A machine tool spare part monitoring method, device and medium based on an industrial internet

Abstract

The application discloses a machine tool spare part monitoring method and device based on an industrial internet, and a medium, wherein the method comprises the following steps: collecting operation parameters of machine tool spare parts, reconstructing feature spaces of the operation parameters to obtain operation sample data; performing state diagnosis on the operation sample data to obtain state diagnosis information of the machine tool spare parts; determining defect growth levels of the machine tool spare parts according to the state diagnosis information, so as to determine specified machine tool spare parts with defect growth levels greater than a preset level from the machine tool spare parts; obtaining historical machine tool spare parts corresponding to the specified machine tool spare parts, and determining the similarity between the specified machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining use time length of the machine tool spare parts according to the similarity; the spare part types and operation conditions corresponding to the historical machine tool spare parts and the specified machine tool spare parts are the same.

Description

Technical Field

[0001] The present application relates to the technical field of CNC machine tool monitoring, and specifically to a machine tool spare parts monitoring method, equipment and medium based on the Industrial Internet. Background Art

[0002] As an automated machine tool equipped with a program control system, digitally controlled machine tools can greatly improve the processing capacity and efficiency of machine tools and are currently widely used in industry.

[0003] Consumables such as machine tool spare parts are essential for industrial production. During daily industrial production, the operating status of machine tool spare parts must be monitored in real time, and the remaining life of the spare parts must be reasonably predicted to ensure the safety and reliability of the equipment. However, currently, most spare parts are regularly inspected and estimated using manual labor or monitoring equipment such as cameras. Monitoring the remaining life of spare parts using these methods is unreliable and costly, making them difficult to apply to the industrial sector. Summary of the Invention

[0004] In order to solve the above problems, this application proposes a machine tool spare parts monitoring method based on the Industrial Internet, including:

[0005] Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data;

[0006] Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part;

[0007] determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level;

[0008] Obtain historical machine tool spare parts corresponding to the designated machine tool spare parts, and determine the similarity between the designated machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the designated machine tool spare parts based on the similarity; the historical machine tool spare parts and the designated machine tool spare parts have the same spare parts type and operating conditions.

[0009] In one implementation of the present application, the feature space reconstruction of the operating parameters to obtain operating sample data specifically includes:

[0010] Generate an original time series corresponding to the operating parameters;

[0011] Downsampling the original time series according to different time resolutions to obtain a feature sequence for characterizing the operating parameters;

[0012] Reconstructing the feature space of the feature sequence to obtain a reconstructed feature sequence;

[0013] The reconstructed feature sequence is clustered to generate clustered running sample data.

[0014] In one implementation of the present application, after predicting the remaining service life of the machine tool spare part based on the similarity, the method further includes:

[0015] Determine the machine tool spare part whose remaining service life is less than a preset service life as a spare part to be replaced, and determine the fuzzy demand quantity of the spare part to be replaced;

[0016] Performing random modeling on the fuzzy demand quantity, and determining the fuzzy constraint conditions of the spare parts to be replaced based on a fuzzy evaluation model obtained after the random modeling;

[0017] Determining a target cost model for the spare part to be replaced based on the fuzzy constraint conditions;

[0018] The order unit price and unit inventory cost of the spare part to be replaced are obtained, and based on the target cost model, the actual demand quantity of the spare part to be replaced is obtained according to the order unit price, the unit inventory cost and the fuzzy demand quantity.

[0019] In one implementation of the present application, determining the similarity between the designated machine tool spare part and the historical machine tool spare part to predict the remaining service life of the machine tool spare part based on the similarity specifically includes:

[0020] determining a current monitoring point of the machine tool spare part;

[0021] Obtaining target operation sample data of the designated machine tool spare part within a preset evaluation interval before the current monitoring point, and historical sample data of the historical machine tool spare part within any preset evaluation interval;

[0022] Calculating the similarity between the target sample data and the historical sample data corresponding to the current monitoring point;

[0023] Determining a monitoring weight corresponding to the historical machine tool spare part at the current monitoring point according to a ratio between the similarity of the historical machine tool spare part and the sum of the similarities of all historical machine tool spare parts;

[0024] The actual remaining usage time of the historical machine tool spare part at the current monitoring point is determined, and the remaining usage time of the machine tool spare part is predicted based on the actual remaining usage time, the monitoring weight and the similarity.

[0025] In one implementation of the present application, before determining the defect growth level of the machine tool spare part according to the status diagnosis information, the method further includes:

[0026] Determine a spare parts association network corresponding to each machine tool spare part, wherein a node of the spare parts association network represents a fault event corresponding to the machine tool spare part, an edge represents an association relationship between the fault events, the weight of the edge represents a degree of association between the fault events, and the direction of the edge represents an event impact relationship of the fault event;

[0027] Determining a fault event corresponding to the machine tool spare part according to the status diagnosis information;

[0028] Determining, based on the spare parts association network, associated fault events that can generate the event impact relationship on the fault event, and weights between the associated fault events and the fault event;

[0029] determining a first fault level and a second fault level corresponding to the fault event and the associated fault event, respectively, and determining a corresponding first self-influence and a second self-influence according to the first fault level and the second fault level; the first fault level and the second fault level are positively correlated with the first self-influence and the second self-influence, respectively;

[0030] The event impact of the associated fault event on the machine tool spare part is determined according to the product of the first self-influence, the second self-influence and the weight.

[0031] In one implementation of the present application, determining the defect growth level of the machine tool spare part according to the status diagnosis information specifically includes:

[0032] Determining whether a failure event occurs in the machine tool spare part according to the status diagnosis information;

[0033] In the event that a fault event occurs on the machine tool spare part, taking the fault level corresponding to the fault event as the initial defect growth level of the machine tool spare part;

[0034] The ratio between the target event impact degree corresponding to the machine tool spare part and the sum of the event impact degrees is used as the corresponding event impact coefficient; the target event impact degree is greater than a preset threshold;

[0035] Performing coefficient compensation on the initial defect growth level according to the event impact coefficient to obtain a compensated defect growth level;

[0036] In the case that no failure event occurs to the machine tool spare part, an event impact coefficient corresponding to the machine tool spare part is determined, and the defect growth level of the machine tool spare part is determined based on the event impact coefficient.

[0037] In one implementation of the present application, after obtaining the actual demand for the spare parts to be replaced, the method further includes:

[0038] Determine the spare parts to be put into storage from the spare parts to be replaced according to the remaining service life of the spare parts to be replaced, and generate a storage request carrying information of the spare parts to be put into storage; the information of the spare parts to be put into storage includes a spare part identifier;

[0039] Determine, based on the spare part identification, whether there is a storage location in the current spare parts warehouse that matches the spare part identification;

[0040] If not, determining, based on the spare parts association network, the multiple nodes where the spare parts to be stored are located, and the categories of other nodes connected by the edges associated with the multiple nodes;

[0041] The storage location of the spare part to be stored is determined according to the number of edges connected to other nodes in different categories.

[0042] In one implementation of the present application, clustering the reconstructed feature sequence to generate clustered running sample data specifically includes:

[0043] Determining the local density and distance deviation of the feature sequence, and determining the cluster center point according to the local density and the distance deviation;

[0044] The non-cluster center points are clustered according to the cluster center points to obtain clustered running sample data.

[0045] An embodiment of the present application provides a machine tool spare parts monitoring device based on the Industrial Internet, characterized in that the device includes:

[0046] at least one processor;

[0047] and, a memory communicatively coupled to the at least one processor;

[0048] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0049] Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data;

[0050] Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part;

[0051] determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level;

[0052] Obtain historical machine tool spare parts corresponding to the designated machine tool spare parts, and determine the similarity between the designated machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the designated machine tool spare parts based on the similarity; the historical machine tool spare parts and the designated machine tool spare parts have the same spare parts type and operating conditions.

[0053] An embodiment of the present application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0054] Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data;

[0055] Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part;

[0056] determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level;

[0057] Obtain historical machine tool spare parts corresponding to the designated machine tool spare parts, and determine the similarity between the designated machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the designated machine tool spare parts based on the similarity; the historical machine tool spare parts and the designated machine tool spare parts have the same spare parts type and operating conditions.

[0058] The machine tool spare parts monitoring method based on the Industrial Internet proposed in this application can bring the following beneficial effects:

[0059] The collected machine tool spare parts operation sample data is diagnosed, and the defective designated machine tool spare parts are screened out according to the status diagnosis results. Then, by obtaining historical machine tool spare parts information with the same usage scenario as the designated machine tool spare parts, the service life of the designated machine tool spare parts is predicted, realizing automatic monitoring of machine tool spare parts with higher accuracy and improved monitoring efficiency. In addition, the demand status of the spare parts can be prompted by the predicted remaining usage time of the spare parts, effectively improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0061] Figure 1 A flowchart of a machine tool spare parts monitoring method based on the Industrial Internet provided in an embodiment of the present application;

[0062] Figure 2 A schematic diagram of fuzzy sets of different types of uncertain requirements provided in an embodiment of the present application;

[0063] Figure 3 A structural schematic diagram of a machine tool spare parts monitoring device based on the Industrial Internet provided in an embodiment of the present application. DETAILED DESCRIPTION

[0064] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0065] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, an embodiment of the present application provides a machine tool spare parts monitoring method based on the Industrial Internet, including:

[0067] S101: collecting operating parameters of machine tool spare parts, and reconstructing the operating parameters in a feature space to obtain operating sample data.

[0068] Machine tool spare parts refer to components and parts used to replace vulnerable parts in machines and instruments, such as bearings and cutting tools. In the present application, machine tool spare parts generally refer to spare parts in service and in use. Multiple sensors installed on the machine tool collect operating parameters of the machine tool spare parts at preset sampling intervals. These parameters include, but are not limited to, temperature, frequency, current, and voltage.

[0069] In one embodiment, after obtaining the operating parameters, the present application can generate the original time series corresponding to the operating parameters according to the sampling time. In order to improve the accuracy of feature analysis, after obtaining the original time series, it is necessary to downsample the original time series according to different time resolutions, that is, average the sequence values ​​within the window with the time resolution as the window length, so as to obtain a coarse-grained feature sequence for characterizing the operating parameters. After obtaining the feature sequence, the feature space is reconstructed to obtain a reconstructed feature sequence. This process can be achieved by immune genetic feature reconstruction algorithm, metric learning, semantic-based reconstruction algorithm, etc. The reconstructed feature sequence makes the difference between dissimilar sample data larger and larger. The reconstructed feature sequence is clustered to generate clustered operating sample data. The operating sample data obtained at this time is classified according to the actual working conditions. The operating sample data obtained in this way is more targeted and can effectively improve the accuracy of subsequent analysis results.

[0070] Clustering can be achieved through the following steps: determining the local density and distance deviation of each sample point contained in the feature sequence, and selecting the sample point with the largest local density as the cluster center. After determining the cluster center, clustering the non-cluster center points based on the cluster center to obtain the clustered running sample data. This can be achieved specifically through the following formula:

[0071]

[0072] in, represents the local density of the i-th sample point, δ i Indicates the distance deviation of the i-th sample point.

[0073] S102: Perform status diagnosis on the running sample data to obtain status diagnosis information of the machine tool spare parts.

[0074] After obtaining the running sample data, the running sample data is diagnosed using a preset state diagnosis model to obtain state diagnosis information of the machine tool spare part, wherein the state diagnosis information is used to indicate whether a fault has occurred in the current machine tool spare part.

[0075] It should be noted that the state diagnosis model is obtained through training of a support vector regression machine. The state diagnosis information predicted by the support vector regression machine can be used to obtain the failure events occurring in the current machine tool spare parts.

[0076] S103: Determine the defect growth level of the machine tool spare parts according to the status diagnosis information, and determine a designated machine tool spare part having a defect growth level greater than a preset level from the machine tool spare parts.

[0077] After obtaining the current status diagnostic information of the machine tool spare parts, it is necessary to determine the fault events that have occurred in the machine tool spare parts. Taking bearings as an example, based on the diagnosed operating status, it can be determined whether the bearings have experienced fault events such as wear, excessive load, and improper lubrication.

[0078] If a machine tool spare part experiences a failure, the fault level corresponding to the failure event can be determined based on the preset mapping relationship between failure events and fault levels. This fault level is then used as the initial defect growth level for the machine tool spare part. The defect growth level represents the operating trend of the machine tool spare part; higher levels indicate a trend toward more severe failures. In addition to being affected by their own operation, machine tool spare parts can also be affected by other associated spare parts, leading to associated failures. Therefore, when determining the actual defect growth level of a machine tool spare part, the collateral impact of other machine tool spare parts on the current machine tool spare part must also be considered.

[0079] Specifically, a spare part association network corresponding to each machine tool spare part is determined. The nodes of the spare part association network represent the fault events corresponding to the machine tool spare part, the edges represent the associations between the fault events, the edge weights represent the degree of association between the fault events, and the edge directions represent the event impact relationships of the fault events. It should be noted that the spare part association network can be derived based on historical fault events and their resolutions. After determining the spare part association network, the fault events corresponding to the machine tool spare part are determined based on the status diagnostic information. Then, based on the spare part association network, the associated fault events that can generate external event impact relationships related to the fault event are determined, as well as the weights between the associated fault events and the fault events. It can be understood that this process is essentially equivalent to determining whether the fault event node corresponding to the machine tool spare part corresponds to the endpoint of a directed edge. Subsequently, the first and second fault levels corresponding to the fault event and the associated fault event are determined, respectively. Based on the first and second fault levels, the corresponding first and second self-influences are determined. The self-influences represent the degree of impact generated by different faults, and the first and second fault levels are positively correlated with the first and second self-influences, respectively. After obtaining the first and second self-influences, the product of the first and second self-influences and the weights is summed. The summed result is the event impact of the machine tool spare part corresponding to the associated fault event. The event impact indicates the degree to which a machine tool spare part is affected by its associated machine tool spare parts. A greater event impact indicates a greater impact from its associated machine tool spare parts, making it more likely to experience a chain failure.

[0080] After determining the event impacts corresponding to different spare parts, the initial defect growth can be compensated by the event impacts generated by multiple associated fault events associated with the current fault event, thereby improving the accuracy of the evaluation results.

[0081] Specifically, if a fault event occurs in a machine tool spare part, the ratio between the target event impact degree corresponding to the machine tool spare part and the sum of the event impact degrees is used as its corresponding event impact coefficient; wherein the target event impact degree is greater than a preset threshold. Then, according to the event impact coefficient, the initial defect growth level obtained above is coefficient-compensated to obtain the compensated defect growth level. The defect growth level obtained at this time represents the final fault assessment data of the machine tool spare part. If no fault event occurs in the machine tool spare part, the event impact coefficient corresponding to the machine tool spare part is determined at this time, and the defect growth level of the machine tool spare part is determined by the event impact coefficient. It should be noted that the initial defect growth level of the machine tool spare part corresponds to the fault level, and its corresponding value is greater than 1. That is, once a fault occurs in a machine tool spare part, its fault level is greater than level one by default. For a machine tool spare part that has not failed, its corresponding fault level can be defaulted to level one. In this way, the defect growth level of the machine tool spare part can be determined only by the event impact coefficient.

[0082] After obtaining the defect growth levels of different machine tool spare parts, if the defect growth level of a specified machine tool spare part is greater than the preset level, it means that its damage has reached the level that requires short-term replacement. At this time, these machine tool spare parts need to be screened out for the next step of life prediction.

[0083] S104: Obtain historical machine tool spare parts corresponding to the specified machine tool spare parts, and determine the similarity between the specified machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the machine tool spare parts based on the similarity; the historical machine tool spare parts and the specified machine tool spare parts have the same spare parts type and operating conditions.

[0084] Before predicting the life of machine tool spare parts, the following prerequisites must be met: the life status indicators of machine tool spare parts have been determined, the life status indicators can be continuously monitored and recorded, and a certain number of spare parts monitoring records have been established. In this way, based on the recorded data, historical machine tool spare parts with the same spare part type and operating conditions as the current service spare parts can be obtained. After obtaining the historical machine tool spare parts, the current monitoring point and the preset evaluation interval are determined. The evaluation interval can generally be determined based on experience or actual needs. The target operation sample data of the specified machine tool spare part within the preset evaluation interval before the current monitoring point, as well as the historical sample data of the historical machine tool spare parts within any preset evaluation interval, are obtained.

[0085] It should be noted that the above target sample data and historical sample data exist in the form of state vectors, which can be specifically expressed as: C0(k,H)=[C0(k.Δt),...,C0((kH).Δt)] (1), Wherein, Δt is the sampling interval, time point t is the kth monitoring point, T is the preset evaluation interval, T=(H+1).Δt, and H is a non-integer.

[0086] The similarity between the target running sample data and the historical sample data at the current monitoring point t = k.Δt is calculated using the following formula:

[0087]

[0088]

[0089] (H≤q≤M i ) (4)

[0090] Among them, α∈(0,1] is a real number used to adjust the proportion of similar state quantities, C0((kg).Δt) is the g-th state index of the machine tool spare part before the current monitoring point, C i ((qg).Δt) is the g-th status index of the historical spare part i before point q, M i is the failure monitoring point of historical spare part i, M i .Δt is the historical failure time point of spare part i.

[0091] According to the ratio between the similarity of historical machine tool spare parts and the sum of the similarities of all historical machine tool spare parts, the monitoring weight Vi(k) corresponding to the historical machine tool spare parts at the current monitoring point is determined, which can be specifically achieved through the following formula:

[0092]

[0093]

[0094] Where n represents the total number of historical machine tool spare parts.

[0095] Determine the actual remaining usage time of historical machine tool spare parts at the current monitoring point. Based on the actual remaining usage time, monitoring weight and similarity, predict the remaining usage time of machine tool spare parts. The specific formula can be expressed as follows:

[0096] Li(k)=(Mi-Ni(k)).Δt (6)

[0097] N i (k)=argminZ(k,H,i,q) (7)

[0098]

[0099] After predicting the service life of the replacement parts, the number of spare parts that are about to break is counted, and this number becomes the company's spare parts demand for the next phase. However, since model-based predictions are subject to certain errors, this invention uses fuzzy random modeling of spare parts demand to determine the company's optimal order quantity for each batch, allowing the company to maintain normal production while reducing costs.

[0100] First, the machine tool spare parts whose remaining service life is less than a preset time are determined to be spare parts to be replaced, and the fuzzy demand for the spare parts to be replaced is determined. The fuzzy demand is the number of spare parts to be replaced.

[0101] Then, the fuzzy demand quantity is stochastically modeled, and the fuzzy constraint conditions of the spare parts to be replaced are determined based on the fuzzy evaluation model obtained after stochastic modeling. Figure 2 The fuzzy set diagrams of different types of uncertain demands are shown, which are triangular random fuzzy numbers and trapezoidal random fuzzy numbers For any x∈U, there is a number μ(x)∈[0,1] corresponding to it. μ(x) is called the degree of membership of x to U, and μ is called the membership function of x, which is also a fuzzy number. Considering the prediction success rate, this application uses triangular fuzzy numbers for random modeling. The membership function expression of the fuzzy evaluation model obtained after modeling is as follows:

[0102]

[0103] The objective function is to minimize the spare parts inventory cost:

[0104]

[0105]

[0106] Among them, D i is the demand of the enterprise in period i, T is the ordering cycle of spare parts, u i is the order price in period i, x i is the order quantity of period i. To ensure the calculation efficiency, let 0≤x i ≤M, M is a large positive real number, v i is the unit inventory cost in period i, s i is the remaining spare parts quantity at the end of period i.

[0107] Fuzzy number D=[d a ,d b ,d c ] is μ D (x), the fuzzy constraint conditions are solved according to the fuzzy number theorem. The solution is as follows:

[0108] si-1 +x i -s i ≥(1-θ)d a +θd b (12)

[0109] s i-1 +x i -s i ≥(1-θ)d c +θd b (13)

[0110] Then, according to the fuzzy constraints obtained above, substitute them into the objective function to determine the target cost model of the spare parts to be replaced:

[0111]

[0112]

[0113] After the target cost model is established, the order unit price and unit inventory cost of the spare parts to be replaced are obtained. Then, through the target cost model, the actual demand for the spare parts to be replaced is obtained based on the order unit price, unit inventory cost and fuzzy demand.

[0114] In one embodiment, after determining the demand for each machine tool spare part during different replacement cycles, the remaining service life of the replacement parts is used to identify the spare parts to be stored from the replacement parts. A storage request is generated containing the information about the replacement parts to be stored. The information about the replacement parts to be stored includes the spare part identifier. After determining the spare part identifier, the spare part identifier is used to determine whether a location matching the spare part identifier exists within the current spare parts warehouse. If so, the replacement part can be directly stored in that location. If not, it is determined that there is no suitable location for the replacement part to be stored. To reduce replacement costs, the spare part association network can be used to determine the multiple nodes where the replacement parts to be stored are located, as well as the categories of other nodes connected by the edges associated with these multiple nodes. Based on the number of edges connected to other nodes in different categories, the node with the largest number of connected edges is determined to be the spare part with the strongest association with the replacement part to be stored. Based on the location of the replacement part, the replacement location for the replacement part to be stored is determined, further reducing storage costs.

[0115] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this application embodiment also provides an industrial Internet machine tool spare parts monitoring device, whose structure is as follows Figure 3 shown.

[0116] Figure 3 This is a schematic diagram of the structure of a machine tool spare parts monitoring device for the industrial Internet provided in an embodiment of the present application. Figure 3 As shown, the equipment includes:

[0117] at least one processor 301;

[0118] and a memory 302 communicatively connected to the at least one processor 301;

[0119] The memory 302 stores instructions that can be executed by at least one processor 301. The instructions are executed by the at least one processor 301 to enable the at least one processor 301 to:

[0120] Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data;

[0121] Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part;

[0122] determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level;

[0123] Obtain historical machine tool spare parts corresponding to the designated machine tool spare parts, and determine the similarity between the designated machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the machine tool spare parts based on the similarity; the historical machine tool spare parts and the designated machine tool spare parts have the same spare parts type and operating conditions.

[0124] An embodiment of the present application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0125] Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data;

[0126] Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part;

[0127] determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level;

[0128] Obtain historical machine tool spare parts corresponding to the designated machine tool spare parts, and determine the similarity between the designated machine tool spare parts and the historical machine tool spare parts, so as to predict the remaining service life of the machine tool spare parts based on the similarity; the historical machine tool spare parts and the designated machine tool spare parts have the same spare parts type and operating conditions.

[0129] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0130] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0131] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0136] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0139] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A machine tool spare parts monitoring method based on the Industrial Internet, characterized in that: The method comprises: Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data; Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part; determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level; Obtaining historical machine tool spare parts corresponding to the designated machine tool spare part, and determining a similarity between the designated machine tool spare part and the historical machine tool spare parts, so as to predict the remaining useful life of the designated machine tool spare part based on the similarity; the historical machine tool spare parts and the designated machine tool spare part have the same spare part type and operating condition; Before determining the defect growth level of the machine tool spare part according to the status diagnosis information, the method further includes: Determine a spare parts association network corresponding to each machine tool spare part, wherein a node of the spare parts association network represents a fault event corresponding to the machine tool spare part, an edge represents an association relationship between the fault events, the weight of the edge represents a degree of association between the fault events, and the direction of the edge represents an event impact relationship of the fault event; Determining a fault event corresponding to the machine tool spare part according to the status diagnosis information; Determining, based on the spare parts association network, associated fault events that can generate the event impact relationship on the fault event, and weights between the associated fault events and the fault event; determining a first fault level and a second fault level corresponding to the fault event and the associated fault event, respectively, and determining a corresponding first self-influence and a second self-influence according to the first fault level and the second fault level; the first fault level and the second fault level are positively correlated with the first self-influence and the second self-influence, respectively; The event impact of the associated fault event on the machine tool spare part is determined according to the product of the first self-influence, the second self-influence and the weight.

2. The method for monitoring machine tool spare parts based on the Industrial Internet according to claim 1, characterized in that: Reconstructing the feature space of the operating parameters to obtain operating sample data specifically includes: Generate an original time series corresponding to the operating parameters; Downsampling the original time series according to different time resolutions to obtain a feature sequence for characterizing the operating parameters; Reconstructing the feature space of the feature sequence to obtain a reconstructed feature sequence; The reconstructed feature sequence is clustered to generate clustered running sample data.

3. The method for monitoring machine tool spare parts based on the industrial Internet according to claim 1, characterized in that: After predicting the remaining service life of the machine tool spare part according to the similarity, the method further includes: Determine the machine tool spare part whose remaining service life is less than a preset service life as a spare part to be replaced, and determine the fuzzy demand quantity of the spare part to be replaced; Performing random modeling on the fuzzy demand quantity, and determining the fuzzy constraint conditions of the spare parts to be replaced based on a fuzzy evaluation model obtained after the random modeling; Determining a target cost model for the spare part to be replaced based on the fuzzy constraint conditions; The order unit price and unit inventory cost of the spare part to be replaced are obtained, and based on the target cost model, the actual demand quantity of the spare part to be replaced is obtained according to the order unit price, the unit inventory cost and the fuzzy demand quantity.

4. The method for monitoring machine tool spare parts based on the Industrial Internet according to claim 1, characterized in that: Determining the similarity between the designated machine tool spare part and the historical machine tool spare part, so as to predict the remaining service life of the machine tool spare part according to the similarity, specifically comprising: determining a current monitoring point of the machine tool spare part; Obtaining target operation sample data of the designated machine tool spare part within a preset evaluation interval before the current monitoring point, and historical sample data of the historical machine tool spare part within any preset evaluation interval; Calculating the similarity between the target running sample data and the historical sample data corresponding to the current monitoring point; Determining a monitoring weight corresponding to the historical machine tool spare part at the current monitoring point according to a ratio between the similarity of the historical machine tool spare part and the sum of the similarities of all historical machine tool spare parts; The actual remaining usage time of the historical machine tool spare part at the current monitoring point is determined, and the remaining usage time of the machine tool spare part is predicted based on the actual remaining usage time, the monitoring weight and the similarity.

5. The method for monitoring machine tool spare parts based on the industrial Internet according to claim 1, characterized in that: Determining the defect growth level of the machine tool spare part according to the status diagnosis information specifically includes: Determining whether a failure event occurs in the machine tool spare part according to the status diagnosis information; In the event that a fault event occurs on the machine tool spare part, taking the fault level corresponding to the fault event as the initial defect growth level of the machine tool spare part; The ratio between the target event impact degree corresponding to the machine tool spare part and the sum of the event impact degrees is used as the corresponding event impact coefficient; the target event impact degree is greater than a preset threshold; Performing coefficient compensation on the initial defect growth level according to the event impact coefficient to obtain a compensated defect growth level; In the case that no failure event occurs to the machine tool spare part, an event impact coefficient corresponding to the machine tool spare part is determined, and the defect growth level of the machine tool spare part is determined based on the event impact coefficient.

6. The method for monitoring machine tool spare parts based on the Industrial Internet according to claim 3, characterized in that: After obtaining the actual demand for the spare parts to be replaced, the method further includes: Determine the spare parts to be put into storage from the spare parts to be replaced according to the remaining service life of the spare parts to be replaced, and generate a storage request carrying information of the spare parts to be put into storage; the information of the spare parts to be put into storage includes a spare part identifier; Determine, based on the spare part identification, whether there is a storage location in the current spare parts warehouse that matches the spare part identification; If not, determining, based on the spare parts association network, the multiple nodes where the spare parts to be stored are located, and the categories of other nodes connected by the edges associated with the multiple nodes; The storage location of the spare part to be stored is determined according to the number of edges connected to other nodes in different categories.

7. The method for monitoring machine tool spare parts based on the Industrial Internet according to claim 2, characterized in that: Clustering the reconstructed feature sequence to generate clustered running sample data specifically includes: Determining the local density and distance deviation of the feature sequence, and determining the cluster center point according to the local density and the distance deviation; The non-cluster center points are clustered according to the cluster center points to obtain clustered running sample data.

8. A machine tool spare parts monitoring device based on the Industrial Internet, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data; Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part; determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level; Obtaining historical machine tool spare parts corresponding to the designated machine tool spare part, and determining a similarity between the designated machine tool spare part and the historical machine tool spare parts, so as to predict the remaining useful life of the machine tool spare part based on the similarity; the historical machine tool spare parts and the designated machine tool spare part have the same spare part type and operating condition; Before determining the defect growth level of the machine tool spare part according to the status diagnosis information, the method further includes: Determine a spare parts association network corresponding to each machine tool spare part, wherein a node of the spare parts association network represents a fault event corresponding to the machine tool spare part, an edge represents an association relationship between the fault events, the weight of the edge represents a degree of association between the fault events, and the direction of the edge represents an event impact relationship of the fault event; Determining a fault event corresponding to the machine tool spare part according to the status diagnosis information; Determining, based on the spare parts association network, associated fault events that can generate the event impact relationship on the fault event, and weights between the associated fault events and the fault event; determining a first fault level and a second fault level corresponding to the fault event and the associated fault event, respectively, and determining a corresponding first self-influence and a second self-influence according to the first fault level and the second fault level; the first fault level and the second fault level are positively correlated with the first self-influence and the second self-influence, respectively; The event impact of the associated fault event on the machine tool spare part is determined according to the product of the first self-influence, the second self-influence and the weight.

9. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Collecting operating parameters of machine tool spare parts, and reconstructing feature space of the operating parameters to obtain operating sample data; Performing status diagnosis on the operation sample data to obtain status diagnosis information of the machine tool spare part; determining, based on the status diagnosis information, a defect growth level of the machine tool spare parts, so as to determine, from the machine tool spare parts, a designated machine tool spare part having a defect growth level greater than a preset level; Obtaining historical machine tool spare parts corresponding to the designated machine tool spare part, and determining a similarity between the designated machine tool spare part and the historical machine tool spare parts, so as to predict the remaining useful life of the machine tool spare part based on the similarity; the historical machine tool spare parts and the designated machine tool spare part have the same spare part type and operating condition; Before determining the defect growth level of the machine tool spare part according to the status diagnosis information, the method further includes: Determine a spare parts association network corresponding to each machine tool spare part, wherein a node of the spare parts association network represents a fault event corresponding to the machine tool spare part, an edge represents an association relationship between the fault events, the weight of the edge represents a degree of association between the fault events, and the direction of the edge represents an event impact relationship of the fault event; Determining a fault event corresponding to the machine tool spare part according to the status diagnosis information; Determining, based on the spare parts association network, associated fault events that can generate the event impact relationship on the fault event, and weights between the associated fault events and the fault event; determining a first fault level and a second fault level corresponding to the fault event and the associated fault event, respectively, and determining a corresponding first self-influence and a second self-influence according to the first fault level and the second fault level; the first fault level and the second fault level are positively correlated with the first self-influence and the second self-influence, respectively; The event impact of the associated fault event on the machine tool spare part is determined according to the product of the first self-influence, the second self-influence and the weight.

Images