing piezoelectric sensors at key locations on the needle bed or knitting head to collect high-frequency vibration signals during the knitting process in real time. When the system determines that the vibration amplitude exceeds a preset safety threshold, it issues an alarm signal and controls the machine to stop immediately, thereby achieving the identification and protection against needle strikes.

[0003] However, in practical applications, the above-mentioned detection scheme based on piezoelectric sensors has low detection sensitivity and a high false alarm rate. Summary of the Invention

[0004] This application mainly provides a method, apparatus, equipment, and storage medium for detecting needle collisions on flat knitting machines, which solves the problems of low detection sensitivity and high false judgment rate.

[0005] This application provides a method for detecting needle collision on a flat knitting machine, applied to the flat knitting machine, which is equipped with an accelerometer, a servo motor encoder, and a vibration sensor. The detection method includes: The impact signal is obtained through the accelerometer; The energy value is calculated based on the impact signal and the signal energy integral formula. In response to the energy value being greater than a preset dynamic baseline threshold, a primary alarm is triggered, wherein the dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles. The servo motor speed fluctuation is obtained through the servo motor encoder, and the wavelet packet entropy value is obtained through the vibration sensor. In response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold, a pin collision event is determined to have occurred. An alarm is triggered and the machine is shut down based on the aforementioned striker event.

[0006] In some embodiments, the flat knitting machine is further provided with an infrared photoelectric beam array, and the step of determining that a needle collision event has occurred in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold further includes: The position of the knitting needle is monitored in real time by the infrared photoelectric beam array; In response to the abnormal needle position, the needle collision event is verified.

[0007] In some embodiments, the infrared photoelectric beam array includes multiple sets of infrared gratings, and the step of real-time monitoring of the knitting needle position via the infrared photoelectric beam array; the step of responding to an abnormal knitting needle position includes: Real-time monitoring of the occlusion status of multiple sets of infrared gratings; When any set of infrared gratings is continuously blocked for more than a preset time, the striker event is verified.

[0008] In some embodiments, the flat knitting machine is further equipped with a temperature sensor and a humidity sensor, and the detection method further includes: The current environmental parameters are acquired by the temperature sensor and the humidity sensor respectively, and the current environmental parameters are recorded; wherein, the current environmental parameters include the current temperature and the current humidity.

[0009] In some embodiments, the detection method further includes: In response to the energy value being less than or equal to the preset dynamic baseline threshold, the monitoring of the flat knitting machine continues; Alternatively, in response to the servo motor speed fluctuation being less than or equal to the preset speed deviation or the wavelet packet entropy value being less than or equal to the preset entropy threshold, the monitoring of the flat knitting machine continues.

[0010] In some embodiments, the step of dynamically updating the dynamic baseline threshold based on the acceleration of a preset number of past normal weaving cycles includes: Obtain a preset number of accelerations within past normal weaving cycles and construct a historical data set; Statistical parameters are calculated based on the historical data set, including the mean and standard deviation; The updated dynamic baseline threshold is calculated using a formula based on the mean and the standard deviation.

[0011] In some embodiments, the detection method further includes: The ambient temperature of the flat knitting machine is obtained in real time; The preset entropy threshold is corrected by temperature compensation based on the ambient temperature to obtain the corrected preset entropy threshold.

[0012] This application also provides a detection device for needle collision on a flat knitting machine, comprising: The first acquisition module is used to acquire the impact signal through the accelerometer; An energy value calculation module is used to calculate the energy value based on the impact signal and the signal energy integral formula; A triggering module is used to determine to trigger a primary alarm in response to the energy value being greater than a preset dynamic baseline threshold, wherein the dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles. The second acquisition module is used to acquire the servo motor speed fluctuation through the servo motor encoder and to acquire the wavelet packet entropy value through the vibration sensor. The striker module is used to determine that a striker event has occurred in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold. An alarm module is used to trigger an alarm and stop the machine based on the striker event.

[0013] This application also provides an electronic device, including: at least one processor and a memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the detection method as described in any of the preceding claims.

[0014] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the detection method described in any of the preceding claims.

[0015] The beneficial effects of this application are as follows: Unlike existing detection schemes based on piezoelectric sensors, this application introduces an accelerometer for high-frequency impact sampling and calculates the energy value using a signal energy integral formula, which can sensitively capture the pulse energy characteristics of the impact pin at the moment of impact. At the same time, a dynamic baseline threshold is used instead of a fixed threshold, so that the detection standard is adaptively adjusted according to the machine's operating state, effectively avoiding false alarms caused by mechanical resonance or environmental noise. Based on triggering the primary alarm, a servo motor encoder is further introduced to monitor the servo motor speed fluctuation, and a vibration sensor is used to extract the wavelet packet entropy value. Only when the energy value, servo motor speed fluctuation, and entropy value are all abnormal is it finally determined to be an impact pin event, thus constructing a multi-dimensional cross-validation mechanism, fundamentally solving the possibility of false alarms from a single sensor. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic flowchart of an embodiment of the detection method for needle collision on a flat knitting machine provided in this application; Figure 2 This is a schematic flowchart of another embodiment of the detection method for needle collision on a flat knitting machine provided in this application; Figure 3 This is a flowchart illustrating another embodiment of the detection method for needle collision on a flat knitting machine provided in this application; Figure 4 This is a schematic diagram of an embodiment of the detection device for needle collision on a flat knitting machine provided in this application; Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application; Figure 6 This is a schematic diagram of an embodiment of the computer-readable storage medium provided in this application. Detailed Implementation

[0017] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly indicating the number, specific order, or primary and secondary relationship of the indicated technical features.

[0021] This application provides a method for detecting needle collision on a flat knitting machine, which is equipped with an accelerometer, a servo motor encoder, and a vibration sensor.

[0022] Optionally, an accelerometer, including but not limited to a triaxial accelerometer, is mounted on the side of the machine head, with a sampling frequency greater than or equal to 2kHz, to capture instantaneous impact signals along the X, Y, and Z axes. A servo motor encoder is mounted on the servo motor shaft end to acquire real-time servo motor speed fluctuations. A vibration sensor, including but not limited to a piezoelectric vibration sensor, is mounted on the needle bed support frame to detect high-frequency mechanical vibration energy in the 8kHz-12kHz range.

[0023] See Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the method for detecting needle collisions on a flat knitting machine provided in this application; the method for detecting needle collisions on a flat knitting machine in this embodiment includes: Step S110: Obtain the impact signal through the accelerometer.

[0024] Among them, the impact signal refers to the transient vibration acceleration time-domain signal obtained by the accelerometer in real time during the weaving process and after preprocessing (DC / trend removal and optional bandpass limiting).

[0025] In some embodiments, the accelerometer is securely mounted on a rigid structure on the side of the knitting head to ensure that the accelerometer and the knitting head have the same vibration modes; the sampling frequency of the accelerometer is set to be greater than or equal to 2kHz so that the accelerometer is in an oversampling state to capture microsecond-level transient impact signals; when the knitting needles collide or jam during the knitting process, the violent collision at the needle plate will generate a high-frequency stress wave. This mechanical shock wave is rapidly transmitted to the accelerometer through the needle bed and the metal structure of the knitting head. The accelerometer senses the changes in vibration acceleration in the X, Y, and Z axes in real time and converts the physical vibration into an analog voltage signal output. After being quantized by an analog-to-digital converter, the original impact signal sequence containing time-domain waveform information is obtained, i.e., the impact signal.

[0026] Step S120: Calculate the energy value based on the impact signal and the signal energy integral formula.

[0027] Among them, the energy value refers to the scalar accumulation of the impact signal within a defined effective time window of impact (e.g., [t1, t2]) calculated according to the signal energy integral relationship.

[0028] In some embodiments, after acquiring the impact signal through an accelerometer, the impact signal is substituted into the signal energy integral formula to calculate the total energy value.

[0029] Optionally, the signal energy integral formula is: ,in, This represents the total energy value of the impact event (firing pin). t represents the instantaneous value of acceleration (impact signal) collected at time t, and t1 and t2 represent the time boundaries for determining the start and end of the impact, respectively. By combining squaring and definite integral, the signal energy integral formula transforms the time-domain vibration waveform into a single energy scalar, providing a reliable quantitative basis for subsequent comparison with the dynamic baseline threshold.

[0030] Step S130: In response to the energy value being greater than the preset dynamic baseline threshold, a primary alarm is triggered. The dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles.

[0031] Among them, the dynamic baseline threshold is an energy reference benchmark that is adaptively updated according to the real-time operating status of the flat knitting machine, such as automatically adjusting according to the fabric density.

[0032] In some embodiments, after the energy value is calculated by the signal energy integral formula, the energy value is compared with a preset dynamic baseline threshold. When the energy value is greater than the preset dynamic baseline threshold, it is considered that a suspected destructive impact has occurred. However, at this time, it may still be a strong vibration caused by the ejection of fly debris, the impact of the settling plate, or the inertial impact of the machine head acceleration and deceleration. Therefore, it is not immediately determined to be a pin strike event, but rather to trigger a primary alarm.

[0033] Optionally, the primary alarm serves as a first-level gating / initial screening flag, quickly waking up or increasing the weight of subsequent review channels. For example, it allows / starts secondary discrimination of servo motor speed fluctuations obtained by the servo motor encoder and wavelet packet entropy values ​​obtained by the vibration sensor (i.e., only after the primary alarm is established will the abnormal judgment of servo motor speed fluctuations and wavelet packet entropy values ​​be entered), thereby improving transient capture sensitivity while reducing false alarm rate and unnecessary machine-wide emergency stop by using hierarchical decision-making.

[0034] In some embodiments, to adapt to the differences in background vibration of the flat knitting machine under different knitting speeds and operating conditions, a dynamic baseline threshold generation mechanism based on the statistical 3σ criterion is introduced. The specific operation of dynamically updating the dynamic baseline threshold based on the acceleration of a preset number of past normal knitting cycles is as follows: obtaining the acceleration within a preset number of past normal knitting cycles and constructing a historical data set; calculating statistical parameters based on the historical data set, including the mean and standard deviation; and calculating the updated dynamic baseline threshold based on the mean and standard deviation using a formula.

[0035] Optionally, the specific calculation formula for the dynamic baseline threshold is: T1=μ+3σ, where μ represents the mean value calculated based on the acceleration of a preset number of past normal knitting cycles, σ represents the standard deviation calculated based on the acceleration of a preset number of past normal knitting cycles, and T1 represents the dynamic baseline threshold. By introducing a 3σ offset, the dynamic baseline threshold can be set outside the 99.73% confidence interval of the normal fluctuation distribution range while adaptively tracking the changes in the operating state of the flat knitting machine. This adapts to the impact energy distribution of different fabric processes, ensuring that the system can both keenly capture destructive impacts that exceed normal physical laws (such as needle impact) and effectively tolerate small random noises caused by mechanical resonance and yarn vibration, thereby significantly reducing the false alarm rate of the system and indirectly reducing the number of invalid verifications of servo motor speed fluctuations and wavelet packet entropy values.

[0036] In some embodiments, the knitting machine continues to be monitored in response to an energy value being less than or equal to a preset dynamic baseline threshold.

[0037] Specifically, after calculating the energy value using the signal energy integral formula, the energy value is compared with a preset dynamic baseline threshold. If the energy value is less than or equal to the preset dynamic baseline threshold, the vibration is determined to be within the normal operating fluctuation range allowed by the current working condition (e.g., inertial ringing of the machine head reversal, needle knocking, short-term disturbance of yarn tension, or slight rubbing of the sinker). The primary alarm is not triggered and the subsequent servo motor encoder and vibration sensor judgment process is not entered. At the same time, the closed-loop maintenance action of continued monitoring is executed.

[0038] Step S140: Obtain the servo motor speed fluctuation through the servo motor encoder and obtain the wavelet packet entropy value through the vibration sensor.

[0039] Among them, servo motor speed fluctuation refers to the instantaneous speed sequence obtained by high-frequency sampling and differential analysis of rotor position information output by servo motor encoder, with the current operating speed reference (which can be given by speed command or steady-state mean) as a reference, forming a deviation / variation measure. Wavelet packet entropy refers to the scalar value obtained by decomposing the structural vibration signal provided by vibration sensor within the same focusing time window of primary alarm calibration into wavelet packets to a predetermined number of layers to obtain the energy of each sub-band (node), normalizing to obtain the distribution, and calculating according to Shannon information entropy.

[0040] In some embodiments, after determining that a primary alarm has been triggered, the servo motor encoder outputs rotor position information in real time, and obtains the servo motor speed fluctuation through the rotor position information. At the same time, the vibration sensor continuously outputs structural vibration signals, and the wavelet packet entropy value is obtained by calculation.

[0041] Step S150: In response to the servo motor speed fluctuation being greater than the preset speed deviation and the wavelet packet entropy value being greater than the preset entropy value threshold, a pin collision event is determined to have occurred.

[0042] Among them, the preset speed deviation refers to the upper limit of permissible speed fluctuation under specific operating conditions, which is used to distinguish between minor speed pulsations caused by normal operation and abnormal load drag caused by the striker. The preset entropy threshold refers to the Shannon entropy corresponding to the normalized subband energy distribution obtained by wavelet packet decomposition of the vibration sensor signal, which is used to distinguish between quasi-periodic / steady-state structural vibration and non-stationary transient impacts such as strikers.

[0043] In some embodiments, after obtaining the servo motor speed fluctuation and wavelet packet entropy value through the servo motor encoder and vibration sensor, the servo motor speed fluctuation and preset speed deviation, and the wavelet packet entropy value and preset entropy value threshold are compared respectively. When the servo motor speed fluctuation is greater than the preset speed deviation and the wavelet packet entropy value is greater than the preset entropy value threshold, it is determined that a pin collision event has occurred.

[0044] For example, if the servo motor speed fluctuation is Δv and the preset speed deviation is 0.5 rpm, and since the servo motor can rotate in both directions, the wavelet packet entropy value is ΔH. The preset entropy threshold is 0.3. That is, when Δv > ±0.5 rpm and ΔH > 0.3, it is determined to be a pin collision event.

[0045] In some embodiments, a temperature-vibration correlation model is established, and a preset entropy threshold is corrected by temperature compensation. Specifically, the ambient temperature of the knitting machine is acquired in real time; the preset entropy threshold is corrected by temperature compensation based on the ambient temperature to obtain the corrected preset entropy threshold.

[0046] Optionally, the flat knitting machine is equipped with a temperature sensor to perform temperature compensation correction on a preset entropy threshold.

[0047] For example, by collecting the ambient temperature T in real time using a temperature sensor, a corrected preset entropy threshold can be obtained using a temperature compensation formula; the temperature compensation formula is: T H =T H0 *(1+k*(T-25℃)), where T H T represents the actual output value after temperature compensation. H0 is the initial reference value, and k is the temperature coefficient.

[0048] This embodiment avoids misjudgment caused by temperature changes by performing temperature compensation correction on the preset entropy threshold.

[0049] In some embodiments, the knitting flat knitting machine continues to be monitored in response to the servo motor speed fluctuation being less than or equal to a preset speed deviation or the wavelet packet entropy value being less than or equal to a preset entropy value threshold.

[0050] Step S160: Trigger an alarm and shut down the machine based on the impact pin event.

[0051] In some embodiments, after determining a pin-striking event through a dual determination of energy value, servo motor speed fluctuation, and wavelet packet entropy value, an emergency shutdown is initiated and an audible and visual alarm is triggered.

[0052] In some embodiments, the flat knitting machine is further equipped with a temperature sensor and a humidity sensor. The temperature sensor and humidity sensor respectively acquire and record the current environmental parameters; wherein the current environmental parameters include the current temperature and the current humidity.

[0053] Optionally, temperature and humidity sensors are mounted on the outside of the machine head cover to measure the working environment of the flat knitting machine.

[0054] Specifically, after a pin-collision incident is identified, the machine is shut down immediately and an audible and visual alarm is triggered. At the same time, the current temperature and humidity are obtained through temperature and humidity sensors, and the current temperature, humidity, and sensor data are recorded in log form.

[0055] Unlike existing piezoelectric sensor-based detection schemes, this embodiment introduces an accelerometer for high-frequency impact sampling and calculates the energy value using a signal energy integration formula, enabling it to sensitively capture the pulse energy characteristics of the impact pin. Simultaneously, a dynamic baseline threshold is used instead of a fixed threshold, allowing the detection standard to adaptively adjust to the machine's operating state, effectively avoiding false alarms caused by mechanical resonance or environmental noise. Building upon the initial alarm triggering, a servo motor encoder is further introduced to monitor servo motor speed fluctuations, and a vibration sensor is used to extract wavelet packet entropy. Only when the energy value, servo motor speed fluctuation, and entropy value are all abnormal is it ultimately determined to be an impact pin event, constructing a multi-dimensional cross-validation mechanism that fundamentally solves the possibility of false alarms from a single sensor.

[0056] See Figure 2 As shown, Figure 2 This is a flowchart illustrating another embodiment of the method for detecting needle collision on a flat knitting machine provided in this application. The flat knitting machine in this embodiment is further equipped with an infrared photoelectric beam array, and the method for detecting needle collision on the flat knitting machine includes: Step S210: Obtain the impact signal through the accelerometer.

[0057] Step S220: Calculate the energy value based on the impact signal and the signal energy integral formula.

[0058] Step S230: In response to the energy value being greater than the preset dynamic baseline threshold, a primary alarm is triggered. The dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles.

[0059] Step S240: Obtain the servo motor speed fluctuation through the servo motor encoder and obtain the wavelet packet entropy value through the vibration sensor.

[0060] Step S250: In response to the servo motor speed fluctuation being greater than the preset speed deviation and the wavelet packet entropy value being greater than the preset entropy value threshold, a pin collision event is determined to have occurred.

[0061] The steps S110-S150 are the same as those in the above embodiments, and will not be repeated here.

[0062] Step S260: Monitor the position of the knitting needle in real time using an infrared photoelectric beam array.

[0063] Optionally, an infrared photoelectric beam array is mounted on the needle bed, specifically on the needle movement path, to monitor the needle position in real time.

[0064] In some embodiments, after dual determination by energy value, servo motor speed fluctuation and wavelet packet entropy value, a needle collision event can be determined. To further verify the needle collision event, the needle position can be monitored by an infrared photoelectric beam array.

[0065] Step S270: In response to the abnormal needle position, the needle collision event is verified.

[0066] Optionally, the infrared photoelectric beam array includes multiple sets of infrared gratings. For example, the infrared photoelectric beam array includes four sets of infrared gratings.

[0067] In some embodiments, the occlusion status of multiple sets of infrared gratings is monitored in real time; when any set of infrared gratings is continuously occluded for more than a preset time, the striker event is verified.

[0068] For example, the occlusion status of four sets of infrared gratings is monitored. If any set of infrared gratings is continuously occluded for more than 50ms, the verification of the striker event is completed.

[0069] Step S280: Trigger an alarm and shut down the machine based on the striker event.

[0070] The steps are the same as those in the above embodiments, and will not be repeated here.

[0071] This embodiment verifies the impact pin event by setting up an infrared photoelectric beam array, further reducing the possibility of misjudgment.

[0072] See Figure 3 As shown, Figure 3This is a flowchart illustrating another embodiment of the detection method for needle collision on a flat knitting machine provided in this application. The detection method in this embodiment first collects data synchronously through multiple sensors, including but not limited to acquiring impact signals via an accelerometer, acquiring servo motor speed fluctuations via a servo motor encoder, acquiring wavelet packet entropy values ​​via a vibration sensor, and monitoring the needle position via an infrared photoelectric beam array. Then, it calculates the energy value E based on the impact signal and determines whether the energy value E is greater than the dynamic baseline threshold T1. If so, it proceeds to verify the servo motor speed fluctuation and wavelet packet entropy value. If the energy value, servo motor speed fluctuation, and wavelet packet entropy value are all abnormal simultaneously, it triggers an emergency stop, followed by an audible and visual alarm and log recording; otherwise, it continues monitoring. Alternatively, it determines whether the infrared grating detects an abnormal needle position; if so, it independently triggers a stop; otherwise, it continues monitoring.

[0073] This embodiment can determine the occurrence of a needle collision event and trigger a shutdown by dual judgment of energy value, servo motor speed fluctuation and wavelet packet entropy value, and can also trigger a shutdown by detecting abnormal needle position through infrared grating, which provides high detection flexibility.

[0074] See Figure 4 As shown, Figure 4 This is a schematic diagram of an embodiment of the detection device for needle collision on a flat knitting machine provided in this application; the detection device for needle collision on a flat knitting machine in this embodiment includes: The first acquisition module 401 is used to acquire the impact signal through the accelerometer; The energy value calculation module 402 is used to calculate the energy value based on the impact signal and the signal energy integral formula; Trigger module 403 is used to determine to trigger a primary alarm in response to the energy value being greater than a preset dynamic baseline threshold, wherein the dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles. The second acquisition module 404 is used to acquire the servo motor speed fluctuation through the servo motor encoder and to acquire the wavelet packet entropy value through the vibration sensor. The striker module 405 is used to determine that a striker event has occurred in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold. Alarm module 406 is used to trigger an alarm and stop the machine based on the striker event.

[0075] Figure 5 This is a schematic diagram of the structure of an embodiment of the electronic device provided in this application. Figure 5 As shown, the electronic device includes a processor 21 and a memory 22 coupled to the processor 21. The memory 22 stores program instructions for implementing the methods of any of the above embodiments; the processor 21 executes the program instructions stored in the memory 22 to implement the steps of the above method embodiments. The processor 21 may also be referred to as a CPU (Central Processing Unit). The processor 21 may be an integrated circuit chip with signal processing capabilities. The processor 21 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor may be a microprocessor or any conventional processor. Figure 6 This is a schematic diagram of the structure of an embodiment of the computer-readable storage medium provided in this application. Figure 6 As shown, the computer-readable storage medium 30 of this application embodiment stores program instructions 31, which, when executed, implement the methods provided in the above embodiments of this application. The program instructions 31 can form a program file and be stored in the computer-readable storage medium 30 in the form of a software product, so that a computer device (which may be a personal computer, server, or network device, etc.) or processor can execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned computer-readable storage medium 30 includes various media capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or terminal devices such as computers, servers, mobile phones, and tablets.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or modules may be electrical, mechanical, or other forms. Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0077] This application also provides a computer program product comprising a computer program that, when executed by a processor, can implement the steps of the methods described in any of the foregoing embodiments. Specifically, the computer program product can be a software or program product containing a computer program, capable of running on a computing device or stored on any available medium.

[0078] In some embodiments, the functions or modules of the apparatus provided in this disclosure can be used to execute the methods described in the above method embodiments. Specific implementations can be referred to the descriptions of the above method embodiments, which will not be repeated here for brevity. The descriptions of the various embodiments above tend to emphasize the differences between them; their similarities or commonalities can be referred to each other, which will not be repeated here for brevity. In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For example, the division of modules or units is merely a logical functional division; in actual implementation, there may be other division methods. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. Additionally, the functional units in the various embodiments of this application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit described above can be implemented in either hardware or software functional units. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application.

[0079] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting needle collision on a flat knitting machine, characterized in that, The method is applied to the flat knitting machine, which is equipped with an accelerometer, a servo motor encoder, and a vibration sensor. The detection method includes: The impact signal is obtained through the accelerometer; The energy value is calculated based on the impact signal and the signal energy integral formula. In response to the energy value being greater than a preset dynamic baseline threshold, a primary alarm is triggered, wherein the dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles. The servo motor speed fluctuation is obtained through the servo motor encoder, and the wavelet packet entropy value is obtained through the vibration sensor. In response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold, a pin collision event is determined to have occurred. An alarm is triggered and the machine is shut down based on the aforementioned striker event.

2. The detection method according to claim 1, characterized in that, The flat knitting machine is also equipped with an infrared photoelectric beam array. After the step of determining that a needle collision event has occurred in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy threshold, the following steps are also included: The position of the knitting needle is monitored in real time by the infrared photoelectric beam array; In response to the abnormal needle position, the needle collision event is verified.

3. The detection method according to claim 2, characterized in that, The infrared photoelectric beam array includes multiple sets of infrared gratings, and the position of the knitting needle is monitored in real time through the infrared photoelectric beam array. The steps in response to the abnormal needle position include: Real-time monitoring of the occlusion status of multiple sets of infrared gratings; When any set of infrared gratings is continuously blocked for more than a preset time, the striker event is verified.

4. The detection method according to claim 1, characterized in that, The flat knitting machine is also equipped with a temperature sensor and a humidity sensor, and the detection method further includes: The current environmental parameters are acquired by the temperature sensor and the humidity sensor respectively, and the current environmental parameters are recorded; wherein, the current environmental parameters include the current temperature and the current humidity.

5. The detection method according to claim 1, characterized in that, The detection method further includes: In response to the energy value being less than or equal to the preset dynamic baseline threshold, the monitoring of the flat knitting machine continues; Alternatively, in response to the servo motor speed fluctuation being less than or equal to the preset speed deviation or the wavelet packet entropy value being less than or equal to the preset entropy threshold, the monitoring of the flat knitting machine continues.

6. The detection method according to any one of claims 1-5, characterized in that, The step of dynamically updating the dynamic baseline threshold based on the acceleration of a preset number of past normal weaving cycles includes: Obtain a preset number of accelerations within past normal weaving cycles and construct a historical data set; Statistical parameters are calculated based on the historical data set, including the mean and standard deviation; The updated dynamic baseline threshold is calculated using a formula based on the mean and the standard deviation.

7. The detection method according to any one of claims 1-5, characterized in that, The detection method further includes: The ambient temperature of the flat knitting machine is obtained in real time; The preset entropy threshold is corrected by temperature compensation based on the ambient temperature to obtain the corrected preset entropy threshold.

8. A detection device for needle collision on a flat knitting machine, characterized in that, include: The first acquisition module is used to acquire the impact signal through the accelerometer; An energy value calculation module is used to calculate the energy value based on the impact signal and the signal energy integral formula; A triggering module is used to determine to trigger a primary alarm in response to the energy value being greater than a preset dynamic baseline threshold, wherein the dynamic baseline threshold is dynamically updated based on the acceleration of a preset number of past normal weaving cycles. The second acquisition module is used to acquire the servo motor speed fluctuation through the servo motor encoder and to acquire the wavelet packet entropy value through the vibration sensor. The striker module is used to determine that a striker event has occurred in response to the servo motor speed fluctuation being greater than a preset speed deviation and the wavelet packet entropy value being greater than a preset entropy value threshold. An alarm module is used to trigger an alarm and stop the machine based on the striker event.

9. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the detection method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the detection method as described in any one of claims 1-7.

Images