EP1651551A1

EP1651551A1 - Method for operating a detector for identifying the overlapping of flat mail in a sorting machine

Info

Publication number: EP1651551A1
Application number: EP04763515A
Authority: EP
Inventors: André ROMPE
Original assignee: Siemens AG
Current assignee: Siemens AG
Priority date: 2003-08-04
Filing date: 2004-07-27
Publication date: 2006-05-03
Anticipated expiration: 2024-07-27
Also published as: US20070100640A1; DE10335645B3; JP2007501176A; WO2005016803A1; CA2534545A1; EP1651551B1; CN1829648A; DE502004006784D1

Abstract

The invention relates to a method whereby the average costs CNDD for each unidentified overlap in a distribution and sorting process and the average costs CRF for the renewed sorting and distribution of each identified overlapped item of mail are determined. Before the sorting operation, the identification rate DR(Pi) of the detector is determined at different working points according to an adjusting parameter Pi. During the sorting operation, the respective actual overlap rate DFR'(Pi) of the sorting machine is estimated, for defined time intervals, from the identification result, the identification rate DR(Pi) and the error rate ER(Pi), according to the adjusting parameters Pi. The actual adjusting parameter Popt with the greatest utility CB'(Popt), which is used to operate the detector until the next interval, is determined by optimisation calculations from the relation for the utility CB'(Pi) of the sorting and distribution process CB'(Pi) = N{( DFR'(Pi)*DR(Pi)*(CNDD-CRF)) - (ER(Pi)*CRF*(1-DFR'(Pi)))} for the operator.

Description

description

Method for operating a detector for detecting overlaps of flat mail items in a sorting machine

The invention relates to a method for operating a detector for detecting overlaps of flat mail items in a transport section of a sorting machine following a separating device.

In conventional mail processing systems, mail batches are separated in sorting machines. It can happen that several consignments are withdrawn from the stack at the same time, i.e. several overlapping consignments leave the feeder and, if this is not recognized, lead to incorrect sorting. For this reason, it is necessary to recognize the overlaps in good time after they have left the separating device in order to route them to a rejection end point / reject compartment (cf. US 6 023 034 A).

Corresponding detectors have been known so far which determine overlaps based on different measurement principles, caused by multiple deductions of the separating device. The detected multiple deductions are sent to the rejection end points of the sorting machines in order to avoid incorrect distribution of the mail items. DE 43 37 004 AI describes a device and a method for detecting overlaps of flexible flat mail items, in which at least a section of each mail item can be moved perpendicular to the conveying direction in the transport path. At least one deflection element is arranged on the transport route, by means of which the movable mail sections are temporarily deflected perpendicular to the conveying direction by a predetermined amount during the conveyance in the transport route. In one detection direction, the presence of overlapping mailpiece sections is detected on the basis of the quick-response behavior of the mailpieces. Corresponding detectors have also become known, in which the narrow sides of the individual mail items are recorded by means of image-recording devices and then evaluated in an image processing device by evaluating the image signals to determine whether several mail items are transported overlapping, for example by counting the light-dark transitions (FR 2 546 083 A, 2 057 309 A).

All of these detectors have a fixed operating point with a certain error and detection rate, at which they are operated regardless of the process in which they are involved.

The invention has for its object to provide a method for the automatic operation of a detector for detecting overlaps of flat mail items in a transport section of a sorting machine following a separating device, in which the detector is operated as a function of sorting and distribution process conditions.

According to the invention the object is achieved by the features of claim 1.

The average costs C _NDD for each undetected overlap in the distribution and sorting process and the average costs C _RF for the repeated sorting and distribution of each identified overlapped shipment are determined offline. Before the sorting operation, the detection rate DR (Pi) and the error rate ER (Pι) of the detector are determined at different operating points depending on a corresponding control parameter Pi. During the sorting operation, the current overlap rate DFR '(Pi) of the sorting machine is determined from the detection result, the detection rate DR (Pι) and the error rate ER (Pi.) For specified time intervals or intervals in which a specified number of mail items are processed in the sorting machine ) depending on the setting parameters Pi. From the relationship for the benefit CB '(Pi) of the operator of the sorting and distribution process

CB '(Pi) = N {(DFR' (Pi) * DR (Pi) * (C _NDD -C _RF )) - (ER (Pi) * C _RF * (l-DFR '(Pi)))}

the current control parameter P _op t is then used in optimization calculations. With the highest benefit CB '(P _op t.) determined with which the detector is operated until the next interval. This means that the detector can be operated automatically at optimal costs, even with different process conditions and costs.

It is advantageous to derive the current overlap rate DFR '(Pi) for the different control parameters Pi from the relationship

N DFR '(Pi) = DR' (Pi) - ER '(Pi)

to be determined, where N _{M is} the number of overlaps determined by the detector in the number N of the detected mail items in an interval.

The invention is then explained in more detail in an exemplary embodiment with reference to the drawing.

1 shows a diagram of the detection rate and the error rate of a detector as a function of the control parameter Pi, FIG. 2 shows a block diagram of the operating process.

The overlaps detected by an overlap detector, ie a plurality of mail items leaving the separating device of the sorting machine overlap, are converted into a so-called Reject compartment directed and then fed again to the separation device. The mailings thus ejected consist of real overlaps and individual mails incorrectly recognized as such. If the overlapped mail items were not recognized and rejected, the mail items related to the mail item with the read address would at least be sent to the wrong next distribution center and would then have to be forwarded from there to the correct address.

Of course, this causes additional costs, which minus the costs for the renewed supply of the overlaps can be avoided by early detection of the overlaps. Since a detection process can also incorrectly recognize normal individual consignments as overlaps as a result of incorrect detections, the costs for the additional sorting of these consignments in the relevant sorting machine must be subtracted from the additional costs saved.

The benefit CB for the operator of the sorting and distribution process thus results from the relationship CB = N {(DFR * DR * (C _NDD - C _RF )) - (ER * C _RF * (1-DFR))}

N * DFR * DR is the number of overlaps detected in the period under consideration and N * ER * (1-DFR) is the number of incorrectly detected individual broadcasts

N = number of processed mail items DFR = overlap rate of the sorting machine DR = detection rate of the detector ER = error rate of the detector

C _NDD = costs for each _undetected overlap C _RF = costs for each repeated feed to the respective sorting machine of detected overlaps These costs depend on the respective type of shipment processing, ie it is, for example, an incoming sorting or an outgoing sorting.

Detectors for determining overlaps have previously worked at a fixed operating point with a certain detection rate DR and a certain error rate ER, which e.g. according to DE-Akz. 103 10 546.8-27 can be determined.

However, in order to influence the benefits for operation, it is necessary to parameterize the detection and error rate, i.e. they can be changed depending on a control parameter Pi. This dependency is shown as an example in Tab. 1 and FIG. 1.

Tab. 1

It can be seen that the error rate increases as the detection rate increases.

The benefit for the operator thus results from the parameterized relationship

CB '(Pi) = N {(DFR' (Pi) * DR (Pi) * (C _NDD - C _RF )) - (ER (Pi) * C _RF * (1-DFR '(Pi)))}

The estimated value for the current overlap rate of the respective sorting machine results in NAD - ER '(Pi) N DFR' (Pi) = DR '(Pi) - ER' (Pi) The entire recognition and optimization process is shown in FIG. 2.

The block diagram in FIG. 2 clearly describes the course of the method. The overlap detector detects the overlaps during the sorting and distribution process 1, which are then directed into a reject compartment and are therefore excluded from the regular process. This reduces the number of _{incorrect sorts} and therefore the costs C _NDD for each _undetected overlap. The mail items from the reject compartments are fed back to the sorting machine and thus cause additional costs C _RF per mail item. These costs C _UDD , C _RF serve as input data for the benefit optimization 2 for the process operator. They are derived offline from the process model. It is obvious that these costs are dependent on the type of the respective processes, i.e. the incorrect sorting costs in a so-called entry sorting and distribution process according to the street and house number are different from the incorrect sorting costs in a so-called exit sorting and distribution process according to the postal code and location. Table 2 gives an example of the corresponding costs for a specific machine type (FVM).

Tab. 2

The sorting process 3 with the overlap detection contains the essential components of separation 3.1, subsequently the overlap detection 3.2 and then the sorting 3.3 according to the read destination addresses. The detected overlaps are fed again to the separation 3.1 via the reject compartments. The broadcasts detected as individual broadcasts fertilize (including the undetected overlaps) are distributed in the sorting compartments provided for in the sorting plan. The current estimated overlap rate DFR 'is determined in the utility optimization 2 from the number of overlaps detected in the period under consideration and the parameterized power values ER' (Pi) and DR '(Pi) 2.2. 2.4. From the benefit equation / benefit model 2.3

CB '(Pi) = N {(DFR' (Pi) * DR (Pi) * (C _NDD -C _RF )) - (ER (Pi) * C _RF * (1-DFR '))} then becomes one Optimization process 2.1 the parameter P _opt with the maximum benefit CB 'determined.

For the detector with the performance _parameters shown in Tab. 1 and FIG. 1, error costs C _NDD = 0.058, C _RF = 0.0035 and N = 1,000,000 processed _mail items, the benefit shown in Table 3 depends on the overlap rate DFR 'and the parameter Pi. The maximum benefit for each overlap rate is indicated by underlining and bold letters. The associated control parameter Pi is then the selected and automatically set parameter P _opt .

Tab,

Claims

claims

1. A method of operating a detector for detecting overlaps of flat mail items in a transport section of a sorting machine following a separating device, characterized in that a) that before the sorting _{operation a1} ) the average costs C _NDD for each undetected overlap in the distribution and sorting process and the average Costs C _RF for the repeated sorting and distribution of each identified overlapped mail item are determined, a2) and as the detection rate DR (Pi) of the detector the proportion of correctly identified overlaps and as the error rate ER (Pi) of the detector the proportion incorrectly as overlap of detected individual mail items are determined by a control parameter Pi, b) and that during the sorting operation automatically after an interval, which is defined by a defined period of time or by a defined number of mail items processed in the sorting machine, bl) for the straight ended interval from the number N _{AD of} the overlaps determined by the detector in this interval and the number N of the programs detected by the detector in this interval, a recognition result N _AD / N is determined, b2) from the recognition result _AD / N together with those of the value of the control parameter Pi in this interval-dependent variables DR (Pi) and ER (Pi) an estimate DFR '(Pi) of the overlap rate that actually occurred in this interval, b3) from the benefit CB '(Pi) of the operator of the sorting and distribution process,

CB '(Pi) = N {(DFR' (Pi) * DR (Pi) * (C _NDD -C _RF )) - (ER (Pi) * C _RF * (1-DFR '(Pi)))}, In optimization calculations, the actuating parameter P _{opt is} determined which would have given the greatest benefit CB '(P _opt ) for this interval, b4) and the value P _opt for the next interval as the value for the actuating parameter Pi and the detector in the next Interval is operated with this control parameter.

2. The method according to claim 1, d a d u r c h g e k e n n z e i c h n e t that the estimate DFR '(Pi) of the actually occurring overlap rate in the just ended interval is made according to the relationship

N A; D - ER '(Pi) N DFR' (Pi) = DR '(Pi) - ER' (Pi)