Plastic crushing operation management system and crushing operation management method

Abstract

To provide a technology that can more appropriately manage crushing operations in a plastic recycling process. [Solution] The plastic crushing operation management system 1 of the present disclosure includes a crusher 200 having a rotary blade 201 that crushes input plastic 100 and a motor 202 that is a power source for rotating the rotary blade 201, and an information processing device 300 that estimates the end stage of crushing operation by the crusher 200 based on the motor current that changes according to the torque generated by the motor 202. The information processing device 300 also includes an acquisition unit 3031 that acquires the motor current at a predetermined cycle, a calculation unit 3032 that calculates a predetermined feature amount for estimating the end stage based on the acquired motor current, and an estimation unit 3033 that estimates the end stage based on the calculated feature amount.

Description

[Technical Field]

[0001] The present invention relates to a plastic crushing operation management system and a plastic crushing operation management method for managing crushing operations carried out in a plastic recycling process. [Background technology]

[0002] In recent years, plastics have been widely used not only as packaging containers for food products, but also in various industrial fields (for example, in the agricultural field for greenhouses and mulch), and are produced and used in large quantities all over the world. Toward the realization of a sustainable society, it is becoming increasingly important to recycle such plastics that are collected after use or as defective products during the manufacturing process.

[0003] The plastic recycling process involves washing, crushing, sorting, etc. Various methods have been proposed to produce reusable plastics from waste plastics.

[0004] For example, Patent Document 1 discloses a method for producing reusable plastics from waste. This method includes a pretreatment step for removing materials unsuitable for pulverization from the waste; a crushing / separation step for crushing the pretreated waste to a predetermined particle size or smaller using a cutter-type crusher to separate metals and plastics from metal-plastic composites contained in the waste; a dry gravity separation step for separating and removing metals from the crushed waste by specific gravity, separating metal-plastic composites from the crushed waste, and returning the resulting material to the crushing / separation step; and a metal-removal electrostatic separation step for electrostatically separating and removing metals contained in the waste that has undergone the dry gravity separation step. In the crushing / separation step, the crushed waste is crushed to an average particle size of 2 to 5 mm, suitable for electrostatic separation for metal removal. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 4686827 Summary of the Invention [Problem to be solved by the invention]

[0006] In order to realize a sustainable society and carbon neutrality, various recycling technologies have been developed to circulate waste as resources without incineration, and plastic recycling has attracted attention. However, plastics collected for recycling are often crushed into relatively small pieces during the recycling process, and after crushing, they often become a plastic mixture containing multiple types of synthetic resin fragments and metal fragments. Therefore, handling the crushed material and separating and recovering each recyclable material from the crushed material can be challenging. Here, the technology described in Patent Document 1 removes metals from plastic residues, including coated electric wires, to obtain recyclable plastics, which may make it possible to separate and recover each recyclable material from a mixture of plastic and metal.

[0007] On the other hand, agricultural plastics that are discarded after use in greenhouses and mulches in the agricultural sector are often made from roughly the same main raw materials, even if the manufacturers and product specifications are different, making them easy to recycle and tend to be recycled at a higher rate than plastics used in other industries. In other words, even if such agricultural plastics are crushed into relatively small pieces during the recycling process, the crushed material is unlikely to become a plastic mixture containing metal pieces, etc., which naturally reduces the challenge of separating and recovering recyclable materials from the crushed material.

[0008] However, even if it is relatively easy to separate and recover recyclable materials from the crushed material in the agricultural plastic recycling process, other processes, particularly the crushing process of agricultural plastic, still have issues. Specifically, in the conventional crushing process of agricultural plastic, the crushing work has been managed by workers' visual monitoring of the condition, which has led to problems such as the burden on workers and the dependency of work quality on individuals.

[0009] The purpose of the present disclosure is to provide a technology that can more appropriately manage the crushing operation in the plastic recycling process. [Means for solving the problem]

[0010] The plastic crushing operation management system disclosed herein is for managing crushing operations carried out in a plastic recycling process. This plastic crushing operation management system includes a crusher having rotary blades for crushing input plastics and a motor as a power source for rotating the rotary blades, and an information processing device that estimates the end stage of the crushing operation by the crusher based on the motor current that varies depending on the torque generated by the motor. The information processing device also includes an acquisition unit that acquires the motor current at a predetermined cycle, a calculation unit that calculates a predetermined feature value for estimating the end stage based on the acquired motor current, and an estimation unit that estimates the end stage based on the calculated feature value.

[0011] The plastic crushing operation management system described above can estimate the completion stage of crushing operations by a crusher using a feature based on the motor current, which represents the change in the load on the motor caused by the rotary blades crushing the plastic, as a judgment criterion. This solves the problems of worker burden and work quality depending on the individual, which can arise when workers visually monitor the status of the crushing operation, thereby enabling more appropriate management of crushing operations. The plastics referred to above are agricultural plastics, which can be defined as plastics discarded after use in greenhouses and mulches in the agricultural field, for example.

[0012] In the plastic crushing operation management system disclosed herein, the calculation unit may calculate, at each time when the motor current is acquired, the difference between the moving average value of the motor current in a first range immediately preceding that time and the value of the motor current at that time, and calculate the variance of the difference in a second range immediately preceding that time, thereby calculating the variance as the feature quantity.The estimation unit may then estimate that the end stage has arrived when the calculated feature quantity is equal to or less than a predetermined first threshold.In this way, it can be estimated that the end stage of the crushing operation by the crusher has arrived at the time when the plastic in the crusher is crushed into powder, based on a clear criterion indicating that the variation in the motor current value has decreased.

[0013] In the plastic crushing operation management system of the present disclosure, the calculation unit may calculate, at each time when the motor current is acquired, a moving average of the motor current in a third range immediately preceding the time, and calculate a moving average slope as the first feature value by dividing the difference between the moving average values ​​at the beginning and end of the third range by the time increment in the third range. At each time when the motor current is acquired, the calculation unit may calculate a distance between the motor current value at that time and a slope line having the moving average slope at that time, and calculate a variance of the distance in a fourth range immediately preceding the time, thereby calculating the variance as the second feature value. The estimation unit may estimate that the end stage has arrived when the calculated first feature value is equal to or less than a predetermined second threshold and the calculated second feature value is equal to or less than a predetermined third threshold. According to this, by subdividing the change in the value of the motor current into two features, a variable element and a variation element, and then simultaneously using the feature quantities representing each, it is possible to more accurately estimate the end stage of the grinding operation by the grinder, even if the value of the motor current contains instantaneous changes.

[0014] In addition, in the plastic crushing operation management system of the present disclosure, the calculation unit may calculate, at each time the motor current is acquired, a moving average value of the motor current in a fifth range immediately preceding that time, and calculate the feature quantity as the moving average slope by dividing the difference between the moving average values ​​at the beginning and end of the fifth range by the time increment in the fifth range.The estimation unit may then estimate that the end stage has arrived if the calculated feature quantity falls within a predetermined range after falling below a predetermined fourth threshold.This makes it possible to accurately estimate the end stage of a re-granulation operation, which can be considered one of the crushing operations of the present disclosure.

[0015] The present disclosure can also be viewed from the perspective of a plastic crushing operation management method. That is, the plastic crushing operation management method of the present disclosure is a plastic crushing operation management method for managing crushing operations carried out in a plastic recycling process, and includes an acquisition step of acquiring, at a predetermined cycle, a motor current that changes depending on the torque generated by a motor that is a power source for rotating rotary blades that crush the plastics fed into a crusher, a calculation step of calculating, based on the acquired motor current, a predetermined feature amount for estimating the end stage of the crushing operation by the crusher, and an estimation step of estimating the end stage based on the calculated feature amount.

[0016] In the calculation step, at each time when the motor current is acquired, a difference between a moving average value of the motor current in a first range immediately before the time and the value of the motor current at the time is calculated, and a variance of the difference in a second range immediately before the time is calculated to be the feature amount. In the estimation step, it may be estimated that the end stage has arrived if the calculated feature amount is equal to or less than a predetermined first threshold.

[0017] In the calculating step, at each time when the motor current is acquired, a moving average value of the motor current in a third range immediately preceding the time is calculated, and a moving average slope calculated by dividing the difference between the moving average values ​​at the beginning and end of the third range by a time increment in the third range is calculated as the first feature value, and at each time when the motor current is acquired, a distance from the motor current value at that time to a sloped line having the moving average slope at that time is calculated, and a variance of the distance in a fourth range immediately preceding the time is calculated to calculate the variance as the second feature value. In the estimating step, it may be estimated that the end stage has arrived if the calculated first feature value is equal to or less than a predetermined second threshold and the calculated second feature value is equal to or less than a predetermined third threshold.

[0018] In the calculating step, at each time when the motor current is acquired, a moving average value of the motor current in a fifth range immediately preceding the time may be calculated, and a moving average slope may be calculated as the feature amount by dividing the difference between the moving average values ​​at the beginning and end of the fifth range by a time increment in the fifth range. In the estimating step, it may be estimated that the end stage has arrived when the calculated feature amount falls within a predetermined range after becoming less than a predetermined fourth threshold. [Effects of the Invention]

[0019] According to the present disclosure, crushing operations can be more effectively managed in the plastic recycling process. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a diagram showing a schematic configuration of a plastic crushing operation management system in a first embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of the transition of the waveform of the motor current when plastic is crushed by the crusher. [Figure 3] FIG. 3 is a diagram illustrating a feature amount for estimating the end stage of a crushing operation by a crusher in the first embodiment. [Figure 4] FIG. 10 is a diagram showing the end stage of the crushing operation by the crusher, estimated based on the feature amount in the first modification of the first embodiment, together with the transition of the waveform of the motor current. [Figure 5] FIG. 10 is a diagram illustrating a feature amount for estimating the end stage of the crushing operation by the crusher in the first modification of the first embodiment. [Figure 6] FIG. 10 is a diagram showing the end stage of the re-granulation work by the pulverizer, estimated based on the feature amount in the second modification of the first embodiment, together with the transition of the waveform of the motor current. [Figure 7] FIG. 10 is a diagram illustrating a feature amount for estimating the end stage of the re-granulation work by the pulverizer in the second modification of the first embodiment. [Figure 8] 10 is a flowchart showing a processing flow of a plastic crushing operation management method in a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. The configurations of the following embodiments are examples, and the present disclosure is not limited to the configurations of the embodiments.

[0022] First Embodiment An overview of the plastic crushing operation management system in the first embodiment will be described with reference to FIG. 1. FIG. 1 is a diagram showing the schematic configuration of the plastic crushing operation management system in this embodiment. The crushing operation management system 1 according to this embodiment is a system for managing the crushing operation carried out in the plastic recycling process. In this embodiment, the following description will be given taking as an example a case where the plastic is agricultural plastic.

[0023] Here, agricultural plastics in this embodiment are defined as plastics that are discarded after being used in the agricultural field in greenhouses, mulches, etc. In the recycling process, such agricultural plastics are subjected to processes such as washing, crushing, and sorting in that order, but in conventional technology, the crushing process is managed by workers visually monitoring the status, which has led to problems such as the burden on workers and the dependency of work quality on individual workers.

[0024] Therefore, the crushing operation management system 1 according to this embodiment solves the problems of worker burden and work quality depending on individuals by more appropriately managing the crushing operation carried out in the plastic recycling process. As shown in Fig. 1, this crushing operation management system 1 includes a crusher 200 that crushes input plastic (agricultural plastic) 100, and an information processing device 300 that estimates the completion stage of the crushing operation by the crusher 200.

[0025] Here, each of the components that make up the crushing operation management system 1 will be described in detail below.

[0026] The crusher 200 is configured to have a rotary blade 201 that crushes the plastic 100 that has been put in, and a motor 202 that is a power source for rotating the rotary blade 201.

[0027] The information processing device 300 then estimates the end stage of the crushing operation by the crusher 200 based on the motor current that changes in accordance with the torque generated by the motor 202.

[0028] The information processing device 300 in this embodiment may be any electronic device having the processing capabilities for arithmetic and processing operations such as data acquisition, generation, and updating, such as a personal computer, server, mainframe, tablet terminal, or other electronic device. That is, the information processing device 300 may be configured as a computer having a processor such as a CPU or GPU, a main storage device such as RAM or ROM, and an auxiliary storage device such as an EPROM, a hard disk drive, a solid-state drive, or removable media. The removable media may be, for example, a USB memory or a disc recording medium such as a CD or DVD. The auxiliary storage device stores an operating system (OS), various programs, various tables, and the like.

[0029] Furthermore, the information processing device 300 may appropriately use SaaS (Software as a Service), Paas (Platform as a Service), or IaaS (Infrastructure as a Service) using a cloud server, without providing software, hardware, an OS, etc. dedicated to the crushing work management system 1 of this embodiment.

[0030] The information processing device 300 has, as functional units, a communication unit 301, a storage unit 302, and a control unit 303. A program stored in the auxiliary storage device is loaded into a working area of ​​the main storage device and executed, and each functional unit is controlled through the execution of the program, thereby realizing each function that matches the predetermined purpose of each functional unit. However, some or all of the functions may be realized by hardware circuits such as ASICs and FPGAs.

[0031] Here, the communication unit 301 is a communication interface for connecting the information processing device 300 to the crusher 200 or a network. The communication unit 301 is configured to include, for example, a network interface board and a wireless communication circuit for wireless communication. The information processing device 300 is connected to the crusher 200 and other external devices via the communication unit 301 so as to be able to communicate with them.

[0032] The storage unit 302 includes a main storage unit and an auxiliary storage unit. The main storage unit is a memory in which programs executed by the control unit 303 and data used by the control programs are developed. The auxiliary storage unit is a device in which programs executed by the control unit 303 and data used by the control programs are stored. The storage unit 302 stores a motor current that changes depending on the torque generated by the motor 202 of the crusher 200.

[0033] The control unit 303 is a functional unit that controls the information processing device 300. The control unit 303 can be realized by an arithmetic processing device such as a CPU. The control unit 303 further includes three functional units: an acquisition unit 3031, a calculation unit 3032, and an estimation unit 3033. These functional units may be realized by the CPU executing stored programs.

[0034] The acquiring unit 3031 acquires the motor current at a predetermined cycle. The acquiring unit 3031 can acquire the motor current, for example, via a network or by being directly connected to the crusher 200. The crusher 200 may be configured to have an interface for outputting the motor current to the outside.

[0035] The calculation unit 3032 calculates a predetermined characteristic amount for estimating the end stage of the crushing operation by the crusher 200 based on the motor current acquired by the acquisition unit 3031. Details of the characteristic amount will be described later.

[0036] The estimation unit 3033 estimates the end stage of the crushing operation by the crusher 200 based on the feature amount calculated by the calculation unit 3032. Details of this estimation process will be described later.

[0037] Next, the characteristics of the motor current when the plastic 100 is crushed by the crusher 200 will be described with reference to FIG.

[0038] FIG. 2 is a diagram illustrating an example of the transition of the waveform of the motor current when the plastic 100 is crushed by the crusher 200. As shown in FIG.

[0039] As shown in Figure 2, the motor current value increases for 50 seconds after the start of crushing the plastic 100 by the crusher 200. Then, the motor current value stabilizes from 50 seconds to 250 seconds after the start of crushing. Meanwhile, the motor current value increases again from 250 seconds to 450 seconds after the start of crushing, and then stabilizes. Then, the motor current value decreases from 450 seconds to 600 seconds after the start of crushing.

[0040] The present inventors have found a correlation between the transition of the waveform of the motor current and the state of crushing of the plastic 100 by the crusher 200. More specifically, for 50 seconds from the start of crushing the plastic 100 by the crusher 200, the plastic 100 is fed into the crusher 200, and the load from the rotary blade 201 of the crusher 200 begins to be applied to the motor 202, causing the value of the motor current to increase. Then, for the period from 50 seconds to 250 seconds after the start of crushing, the feeding of the plastic 100 into the crusher 200 ends, and the resistance to the rotary blade 201 of the crusher 200 becomes approximately constant, and the load on the motor 202 from the rotary blade 201 also becomes approximately constant, causing the value of the motor current to stabilize. On the other hand, during the period from 250 seconds to 450 seconds after the start of the crushing operation, the plastic 100 in the crusher 200 is mixed in the crusher 200, with the plastic 100 having been fed in layers in the vertical direction, and the load on the motor 202 by the rotary blade 201 increases, causing the motor current value to rise again, and the plastic 100 that was in the upper layer in the crusher 200 moves to the lower layer and mixes, causing the motor current value to stabilize. Then, during the period from 450 seconds to 600 seconds after the start of the crushing operation, the plastic 100 in the crusher 200 is crushed into powder, and the motor current value decreases.

[0041] Furthermore, the present inventors have newly discovered that when the plastic 100 in the crusher 200 is being crushed into powder and the value of the motor current decreases, the variation in the value of the motor current becomes smaller.

[0042] However, there are still issues with the crushing process of agricultural plastics. The crushing process shown in Figure 2 takes about 10 minutes, but at agricultural plastic recycling plants, this crushing process is repeated over a continuous period of about 9 hours a day. At the site, the crushing process is managed by multiple workers working in shifts, who visually monitor the condition of the materials.

[0043] However, visual monitoring by workers has led to problems such as the burden on workers and the dependency of work quality on individual workers. For example, in the prior art, the end of the crushing work by the crusher 200 is determined by the worker by monitoring the downward trend of the motor current value as described above and images (video) taken in real time by a camera inside the crusher 200, but the criteria for this determination are vague and have become tacit knowledge.

[0044] If an operator were to overlook the final stage of the above monitoring, the plastic 100 would be over-pulverized, causing the plastic 100 to solidify into a lump-like mass inside the crusher 200. This would not only impair the quality of the plastic 100 to be recycled, but would also require maintenance of the crusher 200.

[0045] Therefore, in the crushing operation management system 1 according to this embodiment, the information processing device 300 estimates the end stage of the crushing operation by the crusher 200. This will be described in detail with reference to FIG.

[0046] 3 is a diagram illustrating a feature quantity for estimating the end stage of the crushing operation by the crusher 200 in this embodiment. Note that the feature quantity in this embodiment is the variance of the difference between the value of the motor current and the moving average value of the motor current.

[0047] In this embodiment, the calculation unit 3032 calculates the moving average value of the motor current for a first range immediately preceding each time the motor current is acquired. Here, the first range is, for example, 20 seconds. In this case, the moving average value can be calculated by dividing the sum of the motor current values ​​for the most recent 20 seconds by the number of motor current data points for the most recent 20 seconds. FIG. 3(a) shows the 20-second moving average value for each time of the transition of the motor current waveform shown in FIG. 2, along with the transition of the motor current waveform. As shown in FIG. 3(a), by setting the first range to 20 seconds, the tendency of the transition of the motor current waveform shown in FIG. 2 can be clearly represented.

[0048] Furthermore, in this embodiment, the calculation unit 3032 calculates the difference between the motor current value at each time point and the moving average value at that time point, and calculates the variance of the difference over a second range immediately preceding that time point. Here, the second range is, for example, 15 seconds. In this case, the variance can be calculated by dividing the sum of squared deviations of the difference over the last 15 seconds by the number of motor current data points over the last 15 seconds. Figure 3(b) shows the 15-second variance of the difference between the motor current value at each time point and the moving average value. As shown in Figure 3(b), during the period from 250 seconds to 450 seconds after the start of the crushing operation (this period, as shown in Figure 2 above, when the plastic 100 introduced into the crusher 200 in layers in the vertical direction is mixed within the crusher 200, the load on the motor 202 by the rotating blade 201 increases, the value of the motor current rises again, and the value of the motor current stabilizes as the plastic 100 in the upper layers in the crusher 200 moves to the lower layers and mixes), the variance is relatively large. In other words, during this period, the variation in the motor current value is large. On the other hand, during the period from 450 seconds to 600 seconds after the start of the crushing operation (this period, as shown in Figure 2 above, when the plastic 100 in the crusher 200 is crushed into powder and the value of the motor current decreases), the variance, which was relatively large up until then, converges to a small value. In other words, during this period, the variation in the value of the motor current converges.

[0049] Then, the estimation unit 3033 in this embodiment estimates that the end stage of the crushing operation by the crusher 200 has arrived when the above-mentioned feature amount is equal to or less than a predetermined first threshold. Here, the above-mentioned first threshold is, for example, when the variance in FIG. 3(b) is 3. The estimation unit 3033 performs the above estimation after a predetermined time has elapsed since the start of the crushing operation (in this embodiment, for example, after 250 seconds have elapsed, when the value of the motor current rises again).

[0050] According to this, based on a clear criterion indicating that the variation in the motor current value has become small, it can be estimated that the end stage of the crushing operation by the crusher 200 has arrived at the time when the plastic 100 in the crusher 200 is crushed into powder. Note that the transition of the motor current waveform is not limited to the example shown in FIG. 2 above, and there can be multiple patterns. However, according to this embodiment, the end stage was estimated for the transition of 1,869 waveforms based on the above criterion, and as a result, it became possible to accurately estimate the end stage for approximately 77.4% of the waveforms (the accuracy of the estimation of the end stage can be defined by a correct / incorrect judgment of the end stage judgment made by the operator).

[0051] This allows the worker to stop and finish the crushing work by the crusher 200 at the completion stage estimated by the information processing device 300, which significantly reduces the burden on the worker and minimizes the dependency of work quality on individuals.

[0052] According to the crushing operation management system 1 described above, the crushing operation in the plastic 100 recycling process can be managed more appropriately.

[0053] <Modification 1 of the First Embodiment> A first modification of the first embodiment will now be described. In the above description of the first embodiment, an example was described in which the variance of the difference between the motor current value and the moving average value of the motor current is used as a feature quantity for estimating the end stage of the crushing operation by the crusher 200. In contrast, in this modification, an example will be described in which the variance of the moving average slope of the motor current and the distance between the motor current value and the moving average slope line are used as feature quantities for estimating the end stage of the crushing operation by the crusher 200.

[0054] The feature quantity described in the above description of the first embodiment is subject to two influences: fluctuations in the value of the motor current due to fluctuations in the load on the motor 202 caused by the rotary blade 201 of the crusher 200, and variation. Therefore, when the plastic 100 in the crusher 200 is crushed into powder and the value of the motor current decreases, the variation in the value of the motor current becomes smaller, but this variation may be affected by the tendency of fluctuations in the value of the motor current.

[0055] Therefore, the present inventors have investigated the fact that the variation in the motor current value decreases as the plastic 100 in the crusher 200 is crushed into powder, by dividing this into two features, the variation in the motor current value and the variation, and then examining the feature quantities representing each of these. This will be explained with reference to Figs. 4 and 5.

[0056] FIG. 4 is a diagram showing the end stage of the crushing operation by the crusher 200, estimated based on the feature amount in this modification, along with the transition of the waveform of the motor current.

[0057] FIG. 5 is a diagram illustrating the feature amount for estimating the end stage of the crushing operation by the crusher 200 in this modified example.

[0058] In this modification, as shown in Fig. 4, the end stage of the crushing operation by the crusher 200 arrives at a predetermined timing during the period when the value of the motor current decreases as described in the first embodiment above. This end stage is determined based on two feature amounts shown in Fig. 5.

[0059] Here, in this modification, the calculation unit 3032 calculates, at each time when the motor current is acquired, a moving average value of the motor current in a third range immediately preceding that time. Here, the third range is, for example, 20 seconds. In this case, the moving average value can be calculated by dividing the sum of the motor current values ​​for the most recent 20 seconds by the number of data points for the motor current values ​​for the most recent 20 seconds. Furthermore, the calculation unit 3032 calculates, as a first feature, a moving average slope calculated by dividing the difference between the moving average values ​​at the beginning and end of the third range by the time increment (20 seconds) for the third range.

[0060] FIG. 5(a) shows the moving average slope at each time point of the transition of the motor current waveform shown in FIG. 4. As shown in FIG. 5(a), after 450 seconds into the grinding operation, when the motor current value shown in FIG. 4 peaks, the moving average slope becomes generally negative. However, in situations where the motor current value fluctuates instantaneously, the moving average slope becomes positive at that timing, even after 450 seconds into the grinding operation. In other words, the time period when the moving average slope becomes generally negative represents a stage in which the motor current value is decreasing, and if an instantaneous fluctuation occurs in the motor current value during that time period, the moving average slope becomes positive at that timing. In this way, the first feature, the moving average slope, is a feature that can capture fluctuations in the motor current value.

[0061] Furthermore, in this modification, the calculation unit 3032 calculates the distance between the motor current value at each time point and a sloped line having the moving average slope for that time point. Here, the sloped line, i.e., the moving average slope line, can be defined based on a point whose coordinate values ​​are the time point at which the motor current is acquired and the moving average value at that time point, and the moving average slope at that time point. The distance is a straight-line distance drawn vertically from the data point of the motor current value at each time point at which the motor current is acquired to the moving average slope line, and can be calculated based on a well-known formula for the distance between a point and a line. Furthermore, the calculation unit 3032 calculates the variance of the distance within a fourth range immediately preceding the time point at which the motor current is acquired, thereby calculating the variance as a second feature. Here, the fourth range is, for example, 20 seconds. In this case, the variance can be calculated by dividing the sum of squared deviations of the distance for the most recent 20 seconds by the number of data points for the motor current value during the most recent 20 seconds.

[0062] Figure 5(b) shows the variance of the distance between the data points of the motor current value and the moving average slope line at each time of the transition of the motor current waveform shown in Figure 4. This variance of distance (the second feature) is a feature that can capture the variation in the motor current value, and after 450 seconds into the grinding operation, when the motor current value shown in Figure 4 reaches its peak, the variance of distance rapidly converges to a smaller value than before, as shown in Figure 5(b).

[0063] Therefore, the estimation unit 3033 in this modification estimates that the end stage of the crushing operation by the crusher 200 has arrived when the moving average slope, which is the first feature amount described above, is equal to or less than a predetermined second threshold value and the variance of the distance, which is the second feature amount described above, is equal to or less than a predetermined third threshold value. Here, the second threshold value is, for example, when the moving average slope in FIG. 5(a) is 0, and the third threshold value is, for example, when the variance in FIG. 5(b) is 6. The estimation unit 3033 performs the above estimation after a predetermined time has elapsed since the start of the crushing operation (in this modification, for example, after 300 seconds have elapsed, when the value of the motor current rises again).

[0064] In this way, by subdividing the change in the value of the motor current into two features, a fluctuation element and a variation element, and then simultaneously using the feature quantities representing each, it is possible to more accurately estimate the end stage of the grinding operation by the grinder 200, even if the value of the motor current includes an instantaneous change. Note that, according to this modified example, the end stage was estimated for the transitions of 1,869 waveforms based on the above-mentioned criteria, and as a result, it became possible to accurately estimate the end stage for approximately 89.1% of the waveforms (the accuracy of the estimation of the end stage can be defined by determining whether it is correct or incorrect compared to the judgment of the end stage made by the operator).

[0065] The crushing operation management system 1 described above also makes it possible to more appropriately manage the crushing operation in the plastic 100 recycling process.

[0066] <Modification 2 of the First Embodiment> A second modification of the first embodiment will be described. In the recycling process of agricultural plastics, after the plastic crushing process, a separation process is carried out to separate plastics that can be recycled as resources. In this separation process, plastics that were not crushed in the crushing process are also separated. Such plastics are then subjected to a re-granulation process in which they are crushed again using a crusher 200. In this modification, plastic 100 represents the plastic that is the target of the re-granulation process. The above-mentioned re-granulation process can also be considered as one of the crushing processes of the present disclosure.

[0067] The present inventors have also found that in the re-granulation operation of plastic 100, there is a correlation between the transition of the waveform of the motor current when plastic 100 is pulverized by pulverizer 200 and the pulverization state of plastic 100 by pulverizer 200. Furthermore, the present inventors have found that the end stage of the re-granulation operation by pulverizer 200 can be estimated by using a feature amount that represents the fluctuation in the value of the motor current. This will be described with reference to Figs. 6 and 7.

[0068] FIG. 6 is a diagram showing the end stage of the re-granulation work by the pulverizer 200, estimated based on the feature amounts in this modified example, along with the transition of the waveform of the motor current.

[0069] FIG. 7 is a diagram illustrating the feature amount for estimating the end stage of the re-granulation work by the pulverizer 200 in this modified example.

[0070] In this modified example, as shown in Figure 6, the value of the motor current increases for 40 seconds after the start of the re-granulation operation of the plastic 100 by the crusher 200. On the other hand, after 40 seconds from the start of the re-granulation operation, the value of the motor current gradually decreases. Then, at a predetermined timing when the value of the motor current decreases, the end stage of the re-granulation operation by the crusher 200 has arrived.

[0071] Regarding this, when focusing on the correlation with the crushing state of the plastic 100 by the crusher 200, the first 40 seconds from the start of the re-granulation work of the plastic 100 by the crusher 200 is a period during which the plastic 100 is mixed inside the crusher 200 as it is fed into the crusher 200, and the load on the motor 202 by the rotating blade 201 of the crusher 200 increases, causing the value of the motor current to rise. On the other hand, after 40 seconds from the start of the re-granulation work, the plastic 100 inside the crusher 200 is crushed into powder, causing the value of the motor current to drop.

[0072] Here, in this modification, the calculation unit 3032 calculates, at each time when the motor current is acquired, a moving average value of the motor current in a fifth range immediately preceding that time. Here, the fifth range is, for example, 30 seconds. In this case, the moving average value can be calculated by dividing the sum of the motor current values ​​for the most recent 30 seconds by the number of motor current value data for the most recent 30 seconds. Furthermore, the calculation unit 3032 calculates, as a feature, a moving average slope calculated by dividing the difference between the moving average values ​​at the beginning and end of the fifth range by the time increment (30 seconds) for the fifth range.

[0073] FIG. 7 shows the moving average slope at each time of the transition of the motor current waveform shown in FIG. 6. After 40 seconds from the start of the regranulation operation, the plastic 100 in the crusher 200 is crushed into powder, and as the motor current value decreases, the moving average slope converges to 0. In other words, the motor current waveform stabilizes at a certain value. At this time, if the moving average slope falls within a predetermined range after falling below a predetermined fourth threshold, it is assumed that the end stage of the regranulation operation by the crusher 200 has arrived, and it has been found that this end stage can be estimated more accurately.

[0074] Therefore, in this modified example, the estimation unit 3033 estimates that the end stage of the re-granulation work by the grinder 200 has arrived when the moving average slope, which is the above-mentioned characteristic quantity, falls below the lower limit value (fourth threshold value of the present disclosure) of the threshold range of -0.15 to 0.15 (the specified range of the present disclosure) and then falls back into this threshold range (the specified range of the present disclosure).

[0075] The crushing operation management system 1 described above also makes it possible to more appropriately manage the crushing operation in the plastic 100 recycling process.

[0076] Second Embodiment A second embodiment will be described with reference to Fig. 8. This embodiment is a plastic crushing operation management method for managing the crushing operation carried out in a plastic recycling process.

[0077] 8 is a flowchart showing the processing flow of the plastic crushing operation management method in this embodiment. In this embodiment, the crushing operation of the plastic 100 is performed by the crusher 200 described in the first embodiment, and the processing flow shown in FIG. 8 is executed by the information processing device 300.

[0078] In this flow, first, an acquisition step is executed in S101. In the processing of S101, the information processing device 300 acquires, at a predetermined cycle, a motor current that changes in response to the torque generated by the motor 202, which is a power source for rotating the rotary blade 201 that crushes the plastic 100 fed into the crusher 200. Details of this acquisition step are as described above in the description of the first embodiment.

[0079] Next, in S102, a calculation step is executed. In the process of S102, the information processing device 300 calculates a predetermined feature amount for estimating the end stage of the crushing operation by the crusher 200 based on the motor current acquired in the process of S101.

[0080] In the processing of S102, the information processing device 300 may calculate, at each time when the motor current is acquired, the difference between the moving average value of the motor current in the first range immediately preceding that time and the value of the motor current at that time, and calculate the variance of the difference in the second range immediately preceding that time, thereby calculating the variance as a feature.

[0081] In this case, in S103, the information processing device 300 can estimate that the crushing operation by the crusher 200 has reached the end stage if the feature amount calculated in the process of S102 is equal to or less than a predetermined first threshold. Details of these processes are as described above in the description of the first embodiment.

[0082] Furthermore, in the processing of S102, the information processing device 300 may calculate, at each time when the motor current is acquired, a moving average value of the motor current in a third range immediately preceding that time, and calculate a moving average slope calculated by dividing the difference between the moving average value at the beginning and end of the third range by the time increment in the third range as a first feature, and at each time when the motor current is acquired, calculate the distance from the value of the motor current at that time to a sloped line having the moving average slope at that time, and calculate the variance of that distance in a fourth range immediately preceding that time, thereby calculating the variance as a second feature.

[0083] In this case, in S103, the information processing device 300 can estimate that the crushing operation by the crusher 200 has reached the end stage if the first feature amount calculated in the process of S102 is equal to or less than a predetermined second threshold value and the second feature amount is equal to or less than a predetermined third threshold value. Details of these processes are as described above in the explanation of Modification 1 of the first embodiment.

[0084] Furthermore, when the plastic crushing operation management method of this embodiment is applied to the re-granulation operation of plastic 100 described in the explanation of variant example 2 of the first embodiment above, in the processing of S102, the information processing device 300 may calculate, at each time when the motor current is acquired, the moving average value of the motor current in the fifth range immediately preceding that time, and may calculate, as a feature, the moving average slope calculated by dividing the difference between the moving average values ​​at the beginning and end of the fifth range by the time increment in the fifth range.

[0085] In this case, the information processing device 300 can estimate in S103 that the end stage of the re-granulation work by the pulverizer 200 has arrived when the feature amount calculated in the process of S102 falls within a predetermined range after becoming less than a predetermined fourth threshold. Details of these processes are as described above in the explanation of Modification 2 of the first embodiment.

[0086] The above-described method for managing the crushing operation of plastics also makes it possible to more appropriately manage the crushing operation in the recycling process of plastics 100. [Explanation of symbols]

[0087] 1. Crushing operation management system 100···Plastic 200 Crusher 201 Rotary blade 202 Motor 300 Information processing device 303 Control section 3031··Acquisition Department 3032··Calculation section 3033·Estimation part

Claims

1. A plastic crushing operation management system for managing crushing operations carried out in a plastic recycling process, a crusher having a rotary blade for crushing the plastics that have been input, and a motor as a power source for rotating the rotary blade; an information processing device that estimates an end stage of the crushing operation by the crusher based on a motor current that changes in accordance with a torque generated by the motor, The information processing device includes: an acquisition unit that acquires the motor current at a predetermined cycle; a calculation unit that calculates a predetermined feature amount for estimating the end stage based on the acquired motor current; an estimation unit that estimates the end stage based on the calculated feature amount, Plastic crushing operation management system.

2. the calculation unit calculates, at each time when the motor current is acquired, a difference between a moving average value of the motor current in a first range immediately before the time and the value of the motor current at the time, and calculates a variance of the difference in a second range immediately before the time, thereby calculating the variance as the feature quantity; the estimation unit estimates that the end stage has arrived when the calculated feature amount is equal to or less than a predetermined first threshold value. The plastic crushing operation management system according to claim 1.

3. the calculation unit calculates, at each time when the motor current is acquired, a moving average value of the motor current in a third range immediately preceding the time, and calculates a moving average slope as the first feature value by dividing a difference between the moving average value at the beginning and end of the third range by a time increment in the third range; at each time when the motor current is acquired, calculates a distance from a sloped line having the moving average slope at the time to the value of the motor current at the time, and calculates a variance of the distance in a fourth range immediately preceding the time, thereby calculating the variance as the second feature value; the estimation unit estimates that the end stage has arrived when the calculated first feature amount is equal to or less than a predetermined second threshold and the calculated second feature amount is equal to or less than a predetermined third threshold. The plastic crushing operation management system according to claim 1.

4. the calculation unit calculates, at each time when the motor current is acquired, a moving average value of the motor current in a fifth range immediately preceding the time, and calculates, as the feature amount, a moving average slope calculated by dividing a difference between the moving average values ​​at the beginning and end of the fifth range by a time increment in the fifth range; the estimation unit estimates that the end stage has arrived when the calculated feature amount falls within a predetermined range after becoming less than a predetermined fourth threshold. The plastic crushing operation management system according to claim 1.

5. A plastic crushing operation management method for managing crushing operations carried out in a plastic recycling process, comprising: an acquisition step of acquiring, at a predetermined cycle, a motor current that changes in accordance with the torque generated by a motor that is a power source for rotating a rotary blade that crushes the plastics fed into the crusher; a calculation step of calculating a predetermined feature amount for estimating an end stage of the crushing operation by the crusher based on the acquired motor current; an estimation step of estimating the end stage based on the calculated feature amount; A method for managing a plastic crushing operation, comprising:

6. In the calculation step, at each time when the motor current is acquired, a difference is calculated between a moving average value of the motor current in a first range immediately preceding the time and the value of the motor current at the time, and a variance of the difference in a second range immediately preceding the time is calculated, thereby calculating the variance as the feature quantity; In the estimation step, it is estimated that the end stage has arrived when the calculated feature amount is equal to or less than a predetermined first threshold.

6. The method for managing plastic crushing operations according to claim 5.

7. In the calculation step, at each time when the motor current is acquired, a moving average value of the motor current in a third range immediately preceding the time is calculated, and a moving average slope calculated by dividing the difference between the moving average value at the beginning and end of the third range by a time increment in the third range is calculated as the first feature amount; at each time when the motor current is acquired, a distance from the value of the motor current at that time to a sloped line having the moving average slope at that time is calculated, and a variance of the distance in a fourth range immediately preceding the time is calculated to calculate the variance as the second feature amount; In the estimation step, it is estimated that the end stage has arrived when the calculated first feature amount is equal to or less than a predetermined second threshold value and the calculated second feature amount is equal to or less than a predetermined third threshold value.

6. The method for managing plastic crushing operations according to claim 5.

8. In the calculation step, at each time when the motor current is acquired, a moving average value of the motor current in a fifth range immediately preceding the time is calculated, and a moving average slope calculated by dividing a difference between the moving average values ​​at the beginning and end of the fifth range by a time increment in the fifth range is calculated as the feature amount; In the estimation step, it is estimated that the end stage has arrived when the calculated feature amount falls within a predetermined range after becoming less than a predetermined fourth threshold.

6. The method for managing plastic crushing operations according to claim 5.

Images