Tool efficiency enhancement via local monitoring communicated to remote and technical guidance

Abstract

A system for monitoring tool performance and providing remote analysis and efficiency guidance may include a tool controller, a plurality of power tools operably coupled to the tool controller to execute a respective tightening operation, a local tool data manager operably coupled to the tool controller and / or the power tools to manage extraction of tool sample data, and a remote tool data manager operably coupled to the local tool data manager to receive the tool sample data and process the tool sample data to generate an improvement recommendation for communication to the local tool data manager that, responsive to acceptance, initiates a change to an instruction for operation of one or more of the power tools with respect to the respective tightening operation. The remote tool data manager may employ an analytic engine including a machine learning module and / or an artificial intelligence module to generate the improvement recommendation.

Description

[0001] AttyDktNo: 717745-01043-P4259PCT01

[0002] TOOL EFFICIENCY ENHANCEMENT VIA LOCAL MONITORING COMMUNICATED

[0003] TO REMOTE AND TECHNICAL GUIDANCE

[0004] TECHNICAL FIELD

[0005] Example embodiments generally relate to employment of a system for the operation of power tools and, in particular, relate to such a system that can have components therein monitored locally and communicate monitoring data to remotely located robust processing resources that provide technical guidance for tool efficiency enhancement in a low cost and low impact environment.

[0006] BACKGROUND

[0007] Power tools are commonly used across all aspects of industry. Power tools are employed for multiple applications including, for example, drilling, tightening, sanding, and / or the like. Handheld power tools are often preferred, or even required, for jobs that require a high degree of freedom of movement or access to certain difficult to reach objects.

[0008] In some contexts, various operations are conducted by humans or machines using power tools as part of a comprehensive assembly process. For example, power tools may be employed to tighten fasteners at various locations along an assembly line for assembling vehicle or engine parts. These assembly processes may include tightening operations that must be performed in specific orders and / or to specific specifications. Invariably, when humans conduct these operations in a repetitive fashion, some tightening operations may be conducted that are not exactly to specification. To mitigate this otherwise quite natural phenomenon, tool controllers are often used to control various aspects of the operation of the power tools.

[0009] Although both the tools themselves and the tool controllers to which they are communicatively coupled may be monitored and connected to other resources that can determine when the tool is operated efficiently, the amounts of data that are needed to export from the tool (or tool controller) can be quite large. If you add to this, a further complication associated with connecting the tools and tool controllers to a local area network (LAN), which is that the LAN may have limited bandwidth or communication capabilities and / or different types of tools (and tool manufacturers) may each have special configuration requirements to permit communication with the LAN, it becomes very difficult to get a thorough picture of ground truth at the line on which the tools are operating itself, much less intercede to improve conditions in a timely fashion. Moreover, although it may be possible to address these issues AttyDktNo: 717745-01043-P4259PCT01 with highly capable networks and tools, doing so would typically involve a major expense and commitment of resources.

[0010] Example embodiments aim to leverage existing tool and software capabilities at the local level in order to determine a system improvement that can be implemented with relatively minimal investment, but can still efficiently extract tool performance data and robustly analyze the tool performance data to permit well informed recommendations to be generated for tool efficiency increases.

[0011] BRIEF SUMMARY OF SOME EXAMPLES

[0012] In an example embodiment, a system for monitoring tool performance and providing remote analysis and efficiency guidance may be provided. The system may include a tool controller, a plurality of power tools operably coupled to the tool controller to execute a respective tightening operation, a local tool data manager operably coupled to the tool controller and / or the power tools to manage extraction of tool sample data, and a remote tool data manager operably coupled to the local tool data manager to receive the tool sample data from the local tool data manager and process the tool sample data to generate an improvement recommendation for communication to the local tool data manager that, responsive to acceptance by the local tool data manager, initiates a change to an instruction for operation of one or more of the power tools with respect to the respective tightening operation. The remote tool data manager may employ an analytic engine including a machine learning module and / or an artificial intelligence module to generate the improvement recommendation.

[0013] BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWING(S)

[0014] Having thus described some example embodiments in general terms, reference will now be made to the accompanying drawings, which are not necessarily drawn to scale, and wherein:

[0015] FIG. 1 illustrates a functional block diagram of a system that may be useful in connection with providing a virtual field technician according to an example embodiment;

[0016] FIG. 2 illustrates a block diagram of a method of providing remote analysis and guidance based on sample tool data gathered locally according to an example embodiment;

[0017] FIG. 3 illustrates a block diagram of a battery and charger modified to improve sample tool data extraction in accordance with an example embodiment;

[0018] FIG. 4 illustrates a functional block diagram of the system of FIG. 1 augmented with a passive sniffing device in accordance with an example embodiment; and AttyDktNo: 717745-01043-P4259PCT01

[0019] FIG. 5 illustrates a block diagram of a passive sniffing device in accordance with an example embodiment;

[0020] FIG. 6 illustrates a block diagram of a context awareness engine in accordance with an example embodiment; and

[0021] FIG. 7 illustrates a block diagram of an analytic engine in accordance with an example embodiment.

[0022] DETAILED DESCRIPTION

[0023] Some example embodiments now will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all example embodiments are shown. Indeed, the examples described and pictured herein should not be construed as being limiting as to the scope, applicability or configuration of the present disclosure. Rather, these example embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like reference numerals refer to like elements throughout. Furthermore, as used herein, the term “or” is to be interpreted as a logical operator that results in true whenever one or more of its operands are true. As used herein, operable coupling should be understood to relate to direct or indirect connection that, in either case, enables functional interconnection of components that are operably coupled to each other.

[0024] As indicated above, typical power tool operation under the control of tool controllers in a comprehensive assembly line faces analytical and control limitations based on tool and network communication capacity, among other things. Some example embodiments may dramatically expand the ability of an enterprise to obtain useful tool operation information without making substantial investments in infrastructure. Instead, relatively inexpensive, easy and non-intrusive architectural and strategic modifications can be made that leverage heavily off of existing capabilities of power tools and the networks that they operate within. A power tool may therefore be employable on an assembly line such that the operations that are to be executed by the power tool can be executed under the control of a tool controller that is connected to a manufacturing execution system (MES). A local tool data manager may be instantiated at or in communication with the MES in order to non-obtrusively extract data from the power tool and tool controller with minimal change to the power tool itself or the tool controller. The local tool data manager may then also communicate with a remote tool data manager that can effectively act as a virtual field technician to leverage machine learning and / or artificial intelligence tools to provide recommendations for improving efficiency that may be AttyDktNo: 717745-01043-P4259PCT01 communicated back to operators at the local tool data manager or to the tools or tool controllers themselves.

[0025] The ways to non-obtrusively extract data may vary, but may be aimed at minimizing the cost and complexity of enabling power tools and / or tool controllers to provide useful data to the local and remote data tool managers. Those ways, and multiple ways are described herein, are therefore one interesting aspect of example embodiments. However, the interactions with the local and remote tool data managers including the information exchanged, how it is exchanged, and the improved analytics employed in connection with that exchange, are additional interesting aspects of example embodiments. These aspects will now be described in connection with the figures of which FIG. 1 provides a diagram of a general system architecture of an example embodiment.

[0026] Referring now to FIG. 1, a manufacturing location 100 is shown to include multiple assembly lines. In this regard, the manufacturing location 100 is shown to include a first assembly line 110, which includes a first set of multiple respective instances of a power tool 112 that are each powered in this example by a battery 114. The first set of multiple instances of the power tool 112 are also each operably coupled to a first tool controller 116. The manufacturing location also includes a second assembly line 120, which includes a second set of multiple respective instances of the power tool 112 (also powered by respective instances of the battery 114) that are each operably coupled to a second tool controller 126. The first and second tool controllers 116 and 126 are then operably coupled to a local tool data manager 130 of an MES 140. The local tool data manager 130 may also include or be operably coupled to a local data repository 150 (e.g., a non-transitory memory device).

[0027] In an example embodiment, the local tool data manager 130 may include a user interface for a local operator (or manager) to provide tool control instructions that may be pushed to tool controllers and / or power tools. In some cases, the tool control instructions may be provided in the form of applications that may be stored at the local data repository 150 or at a memory device of the local tool data manager 130. In some cases, a relatively large number of different applications may be stored for each power tool 112 or tool controller (116 / 126). The applications may be the same or different for power tools 112 that are associated with the first and second tool controllers 116 and 126. The applications may be tightening applications that, for example, provide instructions for performance of a tightening operation. In some cases, the tightening applications may define a specific torque (e.g., within a range between high and low limits), a specific angle (e.g., within a range of torques), a specific speed, or AttyDktNo: 717745-01043-P4259PCT01 various other parameters that may be specific to a given material, location, joint, fastener, or the like. Multiple steps may be defined in some cases.

[0028] Notably, although the power tool 112 is powered by the battery 114 in the example of FIG. 1, it is also possible for each instance of the power tool 112 to instead be powered via a wired connection to an electrical power source, or to be powered by hydraulic, pneumatic, or other non-electrical power sources. Furthermore, although only the first and second assembly lines 110 and 120 are shown in FIG. 1, and each includes three instances of the power tool 112, it should be appreciated that more or fewer instances of the power tool 112 may be included in each of the assembly lines, and more or fewer assembly lines may be included at the manufacturing location 100. Thus, the numbers shown in FIG. 1 are merely selected to illustrate the potential for multiplicity.

[0029] The first and second tool controllers 116 and 126 of FIG. 1 are also shown in communication with their respective instances of the power tool 112 and with the local tool data manager 130. That communication, in each respective instance, may be understood to be either wired or wireless. Thus, for example, the first and second tool controllers 116 and 126 may be operably coupled to the local tool data manager 130 via either a wired or wireless connection, and the first and second tool controllers 116 and 126 may be operably coupled to the respective instances of the power tool 112 on each of the first assembly line 110 and the second assembly line 120, respectively, via either wired or wireless connection. Various communication protocols may be employed to define the operable coupling, and the communication hardware, software, and protocols may define a local area network (LAN) that may exist at the manufacturing location 100.

[0030] The LAN at the manufacturing location 100 (which sometimes may be one of multiple LANs) may provide a communication platform, e.g., a common communication platform, for a set of local devices at the manufacturing location 100. In some cases, the MES 140 and the local tool data manager 130 may be operably coupled to all of the instances of the power tool 112 via the LAN, to enable the local tool data manager 130 to extract various tool parameters and other tool sample data from the power tool 112. However, the MES 140 and the local tool data manager 130 may in turn also be in communication with remote devices via a wide area network (WAN) such as the Internet. In this regard, a remote tool data manager 160 may be operably coupled to the local tool data manager 130 via the WAN or via other communication links (e.g., 5G cellular links). FIG. 1 shows communication links 162 to and from the remote tool data manager 160, and it should be understood that the communication links 162 may be wired or wireless. AttyDktNo: 717745-01043-P4259PCT01

[0031] The remote tool data manager 160 may include an analytic engine 170, which may include or otherwise be operably coupled to a remote data repository 180 (e.g., a non-transitory memory device). The local tool data repository 150 may store (e.g., buffer) tool sample data prior to communication of the tool sample data to the analytic engine 170 and / or the remote data repository 180. The analytic engine 170 may analyze the tool sample data using machine learning and / or artificial intelligence tools, which will be described in greater detail below, in order to generate a recommendation for improving efficiency, safety, or other operational considerations with respect to operation of one or more instances of the power tool 112. In some cases, the recommendation may be provided to an operator at the local tool data manager 130, and the operator may either accept or reject the recommendation. If accepted, a corresponding operational instruction generated based on the recommendation may be pushed to the one or more instances of the power tool 112 (e.g., via a respective one of the first and second tool controllers 116 and 126). If declined, then no further action may be taken at any instance of the power tool 112.

[0032] FIG. 2 illustrates a block diagram showing a method of improving tool efficiency in accordance with an example embodiment. In this regard, to address these issues, tool sample data may initially be collected from the tools themselves at operation 200. The ways this collection can occur may vary, and some different ways will be discussed in greater detail below. Thereafter, the tool sample data may be locally stored (e.g., at the local data repository 150) at operation 210. Tool sample data may thereafter at some point, which may vary, be relayed to a remote or cloud database (e.g., the remote data repository 180) at operation 220. The relayed tool sample data may then be processed by the analytic engine 170 at operation 230. The analytic engine 170 may determine a tool efficiency recommendation (or any other tool operation recommendation) and communicate the recommendation to a local authority (e.g., an operator at the local tool data manager 130) at operation 240. A determination may be made at operation 250 as to whether or not the local authority accepts the recommendation or authorizes adoption of the recommendation. If not authorized, the process simply ends at operation 260. However, if the recommendation is authorized or accepted, then a tool efficiency update or instruction may be pushed or otherwise communicated to the tool (e.g., power tool 112) at operation 270.

[0033] As noted above, one of the interesting aspects of example embodiments may be the way in which the tool sample data is extracted from the respective instances of the power tool 112 and provided to the local tool data manager 130, which is the focus of operations 200, 210 and 220 from FIG. 2. In this regard, for example, real-time data such as a torque trace (or other AttyDktNo: 717745-01043-P4259PCT01 tool generated data) may embody the tool sample data. Torque traces are known to have the potential to be extremely data intensive. Thus, for example, a data file including torque traces may be large and consume a significant amount of bandwidth of the LAN, or even exceed the capabilities of the LAN to transfer in some cases. Meanwhile, the torque traces may be essential for troubleshooting and / or optimizing operation of the power tool 112. Defining a wired LAN, like Ethernet, may require costly and cumbersome cabling work to be performed, and may also complicate any needed or desired future changes. If instead, a wireless LAN is used, network congestion and connectivity issues may complicate operations and reduce effectiveness. Wireless communications may also be slower than wired connections, which may further limit the volume of data that can be transmitted by the multiple instances of the power tool 112.

[0034] To avoid the complications of using bandwidth limited, or expensive hardwired channels for obtaining and communicating the tool sample data, the battery 114 of the power tool 112 may be used. In this regard, for example, an architecture such as that shown in FIG. 3 may be established and, with relatively little investment and modification to the battery 114, a simple, inexpensive, easy to implement and operate way of storing, transferring and thereafter communicating the tool sample data all the way to the analytic engine 170 may be provided.

[0035] Referring now to FIG. 3, some of the components of the power tool 112, the battery 114 and a battery charging device (e.g., charger 300) are described in accordance with an example embodiment. In this regard, the power tool 112 may include a casing / handle 310 and / or other body portions that form a structural base for the power tool 112. The power tool 112 may also include an end effector 312 that includes the mechanical interface for performing the desired and designed work of the power tool 112. Thus, for example, the end effector 312 may include an interface for fastening, drilling, tightening, and / or the like. The end effector 312 may be operably coupled to a motor 313 (e.g., an electric motor) via a drive train 314. The motor 313 may be powered by the battery 112, when the battery 112 is operably coupled to the power tool 112.

[0036] In some cases, a tool sensor suite 316 may be included in the power tool 112 to monitor operation of the motor 313 and / or various other aspects of the operation of the power tool 112 using any of a number of possible sensors in number from as little as one to a multitude for various different examples of the power tool 112. The tool sensor suite 316 may, for example, measure current draw by the motor, voltage of the battery 114, and / or any of the other characteristic parameters of the power tool 112 that may be measured. In some cases, the tool sensor suite 316 may gather the tool sample data in the form of parametric measurements that AttyDktNo: 717745-01043-P4259PCT01 may include, for example, torque information that may form a torque trace. The tool sample data may be obtained directly or indirectly from the respective components being measured / monitored. However, in some cases, the tool sample data may be obtained, and / or communicated after being obtained, via a tool communication bus 318, which may operably couple the battery 114, tool electronics 320, the tool sensor suite 316 and / or the motor 313 within the power tool 112.

[0037] The tool communication bus 318 may be relatively complex in some cases, forming an internal communication network within the power tool 112 for the communication of electrical power, tool sample data and / or control instructions for operation of the power tool 112, or more specifically the motor 313. Thus, for example, the tool communication bus 318 may include one or multiple wires that form a backbone of the internal communication network, which could also or alternatively employ wireless communication for all or some portions of the communications supported.

[0038] When used to communicate instructions associated with operation of the power tool 112, the tool electronics 320 may include a tool memory 322 for storing the instructions and a processor 324 for executing such instructions to control the motor 313 or perform various other control and / or monitoring activities on the power tool 112. The tool memory 322 may also be used to store the tool sample data locally at the power tool 112. In some cases, the tool sample data may be stored temporarily at the power tool 112 until either removed or transferred to another device, or may be replaced by newer data if a certain limit is reached (e.g., a circular buffer).

[0039] When the battery 114 is operably coupled to the power tool 112, the battery 114 may provide power for the motor 313 (e.g., under control of the tool electronics 320) and other electronics within the tool. The tool sensor suite 316 may be used to monitor battery life remaining on the battery 114, ambient operating temperature and / or various other aspects of the performance of the power tool 112 and / or battery 114. In response to the battery life remaining reaching a threshold, an indication may be provided to the operator (and / or the tool controller 126) to indicate that the battery 114 should be recharged (e.g., via a user interface module of the power tool 112 that displays on-tool indications). The battery 114 may then be removed from operable coupling with the power tool 112 and instead operably coupled to the charger 300, which may be located conveniently at some place nearby the first and second assembly lines 110 and 120. Although in some cases, the charger 300 may only charge one instance of the battery 114 at any given time, it is possible and even common for the charger 300 to include multiple charge ports capable of receiving multiple instances of the battery 114 AttyDktNo: 717745-01043-P4259PCT01 in order to charge the multiple instances of the battery 114. When capable of interfacing with multiple instances of the battery 114, the charger 300 may be configured to charge the batteries 114 either in parallel or in series, depending on the architecture of the charger 300. However, in some cases, the charger 300 may actually select between parallel and series charging based on whichever manner is deemed efficient under prevailing circumstances.

[0040] Of note, the power tool 112 may include more components than those shown in FIG. 3 in some cases. Moreover, in some embodiments, the components of the power tool 112 may be provided in separate modules either alone or in combination with one another so that the power tool 112 may be said to be “modular” in that various modules may be operably coupled with each other to define a fully operational instance of the power tool 112. When modular, different modules may have different characteristics or specifications so that, for example, different tool characteristics may be defined based on the selection of individual modules. The charger 300 may also be modular in some cases. In other words, for both the charger 300 and the power tool 112, different sensors, communication interfaces, and other aspects can be easily swapped out for more modern or application-specific options by swapping out modules.

[0041] The charger 300 may also include a casing 340 that forms the base structure of the charger 300 including defining the number of charge ports included at the charger 300. The charger 300 may also include a charger sensor suite 342 including one or more sensors for measuring / detecting various aspects of the performance of the charger 300 and / or the state of charge of the battery 114 being charged thereat. The charger sensor suite 342 may include electrical parameter sensors (e.g., voltage and / or current sensors) that directly measure state of charge and / or the delivery of power to the battery 114 during charging operations. However, since battery charging is necessarily also typically a heat-producing event, the charger sensor suite 342 may also include temperature sensors or any other sensors deemed useful for monitoring the performance of the charger 300 to ensure safety and / or efficiency with respect to charging operations.

[0042] Although not required, in some cases, the charger 300 may also include a communication bus 344, which may define an internal communication network for the various components of the charger 300. Thus, for example, the communication bus 344 may include one or multiple wires that operably couple the various components of the charger 300 to one another, and, like the tool communication bus 318, may also or alternatively employ wireless communication for some of the internal communications that are facilitated by the communication bus 344. In some cases, the communication bus 344 may operably couple the charger sensor suite 342 to charger electronics 350, which may be provided to monitor and / or AttyDktNo: 717745-01043-P4259PCT01 control charging processes to ensure safety and / or efficiency with respect to the charging processes being monitored. The charger electronics 350 may include a charger memory 352 for storing charging data and / or instructions for controlling operation of the charger 300. The charger electronics may also include a processor 354, which may act as an executor of the instructions for controlling operation of the charger 300.

[0043] In some embodiments, the charger 300 may also include a communications unit 360 configured to communicate data (e.g., tool sample data and / or charging data) to devices external to the charger 300. Thus, for example, the communications unit 360 may communicate with the local and / or remote tool data manager 130 / 160 in order to provide information from the charger 300 to the respective one of the local and / or remote tool data manager 130 / 160. In such cases, the communications unit 360 may operate under control of the processor 354 or the communications unit 360 may have its own, separate instance of a processor to control its operations.

[0044] In order to get tool sample data to the charger 300 for communication from the communications unit 360 to the local and / or remote tool data manager 130 / 160, the battery 114 may be used as the transport vehicle for the tool sample data. In this regard, for example, the battery 114 may include a battery memory 370, which may temporarily store the tool sample data to facilitate transfer from the power tool 112 to the charger 300. Although not required, the battery 114 may also include a processor 372, which may be configured to manage the transfer of the tool sample data from the tool memory 322 (or directly from the tool sensor suite 316 via the tool communications bus 318) to the battery memory 370. The processor 372 may then also be configured to manage the transfer of the tool sample data from the battery memory 370 to the charger memory 352 of the charger 300 (e.g., before the tool sample data is communicated off the charger 300 by the communications unit 360.

[0045] In this regard, for example, the processor 372 of the battery 114 may include instructions (e.g., stored also in the battery memory 370) that enable the processor 372 to communicate with the tool sensor suite 316, the tool electronics 320, the processor 324 and / or the tool memory 322 of the power tool 112 in order to extract the tool sample data. The instructions may therefore include information about the communication protocol of the power tool 112 (e.g., to enable interface with the tool memory 322 and / or the tool communications bus 318). The instructions may also include guidance as to the amount of the tool sample data to be transferred, the cadence pace of transfer, the means of transfer, the form of the tool sample data (e.g., compressed or uncompressed, native formatting or reformatted in a particular form, encrypted or unencrypted, etc.). In some embodiments, the instructions may also include AttyDktNo: 717745-01043-P4259PCT01 guidance information about the communication protocol of the charger 300 to enable interface with the charger memory 352 to transfer the tool sample data originally received at the battery memory 370 from the tool memory 322 onto the charger memory 352.

[0046] Thus, in some cases, the battery 114, the power tool 112, and the charger 300 may each have their own respective instances of a processor and memory, and the processors of the three devices may cooperate to transfer tool sample data from the power tool 112 to the charger 300 via the battery 114 and the respective memory devices associated with each processor. However, in some cases, the battery 114 may be provided without the processor 372 (e.g., to reduce cost and / or complexity). In such cases, the processor 324 of the power tool 112 may include instructions for transferring the tool sample data (e.g., torque trace information or other data) from the tool memory 322 or directly from the tool sensor suite 316 to the battery memory 370. The processor 324 may also, for example, include instructions to define the amount of the tool sample data to be transferred, the cadence or pace of transfer, the means of transfer, the form of the tool sample data (e.g., compressed or uncompressed, native formatting or reformatted in a particular form, encrypted or unencrypted, etc.) and thereby also control the formatting of the tool sample data stored at the battery memory 370. The processor 324 may also provide instructions or signaling for use after the battery 114 is taken out of communication with the power tool 112 and operably coupled to the charger 300 to direct the tool sample data to be extracted from the battery memory 370. As noted above, the tool sample data may be loaded onto the charger memory 352. However, in some embodiments, the tool sample data may be provided (e.g., via the communications bus 344) directly to the communications unit 360 for provision to the local and / or remote tool data manager 130 / 160. In still other example embodiments, the tool sample data may be transferred from the battery memory 370 to a removable memory 380 (e.g., a thumb drive or the like), and the removable memory 380 may thereafter be manually carried and placed into communication with the local and / or remote tool data manager 130 / 160. However, in some cases, the removable memory 380 may itself be configured for wireless communication directly with the local and / or remote tool data manager 130 / 160 (e.g., via WiFi and / or 5G communication protocols).

[0047] Notably, whereas the preceding example utilized the processor 324 of the power tool 112 as the main coordinator or controller of the transfer of the tool sample data, that role could alternatively be taken by the processor 354 of the charger 300. Moreover, the processor 354 of the charger 300 and the processor 324 of the power tool 112 may also cooperate (i.e., without any processor assistance on the battery 114) to manage the transfer of the tool sample data (or AttyDktNo: 717745-01043-P4259PCT01 any other information) from the power tool 112 to the charger 300 via the battery 114, and more particularly via the battery memory 370.

[0048] The communications unit 360 may be a communications interface that merely employs proper communication protocols associated with the LAN of the manufacturing location 100, thereby employing proprietary or more familiar publicly available wireless (or wired) communication protocols. However, in some cases, in order to avoid loading down the LAN or otherwise utilizing resources of the MES, the communication unit 360 may employ cellular communication resources (e.g., 5G and / or LTE wireless communication devices) for providing the tool sample data from the charger 300 (after transfer thereto) to the remote tool data manager 160. This approach may alleviate concerns from security in IT teams at the manufacturing location 100 by avoiding use of local resources. This approach may also greatly simplify initial system setup and provide for reliable communication in mobile contexts as well without placing any requirements on customer-operated networks or equipment.

[0049] As can be appreciated from the description above, the battery 114 may be a reliable and low cost transfer vehicle for moving the tool sample data from the power tool 112 to the analytic engine 160. Moreover, the battery 114 may provide great flexibility with respect to specifically how the tool sample data is extracted and ultimately communicated to the analytic engine without any major modifications to network infrastructure at the manufacturing location 100. Instead, the battery 114 is simply upgraded into what is effectively a smart battery with the addition of the battery memory 370 (and perhaps also the processor 372). Whereas using the battery 114 as a transport mechanism to take tool sample data from the power tool 112 to the analytic engine 170 may minimize other changes to network infrastructure of the manufacturing location 100, doing so does require a multiplicity of changes in that multiple batteries may need to have memory devices installed therein. Accordingly, in some cases, alternative means to take tool sample data from the power tool 112 to the analytic engine 170 that are more centralized may be desired.

[0050] FIG. 4 illustrates an example embodiment with a more centralized, yet still relatively simple and low cost modification, may be used to take tool sample data from the power tool 112 to the analytic engine 170. In this regard, the example of FIG. 4 is substantially identical to the example of FIG. 1 except that a passive sniffing device (PSD) 400 is included in the system. The PSD 400 of this example is provided on the LAN 410 that connects the first and second tool controllers 116 and 126, along with their respective instances of the power tool 112. The LAN 410 in this situation may be understood to be a tool control network (e.g., under control of the local tool data manager 130 or a similar control device) via which control AttyDktNo: 717745-01043-P4259PCT01 instructions, communications, signaling, messages and / or data is shared between instances of the power tool 112, tool controllers (e.g., the first and second tool controllers 116 and 126) and the local tool data manager 130. The PSD 400 may be configured to monitor communications, signaling and other data traffic on the tool control network (e.g., TorqueNet, ToolsNet, or the like) and extract information passively, which can be used to determine tool sample data such as torque traces and / or the like. The PSD 400 may then communicate the tool sample data to the analytic engine 170 either directly or indirectly. For indirect transmission, the PSD 400 may use the LAN 410 connection to the local tool data manager 130, and thereafter the communication links 162 to provide the tool sample data to the analytic engine 170 (and more generally to the remote tool data manager 160).

[0051] FIG. 5 illustrates a block diagram of the PSD 400 according to an example embodiment. In this regard, the PSD 400 may include a torque trace sniffer 500. The torque trace sniffer 500 may be configured (e.g., via processing circuitry 510 that controls or embodies the torque trace sniffer 500) to passively monitor tool control network communications to extract, relay or otherwise communicate any information that appears to be related to torque traces or other useful data to the remote tool data manager 160, either directly or via the local tool data manager 130. Thus, the processing circuitry 510 should be understood to be configurable to perform actions in accordance with example embodiments described herein. As such, for example, at least some of the functions attributable to the torque trace sniffer 500 (or the PSD 400 more generally) may be carried out by or otherwise instructed by the processing circuitry 510. The processing circuitry 510 may provide the hardware that is programmed or that hosts software to configure the system for enabling torque trace identification, extraction, relaying and / or communication consistent with example embodiments. In this regard, both the identification of the information on the tool control network that appears to be related to torque traces, and the communication of that information on to the remote tool data manager 160 may therefore be accomplished using the processing circuitry 510.

[0052] The processing circuitry 510 may be configured to perform data processing, control function execution and / or other processing and management services according to an example embodiment of the present invention. In some embodiments, the processing circuitry 510 may be embodied as a chip or chip set. In other words, the processing circuitry 510 may comprise one or more physical packages (e.g., chips) including materials, components and / or wires on a structural assembly (e.g., a baseboard). In an example embodiment, the processing circuitry 510 may include one or more instances of a processor 512 and memory 514 that may be in communication with or otherwise control the torque trace sniffer 500, a communication AttyDktNo: 717745-01043-P4259PCT01 interface 520, and in some cases also an encryption handler 530. As such, the processing circuitry 510 may be embodied as a circuit chip (e.g., an integrated circuit chip) configured (e.g., with hardware, software or a combination of hardware and software) to perform operations described herein.

[0053] The communication interface 520 may include one or more interface mechanisms for enabling communication with the various internal and / or external devices of the PSD 400, the tool control network, the LAN 410, and / or the local and remote tool data managers 130 and 160. Thus, for example, the communication interface 520 may handle routing of communications within the PSD 400 and various other devices (e.g., tool controllers 116 / 126, local and remote tool data managers 130 and 160, etc.) within the tool control network and / or the LAN 410. In some cases, the communication interface 520 may be any means such as a device or circuitry embodied in either hardware, or a combination of hardware and software that is configured to receive and / or transmit data from / to devices in communication with the processing circuitry 510. In some cases, the communication interface 520 may include one or more ports for external component connectivity and / or communication (e.g., Ethernet or wireless communications, and / or the like). Standard ports such as USB, other data ports, or power cable ports may be provided. However, in some cases, the ports may be for proprietary connectivity mechanisms. In some embodiments, the communication interface 520 may include antennas, radio equipment and / or the like to enable the PSD 400 to interface with other components or devices wirelessly (e.g., via 5G cellular communication to avoid using network resources). In this regard, similar to the discussion above, the communication interface 520 may use cellular networks to directly report tool sample data to the remote tool data manager 160 in order to avoid using local communication resources, or bogging down local networks. Otherwise, wired communication, or combinations of wired and wireless communication, may be employed in other example embodiments.

[0054] In an exemplary embodiment, the memory 514 may include one or more non-transitory memory devices such as, for example, volatile and / or non-volatile memory that may be either fixed or removable. The memory 514 may be configured to store information, data, applications, instructions or the like for enabling the PSD 400 to carry out various functions in accordance with exemplary embodiments of the present invention. For example, the memory 514 could be configured to buffer input data for processing by the processor 512. Additionally or alternatively, the memory 514 could be configured to store instructions for execution by the processor 512. As yet another alternative, the memory 514 may include one or more databases that may store a variety of data sets indicative of tool sample data for comparison to data AttyDktNo: 717745-01043-P4259PCT01 detected on the tool control network to determine a likelihood as to whether the data being compared is tool sample data (e.g., torque trace data) or other useful data. Thus, in some cases, the memory 514 may store information associated with patterns, feature vectors, histograms, processing algorithms and / or the like to be employed for inclusion in the PSD as applications associated with the execution of example embodiments by virtue of detecting tool sample data. Among the contents of the memory 514, applications may be stored for execution by the processor 512 in order to carry out the functionality associated with each respective application. In some cases, the applications may include directions for identifying tool sample data (e.g., torque trace data) and relaying of the tool sample date identified on eventually to the remote tool data manager 160, as described herein.

[0055] The processor 512 may be embodied in a number of different ways. For example, the processor 512 may be embodied as various processing means such as one or more of a microprocessor or other processing element, a coprocessor, a controller or various other computing or processing devices including integrated circuits such as, for example, an ASIC (application specific integrated circuit), an FPGA (field programmable gate array), or the like. In an example embodiment, the processor 512 may be configured to execute instructions stored in the memory 514 or otherwise accessible to the processor 512. As such, whether configured by hardware or by a combination of hardware and software, the processor 512 may represent an entity (e.g., physically embodied in circuitry - in the form of processing circuitry 510) capable of performing operations according to embodiments of the present invention while configured accordingly. Thus, for example, when the processor 512 is embodied as an ASIC, FPGA or the like, the processor 512 may be specifically configured hardware for conducting the operations described herein. Alternatively, as another example, when the processor 512 is embodied as an executor of software instructions, the instructions may specifically configure the processor 512 to perform the operations described herein.

[0056] In an example embodiment, the torque trace sniffer 500 may therefore be any means such as a device or circuitry embodied in either hardware, or a combination of hardware and software that is configured to perform the corresponding functions of the PSD 400 as described herein under the control of the processing circuitry 510. In an example embodiment, the torque trace sniffer 500 may be configured to collect unencrypted data transmitted by the power tools 112 and / or the tool controllers (116 / 126) and act as a pass through device for such unencrypted data to route the unencrypted data to the remote tool data manager 160 (e.g., directly or indirectly) for analysis and recommendation generation as described in greater detail below. In some cases, any data identified as torque trace data (or other tool sample data) may be stored AttyDktNo: 717745-01043-P4259PCT01 locally (e.g., at the memory 514, or at the local data repository 150) for later communication (e.g., asynchronously) to the remote tool data manager 160 for analysis and recommendation generation. However, in other cases, the communication interface 520 may enable real time communication (e.g., synchronously) of the torque trace data (or other tool sample data) to the remote tool data manager 160 (directly or indirectly) without intermediate storage.

[0057] In some embodiments, the extraction of unencrypted data may be associated specifically with power tools of one perhaps known or affiliated tool manufacturer, where the specific signature of tool trace data can be recognized. However, since some workplaces may have tools from multiple manufacturers, and some of the other manufacturers may have encrypted (or at least not easily recognizable) message formats or data communication protocols, the PSD 400 of some example embodiments may include the encryption handler 530 to attempt to extract proprietary or encrypted data that may be related to tool sample data. In this regard, for example, the encryption handler 530 (if employed) may include machine learning and / or artificial intelligence tools that find patterns in data, including encrypted data, to suggest that such data may be associated with torque traces or other useful tool sample data. For example, file size, headers, preambles, or other key symbols or data patterns may be identifiable as being associated with torque traces. If identified as potentially being associated with tool sample data, the encryption handler 530 may either attempt decryption locally, or pass the information (e.g., still encrypted) on to the analytic engine 170 for further processing and decryption efforts. To the extent decryption is successful, any tool sample data that is decrypted may then be processed by the analytic engine 170 as described in greater detail below.

[0058] The remote tool data manager 160 may utilize the remote data repository 180 to store tool sample data that is received (from any source, e.g., the PSD 400, the local tool data manager 130, or the Internet) for use in analytic operations of the analytic engine 170. These analytic operations may be focused on throughput improvements. In this regard, for typical manufacturing environments, where throughput is a critical metric, manufacturers have a clear incentive to perform continuous monitoring of performance to attempt to improve safety and efficiency. Tool efficiency significantly impacts overall throughput, and any downtime caused by tool inefficiencies may result in lost profit or opportunity.

[0059] Historically, tools used in manufacturing environments have lacked an awareness of their operating environment and how they are used in context. Thus, tool manufacturers have typically aimed efforts to optimize tool performance primarily on the collection of data directly from tools or from data provided by operators. This can limit the tool’s ability to dynamically AttyDktNo: 717745-01043-P4259PCT01 adapt its performance to account for various factors that could increase productivity and enhance overall performance of the tool, as well as the overall manufacturing operations at the site where it's used. Thus, it may be desirable to provide an ability to understand tool context either at the tool itself, or at a controller of the tool. To provide such contextual understanding, some example embodiments may provide a context awareness engine 600, which may be located at or in communication with either or both of the local and remote tool data managers 130 and 160. Moreover, in some cases, the context awareness engine may be part of or in communication with the analytic engine 170 to leverage capabilities of the analytic engine 170 to analyze data and improve tool operating efficiencies.

[0060] In some example embodiments, the context awareness engine 600 may be configured to combine data collected from power tools and external data sources in order to provide a more comprehensive understanding of tasks being performed by the power tools, and the context in which those tasks are being performed in order to identify opportunities to increase efficiency. Thus, the operations of the context awareness engine 600 may enable the provision of a context awareness efficiency feature that may integrate internal and external data to gain deeper understandings of how to optimize tool performance, aiming to increase throughput across entire manufacturing processes and not just single steps within the processes. The context awareness engine 600 of some example embodiments may be configured to communicate (directly or indirectly) with the power tools 112 in order to reconfigure them in real-time or near real-time, thereby enabling a dynamic response to current conditions instead of relying on predefined configurations that are static, or only changeable at discrete intervals. This type of dynamic response and adaptability may reduce (or minimize) tool and manufacturing process downtime and may therefore significantly enhance overall efficiency.

[0061] FIG. 6 illustrates a block diagram of the context awareness engine 600 of an example embodiment. As noted above, the context awareness engine 600 may be instantiated or located at or in communication with the analytic engine 170 in some cases (and therefore more generally at the remote tool data manager 160. However, in other examples, the context awareness engine 600 may be at or in communication with the local tool data manager 130.

[0062] Turning to FIG. 6, the context awareness engine 600 may include processing circuitry 610 that is configurable to perform actions in accordance with example embodiments described herein. As such, for example, at least some of the functions attributable to the context awareness engine 600 may be carried out by or otherwise instructed by the processing circuitry 610. The processing circuitry 610 may provide the hardware that is programmed or that hosts software to configure the system for enabling contextual awareness of various factors involving AttyDktNo: 717745-01043-P4259PCT01 operation of the power tools 112 to be shared with the analytic engine 170 or otherwise processed directly at the context awareness engine 600 to provide control instructions or other operational recommendations to the power tools 112, the first and second tool controllers 116 and 126, and / or to an operator or manager at the local tool data manager 130 consistent with example embodiments. In this regard, both the generation of the recommendations themselves, and any other communications associated with power tools and tool controllers, may therefore be accomplished using the processing circuitry 610.

[0063] The processing circuitry 610 may be configured to perform data processing, control function execution and / or other processing and management services according to an example embodiment of the present invention. In some embodiments, the processing circuitry 610 may be embodied as a chip or chip set. In other words, the processing circuitry 610 may comprise one or more physical packages (e.g., chips) including materials, components and / or wires on a structural assembly (e.g., a baseboard).

[0064] In an example embodiment, the processing circuitry 610 may include one or more instances of a processor 612 and memory 614 that may be in communication with or otherwise control a device interface 620 and, in some cases, a user interface 630. As such, the processing circuitry 610 may be embodied as a circuit chip (e.g., an integrated circuit chip) configured (e.g., with hardware, software or a combination of hardware and software) to perform operations described herein.

[0065] The user interface 630 (if implemented) may be in communication with the processing circuitry 610 (directly or via the device interface 620) to receive an indication of a user input at the user interface 630 and / or to provide an audible, visual, mechanical or other output to the user. As such, the user interface 630 may include, for example, a display, one or more buttons or keys (e.g., function buttons), and / or other input / output mechanisms (e.g., keyboard, microphone, speakers, cursor, joystick, lights and / or the like). The user interface 630 may display or otherwise provide an output of information enabling an operator to define new applications or update existing applications. The user interface 630 may also be configured to display one or more control consoles for setting up the management of update provisioning to tool controllers (116 / 126) or to view the status of activities or other information associated with recommendations regarding efficiency improvements as described herein.

[0066] In an example embodiment, the user interface 630 may be used to input or otherwise access production scenario information of a contextual nature that may be used by the analytic engine 170 and / or recommendation engine 640 to determine potential improvements to efficiency of operations. For example, the production scenario information may include AttyDktNo: 717745-01043-P4259PCT01 worker shifts, break schedules, production schedule, numbers of cycles for a particular production run, etc. Notably, the same information may be extracted from or provided by other software operably coupled to the context awareness engine 600 instead of being manually entered by the user. In such cases, the user may initially link the context awareness engine 600 to the computers, servers or other sources of schedule or other such information.

[0067] The device interface 620 may include one or more interface mechanisms for enabling communication with the various internal and / or external devices. Thus, for example, the device interface 620 may handle routing of communications within the context awareness engine 600 and / or between the context awareness engine 600 and various other devices (e.g., tool controllers 116 / 126, power tools 112, analytic engine 170, local and remote tool data managers 130 and 160, etc.) within the system. In some cases, the device interface 620 may be any means such as a device or circuitry embodied in either hardware, or a combination of hardware and software that is configured to receive and / or transmit data from / to devices in communication with the processing circuitry 610. In some cases, the device interface 620 may include one or more ports for external component connectivity and / or communication (e.g., Ethernet or wireless communications, and / or the like). Standard ports such as USB, other data ports, or power cable ports may be provided. However, in some cases, the ports may be for proprietary connectivity mechanisms. In some embodiments, the device interface 620 may include antennas, radio equipment and / or the like to enable the context awareness engine 600 to interface with other components or devices wirelessly. Otherwise, wired communication, or combinations of wired and wireless communication, may be employed.

[0068] In an exemplary embodiment, the memory 614 and the processor 612 may have physical form and / or functional capabilities similar to those of the memory and processors discussed above. However, the memory 614 may specifically store the production scenario information discussed above, along with any operational environment information (e.g., humidity levels, ambient temperature, safety conditions and / or the like) that may be provided by environmental sensors 650 located at the manufacturing location 100 proximate the power tools 112 and / or tool controllers 116 / 126. In some cases, the memory 614 may also store applications for determining recommendations based on the operational environment information and / or the production scenario information.

[0069] In an example embodiment, the recommendation engine 640 may therefore be any means such as a device or circuitry embodied in either hardware, or a combination of hardware and software that is configured to perform the corresponding functions of the recommendation engine 640 as described herein under the control of the processing circuitry 610. In an example AttyDktNo: 717745-01043-P4259PCT01 embodiment, the recommendation engine 640 may be configured to process the production scenario information and the operational environment information and perform various actions associated with management and distribution of recommendations or instructions based at least in part on the production scenario information and the operational environment information, in some cases along with other information as well. As an example, if one instance of the power tool 112 is determined to be operating in an unsafe or unproductive environment (e.g., high local temperature and / or having a situation where the battery 114 is nearly exhausted of power), where the operator cannot quickly swap in a new battery (e.g., due to state of charge of batteries on the charger 300), the context awareness engine 600 may be aware of the safety condition (e.g., via temperature reports coming from the environmental sensors), the state of charge of all batteries in the system, and the production schedule to indicate when the next break will occur. The recommendation engine 640 may then issue recommendations including a temporary slowdown in the running of the power tool 112 to conserve battery life until the next scheduled break when the battery 114 can be changed, along with a recommendation to increase air conditioning unit operation to reduce temperature. The recommendation may therefore address a safety issue, and also reduce unnecessary downtime by instead conducting the battery swap at an otherwise scheduled break. Notably, the control of ambient temperature is merely one example, aimed at avoiding tool overheat to extend operating time and increase throughput, of how operational environment information can be learned and modified to increase efficiency. Other environmental control initiatives, tool control instructions, and personnel management adjustments may also or alternatively be made by the recommendation engine 640 and, for example, sent to a manager or operator at the local tool data manager 130 for acceptance before the changes may be made either automatically or manually upon adoption of the recommendation sent.

[0070] In some example embodiments, the recommendation engine 640 may interface with or even be a part of the analytic engine 170. The analytic engine 170 may perform detailed analysis on tool sample data (e.g., torque traces, etc.), the production scenario information and the operational environment information, and may provide information that can be used by the recommendation engine 640 to generate recommendations. However, in other cases, the analytic engine 170 may generate instructions that are automatically sent and implemented at the first and second tool controllers 116 and 126, one or more of the power tools 112, or various other components. Notably, although the analytic engine 170 is shown as being located at the remote tool data manager 160 in FIGS. 1 and 4, the analytic engine 170 may alternatively be located at the MES 140 or even at the local tool data manager 130 in some cases. AttyDktNo: 717745-01043-P4259PCT01

[0071] The analytic engine 170 may employ machine learning and / or artificial intelligence tools to perform its analysis. One example architecture for the analytic engine 170 is shown in block diagram form in FIG. 7. In this regard, the analytic engine 170 may include an Al module 700 and a machine learning module 710. The Al module 700 and the machine learning module 710 may each include also the same or separate instances of processors and memory similar in function (and in some cases also form) to those described above. Moreover, the Al module 700 and the machine learning module 710 may each include various sub-modules such as, for example, a generative Al module 702 and a deep learning module 712, respectively. The Al module 700 and the machine learning module 710 may each be employed to, among perhaps other things, determine operational efficiencies that may achieved with respect to the power tools 112. Within this context, the Al module 700 may be generally understood to include software programming that can mimic cognitive decision-making to sense, reason and adapt, whereas the generative Al module 702 may further generate new data that appears to be produced by humans. The machine learning module 710 may include one or more algorithms that improve performance with respect to processing of data as more exposure to the data is provided over time. Meanwhile, the deep learning module 712 may include a sub-set of machine learning in which multilayered neural networks are used where each layer transforms input data into more abstract representations.

[0072] In an example embodiment, the Al module 700 may include both text-based filters and natural language processing (NLP) to process queries associated with identifying potential improvements to tool operations and / or environmental factors that may ultimately lead to higher efficiency operations. Thus, for example, the Al module 700 may be used along with the machine learning module 710 to identify specific situations, events, or information that may indicate inefficiencies, and further identify potential changes that may improve efficiency. In an example embodiment, the Al module 700 may be specifically configured to determine a tool context inference based on information received, and provide an improvement recommendation for control of the power tools 112 based on the tool context inference. In some cases, the Al module 700 may be configured to generate product documentation data based on the tool sample data. The product documentation data may include records regarding run time, number of cycles, torque trace data, or any other parameters capable of being logged, recorded, tracked or monitored. In an example embodiment, the Al module 700 may also be configured to search a knowledge database (e.g., at the remote data repository 180 or the Internet) to provide an improvement recommendation for control of the power tools based on AttyDktNo: 717745-01043-P4259PCT01 the tool sample data, and referencing the knowledge database using the tool sample data as an input to cross reference the improvement recommendation from a table.

[0073] In some cases, the Al module 700 may further include a data scraper that may scrape data from various identified sources or feeds such as, for example, the tool sample data, production scenario information, operational environment information and / or the like. The data scraper may be embodied as a large language model (LLM) that is used in connection with generating annotations or classifications of data. The LLM (e.g., ChatGPT or other GPT models, etc.) may include an Al accelerator that processes vast amounts of data and applies weights to the data received using trained neural networks that effectively enable removal of low quality data, duplicated data, and other non-useful data, thereby leaving relevant and high quality in much smaller datasets for further processing. The Al module 700 may also pre-treat the data so that the data can be provided in a form that can be processed by the machine learning module 710.

[0074] The machine learning module 710 may employ one or more instances of a neural network (e.g., a convolutional neural network (CNN), Recurrent Neural Network (RNN)), a support vector machine (SVM), Bayesian network, logistic regression, logistic classification, decision tree, ensemble classifier or other machine learning model to process inputs received thereat to generate outputs as described herein. The machine learning module 710 may have different methods for learning such as supervised (identifying patterns in raw labeled data upon which inference processes are desired to be performed via training examples), unsupervised (identifying patterns in raw unlabled data upon which inference processes are desired to be performed without training examples), or reinforcement. In an example embodiment, the machine learning module 710 may include a neural network of nodes where each node includes input values, a set of weights, and an activation function. The neural network node may calculate the activation function on the input values to produce an output value. The activation function may be a non-linear function computed on the weighted sum of the input values plus an optional constant. Neural network nodes may be connected to each other such that the output of one node is the input of another node. Moreover, neural network nodes may be organized into layers, each layer comprising one or more nodes. The neural network may be trained and update its internal parameters via backpropagation during training (e.g., via RNN). A CNN may be a type of neural network that further adds one or more convolutional filters (e.g., kernels) that operate on the outputs of the preceding neural network layer to produce and output to then next layer. The convolutional filters may have a window in which they operate, which is spatially local. A node of a preceding layer may be connected to a node in the current layer AttyDktNo: 717745-01043-P4259PCT01 if the node of the preceding layer is within the window. If not within the window, then the nodes are not connected. The CNN can therefore process massive amounts of information and detect patterns therein in relatively short periods of time as compared to general purpose computers, regardless of their programming and processor speeds.

[0075] In an example embodiment, the machine learning module 710 may be trained on a training set of tool parameters correlated to physical results. The machine learning module 710 may identify patterns in the tool sample data that correlate to physical results in terms of torque values, angle values or other parameters of interest and generate an improvement recommendation for control of the power tools 112 based on the identified patterns. The patterns may be associated with, for example, common joint failures and causes. In this regard, some temperature increases that are detected may be associated with increased friction. The tool sample data may fit into patterns noticed at other facilities with other tools associated with a lack of lubrication, rust, shadowing, paint being on threads, damaged threads, variations in finish, or other causes that may be detectable through association with patterns in other measurable parameters. Moreover, in some cases, each joint may have a unique signature created by its torque curve, but may have some variations each cycle. However, similarities may be sufficient to reliably identify a particular joint. Sensor data may also be monitored for reaction torque, and particular tool configurations, user error, or a need for reaction arms may be identified before an incident occurs with the tool. In some situations, analysis of low torque transducer data may be recognized as well.

[0076] In an example embodiment, the analytic engine 170 may interface with the recommendation engine 640 to provide the improvement recommendations for approval at the local tool data manager, and the improvement recommendation may define an operational adjustment with respect to operation of one or more of the power tools 112. In an example embodiment, the improvement recommendation may include an adjustment to an operating environment of the one or more of the power tools 112 such as, for example, an adjustment to temperature, humidity or a safety condition in a manufacturing environment of the one or more of the power tools. Alternatively or additionally, the improvement recommendation may include an adjustment to a production schedule of the one or more of the power tools 112, which may include adjusting tool speed to conserve battery power until a next scheduled break, and directing battery changing or change out during the next scheduled break, directing a tool swap at a next scheduled break or shift change responsive to tool temperature reaching a predefined threshold, an adjustment to a number of cycles of the one or more of the power tools AttyDktNo: 717745-01043-P4259PCT01 for a given production run, a dynamic adjustment to an operational parameter of the one or more of the power tools 112 at a predetermined time or for a predetermined period of time.

[0077] Of note, the training data used for the machine learning module 710 may be generated by a limited set of subject matter experts (SMEs) that may import their knowledge into the system via the training data. The SMEs may know how to change tool settings to improve performance and efficiency under certain conditions or circumstances. The training data may therefore teach the machine learning module 710 to review actual data at any particular location and apply the expertise of the SMEs, via the training data set, to the actual data to apply expert level modification to the power tools 112 at a remote location from the SMEs at any time, day or night, 365 days a year. In effect, the machine learning module 710 transforms the remote tool data manager 160 into a virtual field technician that can analyze data at any location across the country without having a physical human presence at the location.

[0078] In some cases, the machine learning module 710 may further be capable to determining patterns in tool sample data that indicate how to more efficiently collect data such as by avoiding redundant data, avoiding dead time in collected files, or avoiding time that has less useful information. Over time, after detecting such patterns, and detecting cues that can be used to identify the most useful pieces of files, the machine learning module 710 may be able to identify the most efficient times to start and stop data collection and therefore help reduce file size for files made and needing transfer. The cues may include, for example, learning that data collection can be condensed to being collected every nth operation for a given dataset of two or more attributes that are being collected. Thus, more generally, the analytic engine 170 may place tools in a learning mode or a normal (operational) mode. In the normal mode, of course, normal operation of the power tool 112 may be managed by its tool controller. However, in the learning mode, the machine learning module 710 may identify patterns to more efficiently collect data and communicate the data for analysis. For example, the power tool 112 may have a secondary data collection mode that collects different data and may also collect such data at different rates than the data and rates that apply to data collection in the normal mode. Moreover, instead of large data files, smaller files may be collected and sent in manageable batches that are more efficient to communicate and process. In this regard, in some cases torque traces may be broken into smaller chunks for storage or processing. Moreover, if only certain parts (or chunks) are actually useful data, and the others are superfluous, the superfluous data may be discarded to reduce the amount of data communicated or stored. This may effectively lead to automated or intelligent data trimming to exclude AttyDktNo: 717745-01043-P4259PCT01 irrelevant data (e.g., not recording time when the tool is free spinning) for data compression and trace compilation.

[0079] In an example embodiment, in order to define a dataset of line operation data, the analytic engine 170 may store a flagged secondary dataset in the remote data repository 180. The secondary dataset may be accumulated with a number of selected ones of the power tools 112, and may be communicated from the tools 112 or their respective tool controller (116 / 126) to the analytic engine 170 either directly or via the local tool manager 130. In some cases, an assigned flag may be provided for a secondary learning mode of operation for all connected tools. The data that may be tagged as the secondary dataset may be tagged by operation retaining tool and line specific information, but not sensitive data to assembled parts. There may be two or more methods of distribution of data based on the purpose of the data. For example, a first path to the local tool data manager 130 or the remote tool data manager 160 may be used to store data in real time, and a second path may be provided to the remote tool data manager 160 that may store data asynchronously or offline for analysis. Temperature, torque profile, and other information may be used to refine performance within an allowable set of changes selected by the managers of the manufacturing location 100 or by an operator of the system shown in FIGS. 1 and 4.

[0080] In some cases, the analytic engine 170 may have a user interface separate from the remote tool manager 160. However, such interface may be shared in other cases. In any case, the user interface of the analytic engine 170 may be used to display trace data, highlight any abnormality of the trace, and / or generate new visual or textual content to help a user better understand a recommendation or answer to a user query. The abnormality may be clicked on by the user or otherwise selected for further information as determined by the analytic engine 170. The Al module 700 may also be queried with natural language prompts to define specific analysis that is desired, specific alerts that are desired, or any of a number of other useful interactions including those that may be associated with adjusting tool operations or providing recommendations regarding the same.

[0081] In some embodiments, the analytic engine 170 may further be configured to assist with capturing data that can be used for calibration of the tools. The calibration may leverage current data sensed locally, and the wealth of tool data from across many locations inside and outside of an enterprise. Thus, an external server (e.g., the remote tool data manager 160) may be used to dynamically update parameters for a joint (simulated or real) for use in calibration. Results may be fed to the MES or other MESs with secure or encrypted communications. Moreover, calibration information may be shared bi-directionally between tools and the analytic engine AttyDktNo: 717745-01043-P4259PCT01

[0082] 170. Troubleshooting tools may also be provided by the analytic engine for connectivity, tool performance, and many other potential issues.

[0083] Accordingly, example embodiments may include a system for monitoring tool performance and providing remote analysis and efficiency guidance. The system may include a tool controller, a plurality of power tools operably coupled to the tool controller to execute a respective working operation (e.g., tightening, material removal, etc.), a local tool data manager operably coupled to the tool controller and / or the power tools to manage extraction of tool sample data, and a remote tool data manager operably coupled to the local tool data manager to receive the tool sample data from the local tool data manager and process the tool sample data to generate an improvement recommendation for communication to the local tool data manager that, responsive to acceptance by the local tool data manager, initiates a change to an instruction for operation of one or more of the power tools with respect to the respective working operation. The remote tool data manager may employ an analytic engine including a machine learning module and / or an artificial intelligence module to generate the improvement recommendation.

[0084] In some embodiments, the system (and a corresponding method for operating or achieving the desired results of the system, along with any component configured to perform the operations of the method) may include (or be configured to perform) additional components / modules, optional operations, and / or the components / operations described above may be modified or augmented. Some examples of modifications, optional operations and augmentations are described below. It should be appreciated that the modifications, optional operations and augmentations may each be added alone, or they may be added cumulatively in any desirable combination. In this regard, for example, each of the power tools may be battery operated, and each respective one of the power tools includes a battery that includes a battery memory that stores the tool sample data locally at the battery. In an example embodiment, the battery memory may be operably coupled to a tool communication bus of a corresponding one the power tools to receive the tool sample data via the tool communication bus responsive to connection of the battery to the respective one of the power tools. In some cases, the battery memory may be operably coupled to a charger communication bus responsive to connection of the battery to a charger. In an example embodiment, the tool sample data may be extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, and the communications unit may be wirelessly communicates the tool sample data to the remote tool data manager. In some cases, the communications unit may communicate with the remote tool data manager via a cellular communication network. AttyDktNo: 717745-01043-P4259PCT01

[0085] In an example embodiment, the tool sample data may be extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, and the communications unit may communicate the tool sample data to the remote tool data manager via a wired connection. In some cases, the tool sample data may be extracted from the battery memory and stored at a charger memory of the charger, and the tool sample data may be transferred from the charger memory to a removable memory device, and the removable memory device is operably coupled to the remote tool data manager to transfer the tool sample data to the remote tool data manager. In an example embodiment, the tool sample data may be stored in the battery memory responsive to instructions from a processor of the battery, a processor of the corresponding one the power tools, or a processor of the charger. In some cases, the system may further include one or more additional tool controllers and respective additional power tools operably coupled thereto,. The tool controller, the one or more additional tool controllers, the power tools and the respective additional power tools may all be communicatively coupled to each other to define a tool control network. The local tool data manager may include a passive sniffing device operably coupled to the tool control network to extract real time torque profile data as the tool sample data from one or more of the power tools and the respective additional power tools. In an example embodiment, the passive sniffing device may be operably coupled to the remote tool data manager wirelessly to communicate the torque profile data to the remote tool data manager. In some cases, the passive sniffing device communicates with the remote tool data manager via a cellular communication network. In an example embodiment, the passive sniffing device communicates the tool sample data to the remote tool data manager via a wired connection. In some cases, the passive sniffing device includes a local memory for storing the tool sample data, and the tool sample data is transferred to the remote tool data manager via a removable memory that receives the tool sample data when operably coupled to the passive sniffing device. In an example embodiment, the passive sniffing device extracts the torque profile data from unencrypted data communicated on the tool control network. In some cases, the passive sniffing device extracts encrypted data communicated on the tool control network and provides the encrypted data to the analytic engine. In an example embodiment, the analytic engine extracts the torque profile data from the encrypted data. In some cases, In an example embodiment, the analytic engine may include a machine learning that is trained on a training set of tool parameters correlated to physical results, and the analytic engine may identify patterns in the tool sample data via the machine learning module and generate the improvement recommendation for control of the power tools based on the identified patterns. In an example AttyDktNo: 717745-01043-P4259PCT01 embodiment, the analytic engine may include an artificial intelligence module configured to determine a tool context inference and provide the improvement recommendation for control of the power tools based on the tool context inference. In some cases, the analytic engine may include an artificial intelligence module configured to generate product documentation data based on the tool sample data. In an example embodiment, the analytic engine may include an artificial intelligence module configured to search a knowledge database to provide the improvement recommendation for control of the power tools based on the tool sample data. In some cases, the analytic engine provides the improvement recommendation for approval at the local tool data manager, and the improvement recommendation defines an operational adjustment with respect to operation of one or more of the power tools. In an example embodiment, the improvement recommendation may include an adjustment to an operating environment of the one or more of the power tools. In some cases, the adjustment to the operating environment may include an adjustment to temperature, humidity or a safety condition in a manufacturing environment of the one or more of the power tools. In an example embodiment, the improvement recommendation may include an adjustment to a production schedule of the one or more of the power tools. In some cases, the adjustment to the production schedule may include adjusting tool speed to conserve battery power until a next scheduled break, and directing battery changing or change out during the next scheduled break. In an example embodiment, the adjustment to the production schedule may include directing a tool swap at a next scheduled break or shift change responsive to tool temperature reaching a predefined threshold. In some cases, the improvement recommendation may include an adjustment to a number of cycles of the one or more of the power tools for a given production run. In an example embodiment, the improvement recommendation may include a dynamic adjustment to an operational parameter of the one or more of the power tools at a predetermined time or for a predetermined period of time. In some cases, the operational adjustment may be pushed to the one or more of the power tools responsive to approval of the improvement recommendation at the local tool data manager.

[0086] Many modifications and other embodiments of the inventions set forth herein will come to mind to one skilled in the art to which these inventions pertain having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Therefore, it is to be understood that the inventions are not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Moreover, although the foregoing descriptions and the associated drawings describe exemplary embodiments in the context of certain exemplary combinations AttyDktNo: 717745-01043-P4259PCT01 of elements and / or functions, it should be appreciated that different combinations of elements and / or functions may be provided by alternative embodiments without departing from the scope of the appended claims. In this regard, for example, different combinations of elements and / or functions than those explicitly described above are also contemplated as may be set forth in some of the appended claims. In cases where advantages, benefits or solutions to problems are described herein, it should be appreciated that such advantages, benefits and / or solutions may be applicable to some example embodiments, but not necessarily all example embodiments. Thus, any advantages, benefits or solutions described herein should not be thought of as being critical, required or essential to all embodiments or to that which is claimed herein. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims

AttyDktNo: 717745-01043-P4259PCT01WHAT IS CLAIMED:

1. A system for monitoring tool performance and providing remote analysis and efficiency guidance, the system comprising: a tool controller; a plurality of power tools operably coupled to the tool controller to execute a respective working operation; a local tool data manager operably coupled to the tool controller and / or the power tools to manage extraction of tool sample data; and a remote tool data manager operably coupled to the local tool data manager to receive the tool sample data from the local tool data manager and process the tool sample data to generate an improvement recommendation for communication to the local tool data manager that, responsive to acceptance by the local tool data manager, initiates a change to an instruction for operation of one or more of the power tools with respect to the respective working operation, wherein the remote tool data manager employs an analytic engine to generate the improvement recommendation.

2. The system of claim 1, wherein each of the power tools is battery operated, and each respective one of the power tools includes a battery, wherein the battery includes a battery memory that stores the tool sample data locally at the battery.

3. The system of claim 2, wherein the battery memory is operably coupled to a tool communication bus of a corresponding one the power tools to receive the tool sample data via the tool communication bus responsive to connection of the battery to the respective one of the power tools.

4. The system of claim 3, wherein the battery memory is operably coupled to a charger communication bus responsive to connection of the battery to a charger.

5. The system of claim 4, wherein the tool sample data is extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, andAttyDktNo: 717745-01043-P4259PCT01 wherein the communications unit wirelessly communicates the tool sample data to the remote tool data manager.

6. The system of claim 5, wherein the communications unit communicates with the remote tool data manager via a cellular communication network.

7. The system of claim 4, wherein the tool sample data is extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, and wherein the communications unit communicates the tool sample data to the remote tool data manager via a wired connection.

8. The system of claim 4, wherein the tool sample data is extracted from the battery memory and stored at a charger memory of the charger, and wherein the tool sample data is transferred from the charger memory to a removable memory device, and the removable memory device is operably coupled to the remote tool data manager to transfer the tool sample data to the remote tool data manager.

9. The system of claim 3, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the battery.

10. The system of claim 3, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the corresponding one the power tools.

11. The system of claim 3, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the charger.

12. The system of claim 1, further comprising one or more additional tool controllers and respective additional power tools operably coupled thereto, wherein the tool controller, the one or more additional tool controllers, the power tools and the respective additional power tools are all communicatively coupled to each other to define a tool control network, andAttyDktNo: 717745-01043-P4259PCT01 wherein the local tool data manager includes a passive sniffing device operably coupled to the tool control network to extract tool sample data from one or more of the power tools and the respective additional power tools.

13. The system of claim 12, wherein the passive sniffing device is operably coupled to the remote tool data manager wirelessly to communicate the tool sample data to the remote tool data manager.

14. The system of claim 13, wherein the passive sniffing device communicates with the remote tool data manager via a cellular communication network.

15. The system of claim 12, wherein the passive sniffing device communicates the tool sample data to the remote tool data manager via a wired connection.

16. The system of claim 12, wherein the passive sniffing device includes a local memory for storing the tool sample data, and wherein the tool sample data is transferred to the remote tool data manager via a removable memory that receives the tool sample data when operably coupled to the passive sniffing device.

17. The system of claim 12, wherein the passive sniffing device extracts unencrypted data communicated on the tool control network.

18. The system of claim 12, wherein the passive sniffing device extracts encrypted data communicated on the tool control network19. The system of claim 12, wherein the analytic engine extracts torque profile data from the tool sample data.

20. The system of claim 12, wherein a database is operably coupled to the analytic engine to store the tool sample data.AttyDktNo: 717745-01043-P4259PCT0121. The system of claim 1, wherein the tool sample data is collected in a normal mode or a secondary data collection mode that collects different data or collects data at different rates than data and rates applied to data collection in the normal mode.

22. The system of claim 1, wherein the tool sample data is collected, stored or communicated in batches.

23. The system of claim 1, wherein the tool sample data includes a first dataset associated with a first selected group of the power tools, and a second dataset associated with a second selected group of power tools, wherein the second dataset is flagged by the analytic engine for use in offline learning by the analytic engine.

24. The system of claim 1, wherein the analytic engine comprises a machine learning module, wherein the machine learning module is trained on a training set of tool parameters correlated to physical results, and wherein the analytic engine identifies patterns in the tool sample data via the machine learning module and generates the improvement recommendation for control of the power tools based on the identified patterns.

25. The system of claim 1, wherein the analytic engine includes an artificial intelligence module configured to determine a tool context inference and provide the improvement recommendation for control of the power tools based on the tool context inference.

26. The system of claim 1, wherein the analytic engine includes an artificial intelligence module configured to generate product documentation data based on the tool sample data.

27. The system of claim 1, wherein the analytic engine includes an artificial intelligence module configured to search a knowledge database to provide the improvement recommendation for control of the power tools based on the tool sample data.AttyDktNo: 717745-01043-P4259PCT0128. The system of claim 1, wherein the analytic engine provides the improvement recommendation for approval at the local tool data manager, the improvement recommendation defining an operational adjustment with respect to operation of one or more of the power tools.

29. The system of claim 28, wherein the improvement recommendation comprises an adjustment to an operating environment of the one or more of the power tools.

30. The system of claim 29, wherein the adjustment to the operating environment comprises an adjustment to temperature, humidity or a safety condition in a manufacturing environment of the one or more of the power tools.

31. The system of claim 28, wherein the improvement recommendation comprises an adjustment to a production schedule of the one or more of the power tools.

32. The system of claim 31, wherein the adjustment to the production schedule comprises adjusting tool speed to conserve battery power until a next scheduled break, and directing battery changing or change out during the next scheduled break.

33. The system of claim 31, wherein the adjustment to the production schedule comprises directing a tool swap at a next scheduled break or shift change responsive to tool temperature reaching a predefined threshold.

34. The system of claim 28, wherein the improvement recommendation comprises an adjustment to a number of cycles of the one or more of the power tools for a given production run.

35. The system of claim 28, wherein the improvement recommendation comprises a dynamic adjustment to an operational parameter of the one or more of the power tools at a predetermined time or for a predetermined period of time.

36. The system of claim 28, wherein the operational adjustment is pushed to the one or more of the power tools responsive to approval of the improvement recommendation at the local tool data manager.AttyDktNo: 717745-01043-P4259PCT0137. The system of claim 1, wherein the analytic engine provides the improvement recommendation for approval at the local tool data manager, and wherein the approval is provided by a human operator at the local tool data manager.

38. The system of claim 1, wherein the analytic engine provides the improvement recommendation for approval at the local tool data manager, and wherein the approval is provided automatically based on policy provided at the local tool data manager at system configuration.

39. A system comprising: a plurality of power tools; one or more tool controllers operably coupled to respective ones of the power tools to define a tool control network; and a passive sniffing device operably coupled to the tool control network to extract tool sample data from the power tools.

40. The system of claim 39, wherein the passive sniffing device is operably coupled to a local storage device for storing the extracted tool sample data.

41. The system of claim 39, wherein the passive sniffing device is operably coupled to a remote storage device for storing the extracted tool sample data.

42. A system for monitoring tool performance and providing analysis and efficiency guidance, the system comprising: a tool controller; a plurality of power tools operably coupled to the tool controller to perform an operation; and a local tool data manager operably coupled to the tool controller and / or the power tools to manage extraction of tool sample data, and process the tool sample data to generate an improvement recommendation, wherein the local tool data manager employs an analytic engine to generate the improvement recommendation.AttyDktNo: 717745-01043-P4259PCT0143. The system of claim 42, wherein the local tool data manager includes a database for storing the tool sample data.

44. The system of claim 42, wherein each of the power tools is battery operated, and each respective one of the power tools includes a battery, wherein the battery includes a battery memory that stores the tool sample data locally at the battery.

45. The system of claim 44, wherein the battery memory is operably coupled to a tool communication bus of a corresponding one the power tools to receive the tool sample data via the tool communication bus responsive to connection of the battery to the respective one of the power tools.

46. The system of claim 45, wherein the battery memory is operably coupled to a charger communication bus responsive to connection of the battery to a charger.

47. The system of claim 46, wherein the tool sample data is extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, and wherein the communications unit wirelessly communicates the tool sample data to the remote tool data manager.

48. The system of claim 47, wherein the communications unit communicates with the remote tool data manager via a cellular communication network.

49. The system of claim 46, wherein the tool sample data is extracted from the battery memory and communicated to a communications unit of the charger via the charger communication bus, and wherein the communications unit communicates the tool sample data to the remote tool data manager via a wired connection.

50. The system of claim 46, wherein the tool sample data is extracted from the battery memory and stored at a charger memory of the charger, andAttyDktNo: 717745-01043-P4259PCT01 wherein the tool sample data is transferred from the charger memory to a removable memory device, and the removable memory device is operably coupled to the remote tool data manager to transfer the tool sample data to the remote tool data manager.

51. The system of claim 45, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the battery.

52. The system of claim 45, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the corresponding one the power tools.

53. The system of claim 45, wherein the tool sample data is stored in the battery memory responsive to instructions from a processor of the charger.

Images